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 1,801–1,900 of 2,807
Yadav, R. K., Neogi, S. G., & Semwal, V. B. (2022) · Lecture notes in networks and systems · doi:10.1007/978-981-19-1142-2_47 · Cited by 3
Semi-unsupervised Learning of Human Activity using Deep Generative ModelsPreprint
Willetts, M., Doherty, A., Roberts, S., & Holmes, C. C. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1810.12176 · Cited by 6
“Numerous methods have been proposed for activity recognition, including: deep discriminative models [8, 9, 10]; random forests [11]; probabilistic graphical models/Hidden Markov Models [11, 2]; and Gaussian processes [12].”
MethodOctave Mix: Data Augmentation Using Frequency Decomposition for Activity Recognition
Hasegawa, T. (2021) · IEEE Access · doi:10.1109/access.2021.3070778 · Cited by 5
“A method combining multiple sensors [27], methods inserting recurrent layer after several convolution-pooling layers [28, 29], and more advanced methods introducing Inception, Residual, and Attention modules [30, 31, 32, 33, 34] have been studied.”
MethodRaza, A. (2023) · theses.fr (ABES) · doi:10.70675/ac35dc8az89ccz4977z8f25zb7c8937f7cf0 · Cited by 22
Tian, Y., Gu, Y., Lu, Q., & Kamijo, S. (2025) · Sensors · doi:10.3390/s25030649 · Cited by 8
“We redeployed Proposed method and baseline work TPN [37], MSRLSTM [10], DCL [38], ABLSTM [39], PEN [40], and PCL [41] on the Tokyo dataset to evaluate performance in the consumer behavior application scenario.”
Bayesian Optimization of Neural Architectures for Human Activity Recognition
Osmani, A., & Hamidi, M. (2019) · Springer series in adaptive environments · doi:10.1007/978-3-030-13001-5_12 · Cited by 4
Transformer Networks for Data Augmentation of Human Physical Activity RecognitionPreprint
Ramachandra, S., Hoelzemann, A., & Laerhoven, K. V. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2109.01081 · Cited by 10
“The validation model chosen here is one DeepConvLSTM model [8] and one transformer model [15] for each of the datasets.”
MethodBig–Little Adaptive Neural Networks on Low-Power Near-Subthreshold Processors
Shen, Z., Howard, N., & Nunez-Yanez, J. L. (2022) · Journal of Low Power Electronics and Applications · doi:10.3390/jlpea12020028 · Cited by 4
“Due to the flash memory size of MCU, we decided not to use the LSTM layers which have millions of parameters as shown in [23].”
BackgroundMethodResultHoussein, E. H., Ibrahim, I. A., Mahdy, M. A., Kayed, M., Albarrak, A. M., & Mohamed, W. M. (2025) · Journal Of Big Data · doi:10.1186/s40537-025-01293-5 · Cited by 4
“The research in [20] merged CNNs with LSTMs to facilitate activity recognition, also the authors pointed out that the shallow layers of CNNs do not effectively extract hierarchical features over multiple temporal dimensions.”
