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
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
Items 301–400 of 1,007
Nguyen-Trong, K., Vu, H. N., Trung, N. N., & Pham, C. (2021) · IEEE Sensors Journal · doi:10.1109/jsen.2021.3074642 · Cited by 45
Environment sound classification using an attention-based residual neural network
Tripathi, A. M., & Mishra, A. (2021) · Neurocomputing · doi:10.1016/j.neucom.2021.06.031 · Cited by 45
Classification of Tennis Shots with a Neural Network Approach
Ganser, A., Hollaus, B., & Stabinger, S. (2021) · Sensors · doi:10.3390/s21175703 · Cited by 47
“State-of-the-art deep neural networks are well suited for time series classification (TSC) [18] and give new possibilities in classifying tennis shots.”
BackgroundA Multimodal Deep Learning-Based Fault Detection Model for a Plastic Injection Molding Process
Kim, G., Choi, J. G., Ku, M., Cho, H., & Lim, S. (2021) · IEEE Access · doi:10.1109/access.2021.3115665 · Cited by 44
“Despite the improved performances of these algorithms, a deep learning approach is required to better understand data generated in the manufacturing industry because of the data’s large number of variables and the nature of dependencies, as previously mentioned [50].”
BackgroundMultilayer dynamic ensemble model for intensive care unit mortality prediction of neonate patients
Juraev, F., El–Sappagh, S., Abdukhamidov, E., Ali, F., & Abuhmed, T. (2022) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2022.104216 · Cited by 44
“For example, the patient's temperature is the most important feature for predicting if the neonate will die in the ICU, and this is medically confirmed knowledge [124].”
BackgroundUtilizing CNN-LSTM techniques for the enhancement of medical systems
Rayan, A., Alruwaili, S. H., Alaerjan, A., Alanazi, S., Taloba, A. I., Shahin, O. R., & Salem, M. (2023) · Alexandria Engineering Journal · doi:10.1016/j.aej.2023.04.009 · Cited by 47
“The most common, recognized, effective, and widely applied deep learning techniques are the LSTM and CNN networks [23].”
BackgroundSelf-Bidirectional Decoupled Distillation for Time Series Classification
Xiao, Z., Xing, H., Qu, R., Li, H., Feng, L., Zhao, B., & Yang, J. (2024) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2024.3360180 · Cited by 48
Shi, D., Ye, Y., Gillwald, M., & Hecht, M. (2021) · Mechanical Systems and Signal Processing · doi:10.1016/j.ymssp.2021.108217 · Cited by 43
Efficient Fine-Grained Website Fingerprinting via Encrypted Traffic Analysis with Deep Learning
Shen, M., Gao, Z., Zhu, L., & Xu, K. (2021) · International Workshop on Quality of Service · doi:10.1109/iwqos52092.2021.9521272 · Cited by 44
“Inspired by the recent advances in time series classification (TSC) [23], we employ CNNs to build a powerful classifier, as it can learn space invariant features in input space.”
MethodKarri, M., & Annavarapu, C. S. R. (2022) · Expert Systems with Applications · doi:10.1016/j.eswa.2022.119221 · Cited by 43
Diversify: A General Framework for Time Series Out-of-Distribution Detection and Generalization
Wang, L., Wang, J., Sun, X., Chen, Y., Ji, X., Yang, Q., & Xie, X. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2024.3355212 · Cited by 51
“More related work and details can be found in the following surveys [29]–[31].”
BackgroundAdvanced Stock Price Prediction with xLSTM-Based Models: Improving Long-Term Forecasting
Fan, X., Tao, C., & Zhao, J. (2024) · International Conference on Soft Computing & Machine Intelligence (ISCMI) · doi:10.1109/iscmi63661.2024.10851608 · Cited by 48
Energy-efficient deep learning inference on edge devices
Daghero, F., Pagliari, D. J., & Poncino, M. (2020) · Advances in computers · doi:10.1016/bs.adcom.2020.07.002 · Cited by 48
Automated Arrhythmia Detection Based on RR Intervals
Faust, O., Kareem, M., Ali, A., Ciaccio, E. J., & Acharya, U. R. (2021) · Diagnostics · doi:10.3390/diagnostics11081446 · Cited by 44
Bertsimas, D., Dunn, J., Gibson, E., & Orfanoudaki, A. (2022) · Machine Learning · doi:10.1007/s10994-021-06117-0 · Cited by 51
“1 3 Nemenyi critical diagrams for UCI experiments with simulated censoring In this section, we show Nemenyi Critical Diagrams for the results from the UCI datasets for different levels of censoring (Fawaz et al. 2019).”
