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 501–600 of 2,807
Real-Time Physical Activity Recognition on Smart Mobile Devices Using Convolutional Neural Networks
Peppas, K. P., Tsolakis, A. C., Krinidis, S., & Tzovaras, D. K. (2020) · Applied Sciences · doi:10.3390/app10238482 · Cited by 53
Activity, Plan, and Goal Recognition: A Review
Van-Horenbeke, F. A., & Peer, A. (2021) · Frontiers in Robotics and AI · doi:10.3389/frobt.2021.643010 · Cited by 66
“Ordóñez and Roggen (2016) combined convolutional neural networks with long short-term memory networks for the task of activity recognition.”
BackgroundRobust human position estimation in cooperative robotic cells
Amorim, A., Guimares, D., Mendona, T., et al. (2020) · Robotics and Computer-Integrated Manufacturing · doi:10.1016/j.rcim.2020.102035 · Cited by 44
Nguyen-Trong, K., Vu, H. N., Trung, N. N., & Pham, C. (2021) · IEEE Sensors Journal · doi:10.1109/jsen.2021.3074642 · Cited by 54
Iterative Learning Control for a Soft Exoskeleton with Hip and Knee Joint Assistance
Chen, C., Zhang, Y., Li, Y., Wang, Z., Liu, Y., Cao, W., & Wu, X. (2020) · Sensors · doi:10.3390/s20154333 · Cited by 48
A human activity recognition method using wearable sensors based on convtransformer model
Zhang, Z., Wang, W., An, A., Qin, Y., & Yang, F. (2023) · Evolving Systems · doi:10.1007/s12530-022-09480-y · Cited by 48
“Ordóñez et al. propose a deep convolutional and lstm recurrent neural networks (DeepConvLSTM) to improve the convergence speed of LSTM and overcome the limitations of modeling the local information of the inputs (Ordóñez and Roggen 2016).”
BackgroundA.Santoyo-Ramón, J., Casilari, E., & Cano, J. M. B. (2022) · Measurement · doi:10.1016/j.measurement.2022.110945 · Cited by 53
HAR-DeepConvLG: Hybrid deep learning-based model for human activity recognition in IoT applications
Ding, W., Abdel‐Basset, M., & Mohamed, R. (2023) · Information Sciences · doi:10.1016/j.ins.2023.119394 · Cited by 51
Deep Auto-Set: A Deep Auto-Encoder-Set Network for Activity Recognition Using Wearables
Varamin, A. A., Abbasnejad, E., Shi, Q., Ranasinghe, D. C., & Rezatofighi, H. (2018) · Proceedings of the 15th EAI International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services · doi:10.1145/3286978.3287024 · Cited by 44
“In this architecture, all convolution (and deconvolution) layers apply afilter ofwidth 5 (as in [16]) and”
BackgroundMethodInfluentialSpherical DNNs and Their Applications in 360 Images and Videos
Xu, Y., Zhang, Z., & Gao, S. (2021) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2021.3100259 · Cited by 44
“The Long Short-Term Memory (LSTM) and the Convolu-tional LSTM (ConvLSTM) [42] have shown their power to extract the temporal features in many video-based computer vision tasks, such as activity recognition [43], anomaly detection [44] and so on.”
BackgroundDeep Convolutional and LSTM Networks on Multi-Channel Time Series Data for Gait Phase Recognition
Kreuzer, D., & Münz, M. (2021) · Sensors · doi:10.3390/s21030789 · Cited by 56
Cross-Domain HAR: Few-Shot Transfer Learning for Human Activity Recognition
Thukral, M., Haresamudram, H., & Plötz, T. (2025) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3704921 · Cited by 71
“Impact of using different encoders in Cross-Domain HAR (using Mobiact source dataset) : we replace the convolutional encoder with DeepConvLSTM [33].”