Dhanalakshmi, R., Nivashini, A., Vijayaraghavan, N., & Narasimhan, S. (2023) · Lecture notes in mechanical engineering · doi:10.1007/978-981-99-1665-8_39 · Cited by 3
An Effective Approach for Wearable Sensor-Based Human Activity Recognition in Elderly Monitoring
Errafik, Y., Dhassi, Y., Baghrous, M., & Kenzi, A. (2025) · BioMedInformatics · doi:10.3390/biomedinformatics5030038 · Cited by 4
Deep Learning-Based Activity Monitoring for Smart Environment Using Radar
Susithra, N., Santhanamari, G., Deepa, M., Reba, P., Ramya, K. C., & Garg, L. (2021) · EAI/Springer Innovations in Communication and Computing · doi:10.1007/978-3-030-70183-3_5 · Cited by 3
A Method of Equipment Safety Certification Based on Daily Cycle Activity
Ye, N., Sun, C., Xu, R., & Sun, F. (2021) · International Conference on Artificial Intelligence and Big Data (ICAIBD) · doi:10.1109/icaibd51990.2021.9458971 · Cited by 3
Equipment data-based activity recognition of construction machinery
Fischer, A., Bedrikow, A. B., Kessler, S., & Fottner, J. (2021) · IEEE International Conference on Engineering, Technology and Innovation (ICE/ITMC) · doi:10.1109/ice/itmc52061.2021.9570272 · Cited by 6
A Hybrid Deep Learning-Based Approach for Human Activity Recognition Using Wearable Sensors
Sharma, D., Roy, A., Bag, S. P., Singh, P. K., & Badr, Y. (2023) · Studies in big data · doi:10.1007/978-3-031-40688-1_11 · Cited by 7
A Hybrid Deep Learning Model for Human Activity Recognition Using Wearable Sensors
Gaurav, K., Roy, B., & Bharti, J. (2022) · Algorithms for intelligent systems · doi:10.1007/978-981-16-9650-3_16 · Cited by 4
Oishi, N., Birch, P. M., Roggen, D., & Lago, P. (2026) · IEEE Sensors Journal · doi:10.1109/jsen.2026.3661047 · Cited by 9
“Restrictions apply.”
Self-citationYang, M., Lu, S., Ding, H., et al. (2023) · Frontiers in Physics · doi:10.3389/fphy.2023.1159531 · Cited by 3
STMultiple: Sparse Transformer Based on RFID for Multi-Object Activity Recognition
Shen, S., Yang, M., Hou, X., Yang, L., Chen, S., Dong, W., Yu, B. W., & Wang, Q. (2023) · International Journal of Software Engineering and Knowledge Engineering · doi:10.1142/s0218194023410073 · Cited by 3
Rajamoney, J., & Ramachandran, A. (2022) · Concurrency and Computation Practice and Experience · doi:10.1002/cpe.7468 · Cited by 3
Video-Based Lifting Action Recognition Using Rank-Altered Kinematic Feature Pairs
Jung, S., Su, B., Lu, L., Qing, L., & Xu, X. (2024) · Human Factors The Journal of the Human Factors and Ergonomics Society · doi:10.1177/00187208241309748 · Cited by 4
“To date, IMUs have been the primary measurement tool in lifting action recognition studies (e.g., Anagnostis et al., 2021; Bangaru et al., 2021; Ordóñez et al., 2016; Thomas et al., 2022), as they not only accurately capture body motions but also provide high portability and affordability.”
Human Activity Recognition Using Deep Models and Its Analysis from Domain Adaptation Perspective
Gurov, N., Khan, A., Hussain, R., & Khattak, A. M. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-29852-4_15 · Cited by 4
Enhancing Causal Estimation through Unlabeled Offline Data
Teichner, R., Eytan, D., & Meir, R. (2022) · International Conference on Frontiers of Signal Processing (ICFSP) · doi:10.1109/icfsp55781.2022.9924647 · Cited by 4
“Given raw data r n at sampling rate r s Herz, resampling it to a sampling rate f s Herz using zero-order-hold interpolation is expressed by We utilize the DeepConvLSTM architecture presented in (Ord´o˜nez & Roggen, 2016) with slight changes.”
MethodPonce-Espinosa, H., & Martínez-Villaseñor, L. (2020) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn48605.2020.9206757 · Cited by 3
“CNNs have the ability to extract features stacking several convolutional operators to create more abstract feature hierarchies [8].”
BackgroundMekruksavanich, S., Phaphan, W., Jeefoo, P., & Jitpattanakul, A. (2024) · IEEE International Conference on Software Engineering and Service Science (ICSESS) · doi:10.1109/icsess62520.2024.10719376 · Cited by 3
“Ord´o˜nez and Roggen [28] introduced a sophisticated deep convolutional LSTM network for multi-modal action identification, showcasing its ability to capture spatial and temporal characteristics accurately.”
BackgroundDomínguez-Vidal, J. E., & Sanfeliu, A. (2023) · IEEE International Conference on Robot and Human Interactive Communication (RO-MAN) · doi:10.1109/ro-man57019.2023.10309648 · Cited by 3
“This is when we start trying to predict the human’s future actions with increasing success over the years and process these predictions to try to infer their intent [10], [11].”
