The DOI matches its Crossref record; 142 of the 149 references it cites were found in a registry or an index; none of the 84 sources its claims cite is checked for support yet.
Deep learning for time series classification: a review
Open accessOverview
AI snapshot
Written from the paper’s full text.
TL;DR
This review empirically compares nine end-to-end deep learning architectures for time series classification across 97 univariate and multivariate datasets, training 8,730 models. It finds that a deep residual network (ResNet) is the strongest DNN, significantly outperforming most other deep models and reaching performance not significantly different from COTE/HIVE-COTE on the UCR/UEA archive.
Key findings
- ResNet significantly outperformed the other deep learning approaches on the 85 univariate UCR/UEA datasets, with an average rank of almost 2, winning on 50 out of 85 problems; FCN and Encoder followed as second and third.
- ResNet was not significantly different from COTE/HIVE-COTE in pairwise statistical tests, while NN-DTW-WW and EE showed the lowest average ranks among compared state-of-the-art methods.
- MCNN and t-LeNet, which use window slicing/subsequence extraction, yielded very low accuracies with only one win (Earthquakes); MCDCNN and Time-CNN performed similarly to MLP.
- ResNet was more stable across random initializations than FCN, with average standard deviation 1.48 versus 1.70; on DiatomSizeReduction, ResNet and FCN reached only 30% accuracy while Time-CNN reached 95%.
Methods
- The authors reimplemented nine discriminative end-to-end deep learning models (MLP, FCN, ResNet, Encoder, MCNN, t-LeNet, MCDCNN, Time-CNN, TWIESN) in a common Keras/TensorFlow framework and trained each with 10 random initializations on 97 datasets: 85 univariate UCR/UEA datasets and 12 multivariate datasets.
- In total, 8,730 experiments were run on a cluster of 60 GPUs; accuracy was averaged over the 10 runs, and comparisons with published state-of-the-art results used median test error.
- Statistical comparison used the Friedman test followed by pairwise Wilcoxon signed-rank tests with Holm’s alpha correction (5%), visualized with critical difference diagrams.
Limitations
- The paper states that generative models and models using hand-engineered features were excluded, and that transfer learning, data augmentation, training/testing time, and normalization effects were not thoroughly studied.
- The paper acknowledges that non-deep state-of-the-art algorithms were not trained or tuned by the authors, so the comparison may favor DNNs; it also notes that the compared architectures may have been overfitted or empirically designed for the UCR/UEA archive.
- Evident from the text: the multivariate archive contains only 12 datasets, and the statistical test failed to find significant differences among the nine classifiers on that archive; ResNet’s hyperparameters were not tuned per dataset, and random initialization can significantly affect DNN accuracy.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
64 Not checked yet · 47 Own interpretation · 44 Own result · 22 No basis given · 6 Own method
None of the sources cited for this claim have been checked yet.
In the paper
“our experiments showed that not only DNNs are able to significantly outperform the NN-DTW, but are also able to achieve results that are not significantly different than COTE and HIVE-COTE using a deep residual network architecture (He et al., 2016; Wang et al., 2017b).”
What the sources say
- Not checked yetcites He et al., 2016
- Not checked yetcites Wang et al., 2017b
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Rests on an assumption: The UCR/UEA archive datasets are representative of TSC problems.
- Rests on an assumption: The deep learning implementations in the framework faithfully represent the original methods.
None of the sources cited for this claim have been checked yet.
In the paper
“our experiments showed that not only DNNs are able to significantly outperform the NN-DTW, but are also able to achieve results that are not significantly different than COTE and HIVE-COTE using a deep residual network architecture (He et al., 2016; Wang et al., 2017b).”
What the sources say
- Not checked yetcites He et al., 2016
- Not checked yetcites Wang et al., 2017b
boosteddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Rests on an assumption: The UCR/UEA archive datasets are representative of TSC problems.
- Rests on an assumption: The deep learning implementations in the framework faithfully represent the original methods.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“In addition, one of the advantages of FCNs is the invariance (denoted by # invar in Table 1) in the number of parameters for 4 layers (out of 5) across time series of different lengths.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“We should note that twenty datasets contains a relatively small training set (50 or fewer instances) which surprisingly was not an impediment for obtaining high accuracy when applying a very deep architecture such as ResNet.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“During our study, we found that CNN is the most widely applied architecture for the TSC problem”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“In our experiments, when comparing to state-of-the-art algorithms, we have encountered this problem with (ResNet > COTE > HIVE- COTE).”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“where the statistical test failed to find any significant difference between the nine classifiers”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“and significantly outperforms the FCN architecture.”
boosteddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“One exception is the electrocardiography (ECG) datasets (7 in total) where ResNet was drastically beaten by the FCN model in 71.4% of ECG datasets.”
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“we can clearly see the dominance of ResNet as the best performing approach across different domains.”
boosted- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Probably not a substantial claim. 47
- It may state two separate claims as one. 52
- The quote only partly states this claim. 2
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Finally, we analyze how poor random initializations can have a significant effect on a DNN's performance.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“We can see that FCN does not hold any pooling nor a regularization operation.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Similarly to the FCN model, the layers (except the final one) in the ResNet architecture have an invariant number of parameters across different datasets.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The ResNet significantly outperforms the other approaches with an average rank of almost 2.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“This suggestion is also supported by the fact that Time-CNN is the smallest model: it contains a very small number of parameters by design with only 18 filters compared to the 512 filters of FCN.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Again, ResNet and FCN still dominate with not much of a difference.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one. The quote only partly states this claim.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“our empirical study strongly suggests to use ResNet instead of any other deep learning algorithm - it is the most accurate one with similar runtime to FCN (the second most accurate DNN).”
boosted- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Although the datasets used in our experiments are relatively small compared to the billions of labeled images (such as ImageNet (Russakovsky et al., 2015) and OpenImages (Krasin et al., 2017) challenges), the deepest networks did reach competitive accuracies on the UCR/UEA archive benchmark.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“The MCNN and t-LeNet architectures yielded very low accuracies with only one win for the Earthquakes dataset.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“FCN wins on 36 datasets whereases Encoder wins only on 17”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“ResNet and FCN achieved the worst accuracy (30%) on this dataset while Time-CNN reached the best accuracy (95%).”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“However, TWIESN did reach competitive accuracies on several long time series datasets such as reaching a 96.8% accuracy on Meat whose time series length is equal to 448.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Overall, our results show that, on average, ResNet is the best architecture with FCN and Encoder following as second and third respectively.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“In other words, FCN's learned representation has too many data points close to the decision boundary whereas ResNet's hidden features enables projecting data points further away from the decision boundary.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- Rests on an assumption: MDS plots with Euclidean distance on GAP vectors preserve class separability sufficiently to interpret model performance.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“which is evident by the relatively low accuracy of both models FCN and ResNet which is equal respectively to 58.7% and 74.4%.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“In other words, FCN's CAM contains much more smoother regions with cyan, green and yellow regions, whereas ResNet's CAM contains more dark red and blue subsequences”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“ResNet performed very well in general except for the ECG datasets where it was outperformed by FCN.”
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“In other words, the weight's initial value can easily decrease the accuracy of FCN whereas ResNet maintained a relatively high accuracy when taking the worst initial weight values.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“We found small variance between the approaches that replace the GAP layer with an FC dense layer (MCDCNN, CNN) which also showed similar performance to TWIESN and MLP.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“We note that both deep learning models (FCN and ResNet) managed to project the data from GunPoint into a linearly separable space”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- Rests on an assumption: MDS plots with Euclidean distance on GAP vectors preserve class separability sufficiently to interpret model performance.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“we observed in our experiments, that DNNs for TSC suffer from a significant decrease (increase) in accuracy when initialized with bad (good) random weights.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
In the paper
“DNNs have indeed revolutionized the field of computer vision especially with the advent of novel deeper architectures such as Residual and Convolutional Neural Networks.”
- Also stated in: § 1 Introduction · p. 2 · plain
“Deep Convolutional Neural Networks (CNNs) have revolutionized the field of computer vision (Krizhevsky et al., 2012).”
What the sources say
- Not checked yetcites Krizhevsky et al., 2012
boosteddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
- Also stated in: § 1 Introduction · p. 2 · plain
None of the sources cited for this claim have been checked yet.
In the paper
“To achieve its high accuracy, HIVE-COTE becomes hugely computationally intensive and impractical to run on a real big data mining problem (Bagnall et al., 2017).”
- Also stated in: § 1 Introduction · p. 2 · hedged
“The approach requires training 37 classifiers as well as cross-validating each hyperparameter of these algorithms, which makes the approach infeasible to train in some situations (Lucas et al., 2018).”
What the sources say
- Not checked yetcites Bagnall et al., 2017 source
- Not checked yetcites Lucas et al., 2018
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- Also stated in: § 1 Introduction · p. 2 · hedged
None of the sources cited for this claim have been checked yet.
In the paper
“Apart from images, sequential data such as text and audio can also be processed with DNNs to reach state-of-the-art performance for document classification and speech recognition.”
