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 401–500 of 1,007
Deep learning based classification of sheep behaviour from accelerometer data with imbalance
Turner, K. E., Thompson, A. N., Harris, I., Ferguson, M. B., & Sohel, F. A. (2022) · Information Processing in Agriculture · doi:10.1016/j.inpa.2022.04.001 · Cited by 39
RODAN: a fully convolutional architecture for basecalling nanopore RNA sequencing data
Neumann, D., Reddy, A. S. N., & Ben‐Hur, A. (2022) · BMC Bioinformatics · doi:10.1186/s12859-022-04686-y · Cited by 35
“Convolutional networks have emerged as an important technique for working with noisy one dimensional signals [9], and are therefore a good approach for decoding the signal generated by ONT data.”
BackgroundA Series-Based Deep Learning Approach to Lung Nodule Image Classification
Balcı, M. A., Batrancea, L. M., Akgüller, Ö., & Nichita, A. (2023) · Cancers · doi:10.3390/cancers15030843 · Cited by 37
SSI-LSTM network for adaptive operational modal analysis of building structures
Yun, D. Y., Shim, H. B., & Park, H. S. (2023) · Mechanical Systems and Signal Processing · doi:10.1016/j.ymssp.2023.110306 · Cited by 38
VTGAN: hybrid generative adversarial networks for cloud workload prediction
Maiyza, A. I., Korany, N. O., Banawan, K., Hassan, H. A., & Sheta, W. M. (2023) · Journal of Cloud Computing Advances Systems and Applications · doi:10.1186/s13677-023-00473-z · Cited by 38
“Deep learning approaches Due to the recent success of DL in various applications, several works employed DL approaches for time-series analysis and prediction [27].”
MethodWHEN: A Wavelet-DTW Hybrid Attention Network for Heterogeneous Time Series Analysis
Wang, J., Yang, C., Jiang, X., & Wu, J. (2023) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3580305.3599549 · Cited by 39
A shale gas production prediction model based on masked convolutional neural network
Zhou, W., Li, X., Qi, Z., Zhao, H., & Yi, J. (2023) · Applied Energy · doi:10.1016/j.apenergy.2023.122092 · Cited by 34
ECG-based emotion recognition using random convolutional kernel method
Fang, A., Pan, F., Yu, W., Yang, L., & He, P. (2024) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2023.105907 · Cited by 34
Empirical comparison of deep learning models for fNIRS pain decoding
Rojas, R. F., Joseph, C., Bargshady, G., & Ou, K. (2024) · Frontiers in Neuroinformatics · doi:10.3389/fninf.2024.1320189 · Cited by 34
Evaluation is key: a survey on evaluation measures for synthetic time series
Stenger, M., Leppich, R., Foster, I. T., Kounev, S., & Bauer, A. (2024) · Journal Of Big Data · doi:10.1186/s40537-024-00924-7 · Cited by 41
Hands-On Fundamentals of 1D Convolutional Neural Networks—A Tutorial for Beginner Users
Cacciari, I., & Ranfagni, A. (2024) · Applied Sciences · doi:10.3390/app14188500 · Cited by 43
Look into the LITE in deep learning for time series classification
Ismail-Fawaz, A., Devanne, M., Berretti, S., Weber, J., & Forestier, G. (2025) · International Journal of Data Science and Analytics · doi:10.1007/s41060-024-00708-5 · Cited by 41
“A comparative study in [30] shows that using convolutions, especially ResNet, outperforms other models that use multi-scale transformation or pooling layers with convolutions [8, 62].”
