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 101–200 of 1,007
Explainable Deep Neural Networks for Multivariate Time Series Predictions
Assaf, R., & Schumann, A. (2019) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2019/932 · Cited by 103
“Deep neural networks such as convolutional neural networks (CNNs) [LeCun et al., 1995] are considered state-of-the-art for this task [Fawaz et al., 2018; Zheng et al., 2014; Zheng et al., 2016], this is mainly due to their ability to learn meaningful representations from the data without the need…”
BackgroundDeep Neural Network Ensembles for Time Series Classification
Ismail Fawaz, H., Forestier, G., Weber, J., Idoumghar, L., & Muller, P.-A. (2019) · 2019 International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2019.8852316 · Cited by 103
“All of these architectures were implemented in a common framework during our empirical study [19], containing originally 9 different deep learning approaches for TSC.”
BackgroundMethodInfluentialSelf-citationCWT Based Transfer Learning for Motor Imagery Classification for Brain computer Interfaces
Kant, P., Laskar, S. H., Hazarika, J., & Mahamune, R. (2020) · Journal of Neuroscience Methods · doi:10.1016/j.jneumeth.2020.108886 · Cited by 102
Temporal Convolutional Neural Network for the Classification of Satellite Image Time Series
Pelletier, C., Webb, G. I., & Petitjean, F. (2019) · Remote Sensing · doi:10.3390/rs11050523 · Cited by 122
GRATIS: GeneRAting TIme Series with diverse and controllable characteristics
Kang, Y., Hyndman, R. J., & Li, F. (2020) · Statistical Analysis and Data Mining The ASA Data Science Journal · doi:10.1002/sam.11461 · Cited by 114
Coşkuner, G., Jassim, M. S., Zontul, M., & Karateke, S. (2020) · Waste Management & Research The Journal for a Sustainable Circular Economy · doi:10.1177/0734242x20935181 · Cited by 100
“The multi-layer perceptron (MLP) is a class of ANN models that is applied to predict solutions to time series problems due to their stochastic input–output matching capabilities (Fawaz et al., 2019).”
Galić, I., Habijan, M., Leventić, H., & Romić, K. (2023) · Electronics · doi:10.3390/electronics12214411 · Cited by 116
Li, Y., Wang, Z., Zhao, T., Li, H., Jiang, J., & Ye, J. (2024) · TrAC Trends in Analytical Chemistry · doi:10.1016/j.trac.2024.117958 · Cited by 105
Molecular barcoding of native RNAs using nanopore sequencing and deep learningPreprint
Smith, M. A., Ersavas, T., Ferguson, J. M., Liu, H., Lucas, M. C., Begik, O., Bojarski, L., Barton, K., & Novoa, E. M. (2020) · Genome Research · doi:10.1101/gr.260836.120 · Cited by 96
“CNNs have been widely used in signal and time-series analysis problems, including speech recognition and electrical and optical signal coding-decoding (Ismail Fawaz et al. 2019).”
MethodTime–frequency time–space LSTM for robust classification of physiological signals
Pham, T. D. (2021) · Scientific Reports · doi:10.1038/s41598-021-86432-7 · Cited by 110
Application of Deep Learning Architectures for Satellite Image Time Series Prediction: A Review
Moskolaï, W. R., Abdou, W., Dipandà, A., & Kolyang (2021) · Remote Sensing · doi:10.3390/rs13234822 · Cited by 106
“For instance, in [1,12–14], the authors surveyed the use of ML and DL techniques for time series analysis and forecasting.”
BackgroundGündüz, H. (2021) · Financial Innovation · doi:10.1186/s40854-021-00243-3 · Cited by 96
A Survey on Time-Series Pre-Trained Models
Ma, Q., Liu, Z., Zheng, Z., Huang, Z., Zhu, S., Yu, Z., & Kwok, J. T.-Y. (2024) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2024.3475809 · Cited by 133
“1) Time-Series Classification: In time-series classification [41], a labeled time series dataset is used to train a clas-sifier, which can then be used to classify unseen samples.”
