Deep Convolutional and LSTM Recurrent Neural Networks for Multimodal Wearable Activity Recognition
Open accessThe DOI matches its Crossref record; 48 of the 49 references it cites were found in a registry or an index; 8 of the 23 sources its claims cite were checked for support.
Abstract
Introduces DeepConvLSTM, a deep learning architecture combining convolutional and LSTM recurrent units for multimodal wearable activity recognition, outperforming non-recurrent deep networks and handcrafted feature baselines by 4% to 9%.
Overview
CoChat Summary
TL;DR
The paper proposes DeepConvLSTM, a deep framework combining four convolutional layers with two LSTM recurrent layers for wearable activity recognition from raw multimodal sensor data. It reports improved F1 scores over a baseline CNN and prior results on the OPPORTUNITY and Skoda datasets, including 0.915 F1 for OPPORTUNITY gestures with the Null class and 0.958 F1 on Skoda.
Key findings
- On OPPORTUNITY, DeepConvLSTM achieved F1 scores of 0.930 for modes of locomotion without Null, 0.895 for modes with Null, 0.866 for gestures without Null, and 0.915 for gestures with Null; the baseline CNN scored 0.912, 0.878, 0.783, and 0.883, respectively. The paper reports a 6% average improvement over the best OPPORTUNITY challenge submissions and more than 9% improvement on gesture recognition without Null.
- On Skoda, DeepConvLSTM reached 0.958 F1, compared with 0.884 for the baseline CNN, 0.893 for CNN [43], and 0.861 for CNN [23], improving the best reported result by 6%.
- Multimodal fusion improved gesture recognition on OPPORTUNITY without Null: 0.689 F1 with accelerometers only, 0.611 with gyroscopes only, 0.745 with accelerometers + gyroscopes, 0.839 with accelerometers + gyroscopes + magnetic sensors, and 0.864 with the full OPPORTUNITY sensor set.
- DeepConvLSTM had 999,122 parameters versus 7,445,458 for the baseline CNN, a 600% increase for the baseline; training took 340.3 min versus 282.2 min, and classification took 6.68 s versus 5.43 s, with DeepConvLSTM classifying almost 15 min of data per second and achieving 900× real-time on the GPU used.
Methods
- DeepConvLSTM uses four convolutional layers with 64 feature maps each, followed by two dense LSTM layers with 128 cells and a softmax output; the baseline CNN shares the convolutional layers but uses two non-recurrent dense layers with 128 units. Models were trained supervised with cross-entropy loss, mini-batch gradient descent with RMSProp, learning rate 10e-3, decay factor 0.9, mini-batches of 100 segments, and dropout p=0.5 on dense-layer inputs.
- Inputs were sliding windows of 500 ms with 250 ms step size, using raw sensor data with minimal preprocessing: linear interpolation for missing values and per-channel normalization to [0,1]. Evaluation used weighted F1 to address class imbalance.
- Experiments used the OPPORTUNITY dataset (on-body sensors, 113 channels, 30 Hz; Task A: 5-class modes of locomotion/postures; Task B: 18-class sporadic gestures) and the Skoda dataset (one subject, 10 right-arm 3D accelerometers, decimated to 30 Hz, 10 manipulative gestures, about 3 h and about 70 repetitions per gesture). Analyses included comparison to baseline CNN and published results, confusion matrices, sensor-modality fusion, and hyperparameter evaluations of sequence length and number of convolutional layers.
Limitations
- The paper states that DeepConvLSTM has not yet been implemented on a wearable device; the GPU used clearly outperforms current high-end wearable computational power, and training is best envisioned server-side. It also states that pooling was omitted because the sliding-window setup limits downsampling, though pooling could be useful without that requirement, and that training time increases with the number of layers, creating a performance–computational budget trade-off.
- Evident from the text: Skoda evaluation uses one subject and only right-arm sensors, and OPPORTUNITY testing is limited to ADL4 and ADL5 for Subjects 2 and 3, which constrains generalizability. The text does not report cross-validation or statistical significance testing.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Figures



![Figure 4 Placement of on-body sensors used in the OPPORTUNITYdataset (left: inertial measurements units; right: 3-axis accelerometers) [7].](https://figures.cochat.ai/paper-figures/27c0e4b39d104fe2b5315587d736fd2d/deep-convolutional-and-lstm-recurrent-neural-networks-for-multimodal-wearable-figure-4.jpg)




Verification
Claims the paper makes
5 Valid · 5 Not valid · 13 Not checked · 99 Own results and interpretations
Every source the paper cites for this claim was checked and supports it.
In the paper
“The choice of the number of recurrent layers is made following the results presented in [33], where the authors showed that a depth of at least two recurrent layers is beneficial when processing sequential data.”
§ Deep Convolutional and LSTM Recurrent Neural Networks for Multimodal Wearable Activity Recognition > 3. Architecture > 3.1. DeepConvLSTM
What the sources say
- Supportedcites [33] Karpathy A. Johnson J. Li F.F. Visualizing and understanding recurrent networks Cornell Univ. Lab. 2015 arXiv:1506.02078 source
Section 4.1 compares recurrent networks with one, two, and three layers on two sequence datasets and states that a depth of at least two is consistently beneficial. This directly supports the attributed finding, within the paper’s tested settings. (LLM, conf=0.94)
boostedstates a cause- 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.
- Supported
Every source the paper cites for this claim was checked and supports it.
In the paper
“This seems to indicate that although deep learning techniques are often employed with large amounts of data, (e.g., millions of frames in computer vision [22]), they may actually be applicable to problem domains where acquiring annotated data is very costly, such as in supervised activity recognition.”
§ Deep Convolutional and LSTM Recurrent Neural Networks for Multimodal Wearable Activity Recognition > 5. Results and Discussion > 5.4. Discussion
What the sources say
- Supportedcites [22] Pigou L. Oord A.V.D. Dieleman S. van Herreweghe M. Dambre J. Beyond Temporal Pooling: Recurrence and Temporal Convolutions for Gesture Recognition in Video arXiv Preprint 2015 arXiv:1506.01911 source
The citation is attached to the example of large-scale computer-vision data, not to the citing authors’ conclusion about costly annotation. Section 4.1 (page unavailable) reports 1,720,800 labeled video frames in the gesture-recognition dataset, supporting the cited example of data on the order of millions of frames. (LLM, conf=0.86)
hedgedstates a possible cause- 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.