Self-citationTransFusion: Generating long, high fidelity time series using diffusion models with transformers
Sikder, M. F., Ramachandranpillai, R., & Heintz, F. (2025) · Machine Learning with Applications · doi:10.1016/j.mlwa.2025.100652 · Cited by 48
Imputation of clinical covariates in time series
Bertsimas, D., Orfanoudaki, A., & Pawlowski, C. (2020) · Machine Learning · doi:10.1007/s10994-020-05923-2 · Cited by 35
Deep Learning for Cardiologist-Level Myocardial Infarction Detection in Electrocardiograms
Gupta, A., Huerta, E. A., Zhao, Z., & Moussa, I. (2020) · World Congress on Medical Physics and Biomedical Engineering, September 7 - 12, 2009, Munich, Germany · doi:10.1007/978-3-030-64610-3_40 · Cited by 34
Data Augmentation for Deep Learning-Based ECG Analysis
Pan, Q., Li, X., & Fang, L. (2020) · Springer eBooks · doi:10.1007/978-981-15-3824-7_6 · Cited by 40
Zhang, H., & Fu, R. (2020) · Sensors · doi:10.3390/s20174887 · Cited by 35
Hao, W., Liu, L., Yang, X. “., Li, Y., & Byon, Y.-J. (2020) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2020.3033436 · Cited by 34
Learning dynamical systems in noise using convolutional neural networks
Mukhopadhyay, S., & Banerjee, S. (2020) · Chaos An Interdisciplinary Journal of Nonlinear Science · doi:10.1063/5.0009326 · Cited by 35
Offline and Online Learning of Signal Temporal Logic Formulae Using Decision Trees
Bombara, G., & Belta, C. A. (2021) · ACM Transactions on Cyber-Physical Systems · doi:10.1145/3433994 · Cited by 34
AI-aided on-chip nucleic acid assay for smart diagnosis of infectious disease
Sun, H. R., Xiong, L., Huang, Y., Chen, X., Yu, Y., Shao-zhen, Y., Dong, H., Yuan, J. Y., & Zhang, W. (2021) · Fundamental Research · doi:10.1016/j.fmre.2021.12.005 · Cited by 34
“Deep neural networks are usually hindered from time series forecasting since the data are typically nonlinear and highly dynamic [35] .”
Identifying Root-Cause Metrics for Incident Diagnosis in Online Service Systems
Wu, C., Zhao, N., Wang, L., Yang, X., Li, S., Zhang, M., Jin, X., Wen, X., Nie, X., Zhang, W., et al. (2021) · Proceedings/Proceedings - International Symposium on Software Reliability Engineering · doi:10.1109/issre52982.2021.00022 · Cited by 37
“As demonstrated in §II-B, despite the fact that some metrics perform abnormally before the incident occurs, the anomaly patterns are unimportant and could be neglected (for example, the decrease in CPU usage), and different anomaly patterns tend to show different explanatory power to root causes.”
Integration of PSO and Deep Learning for Trend Analysis of Meta-Verse
Veeraiah, V., Khan, H. Q., Kumar, A., Ahamad, S., Mahajan, A. A., & Gupta, A. (2022) · International Conference on Advance Computing and Innovative Technologies in Engineering (ICACITE) · doi:10.1109/icacite53722.2022.9823883 · Cited by 34
Ngamakeur, K., Yongchareon, S., Yu, J., & Islam, M. S. (2022) · Pervasive and Mobile Computing · doi:10.1016/j.pmcj.2022.101721 · Cited by 34
Classifying animal behavior from accelerometry data via recurrent neural networks
Wang, L., Arablouei, R., Alvarenga, F. A. P., & Bishop-Hurley, G. J. (2023) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2023.107647 · Cited by 42
Mozaffari, M. H., & Tay, L. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.10575 · Cited by 49
“…dimension size, but usually, dimensions up to three are common in different applications, for example, 1D CNN for signals and time series (Ismail Fawaz et al., 2019), 2D for images (pixel-level) and matrices (Krizhevsky et al., 2017), and 3D for volumetric data (voxel-level) such as medical…”
Disjoint-CNN for Multivariate Time Series Classification
Foumani, N. M., Tan, C. W., & Salehi, M. (2021) · IEEE ... International Conference on Data Mining workshops · doi:10.1109/icdmw53433.2021.00099 · Cited by 34
Revin, I., Potemkin, V. A., Balabanov, N. R., & Nikitin, N. O. (2023) · Knowledge-Based Systems · doi:10.1016/j.knosys.2023.110483 · Cited by 33
Zhang, Z., Li, Y., Wang, G., Carranza, E. J. M., Yang, S., Sha, D., Fan, J., Zhang, X., & Dong, Y. (2023) · Mathematical Geosciences · doi:10.1007/s11004-023-10065-x · Cited by 33
Survey of Time Series Data Generation in IoT
Hu, C., Sun, Z., Li, C., Zhang, Y., & Xing, C. (2023) · Sensors · doi:10.3390/s23156976 · Cited by 42
IMU-Based Fitness Activity Recognition Using CNNs for Time Series Classification
Müller, P. N., Müller, A. J., Achenbach, P., & Göbel, S. P. (2024) · Sensors · doi:10.3390/s24030742 · Cited by 33
Multivariate time series classification with crucial timestamps guidance
Zhang, D., Gao, J., & Li, X. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2024.124591 · Cited by 35
Moglia, V., Johnson, O. A., Cook, G., de Kamps, M., & Smith, L. (2025) · BMC Medical Research Methodology · doi:10.1186/s12874-025-02473-w · Cited by 41
“Problems requiring analysis of longitudinal data occur in many applications, such as meteorology, finance, transportation, and audio processing [16, 17].”
