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 1,501–1,600 of 2,807
Arce-Sáenz, L. A., Izquierdo-Reyes, J., & Bustamante-Bello, R. (2025) · Scientific Reports · doi:10.1038/s41598-025-10573-2 · Cited by 8
“Moreover, this approach eliminates the need for domain-specific preprocessing or handcrafted features 30,40,41 , making it Table 1 .”
InfluentialActivity Recognition: Translation across Sensor Modalities Using Deep Learning
Okita, T., & Inoue, S. (2018) · ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp) · doi:10.1145/3267305.3267512 · Cited by 7
Kalabakov, S., Gjoreski, M., Gjoreski, H., & Gams, M. (2021) · Informatica · doi:10.31449/inf.v45i2.3648 · Cited by 8
Context-Aware Data Association for Multi-Inhabitant Sensor-Based Activity Recognition
Arrotta, L., Bettini, C., Civitarese, G., & Presotto, R. (2020) · IEEE International Conference on Mobile Data Management (MDM) · doi:10.1109/mdm48529.2020.00034 · Cited by 10
“In our experimental setup, we use a state-of-the-art deeplearning neural network that combines convolutional and recurrent layers [17].”
MethodEmerging trends in biomedical trait-based human identification: A bibliometric analysis
Girdhar, N., Sharma, D., Kumar, R., Sahu, M., & Lin, C. (2024) · SLAS TECHNOLOGY · doi:10.1016/j.slast.2024.100136 · Cited by 10
“Similarly, the document referenced by (Ordóñez and Roggen [57]) has a TLS of 29 and has been cited 7 times.”
MethodHuang, Q., Xie, W., Li, C., Wang, Y., & Liu, Y. (2023) · Applied Sciences · doi:10.3390/app131910560 · Cited by 9
Hybrid Attention with CNN-BiLSTM and CBAM for Efficient Wearable Activity Recognition
Mekruksavanich, S., Jantawong, P., Phaphan, W., & Jitpattanakul, A. (2024) · Joint International Conference on Digital Arts, Media and Technology with ECTI Northern Section Conference on Electrical, Electronics, Computer and Telecommunications Engineering (ECTI DAMT & NCON) · doi:10.1109/ectidamtncon60518.2024.10480050 · Cited by 7
From Human Pose to On-Body Devices for Human-Activity Recognition
Rueda, F. M., & Fink, G. A. (2021) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr48806.2021.9412283 · Cited by 11
“Following [5], data are split into training, validation, and testing sets.”
BackgroundMethodResultInfluentialBello, H., Zhou, B., Suh, S., Marin, L. A. S., & Lukowicz, P. (2022) · Frontiers in Computer Science · doi:10.3389/fcomp.2022.915280 · Cited by 7
Gesture-based incident reporting through smart watches
Kasnesis, P., Chatzigeorgiou, C., Toumanidis, L., & Patrikakis, C. Z. (2019) · IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops) · doi:10.1109/percomw.2019.8730586 · Cited by 7
“What is more, previous implementations of DL approaches applied to sensor-based human activity recognition and hand gesture recognition have outperformed past techniques based on hand-crafted features [11][12].”
MethodORSNet: A Hybrid Neural Network for Official Sports Referee Signal Recognition
Pan, T., Chang, C.-Y., Tsai, W.-L., & Hu, M. (2018) · ACM International Workshop on Multimedia Content Analysis in Sports (MMSports) · doi:10.1145/3265845.3265849 · Cited by 9
“[17] proposed a generic deep framework for activity recognition based on convolutional and LSTM recurrent units, which can explicitly model the temporal dynamics of feature activations.”
BackgroundZhang, M., Xie, C., Tian, B., Yang, Y., Guo, Y., Zhu, Y. Q., & Bian, S. (2023) · Water · doi:10.3390/w15213779 · Cited by 8
Zhang, P., Zhang, Z., & Chao, H. (2020) · Sensors · doi:10.3390/s20144016 · Cited by 7
Exploring the Benefits of Time Series Data Augmentation for Wearable Human Activity Recognition.
Hasan, M. A., Li, F., Piet, A., Gouverneur, P., Irshad, M. T., & Grzegorzek, M. (2023) · International Workshop on Sensor-based Activity Recognition and Interaction (iWOAR) · doi:10.1145/3615834.3615842 · Cited by 10
“From the table 3, it can be seen that the Time Warping method outperforms all other approaches, including the baseline model (baseline is a reproduction of Ordonez et al. without augmentation[24]).”