A Semi-Automatic Annotation Approach for Human Activity Recognition
Bota, P. J., da Silva, J. K. A., Folgado, D., & Gamboa, H. F. S. (2019) · Sensors · doi:10.3390/s19030501 · Cited by 48
Hybrid deep learning approaches for smartphone sensor-based human activity recognition
Ghate, V., & Sweetlin Hemalatha, C. (2021) · Multimedia Tools and Applications · doi:10.1007/s11042-020-10478-4 · Cited by 42
E-commerce Time Series Forecasting using LSTM Neural Network and Support Vector Regression
Chniti, G., Bakir, H., & Zaher, H. (2017) · International Conference on Big Data and Internet of Things (BDIOT) · doi:10.1145/3175684.3175695 · Cited by 51
“The tanh is the output activation function [22].”
BackgroundLi, S., Zhu, T., Duan, F., Chen, L., Ning, H., Nugent, C., & Wan, Y. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3463405 · Cited by 83
“Recent advancements in deep learning have facilitated the application of convolutional neural networks [56], recurrent neural networks [57], and hybrid structures [58] for feature extraction and activity recognition.”
BackgroundLi, B., & Sano, A. (2020) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc44109.2020.9175463 · Cited by 44
“Numerous studies have proved the advantage of distributing raw sensory data in artificial neural networks to learn features through back propagation for predicting activities, depressive states, emotions, etc. [11, 12].”
BackgroundKubota, A., Iqbal, T., Shah, J., & Riek, L. D. (2019) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2019.8793954 · Cited by 59
“In accordance with other real-time activity recognition systems, we sampled our data at a consistent rate of 30Hz in order to reduce the computation required by the systems [8], [9], [30].”
MethodReal time human activity recognition on smartphones using LSTM networks
Milenkoski, M., Trivodaliev, K. V., Kalajdziski, S., Jovanov, M., & Stojkoska, B. R. (2018) · International Convention on Information and Communication Technology, Electronics and Microelectronics · doi:10.23919/mipro.2018.8400205 · Cited by 53
“In [10], LSTM is used for offline activity recognition, using different sensors from wearables.”
MethodWi-PIGR: Path Independent Gait Recognition With Commodity Wi-Fi
Zhang, L., Wang, C., & Zhang, D. (2021) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2021.3052314 · Cited by 51
Cuperman, R., Jansen, K. M. B., & Ciszewski, M. G. (2022) · Sensors · doi:10.3390/s22041347 · Cited by 49
Human Activity Recognition using PCA and BiLSTM Recurrent Neural Networks
Aljarrah, A. A., & Ali, A. H. (2019) · International Conference on Engineering Technology and its Applications (IICETA) · doi:10.1109/iiceta47481.2019.9012979 · Cited by 45
“For instance, [16] have constructed Deep ConvLSTM model for human activity recognition based on the Long Short-Term Memory (LSTM) model and Multimodal Wearable sensors.”
MethodEfficiency investigation of artificial neural networks in human activity recognition
Sütő, J., & Oniga, S. (2017) · Journal of Ambient Intelligence and Humanized Computing · doi:10.1007/s12652-017-0513-5 · Cited by 49
“Nowadays numerous public datasets are available for scientific HAR purposes, including the OPPORTUNITY, PAMAP2, Skoda, Acti-tracker, etc. datasets (Hammerla et al. 2016; Ordonez and Roggen 2016; Zheng et al. 2014).”
BackgroundMallikarjuna, B., Shrivastava, G., & Sharma, M. (2021) · Expert Systems · doi:10.1111/exsy.12778 · Cited by 61
“The patient-relevant data is stored in a cloud database in the form of medical images and process the data by using blockchain (Ord (cid:2) oñez & Roggen, 2016).”
MethodA Context Knowledge Map Guided Coarse-to-Fine Action Recognition
Ji, Y., Zhan, Y., Yang, Y., Xu, X., Shen, F., & Shen, H. T. (2019) · IEEE Transactions on Image Processing · doi:10.1109/tip.2019.2952088 · Cited by 42
“Some researches extracted multi-modal motion features and fused then to improve recognition performance [10], [16], [22], [26], [27].”
