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
Items 201–336 of 336
Actitracker: A Smartphone-Based Activity Recognition System for Improving Health and Well-Being
Weiss, G. M., Lockhart, J. W., Pulickal, T. T., McHugh, P. T., Ronan, I. H., & Timko, J. L. (2016) · 2016 IEEE International Conference on Data Science and Advanced Analytics (DSAA) · doi:10.1109/dsaa.2016.89 · Cited by 62 · cited 2×
“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.”
BackgroundFlexible Piezoelectric Sensor-Based Gait Recognition
Cha, Y., Kim, H., & Kim, D. (2018) · Sensors · doi:10.3390/s18020468 · Cited by 61 · cited 1×
“Other wearable sensors used in HAR include (but are not limited to) piezoelectric sensor [66,67] for converting changes in pressure, acceleration, temperature, strain, or force to electrical charge, barometric pressure sensor [68] for atmospheric pressure, temperature measurement [69], electroencephalography (EEG) for…”
MethodNovel approaches to human activity recognition based on accelerometer data
Jordão, A., Tôrres, L. A. B., & Schwartz, W. R. (2018) · Signal Image and Video Processing · doi:10.1007/s11760-018-1293-x · Cited by 61 · cited 1×
“[140] C-P-C-P-C-P-S 12×2 daily activities including brush teeth, comb hair, get up from bed, etc 12 S1, S2, S3 WHARF”
BackgroundHuman Motion Recognition by Textile Sensors Based on Machine Learning Algorithms
Vu, C. C., & Kim, J. (2018) · Sensors · doi:10.3390/s18093109 · Cited by 60
Recognizing Human Activities from Raw Accelerometer Data Using Deep Neural Networks
Zhang, L., Wu, X., & Luo, D. (2015) · 2015 IEEE 14th International Conference on Machine Learning and Applications (ICMLA) · doi:10.1109/icmla.2015.48 · Cited by 59 · cited 2×
“In later works, DBN is applied to publicly available datasets [6, 222, 326] [179].”
MethodDynamic hand gesture recognition for wearable devices with low complexity recurrent neural networks
Shin, S., & Sung, W. (2016) · 2016 IEEE International Symposium on Circuits and Systems (ISCAS) · doi:10.1109/iscas.2016.7539037 · Cited by 59 · 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.”
BackgroundMulti-Layered Deep Learning Features Fusion for Human Action Recognition
Kiran, S., Khan, M. A., Javed, M. Y., Alhaisoni, M. M., Tariq, U., Nam, Y., Damaševičius, R., & Sharif, M. I. (2021) · Computers, materials & continua/Computers, materials & continua (Print) · doi:10.32604/cmc.2021.017800 · Cited by 58 · cited 1×
“First of all, we omitted image or video-based HAR works, such as [152], since there is a huge body of work in the computer vision community and the method is significantly different from sensor-based HAR.”
MethodEMG-Based Motion Discrimination Using a Novel Recurrent Neural Network
Bu, N., Fukuda, O., & Tsuji, T. (2003) · Journal of Intelligent Information Systems · doi:10.1023/a:1024706431807 · Cited by 56 · 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.”
MethodInfluentialCheron, G. A., Leurs, F., Bengoetxea, A., Draye, J.-P., Destrée, M., & Dan, B. (2003) · Journal of Neuroscience Methods · doi:10.1016/s0165-0270(03)00167-5 · Cited by 56 · 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.”
MethodInfluentialI Can't Be Myself: Effects of Wearable Cameras on the Capture of Authentic Behavior in the Wild
Alharbi, R., Stump, T. K., Vafaie, N., Pfammatter, A. F., Spring, B. J., & Alshurafa, N. I. (2018) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3264900 · Cited by 56 · 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.”
BackgroundSelf-citationA Novel Distribution-Embedded Neural Network for Sensor-Based Activity Recognition
Qian, H., Pan, S. J., Da, B., & Miao, C. (2019) · Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2019/779 · Cited by 56 · cited 1×
“[215] developed the model with SMMAR in statistical”
MethodChen, Z., Fiandrino, C., & Kantarcı, B. (2021) · Journal of Systems Architecture · doi:10.1016/j.sysarc.2021.102011 · Cited by 55 · cited 1×
“[69] reviewed mobile crowdsourcing solutions with blockchain technology to resolve the data quality, privacy, and security issues.”
BackgroundContinuous angular position estimation of human ankle during unconstrained locomotion
Gupta, R., Dhindsa, I. S., & Agarwal, R. (2020) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2020.101968 · Cited by 54 · 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.”
MethodInfluentialTowards a New Ubiquitous Learning Environment Based on Blockchain Technology
Bdiwi, R., de Runz, C., Faïz, S., & Ali-Chérif, A. (2017) · IEEE International Conference on Advanced Learning Technologies (ICALT) · doi:10.1109/icalt.2017.37 · Cited by 51 · cited 1×
“It has been explored to facilitate the privacy-preserving data collection and sharing [35, 36, 253].”