MethodInfluentialDeep learning—Accelerating Next Generation Performance Analysis Systems?
Brock, H. (2018) · Conference of the International Sports Engineering Association (ISEA) · doi:10.3390/proceedings2060303 · Cited by 7
“Most recently, even higher accuracy was reported by the introduction of a deep recurrent convolutional network, which could outperform any of the previous networks by 4% on average [18].”
BackgroundEnhancing Sensor-Based Human Activity Recognition With Multiresolution Wavelet-Attention
Wieland, C., & Pankratius, V. (2025) · IEEE Sensors Journal · doi:10.1109/jsen.2025.3571572 · Cited by 14
“However, multilocation information is important to properly detect the performed activities (see [18]).”
InfluentialA Lightweight Deep Human Activity Recognition Algorithm Using Multiknowledge Distillation
Chen, R., Luo, H., Zhao, F., Meng, X., Xie, Z., & Zhu, Y. (2024) · IEEE Sensors Journal · doi:10.1109/jsen.2024.3443308 · Cited by 15
“Theearliest form of KD, known as response-based KD, uses the teacher model’s responses as soft labels for auxiliary constraints in training the student model [17].”
BackgroundWu, J., & Liu, Q. (2023) · Neural Processing Letters · doi:10.1007/s11063-023-11385-z · Cited by 11
Sparse Feature Learning for Human Activity Recognition
Ullah, S., & Kim, D. (2021) · IEEE International Conference on Big Data and Smart Computing (BigComp) · doi:10.1109/bigcomp51126.2021.00066 · Cited by 8
“Recently, the combination of CNN and RNN, such as CNN-LSTM architectures [9-10], have outperformed the traditional temporal CNN or LSTM based models in terms of computational complexity, parameters utilization (reduced parameters), and compact size.”
MethodNguyen, T. D. T., Park, J. H., Hossain, M. I., Hossain, M. D., Lee, S., Jang, J. W., Jo, S. H., Huynh, L. N. T., Tran, T. K., & Huh, E. (2019) · IEEE International Conference on Cloud Computing Technology and Science · doi:10.1109/cloudcom.2019.00066 · Cited by 10
“LSTM uses the concept of the gate to add or remove information of each individual memory cell.”
MethodInfluentialSensor-based human activity recognition using fuzzified deep CNN architecture with λmax method
Gomathi, V., Kalaiselvi, S., & Thamarai Selvi, D. (2022) · Sensor Review · doi:10.1108/sr-06-2021-0195 · Cited by 9
Enhancing Inertial Hand based HAR through Joint Representation of Language, Pose and Synthetic IMUs
Rey, V. F., Ray, L. S. S., Xia, Q., Wu, K., & Lukowicz, P. (2024) · ACM International Symposium on Wearable Computers (ISWC) · doi:10.1145/3675095.3676609 · Cited by 16
“DCL (Real): Only real IMU data of the target dataset is used for training, the HAR model is DeepConvLSTM (DCL) [15], which is widely used for IMU-based HAR tasks.”
MethodRobustness of Deep LSTM Networks in Freehand Gesture Recognition
Schak, M., & Gepperth, A. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-30508-6_27 · Cited by 7
A Wearable Multi-modal Edge-Computing System for Real-Time Kitchen Activity Recognition
Liu, M., Suh, S., Vargas, J. F., Zhou, B., Gruenerbl, A., & Lukowicz, P. (2024) · Communications in computer and information science · doi:10.1007/978-981-97-9003-6_9 · Cited by 11
Advancing Human Fall Detection Through Motion Data from Smart Wearable Sensors and CNN-BiGRU Model
Mekruksavanich, S., Phaphan, W., & Jitpattanakul, A. (2024) · IEEE International Conference on Software Engineering and Service Science (ICSESS) · doi:10.1109/icsess62520.2024.10719052 · Cited by 8
“At the same time, recurrent neural networks (RNNs), such as long short-term memory (LSTM) and gated recurrent units (GRU), are particularly suitable for exhibiting temporal dependencies in sequential data [11], [12].”
