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 201–300 of 1,007
Cheng, W., Suganthan, P. N., & Katuwal, R. (2021) · Applied Soft Computing · doi:10.1016/j.asoc.2021.107826 · Cited by 65
Lee, M.-C., Chang, J.-W., Yeh, S., Chia, T.-L., Liao, J.-S., & Chen, X. (2022) · Neural Computing and Applications · doi:10.1007/s00521-021-06828-4 · Cited by 75
“…field of deep learning, recurrent neural network (RNN) [13], long short-term memory (LSTM) [14], and attention mechanism [15, 16] are particularly good at processing time series data, such as natural language processing, machine translation, speech recognition, and financial index prediction [17–19].”
BackgroundStochastic physics-informed neural ordinary differential equations
O'Leary, J., Paulson, J. A., & Mesbah, A. (2022) · Journal of Computational Physics · doi:10.1016/j.jcp.2022.111466 · Cited by 65
Performance enhancing techniques for deep learning models in time series forecasting
Fang, X., & Yuan, Z. (2019) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2019.07.011 · Cited by 65
Towards Low-Cost Sign Language Gesture Recognition Leveraging Wearables
Zhao, T., Liu, J., Wang, Y., Liu, H., & Chen, Y. J. (2019) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2019.2962760 · Cited by 65
“Those results prove that the ResNet as the fundamental multi-variate TSC is also suitable for our system, which not only provides the good performance without the procedure of extracting the features but also can take advantage of the transfer learning to significantly reduce the training effort to achieve decent perfo…”
MethodNetwork Anomaly Detection With Temporal Convolutional Network and U-Net Model
Mezina, A., Bürget, R., & Travieso, C. M. (2021) · IEEE Access · doi:10.1109/access.2021.3121998 · Cited by 67
“The detailed description of them can be found in [43].”
BackgroundOnline quality inspection of resistance spot welding for automotive production lines
Dai, W., Li, D., Zheng, Y., Wang, D., Tang, D., Wang, H., & Peng, Y. (2022) · Journal of Manufacturing Systems · doi:10.1016/j.jmsy.2022.04.008 · Cited by 71
Reinforcement Learning Based Dynamic Model Combination for Time Series Forecasting
Fu, Y., Wu, D., & Boulet, B. (2022) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v36i6.20618 · Cited by 67
“Existing time series forecasting methods can be mainly divided into two categories, namely, statistical methods and ML-based methods (Fawaz et al. 2019).”
MethodDetection of Corona Faults in Switchgear by Using 1D-CNN, LSTM, and 1D-CNN-LSTM Methods
Alsumaidaee, Y. A. M., Yaw, C. T., Koh, S. P., Kiong, T. S., Chen, C. P., Yusaf, T. F., Abdalla, A. N., Ali, K., & Raj, A. A. (2023) · Sensors · doi:10.3390/s23063108 · Cited by 67
Developing Machine Learning-Based Models for Railway Inspection
Yang, C., Sun, Y., Ladubec, C., & Liu, Y. (2020) · Applied Sciences · doi:10.3390/app11010013 · Cited by 64
“Recently some works have demonstrated deep neural networks, especially convolutional neural networks (CNN), for end-to-end time series classification [27,28].”