BackgroundSiirtola, P., & Röning, J. (2019) · Sensors · doi:10.3390/s19235151 · Cited by 51
A public domain dataset for ADL recognition using wrist-placed accelerometers
Bruno, B., Mastrogiovanni, F., & Sgorbissa, A. (2014) · The 23rd IEEE International Symposium on Robot and Human Interactive Communication · doi:10.1109/roman.2014.6926341 · Cited by 50 · 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…”
BackgroundAlharbi, R., Tolba, M., Petito, L. C., Hester, J. D., & Alshurafa, N. I. (2019) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3351230 · Cited by 50 · 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.”
BackgroundSelf-citationMobiRNN: Efficient Recurrent Neural Network Execution on Mobile GPU
Cao, Q., Balasubramanian, N., & Balasubramanian, A. (2017) · Proceedings of the 1st International Workshop on Deep Learning for Mobile Systems and Applications · doi:10.1145/3089801.3089804 · Cited by 49 · cited 1×
“[50] proposes a smartphone-based architecture that offloads DNN computations onto the mobile GPU to improve inference time.”
BackgroundDistributionally Robust Semi-Supervised Learning for People-Centric Sensing
Chen, K., Yao, L., Zhang, D., Chang, X., Long, G., & Wang, S. (2019) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v33i01.33013321 · Cited by 49 · cited 1×
“proposed an encoder-decoder based method that reduces distribution discrepancies between labeled and unlabeled data, that arise due to differences in biology and behavior from different people, while preserving the inherent similarities of different people performing the same task [62].”
MethodGao, Y., Long, Y., Guan, Y., Basu, A., Baggaley, J., & Ploetz, T. (2019) · Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies · doi:10.1145/3314399 · Cited by 49 · 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].”
BackgroundBrown, V., Moodie, M., Herrera, A. M. M., Veerman, L. J., & Carter, R. (2016) · Preventive Medicine · doi:10.1016/j.ypmed.2016.12.020 · Cited by 48 · cited 1×
“Moreover, there has been evidence of the association between modes of transport (motor vehicle, walking, cycling, and public transport) and obesity-related outcomes [46].”
BackgroundImproving Pedestrian Safety in Cities Using Intelligent Wearable Systems
Xia, S., de Godoy, D., Islam, B., Islam, M. T., Nirjon, S., Kinget, P. R., & Jiang, X. (2019) · IEEE Internet of Things Journal · doi:10.1109/jiot.2019.2903519 · Cited by 48
Self-citationAn Ultra-Low Energy Human Activity Recognition Accelerator for Wearable Health Applications
Bhat, G., Tuncel, Y., An, S., Lee, H. G., & Ogras, U. Y. (2019) · ACM Transactions on Embedded Computing Systems · doi:10.1145/3358175 · Cited by 48
A Blockchain Based Decentralized Platform for Ubiquitous Learning Environment
Bdiwi, R., de Runz, C., Faïz, S., & Ali-Chérif, A. (2018) · IEEE International Conference on Advanced Learning Technologies (ICALT) · doi:10.1109/icalt.2018.00028 · Cited by 47 · cited 1×
“It has been explored to facilitate the privacy-preserving data collection and sharing [35, 36, 253].”
BackgroundReal-Time Hand Gesture Recognition Model Using Deep Learning Techniques and EMG Signals
Chung, E. A., & Benalcazar, M. E. (2019) · 2019 27th European Signal Processing Conference (EUSIPCO) · doi:10.23919/eusipco.2019.8903136 · Cited by 47 · cited 1×
“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].”
MethodA CNN-LSTM neural network for recognition of puffing in smoking episodes using wearable sensors
Senyurek, V. Y., Imtiaz, M. H., Belsare, P. V., Tiffany, S. T., & Sazonov, E. E. (2020) · Biomedical Engineering Letters · doi:10.1007/s13534-020-00147-8 · Cited by 47 · 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.”
BackgroundUser adaptation of convolutional neural network for human activity recognition
Matsui, S., Inoue, N., Akagi, Y., Nagino, G., & Shinoda, K. (2017) · 2017 25th European Signal Processing Conference (EUSIPCO) · doi:10.23919/eusipco.2017.8081308 · Cited by 46 · cited 3×
“In [184], the Short-time Fourier transform (STFT) for time-series sensor data is calculated and its power spectrum is used as the input to a CNN.”
MethodInfluentialSmartphone Continuous Authentication Using Deep Learning Autoencoders
Parreno-Centeno, M., van Moorsel, A., & Castruccio, S. (2017) · Conference on Privacy, Security and Trust · doi:10.1109/pst.2017.00026 · Cited by 46 · cited 1×
“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].”
MethodA study on Human Activity Recognition Using Gyroscope, Accelerometer, Temperature and Humidity data
Barna, A., Masum, A. K. M., Hossain, M. E., Bahadur, E. H., & Alam, M. S. (2019) · International Conference on Electrical, Computer and Communication Engineering · doi:10.1109/ecace.2019.8679226 · Cited by 46 · 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)…”
MethodQin, Y., Luo, H., Zhao, F., Wang, C., Wang, J., & Zhang, Y. (2019) · IEEE Access · doi:10.1109/access.2019.2944686 · Cited by 46 · cited 1×
“proposed a deep-learning algorithm that combines CNN and LSTM networks [218].”