BackgroundMLPs Are All You Need for Human Activity Recognition
Ojiako, K., & Farrahi, K. (2023) · Applied Sciences · doi:10.20944/preprints202309.0635.v1 · Cited by 12
“The parts of the dataset that are trained, tested, and validated are identical to the previous literature [34,35].”
Accurate Classification of Sport Activities Under Tiny Deployability Constraints
Mazinani, A., Davoli, L., Pau, D. P., & Ferrari, G. (2023) · IEEE International Conference on Internet of Things and Intelligence Systems (IoTaIS) · doi:10.1109/iotais60147.2023.10346056 · Cited by 3
“In [11], the authors propose an activity recognition classifier to categorize 5 movements and 27 hand gestures by considering deep CNN and LSTM: the presented simulation results reveal a F1 score for the two classifiers equal to, respectively, 0 .”
BackgroundActivity recognition using smartphones and wearable devices: Traditional approaches, New solutions
Iskanderov, J., & Guvensan, M. A. (2019) · Pamukkale University Journal of Engineering Sciences · doi:10.5505/pajes.2018.84758 · Cited by 4
Federated Quantum Kernel-Based Long Short-Term Memory for Human Activity Recognition
Hsu, Y.-C., Jiang, J.-C., Lin, C.-H., Chen, W.-T., Peng, K. C., Tiwari, P., Chen, S. Y.-C., & Kuo, E.-J. (2025) · IEEE International Conference on Quantum Computing and Engineering (QCE) · doi:10.1109/qce65121.2025.10293 · Cited by 9
Gesture Recognition Dynamics: Unveiling Video Patterns with Deep Learning
Agumamidi, N. R., & Akther, S. (2024) · International Conference on Data Science and Network Security (ICDSNS) · doi:10.1109/icdsns62112.2024.10691103 · Cited by 3
“The importance of HAR spans multiple fields, demographics, and applications: human activity recognition has applications in health asset monitoring, sports performance analysis, security monitoring and surveillance, and the development of high-functioning human-computer interfaces [2].”
BackgroundLi, Z., Fu, M., Fu, B., & Liu, Y. (2025) · Signal Image and Video Processing · doi:10.1007/s11760-025-04888-w · Cited by 4
“Residual temporal convolutional networks and hybrid CNN–LSTM or CNN–RNN designs support efficient parallel sequence processing and have shown strong performance on wearable HAR benchmarks [12, 13].”
A Comprehensive Survey and Analysis of CNN-LSTM-Based Approaches for Human Activity Recognition
Negrete, P. D. M., Flores, A., Minango, J., & Zambrano, M., V (2024) · Smart innovation, systems and technologies · doi:10.1007/978-3-031-66961-3_54 · Cited by 4
Detection of drinking via a wrist-worn inertial sensor.
Senyurek, V. Y., Imtiaz, M. H., & Hassan, N. (2019) · International Electronic Conference on Sensors and Applications (ECSA) · doi:10.3390/ecsa-6-06590 · Cited by 3
Sensing Technologies for Hand Gesture Recognition in Human–Robot Interaction: A Review
Liang, B., Li, N., Li, G., Huang, J., Yu, Z., & Zhao, X. (2025) · IEEE Sensors Journal · doi:10.1109/jsen.2025.3635622 · Cited by 6
“These features can be either handcrafted for use with traditional machine learning models or, automatically learned by deep learning models, which excel at capturing complex spatiotemporal patterns in sensor data [146].”
Deep Hybrid Learning for Anomaly Detection in Behavioral Monitoring
Georgakopoulos, S. V., Tasoulis, S. K., Vrahatis, A. G., Moustakidis, S., Tsaopoulos, D. E., & Plagianakos, V. P. (2022) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn55064.2022.9892769 · Cited by 5
“The former takes care of time dependence, keeping in memory previously gained information, and the latter tends to uncorver hidden patterns in a time window, utilizing a convolution step [10].”