DACAD: Domain Adaptation Contrastive Learning for Anomaly Detection in Multivariate Time Series
Darban, Z. Z., Yang, Y., Webb, G. I., Aggarwal, C. C., Wen, Q., Pan, S., & Salehi, M. (2025) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2025.3569909 · Cited by 46
“However, the time series domain differs greatly from the image and text data domains for which UDA methods are well developed [3], [4].”
End-to-end multivariate time series classification via hybrid deep learning architectures
Khan, M., Wang, H., Ngueilbaye, A., & El-Fatyany, A. (2020) · Personal and Ubiquitous Computing · doi:10.1007/s00779-020-01447-7 · Cited by 34
Red Alert for Power Leakage: Exploiting Intel RAPL-Induced Side Channels
Zhang, Z., Liang, S., Yao, F., & Gao, X. (2021) · ACM Asia Conference on Computer and Communications Security (ASIA CCS) · doi:10.1145/3433210.3437517 · Cited by 33
“One of the primary reasons is that RNN is designed mainly for time series prediction, and the other reason is that RNN usually suffers from the vanishing gradient problem more severely when training on long time series [7].”
BackgroundLearnable Dynamic Temporal Pooling for Time Series Classification
Lee, D., Lee, S., & Yu, H. (2021) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v35i9.17008 · Cited by 33
Peeking inside the Black Box: Interpreting Deep-learning Models for Exoplanet Atmospheric Retrievals
Yip, K. H., Changeat, Q., Νικολάου, Ν., Morvan, M., Edwards, B., Waldmann, I. P., & Tinetti, G. (2021) · The Astronomical Journal · doi:10.3847/1538-3881/ac1744 · Cited by 33
Identification of Crop Type Based on C-AENN Using Time Series Sentinel-1A SAR Data
Guo, Z., Qi, W., Huang, Y., Zhao, J., Yang, H., Koo, V. C., & Li, N. (2022) · Remote Sensing · doi:10.3390/rs14061379 · Cited by 33
de Godoy, R. V., Dwivedi, A., & Liarokapis, M. V. (2022) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2022.3196622 · Cited by 33
“In recent studies, they have been employed in executing several classification [12] and regression [13]–[15] tasks.”
MethodAbidi, A., Ienco, D., Abbes, A. B., & Farah, I. R. (2023) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2023.106152 · Cited by 33
Deep learning ensembles for accurate fog-related low-visibility events forecasting
Peláez-Rodríguez, C., Pérez‐Aracil, J., de Lopez-Diz, A., Casanova-Mateo, C., Fister, D., Jiménez-Fernández, S., & Salcedo‐Sanz, S. (2023) · Neurocomputing · doi:10.1016/j.neucom.2023.126435 · Cited by 35
Zhang, X., Peng, H., Zhang, J., & Wang, Y. (2022) · Expert Systems with Applications · doi:10.1016/j.eswa.2022.119073 · Cited by 35
Detecting Input Recognition Errors and User Errors using Gaze Dynamics in Virtual Reality
Sendhilnathan, N., Zhang, T., Lafreniere, B., Grossman, T., & Jonker, T. R. (2022) · ACM Symposium on User Interface Software and Technology (UIST) · doi:10.1145/3526113.3545628 · Cited by 32
“These kernels have been proven to be efective in learning discriminating features [6], which are crucial for a classifcation problem, in contrast to a recurrent neural network (RNN) architecture which is more often used to predict a value in a time series [34].”