BackgroundLearning Deep and Shallow Features for Human Activity Recognition
Sani, S., Massie, S., Wiratunga, N., & Cooper, K. (2017) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-63558-3_40 · Cited by 45 · cited 1×
“This allows CNN to learn excellent features as shown in [242], which compares the features extracted from CNN to hand-crafted time and frequency domain features (Fast Fourier Transform and Discrete Cosine Transform).”
MethodTry Walking in My Shoes, if You Can: Accurate Gait Recognition Through Deep Learning
Giorgi, G., Martinelli, F., Saracino, A., & Sheikhalishahi, M. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-66284-8_32 · Cited by 45 · cited 2×
“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].”
BackgroundMethodHuman Activity Recognition Based on Deep Learning Method
Shi, X., Li, Y., Zhou, F., & Liu, L. (2018) · 2018 International Conference on Radar (RADAR) · doi:10.1109/radar.2018.8557335 · Cited by 45 · 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.”
MethodSelf-citationGANs May Have No Nash EquilibriaPreprint
Farnia, F., & Ozdaglar, A. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2002.09124 · Cited by 45 · cited 1×
“However, it is not theoretically guaranteed that GAN zero-sum games reach Nash Equilibria [90].”
BackgroundDeep Auto-Set: A Deep Auto-Encoder-Set Network for Activity Recognition Using Wearables
Varamin, A. A., Abbasnejad, E., Shi, Q., Ranasinghe, D. C., & Rezatofighi, H. (2018) · Proceedings of the 15th EAI International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services · doi:10.1145/3286978.3287024 · Cited by 44 · 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].”
BackgroundMethodIoT Sensor-Based Activity Recognition: Human Activity Recognition
Ahad, M. A. R., Antar, A. D., & Ahmed, M. (2021) · Intelligent Systems Reference Library · doi:10.1007/978-3-030-51379-5 · Cited by 44
Sanabria, A. R., Zambonelli, F., Dobson, S., & Ye, J. (2021) · Pervasive and Mobile Computing · doi:10.1016/j.pmcj.2021.101477 · Cited by 43 · cited 1×
“Even more, transfer learning under conditions of cross-body, cross-user, and cross-sensor has been demonstrated superior performance in [241].”
BackgroundDeep Learning for Human Activity Recognition
San, P. P., Kakar, P., Li, X., Krishnaswamy, S. P., Yang, J.-B., & Nguyen, M. N. (2017) · Elsevier eBooks · doi:10.1016/b978-0-12-809393-1.00009-x · Cited by 42
(2006) · Lecture Notes in Computer Science · doi:10.1007/11840930 · Cited by 42
Deep Convolutional Bidirectional LSTM Based Transportation Mode Recognition
Jeyakumar, J. V., Lee, E. S., Xia, Z., Sandha, S. S., Tausik, N., & Srivastava, M. B. (2018) · ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp) · doi:10.1145/3267305.3267529 · Cited by 41 · 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].”
BackgroundMulti-modality Sensor Data Classification with Selective Attention
Zhang, X., Yao, L., Huang, C., Wang, S., Tan, M., Long, G., & Wang, C. (2018) · Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2018/432 · Cited by 41 · cited 3×
“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].”
BackgroundMethodGudur, G. K., & Perepu, S. K. (2021) · Communications in computer and information science · doi:10.1007/978-981-16-0575-8_5 · Cited by 41 · cited 1×
“Besides, Gudur and Perepu [112] implemented on-device federated learning using model distillation update and so-called weighted α-updates strategies to resolve model heterogeneities on a resource-limited embedded system (Raspberry Pi), which proved its effectiveness and efficiency.”
MethodAutomated analysis of in meal eating behavior using a commercial wristband IMU sensor
Kyritsis, K., Tatli, C. L., Diou, C., & Delopoulos, A. N. (2017) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc.2017.8037449 · Cited by 40 · cited 2×
“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.”
BackgroundOnline Human Gesture Recognition using Recurrent Neural Networks and Wearable Sensors
Carfì, A., Motolese, C., Bruno, B., & Mastrogiovanni, F. (2018) · IEEE RO-MAN · doi:10.1109/roman.2018.8525769 · Cited by 40 · 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].”
BackgroundBenchmarking the SHL Recognition Challenge with Classical and Deep-Learning Pipelines
Wang, L., Gjoreski, H., Ciliberto, M., Mekki, S., Valentin, S., & Roggen, D. (2018) · ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp) · doi:10.1145/3267305.3267531 · Cited by 40 · 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].”
BackgroundSynthetic Sensor Data for Human Activity Recognition
Alharbi, F., Ouarbya, L., & Ward, J. A. (2020) · 2020 International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn48605.2020.9206624 · Cited by 40 · cited 1×
“Similarly, [13] assesses synthetic data with CNN or LSTM models as a generator.”