MethodRestHAR: Residual Feature Learning Transformer for Human Activity Recognition from Multi-sensor Data
Shome, D. (2021) · International Conference on Soft Computing & Machine Intelligence (ISCMI) · doi:10.1109/iscmi53840.2021.9654816 · Cited by 3
“A combination of CNN and LSTM was developed in [10] where the authors claim that the CNN layers are responsible for feature extraction from raw data and the LSTMs capture the temporal patterns from the extracted features.”
BackgroundProceedings of the 22nd Engineering Applications of Neural Networks Conference: EANN 2021
Charalampos, S., Nousi, P., Tosidis, P., Tsampazis, K., Passalis, N., Tefas, A., & Nikolaidis, N. (2021) · Proceedings of the international neural networks society · doi:10.1007/978-3-030-80568-5 · Cited by 3
Pellatt, L., & Roggen, D. (2020) · ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp) · doi:10.1145/3410530.3414365 · Cited by 5
Self-citationNyajowi, T., Oyie, N. O., & Ahuna, M. (2022) · International Journal of Engineering and Advanced Technology · doi:10.35940/ijeat.f3753.0811622 · Cited by 3
Papageorgiou, G., Skamnia, E., & Εconomou, P. (2025) · Wiley Interdisciplinary Reviews Data Mining and Knowledge Discovery · doi:10.1002/widm.70016 · Cited by 10
“The breadth of research in this domain, including works like Adnane et al. (2012), Zappella et al. (2013), Wulsin et al. (2011), and Ordóñez and Roggen (2016) (which is first in rank as reported in Table 12, with an average of almost 214 citations per year), demonstrates the field's prominence and…”
A Meta-learning System for Automatic Objects Tracking
Li, Q., Wang, W., & Zhang, J. (2022) · International Conference on Applied Machine Learning (ICAML) · doi:10.1109/icaml57167.2022.00012 · Cited by 3
“As an excellent algorithm, LSTM also has been developed in many fields [6,7].”
MethodHuman Activity Classification Using Recurrence Plot and Residual Network
Lew, C. H., Lim, K. M., Lee, C. P., & Lim, J. Y. (2023) · IEEE Conference on Systems, Process and Control · doi:10.1109/icspc59664.2023.10420336 · Cited by 3
“Additionally, Ordóñez & Roggen proposed Deep Convolutional LSTM (DeepConvLSTM)[8], a model combining convolutional and LSTM recurrent units for human activity recognition.”
BackgroundConvolutional Neural Network for Elderly Wandering Prediction in Indoor Scenarios
Oliveira, R. F. C., Barreto, F., & Abreu, R. (2021) · International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC) · doi:10.5220/0010379902530260 · Cited by 3
“As stated in (Ordóñez and Roggen, 2016), human activity recognition (HAR) is based on the assumption that specific body movements translate into characteristic sensor signal patterns, which can be sensed and classified using machine learning techniques.”
BackgroundPost-Stroke identification of EEG signals using recurrent neural networks and long short-term memory
Sansiagi, W., Djamal, E. C., Djajasasmita, D., et al. (2021) · International Journal of Advances in Intelligent Informatics · doi:10.26555/ijain.v7i2.512 · Cited by 3
“One of the widely used RNN configurations is Long Short-Term Memory (LSTM) [27][28].”
MethodMatching Skeleton-based Activity Representations with Heterogeneous Signals for HAR
Li, S., Zhang, J., Fu, X., Zhang, X., Shang, J., & Gupta, R. K. (2025) · ACM Conference on Embedded Networked Sensor Systems (SenSys) · doi:10.1145/3715014.3722089 · Cited by 5
Multi-Sensor Fusion Based Robot Self-Activity Recognition
Luo, D., Ma, Y., Zhang, X., & Wu, X. H. (2018) · IEEE-RAS International Conference on Humanoid Robots (Humanoids) · doi:10.1109/humanoids.2018.8624918 · Cited by 3
“Because deep learning has achieved great success in the field of computer vision, speech recognition and many other, more and more researchers have used deep learning for activity recognition [2], [3], [4], [5].”