- Also stated in: § 1 Introduction · p. 2 · plain
“Following the success of deep neural networks (DNNs) in computer vision, a huge amount of research proposed several DNN architectures to solve natural language processing (NLP) tasks such as machine translation (Sutskever et al., 2014; Bahdanau et al., 2015), learning word embeddings (Mikolov et al., 2013; Mikolov et al., 2013) and document classification (Le and Mikolov, 2014; Goldberg, 2016). DN”
What the sources say
- Not checked yetcites Sutskever et al., 2014
- Not checked yetcites Hinton et al., 2012 source
- Not checked yetcites Le and Mikolov, 2014
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
- Also stated in: § 1 Introduction · p. 2 · plain
None of the sources cited for this claim have been checked yet.
In the paper
“Once we have established that a statistical difference exists within the classifiers' performance, we followed the pairwise post-hoc analysis recommended by Benavoli et al. (2016) where the average rank comparison is replaced by a Wilcoxon signed-rank test (Wilcoxon, 1945) with Holm's alpha correction (Holm, 1979; Garcia and Herrera, 2008).”
What the sources say
- Not checked yetcites Benavoli et al., 2016
- Not checked yetcites Wilcoxon, 1945 source
- Not checked yetcites Holm, 1979
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
None of the sources cited for this claim have been checked yet.
In the paper
“The multivariate evaluation shows another benefit of deep learning models, which is the ability to handle the curse of dimensionality (Bellman, 2010; Keogh and Mueen, 2017) by leveraging different degrees of smoothness in compositional function (Poggio et al., 2017) as well as the parallel computations of the GPUs (Lu et al., 2015).”
What the sources say
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- Rests on an assumption: The UCR/UEA archive datasets are representative of TSC problems.
In the paper
“Apart from time series forecasting, we found that these neural networks were rarely applied for time series classification which is mainly due to three factors: (1) the type of this architecture is designed mainly to predict an output for each element (time stamp) in the time series (L¨ angkvist et al., 2014);”
What the sources say
- Not checked yetcites L¨ angkvist et al., 2014
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
In the paper
“(3) RNNs are considered hard to train and parallelize which led the researchers to avoid using them for computational reasons (Pascanu et al., 2013).”
What the sources say
- Not checked yetcites Pascanu et al., 2013
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
In the paper
“They were designed to mitigate the challenges of RNNs by eliminating the need to compute the gradient for the hidden layers which reduces the training time of these neural networks thus avoiding the vanishing gradient problem.”
What the sources say
- Not checked yetcites Gallicchio and Micheli, 2017
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
None of the sources cited for this claim have been checked yet.
In the paper
“This is surprising as deep learning has seen very successful applications in the last years.”
- Also stated in: § 1 Introduction · p. 2 · plain
“After having established the current state-of-the-art of non deep classifiers for TSC (Bagnall et al., 2017), we discuss the success of Deep Learning (LeCun et al., 2015) in various classification tasks which motivated the recent utilization of deep learning models for TSC (Wang et al., 2017b).”
What the sources say
- Not checked yetcites LeCun et al., 2015 source
- Not checked yetcites Wang et al., 2017b
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim.
- Also stated in: § 1 Introduction · p. 2 · plain
In the paper
“Deep learning approaches for TSC can be separated into two main categories: the generative and the discriminative models (as proposed in L¨ angkvist et al. (2014)).”
What the sources say
- Not checked yetcites L¨ angkvist et al., 2014
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
None of the sources cited for this claim have been checked yet.
In the paper
“As for comparing the classifiers over multiple datasets, we followed the recommendations in Demˇ sar (2006) and used the Friedman test (Friedman, 1940) to reject the null hypothesis.”
What the sources say
- Not checked yetcites Demˇ sar, 2006
- Not checked yetcites Friedman, 1940 source
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim.
In the paper
“Generative models usually exhibit an unsupervised training step that precedes the learning phase of the classifier (L¨ angkvist et al., 2014).”
What the sources say
- Not checked yetcites L¨ angkvist et al., 2014
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Finally, adding to the huge runtime of HIVE-COTE, the decision taken by 37 classifiers cannot be interpreted easily by domain experts, since researchers already struggle with understanding the decisions taken by an individual classifier.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“MLP does not have any layer whose number of parameters is invariant across time series of different lengths (denoted by # invar in Table 1) which means that the transferability of the network is not trivial: the number of parameters (weights) of the network depends directly on the length of the input time series.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
In the paper
“One final note is that the careful design of Encoder's attention mechanism enabled the invariance across all layers which encouraged the authors to implement a transfer learning approach.”
What the sources say
- Not checked yetcites Serr` a et al., 2018
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
In the paper
“Residual Networks (ResNets) (Wang et al., 2017b; Geng and Luo, 2018) which add linear shortcut connections for the convolutional layers potentially enhancing the model's accuracy (He et al., 2016).”
What the sources say
- Not checked yetcites He et al., 2016
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
In the paper
“To measure the performance of the model on the test data (generalization), we adopted the accuracy measure (similarly to Bagnall et al. (2017)).”
What the sources say
- Not checked yetcites Bagnall et al., 2017 source
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“Although ESNs were originally proposed for time series forecasting, Tanisaro and Heidemann (2016) proposed a variant of ESNs that uses directly the raw input time series and predicts a probability distribution over the class variables.”
What the sources say
- Not checked yetcites Tanisaro and Heidemann, 2016
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
In the paper
“In addition, one of the main characteristics of this architecture is the replacement of the traditional final FC layer with a Global Average Pooling (GAP) layer which reduces drastically the number of parameters in a neural network while enabling the use of the CAM (Zhou et al., 2016) that highlights which parts of the input time series contributed the most to a certain classification.”
What the sources say
- Not checked yetcites Zhou et al., 2016
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
In the paper
“The latter approach reached higher accuracy thus benefiting from the transfer learning technique.”
What the sources say
- Not checked yetcites Serr` a et al., 2018
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
In the paper
“In contrast to feature engineering, end-to-end deep learning aims to incorporate the feature learning process while fine-tuning the discriminative classifier (Nweke et al., 2018).”
What the sources say
- Not checked yetcites Nweke et al., 2018 source
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“which is probably due to their robustness and the relatively small amount of training time compared to complex architectures such as RNNs or MLPs.”
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
What the paper did — it cites no source for this, so there is none to check. The quote shows it is in the paper.
In the paper
“For memory usage limitations over a single GPU, we left the MTS dataset Performance Measurement System (PeMS) out of our experimentations.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Unlike ResNet and FCN, this approach does not have much invariant layers (2 out of 4) due to the use of an FC layer instead of a GAP layer, thus increasing drastically the number of parameters needed to be trained which also depends on the length of the input time series.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
In the paper
“This has also been the consensus in the human activity recognition literature, where the accuracy of deep learning methods depends highly on the quality of the extracted features (Nweke et al., 2018).”
What the sources say
- Not checked yetcites Nweke et al., 2018 source
boostedcorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim.
In the paper
“We also evaluated all deep learning models on Baydogan's archive (Baydogan, 2015) that contains 13 MTS classification datasets.”
What the sources say
- Not checked yetcites Baydogan, 2015
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“However, any deep learning algorithm can benefit from this type of modification.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“That being said, we can easily pre-train a model on a source dataset, then transfer and fine-tune it on a target dataset without having to modify the hidden layers of the network.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“This archive also exhibits datasets with different characteristics such as the length of the time series which, unlike the UCR/UEA archive, varies among the same dataset. This is due to the fact that the datasets in the UCR/UEA archive are already re-scaled to have an equal length among one dataset (Bagnall et al., 2017).”
What the sources say
- Not checked yetcites Bagnall et al., 2017 source
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“FCNs are mainly convolutional networks that do not contain any local pooling layers which means that the length of a time series is kept unchanged throughout the convolutions.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
In the paper
“Cui et al. (2016) were the first to introduce the Window Slicing (WS) method as a data augmentation technique.”
What the sources say
- Not checked yetcites Cui et al., 2016
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“Actually, the difference with the usual convolutions (such as in FCNs) is that a linear shortcut is added to link the output of a residual block to its input thus enabling the flow of the gradient directly through these connections, which makes training a DNN much easier by reducing the vanishing gradient effect (He et al., 2016).”
What the sources say
- Not checked yetcites He et al., 2016
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The problem with an MLP approach is that temporal information is lost and the features learned are no longer time-invariant.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
In the paper
“We made this choice because we believe that the main goal of deep learning approaches is to remove the bias due to manually designed features (Ord´ o¨ nez and Roggen, 2016), thus enabling the network to learn the most discriminant useful features for the classification task.”
What the sources say
- Not checked yetcites Ord´ o¨ nez and Roggen, 2016
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
In the paper
“This form of pre-processing has also been used by Ratanamahatana and Keogh (2005) to show that the length of a time series is not an issue for TSC problems.”
