Deep Learning in Human Activity Recognition with Wearable Sensors: A Review on Advances
Open accessThe DOI matches its Crossref record; 334 of the 353 references it cites were found in a registry or an index, and 1 are not checked yet; 24 of the 191 sources its claims cite were checked for support.
Abstract
Mobile and wearable devices have enabled numerous applications, including activity tracking, wellness monitoring, and human–computer interaction, that measure and improve our daily lives. Many of these applications are made possible by leveraging the rich collection of low-power sensors found in many mobile and wearable devices to perform human activity recognition (HAR). Recently, deep learning has greatly pushed the boundaries of HAR on mobile and wearable devices. This paper systematically categorizes and summarizes existing work that introduces deep learning methods for wearables-based HAR and provides a comprehensive analysis of the current advancements, developing trends, and major challenges. We also present cutting-edge frontiers and future directions for deep learning-based HAR.
Verified 2026-10-07 · 1 reference not checked yet
Overview
CoChat Summary
TL;DR
This review systematically categorizes deep learning approaches for wearable-sensor human activity recognition (HAR), covering applications, sensors, datasets, algorithms, and open challenges. It concludes that deep learning has advanced HAR but that data, label, modeling, and deployment challenges remain.
Key findings
- The review screened 8,400 Google Scholar results and ultimately reviewed 176 papers, selecting the top 25% most relevant after exclusions.
- It organizes wearable HAR deep learning methods into six families—autoencoder, DBN, CNN, RNN (including LSTM/GRU), GAN, and deep reinforcement learning—plus hybrid models, and compares their pros, cons, deployment considerations, and model-selection criteria.
- Representative reported results include DBN accuracy of 82.3% on Opportunity, 99.2% on USC-HAD, and 99.1% on DSA; a stacked autoencoder reached 92.16% on a UCI HAR dataset; CNN+BiLSTM reached 96.37% on UCI-HAR, 96.05% on WISDM, and 94.29% on PAMAP2.
- Major challenges and opportunities are grouped into data acquisition (need for more data, quality/missing data, privacy), label acquisition (shortage of labels, in-field datasets), modeling (segmentation, complex activities, generalizability, robustness), and deployment (resource-limited platforms, computation partitioning).
Methods
- Systematic review following the 27-item PRISMA process; searched Google Scholar with meta-keywords combining HAR/wearable terms and deep learning terms using an AND rule, taking top 200 results per combination.
- Exclusion criteria removed vision/image/video HAR, environmental-sensor HAR such as WiFi- and RFID-based HAR, minor algorithmic advances, review papers, non-English papers, and works not proposing novel systems or algorithms; final set was 176 papers.
- Analysis is narrative and taxonomic: categorizes works by sensor, application, deep learning approach, and challenge, and compares algorithms on public datasets, pros/cons, deployment, and high-level model-selection criteria.
Limitations
- Stated: the review cannot include all published papers in this rapidly growing field; selection of representative works is subject to bias; it may miss the first paper initiating or adopting a method; and heterogeneity in devices, participant demography, and algorithm implementation can affect study results.