MethodA novel framework for detecting social bots with deep neural networks and active learning
Wu, Y., Fang, Y., Shang, S., Jin, J., Wei, L., & Wang, H. (2020) · Knowledge-Based Systems · doi:10.1016/j.knosys.2020.106525 · Cited by 95
Westermann, P., Welzel, M., & Evins, R. (2020) · Applied Energy · doi:10.1016/j.apenergy.2020.115563 · Cited by 101
Animal behavior classification via deep learning on embedded systems
Arablouei, R., Wang, L., Currie, L., Yates, J., Alvarenga, F. A. P., & Bishop-Hurley, G. J. (2023) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2023.107707 · Cited by 94
Chakraborty, D., Mondal, J., Barua, H. B., & Bhattacharjee, A. (2023) · Renewable energy focus · doi:10.1016/j.ref.2023.01.006 · Cited by 94
“Since, in general meteorological data can be time series in nature learning based methods can be employed in some way or another [4].”
BackgroundPrognostics and Health Management of Industrial Assets: Current Progress and Road Ahead
Biggio, L., & Kastanis, I. (2020) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2020.578613 · Cited by 114
“Few attempts, however, have been made to extend these approaches to time-series data [see for example (Fawaz et al., 2019), (Guillemé et al.”
BackgroundBREIZHCROPS: A TIME SERIES DATASET FOR CROP TYPE MAPPING
Rußwurm, M., Pelletier, C., Zollner, M., Lefèvre, S., & Körner, M. (2020) · The international archives of the photogrammetry, remote sensing and spatial information sciences/International archives of the photogrammetry, remote sensing and spatial information sciences · doi:10.5194/isprs-archives-xliii-b2-2020-1545-2020 · Cited by 115
“InceptionTime stacks three Inception modules where each convolutional filter has a hidden vector dimensionality of H = 128 .”
BackgroundMethodInfluentialTiyasha, T., Tung, T. M., & Yaseen, Z. M. (2021) · Natural Resources Research · doi:10.1007/s11053-021-09922-5 · Cited by 92
Price graphs: Utilizing the structural information of financial time series for stock prediction
Wu, J., Xu, K., Chen, X., Li, S., & Zhao, J. (2021) · Information Sciences · doi:10.1016/j.ins.2021.12.089 · Cited by 95
Trend attention fully convolutional network for remaining useful life estimation
Fan, L., Chai, Y., & Chen, X. (2022) · Reliability Engineering & System Safety · doi:10.1016/j.ress.2022.108590 · Cited by 93
Khan, M., Wang, H., Riaz, A., El-Fatyany, A., & Karim, S. (2021) · The Journal of Supercomputing · doi:10.1007/s11227-020-03560-z · Cited by 99
“, (Um, y(Um))} , the goal is to find a function f , which is a classifier or model, so that f (U) = y(U) and for time series U ∉ [24].”
BackgroundSelf-supervised Learning for Semi-supervised Time Series Classification
Jawed, S., Grabocka, J., & Schmidt-Thieme, L. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-47426-3_39 · Cited by 89
A Hybrid Deep Learning Approach for Replay and DDoS Attack Detection in a Smart City
Elsaeidy, A. A., Jamalipour, A., & Munasinghe, K. S. (2021) · IEEE Access · doi:10.1109/access.2021.3128701 · Cited by 88
“Critical difference diagrams are based on the Wilcoxon-Holm method to detect pairwise significance [49].”
MethodManiruzzaman, M., Hasan, M. A. M., Asai, N., & Shin, J. (2023) · IEEE Access · doi:10.1109/access.2023.3264266 · Cited by 88
A systematic review of neurophysiological sensing for the assessment of acute pain
Rojas, R. F., Brown, N. A. T., Waddington, G. S., & Goecke, R. (2023) · npj Digital Medicine · doi:10.1038/s41746-023-00810-1 · Cited by 93
A Survey on Deep Learning for Time-Series Forecasting
Mahmoud, A., & Mohammed, A. (2020) · Studies in big data · doi:10.1007/978-3-030-59338-4_19 · Cited by 99
Knowledge-driven Biometric Authentication in Virtual Reality
Mathis, F., Fawaz, H. I., & Khamis, M. (2020) · CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA) · doi:10.1145/3334480.3382799 · Cited by 86
“First, we show that human behavioural biometrics collected during knowledge-driven nat-ural asymmetrical bimanual cooperation [19] are promising for establishing an additional security layer in VR by applying state-of-the-art deep learning architectures for time series classification (TSC) [21].”