What the sources say
- Not checked yetcites Ratanamahatana and Keogh (2005)
boosted- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“By using an FC layer before the softmax classifier, the transferability of this network is limited to the first and second convolutional layers.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The first characteristic of Time-CNN is the use of the mean squared error (MSE) instead of the traditional categorical cross-entropy loss function, which has been used by all the deep learning approaches we have mentioned so far. Hence, instead of a softmax classifier, the final layer is a traditional FC layer with sigmoid as the activation function, which does not guarantee a sum of probabilities”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Unlike GAP, local pooling introduces invariance to small perturbations in the activation map (the result of a convolution) by taking the maximum value in a local pooling window.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
What the paper did — it cites no source for this, so there is none to check. The quote shows it is in the paper.
In the paper
“Since we did not train nor test any of the state-of-the-art non deep learning algorithms, it is possible that we allowed much more training time for the described DNNs.”
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
In the paper
“our findings are in agreement with the deep learning for computer vision literature where deeper neural networks are much more successful than shallower architectures (He et al., 2016).”
What the sources say
- Not checked yetcites He et al., 2016
boosteddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Interestingly, DiatomSizeReduction is the smallest datasets in the UCR/UEA archive (with 16 training instances), which suggests that ResNet and FCN are easily overfitting this dataset.”
hedgedconditionalSingle case- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“This step is very important for deep learning models whose architecture depends on the length of the input time series (such as a MLP) and for parallel computation over the GPUs.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. It may state two separate claims as one.
- Rests on an assumption: The MTS archive contains time series of unequal length.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“In addition to the huge training time, HIVE-COTE's classification time is bounded by a linear scan of the training set due to employing a nearest neighbor classifier, whereas the trivial GPU parallelization of DNNs provides instant classification.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
In the paper
“since increasing the number of convolutional layers will increase the path length viewed by the CNN model (Vaswani et al., 2017), ResNet and FCN managed to outperform other approaches whose filter length is longer (21) such as Encoder.”
What the sources say
- Not checked yetcites Vaswani et al., 2017
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“This FC layer reduces the effect of learning time invariant features which explains why MLP, Time-CNN and MCDCNN exhibit very similar performance.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Therefore, we believe that allowing a much more thorough search of DTW's warping window would lead to a fairer comparison between deep learning approaches and other state-of-the-art TSC algorithms.”
hedgeddirect- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence.
What the paper did — it cites no source for this, so there is none to check. The quote shows it is in the paper.
In the paper
“unlike HIVE-COTE, ResNet's hyperparameters were not tuned for each dataset but rather the same architecture was used for the whole benchmark”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“One final observation that is in agreement with the deep learning literature is that in order to achieve high accuracies while training a DNN, a large training set is needed.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“suggesting that these methods are no longer competitive with current state-of-the-art algorithms for TSC.”
hedged- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“suggesting further investigation of these hyperparameters should improve DNNs' accuracy for TSC.”
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“it is only natural to think that discovering patterns in a one dimensional space (time) should be an easier task for CNNs thus requiring less data to learn from.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds. It may state two separate claims as one.
What the paper did — it cites no source for this, so there is none to check. The quote shows it is in the paper.
In the paper
“which enables us to take the mean accuracy over the 10 runs in order to reduce the bias due to the weights' initial values.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim.
In the paper
“for a lazy machine learning algorithm such as NN-DTW, training time is zero when allowing maximum warping whereas it has been shown that judicially setting the warping window Dau et al. (2017) can lead to a significant increase in accuracy.”
What the sources say
- Not checked yetcites Dau et al., 2017
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“These observations reinforces the need to have an equally large MTS classification archive in order to evaluate hybrid univariate/multivariate time series classifiers.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence.
In the paper
“but the fact that ResNet is not significantly different than COTE suggests that more datasets would give a better insight into these performances (Demˇ sar, 2006).”
What the sources say
- Not checked yetcites Demˇ sar, 2006
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper’s conclusions may not depend on it.
In the paper
“It is worthwhile noting that cliques formed by the Wilcoxon Signed Rank Test with Holm's alpha correction do not necessary reflect the rank order (Lines et al., 2018).”
What the sources say
- Not checked yetcites Lines et al., 2018 source
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Although Time-CNN and MCDCNN are the only architectures originally proposed for MTS data”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“We believe that the success of ResNet is highly due to its deep flexible architecture.”
hedgeddirect- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence.
In the paper
“especially since normalization is known to have a huge effect on DNNs' learning capabilities (Zhang et al., 2017).”
What the sources say
- Not checked yetcites Zhang et al., 2017
boosteddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“which probably explains why FCN is less accurate than ResNet on this dataset.”
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The quote only partly states this claim.
- Rests on an assumption: CAM visualizations faithfully indicate which time series regions contribute to class identification.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“In fact, most DNNs architectures, with the categorical cross-entropy as their cost function, employ mainly the same classifier: softmax which is basically designed for multi-class classification.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
In the paper
“we stress that the shapelet transformation classifier (Hills et al., 2014) is an ensemble approach, which makes unclear how the shapelets affect the decision taken by the individual classifiers whereas for an end-to-end deep learning model we can directly explain the classification by using the Class Activation Map.”
What the sources say
- Not checked yetcites Hills et al., 2014 source
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“On the other hand, the part where the actor raises his/her arm seems to be also a discriminative part of the data which suggests that the deep learning algorithms are identifying more 'shapelets'.”
hedgedcorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Finally, another interesting observation is the ability of CNNs to localize a given discriminative shape regardless where it appears in the time series, which is evidence for CNNs' capability of learning time-invariant warped features.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“We should note that this observation cannot confirm which classifier extracted the most discriminative subsequences especially because all algorithms achieved similar accuracy on GunPoint dataset.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
The paper relies on this without support.
The UCR/UEA archive datasets are representative of TSC problems.
“we tested the approaches on 12 Multivariate Time Series (MTS) datasets (Baydogan, 2015).”
The paper relies on this without support.
The 97 time series datasets used are sufficient to generalize about DNN performance for TSC.
“By training 8,730 deep learning models on 97 time series datasets, we propose the most exhaustive study of DNNs for TSC to date.”
The paper relies on this without support.
The deep learning implementations in the framework faithfully represent the original methods.
“We also provide an open source deep learning framework to the TSC community where we implemented each of the compared approaches and evaluated them on a univariate TSC benchmark (the UCR/UEA archive) and 12 multivariate time series datasets.”
The paper relies on this without support.
The MTS archive contains time series of unequal length.
“In order to solve the problem of unequal length time series in the MTS archive”
The paper relies on this without support.
CAM visualizations faithfully indicate which time series regions contribute to class identification.
“Highlighting with the Class Activation Map the contribution of each time series region for the three classes in Meat when using the FCN and ResNet classifiers.”
The paper relies on this without support.
MDS plots with Euclidean distance on GAP vectors preserve class separability sufficiently to interpret model performance.
“Figure 15 shows three MDS plots for the GunPoint dataset using: (1) the raw input time series (Figure 15a); (2) the learned latent features from the GAP layer for FCN (Figure 15b); and (3)”
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“These approaches, categorized as temporal representation[105,106], divide the entire framework into two stages: “temporal representation” and “temporal prediction.””
From Advancements in the estimation of the state of charge of lithium-ion battery: a comprehensive review of traditional and deep learning approaches (2025) · cites this paper as [105]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“These include the high computational cost incurred by running multiple instances [18,19]”
From TVGeAN: Tensor Visibility Graph-Enhanced Attention Network for Versatile Multivariant Time Series Learning Tasks (2024) · cites this paper as [19]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ 4.1.1 Univariate archive · p. 21
“| WalkVsRun | 128-1918 | 1919 | 2 | 62 | 28 | 16 |”
§ 4.1.2 Multivariate archive · p. 21
“thus each time series will have a length equal to the longest time series' length.”
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ 3.2.1 Multi Layer Perceptron · p. 14
“MLP does not have any layer whose number of parameters is invariant across time series of different lengths”
§ 3.2.1 Multi Layer Perceptron · p. 14
“All three hidden FC layers are composed of 500 neurons with ReLU as the activation function.”
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · cited 12×
“First of all, our findings are in agreement with the deep learning for computer vision literature where deeper 1 The implementations are available on https://github.com/hfawaz/dl-4-tsc neural networks are much more successful than shallower architectures (He et al., 2016).”
BackgroundResultInfluentialVaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017) · arXiv · doi:10.48550/arxiv.1706.03762 · Cited by 120,404 · cited 4×
“The MLP, which is the most traditional form of DNNs, was proposed in Wang et al. (2017b) as a baseline architecture for TSC.”
BackgroundMethodInfluentialImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155 · cited 7×
“Since AlexNet (Krizhevsky et al. 2012) won the ImageNet competition in 2012, deep CNNs have seen a lot of successful applications in many different domains (LeCun et al.”
BackgroundInfluentialAdam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946 · cited 1×
“All models were optimized using a variant of Stochastic Gradient Descent (SGD) such as Adam (Kingma and Ba, 2015) and AdaDelta (Zeiler, 2012).”
MethodLeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
Gradient-based learning applied to document recognition
Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998) · Proceedings of the IEEE · doi:10.1109/5.726791 · Cited by 58,805
Going deeper with convolutions
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298594 · Cited by 48,562
ImageNet Large Scale Visual Recognition Challenge
Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al. (2015) · International Journal of Computer Vision · doi:10.1007/s11263-015-0816-y · Cited by 39,380
(2014) · Cited by 33,419
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Ioffe, S., & Szegedy, C. (2015) · arXiv · doi:10.48550/arxiv.1502.03167 · Cited by 27,818
Efficient Estimation of Word Representations in Vector Space
Mikolov, T., Chen, K., Corrado, G., & Dean, J. (2013) · arXiv · doi:10.48550/arxiv.1301.3781 · Cited by 26,568 · cited 1×
“…proposed several DNN architectures to solve natural language processing (NLP) tasks such as machine translation (Sutskever et al., 2014; Bahdanau et al., 2015), learning word embeddings (Mikolov et al., 2013; Mikolov et al., 2013) and document classification (Le and Mikolov, 2014; Goldberg, 2016).”
BackgroundDistributed Representations of Words and Phrases and their Compositionality
Mikolov, T., Sutskever, I., Chen, K., Corrado, G., & Dean, J. (2013) · arXiv · doi:10.48550/arxiv.1310.4546 · Cited by 24,533 · cited 1×
“…proposed several DNN architectures to solve natural language processing (NLP) tasks such as machine translation (Sutskever et al., 2014; Bahdanau et al., 2015), learning word embeddings (Mikolov et al., 2013; Mikolov et al., 2013) and document classification (Le and Mikolov, 2014; Goldberg, 2016).”
BackgroundPan, S. J., & Yang, Q. (2010) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2009.191 · Cited by 23,387
Book Review: Pattern Recognition and Machine Learning
Nasrabadi, N. M. (2007) · Journal of Electronic Imaging · doi:10.1117/1.2819119 · Cited by 22,066 · cited 2×
“Regularization methods such as l2-norm weight decay (Bishop, 2006) or Dropout (Srivastava et al.”
MethodA Simple Sequentially Rejective Multiple Test Procedure
(1979) · Scandinavian Journal of Statistics · doi:10.2307/4615733 · Cited by 21,526 · cited 4×
“(2016) where the average rank comparison is replaced by a Wilcoxon signed-rank test (Wilcoxon, 1945) with Holm’s alpha correction (Holm, 1979; Garcia and Herrera, 2008).”
MethodInfluentialDelving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
He, K., Zhang, X., Ren, S., & Sun, J. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.123 · Cited by 19,741 · cited 2×
“Each convolution is followed by an instance normalization operation (Ulyanov et al., 2016) whose output is fed to the Parametric Rectified Linear Unit (PReLU) (He et al., 2015) activation function.”
MethodSequence to Sequence Learning with Neural Networks
Sutskever, I., Vinyals, O., & Le, Q. V. (2014) · arXiv · doi:10.48550/arxiv.1409.3215 · Cited by 17,766 · cited 2×
“…deep CNNs have seen a lot of successful applications in many different domains (LeCun et al., 2015) such as reaching human level performance in image recognition problems (Szegedy et al., 2015) as well as different natural language processing tasks (Sutskever et al., 2014; Bahdanau et al., 2015).”
BackgroundNeural Machine Translation by Jointly Learning to Align and Translate
Bahdanau, D., Cho, K., & Bengio, Y. (2014) · arXiv · doi:10.48550/arxiv.1409.0473 · Cited by 16,213 · cited 4×
“…of research proposed several DNN architectures to solve natural language processing (NLP) tasks such as machine translation (Sutskever et al., 2014; Bahdanau et al., 2015), learning word embeddings (Mikolov et al., 2013; Mikolov et al., 2013) and document classification (Le and Mikolov, 2014;…”
BackgroundInfluentialIndividual Comparisons by Ranking Methods
Wilcoxon, F. (1945) · Biometrics Bulletin · doi:10.2307/3001968 · Cited by 15,354
Convolutional Neural Networks for Sentence Classification
Kim, Y. (2014) · Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.3115/v1/d14-1181 · Cited by 14,831 · cited 2×
“, 2012) and sentence classification (Kim, 2014) where text and audio, similarly to time series data, exhibit a natural temporal ordering.”
BackgroundBellman, R. E. (2010) · doi:10.1515/9781400835386 · Cited by 14,588
(2010) · Cited by 14,134
Statistical Comparisons of Classifiers over Multiple Data Sets
Demšar, J. (2006) · doi:10.5555/1248547.1248548 · Cited by 12,051
Learning Deep Features for Discriminative Localization
Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., & Torralba, A. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.319 · Cited by 11,428 · cited 6×
“In addition, one of the main characteristics of this architecture is the replacement of the traditional final FC layer with a Global Average Pooling (GAP) layer which reduces drastically the number of parameters in a neural network while enabling the use of the CAM (Zhou et al., 2016) that highlights which parts of th…”
BackgroundMethodInfluentialHinton, G., Deng, L., Yu, D., Dahl, G., Mohamed, A.-R., Jaitly, N., Senior, A., Vanhoucke, V., Nguyen, P., Sainath, T., et al. (2012) · IEEE Signal Processing Magazine · doi:10.1109/msp.2012.2205597 · Cited by 10,260
Pattern Recognition and Machine Learning
(2006) · doi:10.1007/978-0-387-45528-0 · Cited by 9,824
Distributed Representations of Sentences and DocumentsPreprint
Le, Q. V., & Mikolov, T. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1405.4053 · Cited by 7,905 · cited 3×
“…proposed several DNN architectures to solve natural language processing (NLP) tasks such as machine translation (Sutskever et al., 2014; Bahdanau et al., 2015), learning word embeddings (Mikolov et al., 2013; Mikolov et al., 2013) and document classification (Le and Mikolov, 2014; Goldberg, 2016).”
BackgroundHow transferable are features in deep neural networks?
Yosinski, J., Clune, J., Bengio, Y., & Lipson, H. (2014) · arXiv · doi:10.48550/arxiv.1411.1792 · Cited by 6,061 · cited 1×
“But since we are aiming at visualizing the class specific latent space, we chose to use the last latent representation of a DNN (the one directly before the softmax classifier), which is known to be a class specific layer (Yosinski et al., 2014).”
MethodADADELTA: An Adaptive Learning Rate Method
Zeiler, M. D. (2012) · arXiv · doi:10.48550/arxiv.1212.5701 · Cited by 5,322
Instance Normalization: The Missing Ingredient for Fast StylizationPreprint
Ulyanov, D., Vedaldi, A., & Lempitsky, V. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1607.08022 · Cited by 4,325 · cited 3×
“Each convolution is followed by an instance normalization operation (Ulyanov et al., 2016) whose output is fed to the Parametric Rectified Linear Unit (PReLU) (He et al., 2015) activation function.”
MethodOn the difficulty of training recurrent neural networks
Pascanu, R., Mikolov, T., & Bengio, Y. (2012) · arXiv · doi:10.48550/arxiv.1211.5063 · Cited by 4,310 · cited 2×
“, 2012); (3) RNNs are considered hard to train and parallelize which led the researchers to avoid using them for computational reasons (Pascanu et al., 2013).”
BackgroundKruskal, J. B., & Wish, M. (1978) · Sage eBooks · doi:10.4135/9781412985130 · Cited by 4,004
Harnessing Nonlinearity: Predicting Chaotic Systems and Saving Energy in Wireless Communication
Jaeger, H., & Haas, H. (2004) · Science · doi:10.1126/science.1091277 · Cited by 3,811
Ridge Regression: Applications to Nonorthogonal Problems
Hoerl, A. E., & Kennard, R. W. (1970) · Technometrics · doi:10.1080/00401706.1970.10488635 · Cited by 3,018
Understanding deep learning requires rethinking generalization
Zhang, C., Bengio, S., Hardt, M., Recht, B., & Vinyals, O. (2016) · arXiv · doi:10.48550/arxiv.1611.03530 · Cited by 2,838 · cited 3×
“, 2017) should be further studied for univariate as well as multivariate data, especially since normalization is known to have a huge effect on DNNs’ learning capabilities (Zhang et al., 2017).”
BackgroundMethodResultInfluentialA Comparison of Alternative Tests of Significance for the Problem of $m$ Rankings
Friedman, M. (1940) · The Annals of Mathematical Statistics · doi:10.1214/aoms/1177731944 · Cited by 2,785 · cited 4×
“As for comparing the classifiers over multiple datasets, we followed the recommendations in Demšar (2006) and used the Friedman test (Friedman, 1940) to reject the null hypothesis.”
MethodInfluentialDeep Convolutional and LSTM Recurrent Neural Networks for Multimodal Wearable Activity Recognition
Ordóñez, F., & Roggen, D. (2016) · Sensors · doi:10.3390/s16010115 · Cited by 2,761 · cited 2×
“We think that our choice makes sense in a way that the goal of deep learning approaches is to remove the bias due to manually designed features (Ordón̈ez and Roggen, 2016), thus enabling the network to learn the most discriminant useful features for the classification task.”