- Evident from the text: as a review, it does not present a new primary experiment or meta-analysis; reliance on Google Scholar relevance and top-25% selection may introduce selection bias; and it excludes image/video and environmental-sensor HAR by design, so findings are scoped to wearable on-body sensing.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Figures
![Figure 1 Wearable devices and their application. (a) Distribution of wearable applications [6]. (b) Typical wearable devices. (c) Distribution of wearable devices placed on common body areas [6].](https://figures.cochat.ai/paper-figures/8e85a1d007e84570831f7f35cce18d9f/deep-learning-in-human-activity-recognition-with-wearable-sensors-a-review-on-figure-1.jpg)



![Figure 5 Illustration of an autoencoder network [132].](https://figures.cochat.ai/paper-figures/7974dc35bb6d458cb837df1809383f8b/deep-learning-in-human-activity-recognition-with-wearable-sensors-a-review-on-figure-5.jpg)
![Figure 6 The greedy layer-wise training of DBNs. The first level is trained on triaxial acceleration data. Then, more RBMs are repeatedly stacked to form a deep activity recognition model [151].](https://figures.cochat.ai/paper-figures/8036e2c96a5d44afb7becd06a47fe63d/deep-learning-in-human-activity-recognition-with-wearable-sensors-a-review-on-figure-6.jpg)
![Figure 7 Schematic diagram of an RNN node and LSTM cell [202]. Left: RNN node where ht−1 is the previous hidden state, xt is the current input sample data, ht is the current hidden state, yt is the current output, and ℱ is the activation function. Right: LSTM cell with internal recurrence ct and outer recurrence ht.](https://figures.cochat.ai/paper-figures/cb6c354fef12433d903f88c3cc346079/deep-learning-in-human-activity-recognition-with-wearable-sensors-a-review-on-figure-7.jpg)
![Figure 8 The structure of LSTM and bi-directional LSTM model [204]. (a). LSTM network hidden layers containing LSTM cells and a final softmax layer at the top. (b) bi-directional LSTM network with two parallel tracks in both future (green) and past (red) directions.](https://figures.cochat.ai/paper-figures/0a460e895bc245f0a3c521d66600117b/deep-learning-in-human-activity-recognition-with-wearable-sensors-a-review-on-figure-8.jpg)
![Figure 9 A typical structure of a reinforcement learning network [229].](https://figures.cochat.ai/paper-figures/8b69aab45fc54212a45072942e10e21a/deep-learning-in-human-activity-recognition-with-wearable-sensors-a-review-on-figure-9.jpg)

Verification
Claims the paper makes
20 Valid · 19 Not valid · 101 Not checked · 99 Own results and interpretations
Every source the paper cites for this claim was checked and supports it.
In the paper
“Sigcha et al. in [149] uses a denoising autoencoder to detect freezing of gait (FOG) in Parkinson’s disease patients.”
§ Deep Learning in Human Activity Recognition with Wearable Sensors: A Review on Advances > 5. Deep Learning Approaches > 5.1. Autoencoder
What the sources say
- Supportedcites [149] Sigcha, L., Costa, N., Pavón, I., Costa, S., Arezes, P., López, J.M., and De Arcas, G. (2020). Deep learning approaches for detecting freezing of gait in Parkinson’s disease patients through on-body acceleration sensors. Sensors, 20. source
Section 3.4 says the authors tested a reconstruction-error denoiser autoencoder. Section 4.3.1 explains that the autoencoder treated abnormal movement patterns as FOG events in data from Parkinson’s disease patients. (LLM, conf=0.94)
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.
- Supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Autoencoders are also commonly used to detect abnormal muscle movements, such as Parkinson’s Disease and Autism Spectrum Disorder (ASD).”
§ Deep Learning in Human Activity Recognition with Wearable Sensors: A Review on Advances > 5. Deep Learning Approaches > 5.1. Autoencoder
What the sources say
- Partly supportedcites [34] Mohammadian Rad, N., Van Laarhoven, T., Furlanello, C., and Marchiori, E. (2018). Novelty Detection Using Deep Normative Modeling for IMU-BasedAbnormal Movement Monitoring in Parkinson’s Disease and Autism Spectrum Disorders. Sensors, 18. sourceExperimental — accuracy not yet measured
The Conclusions report using a convolutional denoising autoencoder to detect abnormal movements in patients with Parkinson’s disease and ASD. The paper does not establish that autoencoders are commonly used for those conditions; its Introduction says earlier studies mainly used supervised methods. The cited passages have no page numbers. (LLM, conf=0.84)
- Supportedcites [149] Sigcha, L., Costa, N., Pavón, I., Costa, S., Arezes, P., López, J.M., and De Arcas, G. (2020). Deep learning approaches for detecting freezing of gait in Parkinson’s disease patients through on-body acceleration sensors. Sensors, 20. source
The Related Work section reports an autoencoder-based method for detecting atypical movement patterns in people with autism spectrum disorder and Parkinson’s disease. Sections 3.4 and 4.3 also describe this paper’s use of a denoising autoencoder to detect abnormal movement associated with freezing of gait in Parkinson’s disease. (LLM, conf=0.87)
plainstates a cause- 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.
- Partly supported
Every source the paper cites for this claim was checked and supports it.
In the paper
“Gao et al. [177] has introduced a novel dual attention module including channel and temporal attention to improving the representation learning ability of a CNN model.”