MethodExplaining Any Time Series Classifier
Guidotti, R., Monreale, A., Spinnato, F., Pedreschi, D., & Giannotti, F. (2020) · 2020 IEEE Second International Conference on Cognitive Machine Intelligence (CogMI) · doi:10.1109/cogmi50398.2020.00029 · Cited by 46
LITE: Light Inception with boosTing tEchniques for Time Series Classification
Ismail-Fawaz, A., Devanne, M., Berretti, S., Weber, J., & Forestier, G. (2023) · IEEE International Conference on Data Science and Advanced Analytics (DSAA) · doi:10.1109/dsaa60987.2023.10302569 · Cited by 42
“Deep learning models have been proposed in the time series context for classification [10]–[14], clustering [15], averaging [16], representation learning [17]–[19], adversarial attacks [20], [21], etc. .”
BackgroundMethodSelf-citationSystematic evaluation of common natural language processing techniques to codify clinical notes
Tavabi, N., Singh, M., Pruneski, J. A., & Kiapour, A. M. (2024) · PLoS ONE · doi:10.1371/journal.pone.0298892 · Cited by 42
Label-Efficient Time Series Representation Learning: A Review
Eldele, E., Ragab, M., Chen, Z., Wu, M., Kwoh, C. K., & Li, X. (2024) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2024.3430236 · Cited by 56
“Unfortunately, the applicability of deep learning models in real-world scenarios is tied to the availability of large and labeled datasets, which are usually lacking for time series applications [1], [2].”
Papagiannopoulou, C., Parchen, R., Rubbens, P., & Waegeman, W. (2020) · Analytical Chemistry · doi:10.1021/acs.analchem.9b05806 · Cited by 46
Vo, K., Le, T., Rahmani, A. M., Dutt, N. D., & Cao, H. (2020) · Sensors · doi:10.3390/s20133757 · Cited by 42
Learning future terrorist targets through temporal meta-graphs
Campedelli, G. M., Bartulovic, M., & Carley, K. M. (2021) · Scientific Reports · doi:10.1038/s41598-021-87709-7 · Cited by 42
“However, CNNs can also handle unidimensional signals such as time series [39].”
BackgroundPredicting Opportune Moments to Deliver Notifications in Virtual Reality
Chen, K., Chang, Y.-J., & Chan, L. (2022) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3491102.3517529 · Cited by 48
“For the time series NN architecture that processes time-series sensor data, we initially explored two commonly used architectures for time series classifcation [15], including one-dimensional convolutional neural networks (1D-CNN), and a variant of the recurrent”
MethodLiang, G., Zhao, T., Shangguan, Z., Li, N., Wu, M., Lyu, J., Du, Y., & Wei, Y. (2022) · Mechanical Systems and Signal Processing · doi:10.1016/j.ymssp.2022.109197 · Cited by 42
Fully convolutional networks with shapelet features for time series classification
Ji, C., Hu, Y., Liu, S., Pan, L., Li, B., & Zheng, X. (2022) · Information Sciences · doi:10.1016/j.ins.2022.09.009 · Cited by 42
Learning multiple gaussian prototypes for open-set recognition
Liu, J., Tian, J. K., Han, W., Qin, Z., Fan, Y., & Shao, J. (2023) · Information Sciences · doi:10.1016/j.ins.2023.01.062 · Cited by 42
Multi-feature based network for multivariate time series classification
Du, M., Wei, Y., Zheng, X., & Ji, C. (2023) · Information Sciences · doi:10.1016/j.ins.2023.119009 · Cited by 43
Perbet, P., Guindon, L., Côté, J.-F., & Béland, M. (2024) · Remote Sensing of Environment · doi:10.1016/j.rse.2024.114107 · Cited by 44
Attention-Based Convolutional Neural Network for Earthquake Event Classification
Ku, B., Kim, G., Ahn, J.-K., Lee, J., & Ko, H. (2020) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2020.3014418 · Cited by 42