BackgroundInfluentialA Hierarchical Classifier for Detecting Metro-Journey Activities in Data Sampled at Low Frequency
Dewan, A., Gunturi, V. M. V., Naik, V. S., Vishwakarma, K., & Bohra, S. (2019) · International Conference on Advances in Mobile Computing and Multimedia (MoMM) · doi:10.1145/3365921.3365937 · Cited by 3
Abusive Language Detection and Characterization of Twitter Behavior
Davis, D., Murali, R. B., & Babu, R. (2020) · International Journal of Computer Sciences and Engineering · doi:10.48550/arxiv.2009.14261 · Cited by 3
“Similarly in paper [8] proved that Long Short Term Memory (LSTM) RNN is better for sequence learning problems than standard CNN.”
A Data-Driven Study on the Hawthorne Effect in Sensor-Based Human Activity Recognition
Hoelzemann, A., Bock, M., Bastias, E. A. V., Touhami, S. E. O., Nassiri, K., & Laerhoven, K. V. (2023) · ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp) · doi:10.1145/3594739.3610743 · Cited by 4
“As proposed by Ordoñez and Roggen in [14], a popular methodology in human activity recognition remains the usage of convolutional and recurrent layers.”
BackgroundHuman Activities Recognition Using Machine Learning and Artificial Initialization
Gandhi, V. R. (2024) · International Journal of Scientific Research in Computer Science Engineering and Information Technology · doi:10.32628/cseit2410276 · Cited by 3
Android Malware Detection Using Data Mining Techniques on Process Control Block Information
Alawneh, H. (2020) · Cited by 3
Solar Radio Burst Prediction Based on a Multimodal Model
Wang, Y., Feng, S., Du, Q., et al. (2024) · Solar Physics · doi:10.1007/s11207-024-02296-w · Cited by 3
“By stacking multiple convolutional kernels, the CNN generates an incremental abstraction of the feature hierarchy, enabling the model to automatically learn multilevel feature representations (Ordóñez and Roggen, 2016).”
Learning behavioral context recognition with multi-stream temporal convolutional networksPreprint
Saeed, A., Özçelebi, T., Trajanovski, S., & Lukkien, J. J. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1808.08766 · Cited by 11
Indoor Abnormal Behavior Detection for the Elderly: A Review
Gu, T., & Tang, M. (2025) · Sensors · doi:10.3390/s25113313 · Cited by 10
“Ordonez and Roggen [52] proposed a deep learning framework called DeepConvLSTM, which combines CNN and Long Short-Term Memory (LSTM), which is suitable for the HAR of multimodal wearable sensors and supports the natural fusion of multimodal sensor data without the need for manual design features.”
Distributed Communicating Neural Network Architecture for Smart Environments
Abudu, P., & Markham, A. (2019) · IEEE International Conference on Smart Computing · doi:10.1109/smartcomp.2019.00058 · Cited by 3
“[31], [32] employ RNNs for multimodal human activity recognition in sensor-rich environments using wearables.”
MethodMEx: Multi-modal Exercises Dataset for Human Activity RecognitionPreprint
Wijekoon, A., Wiratunga, N., & Cooper, K. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1908.08992 · Cited by 27
“e capturing multiple limb movements and need to be captured with strategically placed multiple sensors. Recent literature has looked at sensor fusion for HAR with multiple sensors yet single modality [6,4,3], but not in a qualitative manner. Evidently there are challenges that arise when reasoning with multi-modal sen…”
BackgroundDeep metric loss for multimodal learning
Moon, S., & Lee, H. (2025) · Machine Learning · doi:10.1007/s10994-024-06709-6 · Cited by 4
“We used the same hyperparameters for training, validation, and testing as in the DeepConvLSTM paper.”
A Real-Time Portable IoT System for Telework Tracking
Zhang, Y., Chen, Z., Tian, H., Kido, K., Ono, N., Chen, W., TAMURA, T., Altaf‐Ul‐Amin, M., Kanaya, S., & Huang, M. (2021) · Frontiers in Digital Health · doi:10.3389/fdgth.2021.643042 · Cited by 4
“Numerous previous research utilizing wearable sensor fusion in HAR show the clear prospect of accurate HAR recognition using portable sensors (8–10).”