BackgroundConfidence-Calibrated Human Activity Recognition
Roy, D., Girdzijauskas, Š., & Socolovschi, S. (2021) · Sensors · doi:10.3390/s21196566 · Cited by 9
Zheng, L., Li, S., Zhu, C., & Gao, Y. (2019) · ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp) · doi:10.1145/3341162.3344851 · Cited by 6
“Some machine learning based methods [5, 6, 12, 15] and deep learning based methods [3, 4, 9–11 , 16] have In this paper, the signals from the smartphone sensors are classified with a recurrent neural network based on short-time frequency features.”
MethodImage-based Activity Recognition from IMU Data
Guinea, A. S., Sarabchian, M., & Mühlhäuser, M. (2021) · IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops) · doi:10.1109/percomworkshops51409.2021.9430990 · Cited by 10
“, [3], [4]), with only a handful of them proposing to generate images from the time series in an attempt to improve the performance (e.”
BackgroundMethodDegbey, G.-S., Hwang, E., Park, J., & Lee, S. (2024) · International Journal of Environmental Research and Public Health · doi:10.3390/ijerph21091178 · Cited by 8
“When the data were trained using the LSTM model, a rapid decrease in loss was observed within the first five epochs, along with high accuracy on both the training and the validation set.”
MethodA lightweight deep learning with feature weighting for activity recognition
Ige, A. O., & Noor, M. H. M. (2022) · Computational Intelligence · doi:10.1111/coin.12565 · Cited by 10
“In Murahari, 22 a DeepConvLSTM with attention was proposed to extend the work in Ordóñez, 47 and a relative improvement of 87.5% was recorded on the PAMAP2 dataset using the model with attention, and an accuracy of 74.8% on the model without attention.”
MethodInfluentialGaitKeeper: An AI-Enabled Mobile Technology to Standardize and Measure Gait Speed
Davey, N., Harte, G., Boran, A., Elwaine, P. M., & Kennelly, S. (2024) · Sensors · doi:10.3390/s24175550 · Cited by 9
Towards Stroke Patients’ Upper-Limb Automatic Motor Assessment Using Smartwatches
Bensalah, A., Chen, J., Fornés, A., Carmona-Duarte, C., Lladós, J., & Ferrer, M. A. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-68763-2_36 · Cited by 11
Deep Learning Approaches for Recognizing Daily Human Activities Using Smart Home Sensors
Sanpote, W., Jantawong, P., Hnoohom, N., Jitpattanakul, A., & Mekruksavanich, S. (2023) · Joint International Conference on Digital Arts, Media and Technology with ECTI Northern Section Conference on Electrical, Electronics, Computer and Telecommunications Engineering (ECTI DAMT & NCON) · doi:10.1109/ectidamtncon57770.2023.10139507 · Cited by 8
“Consequently, sensor-based solutions can be classified into three categories: Wearable [10]–[13], Sensor on Objects [14], [15], and Ambient Sensor [16].”
BackgroundMulti-Branch CNN GRU with attention mechanism for human action recognition
Verma, U., Tyagi, P., & Aneja, M. K. (2023) · Engineering Research Express · doi:10.1088/2631-8695/acd98c · Cited by 13
Ellouze, A., Kadri, N., Alaerjan, A., & Ksantini, M. (2024) · Computers, materials & continua/Computers, materials & continua (Print) · doi:10.32604/cmc.2024.048061 · Cited by 9
ConvNet-based performers attention and supervised contrastive learning for activity recognition
Hamad, R. A., Yang, L., Woo, W. L., & Wei, B. W. (2022) · Applied Intelligence · doi:10.1007/s10489-022-03937-y · Cited by 9
“To show the results of the proposed model, the average F-score of the cross-validation is computed as done in the following research [11, 25, 33, 34].”
MethodUnsupervised Embedding Learning for Human Activity Recognition Using Wearable Sensor DataPreprint
Sheng, T., & Huber, M. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2307.11796 · Cited by 10
“In (Morales and Roggen 2016), convolutional neural networks are employed to extract the features and recognize the type of the activity.”