Ienco, D., Gbodjo, Y. J. E., Gaetano, R., & Interdonato, R. (2020) · IEEE Access · doi:10.1109/access.2020.3024133 · Cited by 41
Bouchabou, D., Nguyen, S. M., Lohr, C., Leduc, B., & Kanellos, I. (2021) · Communications in computer and information science · doi:10.1007/978-981-16-0575-8_9 · Cited by 41
Randomized outlier detection with trees
Buschjäger, S., Honysz, P.-J., & Morik, K. J. (2020) · International Journal of Data Science and Analytics · doi:10.1007/s41060-020-00238-w · Cited by 43
Huang, Z., Yang, C., Chen, X., Zhou, X., Chen, G., Huang, T., & Gui, W. (2021) · Applied Soft Computing · doi:10.1016/j.asoc.2021.107314 · Cited by 39
de Godoy, R. V., Lahr, G. J. G., Dwivedi, A., Reis, T. J. S., Polegato, P. H., Becker, M., Caurin, G. A. P., & Liarokapis, M. V. (2022) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2022.3192623 · Cited by 42
Mers, M., Yang, Z., Hsieh, Y., & Tsai, Y. J. (2022) · Transportation Research Record Journal of the Transportation Research Board · doi:10.1177/03611981221100521 · Cited by 46
“When compared with other ML methods, its inclusion of a ‘‘memory’’ hidden state has shown exceptional timeseries analysis abilities (14).”
MethodResultThe FreshPRINCE: A Simple Transformation Based Pipeline Time Series Classifier
Middlehurst, M., & Bagnall, A. J. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-09282-4_13 · Cited by 40
“InceptionTime builds on a residual network (ResNet), the prior best network for TSC [13].”
BackgroundGraph Time-series Modeling in Deep Learning: A Survey
Chen, H., & Eldardiry, H. (2023) · ACM Transactions on Knowledge Discovery from Data · doi:10.1145/3638534 · Cited by 43
Streamflow forecasting with deep learning models: A side-by-side comparison in Northwest Spain
Farfán, J. F., & Cea, L. (2024) · Earth Science Informatics · doi:10.1007/s12145-024-01454-9 · Cited by 46
“On the other hand, CNN are effective in the identification of features in a data set for prediction tasks without directly learning from lagged observations (Ismail Fawaz et al. 2019; Indolia et al. 2018).”
DTL-5G: Deep transfer learning-based DDoS attack detection in 5G and beyond networks
Farzaneh, B., Shahriar, N., Muktadir, A. H. A., Towhid, M. S., & Khosravani, M. S. (2024) · Computer Communications · doi:10.1016/j.comcom.2024.107927 · Cited by 40
“We followed [50, 51] to implement architectures as shown in Table 4.”
Deep learning for predicting rate-induced tipping
Huang, Y., Bathiany, S., Ashwin, P., & Boers, N. (2024) · Nature Machine Intelligence · doi:10.1038/s42256-024-00937-0 · Cited by 53
“We also experimented with multilayer perceptron 33 , long short-term memory 14,46 and self-attention 47 architectures for the DL model.”
A new multi-process collaborative architecture for time series classification
Xiao, Z., Xu, X., Zhang, H., & Szczerbicki, E. (2021) · Knowledge-Based Systems · doi:10.1016/j.knosys.2021.106934 · Cited by 42
From Sound Perception to Automatic Detection of Schizophrenia: An EEG-Based Deep Learning Approach
Barros, C., Roach, B. J., Ford, J. M., Pinheiro, A. P., & Silva, C. A. (2022) · Frontiers in Psychiatry · doi:10.3389/fpsyt.2021.813460 · Cited by 41
Manzella, F., Pagliarini, G., Sciavicco, G., & Stan, I. E. (2023) · Artificial Intelligence in Medicine · doi:10.1016/j.artmed.2022.102486 · Cited by 47
“A systematic treatment of deep learning methods is beyond the scope of this paper, but an up-do-date and comprehensive review on this topic can be found in Fawaz et al. [53], where the taxonomy for neural networks-based methods from Längkvist et al. [54] is extended.”