Evaluating the Effectiveness of Plantar Pressure Sensors for Fall Detection in Sloped Surfaces
Mahmud, T., Kayastha, R., Kisi, K., Ngu, A. H. H., & Alamgeer, S. (2025) · Electronics · doi:10.3390/electronics14153003 · Cited by 5
“Similarly, Ordóñez et al. [20] proposed DeepConvLSTM models for activity recognition using dense sensor networks, which may be impractical for deployment due to their size and complexity.”
Comparative study of K-NN algorithm for transportation mode detection using mobile phone sensor data
Erkil, H., Aktı, İ., Dael, F. A., Shayea, I. A. M., & El‐Saleh, A. A. (2024) · AIP conference proceedings · doi:10.1063/5.0216676 · Cited by 4
A New Motion Data Structuring for Human Activity Recognition Using Convolutional Neural Network
Alemayoh, T. T., Lee, J. H., & Okamoto, S. (2020) · IEEE/RAS-EMBS International Conference on Biomedical Robotics and Biomechatronics (BioRob) · doi:10.1109/biorob49111.2020.9224310 · Cited by 4
“To improve the performance of a neural network model, Ordóñez et al [22] and Jiang et al [4] added RNN and SVM to CNN respectively.”
MethodNasir, I., Khan, M. H., & Farid, M. S. (2025) · Journal of the Franklin Institute · doi:10.1016/j.jfranklin.2025.108218 · Cited by 3
Knowledge Distillation for Efficient Human Activity Recognition on Resource-Constrained Smartwatches
Fan, Y., Phaphan, W., Jitpattanakul, A., & Mekruksavanich, S. (2026) · IEEE Access · doi:10.1109/access.2026.3664977 · Cited by 8
“Lastly, Ordóñez et al. [15] presented the Deep-Conv-LSTM architecture, which integrates CNN, LSTM, and fully connected DNN layers, delivering outstanding results on the Opportunity and Skoda datasets.”
A Multifunctional and Robust Learning Approach for Human Motion Modelling
Zhang, C.-Y., Xiao, Y.-Y., & Pu, J.-Q. (2019) · International Conference on Information, Cybernetics, and Computational Social Systems (ICCSS) · doi:10.1109/iccss48103.2019.9115436 · Cited by 3
Domesticated Cat Activity Detection Using Deep Learning Technique
Mozumder, M. A. I., Sumon, R. I., Uddin, S. M. I., & Kim, H. (2024) · International Conference on Electrical, Computer and Energy Technologies (ICECET) · doi:10.1109/icecet61485.2024.10698381 · Cited by 5
“Their model's validation accuracy ranged from 83 to 94 percent [11].”
BackgroundBhadane, C., Siddiqui, M. U., Soni, S., & Singh, V. P. (2020) · Algorithms for intelligent systems · doi:10.1007/978-981-15-3242-9_45 · Cited by 3
FilterNet: A Many-to-Many Deep Learning Architecture for Time Series Classification
Chambers, R. D., & Yoder, N. C. (2020) · doi:10.20944/preprints202002.0318.v2 · Cited by 17
Personalized Human Activity Recognition using Hypergraph Learning with Fusion Features
Wang, L., Sun, J., Pan, T., Ye, Y., He, W., & Yang, K. (2021) · International Conference on Electronics Technology (ICET) · doi:10.1109/icet51757.2021.9451065 · Cited by 4
“Other methods apply deep learning to activity recognition [9],[10],[11],[12],[13], which can automatically learn higher-level deep features reflecting hidden relationships among data, and thus achieve higher classification accuracy.”