BackgroundTransfer Learning With Time Series Data: A Systematic Mapping Study
Weber, M., Auch, M., Doblander, C., Mandl, P., & Jacobsen, H. (2021) · IEEE Access · doi:10.1109/access.2021.3134628 · Cited by 67
Flah, M., Ragab, M., Lazhari, M., & Nehdi, M. L. (2022) · Automation in Construction · doi:10.1016/j.autcon.2022.104271 · Cited by 63
Cai, Y., Wang, H., Ye, H., Jin, Y., & Gao, W. (2023) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.119538 · Cited by 70
Vaquerizo-Villar, F., Gutiérrez‐Tobal, G. C., Merino, E. C., Álvarez, D., Gozal, D., del Campo, F., Gozal, D., & Hornero, R. (2023) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2023.107419 · Cited by 68
Zhang, Y., & Ying Lei, A. (2021) · Symmetry · doi:10.3390/sym13071186 · Cited by 63
Text Analysis for Psychology: Methods, Principles, and PracticesPreprint
Kennedy, B., Ashokkumar, A., Boyd, R. L., & Dehghani, M. (2021) · PsyArXiv (OSF Preprints) · doi:10.31234/osf.io/h2b8t · Cited by 62
Korkmaz, D., Açıkgöz, H., & Yıldız, C. (2021) · International Journal of Green Energy · doi:10.1080/15435075.2021.1875474 · Cited by 62
Deep learning methods evaluation to predict air quality based on Computational Fluid Dynamics
Jurado, X., Reiminger, N., Benmoussa, M., Vázquez, J., & Wemmert, C. (2022) · Expert Systems with Applications · doi:10.1016/j.eswa.2022.117294 · Cited by 64
Guo, F., Li, W., Jiang, P., Chen, F., & Liu, Y. (2022) · Materials · doi:10.3390/ma15124270 · Cited by 62
Causal Discovery from Temporal Data: An Overview and New Perspectives
Gong, C., Zhang, C., Yao, D., Bi, J., Li, W., & Xu, Y. (2024) · ACM Computing Surveys · doi:10.1145/3705297 · Cited by 96
Towards resource-frugal deep convolutional neural networks for hyperspectral image segmentation
Nalepa, J., Antoniak, M., Myller, M., Lorenzo, P. R., & Marcinkiewicz, M. (2020) · Microprocessors and Microsystems · doi:10.1016/j.micpro.2020.102994 · Cited by 63
IntelliO3-ts v1.0: a neural network approach to predict near-surface ozone concentrations in Germany
Kleinert, F., Leufen, L. H., & Schultz, M. G. (2021) · Geoscientific model development · doi:10.5194/gmd-14-1-2021 · Cited by 64
Deep learning based inverse model for building fire source location and intensity estimation
Kou, L., Wang, X., Guo, X., Zhu, J., & Zhang, H. (2021) · Fire Safety Journal · doi:10.1016/j.firesaf.2021.103310 · Cited by 61
Meng, T., Tao, Y., Chen, Z., Avila, J. R. S., Ran, Q., Shao, Y., Huang, R., Xie, Y., Zhao, Q., Zhang, Z., et al. (2021) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2021.3117367 · Cited by 64
CALDA: Improving Multi-Source Time Series Domain Adaptation With Contrastive Adversarial Learning
Wilson, G., Doppa, J. R., & Cook, D. J. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2023.3298346 · Cited by 67
Adaptive feature fusion for time series classification
Wang, T., Liu, Z., Zhang, T., Hussain, S. F., Waqas, M. M., & Li, Y. (2022) · Knowledge-Based Systems · doi:10.1016/j.knosys.2022.108459 · Cited by 59
Deep learning models for visibility forecasting using climatological data
Ortega, L. C., Otero, L. D., Solomon, M., Otero, C. E., & Fabregas, A. (2022) · International Journal of Forecasting · doi:10.1016/j.ijforecast.2022.03.009 · Cited by 65
Measuring service quality based on customer emotion: An explainable AI approach
Guo, Y., Li, Y., De, L., & Xu, S. X. (2023) · Decision Support Systems · doi:10.1016/j.dss.2023.114051 · Cited by 66
Explainable Multivariate Time Series Classification
Hsieh, T.-Y., Wang, S., Sun, Y., & Honavar, V. (2021) · ACM International Conference on Web Search and Data Mining (WSDM) · doi:10.1145/3437963.3441815 · Cited by 65
“The success of deep neural networks on a wide range of classification problems [31] has inspired much work on variants of deep neural networks for time series classification (see [15] for a review).”
BackgroundMapping Seasonal Agricultural Land Use Types Using Deep Learning on Sentinel-2 Image Time Series
Debella-Gilo, M., & Gjertsen, A. K. (2021) · Remote Sensing · doi:10.3390/rs13020289 · Cited by 64
“Detailed reviews of methods used in time series classification, including deep learning, are available [19] and will not be discussed here.”