MethodArı hastalıklarının hibrit bir derin öğrenme yöntemi ile tespiti
Metlek, S., & Kayaalp, K. (2021) · Gazi Üniversitesi Mühendislik-Mimarlık Fakültesi Dergisi · doi:10.17341/gazimmfd.749443 · Cited by 12
ALAE-TAE-CutMix+: Beyond the State-of-the-Art for Human Activity Recognition Using Wearable Sensors
Ahmad, N., & Leung, H.-F. (2023) · IEEE International Conference on Pervasive Computing and Communications · doi:10.1109/percom56429.2023.10099138 · Cited by 13
“The results of baseline studies [11], [17] are directly quoted from [1], and other baseline studies are obtained from [1], [10], [16], except for the GOTOV dataset,”
BackgroundMethodResultSelf-Supervised Learning for Activity Recognition Based on Datasets With Imbalanced Classes
Hamad, R. A., Woo, W. L., Wei, B. W., & Yang, L. (2025) · IEEE Transactions on Emerging Topics in Computational Intelligence · doi:10.1109/tetci.2025.3526504 · Cited by 11
“Recurrent and convolutional neural networks have demonstrated satisfying performance in various recognition systems from sequential data such as human activity recognition [7], [24], [25], [26].”
ALANet:Autoencoder-LSTM for pain and protective behaviour detection
Yuan, X., & Mahmoud, M. (2020) · International Conference on Automatic Face and Gesture Recognition · doi:10.1109/fg47880.2020.00063 · Cited by 9
Activity recognition from smartphone data using weighted learning methods
Abidine, M. B., & Fergani, B. (2021) · Intelligenza Artificiale · doi:10.3233/ia-200059 · Cited by 6
“…Neighbors (kNN) [17, 18], Bagging [18], Decision Tree [19], Artificial Neural Networks (ANN) [20], Boosting algorithm [21], Quadratic discriminant analysis [11], Convolutional neural networks (CNN), Long-short-term memory recurrent (LSTM) neural networks [22], and improved LSTM networks [23].”
Weighted voting ensemble of hybrid CNN-LSTM Models for vision-based human activity recognition
Aggarwal, S., Bhola, G., & Vishwakarma, D. K. (2024) · Multimedia Tools and Applications · doi:10.1007/s11042-024-19582-1 · Cited by 7
“Recurrent neural networks, including LSTMs, have been widely used for sensor-based HAR [26–30].”
IOT, Deep Learning and Cybersecurity in Smart Homes: A Survey
Atieh, M., Mohammad, O. H., Sabra, A., & Rmayti, N. (2022) · Wiley eBooks · doi:10.1002/9781119987451.ch6 · Cited by 6
VALERIAN: Invariant Feature Learning for IMU Sensor-based Human Activity Recognition in the Wild
Hao, Y., Wang, B., & Zheng, R. (2023) · IEEE/ACM International Conference on Internet-of-Things Design and Implementation (IoTDI) · doi:10.1145/3576842.3582390 · Cited by 8
“Implementation The implementation of the feature extractor follows DeepConvLSTM in all models.”
BackgroundMethodInfluentialIOTeeth: Intra-Oral Teeth Sensing System for Dental Occlusal Diseases Recognition
Hu, Z., Radmehr, A., Zhang, Y., Pan, S., & Nguyen, P. (2024) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3643516 · Cited by 12
“Given the distinct pattern, we propose to leverage the Convolutional Neural Network (CNN)-based model to recognize activities from signals for its strong performance in local salience pattern extraction [54, 95].”
MethodHaq, I. U., Felicetti, F., & Lamonaca, F. (2026) · Journal of Sensor and Actuator Networks · doi:10.3390/jsan15010008 · Cited by 11
“Documented threat vectors include signal injection or replay attacks on inertial data streams, tampering with learned model parameters, unauthorized modification of controller settings, and denial-of-service conditions that interfere with real-time operation [29,43,96].”
InfluentialOptimizing Accuracy-Efficiency Trade-Offs of On-Device Activity Inference With Star Operation
Chen, G., Fu, Z., Sha, Y., Xiong, D., Zhang, L., Wu, H., & Song, A. (2025) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2025.3619549 · Cited by 6
“The F1-score (i.e., the harmonic mean of precision and recall) is crucial in evaluating sensor-based HAR models, especially when dealing with class imbalance [19].”
IoT for healthcare applications
Sayrafian, K., Ambroziak, S. J., Bajić, D., Berbakov, L., Correia, L. M., Cwalina, K. K., Garcia‐Pardo, C., Gardašević, G., Katzis, K., Kułakowski, P., et al. (2021) · Elsevier eBooks · doi:10.1016/b978-0-12-820581-5.00014-6 · Cited by 6
Finger-Worn Device Based Hand Gesture Recognition Using Long Short-Term Memory
Cheng, Z., & Zhou, Y. (2018) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc.2018.00356 · Cited by 6
“It has shown impressive performance and stability in sequence prediction problems like speech recognition [25], [26], machine translation [27], image captioning [24], and wearable activity recognition [28].”