BackgroundHate Speech Detection: A Solved Problem? The Challenging Case of Long Tail on Twitter
Zhang, Z., & Luo, L. (2018) · White Rose Research Online (University of Leeds, The University of Sheffield, University of York) · doi:10.48550/arxiv.1803.03662 · Cited by 42
Human Activity Recognition from Wearable Sensor Data Using Self-AttentionPreprint
Mahmud, S., Tonmoy, M. T. H., Bhaumik, K. K., Rahman, A. K. M. M., Amin, M. A., Shoyaib, M., Khan, M. A. H., & Ali, A. (2020) · European Conference on Artificial Intelligence · doi:10.48550/arxiv.2003.09018 · Cited by 132
“…human activity recognition datasets: PAMAP2 [21], USC-HAD [28], Opportunity [22], and SKODA [23] and compared our results with the current state-of-the-art techniques namely DeepConvLSTM [17] and Convolutional Autoencoder (ConvAE) [10] to demonstrate the effectiveness of the proposed approach.”
BackgroundMethodResultInfluentialAgac, S., & İncel, Ö. D. (2023) · Diagnostics · doi:10.3390/diagnostics13111861 · Cited by 60
“DeepConvLSTM, presented in [30], is one of the most popular deep learning architectures proposed for sensor-based multimodal wearable activity recognition.”
BackgroundDeep learning based trajectory optimization for UAV aerial refueling docking under bow wave
Liu, Y., Wang, H., Su, Z., & Fan, J. (2018) · Aerospace Science and Technology · doi:10.1016/j.ast.2018.07.024 · Cited by 44
A Deep Machine Learning Method for Concurrent and Interleaved Human Activity Recognition
Thapa, K., Al, Z. M. A., Lamichhane, B., & Yang, S. (2020) · Sensors · doi:10.3390/s20205770 · Cited by 44
A Deep Learning Method for Complex Human Activity Recognition Using Virtual Wearable Sensors
Xiao, F., Pei, L., Chu, L., Zou, D., Yu, W., Zhu, Y., & Li, T. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-69873-7_19 · Cited by 59
Samanta, R. K., Sadhukhan, B., Samaddar, H., Sarkar, S., Koner, C., & Ghosh, M. (2022) · CAAI Transactions on Intelligence Technology · doi:10.1049/cit2.12114 · Cited by 53
X-CHAR: A Concept-based Explainable Complex Human Activity Recognition Model
Jeyakumar, J. V., Sarker, A., Garcia, L. A., & Srivastava, M. B. (2023) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3580804 · Cited by 58
“Francisco et al. [41] used a hybrid model consisting of both convolutional layers and recurrent layers that can capture the Spatio-temporal relationships in the data to infer the activities.”
A Cascade Ensemble Learning Model for Human Activity Recognition with Smartphones
Xu, S., Tang, Q., Jin, L., & Pan, Z. (2019) · Sensors · doi:10.3390/s19102307 · Cited by 46
Dawar, N., & Kehtarnavaz, N. (2018) · IEEE Access · doi:10.1109/access.2017.2788558 · Cited by 41
“[14]–[16].”
Transportation mode recognition fusing wearable motion, sound and vision sensors
Richoz, S., Wang, L., Birch, P. M., & Roggen, D. (2020) · IEEE Sensors Journal · doi:10.1109/jsen.2020.2987306 · Cited by 46
“Many machine learning approaches have been proposed to fuse multimodal information for classification tasks [31], [33], [39], [40].”
BackgroundMethodSelf-citationHassan, M. M., Ullah, S., Hossain, M. S., & Alelaiwi, A. A. (2020) · The Journal of Supercomputing · doi:10.1007/s11227-020-03361-4 · Cited by 45
“Among the deep learning algorithms, deep belief network (DBN) [13–16], convolutional neural network (CNN) [19–22], recurrent neural networks (RNNs) [17, 18] and deep neural network [23] are being used for human activity recognition.”
BackgroundMethodMulti-STMT: Multi-Level Network for Human Activity Recognition Based on Wearable Sensors
Zhang, H., & Xu, L. (2024) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2024.3365155 · Cited by 57
“Recently, a novel deep-learning model called convolutional neural network (CNN)–RNN has been successfully applied to HAR, outperforming simple CNN and RNN models [14], [15], [16].”