BackgroundScalable and accurate deep learning with electronic health records
Rajkomar, A., Oren, E., Chen, K., Dai, A. M., Hajaj, N., Hardt, M., Liu, P. J., Liu, X., Marcus, J., Sun, M., et al. (2018) · npj Digital Medicine · doi:10.1038/s41746-018-0029-1 · Cited by 2,648
Understanding deep learning (still) requires rethinking generalization
Zhang, C., Bengio, S., Hardt, M., Recht, B., & Vinyals, O. (2021) · Communications of the ACM · doi:10.1145/3446776 · Cited by 2,400
Time series classification from scratch with deep neural networks: A strong baseline
Wang, Z., Yan, W., & Oates, T. (2017) · 2017 International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2017.7966039 · Cited by 2,299 · cited 18×
“In Wang et al. (2017b); Geng and Luo (2018), an MLP was designed to learn from scratch a discriminative time series classifier.”
BackgroundMethodResultInfluentialScalable and accurate deep learning with electronic health records.
Rajkomar, A., Oren, E., Chen, K., Dai, A. M., Hajaj, N., Hardt, M., Liu, P. J., Liu, X., Marcus, J., Sun, M., et al. (2018) · eScholarship (California Digital Library) · Cited by 2,242
Deep learning for sensor-based activity recognition: A survey
Wang, J., Chen, Y., Hao, S., Peng, X., & Hu, L. (2019) · Pattern Recognition Letters · doi:10.1016/j.patrec.2018.02.010 · Cited by 2,014 · cited 2×
“More recently in Wang et al. (2018), the architectures proposed in Wang et al. (2017b) were modified to leverage a filter initialization technique based on the Daubechies 4 Wavelet values (Rowe and Abbott, 1995).”
BackgroundMethodBagnall, A., Lines, J., Bostrom, A., Large, J., & Keogh, E. (2017) · Data Mining and Knowledge Discovery · doi:10.1007/s10618-016-0483-9 · Cited by 1,377 · cited 46×
“However, given the small sample size (only 7 datasets), we cannot conclude that FCN will almost always outperform the ResNet model for ECG datasets (Bagnall et al., 2017).”
BackgroundMethodResultInfluentialLeCun, Y., Bottou, L., Orr, G., & Müller, K. (1998) · neural information processing systems · Cited by 1,333
A Primer on Neural Network Models for Natural Language Processing
Goldberg, Y. (2016) · Journal of Artificial Intelligence Research · doi:10.1613/jair.4992 · Cited by 1,316
García, S., & Herrera, F. (2008) · Cited by 1,277
A review of unsupervised feature learning and deep learning for time-series modeling
Längkvist, M., Karlsson, L., & Loutfi, A. (2014) · Pattern Recognition Letters · doi:10.1016/j.patrec.2014.01.008 · Cited by 1,276
Dau, H. A., Bagnall, A., Kamgar, K., Yeh, C.-C. M., Zhu, Y., Gharghabi, S., Ratanamahatana, C. A., & Keogh, E. (2019) · IEEE/CAA Journal of Automatica Sinica · doi:10.1109/jas.2019.1911747 · Cited by 1,128
Deep convolutional neural networks for LVCSR
Sainath, T. N., Mohamed, A., Kingsbury, B. E. D., & Ramabhadran, B. (2013) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2013.6639347 · Cited by 1,083 · cited 1×
“DNNs also had a huge impact on the speech recognition community (Hinton et al., 2012; Sainath et al., 2013).”
BackgroundDeep learning for healthcare applications based on physiological signals: A review
Faust, O., Hagiwara, Y., Hong, T. J., Lih, O. S., & Acharya, U. R. (2018) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2018.04.005 · Cited by 1,081 · cited 1×
“Finally, a recent review of deep learning for physiological signals classification revealed that CNNs were the most popular architecture (Faust et al., 2018) for the considered task.”
BackgroundEsling, P., & Agón, C. (2012) · ACM Computing Surveys · doi:10.1145/2379776.2379788 · Cited by 1,075
10 CHALLENGING PROBLEMS IN DATA MINING RESEARCH
Yang, Q., & Wu, X. (2006) · International Journal of Information Technology & Decision Making · doi:10.1142/s0219622006002258 · Cited by 956
Nweke, H. F., Teh, Y. W., Al-garadi, M. A., & Alo, U. R. (2018) · Expert Systems with Applications · doi:10.1016/j.eswa.2018.03.056 · Cited by 930
LeCun, Y., Bottou, L., Orr, G., & Müller, K. R. (1998) · Lecture notes in computer science · doi:10.1007/3-540-49430-8_2 · Cited by 920
Convolutional neural networks for time series classification
College of Electronic Science and Engineering, N. U. O. D. T., Zhao, B., Lu, H., College of Electronic Science and Engineering, N. U. O. D. T., Chen, S., College of Electronic Science and Engineering, N. U. O. D. T., Liu, J., College of Electronic Science and Engineering, N. U. O. D. T., Wu, D., & College of Electronic Science and Engineering, N. U. O. D. T. (2017) · Journal of Systems Engineering and Electronics · doi:10.21629/jsee.2017.01.18 · Cited by 888 · cited 2×
“In Le Guennec et al. (2016); Cui et al. (2016); Wang et al. (2017b); Zhao et al. (2017), traditional CNNs were also validated on the UCR/UEA archive.”
MethodReal-time human activity recognition from accelerometer data using Convolutional Neural Networks
Ignatov, A. (2017) · Applied Soft Computing · doi:10.1016/j.asoc.2017.09.027 · Cited by 843 · cited 1×
“In fact, most of the deep learning approaches for TSC with some hand engineered features are present in human activity recognition tasks (Ignatov, 2018).”
BackgroundImaging Time-Series to Improve Classification and ImputationPreprint
Wang, Z., & Oates, T. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1506.00327 · Cited by 832
Time Series Classification Using Multi-Channels Deep Convolutional Neural Networks
Zheng, Y., Liu, Q., Chen, E., Ge, Y., & Zhao, J. L. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-08010-9_33 · Cited by 706 · cited 1×
“Multi Channel Deep Convolutional Neural Network (MCDCNN) was originally proposed and validated on two multivariate time series datasets (Zheng et al., 2014, 2016).”
MethodMulti-Scale Convolutional Neural Networks for Time Series ClassificationPreprint
Cui, Z.-C., Chen, W.-L., & Chen, Y. (2016) · arXiv.org · doi:10.48550/arxiv.1603.06995 · Cited by 637
A time series forest for classification and feature extraction
Deng, H., Runger, G. C., Tuv, E., & Vladimir, M. (2013) · Information Sciences · doi:10.1016/j.ins.2013.02.030 · Cited by 632
Deep k-Nearest Neighbors: Towards Confident, Interpretable and Robust Deep LearningPreprint
Papernot, N., & McDaniel, P. D. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1803.04765 · Cited by 592
The BOSS is concerned with time series classification in the presence of noise
Schäfer, P. (2014) · Data Mining and Knowledge Discovery · doi:10.1007/s10618-014-0377-7 · Cited by 564 · cited 12×
“Despite the fact that a huge number of parameters risks overfitting (Zhang et al., 2017) the relatively small train set in the UCR/UEA archive, our experiments showed that not only DNNs are able to significantly outperform the NN-DTW, but are also able to achieve results that are not significantly different than COTE…”
BackgroundMethodInfluentialWhy and when can deep-but not shallow-networks avoid the curse of dimensionality: A review
Poggio, T., Mhaskar, H., Rosasco, L., Miranda, B., & Liao, Q. (2017) · International Journal of Automation and Computing · doi:10.1007/s11633-017-1054-2 · Cited by 559 · cited 2×
“…benefit of deep learning models, which is the ability to handle the curse of dimensionality (Bellman, 2010; Keogh and Mueen, 2017) by leveraging different degrees of smoothness in compositional function (Poggio et al., 2017) as well as the parallel computations of the GPUs (Lu et al., 2015).”
BackgroundDeep Learning for Time-Series AnalysisPreprint
Gamboa, J. C. B. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1701.01887 · Cited by 549
Classification of time series by shapelet transformation
Hills, J., Lines, J., Baranauskas, E., Mapp, J., & Bagnall, A. (2014) · Data Mining and Knowledge Discovery · doi:10.1007/s10618-013-0322-1 · Cited by 538 · cited 16×
“Hence, recent contributions have focused on developing ensemblingmethods that significantly outperforms the NN coupled with DTW (NN-DTW) (Bagnall et al. 2016; Hills et al. 2014; Bostrom and Bagnall 2015; Lines et al. 2016; Schäfer 2015; Kate 2016; Deng et al. 2013; Baydogan et al. 2013).”
BackgroundMethodInfluentialTime series classification with ensembles of elastic distance measures
Lines, J., & Bagnall, A. J. (2014) · Data Mining and Knowledge Discovery · doi:10.1007/s10618-014-0361-2 · Cited by 513 · cited 3×
“Lines and Bagnall (2015) compared several distance measures and showed that there is no single distance measure that significantly outperforms DTW.”