BackgroundOptimizing Activity Recognition in Stroke Survivors for Wearable Exoskeletons
Recher, F., Baños, O., Nikamp, C. D. M., Schaake, L., Baten, C. T. M., & Buurkc, J. H. (2018) · IEEE/RAS-EMBS International Conference on Biomedical Robotics and Biomechatronics (BioRob) · doi:10.1109/biorob.2018.8487740 · Cited by 9
Hasan, M. S., Sundberg, C. A., Hasan, H., Kostov, Y. V., Ge, X., Choa, F., & Rao, G. (2023) · IEEE Access · doi:10.1109/access.2023.3303815 · Cited by 6
“RNN is well-suited for time-series or sequential data because the network structure is specifically designed to represent past or historical information in every recurrent step [36], [37].”
BackgroundMultimodal Egocentric Activity Recognition Using Multi-stream CNN
Imran, J., & Raman, B. (2018) · Indian Conference on Computer Vision, Graphics and Image Processing · doi:10.1145/3293353.3293363 · Cited by 6
“On the other hand, deep neural network based techniques like [12, 23, 25, 36] learn features directly from raw sensor data, and achieve higher results than their handcrafted counterparts.”
BackgroundResearch and comprehensive evaluation on delivery schemes of the Grand Inga hydropower station
Song, F., Yu, X., Li, J., et al. (2020) · Global Energy Interconnection · doi:10.1016/j.gloei.2021.01.009 · Cited by 6
Toward End-to-end Prediction of Future Wellbeing using Deep Sensor Representation Learning
Li, B., Yu, H., & Sano, A. (2019) · International Conference on Affective Computing and Intelligent Interaction Workshops and Demos (ACIIW) · doi:10.1109/aciiw.2019.8925072 · Cited by 8
“presented DeepConvLSTM composed of convolutional and LSTM recurrent layers for human activity recognition based on 500 ms data segmentation from accelerometers and gyroscopes [6], and Kanjo et al.”
MethodHuman Activity Recognition in Logistics Using Wearable Sensors and Deep Residual Network
Mekruksavanich, S., Tancharoen, D., & Jitpattanakul, A. (2023) · IEEE Region 10 Conference (TENCON) · doi:10.1109/tencon58879.2023.10322393 · Cited by 6
“Deep architectures integrate feature extraction and classification in an end-to-end manner, which sets them apart from conventional methods [10], [11].”
Multimodal deep learning network based hand ADLs tasks classification for prosthetics control
Li, Z., Zhou, H., Yang, D., & Shuiqing, X. (2017) · IEEE International Conference on Progress in Informatics and Computing · doi:10.1109/pic.2017.8359521 · Cited by 8
“Some research established the DeepConvLSTM framework to recognize different human limb posture by kinematic data with high F1 score[20].”
MethodBetter Application of Bayesian Deep Learning to Diagnose Disease
Singh, P. N. (2021) · International Conference on Computing Methodologies and Communication (ICCMC) · doi:10.1109/iccmc51019.2021.9418301 · Cited by 8
Simulation-Driven Design of Smart Gloves for Gesture Recognition
Leite, C. F. S., Byvshev, P., Mauranen, H., & Xiao, Y. (2022) · Scientific Reports · doi:10.1038/s41598-024-65069-2 · Cited by 10
“We also followed the conventional sliding window approach for segmentation 43,44 ; each sliding window was annotated with the activity (hand gestures, in our case) that was present throughout most of the window.”
MethodCRUFT: Context Recognition under Uncertainty using Fusion and Temporal Learning
Ge, W., & Agu, E. (2020) · International Conference on Machine Learning and Applications · doi:10.1109/icmla51294.2020.00122 · Cited by 9
“Neural networks have also been utilized for smartphone HCR [4], including combining MLPs and CNNs [5], fusing multimodal sensor data and classification using a bi-LSTM [2], using multiple sensor streams with shared weights [6] or converting sensor data to a 2D image that is then analyzed using CNNs [7].”