BackgroundMethodInfluentialDeep learning-based cattle behaviour classification using joint time-frequency data representation
Hosseininoorbin, S., Layeghy, S., Kusý, B., Jurdak, R., Bishop-Hurley, G. J., Greenwood, P. L., & Portmann, M. (2021) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2021.106241 · Cited by 60
“This choice of ReLU and Softmax activation function is a common and proven combination for a wide range of classification problems [41, 42, 43].”
BackgroundBraille letter reading: A benchmark for spatio-temporal pattern recognition on neuromorphic hardware
Müller-Cleve, S. F., Fra, V., Khacef, L., Pequeño-Zurro, A., Klepatsch, D., Forno, E., Ivanovich, D. G., Rastogi, S., Urgese, G., Zenke, F., et al. (2022) · Frontiers in Neuroscience · doi:10.3389/fnins.2022.951164 · Cited by 65
FormerTime: Hierarchical Multi-Scale Representations for Multivariate Time Series Classification
Cheng, M., Liu, Q., Liu, Z., Li, Z., Luo, Y., & Chen, E. (2023) · International World Wide Web Conference (WWW) · doi:10.1145/3543507.3583205 · Cited by 67
Dzieżyc, M., Gjoreski, M., Kazienko, P., Saganowski, S., & Gams, M. (2020) · Sensors · doi:10.3390/s20226535 · Cited by 64
Process Outcome Prediction: CNN vs. LSTM (with Attention)
Weytjens, H., & Weerdt, J. D. (2020) · Lecture notes in business information processing · doi:10.1007/978-3-030-66498-5_24 · Cited by 58
“’s [5] large-scale empirical study of deep learning methods for time series classification includes CNNs but not LSTMs.”
BackgroundResultDeep learning models to predict flood events in fast-flowing watersheds
Luppichini, M., Barsanti, M., Giannecchini, R., & Bini, M. (2021) · The Science of The Total Environment · doi:10.1016/j.scitotenv.2021.151885 · Cited by 59
“The application of deep learning models in various real-world cases, especially in the time series prediction (Fawaz et al., 2020; Yi et al., 2019; Zheng et al., 2019) has been successful.”
Neural Network–Based Financial Volatility Forecasting: A Systematic Review
Ge, W., Lalbakhsh, P., Isai, L., Lenskiy, A. A., & Suominen, H. (2022) · ACM Computing Surveys · doi:10.1145/3483596 · Cited by 69
Deep Temporal Convolution Network for Time Series Classification
Koh, B. H. D., Lim, C. L. P., Rahimi, H., Woo, W. L., & Gao, B. (2021) · Sensors · doi:10.3390/s21020603 · Cited by 57
“Most of them are for image classification [24], and only some are for the one-dimensional multivariate time series data [25].”
BackgroundInternet traffic prediction with deep neural networks
Jiang, W. (2021) · Internet Technology Letters · doi:10.1002/itl2.314 · Cited by 60
Using Gaze Behavior and Head Orientation for Implicit Identification in Virtual Reality
Liebers, J., Horn, P., Burschik, C., Gruenefeld, U., & Schneegaß, S. (2021) · ACM Symposium on Virtual Reality Software and Technology (VRST) · doi:10.1145/3489849.3489880 · Cited by 56
Dangut, M. D., Jennions, I. K., King, S., & Skaf, Z. (2022) · Neural Computing and Applications · doi:10.1007/s00521-022-07167-8 · Cited by 67
“Recent developments in deep learning have made it easy for deep, complex artificial neural networks to automatically extract features from the original dataset (dimension reduction) during training [39, 40].”
BackgroundDeep Residual Network for Smartwatch-Based User Identification through Complex Hand Movements
Mekruksavanich, S., & Jitpattanakul, A. (2022) · Sensors · doi:10.3390/s22083094 · Cited by 58
“As suggestion in [86], we perform the Wilcoxon test [87], which is non-parametric statistical test for pairwise comparing the significant difference.”