BackgroundAlarcón, Á. S., Madrid, N. M., Seepold, R., & Ortega, J. A. (2023) · Frontiers in Neuroscience · doi:10.3389/fnins.2023.1155900 · Cited by 32
“Moreover, the duration of this window is ideal for later visualization of the results using the Grad-CAM technique.”
BackgroundInfluentialDyformer: A dynamic transformer-based architecture for multivariate time series classification
Yang, C., Wang, X., Yao, L., Long, G., & Xu, G. (2023) · Information Sciences · doi:10.1016/j.ins.2023.119881 · Cited by 32
TSGBench: Time Series Generation Benchmark
Ang, Y., Huang, Q., Bao, Y., Tung, A. K. H., & Huang, Z. (2023) · Proceedings of the VLDB Endowment · doi:10.14778/3632093.3632097 · Cited by 32
Degradation path approximation for remaining useful life estimation
Fan, L., Lin, W., Chen, X., Yin, H., & Chai, Y. (2024) · Advanced Engineering Informatics · doi:10.1016/j.aei.2024.102422 · Cited by 32
MTS2Graph: Interpretable multivariate time series classification with temporal evolving graphs
Younis, R., Hakmeh, A., & Ahmadi, Z. (2024) · Pattern Recognition · doi:10.1016/j.patcog.2024.110486 · Cited by 34
Jiang, M., Li, N., Li, M., Wang, Z., Tian, Y., Peng, K., Sheng, H., Li, H., & Li, Q. (2024) · Sensors · doi:10.3390/s24134126 · Cited by 36
“It was the most accurate deep learning model in the evaluation of 12 multivariate time series classification datasets [33].”
MethodSaifullah, S., Mercier, D., Lucieri, A., Dengel, A., & Ahmed, S. (2024) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2024.1236947 · Cited by 53
“The versatile applications of deep neural networks in areas such as image processing [3], object segmentation [4], document analysis [5], time series classification [6], time series predic-”
BackgroundSturm, V., Efrosinin, D., Öhlschuster, M., Gusterer, E., Drillich, M., & Iwersen, M. (2020) · Sensors · doi:10.3390/s20051484 · Cited by 32
“Deep learning approaches are shown to be promising but are still outperformed by distance based methods [26].”
BackgroundScoring and assessment in medical VR training simulators with dynamic time series classification
Vaughan, N., & Gabryś, B. (2020) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2020.103760 · Cited by 32
“The DL implementation architectures were matching with the open source time series classification framework [6].”
MethodResultInfluentialDeep Learning-Based Positioning of Visually Impaired People in Indoor Environments
Mahida, P. T., Shahrestani, S. A., & Cheung, H. (2020) · Sensors · doi:10.3390/s20216238 · Cited by 32
“In order to handle the shallow learning problem, the deep neural network (DNN) is implemented for the self-extraction of appropriate low and high-level features of given raw data [25–27].”
Methoddos Santos, M. C., Pereira, C. M. N. A., & Schirru, R. (2021) · Annals of Nuclear Energy · doi:10.1016/j.anucene.2021.108521 · Cited by 32
PETSC: pattern-based embedding for time series classification
Feremans, L., Čule, B., & Goethals, B. (2022) · Data Mining and Knowledge Discovery · doi:10.1007/s10618-022-00822-7 · Cited by 32
“High accuracy is also achieved by recent methods based on deep learning architectures, such as ResNet (Wang et al. 2017) and InceptionTime (Fawaz et al. 2019, 2020).”