MethodUsing a Motion Sensor to Categorize Low Back Pain Patients: A Machine Learning Approach
Abdollahi, M., Ashouri, S., Abedi, M., Azadeh-Fard, N., Parnianpour, M., & Rashedi, E. (2019) · doi:10.1101/803155 · Cited by 69
IoT Device Onboarding, Monitoring, and Management
Kesavan, S., Senthilkumar, J., Suresh, Y., & Mohanraj, V. (2020) · Advances in web technologies and engineering book series · doi:10.4018/978-1-7998-3111-2.ch012 · Cited by 3
Gesture Recognition from Skeleton Data for Intuitive Human-Machine Interaction
eacute, B. A. S. A., Miguel, S. A. O., & Neto, P. (2018) · Advances in transdisciplinary engineering · doi:10.3233/978-1-61499-898-3-271 · Cited by 3
“The concept of combining the exclusive feature extraction capability of CNNs with the modeling of temporal dynamics by LSTM networks also provided stateof-the-art results for human activity recognition using multi-modal wearable sensors [17].”
BackgroundImproving Lower Limb Activity Recognition Based on Inertial Sensors Using CNN-LSTM Network
Mekruksavanich, S., Jantawong, P., & Jitpattanakul, A. (2023) · Research, Invention, and Innovation Congress: Innovative Electricals and Electronics (RI2C) · doi:10.1109/ri2c60382.2023.10355936 · Cited by 3
“Another study [25] introduced a convolutional RNN specifically designed for recognizing daily activities, demonstrating a notable improvement of 6% compared to existing state-of-the-art methods.”
BackgroundSelf-Supervised Learning for Complex Activity Recognition Through Motif Identification Learning
Xia, Q., Morales, J., Huang, Y., Hara, T., Wu, K., Oshima, H., Fukuda, M., Namioka, Y., & Maekawa, T. (2024) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2024.3514736 · Cited by 7
“Francisco et al. [22] introduced DeepConvLSTM, a Convolu-tional (Conv) and LSTM Recurrent Neural Networks to recognize daily life activities.”
Mekruksavanich, S., Jantawong, P., & Jitpattanakul, A. (2023) · International Conference on Big Data Analytics and Practices (IBDAP) · doi:10.1109/ibdap58581.2023.10271955 · Cited by 3
Wonderwall: A Virtual-to-Real Foundation Model for IMU-based HAR
Miao, S., & Chen, L. (2026) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3789688 · Cited by 9
Visualization of Multivariate Time‐Series Characteristics of Ground Loss Caused by Shield Tunneling
Wen, Z., Rong, X., Gao, F., Wang, Z., & An, D. (2021) · Shock and Vibration · doi:10.1155/2021/6939094 · Cited by 3
Baldominos, A., del Barrio, C., & Sáez, Y. (2016) · Genetic and Evolutionary Computation Conference Companion (GECCO Companion) · doi:10.1145/2908961.2931732 · Cited by 4
“This program acts like an ensemble, where the most suitable decision tree is based on the cluster which is assigned to each test instance.”
BackgroundUllah, R., Zhang, S., Asif, M., & Wahab, F. E. (2025) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2025.110082 · Cited by 6
Ubi-AD: Towards Ubiquitous, Passive Alzheimer Detection using the Smartwatch
Wu, Y. L., Chen, Y., Zhang, J., Gong, X., & Bi, H. (2024) · ACM Transactions on Sensor Networks · doi:10.1145/3656174 · Cited by 5
“We adopt the human activity recognition model [30] as the backbone feature extractor.”
Real-time Recognition of Smartphone User Behavior Based on Prophet AlgorithmsPreprint
Mi, C., Xu, R., & Lin, C. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1909.08997 · Cited by 9
“Among the researches of mobile phone sensor behavior recognition, the scenarios mainly focus on the active interaction between users and smart devices, such as screen interaction, sensor interaction, application interaction [15][16] .”
BackgroundGugulothu, N., Subramanian, E., & Bhat, S. P. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-30484-3_35 · Cited by 3
Pain Assessment based on fNIRS using Bidirectional LSTMsPreprint
Rojas, R. F., Romero, J., López-Aparicio, J., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2012.13231 · Cited by 3
EmbraceNet for Activity: A Deep Multimodal Fusion Architecture for Activity RecognitionPreprint
Choi, J. H., & Lee, J. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2004.13918 · Cited by 5
“For instance, Ordóñez and Roggen [15] employed an early fusion-based approach, which integrates the sensor data at the initial stage, to classify actions of the OPPORTUNITY dataset.”