MethodShahvandi, M. K., & Soja, B. S. (2022) · Advances in Space Research · doi:10.1016/j.asr.2022.05.042 · Cited by 58
Semi-supervised Time Series Classification Model with Self-supervised Learning
Xi, L., Yun, Z., Liu, H., Wang, R., Huang, X., & Fan, H. (2022) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2022.105331 · Cited by 56
A Deep Generative Model for Non-Intrusive Identification of EV Charging Profiles
Wang, S., Du, L., Ye, J., & Zhao, D. (2020) · IEEE Transactions on Smart Grid · doi:10.1109/tsg.2020.2998080 · Cited by 56
“Some recent results [30], [31] have shown that convolutional layers can achieve better performances than recurrent layers in some applications.”
BackgroundEnsembles of localised models for time series forecasting
Godahewa, R., Bandara, K., Webb, G. I., Smyl, S., & Bergmeir, C. (2021) · Knowledge-Based Systems · doi:10.1016/j.knosys.2021.107518 · Cited by 56
“We use the Python implementation cd-diagram available on Github to plot the critical difference diagram [100].”
MethodDeep Learning For Time Series Classification Using New Hand-Crafted Convolution Filters
Ismail-Fawaz, A., Devanne, M., Weber, J., & Forestier, G. (2022) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata55660.2022.10020496 · Cited by 55
Self-citationKraus, M. A., & Drass, M. (2020) · Glass Structures & Engineering · doi:10.1007/s40940-020-00132-8 · Cited by 61
Noise-robust machinery fault diagnosis based on self-attention mechanism in wavelet domain
Tian, A., Zhang, Y., Ma, C., Chen, H., Sheng, W., & Zhou, S. (2022) · Measurement · doi:10.1016/j.measurement.2022.112327 · Cited by 54
TCGAN: Convolutional Generative Adversarial Network for time series classification and clustering
Huang, F., & Deng, Y. S. (2023) · Neural Networks · doi:10.1016/j.neunet.2023.06.033 · Cited by 57
Lightweight convolution transformer for cross-patient seizure detection in multi-channel EEG signals
Rukhsar, S., & Tiwari, A. K. (2023) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2023.107856 · Cited by 54
Towards a Multi-Temporal Deep Learning Approach for Mapping Urban Fabric Using Sentinel 2 Images
Mendili, L. E., Puissant, A., Chougrad, M., & Sebari, I. (2020) · Remote Sensing · doi:10.3390/rs12030423 · Cited by 54
“They operate by using a classifier, for instance, the nearest neighbor classifier (NN), along with a similarity measure like the dynamic time warping distance (DTW) [18].”
MethodZhou, K., Wang, W., Hu, T., & Deng, K. (2020) · Sensors · doi:10.3390/s20247211 · Cited by 59
Interpretable Time-series Classification on Few-shot Samples
Tang, W., Liu, L., & Long, G. (2020) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn48605.2020.9206860 · Cited by 59
“There are also numerous deep learning-based methods to solve TSC tasks [13], [14].”
Untargeted, Targeted and Universal Adversarial Attacks and Defenses on Time Series
Rathore, P., Basak, A., Nistala, S. H., & Runkana, V. (2020) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn48605.2020.9207272 · Cited by 57
Wearable Sensors-Based Hand Gesture Recognition for Human–Robot Collaboration in Construction
Wang, X., Veeramani, D., & Zhu, Z. (2022) · IEEE Sensors Journal · doi:10.1109/jsen.2022.3222801 · Cited by 53
“on multivariate time series classification tasks based on motion sensor data [33], [34] compared to other deep-learning”
MethodMcfly: Automated deep learning on time series
van Kuppevelt, D. E., Meijer, C., Huber, F., van der Ploeg, A., Georgievska, S., & van Hees, V. T. (2020) · SoftwareX · doi:10.1016/j.softx.2020.100548 · Cited by 53
Meta-Learning for Few-Shot Time Series Classification
Narwariya, J., Malhotra, P., Vig, L., Shroff, G. M., & Tv, V. (2020) · Joint International Conference on Data Science & Management of Data (CODS-COMAD) · doi:10.1145/3371158.3371162 · Cited by 53
“Most ResNet implementations for TSC [9, 18, 36, 40] use a feedforward layer followed by a softmax layer to eventually map z to”
BackgroundMethodInfluentialData-driven strategies for predictive maintenance: Lesson learned from an automotive use case
Giordano, D., Giobergia, F., Pastor, E., Macchia, A. L., Cerquitelli, T., Baralis, E., Mellia, M., & Tricarico, D. (2021) · Computers in Industry · doi:10.1016/j.compind.2021.103554 · Cited by 63
Ehrhart, M., Resch, B., Havas, C. R., & Niederseer, D. (2022) · Sensors · doi:10.3390/s22165969 · Cited by 57
“As a starting point, the recent success of FCN in time series classification [9,10] inspired us to utilize an FCN-discriminator in our cGAN workflow.”