MethodA time-efficient convolutional neural network model in human activity recognition
Gholamrezaii, M., & Almodarresi, S. M. T. (2021) · Multimedia Tools and Applications · doi:10.1007/s11042-020-10435-1 · Cited by 40 · cited 1×
“[105] C-P-C-P-S 4×4 locomotion activities 6, 12 S1 UCI, mHealth”
Rubio-Solis, A., Panoutsos, G., Beltran-Perez, C., & Martinez-Hernandez, U. (2020) · Neurocomputing · doi:10.1016/j.neucom.2019.11.105 · Cited by 39 · cited 2×
“As such, the outputs of autoencoders are often used as inputs to other networks and algorithms to improve performance [120, 121, 122, 123, 124].”
BackgroundMethodLiu, Y., Zhang, S., & Gowda, M. (2021) · Proceedings of the International Conference on Internet-of-Things Design and Implementation · doi:10.1145/3450268.3453537 · Cited by 39 · cited 1×
“Several works extracted 3D motion information from videos and transferred the knowledge to synthesize virtual on-body IMU sensor data [264, 265].”
BackgroundSelf-citation(2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-13817-6 · Cited by 39
HASC2011corpus: towards the common ground of human activity recognition
Kawaguchi, N., Yang, Y., Yang, T., Ogawa, N., Iwasaki, Y., Kaji, K., Terada, T., Murao, K., Inoue, S., Kawahara, Y., et al. (2011) · Proceedings of the 13th international conference on Ubiquitous computing · doi:10.1145/2030112.2030218 · Cited by 38 · cited 1×
“[292] utilizes GANs with a customized network to generate synthetic data from the public HAR dataset HASC2010corpus [144].”
MethodA wearable hand gesture recognition device based on acoustic measurements at wrist
Siddiqui, N., & Chan, R. H. M. (2017) · doi:10.1109/embc.2017.8037842 · Cited by 38 · 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].”
MethodInfluentialPAWS: A Wearable Acoustic System for Pedestrian Safety
de Godoy, D., Islam, B., Xia, S., Islam, M. T., Chandrasekaran, R., Chen, Y.-C., Nirjon, S., Kinget, P. R., & Jiang, X. (2018) · IEEE/ACM International Conference on Internet-of-Things Design and Implementation (IoTDI) · doi:10.1109/iotdi.2018.00031 · Cited by 38 · cited 1×
“DNN-based HAR systems can largely benefit by incorporating methodologies proposed by works such as [57, 81, 128, 201, 202, 304, 305, 307], that carefully partition computation and data across multiple devices and the cloud.”
MethodSelf-citationGudur, G. K., Sundaramoorthy, P., & Umaashankar, V. (2019) · EMDL '19 · doi:10.1145/3325413.3329790 · Cited by 38 · cited 2×
“utilized active learning by combining a CNN with Bayesian techniques to represent model uncertainties (B-CNN) [113].”
MethodHuman activity recognition using deep electroencephalography learning
Salehzadeh, A., Calitz, A. P., & Greyling, J. (2020) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2020.102094 · Cited by 38 · 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)…”
MethodMobile Health: Sensors, Analytic Methods, and Applications
(2017) · doi:10.1007/978-3-319-51394-2 · Cited by 38
Xu, X., Nemati, E., Vatanparvar, K., Nathan, V., Ahmed, T., Rahman, M. M., McCaffrey, D., Kuang, J., & Gao, J. A. (2021) · Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies · doi:10.1145/3448124 · Cited by 38 · 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].”
BackgroundRecognition of Human Hand Activities Based on a Single Wrist IMU Using Recurrent Neural Networks
Rivera, P., Añazco, E. V., Choi, M., & Kim, T. (2017) · International Journal of Pharma Medicine and Biological Sciences · doi:10.18178/ijpmbs.6.4.114-118 · Cited by 37 · cited 2×
“Previous studies have shown that LSTMs have high performance in wearable HAR [195, 206, 230].”
BackgroundMethodChikhaoui, B., & Gouineau, F. (2017) · 2017 IEEE International Conference on Data Mining Workshops (ICDMW) · doi:10.1109/icdmw.2017.97 · Cited by 36 · cited 1×
“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].”
MethodGesture recognition with the linear optical sensor and recurrent neural networks
Czuszynski, K., Ruminski, J., & Kwasniewska, A. (2018) · IEEE Sensors Journal · doi:10.1109/jsen.2018.2834968 · Cited by 36 · cited 2×
“[78] showed that training a RNN with raw data and with simple custom features yielded similar performance for gesture recognition (96.”
BackgroundMethodSemi-supervised learning for human activity recognition using adversarial autoencoders
Balabka, D. (2019) · Adjunct Proceedings of the 2019 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2019 ACM International Symposium on Wearable Computers · doi:10.1145/3341162.3344854 · Cited by 36 · cited 1×
“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].”