Deep learning for automated epileptiform discharge detection from scalp EEG: A systematic review
Nhu, D., Janmohamed, M., Antonic‐Baker, A., Perucca, P., O'Brien, T. J., Gilligan, A. K., Kwan, P., Tan, C. W., & Kuhlmann, L. (2022) · Journal of Neural Engineering · doi:10.1088/1741-2552/ac9644 · Cited by 42
“ResNet-TSC [71] stacks multiple convolutional layers with residual connections to ensure the small residuals do not vanish.”
Elastic similarity and distance measures for multivariate time series
Shifaz, A., Pelletier, C., Petitjean, F., & Webb, G. I. (2023) · Knowledge and Information Systems · doi:10.1007/s10115-023-01835-4 · Cited by 50
“A recent review of deep learning methods shows that architectures that use temporal convolutions show higher accuracy [41].”
BackgroundMethodAssessment of Bitcoin carbon footprint
Sarkodie, S. A., Amani, M. A., Ahmed, M. Y., & Owusu, P. A. (2023) · Sustainable Horizons · doi:10.1016/j.horiz.2023.100060 · Cited by 39
Temporal-Frequency Co-training for Time Series Semi-supervised Learning
Liu, Z., Ma, Q., Ma, P., & Wang, L. (2023) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v37i7.26072 · Cited by 41
“In recent years, time series classification algorithms have received much attention due to the powerful feature extraction capability of deep neural networks (Ismail Fawaz et al. 2019).”
BackgroundMethodClassification of cardiac disorders using weighted visibility graph features from ECG signals
Kutluana, G., & Türker, İ. (2023) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2023.105420 · Cited by 39
Dakheel, F., & Çevik, M. (2025) · Energies · doi:10.3390/en18112842 · Cited by 39
Yang, C., & Chang, P.-Y. (2020) · Mathematics · doi:10.3390/math8101784 · Cited by 41
“.”
A Deep Learning-Based Method for Forecasting Gold Price with Respect to Pandemics
Khani, M. M., Vahidnia, S., & Abbasi, A. (2021) · SN Computer Science · doi:10.1007/s42979-021-00724-3 · Cited by 53
A Deep Learning Strategy for Automatic Sleep Staging Based on Two-Channel EEG Headband Data
Casciola, A. A., Carlucci, S. K., Kent, B. A., Punch, A. M., Muszynski, M. A., Zhou, D. J., Kazemi, A., Mirian, M. S., Valerio, J., McKeown, M. J., et al. (2021) · Sensors · doi:10.3390/s21103316 · Cited by 39
Natural visibility encoding for time series and its application in stock trend prediction
Huang, Y., Mao, X., & Deng, Y. (2021) · Knowledge-Based Systems · doi:10.1016/j.knosys.2021.107478 · Cited by 42
1D convolutional neural networks for chart pattern classification in financial time series
Liu, L., & Si, Y. (2022) · The Journal of Supercomputing · doi:10.1007/s11227-022-04431-5 · Cited by 39
“4 CNN architecture (adapted from [11]) In causal convolution, the output neuron depends only on the inputs of earlier points.”
BackgroundMethodInfluentialTransfer Learning to adapt 5G AI-based Fingerprint Localization across Environments
Stahlke, M., Feigl, T., García, M. H. C., Stirling-Gallacher, R. A., Seitz, J., & Mutschler, C. (2022) · IEEE Vehicular Technology Conference · doi:10.1109/vtc2022-spring54318.2022.9860906 · Cited by 39
Personalized Deep Bi-LSTM RNN Based Model for Pain Intensity Classification Using EDA Signal
Pouromran, F., Lin, Y., & Kamarthi, S. V. (2022) · Sensors · doi:10.3390/s22218087 · Cited by 43
GPS Spoofing Detection Method for Small UAVs Using 1D Convolution Neural Network
Sung, Y.-H., Park, S.-J., Kim, D.-Y., & Kim, S. (2022) · Sensors · doi:10.3390/s22239412 · Cited by 44
“The training data were preprocessed by a 3 × 8 matrix with a window size of three channel data and eight ticks. by a 3 × 8 matrix with a window size of three channel data and eight ticks.”