MethodJourdan, T., Debs, N., & Frindel, C. (2021) · Sensors · doi:10.3390/s21144808 · Cited by 50
“…features if their samples were more limited regarding the number of patients [38,63,68,69,79,81,86,95,100] or the acquisition time [34–36,45 ,97 Finally, it should be mentioned that machine learning also has drawbacks, with the first being the computational time required to train a model [106].”
Zhou, K., & Liu, Y. (2021) · Sensors · doi:10.3390/s21144826 · Cited by 44
WISNet: A deep neural network based human activity recognition system
Sharen, H., Anbarasi, L. J., Rukmani, P., Gandomi, A. H., Neeraja, R., & Narendra, M. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2024.124999 · Cited by 49
Benchmarking the SHL Recognition Challenge with Classical and Deep-Learning Pipelines
Wang, L., Gjoreski, H., Ciliberto, M., Mekki, S., Valentin, S., & Roggen, D. (2018) · ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp) · doi:10.1145/3267305.3267531 · Cited by 40
Self-citationDeep Ensemble Learning for Human Activity Recognition Using Wearable Sensors via Filter Activation
Huang, W., Zhang, L., Wang, S., Wu, H., & Song, A. (2022) · ACM Transactions on Embedded Computing Systems · doi:10.1145/3551486 · Cited by 53
“Ordóñez et al. [22] proposed a hybrid model called DeepConvLSTM , which combines CNNs and LSTMs to simultaneously capture local and global features for HAR .”
BackgroundMethodInfluentialDeep Triplet Networks with Attention for Sensor-based Human Activity Recognition
Khaertdinov, B., Ghaleb, E., & Asteriadis, S. (2021) · IEEE International Conference on Pervasive Computing and Communications · doi:10.1109/percom50583.2021.9439116 · Cited by 52
“Architectures which are typically used for this problem include Convolutional Neural Networks (CNNs) [5], [6], Recurrent Neural Networks (RNNs) [7], [8] or hybrid models containing both architectures [9], [10].”
BackgroundMethodDeep Learning for Activity Recognition in Older People Using a Pocket-Worn Smartphone
Nan, Y., Lovell, N. H., Redmond, S. J., Wang, K., Delbaere, K., & van Schooten, K. S. (2020) · Sensors · doi:10.3390/s20247195 · Cited by 46
“LSTM was combined with a CNN in [14], and compared to a CNN alone, with the hybrid model (DeepConvLSTM) improving the result by six percent.”
BackgroundMethodXia, S., Chu, L., Pei, L., Zhang, Z., Yu, W., & Qiu, R. C. (2021) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2021.3111996 · Cited by 40
Human activity recognition: suitability of a neuromorphic approach for on-edge AIoT applications
Fra, V., Forno, E., Pignari, R., Stewart, T. C., Macii, E., & Urgese, G. (2022) · Neuromorphic Computing and Engineering · doi:10.1088/2634-4386/ac4c38 · Cited by 60
“…of representative window sizes employed in the HAR task is reported, showing that typical choices fall within 1 s and 10 s. Exceptions can be found in works by Ordoñez et al [73], by Wan et al [74] and by Xia et al [75], where temporal windows down to 0.25 s are employed for different datasets.”
MethodInfluentialDetection of Tennis Activities with Wearable Sensors
Benages-Pardo, L., Pérez, D. B., & Orrite-Uruñuela, C. (2019) · Sensors · doi:10.3390/s19225004 · Cited by 45
“This kind of networks are also used to extract features in temporal signals such as those provided by wearable sensors [22–26].”
Efficiency of deep neural networks for joint angle modeling in digital gait assessment
Alcaraz, J. C., Moghaddamnia, S., & Peissig, J. (2021) · EURASIP Journal on Advances in Signal Processing · doi:10.1186/s13634-020-00715-1 · Cited by 46
MSAF: Multimodal Split Attention FusionPreprint
Su, L., Hu, C., Li, G., & Cao, D. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2012.07175 · Cited by 91
“Early Fusion. The majority of works in early fusion integrate features immediately after they are extracted from each modality, whereas occasionally studies perform fusion at the input level, such as [31]. A simple solution for early fusion is feature concatenation after they are transformed to the same length, follow…”
BackgroundAdversarial Multi-view Networks for Activity Recognition
Bai, L., Yao, L., Wang, X., Kanhere, S. S., Guo, B., & Yu, Z. (2020) · Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies · doi:10.1145/3397323 · Cited by 40
“Based on this observation, Murahari and Plötz [39] extend the DeepConvLSTM [40] by adding the temporal attention module after the LSTM layer.”