BackgroundMethodInfluentialConvTimeNet: A Pre-trained Deep Convolutional Neural Network for Time Series Classification
Kashiparekh, K., Narwariya, J., Malhotra, P., Vig, L., & Shroff, G. M. (2019) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2019.8852105 · Cited by 87
Polz, J., Chwala, C., Graf, M., & Kunstmann, H. G. (2020) · Atmospheric measurement techniques · doi:10.5194/amt-13-3835-2020 · Cited by 97
Self-Supervised Autoregressive Domain Adaptation for Time Series Data
Ragab, M., Eldele, E., Chen, Z., Wu, M., Kwoh, C. K., & Li, X. (2022) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2022.3183252 · Cited by 86
NLOS Detection using UWB Channel Impulse Responses and Convolutional Neural Networks
Stahlke, M., Kram, S., Mutschler, C., & Mahr, T. (2020) · International Conference on Localization and GNSS · doi:10.1109/icl-gnss49876.2020.9115498 · Cited by 83
“In literature three different CNN models have been employed for time series classification [28]: Fully convolutional network (FCN).”
MethodEnd-to-end deep representation learning for time series clustering: a comparative study
Lafabrègue, B., Weber, J., Gançarski, P., & Forestier, G. (2021) · Data Mining and Knowledge Discovery · doi:10.1007/s10618-021-00796-y · Cited by 89
“This makes them easy to use in various domain, such as image (Guo et al. 2017a; Xie et al. 2016), modelization (Sun et al. 2013), or time series (Fawaz et al. 2019).”
BackgroundInfluentialSelf-citationExplainable deep learning in healthcare: A methodological survey from an attribution view
Jin, D., Sergeeva, E., Weng, W., Chauhan, G., & Szolovits, P. (2022) · WIREs Mechanisms of Disease · doi:10.1002/wsbm.1548 · Cited by 98
FedGL: Federated graph learning framework with global self-supervision
Chen, C., Xu, Z., Hu, W., Zheng, Z., & Zhang, J. (2023) · Information Sciences · doi:10.1016/j.ins.2023.119976 · Cited by 104
Leveraging Hybrid Deep Learning Models for Enhanced Multivariate Time Series Forecasting
Mahmoud, A., & Mohammed, A. (2024) · Neural Processing Letters · doi:10.1007/s11063-024-11656-3 · Cited by 104
A novel validation framework to enhance deep learning models in time-series forecasting
Livieris, I. E., Stavroyiannis, S., Pintelas, E. G., & Pintelas, P. (2020) · Neural Computing and Applications · doi:10.1007/s00521-020-05169-y · Cited by 82
“Recently, Fawaz et al. [11] provided an excellent review, presenting a comprehensive overview of the application of deep learning approaches in various time-series domains.”
BackgroundMethodReplay Attack Detection in Smart Cities Using Deep Learning
Elsaeidy, A. A., Jagannath, N., Sanchis, A. G., Jamalipour, A., & Munasinghe, K. S. (2020) · IEEE Access · doi:10.1109/access.2020.3012411 · Cited by 82
“This local pooling introduces invariance to small disturbances in the activation result by taking the maximum value in a local pooling window [25].”
BackgroundMethodClassification of chaotic time series with deep learning
Boullé, N., Dallas, V., Nakatsukasa, Y., & Samaddar, D. (2019) · Physica D Nonlinear Phenomena · doi:10.1016/j.physd.2019.132261 · Cited by 80
Zhang, Y., Hou, Y., Ouyang, K., & Zhou, S. (2021) · Pattern Recognition · doi:10.1016/j.patcog.2021.108385 · Cited by 81
Silva, D. D., Sierla, S., Alahakoon, D., Osipov, E., Yu, X., & Vyatkin, V. (2020) · IEEE Industrial Electronics Magazine · doi:10.1109/mie.2019.2952165 · Cited by 86
“Deep Learning Deep learning [107] continues to be the most prominent recent develop ment in AI that encompasses feature engineering and feature representa tion into the machine learning process [108]–[111].”
