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.”
MethodA Comprehensive Survey on Graph Neural Networks
Wu, Z., Pan, S., Chen, F., Long, G., Zhang, C., & Yu, P. (2020) · UTS ePRESS (University of Technology Sydney) · Cited by 3,174
Activity recognition using cell phone accelerometers
Kwapisz, J. R., Weiss, G. M., & Moore, S. A. (2011) · ACM SIGKDD Explorations Newsletter · doi:10.1145/1964897.1964918 · Cited by 2,912 · cited 9×
“The accuracy on UCI-HAR, WISDM[155], and PAMAP2[228] datasets achieved 96.”
BackgroundMethodInfluentialA Practical Guide to Training Restricted Boltzmann Machines
Hinton, G. E. (2012) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-35289-8_32 · Cited by 2,852 · cited 1×
“The DBNs built are 2-layer RBMs, with the first layer as a Guassian-binary RBM (containing gaussian visible units) and the second layer as binary-binary (containing only binary units) (please refer to [125] for details).”
BackgroundDeep Convolutional and LSTM Recurrent Neural Networks for Multimodal Wearable Activity Recognition
Ordóñez, F., & Roggen, D. (2016) · Sensors · doi:10.3390/s16010115 · Cited by 2,761 · cited 1×
“[207] proposes a hybrid CNN and LSTM model (DeepConvLSTM) for activity recognition using multimodal wearable sensor data.”
BackgroundLack of Exercise Is a Major Cause of Chronic Diseases
Booth, F. W., Roberts, C. K., & Laye, M. J. (2012) · Comprehensive Physiology · doi:10.1002/cphy.c110025 · Cited by 2,575 · cited 1×
“Regular physical activity is increasingly being linked to reduction in risk for many chronic diseases, such as obesity, diabetes, and cardiovascular disease, and has been shown to improve mental health [44].”
BackgroundGenerative Adversarial Text to Image Synthesis
Reed, S., Akata, Z., Yan, X., Logeswaran, L., Schiele, B., & Lee, H. (2016) · arXiv · doi:10.48550/arxiv.1605.05396 · Cited by 2,494
Arjovsky, M., Chintala, S., & Bottou, L. (2017) · arXiv · doi:10.48550/arxiv.1701.07875 · Cited by 2,225
Deep learning for sensor-based activity recognition: A survey
Wang, J., Chen, Y., Hao, S., Peng, X., & Hu, L. (2019) · Pattern Recognition Letters · doi:10.1016/j.patrec.2018.02.010 · Cited by 2,014 · cited 2×
“There are some existing review papers in the literature for deep learning approaches for sensor-based human activity recognition [63, 204, 224, 291].”
Background(2013) · RECERCAT (Consorci de Serveis Universitaris de Catalunya) · Cited by 1,959
A tutorial on human activity recognition using body-worn inertial sensors
Bulling, A., Blanke, U., & Schiele, B. (2014) · ACM Computing Surveys · doi:10.1145/2499621 · Cited by 1,668 · cited 3×
“Extensive experiments are performed on Opportunity [59], Skoda [316], and Hand-Gesture [49] datasets.”
BackgroundMethodA survey on security and privacy of federated learning
Mothukuri, V., Parizi, R. M., Pouriyeh, S., Huang, Y., Dehghantanha, A., & Srivastava, G. (2021) · Future Generation Computer Systems · doi:10.1016/j.future.2020.10.007 · Cited by 1,480 · cited 1×
“Federated learning is a trending approach to resolve privacy issue in learning problems [45, 167, 192, 259].”
BackgroundIntroducing a New Benchmarked Dataset for Activity Monitoring
Reiss, A., & Stricker, D. (2012) · 2012 16th International Symposium on Wearable Computers · doi:10.1109/iswc.2012.13 · Cited by 1,456 · cited 10×
“The accuracy on UCI-HAR, WISDM[155], and PAMAP2[228] datasets achieved 96.”
BackgroundMethodInfluentialHuman activity recognition with smartphone sensors using deep learning neural networks
Ronao, C. A., & Cho, S.-B. (2016) · Expert Systems with Applications · doi:10.1016/j.eswa.2016.04.032 · Cited by 1,215
Learning the signatures of the human grasp using a scalable tactile glove
Sundaram, S., Kellnhofer, P., Li, Y., Zhu, J.-Y., Torralba, A., & Matusik, W. (2019) · Nature · doi:10.1038/s41586-019-1234-z · Cited by 1,162 · cited 1×
“1b, there are a large number of off-the-shelf smart devices or prototypes under development today, including smartphones, smartwatches, smart glasses, smart rings [208], smart gloves [266], smart armbands [151], smart necklaces [64, 142, 328], smart shoes [106], and Etattoos [249].”
BackgroundSelf-citationDau, H. A., Bagnall, A., Kamgar, K., Yeh, C.-C. M., Zhu, Y., Gharghabi, S., Ratanamahatana, C. A., & Keogh, E. (2019) · IEEE/CAA Journal of Automatica Sinica · doi:10.1109/jas.2019.1911747 · Cited by 1,128
(2015) · Cited by 989
Nweke, H. F., Teh, Y. W., Al-garadi, M. A., & Alo, U. R. (2018) · Expert Systems with Applications · doi:10.1016/j.eswa.2018.03.056 · Cited by 930 · cited 2×
“There are some existing review papers in the literature for deep learning approaches for sensor-based human activity recognition [63, 204, 224, 291].”
BackgroundMethodArjovsky, M., Bottou, L., Gulrajani, I., & Lopez-Paz, D. (2019) · arXiv · doi:10.48550/arxiv.1907.02893 · Cited by 927
A Comprehensive Survey of Deep Learning for Image Captioning
Hossain, M. Z., Sohel, F., Shiratuddin, M. F., & Laga, H. (2019) · ACM Computing Surveys · doi:10.1145/3295748 · Cited by 879 · cited 1×
“If we take a broader view, many works are using cross-modal deep generative models (such as GAN) in data synthesis, such as from video to audio [266], from text to image and vice versa [267, 268].”
BackgroundConvolutional Neural Networks for Human Activity Recognition using Mobile Sensors
Zeng, M., Nguyen, L. T., Yu, B., Mengshoel, O. J., Zhu, J., Wu, P., & Zhang, J. (2014) · Proceedings of the 6th International Conference on Mobile Computing, Applications and Services · doi:10.4108/icst.mobicase.2014.257786 · Cited by 876 · cited 1×
“Therefore, the use of wearables in fitness and lifestyle has the potential to significantly advance one of the most prolific aspects of HAR applications [68, 136, 138, 164, 169, 233, 293, 295, 318].”
BackgroundAccurate activity recognition in a home setting
van Kasteren, T., Noulas, A., Englebienne, G., & Kröse, B. (2008) · Proceedings of the 10th international conference on Ubiquitous computing · doi:10.1145/1409635.1409637 · Cited by 874 · cited 2×
“While most datasets are used to recognize physical activity or daily activities [19, 20, 30, 31, 47, 59, 61, 143, 155, 188, 228, 251, 252, 264, 279, 282, 299, 327, 335], there are also a few datasets dedicated to hand gestures [49, 156], breathing patterns [58], and car assembly line activities [316], as well as those…”
BackgroundMethodLSTM-CNN Architecture for Human Activity Recognition
Xia, K., Huang, J., & Wang, H. (2020) · IEEE Access · doi:10.1109/access.2020.2982225 · Cited by 851 · cited 1×
“Similarly, other researchers [8, 82, 94, 95, 197, 245, 301, 302], [238] have also developed the CNN-LSTM model in varios application scenarios by taking advantage of the feature extraction ability of CNN and the time-series data reasoning ability of LSTM.”
BackgroundChen, C., Jafari, R., & Kehtarnavaz, N. (2015) · 2015 IEEE International Conference on Image Processing (ICIP) · doi:10.1109/icip.2015.7350781 · Cited by 765 · cited 2×
“While most datasets are used to recognize physical activity or daily activities [19, 20, 30, 31, 47, 59, 61, 143, 155, 188, 228, 251, 252, 264, 279, 282, 299, 327, 335], there are also a few datasets dedicated to hand gestures [49, 156], breathing patterns [58], and car assembly line activities [316], as well as those…”
BackgroundMethodZhang, Z., Pi, Z., & Liu, B. (2015) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2014.2359372 · Cited by 748 · cited 1×
“While most datasets are used to recognize physical activity or daily activities [19, 20, 30, 31, 47, 59, 61, 143, 155, 188, 228, 251, 252, 264, 279, 282, 299, 327, 335], there are also a few datasets dedicated to hand gestures [49, 156], breathing patterns [58], and car assembly line activities [316], as well as those…”
BackgroundThe Opportunity challenge: A benchmark database for on-body sensor-based activity recognition
Chavarriaga, R., Sagha, H., Calatroni, A., Digumarti, S. T., Tröster, G., Millán, J. D. R., & Roggen, D. (2013) · Pattern Recognition Letters · doi:10.1016/j.patrec.2012.12.014 · Cited by 742 · cited 7×
“Extensive experiments are performed on Opportunity [59], Skoda [316], and Hand-Gesture [49] datasets.”
BackgroundMethodInfluentialUm, T. T., Pfister, F. M. J., Pichler, D., Endo, S., Lang, M., Hirche, S., Fietzek, U., & Kulić, D. (2017) · Proceedings of the 19th ACM International Conference on Multimodal Interaction · doi:10.1145/3136755.3136817 · Cited by 729 · cited 2×
“In general, using the dataset augmented with synthetic training samples yields higher classification accuracy when compared to using the original dataset [36,56,261,262].”