BackgroundMethodWang, Z., & Oates, T. (2015) · National Conference on Artificial Intelligence · Cited by 500
Learning time-series shapelets
Grabocka, J., Schilling, N., Wistuba, M., & Schmidt-Thieme, L. (2014) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/2623330.2623613 · Cited by 489 · cited 3×
“This observation would also be backed up by the mathematical proof provided by Cui et al. (2016), that showed how the learned filters in a CNN can be considered a generic form of shapelets extracted by the learning shapelets algorithm (Grabocka et al., 2014).”
BackgroundMethodTransfer learning for short-term wind speed prediction with deep neural networks
Hu, Q., Zhang, R., & Zhou, Y. (2015) · Renewable Energy · doi:10.1016/j.renene.2015.06.034 · Cited by 469 · cited 1×
“Usually, to model the time series, classifiers are preceded by an unsupervised pre-training phase such as stacked denoising auto-encoders (SDAEs) (Bengio et al., 2013; Hu et al., 2016).”
BackgroundTime-Series Classification with COTE: The Collective of Transformation-Based Ensembles
Bagnall, A. J., Lines, J., Hills, J., & Bostrom, A. (2015) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2015.2416723 · Cited by 433 · cited 14×
“Despite the fact that a huge number of parameters risks overfitting (Zhang et al., 2017) the relatively small train set in the UCR/UEA archive, our experiments showed that not only DNNs are able to significantly outperform the NN-DTW, but are also able to achieve results that are not significantly different than COTE…”
BackgroundMethodInfluentialUnderstanding the exploding gradient problemPreprint
Pascanu, R., Mikolov, T., & Bengio, Y. (2012) · arXiv (Cornell University) · Cited by 413
Time series shapelets: a novel technique that allows accurate, interpretable and fast classification
Ye, L., & Keogh, E. (2011) · Data Mining and Knowledge Discovery · doi:10.1007/s10618-010-0179-5 · Cited by 406 · cited 2×
“Ye and Keogh (2011) identified that the most important shapelet for the Gun/NoGun classification occurs when the actor’s arm is lowered (about 120 on the horizontal axis in Figure 13).”
BackgroundMethodThree Myths about Dynamic Time Warping Data Mining
Ratanamahatana, C. A., & Keogh, E. (2005) · SIAM International Conference on Data Mining · doi:10.1137/1.9781611972757.50 · Cited by 398 · cited 2×
“This form of pre-processing has also been used by Ratanamahatana and Keogh (2005) to show that the length of a time series is not an issue for TSC problems.”
MethodClassification of time-series images using deep convolutional neural networks
Debayle, J., Hatami, N., & Gavet, Y. (2018) · International Conference on Machine Vision · doi:10.1117/12.2309486 · Cited by 385 · cited 2×
“…extraction method for hand engineering approaches is the transformation of time series into images using specific imaging methods such as Gramian fields (Wang and Oates, 2015b,a), recurrence plots (Hatami et al., 2017; Tripathy and Acharya, 2018) and Markov transition fields (Wang and Oates, 2015).”
MethodA Bag-of-Features Framework to Classify Time Series
Baydogan, M. G., Runger, G., & Tuv, E. (2013) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2013.72 · Cited by 361
Keogh, E., & Mueen, A. (2010) · Encyclopedia of Machine Learning · doi:10.1007/978-0-387-30164-8_192 · Cited by 358
Using dynamic time warping distances as features for improved time series classification
Kate, R. J. (2015) · Data Mining and Knowledge Discovery · doi:10.1007/s10618-015-0418-x · Cited by 355 · cited 13×
“Despite the fact that a huge number of parameters risks overfitting (Zhang et al., 2017) the relatively small train set in the UCR/UEA archive, our experiments showed that not only DNNs are able to significantly outperform the NN-DTW, but are also able to achieve results that are not significantly different than COTE…”
BackgroundMethodInfluentialData Augmentation for Time Series Classification using Convolutional Neural Networks
Guennec, A. L., Malinowski, S., & Tavenard, R. (2016) · HAL · Cited by 341
Lines, J., Taylor, S., & Bagnall, A. (2018) · ACM Transactions on Knowledge Discovery from Data · doi:10.1145/3182382 · Cited by 333
Generalized Denoising Auto-Encoders as Generative Models
Bengio, Y., Yao, L., Alain, G., & Vincent, P. (2013) · arXiv · doi:10.48550/arxiv.1305.6663 · Cited by 324 · cited 2×
“Usually, to model the time series, classifiers are preceded by an unsupervised pre-training phase such as stacked denoising auto-encoders (SDAEs) (Bengio et al., 2013; Hu et al., 2016). A generative CNN-based model was proposed in Wang et al. (2016b);”
BackgroundMethodTime Series Classification With Multivariate Convolutional Neural Network
Liu, C., Hsaio, W.-H., & Tu, Y.-C. (2018) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2018.2864702 · Cited by 323
Transfer learning for time series classification
Ismail Fawaz, H., Forestier, G., Weber, J., Idoumghar, L., & Muller, P.-A. (2018) · 2018 IEEE International Conference on Big Data (Big Data) · doi:10.1109/bigdata.2018.8621990 · Cited by 319
Self-citationShould we really use post-hoc tests based on mean-ranks?Preprint
BenavoliAlessio, CoraniGiorgio, & MangiliFrancesca (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1505.02288 · Cited by 318 · cited 2×
“Then we performed the pairwise posthoc analysis recommended by Benavoli et al. (2016) where the average rank comparison is replaced by a Wilcoxon signed-rank test (Wilcoxon, 1945) with Holm’s alpha (5”
MethodBaird, H. S. (1992) · Springer eBooks · doi:10.1007/978-3-642-77281-8_26 · Cited by 285 · cited 1×
“Another popular technique is data augmentation, which tackles the problem of overfitting a small dataset by increasing the number of training instances (Baird 1992).”
MethodZheng, Y., Liu, Q., Chen, E., Ge, Y., & Zhao, J. L. (2015) · Frontiers of Computer Science · doi:10.1007/s11704-015-4478-2 · Cited by 282
Multilevel Wavelet Decomposition Network for Interpretable Time Series Analysis
Wang, J., Wang, Z., Li, J., & Wu, J. (2018) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3219819.3220060 · Cited by 258 · cited 2×
“More recently in Wang et al. (2018), the architectures proposed in Wang et al. (2017b) were modified to leverage a filter initialization technique based on the Daubechies 4 Wavelet values (Rowe and Abbott, 1995).”
BackgroundMethodReservoir Computing Approaches for Representation and Classification of Multivariate Time Series
Bianchi, F. M., Scardapane, S., Løkse, S., & Jenssen, R. (2020) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2020.3001377 · Cited by 238
Detecting and interpreting myocardial infarction using fully convolutional neural networks
Strodthoff, N., & Strodthoff, C. (2018) · Physiological Measurement · doi:10.1088/1361-6579/aaf34d · Cited by 219
Generating Synthetic Time Series to Augment Sparse Datasets
Forestier, G., Petitjean, F., Dau, H. A., Webb, G. I., & Keogh, E. (2017) · Proceedings · doi:10.1109/icdm.2017.106 · Cited by 201 · cited 3×
“…extensive experimental evaluation, deep learning for time series classification, unlike for computer vision and NLP tasks, still lacks a thorough study of data augmentation (Ismail Fawaz et al., 2018a; Forestier et al., 2017) and transfer learning (Ismail Fawaz et al., 2018c; Serrà et al., 2018).”
BackgroundMethodSelf-citationData augmentation using synthetic data for time series classification with deep residual networksPreprint
Fawaz, H. I., Forestier, G., Weber, J., Idoumghar, L., & Müller, P.-A. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1808.02455 · Cited by 187
Self-citationTimeNet: Pre-trained deep recurrent neural network for time series classificationPreprint
Malhotra, P., Tv, V., Vig, L., Agarwal, P., & Shroff, G. M. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1706.08838 · Cited by 180 · cited 1×
“In Mehdiyev et al. (2017); Malhotra et al. (2018); Rajan and Thiagarajan (2018), an RNN auto-encoder was designed to first generate the time series then using the learned latent representation, they trained a classifier (such as SVM or Random Forest) on top of these representations to predict the…”
MethodLines, J., Taylor, S. L., & Bagnall, A. J. (2016) · Proceedings · doi:10.1109/icdm.2016.0133 · Cited by 177
Che, Z., Cheng, Y., Zhai, S., Sun, Z., & Liu, Y. (2017) · 2017 IEEE International Conference on Data Mining (ICDM) · doi:10.1109/icdm.2017.93 · Cited by 162 · cited 3×
“Other ESN-based approaches (Chen et al., 2015a, 2013; Che et al., 2017b) define a kernel over the learned representation followed by an SVM or an MLP classifier.”