- Supported
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 baseline CNN also offers better results than the OPPORTUNITY submissions in the recognition of models of locomotion.”
§ Deep Convolutional and LSTM Recurrent Neural Networks for Multimodal Wearable Activity Recognition > 5. Results and Discussion > 5.1. Performance Comparison
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
“From the results, we can also see how the model is able to learn from signals obtained from accelerometers, gyroscopes and magnetometers, fusing them without requiring any specific preprocessing.”
§ Deep Convolutional and LSTM Recurrent Neural Networks for Multimodal Wearable Activity Recognition > 6. Conclusions
plainstates a cause- 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 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
“(iv) it is applicable even if the gestures are longer than the observation window.”
§ Deep Convolutional and LSTM Recurrent Neural Networks for Multimodal Wearable Activity Recognition > 5. Results and Discussion > 5.4. Discussion
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: unclear — It is unclear why the paper says it holds.
84 more claims
Create a free account to see all 122 claims and to verify the 2 references still open.
- It may state two separate claims as one. 14
- Probably not a substantial claim. 23
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 cited source doesn’t support the claim as written.
In the citing paper
“However, these complex network framework suffered from low ef ciency and can hardly meet real-time requirements in practice applications.”
From InnoHAR: A Deep Neural Network for Complex Human Activity Recognition (2019) · cites this paper as [19]
Checked by a reasoning model — may be wrong.
Experimental — accuracy not yet measuredThe cited source doesn’t support the claim as written.
In the citing paper
“However, due to the lack of filtration techniques applied to multimodal data, the system’s performance was low.”
From A Multimodal IoT-Based Locomotion Classification System Using Features Engineering and Recursive Neural Network (2023) · cites this paper as [15]
Checked by a reasoning model — may be wrong.
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“and yield better performances than pure CNNs or LSTM networks [12]”
From Comparison of Feature Learning Methods for Human Activity Recognition Using Wearable Sensors (2018) · cites this paper as [12]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“The proposed method outperforms other methods, such as those based on deep believe networks (DBNs) [10], SVM [10], and CNNs [13].”
From Deep Recurrent Neural Networks for Human Activity Recognition (2017) · cites this paper as [13]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“The popular DeepConvLSTM model [7] can only afford four, moderately-sized convolution layers to learn effective data representations, and two LSTM layers for sequence modeling.”
From Complex Deep Neural Networks from Large Scale Virtual IMU Data for Effective Human Activity Recognition Using Wearables (2021) · cites this paper as [7]
Experimental — accuracy not yet measured
20 more claims about this paper
Create a free account to see every claim other papers make about this one.
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 major: it would touch a result — a value a result rests on, reported and recomputed p-values on opposite sides of the significance level, two passages that conflict with no sign which is right, or a cited work retracted before this paper was published.
In the paper
§ Deep Convolutional and LSTM Recurrent Neural Networks for Multimodal Wearable Activity Recognition > 3. Architecture
“The length of the kernels is the same for every convolutional layer, being defined as Pl=5,∀l=2,⋯,5.”
§ Deep Convolutional and LSTM Recurrent Neural Networks for Multimodal Wearable Activity Recognition > 4. Experimental Setup > 4.2. Performance Measure
“Following the OPPORTUNITY challenge experimental setup, the length of the window is 500 ms, with a step size of 250 ms.”
Rated major: it would touch a result — a value a result rests on, reported and recomputed p-values on opposite sides of the significance level, two passages that conflict with no sign which is right, or a cited work retracted before this paper was published.
In the paper
“| Total | 996,800 +(128×nc)+nc | 996,800 +(128×nc)+nc | 7,443,136+(128×nc)+nc | 7,443,136+(128×nc)+nc |”
§ Deep Convolutional and LSTM Recurrent Neural Networks for Multimodal Wearable Activity Recognition > 3. Architecture > 3.3. Model Implementation and Training
Reported 996800 · recomputed 1037888
Rated major: it would touch a result — a value a result rests on, reported and recomputed p-values on opposite sides of the significance level, two passages that conflict with no sign which is right, or a cited work retracted before this paper was published.
In the paper
“| 6 | Wai,Waf,Wac,Wao: 7232×128 | 942,592 | W: 57,856×128 | 7,405,696 |”
§ Deep Convolutional and LSTM Recurrent Neural Networks for Multimodal Wearable Activity Recognition > 3. Architecture > 3.3. Model Implementation and Training
Reported 942592 · recomputed 3702784
Rated major: it would touch a result — a value a result rests on, reported and recomputed p-values on opposite sides of the significance level, two passages that conflict with no sign which is right, or a cited work retracted before this paper was published.
In the paper
“| 7 | Wai,Waf,Wac,Wao: 128×128 | 33,280 | W: 128×128 | 16,512 |”
§ Deep Convolutional and LSTM Recurrent Neural Networks for Multimodal Wearable Activity Recognition > 3. Architecture > 3.3. Model Implementation and Training
Reported 33280 · recomputed 131072
Citations
Cites
ImageNet 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
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 · cited 1×
“Other publications showed much deeper networks, such as “GoogLeNet”, which is a 27-layer deep neural network applied to image classification [45].”
BackgroundReducing the dimensionality of data with neural networks
Hinton, G. E., & Salakhutdinov, R. R. (2006) · Science · doi:10.1126/science.1127647 · Cited by 20,928
Speech recognition with deep recurrent neural networks
Graves, A., Mohamed, A.-R., & Hinton, G. (2013) · 2013 IEEE International Conference on Acoustics, Speech and Signal Processing · doi:10.1109/icassp.2013.6638947 · Cited by 8,893 · cited 1×
“Networks using LSTM cells have offered better performance than standard recurrent units in speech recognition, where they gave state-of-the-art results in phoneme recognition [20].”