BackgroundMethodStisen, A., Blunck, H., Bhattacharya, S., Prentow, T. S., Kjærgaard, M. B., Dey, A., Sonne, T., & Jensen, M. M. (2015) · Proceedings of the 13th ACM Conference on Embedded Networked Sensor Systems · doi:10.1145/2809695.2809718 · Cited by 714 · cited 1×
“During recent years, many efforts have been put into improving the generalizability of models in HAR [3, 219, 262].”
BackgroundWearable Assistant for Parkinson’s Disease Patients With the Freezing of Gait Symptom
Bachlin, M., Plotnik, M., Roggen, D., Maidan, I., Hausdorff, J. M., Giladi, N., & Troster, G. (2010) · IEEE Transactions on Information Technology in Biomedicine · doi:10.1109/titb.2009.2036165 · Cited by 693 · cited 4×
“6 50–200 Hz 37 Daily & Sports Activities [19] Locomotion 9D IMU 19 25 Hz 37 MHEALTH [30, 31] Locomotion & gesture 9D IMU & ECG 12 50 Hz 33 Opportunity [59] Locomotion & gesture 9D IMU 16 50 Hz 32 PAMAP2 [228] Locomotion & activities 9D IMU & HR monitor 18 100 Hz 32 Daphnet [23] Freezing of gait 3D Acc.”
BackgroundMethodInfluentialHuman Activity Recognition Using Wearable Sensors by Deep Convolutional Neural Networks
Jiang, W., & Yin, Z. (2015) · Proceedings of the 23rd ACM international conference on Multimedia · doi:10.1145/2733373.2806333 · Cited by 676 · cited 1×
“Therefore, the use of wearables in fitness and lifestyle has the potential to significantly advance one of the most prolific aspects of HAR applications [68, 136, 138, 164, 169, 233, 293, 295, 318].”
BackgroundQiu, S., Zhao, H., Jiang, N., Wang, Z., Liu, L., An, Y., Zhao, H., Miao, X., Liu, R., & Fortino, G. (2022) · Information Fusion · doi:10.1016/j.inffus.2021.11.006 · Cited by 671 · cited 1×
“That is, how to adapt the model in a dynamic environment without significant performance degradation [7, 220].”
BackgroundDeepSense: A Unified Deep Learning Framework for Time-Series Mobile Sensing Data Processing
Yao, S., Hu, S., Zhao, Y., Zhang, A., & Abdelzaher, T. (2017) · Proceedings of the 26th International Conference on World Wide Web · doi:10.1145/3038912.3052577 · Cited by 667 · cited 1×
“[315] proposes a light-weight CNN and RNN-based system that accounts for noisy sensor readings from smartphones and automatically learns more local and global features between sensor windows to improve classification and regression performance on smartphones.”
BackgroundFederated learning meets blockchain in edge computing: Opportunities and challenges
Nguyen, D. C., Ding, M., Pham, Q.-V., Pathirana, P. N., Le, L. B., Seneviratne, A., Li, J., Niyato, D., & Poor, H. V. (2021) · IEEE Internet of Things Journal · doi:10.1109/jiot.2021.3072611 · Cited by 661 · cited 1×
“The combination of federated learning and blockchain is also a potential solution towards privacy protection [200] and currently still in its very early stage.”
BackgroundA robust human activity recognition system using smartphone sensors and deep learning
Hassan, M. M., Uddin, M. Z., Mohamed, A., & Almogren, A. (2018) · Future Generation Computer Systems · doi:10.1016/j.future.2017.11.029 · Cited by 656 · cited 5×
“Researchers have proposed various algorithms to extract features from sensor signals and to perform activity classification using machine-learned models like K Nearest Neighbor (KNN) and SVM [123, 149, 168, 193, 254, 265, 270, 290, 313, 319].”
MethodInfluentialMultivariate Time Series Imputation with Generative Adversarial Networks
Luo, Y., Cai, X., Zhang, Y., Xu, J., & Yuan, X. (2018) · neural information processing systems · Cited by 627
Deep, Convolutional, and Recurrent Models for Human Activity Recognition Using Wearables
Hammerla, N. Y., Halloran, S., & Ploetz, T. (2016) · arXiv · doi:10.48550/arxiv.1604.08880 · Cited by 606 · cited 3×
“The authors assessed thousands of settings with random hyperparameters and provided guidelines for practitioners seeking to apply deep learning to their own problem scenarios [121].”
BackgroundInfluentialUm, T. T. (n.d.) · mediaTUM – the media and publications repository of the Technical University Munich (Technical University Munich) · Cited by 602
UniMiB SHAR: A Dataset for Human Activity Recognition Using Acceleration Data from Smartphones
Micucci, D., Mobilio, M., & Napoletano, P. (2017) · doi:10.20944/preprints201706.0033.v2 · Cited by 596
UniMiB SHAR: A Dataset for Human Activity Recognition Using Acceleration Data from Smartphones
Micucci, D., Mobilio, M., & Napoletano, P. (2017) · doi:10.20944/preprints201706.0033.v1 · Cited by 596 · cited 3×
“While most datasets are used to recognize physical activity or daily activities [19, 20, 30, 31, 47, 59, 61, 143, 155, 188, 228, 251, 252, 264, 279, 282, 299, 327, 335], there are also a few datasets dedicated to hand gestures [49, 156], breathing patterns [58], and car assembly line activities [316], as well as those…”
BackgroundMethodUniMiB SHAR: A Dataset for Human Activity Recognition Using Acceleration Data from Smartphones
Micucci, D., Mobilio, M., & Napoletano, P. (2017) · Applied Sciences · doi:10.3390/app7101101 · Cited by 596
Deep Learning Models for Real-time Human Activity Recognition with Smartphones
Wan, S., Qi, L., Xu, X., Tong, C., & Gu, Z. (2020) · Mobile Networks and Applications · doi:10.1007/s11036-019-01445-x · Cited by 594
mHealthDroid: A Novel Framework for Agile Development of Mobile Health Applications
Banos, O., Garcia, R., Holgado-Terriza, J. A., Damas, M., Pomares, H., Rojas, I., Saez, A., & Villalonga, C. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-13105-4_14 · Cited by 583 · cited 2×
“6 50–200 Hz 37 Daily & Sports Activities [19] Locomotion 9D IMU 19 25 Hz 37 MHEALTH [30, 31] Locomotion & gesture 9D IMU & ECG 12 50 Hz 33 Opportunity [59] Locomotion & gesture 9D IMU 16 50 Hz 32 PAMAP2 [228] Locomotion & activities 9D IMU & HR monitor 18 100 Hz 32 Daphnet [23] Freezing of gait 3D Acc.”
BackgroundMethodComparative study on classifying human activities with miniature inertial and magnetic sensors
Altun, K., Barshan, B., & Tunçel, O. (2010) · Pattern Recognition · doi:10.1016/j.patcog.2010.04.019 · Cited by 564 · cited 3×
“6 50–200 Hz 37 Daily & Sports Activities [19] Locomotion 9D IMU 19 25 Hz 37 MHEALTH [30, 31] Locomotion & gesture 9D IMU & ECG 12 50 Hz 33 Opportunity [59] Locomotion & gesture 9D IMU 16 50 Hz 32 PAMAP2 [228] Locomotion & activities 9D IMU & HR monitor 18 100 Hz 32 Daphnet [23] Freezing of gait 3D Acc.”
BackgroundMethoduWave: Accelerometer-based personalized gesture recognition and its applications
Liu, J., Wang, Z., Zhong, L., Wickramasuriya, J., & Vasudevan, V. (2009) · 2009 IEEE International Conference on Pervasive Computing and Communications · doi:10.1109/percom.2009.4912759 · Cited by 559
USC-HAD: a daily activity dataset for ubiquitous activity recognition using wearable sensors
Zhang, M., & Sawchuk, A. A. (2012) · Proceedings of the 2012 ACM Conference on Ubiquitous Computing · doi:10.1145/2370216.2370438 · Cited by 554 · cited 5×
“Specifically, the accuracy for the Opportunity, USC-HAD, and DSA datasets are 82.3% (1.6% improvement over traditional methods), 99.2% (13.9% improvement), and 99.1% (15.9% improvement), respectively.”
BackgroundMethodInfluentialFusion of Smartphone Motion Sensors for Physical Activity Recognition
Shoaib, M., Bosch, S., Incel, O., Scholten, H., & Havinga, P. (2014) · Sensors · doi:10.3390/s140610146 · Cited by 552
Universality of deep convolutional neural networks
Zhou, D.-X. (2020) · Applied and Computational Harmonic Analysis · doi:10.1016/j.acha.2019.06.004 · Cited by 530 · 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].”
BackgroundDeep Recurrent Neural Networks for Human Activity Recognition
Murad, A., & Pyun, J.-Y. (2017) · Sensors · doi:10.3390/s17112556 · Cited by 524 · cited 4×
“Previous studies have shown that LSTMs have high performance in wearable HAR [199, 202, 203].”
BackgroundInfluentialSemi-Supervised Learning with Generative Adversarial Networks
Odena, A. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1606.01583 · Cited by 509 · cited 1×
“In the field of HAR, GAN has been applied as a semi-supervised learning approach to deal with unlabeled or partially labeled data for improving performance by learning representations from the unlabeled data which later will be utilized by the network to generalize to the unseen data distribution [178, 205, 260] [247]…”
MethodSullivan, A. N., & Lachman, M. E. (2017) · Frontiers in Public Health · doi:10.3389/fpubh.2016.00289 · Cited by 458 · cited 1×
“Being aware of daily locomotion and transportation patterns can provide physicians with the necessary information to better understand patients’ conditions and also encourage users to engage in more exercise to promote behavior change [43].”