BackgroundMethodTripathy, R. K., & Acharya, U. R. (2018) · Journal of Applied Biomedicine · doi:10.1016/j.bbe.2018.05.005 · Cited by 158
Proximity Forest: an effective and scalable distance-based classifier for time series
Lucas, B., Shifaz, A., Pelletier, C., O’Neill, L., Zaidi, N. A., (15827960), B. G., Petitjean, F., & (14480133), G. W. (2024) · Figshare · Cited by 147
Mid-infrared spectroscopy and authenticity problems in selected meats: a feasibility study
Al-Jowder, O., Kemsley, E. K., & Wilson, R. H. (1997) · Food Chemistry · doi:10.1016/s0308-8146(96)00289-0 · Cited by 140 · cited 1×
“Al-Jowder et al. (1997) described how the data is acquired from 60 independent samples using Fourier transform infrared (FTIR) spectroscopy with attenuated total reflectance (ATR) sampling.”
MethodPetitjean, F., Forestier, G., Webb, G. I., Nicholson, A. E., Chen, Y., & Keogh, E. (2015) · Knowledge and Information Systems · doi:10.1007/s10115-015-0878-8 · Cited by 132 · cited 1×
“Following Lucas et al. (2018); Forestier et al. (2017); Petitjean et al. (2016); Grabocka et al. (2014) we used the mean accuracy measure averaged over the 10 runs on the test set.”
MethodSelf-citationTime-Series Classification Methods: Review and Applications to Power Systems Data
Susto, G. A., Cenedese, A., & Terzi, M. (2017) · Elsevier eBooks · doi:10.1016/b978-0-12-811968-6.00009-7 · Cited by 132
Mehdiyev, N., Lahann, J., Emrich, A., Enke, D. L., Fettke, P., & Loos, P. (2017) · Procedia Computer Science · doi:10.1016/j.procs.2017.09.066 · Cited by 129 · cited 1×
“In Mehdiyev et al. (2017); Malhotra et al. (2018); Rajan and Thiagarajan (2018), an RNN auto-encoder was designed to first generate the time series then using the learned latent representation, they trained a classifier (such as SVM or Random Forest) on top of these representations to predict the…”
MethodWang, L., Wang, Z., & Liu, S. (2015) · Expert Systems with Applications · doi:10.1016/j.eswa.2015.08.055 · Cited by 123 · cited 3×
“Another sub task that has been at the center of recent studies is early time series classification (Wang et al., 2016a) where deep CNNs were modified to include an early classification of time series.”
BackgroundMethodA 1 TOPS/W Analog Deep Machine-Learning Engine With Floating-Gate Storage in 0.13 µm CMOS
Lu, J., Young, S. R., Arel, I., & Holleman, J. H. (2014) · IEEE Journal of Solid-State Circuits · doi:10.1109/jssc.2014.2356197 · Cited by 122 · cited 9×
“This step is very important for deep learning models whose architecture depends on the length of the input time series (such as a MLP) and for parallel computation over the GPUs.”
BackgroundInfluentialEvaluating Surgical Skills from Kinematic Data Using Convolutional Neural Networks
Fawaz, H. I., Forestier, G., Weber, J., Idoumghar, L., & Müller, P.-A. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-00937-3_25 · Cited by 121 · cited 8×
“…extensive experimental evaluation, deep learning for time series classification, unlike for computer vision and NLP tasks, still lacks a thorough study of data augmentation (Ismail Fawaz et al., 2018a; Forestier et al., 2017) and transfer learning (Ismail Fawaz et al., 2018c; Serrà et al., 2018).”
BackgroundMethodInfluentialSelf-citationTowards a Universal Neural Network Encoder for Time Series
Joan, S., Santiago, P., & Karatzoglou, A. (2018) · Frontiers in artificial intelligence and applications · doi:10.3233/978-1-61499-918-8-120 · Cited by 119
Model-based kernel for efficient time series analysis
Chen, H., Tang, F., Peter Tiňo, B., & Yao, X. (2013) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/2487575.2487700 · Cited by 108
Functional echo state network for time series classification
Ma, Q., Shen, L., Chen, W., Wang, J., Wei, J., & Yu, Z. (2016) · Information Sciences · doi:10.1016/j.ins.2016.08.081 · Cited by 102
Speeding up similarity search under dynamic time warping by pruning unpromising alignments
Silva, D. F., Giusti, R., Keogh, E., & Batista, G. E. A. P. A. (2018) · Data Mining and Knowledge Discovery · doi:10.1007/s10618-018-0557-y · Cited by 95 · cited 2×
“With the increase of temporal data availability (Silva et al., 2018), hundreds of TSC algorithms have been proposed since 2015 (Bagnall et al.”
BackgroundDeep Echo State Network (DeepESN): A Brief SurveyPreprint
Gallicchio, C., & Micheli, A. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1712.04323 · Cited by 91 · cited 2×
“Given the aforementioned limitations, a relatively recent type of recurrent architecture was proposed for time series: Echo State Networks (ESNs) (Gallicchio and Micheli 2017).”
BackgroundClassification of Time-Series Images Using Deep Convolutional Neural NetworksPreprint
Hatami, N., Gavet, Y., & Debayle, J. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1710.00886 · Cited by 89 · cited 2×
“…extraction method for hand engineering approaches is the transformation of time series into images using specific imaging methods such as Gramian fields (Wang and Oates, 2015b,a), recurrence plots (Hatami et al., 2017; Tripathy and Acharya, 2018) and Markov transition fields (Wang and Oates, 2015).”
MethodBinary Shapelet Transform for Multiclass Time Series Classification
Bostrom, A., & Bagnall, A. J. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-22729-0_20 · Cited by 85
Multiobjective Learning in the Model Space for Time Series Classification
Gong, Z., Chen, H., Yuan, B., & Yao, X. (2018) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2018.2789422 · Cited by 85 · cited 2×
“In Gong et al. (2018); Wang et al. (2016), a meta-learning evolutionary-based algorithm was proposed to construct an optimal ESN architecture for univariate and multivariate time series.”
BackgroundTime Series Classification Using Time Warping Invariant Echo State Networks
Tanisaro, P., & Heidemann, G. (2016) · International Conference on Machine Learning and Applications · doi:10.1109/icmla.2016.0149 · Cited by 79 · cited 13×
“Although ESNs were originally proposed for time series forecasting, Tanisaro and Heidemann (2016) proposed a variant of ESNs that uses directly the raw input time series and predicts a probability distribution over the class variables.”
BackgroundMethodInfluentialDaubechies wavelets and Mathematica
Rowe, A. C. H., & Abbott, P. C. (1995) · Computers in Physics · doi:10.1063/1.168556 · Cited by 76
Spatio-Temporal Neural Networks for Space-Time Series Forecasting and Relations Discovery
Ziat, A., Delasalles, E., Denoyer, L., & Gallinari, P. (2017) · Proceedings · doi:10.1109/icdm.2017.80 · Cited by 76 · cited 1×
“For spatio-temporal series forecasting problems, such as meteorology and oceanography, DNNs were proposed in Ziat et al. (2017).”
BackgroundGCRNN: Group-Constrained Convolutional Recurrent Neural Network
Lin, S., & Runger, G. C. (2017) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2017.2772336 · Cited by 73 · cited 2×
“We mention one final type of hybrid architectures that showed promising results for the TSC task on the UCR/UEA archive datasets, where mainly CNNs were combined with other types of architectures such as Gated Recurrent Units (Lin and Runger, 2018) and the”
MethodTime-series modeling with undecimated fully convolutional neural networksPreprint
Mittelman, R. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1508.00317 · Cited by 67 · cited 1×
“A generative CNN-based model was proposed in Wang et al. (2016b); Mittelman (2015) where the authors introduced a deconvolutional operation followed by an upsampling technique that helps in reconstructing a multivariate time series.”
MethodGallicchio, C., & Micheli, A. (2018) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2018.8489464 · Cited by 67
Time-series classification with COTE: The collective of transformation-based ensembles
Bagnall, A. J., Lines, J., Hills, J., & Bostrom, A. G. (2016) · IEEE International Conference on Data Engineering (ICDE) · doi:10.1109/icde.2016.7498418 · Cited by 63
A Deep Reinforcement Learning Approach for Early Classification of Time Series
Martinez, C., Perrin, G., Ramasso, E., & Rombaut, M. (2018) · European Signal Processing Conference (EUSIPCO) · doi:10.23919/eusipco.2018.8553544 · Cited by 62 · cited 1×
“More recently, a deep reinforcement learning approach was also proposed for the early TSC task (Martinez et al., 2018).”
BackgroundWang, Z., & Oates, T. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1509.07481 · Cited by 60 · cited 1×
“…extraction method for hand engineering approaches is the transformation of time series into images using specific imaging methods such as Gramian fields (Wang and Oates, 2015b,a), recurrence plots (Hatami et al., 2017; Tripathy and Acharya, 2018) and Markov transition fields (Wang and Oates, 2015).”