MethodInfluentialTime and frequency-domain feature fusion network for multivariate time series classification
Lei, T., Li, J., & Yang, K. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2024.124155 · Cited by 39
An Effective Confidence-Based Early Classification of Time Series
Lv, J., Hu, X., Li, L., & Li, P. (2019) · IEEE Access · doi:10.1109/access.2019.2929644 · Cited by 38
“With the success of deep learning in various classification tasks, more and more deep learning models for TSC such as [22,23] have been proposed.”
BackgroundAutomated Cloud Based Long Short-Term Memory Neural Network Based SWE Prediction
Meyal, A., Versteeg, R. J., Alper, E., Johnson, D., Rodzianko, A., Franklin, M., & Wainwright, H. M. (2020) · Frontiers in Water · doi:10.3389/frwa.2020.574917 · Cited by 39
“Numerous statistical and machine learning approaches exist to predict time series behavior (Fawaz et al., 2019).”
BackgroundViton, F., Elbattah, M., Guérin, J.-L., & Dequen, G. (2020) · IEEE International Conference on Healthcare Informatics (ICHI) · doi:10.1109/ichi48887.2020.9374393 · Cited by 41
Sharan, R. V., Xiong, H., & Berkovsky, S. (2021) · Sensors · doi:10.3390/s21103434 · Cited by 45
Hierarchical Convolutional Neural Networks for Event Classification on PMU Measurements
Pavlovski, M., Alqudah, M., Dokic, T., Hai, A. A., Kezunović, M., & Zoran Obradovic, A. (2021) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2021.3115583 · Cited by 43
“Unlike traditional classification models, convolutional neural networks [36]-[37] include layers capable of performing convolution operations.”
BackgroundChen, L., Liang, X., Feng, Y., Zhang, L., Yang, J., & Liu, Z. (2022) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2022.3144171 · Cited by 37
“In the section, based on the large-scale simulation data from a related wargame platform, we conduct performance evaluation and application analysis of the proposed model by assessing it against the classical LSTM [25]–[27], FCN [28], [29], OctConv [30], and OctFCN models [31] for the online combat intention recogniti…”
MethodDriver Identification Through Heterogeneity Modeling in Car-Following Sequences
Ding, Z., Xu, D., Tu, C., Zhao, H., Moze, M., Aioun, F., & Guillemard, F. (2022) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2022.3151410 · Cited by 37
“…data can be formulated generally as a time series classification (TSC) problem, which has broad applications in speech recognition, signature verifi-cation, financial analysis etc. and a plethora of methods have been developed in literature [34], [35] that can be divided into three groups.”
MethodRandom Dilated Shapelet Transform: A New Approach for Time Series Shapelets
Guillaume, A., Vrain, C., & Elloumi, W. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-09037-0_53 · Cited by 38
“We use critical difference diagrams to display the mean ranks of objects, with cliques (formed by horizontal bars) computed using the Wilcoxon-Holm post-hoc analysis [9], with a p-value of 0.”
MethodBorra, D., Fantozzi, S., & Magosso, E. (2021) · Frontiers in Human Neuroscience · doi:10.3389/fnhum.2021.655840 · Cited by 36
Part. A: A review of the real-time sea-state estimation, using wave buoy analogy
Majidiyan, H., Wang, L., & Enshaei, H. (2022) · Ocean Engineering · doi:10.1016/j.oceaneng.2022.111684 · Cited by 36
Highly Accurate Gear Fault Diagnosis Based on Support Vector Machine
Abdul, Z. K., & Al‐Talabani, A. K. (2022) · Journal of Vibration Engineering & Technologies · doi:10.1007/s42417-022-00768-6 · Cited by 38
“In the training stage, the inputs are fed to the reservoir and the output of the reservoir (teacher output) will be fed to the output layer [7].”