BackgroundKaya, Y., KUNCAN, F., & Ertunç, H. M. (2022) · TURKISH JOURNAL OF ELECTRICAL ENGINEERING & COMPUTER SCIENCES · doi:10.55730/1300-0632.3909 · Cited by 80
Time-series pattern recognition in Smart Manufacturing Systems: A literature review and ontology
Farahani, M. A., McCormick, M. R., Gianinny, R., Hudacheck, F., Harik, R., Liu, Z., & Wuest, T. (2023) · Journal of Manufacturing Systems · doi:10.1016/j.jmsy.2023.05.025 · Cited by 80
“, xT ] is an ordered vector of real values with length T [31].”
BackgroundBlood Glucose Level Prediction: Advanced Deep-Ensemble Learning Approach
Nemat, H., Khadem, H., Eissa, M. R., Elliott, J., & Benaissa, M. (2022) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2022.3144870 · Cited by 85
Robust IoT time series classification with data compression and deep learning
Azar, J., Makhoul, A., Couturier, R., & Demerjian, J. (2020) · Neurocomputing · doi:10.1016/j.neucom.2020.02.097 · Cited by 79
Investigating the Problem of Cryptocurrency Price Prediction: A Deep Learning Approach
Pintelas, E. G., Livieris, I. E., Stavroyiannis, S., Kotsilieris, T., & Pintelas, P. (2020) · IFIP advances in information and communication technology · doi:10.1007/978-3-030-49186-4_9 · Cited by 78
“These networks have become very popular since they have been successfully applied on a wide range of applications and have shown remarkable performance on time series forecasting [5].”
BackgroundRiver Flooding Forecasting and Anomaly Detection Based on Deep Learning
Miau, S., & Hung, W.-H. J. (2020) · IEEE Access · doi:10.1109/access.2020.3034875 · Cited by 89
“So the CNN model can learn a representation from a large sequence of inputs that is most relevant to the prediction problem [47].”
MethodVaquerizo-Villar, F., Álvarez, D., Gozal, D., Gutiérrez‐Tobal, G. C., Barroso-García, V., Santamaría-Vázquez, E., del Campo, F., Gozal, D., & Hornero, R. (2021) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2020.3048901 · Cited by 78
“This agrees with a recent review of deep learning for time series classification (TSC), where CNN-based architectures achieved the highest performance for TSC in an experiment where more than 8000 deep-learning models were trained and assessed on 97 different time series datasets [22].”
BackgroundPrediction of the remaining useful life of cutting tool using the Hurst exponent and CNN-LSTM
Zhang, X., Lu, X. B., Li, W., & Wang, S. (2021) · The International Journal of Advanced Manufacturing Technology · doi:10.1007/s00170-020-06447-8 · Cited by 82
ADATIME: A Benchmarking Suite for Domain Adaptation on Time Series Data
Ragab, M., Eldele, E., Tan, W. L., Foo, C.-S., Chen, Z., Wu, M., Kwoh, C. K., & Li, X. (2023) · ACM Transactions on Knowledge Discovery from Data · doi:10.1145/3587937 · Cited by 81
“This diference in performance may be due to the fact that a more complex model such as 1D-ResNet can better take advantage of the larger size of the HHAR dataset, leading to improved performance [1].”
BackgroundGraph convolutional networks for traffic forecasting with missing values
Zuo, J., Zeitouni, K., Taher, Y., & García-Rodríguez, S. (2022) · Data Mining and Knowledge Discovery · doi:10.1007/s10618-022-00903-7 · Cited by 84
“In order to compare the forecasters over multiple datasets (Ismail Fawaz et al, 2019), we adopted the critical difference diagrams recommended by Demˇsar (2006) and used the Friedman test (Friedman, 1940) to reject the null hypothesis (i.e., check whether there are significant differences at all).”
MethodPham, T. D., Wårdell, K., Eklund, A., & Salerud, G. (2019) · IEEE/CAA Journal of Automatica Sinica · doi:10.1109/jas.2019.1911774 · Cited by 77
“Baseline full convolutional networks were proposed for time series classification [28].”