BackgroundConvolutional networks for images, speech, and time series
LeCun, Y., & Bengio, Y. (1998) · HAL (Le Centre pour la Communication Scientifique Directe) · doi:10.5555/303568.303704 · Cited by 4,231
The class imbalance problem: A systematic study1
Japkowicz, N., & Stephen, S. (2002) · Intelligent Data Analysis · doi:10.3233/ida-2002-6504 · Cited by 3,295
DeepPose: Human Pose Estimation via Deep Neural Networks
Toshev, A., & Szegedy, C. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.214 · Cited by 3,185 · cited 1×
“Deep CNNs have had a major impact on fields, like content recommendation [24], speech recognition [25] and in computer vision [26–28], where they have become the de facto standard approach.”
BackgroundOverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks
Sermanet, P., Eigen, D., Zhang, X., Mathieu, M., Fergus, R., & LeCun, Y. (2013) · arXiv · doi:10.48550/arxiv.1312.6229 · Cited by 2,680 · cited 1×
“Deep CNNs have had a major impact on fields, like content recommendation [24], speech recognition [25] and in computer vision [26–28], where they have become the de facto standard approach.”
BackgroundLee, H., Grosse, R., Ranganath, R., & Ng, A. Y. (2009) · Proceedings of the 26th Annual International Conference on Machine Learning · doi:10.1145/1553374.1553453 · Cited by 2,412 · cited 1×
“Deep learning techniques have outperformed many conventional methods in computer vision [13] and audio classification [14].”
MethodA review of wearable sensors and systems with application in rehabilitation
Patel, S., Park, H., Bonato, P., Chan, L., & Rodgers, M. (2012) · Journal of NeuroEngineering and Rehabilitation · doi:10.1186/1743-0003-9-21 · Cited by 2,396 · cited 1×
“, from simple hand gestures to complex activities, such as “cooking a meal”) and the context in which they occur from sensor data is at the core of smart assistive technologies, such as in smart homes [1], in rehabilitation [2], in health support [3,4], in skill assessment [5] or in industrial settings [6].”
Background
Research works printed but not linked: 1
- Gers F.A. Schraudolph N.N. Schmidhuber J. Learning precise timing with LSTM recurrent networks J. Mach. Learn. Res. 2003 3 115 143
Cited by
Items 101–200 of 2,807
Divide and Conquer-Based 1D CNN Human Activity Recognition Using Test Data Sharpening
Cho, H., & Yoon, S. (2018) · Sensors · doi:10.3390/s18041055 · Cited by 183
“We first compare our method’s HAR performance with the following state of the art approaches: using the lower body OPPORTUNITY dataset, we compare our approach to deep convolutional LSTM networks proposed by Ordóñez and Roggen [28]; using the UCI HAR dataset, we compare our approach to four other approaches, i.e., one…”
BackgroundMethodInfluentialTeng, Q., Wang, K., Zhang, L., & He, J. (2020) · IEEE Sensors Journal · doi:10.1109/jsen.2020.2978772 · Cited by 183
“Ordóñez and Roggen [11] presented a generic deep framework composed of CNN and long-term short memory (LSTM) for activity recognition, which could fuse multimodal sensors to further improve the CNN on classification accuracy.”
BackgroundMethodZeng, M., Gao, H., Yu, T., Mengshoel, O. J., Langseth, H., Lane, I., & Liu, X. (2018) · Proceedings of the 2018 ACM International Symposium on Wearable Computers · doi:10.1145/3267242.3267286 · Cited by 185
“The baseline methods include standard LSTM [12], DeepConvLSTM [19], and LSTM-S (LSTM + sample-by-sample analysis) [11].”
BackgroundMethodInfluentialActivity Recognition and Abnormal Behaviour Detection with Recurrent Neural Networks
Arifoglu, D., & Bouchachia, A. (2017) · Procedia Computer Science · doi:10.1016/j.procs.2017.06.121 · Cited by 181
“Recently, there has been growing interest in deep convolutional neural networks [30, 31, 20, 13], Deep Belief Networks [4], Restricked Boltzman Machines (RBMs) [21, 12, 4, 9] and RNNs [20, 13, 10].”
BackgroundMethodInfluentialPredicting mortgage default using convolutional neural networks
Kvamme, H., Sellereite, N., Aas, K., & Sjursen, S. (2018) · Expert Systems with Applications · doi:10.1016/j.eswa.2018.02.029 · Cited by 179
“This is in some sense similar to other time series prediction tasks where the dataset originally consists of many overlapping series of data (e.g. Ordóñez and Roggen (2016)).”
BackgroundResultVision-based human action recognition: An overview and real world challenges
Jegham, I., Ben Khalifa, A., Alouani, I., & Mahjoub, M. A. (2020) · Forensic Science International: Digital Investigation · doi:10.1016/j.fsidi.2019.200901 · Cited by 181
Deep Learning-Based Anomaly Detection in Video Surveillance: A Survey
Duong, H.-T., Le, V.-T., & Hoang, V. T. (2023) · Sensors · doi:10.3390/s23115024 · Cited by 178
“Moreover, extracting rich semantic features from multimodal datasets is a research trend [75,141], since this information enables explaining the long-term relationship between interacting objects [142].”
BackgroundA Survey on Deep Learning Based Approaches for Action and Gesture Recognition in Image Sequences
Asadi-Aghbolaghi, M., Clapes, A., Bellantonio, M., Escalante, H. J., Ponce-Lopez, V., Baro, X., Guyon, I., Kasaei, S., & Escalera, S. (2017) · 2017 12th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2017) · doi:10.1109/fg.2017.150 · Cited by 173
WiFi Fingerprinting Indoor Localization Using Local Feature-Based Deep LSTM
Chen, Z., Zou, H., Yang, J., Jiang, H., & Xie, L. (2020) · IEEE Systems Journal · doi:10.1109/jsyst.2019.2918678 · Cited by 173
Prediction of vegetation dynamics using NDVI time series data and LSTM
Reddy, D. S., & Prasad, P. R. C. (2018) · Modeling Earth Systems and Environment · doi:10.1007/s40808-018-0431-3 · Cited by 175
“Further, the vanishing gradient descent problem in a standard RNN is resolved in LSTM networks by introducing the concept of the memory cell (Wildml 2015; Colah 2015).”
BackgroundInfluentialDeep Learning for Monitoring of Human Gait: A Review
Alharthi, A. S., Yunas, S. U., & Ozanyan, K. B. (2019) · IEEE Sensors Journal · doi:10.1109/jsen.2019.2928777 · Cited by 175
“In another work, 7 IMUs positioned on the chest, arms and legs along with the12 accelerometers close to the limb joints, were used by Ordóñez and Roggen [65].”