MethodIndoor Localization With Robust Global Channel Charting: A Time-Distance-Based Approach
Stahlke, M., Yammine, G., Feigl, T., Eskofier, B. M., & Mutschler, C. (2023) · IEEE Transactions on Machine Learning in Communications and Networking · doi:10.1109/tmlcn.2023.3256964 · Cited by 52
“We have no local pooling layers between the convolutional layers to keep the dimension of time, which has shown good results in time series downstream tasks [47].”
BackgroundContinual Deep Learning for Time Series Modeling
Ao, S.-I., & Fayek, H. M. (2023) · Sensors · doi:10.3390/s23167167 · Cited by 64
A Survey on Deep Learning based Time Series Analysis with Frequency Transformation
Yi, K., Zhang, Q., Fan, W., Cao, L., Wang, S., He, H., Long, G., Hu, L., Wen, Q., & Xiong, H. (2025) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3711896.3736571 · Cited by 72
“In recent years, time series analysis has attracted rapidly increasing attention from academia and industry, particularly in areas such as time series forecasting [5], anomaly detection [14], and classification [20].”
Khozani, Z. S., Iranmehr, M., & Mohtar, W. H. M. W. (2022) · Geocarto International · doi:10.1080/10106049.2022.2032388 · Cited by 53
“The convolution layer extracts feature of the data by applying a fi lter (Ismail Fawaz et al. 2019) and these features usually go through an activation function, such as Recti fi ed Linear Unit (ReLU) to introduce non-linearity to the model.”
MethodDeep order flow imbalance: Extracting alpha at multiple horizons from the limit order book
Kolm, P. N., Turiel, J., & Westray, N. (2023) · Mathematical Finance · doi:10.1111/mafi.12413 · Cited by 63
“…of parameters in each layer of an MLP is not invariant across time series of different lengths, making transferability of the network challenging (Fawaz et al., 2019).3 Briola et al. (2020) conduct a horse race comparing classical ML approaches and DL in forecasting highfrequency returns…”
Jin, Y., Li, Z., Wang, M., Liu, J., Tian, Y., Liu, Y., Wei, X., Zhao, L., & Liu, C. (2024) · Communications Medicine · doi:10.1038/s43856-024-00464-4 · Cited by 51
Explaining Deep Classification of Time-Series Data with Learned Prototypes
Gee, A. H., Garcia-Olano, D., Ghosh, J., & Paydarfar, D. (2019) · arXiv · doi:10.48550/arxiv.1904.08935 · Cited by 54
Quantitative and Qualitative Analysis of Time-Series Classification Using Deep Learning
Ebrahim, S. A., Poshtan, J., Jamali, S. M., & Ebrahim, N. A. (2020) · IEEE Access · doi:10.1109/access.2020.2993538 · Cited by 53
“overpowering the 1NN-DTW method in time-series classification tasks [11].”