BackgroundRamanujam, E., Perumal, T., & Padmavathi, S. (2021) · IEEE Sensors Journal · doi:10.1109/jsen.2021.3069927 · Cited by 455 · cited 2×
“There are some existing review papers in the literature for deep learning approaches for sensor-based human activity recognition [63, 204, 224, 291].”
BackgroundMethodA CNN-LSTM Approach to Human Activity Recognition
Mutegeki, R., & Han, D. S. (2020) · 2020 International Conference on Artificial Intelligence in Information and Communication (ICAIIC) · doi:10.1109/icaiic48513.2020.9065078 · Cited by 452 · cited 1×
“Similarly, other researchers [8, 82, 94, 95, 197, 245, 301, 302], [238] have also developed the CNN-LSTM model in varios application scenarios by taking advantage of the feature extraction ability of CNN and the time-series data reasoning ability of LSTM.”
BackgroundDeepX: A Software Accelerator for Low-Power Deep Learning Inference on Mobile Devices
Lane, N. D., Bhattacharya, S., Georgiev, P., Forlivesi, C., Jiao, L., Qendro, L., & Kawsar, F. (2016) · 2016 15th ACM/IEEE International Conference on Information Processing in Sensor Networks (IPSN) · doi:10.1109/ipsn.2016.7460664 · Cited by 450 · cited 1×
“[160] proposes a SOC-based architecture for optimizing deep neural network inference, while Lane et al.”
MethodMulti-input CNN-GRU based human activity recognition using wearable sensors
Dua, N., Singh, S. N., & Semwal, V. B. (2021) · Computing · doi:10.1007/s00607-021-00928-8 · Cited by 432 · cited 1×
“[86] proposed a model with CNN combined with GRU and obtained accuracy of 96.”
MethodComputer vision techniques in construction: A critical review
Xu, S., Wang, J., Shou, W., Ngo, T., Sadick, A.-M., & Wang, X. (2021) · Archives of Computational Methods in Engineering · doi:10.1007/s11831-020-09504-3 · Cited by 409 · 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.”
MethodFitbit®: An accurate and reliable device for wireless physical activity tracking
Diaz, K. M., Krupka, D. J., Chang, M. J., Peacock, J., Ma, Y., Goldsmith, J., Schwartz, J. E., & Davidson, K. W. (2015) · International Journal of Cardiology · doi:10.1016/j.ijcard.2015.03.038 · Cited by 405
Deep Learning is Robust to Massive Label Noise
Rolnick, D., Veit, A., Belongie, S., & Shavit, N. (2017) · arXiv · doi:10.48550/arxiv.1705.10694 · Cited by 402
A Deep Learning Approach to Human Activity Recognition Based on Single Accelerometer
Chen, Y., & Xue, Y. (2015) · 2015 IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc.2015.263 · Cited by 378 · cited 3×
“A majority of the CNNs consist of 5 to 9 layers [67, 91, 193, 232, 272, 300, 313], [130], [96], usually including 2 to 3 convolutional layers, 2 to 3 max pooling layers, followed by 1 to 2 fully connected layers before feeding the feature representation into the output layer (softmax layer in most cases).”
BackgroundMethodModular learning in neural networks
Ballard, D. H. (1987) · National Conference on Artificial Intelligence · Cited by 362
Gesture recognition using recurrent neural networks
Murakami, K., & Taguchi, H. (1991) · Proceedings of the SIGCHI conference on Human factors in computing systems Reaching through technology - CHI '91 · doi:10.1145/108844.108900 · Cited by 359 · cited 1×
“Initially, the idea of using temporal information was proposed in 1991 [196] to recognize a finger alphabet consisting of 42 symbols and in 1995 [281] to classify 66 different hand shapes with about 98% accuracy.”
MethodBRITS: Bidirectional Recurrent Imputation for Time Series
Cao, W., Wang, D., Li, J., Zhou, H., Li, L., & Li, Y. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1805.10572 · Cited by 357 · cited 1×
“introduced a bi-directional recurrent neural network to impute time series data on the UCI localization dataset [51].”
BackgroundSelf-citationDeep Residual Bidir-LSTM for Human Activity Recognition Using Wearable Sensors
Zhao, Y., Yang, R., Chevalier, G., Xu, X., & Zhang, Z. (2018) · Mathematical Problems in Engineering · doi:10.1155/2018/7316954 · Cited by 348
A multibranch CNN-BiLSTM model for human activity recognition using wearable sensor data
Challa, S. K., Kumar, A., & Semwal, V. B. (2022) · The Visual Computer · doi:10.1007/s00371-021-02283-3 · Cited by 338 · cited 1×
“[55] proposed a hybrid of CNN and bidirectional long short-term memory (BiLSTM).”
BackgroundInnoHAR: A Deep Neural Network for Complex Human Activity Recognition
Xu, C., Chai, D., He, J., Zhang, X., & Duan, S. (2019) · IEEE Access · doi:10.1109/access.2018.2890675 · Cited by 333 · cited 1×
“In [309], the authors have used GoogLeNet’s Inception module combined with a GRU layer to build a HAR model.”
MethodParajuli, N., Sreenivasan, N., Bifulco, P., Cesarelli, M., Savino, S., Niola, V., Esposito, D., Hamilton, T. J., Naik, G. R., Gunawardana, U., et al. (2019) · Sensors · doi:10.3390/s19204596 · Cited by 332 · cited 1×
“In addition, detecting muscular activities and hand motions using electromyography (EMG) sensors has been widely applied to enable improved prostheses control for people with missing or damaged limbs [186, 209, 211, 240].”
MethodHuman activity recognition from accelerometer data using Convolutional Neural Network
Lee, S.-M., Yoon, S. M., & Cho, H. (2017) · 2017 IEEE International Conference on Big Data and Smart Computing (BigComp) · doi:10.1109/bigcomp.2017.7881728 · Cited by 331 · cited 1×
“Therefore, the use of wearables in fitness and lifestyle has the potential to significantly advance one of the most prolific aspects of HAR applications [68, 136, 138, 164, 169, 233, 293, 295, 318].”
BackgroundActivity Recognition from On-Body Sensors: Accuracy-Power Trade-Off by Dynamic Sensor Selection
Zappi, P., Lombriser, C., Stiefmeier, T., Farella, E., Roggen, D., Benini, L., & Tröster, G. (2008) · Lecture Notes in Computer Science · doi:10.1007/978-3-540-77690-1_2 · Cited by 329 · cited 9×
“Extensive experiments are performed on Opportunity [59], Skoda [316], and Hand-Gesture [49] datasets.”
BackgroundMethodInfluentialRecognizing Detailed Human Context in the Wild from Smartphones and Smartwatches
Vaizman, Y., Ellis, K., & Lanckriet, G. (2017) · IEEE Pervasive Computing · doi:10.1109/mprv.2017.3971131 · Cited by 324 · cited 3×
“12 100 Hz 20 ExtraSensory [279] Locomotion & activities 9D IMU & GPS 10 25–40 Hz 13 HASC [143] Locomotion Smartphone 9D IMU 6 100 Hz 11 Actitracker [299] Locomotion 9D IMU & GPS 5 N/A 6 FIC [156] Feeding gestures 3D Acc.”
BackgroundBanos, O., Villalonga, C., Garcia, R., Saez, A., Damas, M., Holgado-Terriza, J. A., Lee, S., Pomares, H., & Rojas, I. (2015) · BioMedical Engineering OnLine · doi:10.1186/1475-925x-14-s2-s6 · Cited by 321 · cited 2×
“6 50–200 Hz 37 Daily & Sports Activities [19] Locomotion 9D IMU 19 25 Hz 37 MHEALTH [30, 31] Locomotion & gesture 9D IMU & ECG 12 50 Hz 33 Opportunity [59] Locomotion & gesture 9D IMU 16 50 Hz 32 PAMAP2 [228] Locomotion & activities 9D IMU & HR monitor 18 100 Hz 32 Daphnet [23] Freezing of gait 3D Acc.”
BackgroundMethodTransfer learning for time series classification
Ismail Fawaz, H., Forestier, G., Weber, J., Idoumghar, L., & Muller, P.-A. (2018) · 2018 IEEE International Conference on Big Data (Big Data) · doi:10.1109/bigdata.2018.8621990 · Cited by 319
Deep Learning for Sensor-based Human Activity Recognition: Overview, Challenges and Opportunities
Chen, K., Zhang, D., Yao, L., Guo, B., Yu, Z., & Liu, Y. (2020) · arXiv · doi:10.48550/arxiv.2001.07416 · Cited by 314 · cited 3×
“There are some existing review papers in the literature for deep learning approaches for sensor-based human activity recognition [63, 204, 224, 291].”
BackgroundImaging and fusing time series for wearable sensor-based human activity recognition
Qin, Z., Zhang, Y., Meng, S., Qin, Z., & Choo, K.-K. R. (2020) · Information Fusion · doi:10.1016/j.inffus.2019.06.014 · Cited by 309 · cited 1×
“During recent years, many efforts have been put into improving the generalizability of models in HAR [3, 219, 262].”