BackgroundRodrigues, J., Liu, H., Folgado, D., Belo, D., Schultz, T., & Gamboa, H. F. S. (2022) · Biosensors · doi:10.3390/bios12121182 · Cited by 38
“In this work, we borrow an implemented critical difference method of [96] that uses the Wilcoxon–Holm test [97], which counteracts the problem of multiple comparisons and calculates pairwise significance between all methods evaluated.”
BackgroundMethodGaze-aware hand gesture recognition for intelligent construction
Wang, X., Veeramani, D., & Zhu, Z. (2023) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2023.106179 · Cited by 37
Breast cancer classification through multivariate radiomic time series analysis in DCE-MRI sequences
Prinzi, F., Orlando, A. A. M., Gaglio, S., & Vitabile, S. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2024.123557 · Cited by 37
Efficient Time Series Augmentation Methods
Liu, B., Zhang, Z., & Cui, R. (2020) · International Congress on Image and Signal Processing (CISP) · doi:10.1109/cisp-bmei51763.2020.9263602 · Cited by 40
“In recent years, deep learning has been increasingly used to solve time series related tasks, including time series classification [1], prediction [2], and anomaly detection [3].”
MethodDeep learning for supervised classification of temporal data in ecology
Capinha, C., Ceia‐Hasse, A., Kramer, A. M., & Meijer, C. (2021) · Ecological Informatics · doi:10.1016/j.ecoinf.2021.101252 · Cited by 37
Efficient class-specific shapelets learning for interpretable time series classification
Liang, Z., & Wang, H. (2021) · Information Sciences · doi:10.1016/j.ins.2021.03.063 · Cited by 37
Explainable AI for time series via Virtual Inspection Layers
Vielhaben, J., Lapuschkin, S., Montavon, G., & Samek, W. (2024) · Pattern Recognition · doi:10.1016/j.patcog.2024.110309 · Cited by 38
Head Pose Estimation Patterns as Deepfake Detectors
Becattini, F., Bisogni, C., Loia, V., Pero, C., & Hao, F. (2023) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/3612928 · Cited by 40
“To model time series, 1D convolutions have shown remarkable re-sults [22].”
Fernandes, W., Komati, K. S., & Gazolli, K. A. D. S. (2023) · Journal of Petroleum Exploration and Production Technology · doi:10.1007/s13202-023-01710-6 · Cited by 43
de Haro, C., Santos-Pulpón, V., Telías, I., Xifra‐Porxas, A., Subirá, C., Batlle, M., Fernández, R., Murias, G. E., Albaiceta, G. M., Fernández‐Gonzalo, S., et al. (2024) · Critical Care · doi:10.1186/s13054-024-04845-y · Cited by 36
Tavabi, N., Pruneski, J. A., Golchin, S., Singh, M., Sanborn, R. M., Heyworth, B. E., Landschaft, A., Kimia, A. A., & Kiapour, A. M. (2024) · Artificial Intelligence in Medicine · doi:10.1016/j.artmed.2024.102847 · Cited by 40
Cheng, M., He, W., Li, Z., Yang, G., & Zhang, H.-Y. (2024) · Isprs Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2024.09.002 · Cited by 41
Source Model Selection for Deep Learning in the Time Series Domain
Meiseles, A., & Rokach, L. (2020) · IEEE Access · doi:10.1109/access.2019.2963742 · Cited by 37
“Discriminative methods are also generally more accurate than generative methods for TSC [8].”