BackgroundMethodInfluentialTu, X., Mallik, A., Chen, D., Han, K., Altintas, O., Wang, H., & Xie, J. L. (2023) · ACM/IEEE Symposium on Edge Computing (SEC) · doi:10.1145/3583740.3628442 · Cited by 74
“…[4, 5], object detection and tracking [6–8], image super-resolution [9–11], segmentation [12], pose estimation [13], and gesture recognition [14]; (2) natural language processing (NLP) based applications, such as smart reply [15], question answering [16], language translation [17, 18], and…”
New LSTM Deep Learning Algorithm for Driving Behavior Classification
Kadri, N., Ellouze, A., Ksantini, M., & Turki, S. H. (2022) · Cybernetics & Systems · doi:10.1080/01969722.2022.2059133 · Cited by 41
“…studies have been carried out and used to recognize and classify driving behavior from smartphone sensors with deep learning algorithms (Yu et al. 2017; Meseguer et al. 2017; Ord (cid:1) o ~ nez and Roggen 2016; Saleh, Hossny, and Nahavandi 2017; Pienaar and Malekian 2019; Guney and Erdas 2019).”
BackgroundRandom Search One Dimensional CNN for Human Activity Recognition
Ragab, M. G., Abdulkadir, S. J., & Aziz, N. (2020) · doi:10.1109/icci51257.2020.9247810 · Cited by 51
“DeepConvLSTM [20] 95.”
MethodInfluentialLiang, W., Wang, F., Fan, A., Zhao, W., Yao, W., & Yang, P. (2023) · Sensors · doi:10.3390/s23094229 · Cited by 59
Quality prediction in injection molding
Nagorny, P., Pillet, M., Pairel, É., Goff, R. L., Loureaux, J., Wali, M., & Kiener, P. (2017) · IEEE International Conference on Computational Intelligence and Virtual Environments for Measurement Systems and Applications (CIVEMSA) · doi:10.1109/civemsa.2017.7995316 · Cited by 54
“Previous works showed good results on raw signals classification [33].”
ResultKPI-TSAD: A Time-Series Anomaly Detector for KPI Monitoring in Cloud Applications
Qiu, J., Du, Q., & Qian, C. (2019) · Symmetry · doi:10.3390/sym11111350 · Cited by 51
An Ultra-Low Energy Human Activity Recognition Accelerator for Wearable Health Applications
Bhat, G., Tuncel, Y., An, S., Lee, H. G., & Ogras, U. Y. (2019) · ACM Transactions on Embedded Computing Systems · doi:10.1145/3358175 · Cited by 48
“Recently, deep convolutional neural networks (CNN) and recurrent neural networks (RNN) have been employed for human activity recognition [19, 35].”
BackgroundIndoor Localization Using Smartphone Magnetic and Light Sensors: a Deep LSTM Approach
Wang, X., Yu, Z., & Mao, S. (2019) · Mobile Networks and Applications · doi:10.1007/s11036-019-01302-x · Cited by 47
Leveraging Sound and Wrist Motion to Detect Activities of Daily Living with Commodity Smartwatches
Bhattacharya, S., Adaimi, R., & Thomaz, E. (2022) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3534582 · Cited by 55
“Taking as input the raw inertial sensory data, we explored 2 models to establish a baseline performance on our dataset: (1) DeepConvLSTM [41] and (2) Attend&Discriminate [1].”
MethodSteil, J., Müller, P., Sugano, Y., & Bulling, A. (2018) · MPG.PuRe (Max Planck Society) · Cited by 40
Medina, M. Á. L., Espinilla, M., Paggeti, C., & Medina-Quero, J. (2019) · Sensors · doi:10.3390/s19163512 · Cited by 41
“More recently, wearable devices have been used to analyze activities and gestures in AR [7].”