BackgroundHa, S., & Choi, S. (2016) · 2016 International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2016.7727224 · Cited by 307 · cited 1×
“[116] C-P-C-P-FC-FC-S daily activities, locomotion activities 12 S1, S2, S3 ECG mHealth”
BackgroundComparison of Feature Learning Methods for Human Activity Recognition Using Wearable Sensors
Li, F., Shirahama, K., Nisar, M., Köping, L., & Grzegorzek, M. (2018) · Sensors · doi:10.3390/s18020679 · Cited by 302 · cited 5×
“Researchers have proposed various algorithms to extract features from sensor signals and to perform activity classification using machine-learned models like K Nearest Neighbor (KNN) and SVM [123, 149, 168, 193, 254, 265, 270, 290, 313, 319].”
MethodInfluentialThe MobiAct Dataset: Recognition of Activities of Daily Living using Smartphones
Vavoulas, G., Chatzaki, C., Malliotakis, T., Pediaditis, M., & Tsiknakis, M. (2016) · Proceedings of the International Conference on Information and Communication Technologies for Ageing Well and e-Health · doi:10.5220/0005792401430151 · Cited by 301 · cited 1×
“Both the publicly available MobiAct [284] and a new dataset, MotionSense, are used to evaluate the proposed framework’s efficacy.”
MethodUnsupervised and Semi-supervised Learning with Categorical Generative Adversarial Networks
Springenberg, J. T. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1511.06390 · Cited by 300 · cited 1×
“In the field of HAR, GAN has been applied as a semi-supervised learning approach to deal with unlabeled or partially labeled data for improving performance by learning representations from the unlabeled data which later will be utilized by the network to generalize to the unseen data distribution [178, 205, 260] [247]…”
MethodMobile sensor data anonymization
Malekzadeh, M., Clegg, R. G., Cavallaro, A., & Haddadi, H. (2019) · Proceedings of the International Conference on Internet of Things Design and Implementation · doi:10.1145/3302505.3310068 · Cited by 298 · cited 3×
“Similarly, the same authors have proposed another anonymizing autoencoder in [182] for classifying different activities while reducing user identification accuracy.”
BackgroundMethodRecurrent Neural Networks Are Universal Approximators
Schäfer, A. M., & Zimmermann, H. G. (2006) · Lecture Notes in Computer Science · doi:10.1007/11840817_66 · Cited by 297 · 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].”
BackgroundCan Deep Learning Revolutionize Mobile Sensing?
Lane, N. D., & Georgiev, P. (2015) · Proceedings of the 16th International Workshop on Mobile Computing Systems and Applications · doi:10.1145/2699343.2699349 · Cited by 282 · cited 1×
“performed a small-scale exploration into the performance of DNNs for HAR applications on a mobile platforms in various configurations, including utilizing the phone’s CPU and DSP and offloading computation onto remote devices [158].”
BackgroundFirst-Person Activity Recognition: What Are They Doing to Me?
Ryoo, M. S., & Matthies, L. (2013) · 2013 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2013.352 · Cited by 279 · cited 1×
“It is also important to note that the wearable camera market has drastically grown with cameras such as GoPro becoming mainstream [15, 16, 117, 235] over the last few years.”
BackgroundGjoreski, H., Ciliberto, M., Wang, L., Ordonez Morales, F. J., Mekki, S., Valentin, S., & Roggen, D. (2018) · IEEE Access · doi:10.1109/access.2018.2858933 · Cited by 276 · cited 5×
“Dmitrijs demonstrated on the SHL dataset, with a CNN and AAE architecture, that semi-supervised learning on unlabeled data could achieve high accuracy [28].”
BackgroundInfluentialDeep recurrent neural network for mobile human activity recognition with high throughput
Inoue, M., Inoue, S., & Nishida, T. (2018) · Artificial Life and Robotics · doi:10.1007/s10015-017-0422-x · Cited by 275 · cited 1×
“Since then, the recurrent neural network (RNN) with time series as input has been widely applied to classify human activities or estimate hand gestures [52, 65, 132, 175, 268, 269, 275], [12].”
BackgroundEMG Pattern Recognition in the Era of Big Data and Deep Learning
Phinyomark, A., & Scheme, E. (2018) · Big Data and Cognitive Computing · doi:10.3390/bdcc2030021 · Cited by 272 · cited 2×
“Thanks to accurate activity, gesture, and motion detection from wearables, these applications could induce feelings of cold or hot weather by providing an immersive experience by varying the virtual environment and could enable more realistic interaction between the human and virtual objects [186, 211].”
BackgroundMethodRavi, D., Wong, C., Lo, B., & Yang, G.-Z. (2016) · 2016 IEEE 13th International Conference on Wearable and Implantable Body Sensor Networks (BSN) · doi:10.1109/bsn.2016.7516235 · Cited by 269
ViBand: High-Fidelity Bio-Acoustic Sensing Using Commodity Smartwatch Accelerometers
Laput, G., Xiao, R., & Harrison, C. (2016) · Proceedings of the 29th Annual Symposium on User Interface Software and Technology · doi:10.1145/2984511.2984582 · Cited by 265 · cited 1×
“For example, the projects presented in [161, 162] utilize sampling rates above the typical rate.”
BackgroundSteven Eyobu, O., & Han, D. S. (2018) · Sensors · doi:10.3390/s18092892 · Cited by 259
A federated learning system with enhanced feature extraction for human activity recognition
Xiao, Z., Xu, X., Xing, H., Song, F., Wang, X., & Zhao, B. (2021) · Knowledge-Based Systems · doi:10.1016/j.knosys.2021.107338 · Cited by 251 · cited 1×
“[308] realized a federated averaging method combined with a perceptive extraction network to improve the performance of the federated learning system.”
MethodBhattacharya, S., & Lane, N. D. (2016) · Proceedings of the 14th ACM Conference on Embedded Networked Sensor Systems CD-ROM · doi:10.1145/2994551.2994564 · Cited by 236 · cited 3×
“Lane et al. performed a small-scale exploration into the performance of DNNs for HAR applications on a mobile platforms in various configurations, including utilizing the phone’s CPU and DSP and offloading computation onto remote devices [158].”
BackgroundInfluentialTowards Physical Activity Recognition Using Smartphone Sensors
Shoaib, M., Scholten, H., & Havinga, P. J. M. (2013) · 2013 IEEE 10th International Conference on Ubiquitous Intelligence and Computing and 2013 IEEE 10th International Conference on Autonomic and Trusted Computing · doi:10.1109/uic-atc.2013.43 · Cited by 228 · cited 2×
“While most datasets are used to recognize physical activity or daily activities [19, 20, 30, 31, 47, 59, 61, 143, 155, 188, 228, 251, 252, 264, 279, 282, 299, 327, 335], there are also a few datasets dedicated to hand gestures [49, 156], breathing patterns [58], and car assembly line activities [316], as well as those…”
BackgroundMultiday EMG-Based Classification of Hand Motions with Deep Learning Techniques
Zia ur Rehman, M., Waris, A., Gilani, S. O., Jochumsen, M., Niazi, I. K., Jamil, M., Farina, D., & Kamavuako, E. N. (2018) · Sensors · doi:10.3390/s18082497 · Cited by 226 · cited 1×
“There are a number of wearable applications that detect and assess daily activities using sEMG [186, 278].”
BackgroundDanHAR: Dual Attention Network for multimodal human activity recognition using wearable sensors
Gao, W., Zhang, L., Teng, Q., He, J., & Wu, H. (2021) · Applied Soft Computing · doi:10.1016/j.asoc.2021.107728 · Cited by 214 · cited 1×
“[97] has introduced a novel dual attention module including channel and temporal attention to improve the representation learning ability of a CNN model.”
BackgroundWang, K., He, J., & Zhang, L. (2019) · IEEE Sensors Journal · doi:10.1109/jsen.2019.2917225 · Cited by 206 · cited 1×
“Therefore, the use of wearables in fitness and lifestyle has the potential to significantly advance one of the most prolific aspects of HAR applications [68, 136, 138, 164, 169, 233, 293, 295, 318].”
BackgroundText Recognition in the Wild: A Survey
Chen, X., Jin, L., Zhu, Y., Luo, C., & Wang, T. (2022) · ACM Computing Surveys · doi:10.1145/3440756 · Cited by 205
Deep Activity Recognition Models with Triaxial Accelerometers
Alsheikh, M. A., Selim, A., Niyato, D. T., Doyle, L., Lin, S., & Tan, H.-P. (2015) · DR-NTU (Nanyang Technological University) · Cited by 204
Visual to Sound: Generating Natural Sound for Videos in the Wild
Zhou, Y., Wang, Z., Fang, C., Bui, T., & Berg, T. L. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00374 · Cited by 201 · cited 1×
“If we take a broader view, many works are using cross-modal deep generative models (such as GAN) in data synthesis, such as from video to audio [266], from text to image and vice versa [267, 268].”
BackgroundConvolutional Neural Networks for Human Activity Recognition Using Body-Worn Sensors
Moya Rueda, F., Grzeszick, R., Fink, G. A., Feldhorst, S., & Ten Hompel, M. (2018) · Informatics · doi:10.3390/informatics5020026 · Cited by 196 · cited 7×
“A majority of the CNNs consist of 5 to 9 layers [67, 91, 193, 232, 272, 300, 313], [130], [96], usually including 2 to 3 convolutional layers, 2 to 3 max pooling layers, followed by 1 to 2 fully connected layers before feeding the feature representation into the output layer (softmax layer in most cases).”
BackgroundMethodInfluentialUddin, M. Z., Hassan, M. M., Alsanad, A., & Savaglio, C. (2020) · Information Fusion · doi:10.1016/j.inffus.2019.08.004 · Cited by 194 · cited 1×
“Since then, the recurrent neural network (RNN) with time series as input has been widely applied to classify human activities or estimate hand gestures [52, 65, 132, 175, 268, 269, 275], [12].”