MethodHu, Y., Zhang, X.-Q., Xu, L., Xian He, F., Tian, Z., She, W., & Liu, W. (2020) · IEEE Access · doi:10.1109/access.2020.3003162 · Cited by 36 · cited 2×
“The GRU introduces a reset and update gate to control the flow of inputs to a cell [78, 129, 135, 206, 342].”
BackgroundMethodDeepEar: Robust Smartphone Audio Sensing in Unconstrained Acoustic Environments using Deep Learning
Lane, N., Georgiev, P., & Qendro, L. (2015) · UCL Discovery (University College London) · Cited by 36
Real-Time Activity Recognition on Smartphones Using Deep Neural Networks
Zhang, L., Wu, X., & Luo, D. (2015) · 2015 IEEE 12th Intl Conf on Ubiquitous Intelligence and Computing and 2015 IEEE 12th Intl Conf on Autonomic and Trusted Computing and 2015 IEEE 15th Intl Conf on Scalable Computing and Communications and Its Associated Workshops (UIC-ATC-ScalCom) · doi:10.1109/uic-atc-scalcom-cbdcom-iop.2015.224 · Cited by 35 · cited 2×
“In early exploratory work back in 2011 [325], a 5-layer DBN is trained with the input acceleration data collected from mobile phones.”
MethodAutomated Synchronization of Driving Data Using Vibration and Steering Events
Fridman, L., Brown, D. E., Angell, W., Abdić, I., Reimer, B., & Noh, H. Y. (2016) · Pattern Recognition Letters · doi:10.1016/j.patrec.2016.02.011 · Cited by 34 · cited 1×
“A number of attempts have been made to address this issue, such as [93] and the Window Induced Shift Estimation method (SyncWISE) [334].”
MethodNie, J., Liu, Y., Hu, Y. C., Wang, Y., Xia, S., Preindl, M., & Jiang, X. (2021) · Pervasive and Mobile Computing · doi:10.1016/j.pmcj.2021.101424 · Cited by 34 · cited 1×
“DNN-based HAR systems can largely benefit by incorporating methodologies proposed by works such as [57, 81, 128, 201, 202, 304, 305, 307], that carefully partition computation and data across multiple devices and the cloud.”
MethodSelf-citationHioki, M., & Kawasaki, H. (2009) · International Conference on Rehabilitation Robotics · doi:10.1109/icorr.2009.5209609 · Cited by 32 · 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.”
MethodInfluentialHuman Activity Recognition using Multi-Head CNN followed by LSTM
Ahmad, W., Kazmi, B. M., & Ali, H. (2019) · International Conference on Emerging Technologies · doi:10.1109/icet48972.2019.8994412 · Cited by 32 · 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.”
BackgroundDenseNetX and GRU for the sussex-huawei locomotion-transportation recognition challenge
Zhu, Y., Luo, H., Chen, R., Zhao, F., & Su, L. (2020) · ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp) · doi:10.1145/3410530.3414349 · Cited by 32 · 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].”
BackgroundMethodInfluentialSmart Devices Based Multisensory Approach for Complex Human Activity Recognition
Hanif, M. A., Akram, T., Shahzad, A., Khan, M. A., Tariq, U., Choi, J.-I., Nam, Y., & Zulfiqar, Z. (2021) · Computers, materials & continua/Computers, materials & continua (Print) · doi:10.32604/cmc.2022.019815 · Cited by 32 · 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].”
BackgroundHAR-Net: Fusing Deep Representation and Hand-Crafted Features for Human Activity Recognition
Dong, M., Han, J., He, Y., & Jing, X. (2019) · Lecture notes in electrical engineering · doi:10.1007/978-981-13-7123-3_4 · Cited by 30 · cited 1×
“[85] demonstrated performance improvements by leveraging both handcrafted time and frequency domain features along with features generated from a CNN, called HAR-Net, to classify six locomotion activities using accelerometer and gyroscope signals from a smartphone.”
MethodMeagher, C., Franco, E., Turk, R., Wilson, S., Steadman, N., McNicholas, L., Vaidyanathan, R., Burridge, J. H., & Stokes, M. J. (2020) · Journal of Rehabilitation and Assistive Technologies Engineering · doi:10.1177/2055668320916116 · Cited by 30 · cited 1×
“Moreover, Meagher et al [185] proposed developing an MMG device as a wearable sensor to detect mechanical muscle activity for rehabilitation after stroke.”
BackgroundNie, J., Hu, Y. C., Wang, Y., Xia, S., & Jiang, X. (2020) · IEEE/ACM International Conference on Internet-of-Things Design and Implementation (IoTDI) · doi:10.1109/iotdi49375.2020.00011 · Cited by 30 · cited 1×
“DNN-based HAR systems can largely benefit by incorporating methodologies proposed by works such as [57, 81, 128, 201, 202, 304, 305, 307], that carefully partition computation and data across multiple devices and the cloud.”
MethodSelf-citationMohammed, S., & Tashev, I. (2017) · 2017 IEEE 14th International Conference on Wearable and Implantable Body Sensor Networks (BSN) · doi:10.1109/bsn.2017.7936037 · Cited by 29 · 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.”