MethodA Novel CNN-BiLSTM-GRU Hybrid Deep Learning Model for Human Activity Recognition
Lalwani, P. D., & Ganeshan, R. (2024) · International Journal of Computational Intelligence Systems · doi:10.1007/s44196-024-00689-0 · Cited by 45
“The problems with multimodal wearable sensors were tackled by Ordonez et al. [18] Using a Convolutional Neural Network (CNN) framework and smartphone sensors, researchers in [20] developed a Human Activity Recognition (HAR) model to recognize different human behaviors.”
Leng, Z., Kwon, H., & Ploetz, T. (2023) · Proceedings of the 2023 International Symposium on Wearable Computers · doi:10.1145/3594738.3611361 · Cited by 39
“Yet, when only virtual IMU dataset was used for DeepConvLSTM, the performance significantly drop due to too small training dataset.”
MethodA Survey on Intelligent Gesture Recognition Techniques
Ojeda-Castelo, J. J., Capobianco-Uriarte, M. D. L. M., Piedra-Fernandez, J. A., & Ayala, R. (2022) · IEEE Access · doi:10.1109/access.2022.3199358 · Cited by 50
“3) In [130], the authors have developed a Deep Learning-based framework called DeepConvLSTM that combines convolutional layers and recurring LSTMs, in order to recognize human activity from data extracted by wearable sensors.”
BackgroundLocation-based Daily Human Activity Recognition using Hybrid Deep Learning Network
Mekruksavanich, S., Promsakon, C., & Jitpattanakul, A. (2021) · International Joint Conference on Computer Science and Software Engineering · doi:10.1109/jcsse53117.2021.9493807 · Cited by 39
Wang, L., Zhou, Y., Li, R., & Ding, L. (2022) · Knowledge-Based Systems · doi:10.1016/j.knosys.2022.109351 · Cited by 39
Energy-aware human activity recognition for wearable devices: A comprehensive review
Contoli, C., Freschi, V., & Lattanzi, E. (2024) · Pervasive and Mobile Computing · doi:10.1016/j.pmcj.2024.101976 · Cited by 55
Understanding Medication Nonadherence from Social Media: A Sentiment-Enriched Deep Learning Approach
Xie, J., Liu, X., Zeng, D. D., & Fang, X. (2017) · MIS Quarterly · doi:10.25300/misq/2022/15336 · Cited by 59
Hernandez, V., Suzuki, T., & Venture, G. (2020) · PLoS ONE · doi:10.1371/journal.pone.0228869 · Cited by 48
“Regarding deep learning, the state of the art on HAR is presented by Ordóñez and Roggen [17] adapted from Sainath et al. [18] for speech recognition.”
MethodResultInfluentialCapsGaNet: Deep Neural Network Based on Capsule and GRU for Human Activity Recognition
Sun, X., Xu, H., Dong, Z., Shi, L., Liu, Q., Li, J., Li, T., Fan, S., & Wang, Y. (2022) · IEEE Systems Journal · doi:10.1109/jsyst.2022.3153503 · Cited by 38
“Deep CNNs are used to build a new multichannel sequential data structure for multi-sensor recognition in [23].”
MethodAñazco, E. V., Han, S. J., Kim, K., Lopez, P. R., Kim, T.-S., & Lee, S. (2021) · Sensors · doi:10.3390/s21041404 · Cited by 45
Pain Assessment based on fNIRS using Bi-LSTM RNNs
Rojas, R. F., Romero, J., López-Aparicio, J., et al. (2021) · International IEEE/EMBS Conference on Neural Engineering · doi:10.1109/ner49283.2021.9441384 · Cited by 38
Efficient cell classification of mitochondrial images by using deep learning
Iqbal, M. S., El-Ashram, S. A., Hussain, S., Khan, T., Huang, S., Mehmood, R., & Luo, B. (2019) · Journal of Optics · doi:10.1007/s12596-018-0508-4 · Cited by 41
Gait Recognition With Wearable Sensors Using Modified Residual Block-Based Lightweight CNN
Hasan, M. A. M., Abir, F. A., Siam, M. M. H. K., & Shin, J. (2022) · IEEE Access · doi:10.1109/access.2022.3168019 · Cited by 42
PerceptionNet: A Deep Convolutional Neural Network for Late Sensor Fusion
Kasnesis, P., Patrikakis, C. Z., & Venieris, I. S. (2018) · Advances in intelligent systems and computing · doi:10.1007/978-3-030-01054-6_7 · Cited by 49
“Finally, in order to test the general applicability of our approach we used the same CNN architecture on the PAMAP2 dataset and compared it with the conventional CNN-EF [14] and the Convolutional LSTM [15] methods.”