BackgroundZeng, M., Gao, H., Yu, T., Mengshoel, O. J., Langseth, H., Lane, I., & Liu, X. (2018) · Proceedings of the 2018 ACM International Symposium on Wearable Computers · doi:10.1145/3267242.3267286 · Cited by 185 · cited 10×
“Their method has outperformed regular CNN considerably on a number of public datasets such as PAMAP2 [228], WISDM [155], UNIMIB SHAR [188], and Opportunity [59].”
BackgroundMethodInfluentialSamuel, O. W., Asogbon, M. G., Geng, Y., Al-Timemy, A. H., Pirbhulal, S., Ji, N., Chen, S., Fang, P., & Li, G. (2019) · IEEE Access · doi:10.1109/access.2019.2891350 · Cited by 185 · cited 1×
“In addition, detecting muscular activities and hand motions using electromyography (EMG) sensors has been widely applied to enable improved prostheses control for people with missing or damaged limbs [186, 209, 211, 240].”
MethodEskofier, B. M., Lee, S. I., Daneault, J.-F., Golabchi, F. N., Ferreira-Carvalho, G., Vergara-Diaz, G., Sapienza, S., Costante, G., Klucken, J., Kautz, T., et al. (2016) · 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc.2016.7590787 · Cited by 180 · cited 1×
“Specifically, several works have introduced systems and methods for monitoring and assessing Parkinson disease (PD) symptoms [89, 119, 150, 189, 277, 322].”
BackgroundPD Disease State Assessment in Naturalistic Environments Using Deep Learning
Hammerla, N., Fisher, J., Andras, P., Rochester, L., Walker, R., & Ploetz, T. (2015) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v29i1.9484 · Cited by 179 · cited 2×
“In [118], DBNs are employed in Parkinson’s disease diagnosis to explore if they can cope with the unreliable labelling that results from naturalistic recording environments.”
BackgroundDeep Convolutional Neural Networks for Human Activity Recognition with Smartphone Sensors
Ronao, C. A., & Cho, S.-B. (2015) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-26561-2_6 · Cited by 176 · cited 1×
“A majority of the CNNs consist of 5 to 9 layers [67, 91, 193, 232, 272, 300, 313], [130], [96], usually including 2 to 3 convolutional layers, 2 to 3 max pooling layers, followed by 1 to 2 fully connected layers before feeding the feature representation into the output layer (softmax layer in most cases).”
BackgroundBreathPrint: Breathing Acoustics-based User Authentication
Chauhan, J., Hu, Y., Seneviratne, S., Misra, A., Seneviratne, A., & Lee, Y. (2017) · Proceedings of the 15th Annual International Conference on Mobile Systems, Applications, and Services · doi:10.1145/3081333.3081355 · Cited by 170 · cited 1×
“While most datasets are used to recognize physical activity or daily activities [19, 20, 30, 31, 47, 59, 61, 143, 155, 188, 228, 251, 252, 264, 279, 282, 299, 327, 335], there are also a few datasets dedicated to hand gestures [49, 156], breathing patterns [58], and car assembly line activities [316], as well as those…”
BackgroundMonitoring eating habits using a piezoelectric sensor-based necklace
Kalantarian, H., Alshurafa, N. I., Le, T., & Sarrafzadeh, M. (2015) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2015.01.005 · Cited by 169 · cited 1×
“1b, there are a large number of off-the-shelf smart devices or prototypes under development today, including smartphones, smartwatches, smart glasses, smart rings [208], smart gloves [266], smart armbands [151], smart necklaces [64, 142, 328], smart shoes [106], and Etattoos [249].”
BackgroundSelf-citationHuman Activity Recognition Using Federated Learning
Sozinov, K., Vlassov, V., & Girdzijauskas, S. (2018) · 2018 IEEE Intl Conf on Parallel & Distributed Processing with Applications, Ubiquitous Computing & Communications, Big Data & Cloud Computing, Social Computing & Networking, Sustainable Computing & Communications (ISPA/IUCC/BDCloud/SocialCom/SustainCom) · doi:10.1109/bdcloud.2018.00164 · Cited by 167 · cited 1×
“Federated learning is a trending approach to resolve privacy issue in learning problems [45, 167, 192, 259].”
BackgroundMadani, A., Moradi, M., Karargyris, A., & Syeda-Mahmood, T. (2018) · 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018) · doi:10.1109/isbi.2018.8363749 · Cited by 166 · cited 1×
“In the field of HAR, GAN has been applied as a semi-supervised learning approach to deal with unlabeled or partially labeled data for improving performance by learning representations from the unlabeled data which later will be utilized by the network to generalize to the unseen data distribution [178, 205, 260] [247]…”
MethodProtecting sensory data against sensitive inferences
Malekzadeh, M., Clegg, R. G., Cavallaro, A., & Haddadi, H. (2018) · Spiral (Imperial College London) · Cited by 166
HARKE: Human Activity Recognition from Kinetic Energy Harvesting Data in Wearable Devices
Khalifa, S., Lan, G., Hassan, M., Seneviratne, A., & Das, S. K. (2018) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2017.2761744 · Cited by 160 · cited 1×
“Other wearable sensors used in HAR include (but are not limited to) piezoelectric sensor [54, 146] for converting changes in pressure, acceleration, temperature, strain, or force to electrical charge, barometric pressure sensor [183] for atmospheric pressure, temperature measurement [32], electroencephalography (EEG)…”
MethodProtecting Sensory Data against Sensitive Inferences
Malekzadeh, M., Clegg, R. G., Cavallaro, A., & Haddadi, H. (2018) · Proceedings of the 1st Workshop on Privacy by Design in Distributed Systems · doi:10.1145/3195258.3195260 · Cited by 154 · cited 3×
“introduces a framework called Guardian-Estimator-Neutralizer (GEN) that attempts to recognize activities while preserving gender privacy [180].”
MethodSenseGen: A deep learning architecture for synthetic sensor data generation
Alzantot, M., Chakraborty, S., & Srivastava, M. (2017) · 2017 IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops) · doi:10.1109/percomw.2017.7917555 · Cited by 153 · cited 1×
“Deep learning methods are also used to augment the datasets to improve performance [261, 262, 263].”
MethodKwon, H., Tong, C., Haresamudram, H., Gao, Y., Abowd, G. D., Lane, N. D., & Plötz, T. (2020) · Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies · doi:10.1145/3411841 · Cited by 152
Towards multimodal deep learning for activity recognition on mobile devices
Radu, V., Lane, N. D., Bhattacharya, S., Mascolo, C., Marina, M. K., & Kawsar, F. (2016) · Proceedings of the 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing: Adjunct · doi:10.1145/2968219.2971461 · Cited by 147 · cited 2×
“In [222], a RBM is used to improve upon other methods of sensor fusion, as neural networks can identify non-intuitive predictive features largely from cross-sensor correlations and thus offer a more accurate estimation.”
MethodSensing Fine-Grained Hand Activity with Smartwatches
Laput, G., & Harrison, C. (2019) · Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3290605.3300568 · Cited by 147 · cited 1×
“For example, the projects presented in [161, 162] utilize sampling rates above the typical rate.”
BackgroundSoleimani, E., & Nazerfard, E. (2021) · Neurocomputing · doi:10.1016/j.neucom.2020.10.056 · Cited by 146 · cited 1×
“Moreover, [257] is an attempt that utilizes GAN to perform cross-subject transfer learning for HAR since collecting data for each new user is infeasible.”
BackgroundTang, Y., Teng, Q., Zhang, L., Min, F., & He, J. (2021) · IEEE Sensors Journal · doi:10.1109/jsen.2020.3015521 · Cited by 143 · cited 5×
“Researchers have proposed various algorithms to extract features from sensor signals and to perform activity classification using machine-learned models like K Nearest Neighbor (KNN) and SVM [123, 149, 168, 193, 254, 265, 270, 290, 313, 319].”
MethodInfluentialST-DeepHAR: Deep Learning Model for Human Activity Recognition in IoHT Applications
Abdel-Basset, M., Hawash, H., Chakrabortty, R. K., Ryan, M., Elhoseny, M., & Song, H. (2021) · IEEE Internet of Things Journal · doi:10.1109/jiot.2020.3033430 · Cited by 136
Peng (2018) · doi:10.1145/3214277 · Cited by 134 · cited 1×
“[210] proposes AROMA, a complex human activity recognition method that leverages”
MethodStacked Lstm Network for Human Activity Recognition Using Smartphone Data
Ullah, M., Ullah, H., Khan, S. D., & Cheikh, F. A. (2019) · 2019 8th European Workshop on Visual Information Processing (EUVIP) · doi:10.1109/euvip47703.2019.8946180 · Cited by 134
Meta-HAR: Federated Representation Learning for Human Activity Recognition
Li, C., Niu, D., Jiang, B., Zuo, X., & Yang, J. (2021) · Proceedings of the Web Conference 2021 · doi:10.1145/3442381.3450006 · Cited by 133 · cited 1×
“Federated learning is a trending approach to resolve privacy issue in learning problems [45, 167, 192, 259].”
BackgroundAn effective deep autoencoder approach for online smartphone-based human activity recognition
Almaslukh, B., Artoli, A. M., & Al-Muhtadi, J. F. (2017) · Cited by 132
Analog Circuit Incipient Fault Diagnosis Method Using DBN Based Features Extraction
Zhang, C., He, Y., Yuan, L., & Xiang, S. (2018) · IEEE Access · doi:10.1109/access.2018.2823765 · Cited by 130 · cited 1×
“There are many attractive implementations and uses of DBNs in real-life applications such as drug discovery [111], natural language understanding [165], fault diagnosis [323], etc.”