MethodInfluentialSituational continuity-based air combat autonomous maneuvering decision-making
Zhang, J., Yu, Y.-F., Zheng, L., Yang, Q., Shi, G., & Wu, Y. (2022) · Defence Technology · doi:10.1016/j.dt.2022.08.010 · Cited by 31
Blood Glucose Level Time Series Forecasting: Nested Deep Ensemble Learning Lag Fusion
Khadem, H., Nemat, H., Elliott, D., & Benaissa, M. (2023) · Bioengineering · doi:10.3390/bioengineering10040487 · Cited by 36
Predicting cardiovascular disease risk using photoplethysmography and deep learning
Weng, W., Baur, S., Daswani, M., Chen, C., Harrell, L., Kakarmath, S. S., Jabara, M., Behsaz, B., McLean, C. Y., Matias, Y., et al. (2024) · PLOS Global Public Health · doi:10.1371/journal.pgph.0003204 · Cited by 46
Anik, B. M. T. H., Islam, Z., & Abdel-Aty, M. A. (2024) · Transportation Research Part C Emerging Technologies · doi:10.1016/j.trc.2024.104831 · Cited by 44
A review of time series forecasting and spatio-temporal series forecasting in deep learning
Yu, Q., Yang, G., Wang, X., Shi, Y., Feng, Y., & Liu, A. (2025) · The Journal of Supercomputing · doi:10.1007/s11227-025-07632-w · Cited by 45
A Deep Learning‐Based Approach to Forecast the Onset of Magnetic Substorms
Maimaiti, M., Kunduri, B. S. R., Ruohoniemi, J. M., Baker, J. B. H., & House, L. (2019) · Space Weather · doi:10.1029/2019sw002251 · Cited by 31
“…to nodes in preceding layers) and the subsequent max pooling layer (i.e., a downsampled version of the preceding layer) were added to reduce the input dimension while capturing some low ‐ level features from the input data, unlike the implementation of the ResNet model by Fawaz et al. (2019).”
MethodInfluentialApplication of deep learning to improve sleep scoring of wrist actigraphy
Haghayegh, S., Khoshnevis, S., Smolensky, M. H., & Diller, K. R. (2020) · Sleep Medicine · doi:10.1016/j.sleep.2020.05.008 · Cited by 30
Model-Based Design of Closed Loop Deep Brain Stimulation Controller using Reinforcement Learning
Gao, Q., Naumann, M., Jovanov, I., Lesi, V., Kamaravelu, K., Grill, W. M., & Pajić, M. (2020) · ACM/IEEE International Conference on Cyber-Physical Systems (ICCPS) · doi:10.1109/iccps48487.2020.00018 · Cited by 32
“on time-indexed data [37]–[39], existing methods mostly”
Performance Evaluation of Driving Behavior Identification Models through CAN-BUS Data
Azadani, M. N., & Boukerche, A. (2020) · IEEE Wireless Communications and Networking Conference · doi:10.1109/wcnc45663.2020.9120734 · Cited by 31
“…and evaluated in this study are briefly discussed in the following. a) CNN: Although CNN models, as an important type of neural networks, are not specifically designed to capture the time dependencies of the sequential data, they have shown efficient results for time series classification [22].”
Interpretable Detection of Partial Discharge in Power Lines with Deep Learning
Michau, G., Hsu, C.-C., & Fink, O. (2021) · Sensors · doi:10.3390/s21062154 · Cited by 31
“In particular, convolutional neural networks (CNN) have recently demonstrated very good performances for TS classification [23,24], forecasting [25], and anomaly detection [26].”
BackgroundMajstorović, J., Giffard‐Roisin, S., & Poli, P. (2021) · Journal of Geophysical Research Solid Earth · doi:10.1029/2020jb021566 · Cited by 31
“Therefore, the training depends on several hyperparameters: the size of the batch used to split the training data (the minibatch size), the optimization algorithm that updated model weights, the learning rate and momentum that control how weight are updated (Ismail Fawaz et al., 2019).”
MethodMoreira, L., Figueiredo, J., Vilas‐Boas, J. P., & Santos, C. P. (2021) · Machines · doi:10.3390/machines9080154 · Cited by 32
Melzi, P., Tolosana, R., Cecconi, A., García, A. S., Ortega, G. J., Jiménez‐Borreguero, L. J., & Vera-Rodríguez, R. (2021) · Scientific Reports · doi:10.1038/s41598-021-02179-1 · Cited by 34
“Each ECG is measured with a sample frequency of 500 Hz and lasts ten seconds.”
Deng, S., Guo, H., Yan, J., Zhu, D., Li, J., Qiao, M., & Xie, J. (2023) · Chemical Engineering Journal · doi:10.1016/j.cej.2023.144908 · Cited by 31
Amini, A., Dolatshahi, M., & Kerachian, R. (2023) · Water Resources Research · doi:10.1029/2022wr032789 · Cited by 34
“The LSTM and CNN-based networks are probably the most efficient and widely used DNNs to deal with long-term dependencies in time series (Barzegar et al., 2020; Ismail Fawaz et al., 2019).”