Bridging the gap between mechanistic biological models and machine learning surrogates
Gherman, I. M., Abdallah, Z. S., Pang, W., Gorochowski, T. E., Grierson, C., & Marucci, L. (2023) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1010988 · Cited by 81
Voice2Series: Reprogramming Acoustic Models for Time Series ClassificationPreprint
Yang, C.-H. H., Tsai, Y.-Y., & Chen, P. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2106.09296 · Cited by 76
“Recently, deep learning models have been utilized in time series (Fawaz et al., 2019) and demonstrated improved performance.”
MethodSemi-supervised learning for ECG classification without patient-specific labeled data
Zhai, X., Zhou, Z., & Tin, C. (2020) · Expert Systems with Applications · doi:10.1016/j.eswa.2020.113411 · Cited by 75
Deep Unsupervised Domain Adaptation with Time Series Sensor Data: A Survey
Shi, Y., Ying, X., & Yang, J. (2022) · Sensors · doi:10.3390/s22155507 · Cited by 85
A model fusion strategy for identifying aircraft risk using CNN and Att-BiLSTM
Zhou, D., Zhuang, X. D., Zuo, H., Cai, J., Zhao, X., & Xiang, J. (2022) · Reliability Engineering & System Safety · doi:10.1016/j.ress.2022.108750 · Cited by 75
Sakib, M., Mustajab, S., & Alam, M. (2024) · Cluster Computing · doi:10.1007/s10586-024-04684-0 · Cited by 92
Nguyen, X. A., Ljuhar, D., Pacilli, M., Nataraja, R. M., & Chauhan, S. (2019) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2019.05.008 · Cited by 76
Data Augmentation with Suboptimal Warping for Time-Series Classification
Kamycki, K., Kapuściński, T., & Oszust, M. (2019) · Sensors · doi:10.3390/s20010098 · Cited by 74
A machine learning approach for forecasting hierarchical time series
Mancuso, P., Piccialli, V., & Sudoso, A. M. (2021) · Expert Systems with Applications · doi:10.1016/j.eswa.2021.115102 · Cited by 87
“Indeed CNNs are well known for creating useful representations of time series automatically, being highly noise-resistant models, and being able to extract very informative, deep features, which are independent from time [13].”
BackgroundDeep Transfer Learning for Time Series Data Based on Sensor Modality Classification
Li, F., Shirahama, K., Nisar, M. A., Huang, X., & Grzegorzek, M. (2020) · Sensors · doi:10.3390/s20154271 · Cited by 74
Design of deep ensemble classifier with fuzzy decision method for biomedical image classification
Das, A., Mohapatra, S. K., & Mohanty, M. N. (2021) · Applied Soft Computing · doi:10.1016/j.asoc.2021.108178 · Cited by 76
Gültekın, Ö., Çinar, E. M., Özkan, K., & Yazıcı, A. T. (2022) · Expert Systems with Applications · doi:10.1016/j.eswa.2022.117055 · Cited by 80
Time series classification: nearest neighbor versus deep learning models
Jiang, W. (2020) · SN Applied Sciences · doi:10.1007/s42452-020-2506-9 · Cited by 78
“Furthermore, Fawaz et al. [17] gives a comprehensive review of deep learning models for time series classification.”
BackgroundMethodGeneralized Label Enhancement with Sample Correlations
Zheng, Q., Zhu, J., Tang, H., Liu, X., Li, Z., & Lu, H. (2021) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2021.3073157 · Cited by 73
“CD diagrams are calculated based on the Wilcoxon-Holm method [33].”
MethodUsing Siamese Neural Networks to Perform Cross-System Behavioral Authentication in Virtual Reality
Miller, R. A., Banerjee, N. K., & Banerjee, S. (2021) · IEEE Conference on Virtual Reality and 3D User Interfaces (VR) · doi:10.1109/vr50410.2021.00035 · Cited by 75
“We choose to use FCNs, as they provide the highest accuracy for within-system user identi-fication in Mathis et al. [43], and the second highest accuracy for classification on a variety of time-series tasks [17].”