BackgroundShallow Convolutional Neural Networks for Human Activity Recognition Using Wearable Sensors
Huang, W., Zhang, L., Gao, W., Min, F., & He, J. (2021) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2021.3091990 · Cited by 129 · cited 2×
“[130] first propose a shallow CNN that considers cross-channel communication.”
BackgroundSigcha, L., Costa, N., Pavón, I., Costa, S., Arezes, P., López, J. M., & De Arcas, G. (2020) · Sensors · doi:10.3390/s20071895 · Cited by 126
Zhang (2020) · doi:10.1145/3432192 · Cited by 126
Deep Activity Recognition Models with Triaxial Accelerometers
Alsheikh, M. A., Selim, A., Niyato, D., Doyle, L., Lin, S., & Tan, H.-P. (2015) · arXiv · doi:10.48550/arxiv.1511.04664 · Cited by 126
Kim, H. B., Lee, W. W., Kim, A., Lee, H. J., Park, H. Y., Jeon, H. S., Kim, S. K., Jeon, B., & Park, K. S. (2018) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2018.02.007 · Cited by 124 · cited 1×
“Specifically, several works have introduced systems and methods for monitoring and assessing Parkinson disease (PD) symptoms [89, 119, 150, 189, 277, 322].”
BackgroundThe hRing: A wearable haptic device to avoid occlusions in hand tracking
Pacchierotti, C., Salvietti, G., Hussain, I., Meli, L., & Prattichizzo, D. (2016) · 2016 IEEE Haptics Symposium (HAPTICS) · doi:10.1109/haptics.2016.7463167 · Cited by 123 · cited 1×
“1b, there are a large number of off-the-shelf smart devices or prototypes under development today, including smartphones, smartwatches, smart glasses, smart rings [208], smart gloves [266], smart armbands [151], smart necklaces [64, 142, 328], smart shoes [106], and Etattoos [249].”
BackgroundPhysical activity recognition by smartphones, a survey
Morales, J., & Akopian, D. (2017) · Journal of Applied Biomedicine · doi:10.1016/j.bbe.2017.04.004 · Cited by 122 · cited 1×
“Physical activity involves activities such as sitting, walking, laying down, going up or down stairs, jogging, and running [191].”
BackgroundDynamic Gesture Recognition Based on LSTM-CNN
Wu, Y., Zheng, B., & Zhao, Y. (2018) · Chinese Automation Congress · doi:10.1109/cac.2018.8623035 · Cited by 120 · cited 1×
“Similarly, other researchers [8, 82, 94, 95, 197, 245, 301, 302], [238] have also developed the CNN-LSTM model in varios application scenarios by taking advantage of the feature extraction ability of CNN and the time-series data reasoning ability of LSTM.”
BackgroundCompressive Representation for Device-Free Activity Recognition with Passive RFID Signal Strength
Yao, L., Sheng, Q. Z., Li, X., Gu, T., Tan, M., Wang, X., Wang, S., & Ruan, W. (2018) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2017.2706282 · Cited by 117 · cited 1×
“[332] proposed to combine reinforcement learning and LSTM model to improve the adaptability of different kinds of sensors including EEG (EID dataset), RFID (RSSI dataset)[314], and wearable IMU (PAMAP2 dataset)[228].”
BackgroundObjective assessment of depressive symptoms with machine learning and wearable sensors data
Ghandeharioun, A., Fedor, S., Sangermano, L., Ionescu, D., Alpert, J., Dale, C., Sontag, D., & Picard, R. (2017) · 2017 Seventh International Conference on Affective Computing and Intelligent Interaction (ACII) · doi:10.1109/acii.2017.8273620 · Cited by 116 · cited 1×
“Some recent works use wearables to detect cough activity, a major symptom of pulmonary diseases [199, 311, 329, 330] Other works have introduced methods for monitoring stroke in infants using wearable accelerometers [100] and methods for assessing depressive symptoms utilizing wrist-worn sensors [104].”
BackgroundHuman Activity Recognition and Embedded Application Based on Convolutional Neural Network
Yang, X., & Qiu, T. T. (2020) · Journal of Artificial Intelligence and Technology · doi:10.37965/jait.2020.0051 · Cited by 116 · cited 1×
“[319] C-P-FC-FC-S 1×20 daily activities, locomotion activities Skoda, Opportunity, Actitracker [312] C-P-C-P-FC-S 5×5 locomotion activities 6 S1 WISDM [274] C-P-C-P-C-FC 1× 5, 1× 9 locomotion activities 12 S5 mHealth”
An sEMG-Based Human–Robot Interface for Robotic Hands Using Machine Learning and Synergies
Meattini, R., Benatti, S., Scarcia, U., De Gregorio, D., Benini, L., & Melchiorri, C. (2018) · IEEE Transactions on Components, Packaging and Manufacturing Technology · doi:10.1109/tcpmt.2018.2799987 · Cited by 115
A CNN-SVM combined model for pattern recognition of knee motion using mechanomyography signals
Wu, H., Huang, Q., Wang, D., & Gao, L. (2018) · Journal of Electromyography and Kinesiology · doi:10.1016/j.jelekin.2018.07.005 · Cited by 115 · cited 4×
“But as an exception, some studies explored the use of traditional classifiers as the output layer in a CNN [265, 300].”
BackgroundMethodInfluentialBinarized-BLSTM-RNN based Human Activity Recognition
Edel, M., & Koppe, E. (2016) · 2016 International Conference on Indoor Positioning and Indoor Navigation (IPIN) · doi:10.1109/ipin.2016.7743581 · Cited by 114 · cited 1×
“Edel and Köppe [87] reduces computation by utilizing binary weights rather than fixed-point or floating weights.”
MethodKawaguchi, N., Ogawa, N., Iwasaki, Y., Kaji, K., Terada, T., Murao, K., Inoue, S., Kawahara, Y., Sumi, Y., & Nishio, N. (2011) · Proceedings of the 2nd Augmented Human International Conference · doi:10.1145/1959826.1959853 · Cited by 113 · cited 3×
“12 100 Hz 20 ExtraSensory [279] Locomotion & activities 9D IMU & GPS 10 25–40 Hz 13 HASC [143] Locomotion Smartphone 9D IMU 6 100 Hz 11 Actitracker [299] Locomotion 9D IMU & GPS 5 N/A 6 FIC [156] Feeding gestures 3D Acc.”
BackgroundUddin, M. Z., & Hassan, M. M. (2019) · IEEE Sensors Journal · doi:10.1109/jsen.2018.2871203 · Cited by 110 · cited 6×
“Their method has outperformed regular CNN considerably on a number of public datasets such as PAMAP2 [228], WISDM [155], UNIMIB SHAR [188], and Opportunity [59].”
InfluentialZebin, T., Sperrin, M., Peek, N., & Casson, A. J. (2018) · 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc.2018.8513115 · Cited by 107 · cited 1×
“For example, [129] proposes a harmonic loss function and [317] combines LSTM with batch normalization to achieve 92% accuracy with raw accelerometer and gyroscope data.”
MethodAbedin, A., Ehsanpour, M., Shi, Q., Rezatofighi, H., & Ranasinghe, D. C. (2021) · Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies · doi:10.1145/3448083 · Cited by 107 · cited 1×
“Nowadays, multi-sensor based HAR and sensor fusion has become a trend to improve the robustness and generalization of recognition systems [4, 122, 131, 212, 244, 331].”
BackgroundA Blockchain Platform for User Data Sharing Ensuring User Control and Incentives
Shrestha, A. K., Vassileva, J., & Deters, R. (2020) · Frontiers in Blockchain · doi:10.3389/fbloc.2020.497985 · Cited by 105 · cited 1×
“It has been explored to facilitate the privacy-preserving data collection and sharing [35, 36, 253].”
BackgroundDeep Neural Networks for Sensor-Based Human Activity Recognition Using Selective Kernel Convolution
Gao, W., Zhang, L., Huang, W., Min, F., He, J., & Song, A. (2021) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2021.3102735 · Cited by 105 · cited 1×
“A majority of the CNNs consist of 5 to 9 layers [67, 91, 193, 232, 272, 300, 313], [130], [96], usually including 2 to 3 convolutional layers, 2 to 3 max pooling layers, followed by 1 to 2 fully connected layers before feeding the feature representation into the output layer (softmax layer in most cases).”
BackgroundA Review of Privacy-Preserving Federated Learning for the Internet-of-Things
Briggs, C., Fan, Z., & Andras, P. (2021) · Studies in Computational Intelligence · doi:10.1007/978-3-030-70604-3_2 · Cited by 101 · cited 1×
“Federated learning is a trending approach to resolve privacy issue in learning problems [45, 167, 192, 259].”
BackgroundDeep Learning for Human Activity Recognition in Mobile Computing
Plotz, T., & Guan, Y. (2018) · Computer · doi:10.1109/mc.2018.2381112 · Cited by 99 · cited 1×
“As discussed in [213], many methods segment time series using traditional static sliding window methods.”
MethodZygarde: Time-Sensitive On-Device Deep Inference and Adaptation on Intermittently-Powered Systems
Islam, B., & Nirjon, S. (2020) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3411808 · Cited by 97 · cited 2×
“Islam and Nirjon [133] presents an architecture for embedded systems or other batteryless methods that dynamically schedules DNN inference tasks (i.”