§ Deep Learning in Human Activity Recognition with Wearable Sensors: A Review on Advances > 5. Deep Learning Approaches > 5.3. Convolutional Neural Network (CNN)
What the sources say
- Supportedcites [177] Gao, 2021, DanHAR: Dual Attention Network for multimodal human activity recognition using wearable sensors, Appl. Soft Comput. source
The Introduction (p. 2) states that Gao et al. propose DanHAR, a dual attention method blending channel and temporal attention on a CNN model, with the aim of increasing representation power. The Model section (p. 3) also describes its convolution, channel-attention, and temporal-attention components. (LLM, conf=0.94)
plainstates a cause- 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.
- Supported
Every source the paper cites for this claim was checked and supports it.
In the paper
“DeepConvLSTM performed significantly better in distinguishing closely-related activities, such as “Open/Close Door” and “Open/Close Drawer”.”
§ Deep Learning in Human Activity Recognition with Wearable Sensors: A Review on Advances > 5. Deep Learning Approaches > 5.4. Recurrent Neural Network (RNN)
What the sources say
- Supportedcites [208] Ordóñez, F.J., and Roggen, D. (2016). Deep convolutional and lstm recurrent neural networks for multimodal wearable activity recognition. Sensors, 16. source
The Discussion (§5.4) explicitly says DeepConvLSTM was significantly better than the baseline model at distinguishing closely related activities, giving “Open/Close Door 2” and “Open/Close Drawer 3” as examples. The Performance Comparison (§5.1) reports fewer errors for DeepConvLSTM on both pairs. (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: unclear — It is unclear whether 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
“Ketykó et al. [193] uses an RNN to address the domain adaptation problem caused by intra-session, sensor placement, and intra-subject variances.”
§ Deep Learning in Human Activity Recognition with Wearable Sensors: A Review on Advances > 5. Deep Learning Approaches > 5.4. Recurrent Neural Network (RNN)
What the sources say
- Supportedcites [193] Ketykó, I., Kovács, F., and Varga, K.Z. (2019, January 14–19). Domain adaptation for semg-based gesture recognition with recurrent neural networks. Proceedings of the 2019 International Joint Conference on Neural Networks (IJCNN), Budapest, Hungary. source
Section II.B (p. 2) enumerates exactly the three variability cases the claim lists — intra-session (trial-to-trial), inter-session with sensor placement shift/rotation, and the paper's own 'intra-subject' category for differences between subjects — and frames domain adaptation as the response to them. The Architecture (p. 3) and Experimental Setup (p. 4) confirm the model is an RNN (2-stage RNN, 2SRNN, with a stacked LSTM sequence classifier plus a linear domain-adaptation layer), and the Conclusions (p. 6) state it targets the inter-session and inter-subject domain shifts. The citing sentence also reproduces the paper's non-standard use of 'intra-subject' rather than 'inter-subject', so it tracks the source faithfully. (LLM, conf=0.85)
plainstates a cause- 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.
- Supported
82 more claims · 8 with their cited sources checked
Create a free account to see all 239 claims and to verify the 167 references still open.
- Probably not a substantial claim. 122
- It may state two separate claims as one. 58
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“According to [106], wearable devices achieved about 96% accuracy which surpasses that of the camera-based system presented in [103] for HAR.”
From A Survey of Video Surveillance Systems in Smart City (2023) · cites this paper as [106]
Experimental — accuracy not yet measuredIn the citing paper
“Recent reviews of AI-driven wearable electronics highlight the role of AI in wearable signal interpretation, personalized monitoring, human activity recognition, and real-time health analysis [47,48].”
From A Low-Cost, Accurate, and Easily-Worn E-Skin and IMU Hand Kinematic Measurement System (2026) · cites this paper as [48]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ Deep Learning in Human Activity Recognition with Wearable Sensors: A Review on Advances > 5. Deep Learning Approaches > 5.6. Generative Adversarial Network (GAN)
“Wang et al. [238] utilized GANs with a customized network to generate synthetic data from the public HAR dataset HASC2010corpus [239].”