MethodAl-qaness, M. A. A., Dahou, A., Elaziz, M. A., & Helmi, A. M. (2023) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2022.3165875 · Cited by 175
“Ordóñez et al. [14] developed a HAR scheme based on recurrent neural networks (RNNs), called DeepConvLSTM.”
MethodEvolutionary convolutional neural networks: An application to handwriting recognition
Baldominos, A., Saez, Y., & Isasi, P. (2018) · Neurocomputing · doi:10.1016/j.neucom.2017.12.049 · Cited by 175
AHAR: Adaptive CNN for Energy-Efficient Human Activity Recognition in Low-Power Edge Devices
Rashid, N., Demirel, B. U., & Abdullah Al Faruque, M. (2022) · IEEE Internet of Things Journal · doi:10.1109/jiot.2022.3140465 · Cited by 169
“Moreover, both our baseline and adaptive architecture outperforms the work [11] and achieves a comparable performance with respect to [16]–[18] as shown in Table VII.”
BackgroundMethodResultInfluentialGRU-INC: An inception-attention based approach using GRU for human activity recognition
Mim, T. R., Amatullah, M., Afreen, S., Yousuf, M. A., Uddin, S., Alyami, S. A., Hasan, K. F., & Moni, M. A. (2023) · Expert Systems with Applications · doi:10.1016/j.eswa.2022.119419 · Cited by 178
Human Activity Recognition Using Federated Learning
Sozinov, K., Vlassov, V., & Girdzijauskas, S. (2018) · 2018 IEEE Intl Conf on Parallel & Distributed Processing with Applications, Ubiquitous Computing & Communications, Big Data & Cloud Computing, Social Computing & Networking, Sustainable Computing & Communications (ISPA/IUCC/BDCloud/SocialCom/SustainCom) · doi:10.1109/bdcloud.2018.00164 · Cited by 167
Gesture-based human-robot interaction for human assistance in manufacturing
Neto, P., Simão, M., Mendes, N., & Safeea, M. (2019) · The International Journal of Advanced Manufacturing Technology · doi:10.1007/s00170-018-2788-x · Cited by 165
CiFi: Deep convolutional neural networks for indoor localization with 5 GHz Wi-Fi
Wang, X., Wang, X., & Mao, S. (2017) · 2017 IEEE International Conference on Communications (ICC) · doi:10.1109/icc.2017.7997235 · Cited by 161
“DCNN is a powerful deep learning technique that has been successfully applied for image recognition [14] and human activity recognition based on sensors [15] and RFID [16], respectively.”
Distilling the Knowledge From Handcrafted Features for Human Activity Recognition
Chen, Z., Zhang, L., Cao, Z., & Guo, J. (2018) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2018.2789925 · Cited by 160
“presented a deep convolutional LSTM network for human activity recognition [19].”
BackgroundKautz, T., Groh, B. H., Hannink, J., Jensen, U., Strubberg, H., & Eskofier, B. M. (2017) · Data Mining and Knowledge Discovery · doi:10.1007/s10618-017-0495-0 · Cited by 159
“Ordóñez and Roggen (2016) used a recurrent network architecture for gesture recognition from IMMU data.”
BackgroundSaboor, A., Kask, T., Kuusik, A., Alam, M. M., Le Moullec, Y., Niazi, I. K., Zoha, A., & Ahmad, R. (2020) · IEEE Access · doi:10.1109/access.2020.3022818 · Cited by 158
“Gait based authentication is attracting various researchers [96], [144], [146].”
BackgroundSelf-supervised learning for human activity recognition using 700,000 person-days of wearable data
Yuan, H., Chan, S., Creagh, A. P., Tong, C., Acquah, A., Clifton, D. A., & Doherty, A. (2024) · npj Digital Medicine · doi:10.1038/s41746-024-01062-3 · Cited by 166
On attention models for human activity recognition
Murahari, V. S., & Plötz, T. (2018) · Proceedings of the 2018 ACM International Symposium on Wearable Computers · doi:10.1145/3267242.3267287 · Cited by 157
“For example, Convolutional Neural Networks (CNNs) in HAR employ a sliding window procedure to map the timeseries data to a fixed 2D representation that is fed into the convolution layers [9].”
BackgroundMethodInfluentialA Hybrid Deep Learning Model for Human Activity Recognition Using Multimodal Body Sensing Data
Gumaei, A., Hassan, M. M., Alelaiwi, A., & Alsalman, H. (2019) · IEEE Access · doi:10.1109/access.2019.2927134 · Cited by 157
“Among the deep learning methods, Deep Belief Network (DBN) [23]–[25] and Convolutional Neural Network (CNN) network are popular [26], [27].”
MethodHuman Activity Recognition Based on Gramian Angular Field and Deep Convolutional Neural Network
Xu, H., Li, J., Yuan, H., Liu, Q., Fan, S., Li, T., & Sun, X. (2020) · IEEE Access · doi:10.1109/access.2020.3032699 · Cited by 174
“Ordonez et al. proposed a new deep learning model that combined CNN and LSTM units, which was a significant improvement for traditional machine learning methods [16].”
MethodDriving behavior classification based on sensor data fusion using LSTM recurrent neural networks
Saleh, K., Hossny, M., & Nahavandi, S. (2017) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc.2017.8317835 · Cited by 176
“The rolling window is a common preprocessing approach used by all timeseries prediction tasks [5], [7], [9], [10], because at the testing time, it is not practical to only give classification scores after observing all the features vectors during the driving trip.”
BackgroundMethodInfluentialGolestani, N., & Moghaddam, M. (2020) · Nature Communications · doi:10.1038/s41467-020-15086-2 · Cited by 172
“…proposed MI-HAR system in recognizing human activities, we implemented deep recurrent neural networks (RNNs) based on long short-term memory (LSTM) units due to their strong performance in human activity detection, and their capability in learning complex representations of the motion data 60,61 .”