MethodNguyen-Trong, K., & Nguyen, T.-T.-T. (2022) · Journal of Computer Science · doi:10.3844/jcssp.2022.57.66 · Cited by 3
“Sliding windows is one of the most common techniques using for segmentation, as in the works of (Zhang et al., 2019a; Lee and Lee, 2018; NaduvilVadukootu et al., 2017; Ordo´nez˜ and Roggen, 2016).”
BackgroundMethodInfluentialMulti-cue Information Fusion for Two-Layer Activity Recognition
Ji, Y., Li, J., Cheng, H., Xu, X., & Song, J. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-54526-4_21 · Cited by 4
Wang, K., He, J., & Zhang, L. (2020) · arXiv (Cornell University) · Cited by 2
Kataoka, S., Oba, M., & Nonaka, H. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.110232 · Cited by 3
Context-Aware Complex Human Activity Recognition using Hybrid Deep Learning ModelsPreprint
Otebolaku, A., & Omolaja, A. (2022) · Preprints.org · doi:10.20944/preprints202203.0363.v1 · Cited by 3
A Deep Convolutional LSTM for ADLs Classification of the Elderly
Vanijkachorn, P., & Visutsak, P. (2021) · International Conference on Data Analytics for Business and Industry (ICDABI) · doi:10.1109/icdabi53623.2021.9655856 · Cited by 3
IGBT lifetime prediction based on EMD-LSTM
Wang, Z., & Du, X. (2021) · Journal of Physics Conference Series · doi:10.1088/1742-6596/2010/1/012143 · Cited by 3
“As shown in Figure 3, the LSTM cell unit is composed of a gating unit and a memory unit, and the gating unit includes input gates, output gates and forgetting gates [10].”
BackgroundGeneralised Structural CNNs (SCNNs) for time series data with arbitrary graph-toplogies.
Teh, T., Auepanwiriyakul, C., Harston, J. A., & Faisal, A. A. (2018) · Spiral (Imperial College London) · Cited by 3
Feng, H., Shen, Q., Song, R., et al. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4460033 · Cited by 3
Lu, L., & Deng, T. (2025) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2025.109141 · Cited by 3
Inertial Measurement Unit based Human Action Recognition for Soft-Robotic Exoskeleton
Kuschan, J., Burgdorff, M., Filaretov, H., & Krüger, J. (2021) · IOP Conference Series Materials Science and Engineering · doi:10.1088/1757-899x/1140/1/012020 · Cited by 3
“The F1 scores without Null class performs better for both the default and reduced models of the C-DRNN and reduced models of DC-LSTM and CNN-2 better, than for the Opportunity data set.”
BackgroundMethodInfluentialIslam, S. M. M., & Talukder, K. H. (2024) · Measurement Sensors · doi:10.1016/j.measen.2024.101398 · Cited by 4
Maintaining Privacy and Utility in IoT System Analytics
Mossé, D., Pötter, H., & Lee, S. (2020) · IEEE International Conference on Trust, Privacy and Security in Intelligent Systems and Applications (TPS-ISA) · doi:10.1109/tps-isa50397.2020.00030 · Cited by 6
“Other IoT devices can track medication routine and compliance and record various health parameters such as heart rate [20]–[24].”
BackgroundSaha, B., Samanta, R., Roy, R. B., & Ghosh, S. K. (2025) · IEEE Embedded Systems Letters · doi:10.1109/les.2025.3561870 · Cited by 17
“For the HAR dataset, TinyTNAS is compared with expert-designed SOTA models, including CNN-based [16], Deep-Conv-LSTM-based [17], and LSTM-CNN-based [18] approaches.”
Generating an Event Timeline About Daily Activities From a Semantic Concept Stream
Miyanishi, T., Hirayama, J.-I., Maekawa, T., & Kawanabe, M. (2018) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v32i1.11308 · Cited by 3
Berger, L., Haberbusch, M., Gross, C., & Moscato, F. (2024) · ASAIO Journal · doi:10.1097/mat.0000000000002299 · Cited by 3
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.