BackgroundDomain Adaptation for sEMG-based Gesture Recognition with Recurrent Neural Networks
Ketyko, I., Kovacs, F., & Varga, K. Z. (2019) · 2019 International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2019.8852018 · Cited by 94 · cited 7×
“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.”
MethodInfluentialUnsupervised Feature Learning for Human Activity Recognition Using Smartphone Sensors
Li, Y., Shi, D., Ding, B., & Liu, D. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-13817-6_11 · Cited by 93 · cited 3×
“presents an autoencoder architecture where a sparse autoencoder and a denoising autoencoder are used to explore useful feature representations from accelerometer and gyroscope sensor data, and then they perform classification using support vector machines [171].”
MethodSelf-citationDeep Neural Network based Human Activity Recognition for the Order Picking Process
Grzeszick, R., Lenk, J. M., Rueda, F. M., Fink, G. A., Feldhorst, S., & ten Hompel, M. (2017) · Proceedings of the 4th International Workshop on Sensor-based Activity Recognition and Interaction · doi:10.1145/3134230.3134231 · Cited by 93 · cited 1×
“[110] proposed a multi-branch CNN architecture.”
Wang, J., Chen, Y., Gu, Y., Xiao, Y., & Pan, H. (2018) · 2018 International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2018.8489106 · Cited by 92 · cited 1×
“[292] utilizes GANs with a customized network to generate synthetic data from the public HAR dataset HASC2010corpus [144].”
MethodA Human Activity Recognition Algorithm Based on Stacking Denoising Autoencoder and LightGBM
Gao, X., Luo, H., Wang, Q., Zhao, F., Ye, L., & Zhang, Y. (2019) · Sensors · doi:10.3390/s19040947 · Cited by 92 · cited 3×
“Furthermore, autoencoders are commonly used to sanitize and denoise raw sensor data [98, 190, 280], a known problem with wearable signals that impacts our ability to learn patterns in the data.”
BackgroundMethodNeckSense: A Multi-Sensor Necklace for Detecting Eating Activities in Free-Living Conditions
Zhang, S., Zhao, Y., Nguyen, D. T., Xu, R., Sen, S., Hester, J., & Alshurafa, N. (2020) · Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies · doi:10.1145/3397313 · Cited by 92 · cited 1×
“1b, there are a large number of off-the-shelf smart devices or prototypes under development today, including smartphones, smartwatches, smart glasses, smart rings [208], smart gloves [266], smart armbands [151], smart necklaces [64, 142, 328], smart shoes [106], and Etattoos [249].”
BackgroundSelf-citationEEG-based Motion Intention Recognition via Multi-task RNNs
Chen, W., Wang, S., Zhang, X., Yao, L., Yue, L., Qian, B., & Li, X. (2018) · Society for Industrial and Applied Mathematics eBooks · doi:10.1137/1.9781611975321.32 · Cited by 90
Classification of Electromyographic Hand Gesture Signals using Machine Learning Techniques
Jia, G., Lam, H.-K., Liao, J., & Wang, R. (2020) · Neurocomputing · doi:10.1016/j.neucom.2020.03.009 · Cited by 89 · cited 2×
“As such, autoencoders are most commonly used for feature extraction and dimensionality reduction [18, 27, 53, 73, 74, 80, 103, 137, 171, 172, 194, 234, 283, 287, 296, 298].”
BackgroundMethodSun, J., Fu, Y., Li, S., He, J., Xu, C., & Tan, L. (2018) · Journal of Sensors · doi:10.1155/2018/8580959 · Cited by 88 · cited 2×
“But as an exception, some studies explored the use of traditional classifiers as the output layer in a CNN [265, 300].”
BackgroundMethodRecognition of Human Activities Using Continuous Autoencoders with Wearable Sensors
Wang, L. (2016) · Sensors · doi:10.3390/s16020189 · Cited by 87 · cited 1×
“As such, autoencoders are most commonly used for feature extraction and dimensionality reduction [120, 122, 123, 124, 125, 126, 133, 134, 135, 136, 137, 138, 139, 140, 141].”
MethodThe UEA multivariate time series classification archive, 2018
Bagnall, A., Dau, H. A., Lines, J., Flynn, M., Large, J., Bostrom, A., Southam, P., & Keogh, E. (2018) · arXiv · doi:10.48550/arxiv.1811.00075 · Cited by 87 · cited 2×
“Recently, researchers from the University of East Anglia have collaborated with UCR to generate a new collection of datasets, which includes 9 categories of HAR: BasicMotions, Cricket, Epilepsy, ERing, Handwriting, Libras, NATOPS, RacketSports, and UWaveGestureLibrary [24].”
BackgroundDeep Learning for Heterogeneous Human Activity Recognition in Complex IoT Applications
Abdel‐Basset, M., Hawash, H., Chang, V. I. C., Chakrabortty, R. K., & Ryan, M. J. (2020) · IEEE Internet of Things Journal · doi:10.1109/jiot.2020.3038416 · Cited by 87 · cited 1×
“During recent years, many efforts have been put into improving the generalizability of models in HAR [3, 219, 262].”
BackgroundFedDL: Federated Learning via Dynamic Layer Sharing for Human Activity Recognition
Tu, L., Ouyang, X., Zhou, J., He, Y., & Xing, G. (2021) · Proceedings of the 19th ACM Conference on Embedded Networked Sensor Systems · doi:10.1145/3485730.3485946 · Cited by 87 · cited 1×
“[273] designed a dynamic layer sharing scheme which assisted the merging of local models to speed up the model convergence and achieved dynamic aggregation of models.”
MethodHuman Activity Recognition on Smartphones Using a Bidirectional LSTM Network
Hernandez, F., Suarez, L. F., Villamizar, J., & Altuve, M. (2019) · 2019 XXII Symposium on Image, Signal Processing and Artificial Vision (STSIVA) · doi:10.1109/stsiva.2019.8730249 · Cited by 86
Abnormal Gait Recognition Algorithm Based on LSTM-CNN Fusion Network
Gao, J., Gu, P., Ren, Q., Zhang, J., & Song, X. (2019) · IEEE Access · doi:10.1109/access.2019.2950254 · Cited by 86 · cited 1×
“Similarly, other researchers [8, 82, 94, 95, 197, 245, 301, 302], [238] have also developed the CNN-LSTM model in varios application scenarios by taking advantage of the feature extraction ability of CNN and the time-series data reasoning ability of LSTM.”
BackgroundSemi-supervised convolutional neural networks for human activity recognition
Zeng, M., Yu, T., Wang, X., Nguyen, L. T., Mengshoel, O. J., & Lane, I. (2017) · 2017 IEEE International Conference on Big Data (Big Data) · doi:10.1109/bigdata.2017.8257967 · Cited by 85 · cited 1×
“[320] presented two semi-supervised CNN methods that utilizes unlabeled data during training: the convolutional encoder-decoder and the convolutional ladder”
MethodLatent Independent Excitation for Generalizable Sensor-based Cross-Person Activity Recognition
Qian, H., Pan, S. J., & Miao, C. (2021) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v35i13.17416 · Cited by 85 · cited 1×
“[217] introduce Generalizable Independent Latent Excitation (GILE), which greatly enhances the cross-person generalization capability of the model.”
BackgroundInterpretable and Accurate Convolutional Neural Networks for Human Activity Recognition
Kim, E. (2020) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2020.2972628 · Cited by 84 · cited 5×
“Researchers have proposed various algorithms to extract features from sensor signals and to perform activity classification using machine-learned models like K Nearest Neighbor (KNN) and SVM [123, 149, 168, 193, 254, 265, 270, 290, 313, 319].”
MethodInfluentialMulticolumn bidirectional long short-term memory for mobile devices-based human activity recognition
Tao, D., Wen, Y., & Hong, R. (2016) · IEEE Internet of Things Journal · doi:10.1109/jiot.2016.2561962 · Cited by 83 · cited 1×
“Bidirectional LSTMs, having both past and future recurrent connections, were used in [166, 271] to classify activities.”
MethodFingerPing: Recognizing Fine-grained Hand Poses using Active Acoustic On-body Sensing
Zhang, C., Xue, Q., Waghmare, A., Meng, R., Jain, S., Han, Y., Li, X., Cunefare, K., Ploetz, T., Starner, T., et al. (2018) · Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3173574.3174011 · Cited by 82 · cited 1×
“For example, a wrist-worn wearable outfitted with an inertial measurement unit (IMU) can easily detect the wrist shaking [250, 324, 336] to control smart devices to skip a song by shaking the hand, instead of bringing up the screen, locating, and pushing a button.”
BackgroundOnline human activity recognition using low-power wearable devices
Bhat, G., Deb, R., Chaurasia, V. V., Shill, H., & Ogras, U. Y. (2018) · Proceedings of the International Conference on Computer-Aided Design · doi:10.1145/3240765.3240833 · Cited by 82 · cited 1×
“Additionally, in the realm of DL-based HAR, the reward of the agent has to be given by a human, as in the case of [40, 246].”
BackgroundAn ensemble of autonomous auto-encoders for human activity recognition
Garcia, K. D., de Sá, C. R., Poel, M., Carvalho, T., Mendes‐Moreira, J., Cardoso, J. M. P., de Carvalho, A. C. P. L. F., & Kok, J. N. (2021) · Neurocomputing · doi:10.1016/j.neucom.2020.01.125 · Cited by 82 · cited 1×
“[102] proposed an effective multi-class algorithm which consists of an ensemble of autoencoders where each autoencoder is associated with a separate class.”