BackgroundMethodOkai, J., Paraschiakos, S., Beekman, M., Knobbe, A., & de Sa, C. R. (2019) · 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc.2019.8857288 · Cited by 29 · cited 3×
“Previous studies have shown that LSTMs have high performance in wearable HAR [195, 206, 230].”
BackgroundMethodWeakly-supervised sensor-based activity segmentation and recognition via learning from distributions
Qian, H., Pan, S. J., & Miao, C. (2020) · Artificial Intelligence · doi:10.1016/j.artint.2020.103429 · Cited by 29 · cited 1×
“[216] proposed weakly-superviseds sensor-based activity segmentation and recognition method.”
MethodA strain gauge based locomotion mode recognition method using convolutional neural network
Feng, Y., Chen, W., & Wang, Q. (2019) · Advanced Robotics · doi:10.1080/01691864.2018.1563500 · Cited by 28 · 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).”
BackgroundReRAM Crossbar based Recurrent Neural Network for human activity detection
Long, Y., Jung, E. M., Kung, J., & Mukhopadhyay, S. (2016) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2016.7727299 · Cited by 27 · 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].”
BackgroundUnTran: Recognizing Unseen Activities with Unlabeled Data Using Transfer Learning
Khan, M. A. A. H., & Roy, N. (2018) · IEEE/ACM International Conference on Internet-of-Things Design and Implementation (IoTDI) · doi:10.1109/iotdi.2018.00014 · Cited by 27 · cited 1×
“Additionally, autoencoders have been explored for feature extraction in domain transfer learning [10], detecting unseen data [147], and recognizing null classes [9].”
BackgroundMotion2Vector: unsupervised learning in human activity recognition using wrist-sensing data
Bai, L., Yeung, C., Efstratiou, C., & Chikomo, M. (2019) · Adjunct Proceedings of the 2019 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2019 ACM International Symposium on Wearable Computers · doi:10.1145/3341162.3349335 · Cited by 27 · cited 1×
“An autoencoder’s strength in dimensionality reduction has been applied to HAR in wearables [17, 25, 98, 171, 180, 181, 182, 190, 221] and functions as a powerful tool for denoising and information retrieval.”
MethodA unified generative model using generative adversarial network for activity recognition
Chan, M. H., & Noor, M. H. M. (2021) · Journal of Ambient Intelligence and Humanized Computing · doi:10.1007/s12652-020-02548-0 · Cited by 27 · 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.”
MethodXia, S., Nie, J., & Jiang, X. (2021) · ACM/IEEE International Conference on Information Processing in Sensor Networks (IPSN) · doi:10.1145/3412382.3458267 · Cited by 27 · cited 1×
“DNN-based HAR systems can largely benefit by incorporating methodologies proposed by works such as [57, 81, 128, 201, 202, 304, 305, 307], that carefully partition computation and data across multiple devices and the cloud.”
MethodSelf-citationCheron, G. A., Cebolla, A. M., Bengoetxea, A., Leurs, F., & Dan, B. (2006) · Neuroscience Letters · doi:10.1016/j.neulet.2006.12.019 · Cited by 26 · 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.”
MethodInfluentialTime-Elastic Generative Model for Acceleration Time Series in Human Activity Recognition
Muñoz-Organero, M., & Blázquez, R. R. (2017) · Sensors · doi:10.3390/s17020319 · Cited by 25 · cited 1×
“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].”
MethodPattern recognition of human arm movement using deep reinforcement learning
Seok, W., Kim, Y., & Park, C. (2018) · 2018 International Conference on Information Networking (ICOIN) · doi:10.1109/icoin.2018.8343257 · Cited by 25 · cited 17×
“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].”
BackgroundMethodInfluentialA GAN-based data augmentation method for human activity recognition via the caching ability
Shi, J., Zuo, D., & Zhang, Z. (2021) · Internet Technology Letters · doi:10.1002/itl2.257 · Cited by 24 · 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]…”
MethodZhang, S., Nemati, E., Dinh, M., Folkman, N., Ahmed, T., Rahman, M., Kuang, J., Alshurafa, N., & Gao, A. (2022) · ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp43922.2022.9746334 · Cited by 23 · 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].”
BackgroundSelf-citationWeakly-supervised learning for Parkinson's Disease tremor detection
Zhang, A., Cebulla, A., Panev, S., Hodgins, J., & De la Torre, F. (2017) · 2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc.2017.8036782 · Cited by 22 · cited 1×
“Specifically, several works have introduced systems and methods for monitoring and assessing Parkinson disease (PD) symptoms [89, 119, 150, 189, 277, 322].”
BackgroundSynthesizing and Reconstructing Missing Sensory Modalities in Behavioral Context Recognition
Saeed, A., Ozcelebi, T., & Lukkien, J. (2018) · Sensors · doi:10.3390/s18092967 · Cited by 22 · cited 1×
“Usually, the considered corruption includes isotropic Gaussian Figure 4: Illustration of an autoencoder network [237].”