MethodElderly Fall Detection Using Wearable Sensors: A Low Cost Highly Accurate Algorithm
Saleh, M., & Jeannès, R. L. B. (2019) · IEEE Sensors Journal · doi:10.1109/jsen.2019.2891128 · Cited by 171
EmbraceNet: A robust deep learning architecture for multimodal classification
Choi, J.-H., & Lee, J.-S. (2019) · Information Fusion · doi:10.1016/j.inffus.2019.02.010 · Cited by 156
“For the OPPORTUNITY dataset, we borrow an early integration-based model, “DeepConvLSTM”, which was used for classifying activities in the OPPORTUNITY dataset and showed better performance than other methods [3].”
BackgroundMethodInfluentialNoninvasive Human Activity Recognition Using Millimeter-Wave Radar
Yu, C., Xu, Z., Yan, K., Chien, Y., Fang, S., & Wu, H. (2022) · IEEE Systems Journal · doi:10.1109/jsyst.2022.3140546 · Cited by 182
Correlational Convolutional LSTM for human action recognition
Majd, M., & Safabakhsh, R. (2019) · Neurocomputing · doi:10.1016/j.neucom.2018.10.095 · Cited by 169
Kwon, H., Tong, C., Haresamudram, H., Gao, Y., Abowd, G. D., Lane, N. D., & Plötz, T. (2020) · Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies · doi:10.1145/3411841 · Cited by 152
“Method We employ two machine learning models, Random Forest and DeepConvLSTM [54].”
MethodInfluentialInception inspired CNN-GRU hybrid network for human activity recognition
Dua, N., Singh, S. N., Semwal, V. B., & Challa, S. K. (2022) · Multimedia Tools and Applications · doi:10.1007/s11042-021-11885-x · Cited by 160
“The deep convolutional LSTM approach proposed in [47] attained decent accuracy and F1-score values for both datasets.”
MethodInfluentialContrastive Predictive Coding for Human Activity Recognition
Haresamudram, H., Essa, I., & Plötz, T. (2021) · Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies · doi:10.1145/3463506 · Cited by 150
“Approach Method type Mobiact Motionsense UCI-HAR USC-HAD DeepConvLSTM† [59] Supervised 82.”
BackgroundMethodResultInfluentialTSE-CNN: A Two-Stage End-to-End CNN for Human Activity Recognition
Huang, J., Lin, S., Wang, N., Dai, G., Xie, Y., & Zhou, J. (2020) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2019.2909688 · Cited by 145
“[34]”
Wearable Sensor-Based Human Activity Recognition in the Smart Healthcare System
Serpush, F., Menhaj, M. B., Masoumi, B., & Karasfi, B. (2022) · Computational Intelligence and Neuroscience · doi:10.1155/2022/1391906 · Cited by 223
“In the HARS, complex activities are hierarchically unstable [69], which means people do the same activities in different procedures.”
BackgroundA comprehensive survey on human pose estimation approaches
Dubey, S., & Dixit, M. (2022) · Multimedia Systems · doi:10.1007/s00530-022-00980-0 · Cited by 193
“Francisco Javier Ordonez and Daniel Roggen [6], This paper are centered on convolutional and LSTM recurrent units, and a generalized deep architecture for behavior recognition is suggested.”
BackgroundAnguera, M. T., Foguet, O. C., Balcells, M. C., Sánchez-Algarra, P., & Onwuegbuzie, A. J. (2017) · Frontiers in Psychology · doi:10.3389/fpsyg.2017.02196 · Cited by 195
“…with observational data on physical activity through hidden Markov chains (Castañer et al., 2017b); and (d) application of deep learning techniques, which automatically extract multilevel characteristics that maximize the identification of predefined behavioral patterns (Ordóñez and Roggen, 2016).”
BackgroundMasked reconstruction based self-supervision for human activity recognition
Haresamudram, H., Beedu, A., Agrawal, V., Grady, P. L., Essa, I., Hoffman, J., & Plötz, T. (2020) · Proceedings of the 2020 International Symposium on Wearable Computers · doi:10.1145/3410531.3414306 · Cited by 146
“…unsupervised learning techniques, i.e., convolutional autoencoders (CAE) [12] and multi-task self-supervision [30], and, for reference only given that the main focus of this paper is on unsupervised approaches, to supervised learning pipelines (DeepConvLSTM [23] and Trans-former classifier).”
BackgroundA Novel Ensemble ELM for Human Activity Recognition Using Smartphone Sensors
Chen, Z., Jiang, C., & Xie, L. (2019) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2018.2869843 · Cited by 144
“human activities [24].”
Cruciani, F., Vafeiadis, A., Nugent, C., Cleland, I., McCullagh, P., Votis, K., Giakoumis, D., Tzovaras, D., Chen, L., & Hamzaoui, R. (2020) · CCF Transactions on Pervasive Computing and Interaction · doi:10.1007/s42486-020-00026-2 · Cited by 142
Tang, Y., Teng, Q., Zhang, L., Min, F., & He, J. (2021) · IEEE Sensors Journal · doi:10.1109/jsen.2020.3015521 · Cited by 143
“Requiring performance metrics that are independent of the class distribution, we evaluate the models using the weighted F1 score [32]:”
BackgroundMethodA Comprehensive Study of Activity Recognition Using Accelerometers
Twomey, N., Diethe, T., Fafoutis, X., Elsts, A., McConville, R., Flach, P., & Craddock, I. (2018) · Informatics · doi:10.3390/informatics5020027 · Cited by 143
MMNet: A Model-Based Multimodal Network for Human Action Recognition in RGB-D Videos
Yu, B. X. B., Liu, Y., Zhang, X., Zhong, S.-H., & Chan, K. C. C. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3177813 · Cited by 206
“Fusion-based multimodal HAR approaches are generally thought to have the potential to boost recognition accuracy and distinguish difficult actions [10], [13].”
BackgroundA Comprehensive Study of Activity Recognition Using Accelerometers
Twomey, N., Diethe, T., Fafoutis, X., Elsts, A., McConville, R., Flach, P., & Craddock, I. (2018) · doi:10.20944/preprints201803.0147.v1 · Cited by 143
Human activity recognition with inertial sensors using a deep learning approach
Zebin, T., Scully, P. J., & Ozanyan, K. B. (2016) · 2016 IEEE SENSORS · doi:10.1109/icsens.2016.7808590 · Cited by 140
“CNN has recently been applied to the problem of activity recognition in number of research papers [2, 4, 8].”