Convolutional neural network and long short-term memory models for ice-jam predictions
Madaeni, F., Chokmani, K., Lhissou, R., Homayouni, S., Gauthier, Y., & Tolszczuk-Leclerc, S. (2022) · The Cryosphere · doi:10.5194/tc-16-1447-2022 · Cited by 51
Deep Learning Algorithms for Machinery Health Prognostics Using Time-Series Data: A Review
Thoppil, N. M., Vasu, V., & Rao, C. S. P. (2021) · Journal of Vibration Engineering & Technologies · doi:10.1007/s42417-021-00286-x · Cited by 56
On the use of convolutional deep learning to predict shoreline change
la Peña, E. G., Coco, G., Whittaker, C., & Montaño, J. (2023) · Earth Surface Dynamics · doi:10.5194/esurf-11-1145-2023 · Cited by 54
“Following Ismail Fawaz et al. (2019), a convolution centred at a time step t is given by”
MethodBreuillard, H., Dupuis, R., Retinò, A., Contel, O. L., Amaya, J., & Lapenta, G. (2020) · Frontiers in Astronomy and Space Sciences · doi:10.3389/fspas.2020.00055 · Cited by 50
“This lack of overview has been filled recently (Fawaz et al., 2019) and several models show very promising results.”
BackgroundMethodInfluentialUllah, A., & Dral, P. O. (2022) · Nature Communications · doi:10.1038/s41467-022-29621-w · Cited by 51
Modeling spatiotemporal patterns of gait anomaly with a CNN-LSTM deep neural network
Sadeghzadehyazdi, N., Batabyal, T., & Acton, S. T. (2021) · Expert Systems with Applications · doi:10.1016/j.eswa.2021.115582 · Cited by 50
Westphal, E., & Seitz, H. (2021) · Additive manufacturing · doi:10.1016/j.addma.2021.102535 · Cited by 51
Recognition of the Mental Workloads of Pilots in the Cockpit Using EEG Signals
Hernández-Sabaté, A., Yauri, J., Folch, P., Piera, M. À., & Gil, D. (2022) · Applied Sciences · doi:10.3390/app12052298 · Cited by 49
Yan, C. G., Liu, J., Liu, W., & Liu, X. (2022) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2022.105448 · Cited by 51
Spatio-Temporal Abnormal Behavior Prediction in Elderly Persons Using Deep Learning Models
Zerkouk, M., & Chikhaoui, B. (2020) · Sensors · doi:10.3390/s20082359 · Cited by 50
“Tele-health care requires systems with high accuracy, low computational time and minimal user intervention because data are becoming larger and more complex [8].”
BackgroundVehicular traffic flow prediction using deployed traffic counters in a city
Almeida, A., Brás, S., Oliveira, I., & Sargento, S. (2021) · Future Generation Computer Systems · doi:10.1016/j.future.2021.10.022 · Cited by 49
Wagner, N., Mialon, M., Sloth, K. H., Lardy, R., Ledoux, D., Silberberg, M., Roches, A. D. B. D., & Veissier, I. (2020) · Methods · doi:10.1016/j.ymeth.2020.09.003 · Cited by 48
Improving text classification with transformers and layer normalization
Rodrawangpai, B., & Daungjaiboon, W. (2022) · Machine Learning with Applications · doi:10.1016/j.mlwa.2022.100403 · Cited by 55
Raeisi, K., Khazaei, M., Tamburro, G., Croce, P., Comani, S., & Zappasodi, F. (2023) · International Journal of Neural Systems · doi:10.1142/s0129065723500466 · Cited by 52
TSCMamba: Mamba meets multi-view learning for time series classification
Ahamed, M. A., & Cheng, Q. S. (2025) · Information Fusion · doi:10.1016/j.inffus.2025.103079 · Cited by 57
Zhou, D., Zhuang, X. D., & Zuo, H. (2021) · Chinese Journal of Aeronautics · doi:10.1016/j.cja.2021.03.031 · Cited by 51
Deep-Learning Approach to First-Principles Transport Simulations
Bürkle, M., Perera, U., Gimbert, F., Nakamura, H., Kawata, M., & Asai, Y. (2021) · Physical Review Letters · doi:10.1103/physrevlett.126.177701 · Cited by 50
Alfieri, F., Ancona, A., Tripepi, G. L., CROSETTO, D. B., Randazzo, V., Paviglianiti, A., Pasero, E. G. A., Vecchi, L., Cauda, V., & Fagugli, R. M. (2021) · Journal of Nephrology · doi:10.1007/s40620-021-01046-6 · Cited by 48
“We chose a convolutional neural network from a broad range of alternative architectures thanks to its demonstrated ability to match with time series classification problems [14].”