BackgroundMethodInfluentialWearable Computing With Distributed Deep Learning Hierarchy: A Study of Fall Detection
Qian, X., Chen, H., Jiang, H., Green, J., Cheng, H., & Huang, M.-C. (2020) · IEEE Sensors Journal · doi:10.1109/jsen.2020.2988667 · Cited by 38
“Furthermore, some well-known machine learning algorithms such as decision tree and deep learning have emerged as a promising method in fall-related researches [22], [23].”
BackgroundLuo, H., Huang, M., & Zhou, Z. (2018) · Journal of Sound and Vibration · doi:10.1016/j.jsv.2018.05.007 · Cited by 40
Parallel memetic algorithm for training recurrent neural networks for the energy efficiency problem
Ruiz, L. G. B., Capel, M. I., & Pegalajar, M. C. (2018) · Applied Soft Computing · doi:10.1016/j.asoc.2018.12.028 · Cited by 37
Abukhodair, F., Alsaggaf, W., Jamal, A. T., et al. (2021) · Mathematics · doi:10.3390/math9202627 · Cited by 37
“Based on the elected FF, the corresponding fitness value of the right and left antennae are estimated, and beetles move toward the antennae using a smaller fitness number [24,25].”
MethodMachine Learning Solutions for Bridge Scour Forecast Based on Monitoring Data
Yousefpour, N., Downie, S., Walker, S., Perkins, N., & Dikanski, H. (2021) · Transportation Research Record Journal of the Transportation Research Board · doi:10.1177/03611981211012693 · Cited by 43
RepHAR: Decoupling Networks With Accuracy-Speed Tradeoff for Sensor-Based Human Activity Recognition
Teng, Q., Tang, Y., & Hu, G. (2023) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2023.3240198 · Cited by 39
“In the multimodal HAR scenario, Ordóñez and Roggen [23] devised a generic deep learning framework that considers temporal dynamics for activity recognition based on convolutional and long short-term memory (LSTM) recurrent units.”
UAV surveillance for violence detection and individual identification
Srivastava, A., Badal, T., Saxena, P., Vidyarthi, A., & Singh, R. (2022) · Automated Software Engineering · doi:10.1007/s10515-022-00323-3 · Cited by 42
Chikhaoui, B., & Gouineau, F. (2017) · 2017 IEEE International Conference on Data Mining Workshops (ICDMW) · doi:10.1109/icdmw.2017.97 · Cited by 36
“[32] proposed a model that combines deep convolutional networks and long short term memory”
BackgroundSurvey on encode biometric data for transmission in wireless communication networks
Ali, M. H., Ibrahim, A. M., Wahbah, H., & Barazanchi, I. I. A. (2021) · Periodicals of Engineering and Natural Sciences (PEN) · doi:10.21533/pen.v9i4.2570 · Cited by 46
“On the contrary for example, host data is not always reliable, because a compromised machine can be manipulated by a biometric scanner as mentioned in [29].”
BackgroundDeep Dilation on Multimodality Time Series for Human Activity Recognition
Xi, R., Li, M., Hou, M., Fu, M., Qu, H., Liu, D., & Haruna, C. R. (2018) · IEEE Access · doi:10.1109/access.2018.2870841 · Cited by 35
“The results of [25] reveal that a combination of CNN and recurrent dense layers can achieve a better performance, the reason being that CNN can capture spatial relationship while RNNmodels temporal relationship.”
BackgroundIwasawa, Y., Nakayama, K., Yairi, I., & Matsuo, Y. (2017) · Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2017/268 · Cited by 36
Swimming style recognition and lap counting using a smartwatch and deep learning
Brunner, G., Melnyk, D., Sigfússon, B., & Wattenhofer, R. (2019) · Proceedings of the 23rd International Symposium on Wearable Computers · doi:10.1145/3341163.3347719 · Cited by 36
“Our CNN architecture follows a similar structure as in [8, 16] and is depicted in Figure 2.”