MethodEfficient Shapelet Discovery for Time Series Classification
Li, G., Choi, B. K. K., Xu, J., Bhowmick, S. S., Chun, K. P., & Wong, G. L.-H. (2020) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2020.2995870 · Cited by 71
G.V Black dental caries classification and preparation technique using optimal CNN-LSTM classifier
Singh, P., & Sehgal, P. (2020) · Multimedia Tools and Applications · doi:10.1007/s11042-020-09891-6 · Cited by 72
Dong, S., Yu, T., Farahmand, H., & Mostafavi, A. (2020) · Computer-Aided Civil and Infrastructure Engineering · doi:10.1111/mice.12629 · Cited by 72
“Deep learning has been widely applied in time series sequences classification [63].”
MethodA spatio-temporal LSTM model to forecast across multiple temporal and spatial scales
O’Donncha, F., Hu, Y., Palmes, P., Burke, M., Filgueira, R., & Grant, J. (2022) · Ecological Informatics · doi:10.1016/j.ecoinf.2022.101687 · Cited by 86
A CNN-based approach for the estimation of canopy heights and wood volume from GEDI waveforms
Fayad, I., Ienco, D., Baghdadi, N. N., Gaetano, R., Álvares, C. A., Stape, J. L., Scolforo, H. F., & Maire, G. L. (2021) · Remote Sensing of Environment · doi:10.1016/j.rse.2021.112652 · Cited by 78
“When the GEDI signal is considered as a wave signal, one dimensional convolution (1D-CNN) can be directly applied on the raw data with the goal to leverage the information similarly to what is done for time series analysis (Fawaz et al., 2019).”
Unsupervised Deep Learning for IoT Time Series
Liu, Y., Zhou, Y., Yang, K., & Wang, X. (2023) · IEEE Internet of Things Journal · doi:10.1109/jiot.2023.3243391 · Cited by 81
“In contrast, they only investigate specific machine learning (ML) tasks, such as anomaly detection [12], [19]–[23], classification [24], [25], clustering [26]–[31] and prediction [32], [33].”
BackgroundFrom time-series to 2D images for building occupancy prediction using deep transfer learning
Sayed, A. N., Himeur, Y., & Bensaali, F. (2023) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2022.105786 · Cited by 71
Farahani, M. A., McCormick, M. R., Harik, R., & Wuest, T. (2024) · Robotics and Computer-Integrated Manufacturing · doi:10.1016/j.rcim.2024.102839 · Cited by 81
“9 https://pyts.readthedocs.io/en/stable/index.html MLP dl-4-tsc10 Optimization= AdaDelta, Loss= Entropy, Epochs= 1000, Batch=16, Learning rate = 0.1 YES GPU YES FCN dl-4-tsc Optimization= Adam, Loss= Entropy, Epochs= 1000, Batch=16, Learning rate = 0.001 YES GPU YES Encoder dl-4-tsc Optimization= Adam, Loss= Entropy,…”
BackgroundMethodInfluentialAssessment of Fatigue Using Wearable Sensors: A Pilot Study
Luo, H., Lee, P.-A., Clay, I., Jaggi, M., & Luca, V. D. (2020) · Digital Biomarkers · doi:10.1159/000512166 · Cited by 78
Gundry, L., Guo, S., Kennedy, G. F., Keith, J. M., Robinson, M. J., Gavaghan, D. J., Bond, A. M., & Zhang, J. (2021) · Chemical Communications · doi:10.1039/d0cc07549c · Cited by 70
A Systematic Review of Time Series Classification Techniques Used in Biomedical Applications
Wang, W. K., Chen, I.-Y., Hershkovich, L., Yang, J., Shetty, A., Singh, G., Jiang, Y., Kotla, A. V., Shang, Z., Yerrabelli, R., et al. (2022) · Sensors · doi:10.3390/s22208016 · Cited by 70
Sibilano, E., Brunetti, A., Buongiorno, D., Lassi, M., Grippo, A., Bessi, V., Micera, S., Mazzoni, A., & Bevilacqua, V. (2023) · Journal of Neural Engineering · doi:10.1088/1741-2552/acb96e · Cited by 74
“Compared with convolutional neural networks (CNNs) and recurrent neural networks (RNNs), which are the most extensively used architectures for time-series data classification [38], transformers [39] have shownhigher ability to deal with long-range dependencies and recognize patterns in sequences of data [40], as well…”
BackgroundMFGTN: A multi-modal fast gated transformer for identifying single trawl marine fishing vessel
Gu, Y., Hu, Z., Zhao, Y., Liao, J., & Zhang, W. (2024) · Ocean Engineering · doi:10.1016/j.oceaneng.2024.117711 · Cited by 70
Prediction of vascular aging based on smartphone acquired PPG signals
Dall’Olio, L., Curti, N., Remondini, D., Harb, Y. S., Asselbergs, F. W., Castellani, G., & Uh, H. (2020) · Scientific Reports · doi:10.1038/s41598-020-76816-6 · Cited by 70
KryptoOracle: A Real-Time Cryptocurrency Price Prediction Platform Using Twitter Sentiments
Mohapatra, S., Ahmed, N., & Alencar, P. (2019) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata47090.2019.9006554 · Cited by 69
“The state of the art time series machine learning algorithms include the modern deep learning algorithms such as RNNs and LSTMs [24], but unfortunately Spark does not provide deep learning libraries yet.”