BackgroundMethodde Gauna, D. E. R., Sanchez, L. E., Ruiz‐Iniesta, A., Villalonga, C., & Serrano, M. (2023) · Journal of King Saud University - Computer and Information Sciences · doi:10.1016/j.jksuci.2023.101836 · Cited by 6
“Some approaches apply Multi-step Dense to classification problems by training them in a supervised approach; LSTM-RNN in time series problems; to automatically learn multiple layers of feature hierarchies (Ordóñez and Roggen, 2016).”
New prediction method for data spreading in social networks based on machine learning algorithm
Meqdad, M. N., Al-Akam, R., & Kadry, S. (2020) · TELKOMNIKA (Telecommunication Computing Electronics and Control) · doi:10.12928/telkomnika.v18i6.16300 · Cited by 8
“In a study by Watt [23], he investigated the role of threshold values and network structure in information diffusion in these networks.”
Moore, R. P., Archer, K. R., & Choi, L. (2021) · Sensors · doi:10.3390/s21082726 · Cited by 7
Boosting the Performance of Lightweight HAR Models with Attention and Knowledge Distillation
Agac, S., & İncel, Ö. D. (2024) · International Conference on Intelligent Environments (IE) · doi:10.1109/ie61493.2024.10599908 · Cited by 9
“It integrates convolutional and LSTM layers to extract discriminative features and model temporal dependencies based on 2D-time windows sensor data [9].”
BackgroundMethodInfluentialHybrid Analog-Digital Sensing Approach for Low-power Real-time Anomaly Detection in Drones
Hsieh, Y.-T., Anjum, K., Huang, S., Kulkarni, I., & Pompili, D. (2021) · IEEE International Conference on Mobile Ad-Hoc and Sensor Systems (MASS) · doi:10.1109/mass52906.2021.00062 · Cited by 11
Yao, M., Zhang, L., Cheng, D., Liu, J., Wang, L., Wu, H., & Song, A. (2024) · IEEE Sensors Journal · doi:10.1109/jsen.2024.3412395 · Cited by 7
“To ensure a fair comparison with the recent HAR literature [29], we segmented the data using sliding windows of fixed length 30 and stride step 15.”
BackgroundMethodInfluentialLatent Space Representation of Human Movement: Assessing the Effects of Fatigue
Rousseau, T., Venture, G., & Hernandez, V. (2024) · Sensors · doi:10.3390/s24237775 · Cited by 8
“Recent advances in HAR [27] have enabled multimodal sensor analysis [28], with a primary focus on classification tasks [29].”
ActiLabel: A Combinatorial Transfer Learning Framework for Activity RecognitionPreprint
Alinia, P., Mirzadeh, S. I., & Ghasemzadeh, H. G. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.07415 · Cited by 9
Ramamurthy, S. R., Ghosh, I., Gangopadhyay, A., Galik, E. M., & Roy, N. (2022) · Pervasive and Mobile Computing · doi:10.1016/j.pmcj.2022.101698 · Cited by 9
Ashfaque Mostafa, T., Soltaninejad, S., McIsaac, T. L., & Cheng, I. (2021) · doi:10.20944/preprints202108.0347.v1 · Cited by 32
Vision based Human Activity Recognition using Deep Neural Network Framework
Janardhanan, J., & Umamaheswari, S. (2022) · International Journal of Advanced Computer Science and Applications · doi:10.14569/ijacsa.2022.0130621 · Cited by 6
Kumari, P., Cooney, N. J., Kim, T.-S., & Minhas, A. S. (2018) · Asia-Pacific World Congress on Computer Science and Engineering (APWC on CSE) · doi:10.1109/apwconcse46201.2018.8950057 · Cited by 6
Mohammadian Rad, N., Kia, S. M., Zarbo, C., van Laarhoven, T., Jurman, G., Venuti, P., Marchiori, E., & Furlanello, C. (2018) · Signal Processing · doi:10.1016/j.sigpro.2017.10.011 · Cited by 94
“ognition [54], and natural language modeling [55]. Recently, the LSTM has also been successfully used for human activity recognition using wearable technologies as a classic sequence analysis problem [56, 57, 50]. Considering these studies in human activity recognition, it is expected that learning the temporal patter…”
MethodHARE: Unifying the Human Activity Recognition Engineering Workflow
Konak, O., van de Water, R. P., Döring, V., Fiedler, T., Liebe, L., Masopust, L., Postnov, K. V., Sauerwald, F., Treykorn, F., Wischmann, A., et al. (2023) · Sensors · doi:10.3390/s23239571 · Cited by 9
“After the input layer, it is followed by four consecutive convolution layers and two LSTM layers before the softmax classifier [72].”