MethodMuñoz-Organero, M., Powell, L., Heller, B., Harpin, V., & Parker, J. (2019) · Sensors · doi:10.3390/s19132935 · Cited by 36
Hu, Y., Zhang, X.-Q., Xu, L., Xian He, F., Tian, Z., She, W., & Liu, W. (2020) · IEEE Access · doi:10.1109/access.2020.3003162 · Cited by 36
“…(AI) technology [16], massive deep learning methods including forward neural networks (FNNs) [17], [18], recurrent neural networks (RNNs) [19]–[22], autoencoder (AE) [23], and convolutional neural networks (CNNs) [18], [24]–[27] have been proposed to recognize different types of human activities.”
BackgroundMethodZhu, H., Chen, H., & Brown, R. A. (2018) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2018.07.006 · Cited by 43
Upper Body Posture Recognition Using Inertial Sensors and Recurrent Neural Networks
Tang, H.-Y., Tan, S.-H., Su, T.-Y., Chiang, C.-J., & Chen, H.-H. (2021) · Applied Sciences · doi:10.3390/app112412101 · Cited by 46
Replacement AutoEncoder: A Privacy-Preserving Algorithm for Sensory Data Analysis
Malekzadeh, M., Clegg, R. G., & Haddadi, H. (2018) · 2018 IEEE/ACM Third International Conference on Internet-of-Things Design and Implementation (IoTDI) · doi:10.1109/iotdi.2018.00025 · Cited by 76
ResNet-based Network for Recognizing Daily and Transitional Activities based on Smartphone Sensors
Mekruksavanich, S., Jantawong, P., Hnoohom, N., & Jitpattanakul, A. (2022) · International Conference on Big Data Analytics and Practices (IBDAP) · doi:10.1109/ibdap55587.2022.9907111 · Cited by 68
“To better describe the temporal correlations of time-series data, [15], [16] proposed a deepConvLSTM framework for activity recognition by combining CNN and Long Short-Term Memory (LSTM) modules.”
MethodDeep neural learning techniques with long short-term memory for gesture recognition
Jain, D. K., Mahanti, A., Shamsolmoali, P., & Manikandan, R. (2020) · Neural Computing and Applications · doi:10.1007/s00521-020-04742-9 · Cited by 37
Steil, J., Müller, P., Sugano, Y., & Bulling, A. (2018) · International Conference on Human-Computer Interaction with Mobile Devices and Services (MobileHCI) · doi:10.1145/3229434.3229439 · Cited by 54
“Particularly interesting are features extracted from intermediate layers, as for example used for vision-based [17, 24] or wearable sensor-based [31] activity recognition.”
BackgroundAn active semi-supervised deep learning model for human activity recognition
Bi, H., Perelló-Nieto, M., Santos‐Rodríguez, R., Flach, P. A., & Craddock, I. J. (2022) · Journal of Ambient Intelligence and Humanized Computing · doi:10.1007/s12652-022-03768-2 · Cited by 40
“Ordóñez and Roggen (2016) combined LSTM and CNN to explicitly model the temporal dynamics of sequential data, achieving prominent performance in HAR from sensor data.”
BackgroundXu, L., Wu, Q., Pan, L., Meng, F., Li, H., He, C., Wang, H., Cheng, S., & Dai, Y. (2023) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2023.3295899 · Cited by 66
“The deep convolutional and LSTM recurrent neural networks [57] are used for the feature extraction of acceleration signal F a and gyroscope signal F g .”
MethodOpportunities for Smartphone Sensing in E-Health Research: A Narrative Review
Kulkarni, P., Kirkham, R., & McNaney, R. (2022) · Sensors · doi:10.3390/s22103893 · Cited by 43
Development of Oil Production Forecasting Method based on Deep Learning
Abdullayeva, F. J., & İmamverdiyev, Y. (2019) · Statistics Optimization & Information Computing · doi:10.19139/soic-2310-5070-651 · Cited by 41
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.