MethodChakraborty, S., & Stokes, E. C. (2023) · Remote Sensing of Environment · doi:10.1016/j.rse.2023.113818 · Cited by 38
Ienco, D., Gaetano, R., & Interdonato, R. (2023) · Neurocomputing · doi:10.1016/j.neucom.2023.127031 · Cited by 30
Deep Representation Learning: Fundamentals, Technologies, Applications, and Open Challenges
Payandeh, A., Baghaei, K. T., Fayyazsanavi, P., Ramezani, S. B., Chen, Z., & Rahimi, S. (2023) · IEEE Access · doi:10.1109/access.2023.3335196 · Cited by 49
“Examples of such sequential data include sentences in NLP tasks [265] and medical records in healthcare research [266], [267].”
BackgroundJayaprakash, V., You, J. B., Kanike, C., Liu, J., McCallum, C., & Zhang, X. (2024) · Environmental Science & Technology · doi:10.1021/acs.est.3c06447 · Cited by 32
Kwon, S., Jang, J., & Kim, C. O. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2024.125327 · Cited by 33
Yang, Y.-C., Dou, J., Merghadi, A., Liang, W., Dong, A., Xiong, D., & Zhang, L. (2024) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2024.3504241 · Cited by 30
Mekruksavanich, S., Phaphan, W., & Jitpattanakul, A. (2024) · Mathematical Biosciences & Engineering · doi:10.3934/mbe.2025004 · Cited by 31
Gurgul, V., Lessmann, S., & Härdle, W. K. (2025) · International Journal of Forecasting · doi:10.1016/j.ijforecast.2025.02.007 · Cited by 53
“The convolutional layers use sliding filters to learn temporal patterns, such as spikes, drops or specific shapes, with subsequent pooling and dense layers extracting dominant features and making predictions (see Ismail Fawaz, Forestier, Weber, Idoumghar and Muller, 2019).”
Al-Arnaout, Z., Zaki, C., Kotb, Y., AlAkkoumi, M., & Mostafa, N. (2025) · Scientific Reports · doi:10.1038/s41598-025-08582-2 · Cited by 30
“Segmentation method Time series segmentation involves dividing a time series into distinct segments or intervals 60 .”
Ragusa, E., Cambria, E., Zunino, R., & Gastaldo, P. (2019) · Electronics · doi:10.3390/electronics8070783 · Cited by 30
“Hence, deep networks play a major role in all the areas where the learning problem involves complex and stratified feature sets [18]; for example: healthcare [19], time series analysis [20], and object detection [21].”
BackgroundAn Advanced Deep Learning Model for Short-Term Forecasting U.S. Natural Gas Price and Movement
Livieris, I. E., Pintelas, E. G., Kiriakidou, N., & Stavroyiannis, S. (2020) · IFIP advances in information and communication technology · doi:10.1007/978-3-030-49190-1_15 · Cited by 30
“During the last decade, significant deep learning techniques have been successfully applied in a variety of time-series forecasting problems [8,13,17].”
BackgroundOptical process monitoring for Laser-Powder Bed Fusion (L-PBF)
Zouhri, W., Dantan, J., Häfner, B., Eschner, N., Homri, L., Lanza, G., Theile, O., & Schäfer, M. (2020) · CIRP journal of manufacturing science and technology · doi:10.1016/j.cirpj.2020.09.001 · Cited by 30
Neural Architecture Search for Time Series Classification
Rakhshani, H., Fawaz, H. I., Idoumghar, L., Forestier, G., Lepagnot, J., Weber, J., Brévilliers, M., & Müller, P.-A. (2020) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn48605.2020.9206721 · Cited by 33
“For domain agnostic TSC, ResNet is considered the state-of-the-art architecture when evaluated on the 85 datasets from the UCR archive [20].”
InfluentialSelf-citationModeling Time Series Data with Deep Learning: A Review, Analysis, Evaluation and Future Trend
Ang, J.-S., Ng, K.-W., & Chua, F.-F. (2020) · International Conference on Information Technology and Multimedia (ICIMU) · doi:10.1109/icimu49871.2020.9243546 · Cited by 30
“This outstanding baseline model is being implemented in many other researches [15], [17], [44].”