BackgroundGarcia, G. R., Michau, G., Ducoffe, M., Gupta, J. S., & Fink, O. (2021) · Proceedings of the Institution of Mechanical Engineers Part O Journal of Risk and Reliability · doi:10.1177/1748006x21994446 · Cited by 69
“7 In the industry, however, for some complex systems, it is not possible to cover all possible types of fault modes and, therefore, similarly infeasible to collect representative samples to handle their detection in a supervised manner.”
BackgroundData-Driven Modeling of Pregnancy-Related Complications
Espinosa, C. A., Becker, M., Marić, I., Wong, R. J., Shaw, G. M., Gaudilliere, B. L., Aghaeepour, N., Stevenson, D. K., Stelzer, I. A., Peterson, L. S., et al. (2021) · Trends in Molecular Medicine · doi:10.1016/j.molmed.2021.01.007 · Cited by 74
Lopac, N., Hržić, F., Vuksanović, I. P., & Lerga, J. (2021) · IEEE Access · doi:10.1109/access.2021.3139850 · Cited by 70
“Several studies have recently considered the application of deep learning algorithms for time series classification [43], [44].”
BackgroundWang, C., & Liu, G. (2024) · Advanced Engineering Informatics · doi:10.1016/j.aei.2024.102357 · Cited by 74
MultiCNN-FilterLSTM: Resource-efficient sensor-based human activity recognition in IoT applications
Park, H., Kim, N., Lee, G. H., & Choi, J. K. (2022) · Future Generation Computer Systems · doi:10.1016/j.future.2022.09.024 · Cited by 72
Zhao, H., Duan, S., Liu, J., Sun, L., & Reymondin, L. (2021) · Remote Sensing · doi:10.3390/rs13142790 · Cited by 72
“In deep learning algorithms, the recurrent neural network (RNN) [17] and one-dimensional convolutional neural network (1D CNN) [18] have demonstrated excellent performance in the extraction of temporal features [19,20].”
BackgroundKetu, S., & Mishra, P. K. (2021) · Soft Computing · doi:10.1007/s00500-021-06490-x · Cited by 70
RetractedImproved Salp swarm algorithm for solving single-objective continuous optimization problems
Abed-alguni, B. H., Paúl, D., & Hammad, R. (2022) · Applied Intelligence · doi:10.1007/s10489-022-03269-x · Cited by 67
“1) to produce the Critical Difference diagram [81] in Fig.”
Time Series Classification: A Review of Algorithms and Implementations
Faouzi, J. (2024) · IntechOpen eBooks · doi:10.5772/intechopen.1004810 · Cited by 70
Transfer Learning on Small Datasets for Improved Fall Detection
Maray, N., Ngu, A. H. H., Ni, J., Debnath, M., & Wang, L. (2023) · Sensors · doi:10.3390/s23031105 · Cited by 72
“After that, they built a multichannel DNN [34] by fine-tuning the single-channel DNN for each channel on the target domain, and thus the final multichannel DNN can recognize the outputs from all channels on the target domain.”