MethodA Spatio-temporal Graph Transformer driven model for recognizing fine-grained data human activity
Yan, M., Zhang, G., & Ye, C. (2024) · Alexandria Engineering Journal · doi:10.1016/j.aej.2024.06.042 · Cited by 7
RDPD: Rich Data Helps Poor Data via Imitation
Hong, S., Xiao, C., Hoang, T. N., Ma, T., Li, H., & Sun, J. (2019) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2019/817 · Cited by 8
Learning Bodily and Temporal Attention in Protective Movement Behavior DetectionPreprint
Wang, C., Peng, M., Olugbade, T., Lane, N. D., Williams, A. C. D. C., & Bianchi‐Berthouze, N. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1904.10824 · Cited by 5
“[20] focused on temporal attention which they embedded at the end of a convolutional LSTM network (Conv-LSTM) [25].”
BackgroundPellatt, L., & Roggen, D. (2021) · International Symposium on Wearable Computers · doi:10.1145/3460421.3478813 · Cited by 7
Self-citationGear Classification in Skating Cross-Country Skiing Using Inertial Sensors and Deep Learning
Pousibet-Garrido, A., Polo-Rodríguez, A., Moreno-Pérez, J. A., Ruiz‐García, I., Escobedo, P., López-Ruiz, N., Marcén-Cinca, N., Medina-Quero, J., & Carvajal, M. A. (2024) · Sensors · doi:10.3390/s24196422 · Cited by 6
Mekruksavanich, S., Jantawong, P., Phaphan, W., et al. (2024) · Joint International Conference on Digital Arts, Media and Technology with ECTI Northern Section Conference on Electrical, Electronics, Computer and Telecommunications Engineering (ECTI DAMT & NCON) · doi:10.1109/ectidamtncon60518.2024.10480008 · Cited by 6
Construction Tasks Electronic Process Monitoring: Laboratory Circuit-Based Simulation Deployment
Calvetti, D., Sanhudo, L., Mêda, P., Martins, J. P., Gonçalves, M. C., & Sousa, H. J. C. D. (2022) · Buildings · doi:10.3390/buildings12081174 · Cited by 8
Task grouping and optimized deep learning based VM sizing for hosting containers as a service
Patra, M. K., Sahoo, B., Turuk, A. K., et al. (2023) · Journal of Cloud Computing Advances Systems and Applications · doi:10.1186/s13677-023-00441-7 · Cited by 6
“The Deep-ConvLSTM [27, 28] is comprised of the combination of recurrent layers of LSTM and convolutional layers.”
MethodAssessment and Optimization of 1D CNN Model for Human Activity Recognition
Reusch, R. S., Juracy, L. R., & Moraes, F. (2022) · Brazilian Symposium on Computing System Engineering (SBESC) · doi:10.1109/sbesc56799.2022.9964520 · Cited by 9
“Many of the proposed models [5, 8, 11, 12] consist of complex LSTM stacked structures, which require the use of resources that are scarce in embedded systems, such as volatile memory area.”
BackgroundMethodInfluentialOn the Utility of Virtual On-body Acceleration Data for Fine-grained Human Activity Recognition
Leng, Z., Jain, Y., Kwon, H., & Plötz, T. (2023) · International Symposium on Wearable Computers · doi:10.1145/3594738.3611364 · Cited by 13
“Using the virtual IMU data collected from large-scale videos, previous studies were able to train a very complex deep learning model with parameters three orders of magnitude larger than state-of-the-art deep learning models [25].”
Designing a Sensor Glove Using Deep Learning
Chan, J., Veas, E. E., & Simon, J. (2021) · ACM International Conference on Intelligent User Interfaces (IUI) · doi:10.1145/3397481.3450665 · Cited by 6
“Data stream processing: The objective is to detect patterns within the data stream of the sensors that correspond to gestures [22], where the data stream is a multivariate time series.”
BackgroundA Hybrid Deep Neural Networks for Sensor-based Human Activity Recognition
Wang, S., & Zhu, X. (2020) · International Conference on Advanced Computational Intelligence (ICACI) · doi:10.1109/icaci49185.2020.9177818 · Cited by 6
“Literature [11] introduced DeepConvLSTM composed of convolutional and LSTM recurrent layers, which offered better performance than CNN baseline.”