MethodA Deep LSTM based Approach for Intrusion Detection IoT Devices Network in Smart Home
Azumah, S. W., ElSayed, Z., Adewopo, V. A., Zaghloul, Z. S., & Li, C. (2021) · IEEE World Forum on Internet of Things (WF-IoT) · doi:10.1109/wf-iot51360.2021.9596033 · Cited by 53
Deep Learning for Eye Blink Detection Implemented at the Edge
Jordan, A. A., Pégatoquet, A., Castagnetti, A., Raybaut, J., & Coz, P. L. (2020) · IEEE Embedded Systems Letters · doi:10.1109/les.2020.3029313 · Cited by 47
Kraft, D., Srinivasan, K. K., & Bieber, G. (2020) · Technologies · doi:10.3390/technologies8040072 · Cited by 50
An Efficient ResNetSE Architecture for Smoking Activity Recognition from Smartwatch
Hnoohom, N., Mekruksavanich, S., & Jitpattanakul, A. (2022) · Intelligent Automation & Soft Computing · doi:10.32604/iasc.2023.028290 · Cited by 46
Time series classification based on temporal features
Ji, C., Du, M., Hu, Y., Liu, S., Pan, L., & Zheng, X. (2022) · Applied Soft Computing · doi:10.1016/j.asoc.2022.109494 · Cited by 47
Jafari, M., Sadeghi, D., Shoeibi, A., Alinejad‐Rokny, H., Beheshti, A., López-García, D., Chen, Z., Acharya, U. R., & Górriz, J. M. (2023) · Applied Intelligence · doi:10.1007/s10489-023-05155-6 · Cited by 49
“training times compared to traditional neural networks [246].”
Agnostic Local Explanation for Time Series Classification
Guillemé, M., Masson, V., Rozé, L., & Termier, A. (2019) · IEEE International Conference on Tools with Artificial Intelligence (ICTAI) · doi:10.1109/ictai.2019.00067 · Cited by 48
“Lee et al. [10] use a grammarbased decision tree for interpretable TSC and Teijeiro et al. [11] propose a classifier following the abductive reasoning paradigm rather than the more common deductive reasoning paradigm.”
BackgroundMethodInfluentialTime series classification based on statistical features
Lei, Y., & Wu, Z. (2020) · EURASIP Journal on Wireless Communications and Networking · doi:10.1186/s13638-020-1661-4 · Cited by 46
Embedding and learning with signatures
Fermanian, A. (2020) · Computational Statistics & Data Analysis · doi:10.1016/j.csda.2020.107148 · Cited by 57
Auto-adaptive multilayer perceptron for univariate time series classification
Campo, F. A. D., Neri, M. C. G., Villegas, O. O. V., Sánchez, V. G. C., Domínguez, H. D. J. O., & García, V. (2021) · Expert Systems with Applications · doi:10.1016/j.eswa.2021.115147 · Cited by 45
Kamga, G. A. F., Bitjoka, L., Akram, T., Mbom, A. M., Naqvi, S. R., & Bouroubi, Y. (2021) · International Journal of Remote Sensing · doi:10.1080/01431161.2021.1954261 · Cited by 46
“The RNN approaches, which have proven to be efficient at exploiting sequential dimensions in many applications (Maggiori et al. 2017), (Fawaz et al. 2019), have been used in satellite image processing.”
MethodDenoising temporal convolutional recurrent autoencoders for time series classification
Zheng, Z., Zhang, Z., Wang, L., & Luo, X. (2022) · Information Sciences · doi:10.1016/j.ins.2021.12.061 · Cited by 45
Deep Neural Network Ensemble for the Intelligent Fault Diagnosis of Machines Under Imbalanced Data
Jia, F., Li, S., Zuo, H., & Shen, J. (2020) · IEEE Access · doi:10.1109/access.2020.3006895 · Cited by 45
Automated classification of five arrhythmias and normal sinus rhythm based on RR interval signals
Faust, O., & Acharya, U. R. (2021) · Expert Systems with Applications · doi:10.1016/j.eswa.2021.115031 · Cited by 46
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