BackgroundMethodChange detection based on Faster R-CNN for high-resolution remote sensing images
Wang, Q., Zhang, X., Chen, G., Dai, F., Gong, Y., & Zhu, K. (2018) · Remote Sensing Letters · doi:10.1080/2150704x.2018.1492172 · Cited by 153
“At the same time, we compare with other DL-based methods including stacked autoencoder (SAE) (Schlkopf, Platt, and Hofmann 2006), CNN (Hu et al. 2015) and long short-term memory (LSTM) (Ordez and Roggen 2016).”
MethodPrediction of 8-state protein secondary structures by a novel deep learning architecture
Zhang, B., Li, J., & Lü, Q. (2018) · BMC Bioinformatics · doi:10.1186/s12859-018-2280-5 · Cited by 140
“The application of the convolution operator is dependent upon input dimensionality [34].”
Mekruksavanich, S., & Jitpattanakul, A. (2021) · Electronics · doi:10.3390/electronics10141685 · Cited by 138
Gochoo, M., Tan, T.-H., Liu, S.-H., Jean, F.-R., Alnajjar, F., & Huang, S.-C. (2018) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2018.2833618 · Cited by 137
“Ordóñez and Roggen [39] have proposed activity recognition classifier using DCNN and long short-term memory (LSTM) and two open datasets collected by seven inertial measurement units and 12 tri-axial accelerometer wearable sensors.”
BackgroundMethodLiu, J., Huang, X., Li, Q., Chen, Z., Liu, G., & Tai, Y. (2023) · Energy Conversion and Management · doi:10.1016/j.enconman.2023.116804 · Cited by 152
Sigcha, L., Costa, N., Pavón, I., Costa, S., Arezes, P., López, J. M., & De Arcas, G. (2020) · Sensors · doi:10.3390/s20071895 · Cited by 126
LSTM-Based Analysis of Industrial IoT Equipment
Zhang, W., Guo, W., Liu, X., Liu, Y., Zhou, J., Li, B., Lu, Q., & Yang, S. (2018) · IEEE Access · doi:10.1109/access.2018.2825538 · Cited by 135
“Ordóñez and Roggen [19] pointed out that the convolutional LSTM architecture achieved significantly better results than traditional ways, even though the classifier was trained on raw input sequences without any further feature engineering.”
BackgroundMorales, F. J. O., & Roggen, D. (2016) · Proceedings of the 2016 ACM International Symposium on Wearable Computers · doi:10.1145/2971763.2971764 · Cited by 136
“For additional details see a prior simpler model not including pooling layers [17].”
BackgroundMethodResultInfluentialSelf-citationPeng (2018) · doi:10.1145/3214277 · Cited by 134
“This work is inspired by other related studies [23, 24], both applied a CNN plus LSTM structure for HAR.”
BackgroundMethodInfluentialA Review on Deep Learning Techniques for IoT Data
Lakshmanna, K., Kaluri, R., Gundluru, N., Alzamil, Z. S., Rajput, D. S., Khan, A. A., Haq, M. A., & Alhussen, A. (2022) · Electronics · doi:10.3390/electronics11101604 · Cited by 154
A Deep Learning Framework for Driving Behavior Identification on In-Vehicle CAN-BUS Sensor Data
Zhang, J., Wu, Z., Li, F., Xie, C., Ren, T., Chen, J., & Liu, L. (2019) · Sensors · doi:10.3390/s19061356 · Cited by 150
“However, traditional feature extraction methods for driving behavior identification adopt sliding window for static and periodic activities modeling [14].”
MethodA review of machine learning-based human activity recognition for diverse applications
Kulsoom, F., Narejo, S., Mehmood, Z., Chaudhry, H. N., Butt, A., & Bashir, A. K. (2022) · Neural Computing and Applications · doi:10.1007/s00521-022-07665-9 · Cited by 168
“RNN plays a vital role in HAR since each action depends on previous actions and sequence-based operations are vital for HAR pipelines [142].”
BackgroundInfluentialAccurate Ambulatory Gait Analysis in Walking and Running Using Machine Learning Models
Zhang, H., Guo, Y. P., & Zanotto, D. (2019) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2019.2958679 · Cited by 155
Triple Cross-Domain Attention on Human Activity Recognition Using Wearable Sensors
Tang, Y., Zhang, L., Teng, Q., Min, F., & Song, A. (2022) · IEEE Transactions on Emerging Topics in Computational Intelligence · doi:10.1109/tetci.2021.3136642 · Cited by 139
“At the same time, our method is also superior to DeepConvLSTM [37] by a large margin of 2.91%.”
MethodInfluentialQi, W., & Aliverti, A. (2019) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2019.2963048 · Cited by 143
“communicate, collect, and exchange information [5], [6].”
Human activity recognition using wearable sensors by heterogeneous convolutional neural networks
Han, C., Zhang, L., Tang, Y., Huang, W., Min, F., & He, J. (2022) · Expert Systems with Applications · doi:10.1016/j.eswa.2022.116764 · Cited by 130
Shallow Convolutional Neural Networks for Human Activity Recognition Using Wearable Sensors
Huang, W., Zhang, L., Gao, W., Min, F., & He, J. (2021) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2021.3091990 · Cited by 129
“However, most existing CNNs for HAR typically overlook information exchange [13] [14] among channels within the same layer.”
BackgroundMethodInfluentialSurvey on automatic lip-reading in the era of deep learning
Fernandez-Lopez, A., & Sukno, F. M. (2018) · Image and Vision Computing · doi:10.1016/j.imavis.2018.07.002 · Cited by 148
“On the other hand, LSTMs are recurrent neural networks (RNN) useful for modeling sequences due to their cyclic connections that form a temporal memory [172, 173].”
BackgroundAnalysis on change detection techniques for remote sensing applications: A review
Afaq, Y., & Manocha, A. (2021) · Ecological Informatics · doi:10.1016/j.ecoinf.2021.101310 · Cited by 150
Attention-based LSTM predictive model for the attitude and position of shield machine in tunneling
Kang, Q., Chen, E. J., Li, Z., et al. (2023) · Underground Space · doi:10.1016/j.undsp.2023.05.006 · Cited by 127
Deep Learning in Mobile and Wireless Networking: A Survey
Zhang, C., Patras, P., & Haddadi, H. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1803.04311 · Cited by 122
“, [113], [254], [257], [263], [264], [478], and [479]) based on patterns observed in the output of the mobile camera or other sensors.”