BackgroundSelf-relation attention networks for weakly supervised few-shot activity recognition
Deng, S., Guo, Z., Teng, D., Lin, B., Chen, D., Jia, T., & Wang, H. (2023) · Knowledge-Based Systems · doi:10.1016/j.knosys.2023.110720 · Cited by 7
SL-BiLSTM: A Signal-Based Bidirectional LSTM Network for Over-the-Horizon Target Localization
Yu, W., Yu, H., Wang, D., Du, J., & Zhang, M. (2021) · Mathematical Problems in Engineering · doi:10.1155/2021/9992120 · Cited by 6
Differentiable Prior-Driven Data Augmentation for Sensor-Based Human Activity Recognition
Zhang, Y., Gao, Q. H., Hu, R., Ding, Q., Li, B., & Guo, Y. (2025) · IEEE Transactions on Computational Social Systems · doi:10.1109/tcss.2025.3565414 · Cited by 6
“Tovalidate the generalization of DriveData, we apply our data augmentation framework to three baseline classi-fiers, including ConvLSTM [45], DeepSense [46], and Con-vTransformer [20].”
Smartphone Health Biomarkers: Positive Unlabeled Learning of In-the-Wild Contexts
Alajaji, A. S., Gerych, W., Buquicchio, L., Chandrasekaran, K., Mansoor, H., Agu, E., & Rundensteiner, E. A. (2021) · IEEE Pervasive Computing · doi:10.1109/mprv.2021.3051869 · Cited by 6
Pinto, V. H., Amorim, A., Rocha, L. F., et al. (2020) · IEEE International Conference on Autonomous Robot Systems and Competitions · doi:10.1109/icarsc49921.2020.9096200 · Cited by 6
“results [10] [11].”
Effect of Reduced Dimensionality on Deep learning for Human Activity Recognition
Kumari, G., Chakraborty, J., & Nandy, A. (2020) · International Conference on Computing, Communication and Networking Technologies (ICCCNT) · doi:10.1109/icccnt49239.2020.9225419 · Cited by 7
“Usefulness of wearable inertial sensor [13], [14] for solving complex problem of activity detection of various domain”
BackgroundMulti-modal Deep Learning for Assessing Surgeon Technical Skill on a Surgical Knot-tying TaskPreprint
Kasa, K., Burns, D., Goldenberg, M. G., Selim, O., Whyne, C. M., & Hardisty, M. (2022) · doi:10.36227/techrxiv.20085425 · Cited by 6
Health Monitoring Methods in Heart Diseases Based on Data Mining Approach: A Directional Review
Harouni, M., Karimi, M., Nasr, A., Mahmoudi, H., & Najafabadi, Z. A. (2022) · Studies in big data · doi:10.1007/978-981-19-2057-8_5 · Cited by 14
Are Transformers a Useful Tool for Tiny devices in Human Activity Recognition?
Lattanzi, E., Calisti, L., & Contoli, C. (2024) · International Conference on Advances in Artificial Intelligence (ICAAI) · doi:10.1145/3704137.3704171 · Cited by 15
Park, J., Kim, D., & Lee, J. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.110465 · Cited by 8
Chances of Interpretable Transfer Learning for Human Activity Recognition in Warehousing
Kirchhof, M., Schmid, L., Reining, C., ten Hompel, M., & Pauly, M. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-87672-2_11 · Cited by 13
Niño-Tejada, K., Saldaña-Aristizábal, L., Rivas-Caicedo, J. L., & Patarroyo-Montenegro, J. F. (2025) · Electronics · doi:10.3390/electronics14153039 · Cited by 9
Comas-González, Z., Mardini-Bovea, J., Butt, S. A., Sánchez-Comas, A., Synnes, K., Joliet, A., De-La-Hoz-Franco, E., Molina-Estren, D., Piñeres-Espitia, G., Naz, S., et al. (2024) · Automatic Control and Computer Sciences · doi:10.3103/s0146411624010048 · Cited by 6
“However, if we use those computational tools we can deeply filter, analyze and have promising results that can impact the focus of any kind of study [8, 9, 10].”
A neural network for the detection of soccer headers from wearable sensor data
Kern, J., Lober, T., Hermsdörfer, J., & Endo, S. (2022) · Scientific Reports · doi:10.1038/s41598-022-22996-2 · Cited by 9
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.