Towards near real-time assessment of surgical skills: A comparison of feature extraction techniques
Anh, N. X., Nataraja, R. M., & Chauhan, S. (2019) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2019.105234 · Cited by 66
MTEX-CNN: Multivariate Time Series EXplanations for Predictions with Convolutional Neural Networks
Assaf, R., Giurgiu, I., Bagehorn, F., & Schumann, A. (2019) · Industrial Conference on Data Mining · doi:10.1109/icdm.2019.00106 · Cited by 72
“Deep neural networks (DNNs) are state-of-the-art in predictive tasks for temporal data [2], [3] and can learn meaningful representations from the data without the need for manual feature engineering.”
BackgroundStudy of the Few-Shot Learning for ECG Classification Based on the PTB-XL Dataset
Pałczyński, K., Śmigiel, S., Ledziński, D., & Bujnowski, S. (2022) · Sensors · doi:10.3390/s22030904 · Cited by 76
Analyzing Classification Performance of fNIRS-BCI for Gait Rehabilitation Using Deep Neural Networks
Hamid, H., Naseer, N., Nazeer, H., Khan, M. J., Khan, R. A., & Khan, U. S. (2022) · Sensors · doi:10.3390/s22051932 · Cited by 68
“The pooling layer is followed by a fully connected layer, as shown in Figure 6 in which each data point is treated as a single neuron that outputs the class scores, and each neuron is connected to all the neurons in the previous layer [62].”
BackgroundApplication of Deep Learning in Multitemporal Remote Sensing Image Classification
Cheng, X., Sun, Y., Zhang, W., Wang, Y., Cao, X., & Wang, Y. (2023) · Remote Sensing · doi:10.3390/rs15153859 · Cited by 82
“Filters can also be regarded as a general nonlinear transformation of time series [110].”
BackgroundRecognition Algorithms in E-Nose: A Review
Yang, X., Li, M., Ji, X., Chang, J., Deng, Z., & Meng, G. (2023) · IEEE Sensors Journal · doi:10.1109/jsen.2023.3302868 · Cited by 70
CNN-based classification of fNIRS signals in motor imagery BCI system
Ma, T., Wang, S., Xia, Y., Zhu, X., Evans, J. S., Sun, Y., & He, S. (2021) · Journal of Neural Engineering · doi:10.1088/1741-2552/abf187 · Cited by 68
“The task of classifying time series is collectively referred to as the time series classification (TSC) task [25].”
BackgroundMethodInfluential
Metadata
- Authors
- Ismail Fawaz, H., Forestier, G., Weber, J., Idoumghar, L., & Muller, P.-A.
- Affiliations
- Université de Haute-Alsace (FR)
- Venue
- Data Mining and Knowledge Discovery
- Published
- 2019-03-02
- Volume
- 33
- Issue
- 4
- Pages
- 917-963
- ISSN
- 1384-5810 (ISSN-L)
- 1573-756X
- OpenAlex
- W2892035503
- Cited by
- 3,342
- References
- 149
- Citations by year
- 2026: 385 · 2025: 493 · 2024: 507 · 2023: 517 · 2022: 527 · 2021: 494 · 2020: 328 · 2019: 85
- FWCI
- 227.10
- Type
- journal article
- Language
- en
- Open access
- bronze
- doi.org
- Locations
- Data Mining and Knowledge Discovery (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- HAL Portal Artxiker (Hindustan Aeronautics Limited (India)) (submittedVersion, other-oa)
- HAL (submittedVersion, other-oa)
- arXiv (Cornell University)
- Funders
- Agence Nationale de la Recherche (ANR-17-CE23-0015)
- Topics
- Physical Sciences › Computer Science › Signal Processing › Time Series Analysis and Forecasting
- Physical Sciences › Computer Science › Signal Processing › Music and Audio Processing
- Physical Sciences › Computer Science › Artificial Intelligence › Neural Networks and Applications
- Keywords
- time series classification, deep neural network, deep learning architectures, convolutional neural networks, ResNet, multivariate time series, univariate time series
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
A language model drew the claims from the paper on 2026-10-09, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-09 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