BackgroundInfluentialTunca, C., Salur, G., & Ersoy, C. (2019) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2019.2958879 · Cited by 141
“More related to the topic at hand, they have recently gained popularity for gait biometrics [46], and for human action and activity recognition, either based on computer vision [47] or wearable sensors [48].”
BackgroundLocomotion Activity Recognition Using Stacked Denoising Autoencoders
Gu, F., Khoshelham, K., Valaee, S., Shang, J., & Zhang, R. (2018) · IEEE Internet of Things Journal · doi:10.1109/jiot.2018.2823084 · Cited by 124
“The commonly used deep learning methods include stacked autoencoders [15], deep belief networks [31], convolutional neural networks [12], and recurrent neural networks [33].”
MethodWearable Sensor-Based Human Activity Recognition Using Hybrid Deep Learning Techniques
Wang, H., Zhao, J., Li, J., Tian, L., Tu, P., Cao, T., An, Y., Wang, K., & Li, S. (2020) · Security and Communication Networks · doi:10.1155/2020/2132138 · Cited by 124
“*e convolution layer and pooling layer are stacked to form a deep structure, which can automatically extract the action feature information from the original action data [5].”
BackgroundYu, Z., Yang, K., Luo, Y., et al. (2019) · Journal of Hydrology · doi:10.1016/j.jhydrol.2019.124488 · Cited by 123
Human Activity Recognition Based on Motion Sensor Using U-Net
Zhang, Y., Zhang, Z., Zhang, Y., Bao, J., Zhang, Y., & Deng, H. (2019) · IEEE Access · doi:10.1109/access.2019.2920969 · Cited by 121
Human Activity Recognition Based on Wearable Sensor Using Hierarchical Deep LSTM Networks
Wang, L., & Liu, R. (2019) · Circuits Systems and Signal Processing · doi:10.1007/s00034-019-01116-y · Cited by 141
Detection of abnormal behaviour for dementia sufferers using Convolutional Neural Networks
Arifoglu, D., & Bouchachia, A. (2019) · Artificial Intelligence in Medicine · doi:10.1016/j.artmed.2019.01.005 · Cited by 120
“In [29], the authors use a combination of CNNs and Long Short Term (LSTM) RNNs to do multi-modal wearable activity recogni-”
BackgroundMethodWang, J., Zhang, J., & Wang, X. (2017) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2017.2754641 · Cited by 125
“The LSTM model has been successfully applied in natural language processing [29], image segmentation [30], handwritten recognition [31], and multimodal wearable activity recognition [32].”
MethodGu, F., Khoshelham, K., Yu, C., & Shang, J. (2018) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2018.2871808 · Cited by 128
A Deep Learning Approach for Human Activities Recognition From Multimodal Sensing Devices
Ihianle, I. K., Nwajana, A. O., Ebenuwa, S. H., Otuka, R. I., Owa, K., & Orisatoki, M. O. (2020) · IEEE Access · doi:10.1109/access.2020.3027979 · Cited by 158
“The authors [10], [13], [14] applied Deep learning models to recognise human activities of daily living.”
BackgroundMethodInfluentialA Novel Deep Learning Bi-GRU-I Model for Real-Time Human Activity Recognition Using Inertial Sensors
Tong, L., Ma, H., Lin, Q., He, J., & Peng, L. (2022) · IEEE Sensors Journal · doi:10.1109/jsen.2022.3148431 · Cited by 127
Construction activity recognition with convolutional recurrent networks
Slaton, T., Hernandez, C., & Akhavian, R. (2020) · Automation in Construction · doi:10.1016/j.autcon.2020.103138 · Cited by 131
“Furthermore, state-of-the-art results in human gesture recognition bene fi tted greatly from combining di ff erent sensor modalities [32].”
BackgroundMethodInfluentialHuang, W., Zhang, L., Wu, H., Min, F., & Song, A. (2022) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2022.3174816 · Cited by 155
“:3) o ~ nez et al. present a hybrid network architecture called DeepConvLSTM [46] that ensembles CNN and LSTM layers.”
BackgroundGenetic algorithms for hyperparameter optimization in predictive business process monitoring
Francescomarino, C. D., Dumas, M., Federici, M., Ghidini, C., Maggi, F., Rizzi, W., & Simonetto, L. (2018) · Information Systems · doi:10.1016/j.is.2018.01.003 · Cited by 107
Human Activity Recognition and Embedded Application Based on Convolutional Neural Network
Yang, X., & Qiu, T. T. (2020) · Journal of Artificial Intelligence and Technology · doi:10.37965/jait.2020.0051 · Cited by 116
Improve Unsupervised Domain Adaptation with Mixup TrainingPreprint
Yan, S., Song, H., Li, N., Zou, L., & Liu, R. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2001.00677 · Cited by 290
“The architecture of the embedding encoder f is task-specific: we use similar architectures to [6] for visual recognition and WiFi datasets; we employ state-of-the-art Deep-ConvLSTM architecture [11] for OPPORTUNITY.”
MethodANN-based automated scaffold builder activity recognition through wearable EMG and IMU sensors
Bangaru, S. S., Wang, C., Busam, S. A., & Aghazadeh, F. (2021) · Automation in Construction · doi:10.1016/j.autcon.2021.103653 · Cited by 114
Human Activity Recognition from Body Sensor Data using Deep Learning
Hassan, M. M., Huda, S., Uddin, M. Z., Almogren, A., & Alrubaian, M. (2018) · Journal of Medical Systems · doi:10.1007/s10916-018-0948-z · Cited by 113
ColloSSL: Collaborative Self-Supervised Learning for Human Activity Recognition
Jain, Y., Tang, C. I., Min, C., Kawsar, F., & Mathur, A. (2022) · Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies · doi:10.1145/3517246 · Cited by 113
“For this purpose, a number of deep learning based sensor fusion techniques [37, 39, 61, 65, 66] have been proposed, which train a fusion model by concatenating multiple sensor streams.”