§ Deep Learning in Human Activity Recognition with Wearable Sensors: A Review on Advances > References
“239. Kawaguchi N. Yang Y. Yang T. Ogawa N. Iwasaki Y. Kaji K. Terada T. Murao K. Inoue S. Kawahara Y. HASC2011corpus: Towards the Common Ground of Human Activity Recognition”
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ Deep Learning in Human Activity Recognition with Wearable Sensors: A Review on Advances > References
“229. Kung-Hsiang (Steeve) H. Introduction to Various Reinforcement Learning Algorithms. Part I (Q-Learning, SARSA, DQN, DDPG) 2018 Available online: https://towardsdatascience.com/introduction-to-various-reinforcement-learning-algorithms-i-q-learning-sarsa-dqn-ddpg-72a5e0cb6287 (accessed on 13 July 2012)”
§ Deep Learning in Human Activity Recognition with Wearable Sensors: A Review on Advances > References
“Introduction to Various Reinforcement Learning Algorithms. Part I (Q-Learning, SARSA, DQN, DDPG) 2018”
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ Deep Learning in Human Activity Recognition with Wearable Sensors: A Review on Advances > 5. Deep Learning Approaches > 5.2. Deep Belief Network (DBN)
“In early exploratory work back in 2011 [156], a five-layer DBN is trained with the input acceleration data collected from mobile phones.”
§ Deep Learning in Human Activity Recognition with Wearable Sensors: A Review on Advances > References
“156. Zhang L. Wu X. Luo D. Real-Time Activity Recognition on Smartphones Using Deep Neural Networks Proceedings of the 2015 IEEE 12th Intl Conf on Ubiquitous Intelligence and Computing”
Citations
Cites
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318 · cited 6×
“The concept of attention mechanism was proposed in the domain of neural machine translation to address the problem of RNNs being unable to remember long-term relationships.”
BackgroundInfluentialReinforcement Learning: An Introduction
(2005) · IEEE Transactions on Neural Networks · doi:10.1109/tnn.2004.842673 · Cited by 24,496
GAN(Generative Adversarial Nets)
(2017) · Journal of Japan Society for Fuzzy Theory and Intelligent Informatics · doi:10.3156/jsoft.29.5_177_2 · Cited by 19,270
Approximation by superpositions of a sigmoidal function
Cybenko, G. (1989) · Mathematics of Control, Signals, and Systems · doi:10.1007/bf02551274 · Cited by 13,883 · cited 1×
“Second, deep neural networks have been shown to be universal function approximators, capable of approximating almost any function given a large enough network and sufficient observations [77, 243, 340].”
BackgroundEmpirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
Chung, J., Gulcehre, C., Cho, K., & Bengio, Y. (2014) · arXiv · doi:10.48550/arxiv.1412.3555 · Cited by 11,008 · cited 1×
“In an effort to address these challenges, long short-term memory (LSTM)-based RNNs [127], and Gated Recurrent Units (GRUs) [75] are introduced to model temporal sequences and their broad dependencies.”
BackgroundA Comprehensive Survey on Graph Neural Networks
Wu, Z., Pan, S., Chen, F., Long, G., Zhang, C., & Yu, P. S. (2021) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2020.2978386 · Cited by 11,000 · cited 1×
“Besides, graph neural network can also be explored to model the hierarchical structure of simple-to-complex human activities [301].”
BackgroundLearning Deep Architectures for AI
Bengio, Y. (2009) · Foundations and Trends® in Machine Learning · doi:10.1561/2200000006 · Cited by 9,239 · cited 1×
“The observation that DBNs can be trained greedily led to one of the first effective deep learning algorithms [37].”
BackgroundLearning Deep Architectures for AI
Bengio, Y. (2009) · now publishers, Inc. eBooks · doi:10.1561/9781601982957 · Cited by 4,941
Correlates of physical activity: why are some people physically active and others not?
Bauman, A. E., Reis, R. S., Sallis, J. F., Wells, J. C., Loos, R. J., & Martin, B. W. (2012) · The Lancet · doi:10.1016/s0140-6736(12)60735-1 · Cited by 4,151 · cited 1×
“The data recorded by wearable devices during these activities include plenty of information, such as duration and intensity of activity, which further reveal an individual’s daily habits and health conditions [34].”
BackgroundDeep learning for computer vision: A brief review
Voulodimos, A., Doulamis, N., Doulamis, A., & Protopapadakis, E. (2018) · Computational Intelligence and Neuroscience · doi:10.1155/2018/7068349 · Cited by 3,403 · cited 1×
“Additionally, HAR with image/video processing has been extensively studied in the computer vision community [286, 310], and the methodologies commonly used differ significantly from techniques used for IMUs, EEG, PPG, etc.”