BackgroundMotion Recognition for Smart Sports Based on Wearable Inertial Sensors
Wang, H. H., Li, L., Chen, H., Li, Y., Qiu, S., & Gravina, R. (2019) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-030-34833-5_10 · Cited by 22 · 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].”
MethodInfluentialSelf-citationKnow Your Mind: Adaptive Cognitive Activity Recognition with Reinforced CNN
Zhang, X., Yao, L., Wang, X., Zhang, W., Zhang, S., & Liu, Y. (2019) · 2019 IEEE International Conference on Data Mining (ICDM) · doi:10.1109/icdm.2019.00100 · Cited by 22 · cited 1×
“[333] employed CNN for feature extraction and a reinforced selective attention model to automatically choose the most characteristic information from multiple channels.”
MethodSelf-citationDeep generative cross-modal on-body accelerometer data synthesis from videos
Zhang, S., & Alshurafa, N. (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:10.1145/3410530.3414329 · Cited by 21 · cited 1×
“Therefore, taking advantage of the cutting-edge deep generative models may contribute to addressing the wearable sensor data scarcity issue [269].”
BackgroundSelf-citationUnsupervised End-to-End Deep Model for Newborn and Infant Activity Recognition
Jun, K., & Choi, S. (2020) · Sensors · doi:10.3390/s20226467 · Cited by 21 · cited 1×
“Jun and Choi [141] studied classification of newborn and infant activities into four classes: sleeping, moving in agony, moving in normal condition, and movement by an external force.”
BackgroundCombining LSTM and CNN for mode of transportation classification from smartphone sensors
Friedrich, B., Lübbe, C., & Hein, A. (2020) · ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp) · doi:10.1145/3410530.3414350 · Cited by 20 · 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.”
BackgroundCoughBuddy: Multi-Modal Cough Event Detection Using Earbuds Platform
Nemati, E., Zhang, S., Ahmed, T., Rahman, M. M., Kuang, J., & Gao, A. (2021) · 2021 IEEE 17th International Conference on Wearable and Implantable Body Sensor Networks (BSN) · doi:10.1109/bsn51625.2021.9507017 · Cited by 20 · cited 2×
“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].”
BackgroundMethodSelf-citationJin, W., Murali, S., Cho, Y., et al. (2021) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3494992 · Cited by 20
Transfer Learning for Improved Audio-Based Human Activity Recognition
Ntalampiras, S., & Potamitis, I. (2018) · Biosensors · doi:10.3390/bios8030060 · Cited by 18 · 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)…”
MethodMobiGesture: Mobility-aware hand gesture recognition for healthcare
Zhao, H., Ma, Y., Wang, S., Watson, A., & Zhou, G. (2018) · Smart Health · doi:10.1016/j.smhl.2018.07.010 · Cited by 18 · 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.”
BackgroundComputer Safety, Reliability, and Security
(2017) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-66266-4 · Cited by 18
Atypical Sample Regularizer Autoencoder for Cross-Domain Human Activity Recognition
Prabono, A. G., Yahya, B. N., & Lee, S. (2020) · Information Systems Frontiers · doi:10.1007/s10796-020-09992-5 · Cited by 18 · cited 1×
“[214] propose a two-phase autoencoder-based approach of domain adaptation for human activity recognition.”
BackgroundZheng, J., Cao, H., Chen, D., Ansari, R., Chu, K.-C., & Huang, M.-C. (2020) · IEEE Sensors Journal · doi:10.1109/jsen.2020.2986768 · Cited by 17 · cited 2×
“[338] developed a reinforcement learning model for imitating the walking pattern of a lower-limb amputee on a musculoskeletal model.”
BackgroundInvestigating barriers and facilitators to wearable adherence in fine-grained eating detection
Alharbi, R., Vafaie, N., Liu, K., Moran, K., Ledford, G., Pfammatter, A. F., Spring, B. J., & Alshurafa, N. I. (2017) · IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops) · doi:10.1109/percomw.2017.7917597 · Cited by 16 · cited 1×
“used ground truth wearable cameras placed at the wrist, chest, and shoulders to record subject movements and surroundings as subjects moved around outside of a lab setting [14].”
MethodSelf-citationA Drone-based System for Intelligent and Autonomous Homes
Xia, S., Chandrasekaran, R., Liu, Y., et al. (2021) · ACM Conference on Embedded Networked Sensor Systems (SenSys) · doi:10.1145/3485730.3492881 · Cited by 16 · cited 1×
“An exciting new direction is to create generalized frameworks that can adaptively utilize data from whatever sensors happens to be availble, such as this smarthome intelligence system [306].”
BackgroundSelf-citationRecognition and anticipation of hand motions using a recurrent neural network
Vamplew, P. W., & Adams, A. H. (2005) · doi:10.1109/icnn.1995.487241 · Cited by 15
A DBN-BASED MULTI-LEVEL STOCHASTIC SPOKEN LANGUAGE UNDERSTANDING SYSTEM
Lefèvre, F. (2006) · IEEE Spoken Language Technology Workshop (SLT) · doi:10.1109/slt.2006.326822 · Cited by 15 · 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.”