BackgroundCheng, X., Zhang, L., Tang, Y., Liu, Y., Wu, H., & He, J. (2022) · IEEE Sensors Journal · doi:10.1109/jsen.2022.3149337 · Cited by 82
Human activity recognition based on smartphone and wearable sensors using multiscale DCNN ensemble
Sena, J., Barreto, J., Caetano, C., Cramer, G., & Schwartz, W. R. (2021) · Neurocomputing · doi:10.1016/j.neucom.2020.04.151 · Cited by 81 · cited 1×
“One common way to improve robustness is to leverage the benefits of multiple types of sensors together to create multi-sensory systems [296, 310, 311, 312, 313, 314].”
BackgroundReal time gesture recognition using continuous time recurrent neural networks
Bailador, G., Roggen, D., Tröster, G., & Triviño, G. (2007) · International Conference on Body Area Networks · doi:10.4108/bodynets.2007.149 · Cited by 80 · cited 2×
“In addition, many researchers have undertaken extensive work to improve the performance of RNN models in the context of human activity recognition and have proposed various models based on RNNs, including Independently RNN (IndRNN) [339], Continuous Time RNN (CTRNN) [26], Personalized RNN (PerRNN) [297], Colliding Bod…”
BackgroundRamponi, G., Protopapas, P., Brambilla, M., & Janssen, R. R. P. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1811.08295 · Cited by 79 · cited 1×
“Many DL-based methods also augment their datasets to improve performance [134, 226, 261, 277].”
BackgroundAlessandrini, M., Biagetti, G., Crippa, P., Falaschetti, L., & Turchetti, C. (2021) · Electronics · doi:10.3390/electronics10141715 · Cited by 79 · cited 1×
“Since then, the recurrent neural network (RNN) with time series as input has been widely applied to classify human activities or estimate hand gestures [180, 181, 182, 183, 184, 185, 186, 187].”
BackgroundMassé, F., Gonzenbach, R. R., Arami, A., Paraschiv-Ionescu, A., Luft, A. R., & Aminian, K. (2015) · Journal of NeuroEngineering and Rehabilitation · doi:10.1186/s12984-015-0060-2 · Cited by 77 · cited 1×
“Other wearable sensors used in HAR include (but are not limited to) piezoelectric sensor [54, 146] for converting changes in pressure, acceleration, temperature, strain, or force to electrical charge, barometric pressure sensor [183] for atmospheric pressure, temperature measurement [32], electroencephalography (EEG)…”
MethodReplacement AutoEncoder: A Privacy-Preserving Algorithm for Sensory Data Analysis
Malekzadeh, M., Clegg, R. G., & Haddadi, H. (2018) · 2018 IEEE/ACM Third International Conference on Internet-of-Things Design and Implementation (IoTDI) · doi:10.1109/iotdi.2018.00025 · Cited by 76 · cited 3×
“developed a novel replacement autoencoder that removes prominent features of sensitive activities, such as drinking, smoking, or using the restroom [181].”
BackgroundMethodMohammadian Rad, N., Van Laarhoven, T., Furlanello, C., & Marchiori, E. (2018) · Sensors · doi:10.3390/s18103533 · Cited by 76
Data augmentation using synthetic data for time series classification with deep residual networks
Fawaz, H. I., Forestier, G., Weber, J., Idoumghar, L., & Müller, P.-A. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1808.02455 · Cited by 72
Modeling Wrist Micromovements to Measure In-Meal Eating Behavior From Inertial Sensor Data
Kyritsis, K., Diou, C., & Delopoulos, A. N. (2019) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2019.2892011 · Cited by 72 · cited 1×
“[157] break down complex gestures into a series of simpler (atomic) gestures that, when combined, form the complex gesture.”
BackgroundDeep Fisher discriminant learning for mobile hand gesture recognition
Li, C., Xie, C., Zhang, B., Chen, C., & Han, J. (2018) · Pattern Recognition · doi:10.1016/j.patcog.2017.12.023 · Cited by 72 · cited 1×
“Bidirectional LSTMs, having both past and future recurrent connections, were used in [166, 271] to classify activities.”
MethodDeep, S., & Zheng, X. (2019) · International Conference on Parallel and Distributed Computing, Applications and Technologies (PDCAT) · doi:10.1109/pdcat46702.2019.00055 · Cited by 72 · cited 1×
“Similarly, other researchers [8, 82, 94, 95, 197, 245, 301, 302], [238] have also developed the CNN-LSTM model in varios application scenarios by taking advantage of the feature extraction ability of CNN and the time-series data reasoning ability of LSTM.”
BackgroundJia, G., Lam, H., Ma, S., Yang, Z., Xu, Y., & Xiao, B. J. (2020) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2020.2986884 · Cited by 72
Huynh-The, T., Hua, C.-H., Tu, N. A., & Kim, D.-S. (2021) · IEEE Internet of Things Journal · doi:10.1109/jiot.2020.3013272 · Cited by 72 · cited 2×
“Nowadays, multi-sensor based HAR and sensor fusion has become a trend to improve the robustness and generalization of recognition systems [4, 122, 131, 212, 244, 331].”
BackgroundLi, X., Luo, J., & Younes, R. (2020) · Adjunct Proceedings of the 2020 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2020 ACM International Symposium on Wearable Computers · doi:10.1145/3410530.3414367 · Cited by 71 · cited 1×
“[56, 170] generate verisimilar data of different activities and [248] uses the Boulic kinematic model which aims to capture the three dimensional positioning trend to synthesize personified walking data.”
MethodBarut, O., Zhou, L., & Luo, Y. (2020) · IEEE Internet of Things Journal · doi:10.1109/jiot.2020.2996578 · Cited by 70 · cited 1×
“Moreover, Multitask LSTM is developed in [33] to first extract features with shared weight, and then classify activities and estimate intensity in separate branches.”
MethodUsing Deep Learning for Energy Expenditure Estimation with wearable sensors
Zhu, J., Pande, A., Mohapatra, P., & Han, J. J. (2015) · 2015 17th International Conference on E-health Networking, Application & Services (HealthCom) · doi:10.1109/healthcom.2015.7454554 · Cited by 69 · cited 1×
“For example, dedicated products such as Fitbit [84] can estimate and record energy expenditure on smart devices, which can further serve as an important step in tracking personal activity and preventing chronic diseases [341].”
BackgroundAkbari, A., & Jafari, R. (2019) · Proceedings of the 18th International Conference on Information Processing in Sensor Networks · doi:10.1145/3302506.3310391 · Cited by 69 · cited 1×
“Additionally, autoencoders have been explored for feature extraction in domain transfer learning [10], detecting unseen data [147], and recognizing null classes [9].”
BackgroundShi, Y., Manco, M., Moyal, D., Huppert, G., Araki, H., Banks, A., Joshi, H., McKenzie, R., Seewald, A., Griffin, G., et al. (2018) · PLOS ONE · doi:10.1371/journal.pone.0190233 · Cited by 68 · cited 1×
“1b, there are a large number of off-the-shelf smart devices or prototypes under development today, including smartphones, smartwatches, smart glasses, smart rings [208], smart gloves [266], smart armbands [151], smart necklaces [64, 142, 328], smart shoes [106], and Etattoos [249].”
BackgroundVoice In Ear: Spoofing-Resistant and Passphrase-Independent Body Sound Authentication
Gao, Y., Jin, Y., Chauhan, J., Choi, S., Li, J., & Jin, Z. (2021) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3448113 · Cited by 68
Jointly Learning Energy Expenditures and Activities Using Egocentric Multimodal Signals
Nakamura, K., Yeung, S., Alahi, A., & Fei-Fei, L. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.721 · Cited by 67 · cited 1×
“If high-fidelity synthetic wearable sensor data can be generated from the available real-world video datasets (such as Stanford-ECM dataset [294]) or online video corpus, it may help alleviate the in-the-field data scarcity issue.”
BackgroundTriwiyanto, T., Pawana, I. P. A., & Purnomo, M. H. (2020) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2020.2999505 · Cited by 67 · cited 4×
“The choice of 1D-CNN kernel size normally falls in the range of 1×3 to 1×5 (with exceptions in [272, 300, 319] where kernels of size 1×8, 2×101, and 1×20 are adopted).”
BackgroundInfluentialLv, M., Xu, W., & Chen, T. (2019) · Neurocomputing · doi:10.1016/j.neucom.2019.06.051 · Cited by 64 · cited 10×
“Their method has outperformed regular CNN considerably on a number of public datasets such as PAMAP2 [228], WISDM [155], UNIMIB SHAR [188], and Opportunity [59].”
MethodInfluentialiHear Food: Eating Detection Using Commodity Bluetooth Headsets
Gao, Y., Zhang, N., Wang, H., Ding, X., Ye, X., Chen, G., & Cao, Y. (2016) · 2016 IEEE First International Conference on Connected Health: Applications, Systems and Engineering Technologies (CHASE) · doi:10.1109/chase.2016.14 · Cited by 63 · cited 2×
“In [99], a unsupervised 5-layer DBM-DNN is applied for the automatic detection of eating episodes via commercial bluetooth headsets collecting raw”
BackgroundMethodLasagna: towards deep hierarchical understanding and searching over mobile sensing data
Liu, C., Zhang, L., Liu, Z., Liu, K., Li, X., & Liu, Y. (2016) · Proceedings of the 22nd Annual International Conference on Mobile Computing and Networking · doi:10.1145/2973750.2973752 · Cited by 63 · cited 1×
“[173] proposes a hierarchical architecture that constructs high-level human activities from low-level activities.”
Background
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
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.