MethodFeasibility of an AI-Based Measure of the Hand Motions of Expert and Novice Surgeons
Uemura, M., Tomikawa, M., Miao, T., Souzaki, R., Ieiri, S., Akahoshi, T., Lefor, A. K., & Hashizume, M. (2018) · Computational and Mathematical Methods in Medicine · doi:10.1155/2018/9873273 · Cited by 59
Model metric co-learning for time series classification
Chen, H., Tang, F., Peter Tiňo, B., Cohn, A. G., & Yao, X. (2015) · White Rose Research Online (University of Leeds, The University of Sheffield, University of York) · Cited by 52
Time Series Classification by Sequence Learning in All-Subsequence Space
Nguyen, T. L., Gsponer, S., & Ifrim, G. (2017) · IEEE International Conference on Data Engineering (ICDE) · doi:10.1109/icde.2017.142 · Cited by 48
A Deep Transfer Learning Approach for Improved Post-Traumatic Stress Disorder Diagnosis
Banerjee, D., Islam, K. A., Mei, G., Xiao, L., Zhang, G., Xu, R., Ji, S., & Jiang, L. (2017) · Proceedings · doi:10.1109/icdm.2017.10 · Cited by 48
A Generative Modeling Approach to Limited Channel ECG Classification
Rajan, D., & Thiagarajan, J. J. (2018) · doi:10.1109/embc.2018.8512757 · Cited by 46
Convolutional neural network with multi-task learning scheme for acoustic scene classification
Nwe, T. L., Dat, T. H., & Ma, B. (2017) · Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) · doi:10.1109/apsipa.2017.8282241 · Cited by 44 · cited 2×
“, 2018) to acoustic scene classification (Nwe et al., 2017) and cyber-security (Susto et al.”
BackgroundLiu, G., Wang, D., Wang, M., Zhu, C., & Wang, M. (2018) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2018.2798565 · Cited by 42
Large, J., Lines, J., & Bagnall, A. J. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1710.09220 · Cited by 41
A Run Length Transformation for Discriminating Between Auto Regressive Time Series
Bagnall, A. J., & Janacek, G. J. (2013) · Journal of Classification · doi:10.1007/s00357-013-9135-6 · Cited by 39
Applied Gaussian Process in Optimizing Unburned Carbon Content in Fly Ash for Boiler Combustion
Wang, C. L., Liu, Y., Everson, R., Rahat, A. A.-A. M., & Zheng, S. (2017) · Mathematical Problems in Engineering · doi:10.1155/2017/6138930 · Cited by 32 · cited 18×
“In Wang et al. (2017b); Geng and Luo (2018), an MLP was designed to learn from scratch a discriminative time series classifier.”
BackgroundMethodResultInfluentialInternational conference on machine vision
(2007) · International Conference on Machine Vision · doi:10.1109/icmv.2007.4469255 · Cited by 30
Earliness-Aware Deep Convolutional Networks for Early Time Series ClassificationPreprint
Wang, W., Chen, C., Wang, W., Rai, P., & Carin, L. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1611.04578 · Cited by 29
Dau, H. A., Silva, D. F., Petitjean, F., Forestier, G., Bagnall, A. J., & Keogh, E. (2017) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata.2017.8258009 · Cited by 26
Self-citationCost-Sensitive Convolution based Neural Networks for Imbalanced Time-Series ClassificationPreprint
Geng, Y., & Luo, X. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1801.04396 · Cited by 23
Generalized Dynamic Time Warping: Unleashing the Warping Power Hidden in Point-Wise Distances
Neamtu, R., Ahsan, R., Rundensteiner, E. A., Sárközy, G. N., Keogh, E., Dau, H. A., Nguyen, C., & Lovering, C. (2018) · IEEE International Conference on Data Engineering (ICDE) · doi:10.1109/icde.2018.00054 · Cited by 23 · cited 2×
“In this context, this paper targets the following open questions:What is the current state-of-the-art DNN for TSC? Is there a current DNN approach that reaches stateof-the-art performance for TSC and is less complex than HIVE-COTE? What type of DNN architectures works best for the TSC task? How does the random initial…”
BackgroundA Literature Survey Of Early Time Series Classification And Deep Learning
Santos, T., & Kern, R. (2017) · Zenodo (CERN European Organization for Nuclear Research) · doi:10.5281/zenodo.495150 · Cited by 22
Time Series Classification in Reservoir- and Model-Space
Aswolinskiy, W., Reinhart, F., & Steil, J. J. (2017) · Neural Processing Letters · doi:10.1007/s11063-017-9765-5 · Cited by 22
Time Series Classification in Reservoir- and Model-Space: A Comparison
Aswolinskiy, W., Reinhart, F., & Steil, J. J. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-46182-3_17 · Cited by 20
A Cycle Deep Belief Network Model for Multivariate Time Series Classification
Wang, S., Hua, G., Hao, G., & Xie, C. (2017) · Mathematical Problems in Engineering · doi:10.1155/2017/9549323 · Cited by 20
Improving time series similarity measures by integrating preprocessing steps
Höppner, F. (2017) · Data Mining and Knowledge Discovery · doi:10.1007/s10618-016-0490-x · Cited by 17 · cited 9×
“Despite the fact that a huge number of parameters risks overfitting (Zhang et al., 2017) the relatively small train set in the UCR/UEA archive, our experiments showed that not only DNNs are able to significantly outperform the NN-DTW, but are also able to achieve results that are not significantly different than COTE…”
MethodInfluentialChouikhi, N., Ammar, B., & Alimi, A. M. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1804.08996 · Cited by 16 · cited 2×
“Other studies such as in Aswolinskiy et al. (2017); Bianchi et al. (2018); Chouikhi et al. (2018); Ma et al. (2016) used self-predict modeling for time series classification where ESNs were first used to re-construct the time series and then the learned representation in the reservoir space was…”
BackgroundMethodWang, Z., Song, W., Liu, L., Zhang, F., Xue, J., Ye, Y., Fan, M. Y., & Xu, M. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1610.07258 · Cited by 13 · cited 3×
“Another sub task that has been at the center of recent studies is early time series classification (Wang et al., 2016a) where deep CNNs were modified to include an early classification of time series.”
BackgroundMethodModel-Based Time Series Classification
Kotsifakos, A., & Papapetrou, P. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-12571-8_16 · Cited by 9
Research works printed but not linked: 2
- Che Z, He X, Xu K, Liu Y (2017b) DECADE: a deep metric learning model for multivariate time series. In: KDD workshop on mining and learning from time series
- Ismail Fawaz H, Forestier G, Weber J, Idoumghar L, Muller PA (2018c) Transfer learning for time series classification. In: IEEE international conference on big data, pp 1367–1376 · DOI · Paper page
Cited by
Sorted by citations
A Transformer-based Framework for Multivariate Time Series Representation Learning
Zerveas, G., Jayaraman, S., Patel, D., Bhamidipaty, A., & Eickhoff, C. (2021) · Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining · doi:10.1145/3447548.3467401 · Cited by 1,278
Transformers in Time Series: A Survey
Wen, Q., Zhou, T., Zhang, C., Chen, W., Ma, Z., Yan, J., & Sun, L. (2023) · Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2023/759 · Cited by 1,260
Tuli, S., Casale, G., & Jennings, N. R. (2022) · Proceedings of the VLDB Endowment · doi:10.14778/3514061.3514067 · Cited by 1,476
Mamba: Linear-Time Sequence Modeling with Selective State Spaces
Gu, A., & Dao, T. (2023) · arXiv · doi:10.48550/arxiv.2312.00752 · Cited by 1,579
Dempster, A., Petitjean, F., & Webb, G. I. (2020) · Data Mining and Knowledge Discovery · doi:10.1007/s10618-020-00701-z · Cited by 1,165
“A kernel is convolved with an input time series through a sliding dot product operation, to produce a featuremapwhich is, in turn, used as the basis for classification (see Ismail Fawaz et al. 2019a).”
BackgroundMethodInfluential
Metadata
- Authors
- Ismail Fawaz, H., Forestier, G., Weber, J., Idoumghar, L., & Muller, P.-A.
- Affiliations
- Université de Haute-Alsace (FR)
- Venue
- Data Mining and Knowledge Discovery
- Published
- 2019-03-02
- Volume
- 33
- Issue
- 4
- Pages
- 917-963
- ISSN
- 1384-5810 (ISSN-L)
- 1573-756X
- OpenAlex
- W2892035503
- Cited by
- 3,342
- References
- 149
- Citations by year
- 2026: 385 · 2025: 493 · 2024: 507 · 2023: 517 · 2022: 527 · 2021: 494 · 2020: 328 · 2019: 85
- FWCI
- 227.10
- Type
- journal article
- Language
- en
- Open access
- bronze
- doi.org
- Locations
- Data Mining and Knowledge Discovery (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- HAL Portal Artxiker (Hindustan Aeronautics Limited (India)) (submittedVersion, other-oa)
- HAL (submittedVersion, other-oa)
- arXiv (Cornell University)
- Funders
- Agence Nationale de la Recherche (ANR-17-CE23-0015)
- Topics
- Physical Sciences › Computer Science › Signal Processing › Time Series Analysis and Forecasting
- Physical Sciences › Computer Science › Signal Processing › Music and Audio Processing
- Physical Sciences › Computer Science › Artificial Intelligence › Neural Networks and Applications
- Keywords
- time series classification, deep neural network, deep learning architectures, convolutional neural networks, ResNet, multivariate time series, univariate time series
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
A language model drew the claims from the paper on 2026-10-09, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-09 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