MethodInfluentialAutonomic performance prediction framework for data warehouse queries using lazy learning approach
Raza, B., Aslam, A., Sher, A., Malik, A. K., & Faheem, M. (2020) · Applied Soft Computing · doi:10.1016/j.asoc.2020.106216 · Cited by 36
Deep Learning for Accelerometric Data Assessment and Ataxic Gait Monitoring
Procházka, A., Dostál, O., Cejnar, P., Mohamed, H. I., Pavelek, Z., Vališ, M., & Vyšata, O. (2021) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2021.3051093 · Cited by 36
Baasch, G., Westermann, P., & Evins, R. (2021) · Energy and Buildings · doi:10.1016/j.enbuild.2021.110889 · Cited by 38
Stock Movement Prediction and Portfolio Management via Multimodal Learning with Transformer
Daiya, D., & Lin, C. (2021) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp39728.2021.9414893 · Cited by 36
QSAR Modeling Based on Conformation Ensembles Using a Multi-Instance Learning Approach
Zankov, D. V., Matveieva, M., Nikonenko, A., Ирекович, Н. Р., Baskin, I. I., Varnek, A. A., Полищук, П. Г., & Madzhidov, T. (2021) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.1c00692 · Cited by 40
Internet traffic matrix prediction with convolutional LSTM neural network
Jiang, W. (2021) · Internet Technology Letters · doi:10.1002/itl2.322 · Cited by 45
ClaSP - Time Series Segmentation
Schäfer, P., Ermshaus, A., & Leser, U. (2021) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3459637.3482240 · Cited by 37
“3482240 such as classication [4, 16], similarity search [28], or motif discovery [25].”
BackgroundResource-Aware Time Series Imaging Classification for Wireless Link Layer Anomalies
Bertalanič, B., Meža, M., & Fortuna, C. (2022) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2022.3149091 · Cited by 40
“[26] into additional subgroups, namely, models that use hand-engineering features and direct end-to-”
BackgroundLi, P., & Abdel-Aty, M. A. (2022) · Journal of Transportation Engineering Part A Systems · doi:10.1061/jtepbs.0000697 · Cited by 37
A comparative study of different machine learning methods for dissipative quantum dynamics
Rodríguez, L. E. H., Ullah, A., Espinosa, K. J. R., Dral, P. O., & Kananenka, A. A. (2022) · Machine Learning Science and Technology · doi:10.1088/2632-2153/ac9a9d · Cited by 37
Universal early warning signals of phase transitions in climate systems
Dylewsky, D., Lenton, T. M., Scheffer, M., Bury, T. M., Fletcher, C. G., Anand, M., & Bauch, C. T. (2023) · Journal of The Royal Society Interface · doi:10.1098/rsif.2022.0562 · Cited by 36
Yan, J., Wang, L., He, H., Liang, D., Song, W., & Han, W. (2022) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2022.3160617 · Cited by 35
“4) In addition, the similarity-measurement-based transfer learning may also enable DL to solve the problem of large-scale land-cover change detection [16].”
BackgroundAnomaly detection in streaming data: A comparison and evaluation study
Iglesias, F., Hartl, A., Zseby, T., & Zimek, A. (2023) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.120994 · Cited by 35
Multimodal 1D CNN for delamination prediction in CFRP drilling process with industrial robots
Choi, J. G., Kim, D. C., Chung, M., Lim, S., & Park, H. W. (2024) · Computers & Industrial Engineering · doi:10.1016/j.cie.2024.110074 · Cited by 35
Deep Learning and Implementations in Banking
Hassani, H., Huang, X., Silva, E. S., & Ghodsi, M. (2020) · Annals of Data Science · doi:10.1007/s40745-020-00300-1 · Cited by 40
A Multi-Sensor Data Fusion System for Laser Welding Process Monitoring
Deng, F., Yong-shen, H., Lu, S., Chen, Y., Chen, J., Hua, F., Zhang, J., Yang, Y., Hu, J., Lam, T. L., et al. (2020) · IEEE Access · doi:10.1109/access.2020.3015529 · Cited by 41
Chen, Z., & Gu, J. (2020) · IEEE Journal of Solid-State Circuits · doi:10.1109/jssc.2020.3021066 · Cited by 35
“Three conventional classification methods are being developed including the distance, model, and feature-based methods [22], [23].”
MethodFelizardo, L. K., Paiva, F. C. L., Graves, C. V., Matsumoto, É. Y., Costa, A. H. R., Del-Moral-Hernandez, E., & Brandimarte, P. (2022) · Expert Systems with Applications · doi:10.1016/j.eswa.2022.117259 · Cited by 35
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