How Accurately Can Your Wrist Device Recognize Daily Activities and Detect Falls?
Gjoreski, M., Gjoreski, H., Luštrek, M., & Gams, M. (2016) · Sensors · doi:10.3390/s16060800 · Cited by 112
Qi, W., Su, H., Yang, C., Ferrigno, G., De Momi, E., & Aliverti, A. (2019) · Sensors · doi:10.3390/s19173731 · Cited by 111
“A deep generic framework based on CNN and RNN (LSTM) units were implemented on multimodal wearable sensors [45].”
MethodExtracting biological age from biomedical data via deep learning: too much of a good thing?
Pyrkov, T. V., Slipensky, K., Barg, M., Kondrashin, A., Zhurov, B., Zenin, A., Pyatnitskiy, M., Menshikov, L., Markov, S., & Fedichev, P. O. (2018) · Scientific Reports · doi:10.1038/s41598-018-23534-9 · Cited by 111
“However, deep CNNs bring the idea to an entirely new level and are particularly useful for automation of the most relevant features engineering from the data in relation to human activity recognition (HAR) [33, 34], spe-”
BackgroundA Multichannel CNN-GRU Model for Human Activity Recognition
Lu, L., Zhang, C., Cao, K., Deng, T., & Yang, Q. (2022) · IEEE Access · doi:10.1109/access.2022.3185112 · Cited by 124
“A hybrid CNN-LSTM model is proposed in [35] for multi-mode wearable sensor devices.”
MethodMehmood, I., Li, H., Qarout, Y., Umer, W., Anwer, S., Wu, H., Hussain, M., & Antwi‐Afari, M. F. (2023) · Advanced Engineering Informatics · doi:10.1016/j.aei.2023.101978 · Cited by 131
Extracting biological age from biomedical data via deep learning: too much of a good thing?
(2017) · doi:10.1101/219162 · Cited by 109
Servati, A., Zou, L., Wang, Z., Ko, F., & Servati, P. (2017) · Sensors · doi:10.3390/s17071622 · Cited by 106
Abedin, A., Ehsanpour, M., Shi, Q., Rezatofighi, H., & Ranasinghe, D. C. (2021) · Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies · doi:10.1145/3448083 · Cited by 107
“Combining these concepts, [12] proposes DeepConvLSTM by pairing convolutional and recurrent networks in order to model the temporal correlations at a more abstract representation level.”
BackgroundMethodZebin, T., Sperrin, M., Peek, N., & Casson, A. J. (2018) · 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc.2018.8513115 · Cited by 107
“[5] used a DeepConvLSTM network and achieved 91.”
BackgroundMethodInfluentialAnomaly Detection in Videos Using Optical Flow and Convolutional Autoencoder
Duman, E., & Erdem, O. A. (2019) · IEEE Access · doi:10.1109/access.2019.2960654 · Cited by 115
Hybrid deep CNN-SVR algorithm for solar radiation prediction problems in Queensland, Australia
Ghimire, S., Bhandari, B., Casillas-Pérez, D., Deo, R. C., & Salcedo‐Sanz, S. (2022) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2022.104860 · Cited by 124
Human Action Recognition Using Deep Learning Methods on Limited Sensory Data
Tüfek, N., Yalcin, M., Altıntaş, M., Kalaoğlu, F., Li, Y., & Bahadır, S. K. (2019) · IEEE Sensors Journal · doi:10.1109/jsen.2019.2956901 · Cited by 117
“Moreover, we have implemented several methods in order to compare the results of the deep learning methods including Dynamic Time Warping (DTW) [26] and kNN, one dimensional CNN (1D CNN [27]), two-dimensional CNN 2D CNN [28]), 2 layer LSTM [29], 3 layer LSTM [30], bidirectional LSTM [31], 1D CNN and LSTM on UCI HAR da…”
MethodThakur, D., Biswas, S., Ho, E. S. L., & Chattopadhyay, S. (2022) · IEEE Access · doi:10.1109/access.2022.3140373 · Cited by 112
“In [73], the authors proposed CNN-and LSTM-based HAR solutions using two different public datasets collected by wearable sensors.”
Deep Neural Networks for Sensor-Based Human Activity Recognition Using Selective Kernel Convolution
Gao, W., Zhang, L., Huang, W., Min, F., He, J., & Song, A. (2021) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2021.3102735 · Cited by 105
“In the multimodal HAR scenario, Ordóñez and Roggen [22] presented a DeepConvLSTM network, which combines convolutional and LSTM units for fusing multimodal sensor information to improve recognition performance.”
BackgroundMethodResultInfluential
Metadata
- Authors
- Ordóñez, F., & Roggen, D.
- Affiliations
- University of Sussex (GB)
- Corresponding author
- Ordóñez, Francisco
- Venue
- Sensors
- Publisher
- MDPI AG
- Published
- 2016-01-18
- Volume
- 16
- Issue
- 1
- Pages
- 115
- ISSN
- 1424-8220 (ISSN-L)
- PMC
- PMC4732148
- OpenAlex
- W2270470215
- Cited by
- 2,761
- References
- 49
- Citations by year
- 2026: 284 · 2025: 256 · 2024: 284 · 2023: 270 · 2022: 319 · 2021: 379 · 2020: 347 · 2019: 288 · 2018: 219 · 2017: 93 · 2016: 21
- FWCI
- 140.52
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Sensors (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- Sussex Research Online (University of Sussex) (submittedVersion, cc-by)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Figshare (submittedVersion, cc-by)
- Funders
- Google Faculty Research Award (Is deep learning useful for wearable activity recognition?)
- EPSRC (EP/N007816/1)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Context-Aware Activity Recognition Systems
- Physical Sciences › Engineering › Biomedical Engineering › Gait Recognition and Analysis
- Physical Sciences › Computer Science › Signal Processing › Time Series Analysis and Forecasting
- Keywords
- human activity recognition, wearable sensors, multimodal sensor fusion, convolutional neural networks, LSTM neural network, temporal dynamics, automatic feature extraction, hyperparameter optimization
- MeSH terms
- Machine Learning, Clothing, Humans, Human Activities, Signal Processing, Computer-Assisted, Databases, Factual, Neural Networks, Computer, Monitoring, Ambulatory
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.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-10-10, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-10 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol).
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
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.