ResultPredicting COVID-19 Based on Environmental Factors With Machine Learning
Abdulkareem, A. B., Sani, N. S., Sahran, S., Alyessari, Z. A. A., Adam, A., Rahman, A. H. A., & Abdulkarem, A. B. (2021) · Intelligent Automation & Soft Computing · doi:10.32604/iasc.2021.015413 · Cited by 30
“The model is composed of multiple layers, which account for its high performance within minimum instants [13].”
Radar target recognition based on few-shot learning
Yang, Y., Zhang, Z., Mao, W., Li, Y., & Chen-gang, L. (2021) · Multimedia Systems · doi:10.1007/s00530-021-00832-3 · Cited by 30
Banihashemi, F., Weber, M., & Lang, W. (2021) · Building and Environment · doi:10.1016/j.buildenv.2021.108498 · Cited by 29
Similarity Learning based Few Shot Learning for ECG Time Series Classification
Gupta, P., Bhaskarpandit, S., & Gupta, M. (2021) · International Conference on Digital Image Computing: Techniques and Applications (DICTA) · doi:10.1109/dicta52665.2021.9647357 · Cited by 30
Yang, D., Karimi, H. R., & Gelman, L. (2022) · Sensors · doi:10.3390/s22020671 · Cited by 30
“Therefore, SoftPool and Mish activation functions are proposed to deal with these problems [7,8].”
BackgroundLe, W., Vorontsov, E., Romero, F. P., Seddik, L., Elsharief, M. M., Nguyen‐Tan, P. F., Roberge, D., Bahig, H., & Kadoury, S. (2022) · Scientific Reports · doi:10.1038/s41598-022-07034-5 · Cited by 30
dCAM: Dimension-wise Class Activation Map for Explaining Multivariate Data Series Classification
Boniol, P., Meftah, M., Remy, E., & Palpanas, T. (2022) · ACM SIGMOD International Conference on Management of Data (SIGMOD) · doi:10.1145/3514221.3526183 · Cited by 30
“A second architecture is the Residual Neural Network (ResNet) [27, 65].”
BackgroundMethodResultInfluentialSiamese Network-Based Transfer Learning Model to Predict Geogenic Contaminated Groundwaters
Cao, H., Xie, X., Shi, J., Jiang, G., & Wang, Y. (2022) · Environmental Science & Technology · doi:10.1021/acs.est.1c08682 · Cited by 30
Chen, Z.-Y., Sun, M., & Han, X.-X. (2022) · Journal of the Operational Research Society · doi:10.1080/01605682.2022.2101953 · Cited by 33
Montenegro, L., Abreu, M., Fred, A. L. N., & Machado, J. M. (2022) · Applied Sciences · doi:10.3390/app12157404 · Cited by 30
Model-centric transfer learning framework for concept drift detection
Wang, P., Jin, N., Davies, D., & Woo, W. L. (2023) · Knowledge-Based Systems · doi:10.1016/j.knosys.2023.110705 · Cited by 30
Locally Slope-based Dynamic Time Warping for Time Series Classification
Yuan, J., Lin, Q., Zhang, W., & Wang, Z. (2019) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3357384.3357917 · Cited by 31
“We also tried to compare LSDTW with the nine deep learning methods mentioned in [13].”
ResultWear monitoring in fine blanking processes using feature based analysis of acoustic emission signals
Unterberg, M., Voigts, H., Weiser, I. F., Feuerhack, A., Trauth, D., & Bergs, T. (2021) · Procedia CIRP · doi:10.1016/j.procir.2021.11.028 · Cited by 29
Motor imagery EEG signal classification with a multivariate time series approach
Velasco, I., Sipols, A. E., de Blas, C. S., Pastor, L., & Bayona, S. (2023) · BioMedical Engineering OnLine · doi:10.1186/s12938-023-01079-x · Cited by 29
Chen, W., Yu, C., Wang, H., Wang, Z., Yang, L., Wang, Y., Shi, W., & Shi, Y. (2023) · ACM Symposium on User Interface Software and Technology (UIST) · doi:10.1145/3586183.3606741 · Cited by 31
“There has already been extensive research on these types of problems [9, 22, 31, 35].”
Background
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