Method
Research works printed but not linked: 7
- Chen, 2021, NeckFace: Continuously Tracking Full Facial Expressions on Neck-Mounted Wearables, Proc. ACM Interact. Mob. Wearable Ubiquitous Technol., 5, 1
- Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., and Bengio, Y. (2014). Generative adversarial nets. Adv. Neural Inf. Process. Syst., 2672–2680. Available online: https://proceedings.neurips.cc/paper/2014/file/5ca3e9b122f61f8f06494c97b1afccf3-Paper.pdf.
- Abedin, A., Rezatofighi, H., and Ranasinghe, D.C. (2021). Guided-GAN: Adversarial Representation Learning for Activity Recognition with Wearables. arXiv.
- Gulrajani, I., Ahmed, F., Arjovsky, M., Dumoulin, V., and Courville, A. (2017). Improved training of wasserstein gans. arXiv.
- Che, T., Li, Y., Jacob, A.P., Bengio, Y., and Li, W. (2016). Mode regularized generative adversarial networks. arXiv.
- Rizve, M.N., Duarte, K., Rawat, Y.S., and Shah, M. (2021). In defense of pseudo-labeling: An uncertainty-aware pseudo-label selection framework for semi-supervised learning. arXiv.
- Konečnỳ, J., McMahan, B., and Ramage, D. (2015). Federated optimization: Distributed optimization beyond the datacenter. arXiv.
Cited by
McGenity, C., Clarke, E. L., Jennings, C., Matthews, G., Cartlidge, C., Freduah-Agyemang, H., Stocken, D. D., & Treanor, D. (2024) · npj Digital Medicine · doi:10.1038/s41746-024-01106-8 · Cited by 290
Wearable Sensor-Based Human Activity Recognition with Transformer Model
Dirgová Luptáková, I., Kubovčík, M., & Pospíchal, J. (2022) · Sensors · doi:10.3390/s22051911 · Cited by 270
Islam, M. M., Nooruddin, S., Karray, F., & Muhammad, G. (2022) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2022.106060 · Cited by 217
The major human AP endonuclease (Ape1) is involved in the nucleotide incision repair pathway
Gros, L. (2004) · Nucleic Acids Research · doi:10.1093/nar/gkh165 · Cited by 209
Kumar, P., Chauhan, S., & Awasthi, L. K. (2024) · Archives of Computational Methods in Engineering · doi:10.1007/s11831-023-09986-x · Cited by 206
“With the advent of DL, activity recognition performance has reached new heights in wearables-based HAR [111].”
Influential
Metadata
- Authors
- Zhang, S., Li, Y., Zhang, S., Shahabi, F., Xia, S., Deng, Y., & Alshurafa, N.
- Affiliations
- Northwestern University (US)
- McGill University (CA)
- Columbia University (US)
- Corresponding author
- Zhang, Shibo
- Venue
- Sensors
- Publisher
- MDPI AG
- Published
- 2022-02-14
- Volume
- 22
- Issue
- 4
- Pages
- 1476
- ISSN
- 1424-8220 (ISSN-L)
- PMC
- PMC8879042
- OpenAlex
- W3210766530
- Cited by
- 625
- References
- 353
- Citations by year
- 2026: 166 · 2025: 150 · 2024: 135 · 2023: 107 · 2022: 38
- FWCI
- 9.15
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Sensors (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- arXiv (Cornell University)
- 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 › Computer Vision and Pattern Recognition › Human Pose and Action Recognition
- Keywords
- human activity recognition, wearable sensors, deep learning, mobile devices, activity monitoring, wellness monitoring, human-computer interaction, low-power sensors
- MeSH terms
- Wearable Electronic Devices, Deep Learning, Humans, Human Activities
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 2026-10-07, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-07 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol and qwen3.8-omni-flash).
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Deep Learning in Human Activity Recognition with Wearable Sensors: A Review on Advances. https://app.cochat.ai/papers/10.3390/s22041476
- The paper
- Zhang, S., Li, Y., Zhang, S., Shahabi, F., Xia, S., Deng, Y., & Alshurafa, N. (2022). Deep Learning in Human Activity Recognition with Wearable Sensors: A Review on Advances. Sensors. https://doi.org/10.3390/s22041476
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.