BackgroundA survey of activity recognition in egocentric lifelogging datasets
Asnaoui, K. E., Aksasse, H., Aksasse, B., & Ouanan, M. (2017) · International Conference on Wireless Technologies, Embedded and Intelligent Systems (WITS) · doi:10.1109/wits.2017.7934659 · Cited by 15 · 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.”
BackgroundSmartphone-sensors Based Activity Recognition Using IndRNN
Li, S., Li, C., Li, W., Hou, Y., & Cook, C. (2018) · ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp) · doi:10.1145/3267305.3267521 · Cited by 15 · 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 in a Home Setting Using Off the Shelf Smart Watch Technology
Filippoupolitis, A., Takand, B., & Loukas, G. (2016) · International Conference on Ubiquitous Computing and Communications (IUCC) · doi:10.1109/iucc-css.2016.014 · Cited by 14 · 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)…”
MethodUsing respiratory signals for the recognition of human activities
Ramos-Garcia, R. I., Tiffany, S. T., & Sazonov, E. E. (2016) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc.2016.7590668 · Cited by 13 · 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)…”
MethodDevelopment of a wearable HCI controller through sEMG & IMU sensor fusion
Kim, J., Kim, M., & Kim, K. (2016) · International Conference on Ubiquitous Robots and Ambient Intelligence · doi:10.1109/urai.2016.7734026 · Cited by 13 · 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].”
BackgroundSensor Positioning and Data Acquisition for Activity Recognition using Deep Learning
Chung, S., Lim, J., Noh, K. J., Kim, G. G., & Jeong, H. T. (2018) · International Conference on Information and Communication Technology Convergence (ICTC) · doi:10.1109/ictc.2018.8539473 · Cited by 13
Toward a mixed-signal reconfigurable ASIC for real-time activity recognition
Wang, L., Thiemjarus, S., Lo, B. P. L., & Yang, G. (2008) · IEEE/EMBS International Summer School on Medical Devices and Biosensors (ISSS-MDBS) · doi:10.1109/issmdbs.2008.4575060 · Cited by 12 · cited 1×
“[294] developed custom integrated circuits and hardware accelerators that perform the entire HAR pipeline, from sampling to DNN inference with significantly lower power consumption than mobile or GPU-based platforms.”
BackgroundValarezo, A., Rivera, L., Park, H., Park, N., & Kim, T.-S. (2020) · Computer Science and Information Systems · doi:10.2298/csis190920005v · Cited by 12 · cited 1×
“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.”
BackgroundKhatiwada, P., Chatterjee, A., & Subedi, M. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.03324 · Cited by 12
Deep Convolutional Bidirectional LSTM for Complex Activity Recognition with Missing Data
Saha, S. S., Sandha, S. S., & Srivastava, M. (2021) · Smart Innovation, Systems and Technologies · doi:10.1007/978-981-15-8269-1_4 · Cited by 12 · cited 2×
“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.”
BackgroundMethodWang, X., Wang, Y., Wang, Z. J., Wang, C., & Li, Y. (2018) · Nano-, Bio-, Info-Tech Sensors, and Wearable Systems · doi:10.1117/12.2296382 · Cited by 11
Self-citationPerRNN: Personalized Recurrent Neural Networks for Acceleration-Based Human Activity Recognition
Wang, X., Liao, W., Guo, Y., Yu, L., Wang, Q., Pan, M., & Li, P. (2019) · International Conference on Communications · doi:10.1109/icc.2019.8761931 · Cited by 11 · cited 1×
“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…”
BackgroundJangir, M. K., & Singh, K. (2019) · Journal of Discrete Mathematical Sciences and Cryptography · doi:10.1080/09720529.2019.1696552 · Cited by 11 · cited 2×
“[135] utilizes attention in combination with a 1D CNN Gated Recurrent Units (GRUs), achieving HAR performances of 96.”
BackgroundMethodZhang, Y. C., Zhang, S., Liu, M., Daly, E., Battalio, S. L., Kumar, S., Spring, B. J., Rehg, J. M., & Alshurafa, N. I. (2020) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3411824 · Cited by 11 · cited 1×
“A number of attempts have been made to address this issue, such as [93] and the Window Induced Shift Estimation method (SyncWISE) [334].”
MethodSelf-citationKhatiwada, P., Subedi, M., Chatterjee, A., & Gerdes, M. W. (2020) · Preprints.org · doi:10.20944/preprints202010.0367.v1 · Cited by 11 · 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…”
BackgroundTamamori, A., Hayashi, T., Toda, T., & Takeda, K. (2017) · Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) · doi:10.1109/apsipa.2017.8282239 · Cited by 10 · 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].”
BackgroundA Smartphone-Based System for Improving Pedestrian Safety
Xia, S., de Godoy, D., Islam, B., et al. (2018) · IEEE Vehicular Networking Conference (VNC) · doi:10.1109/vnc.2018.8628320 · Cited by 10
Self-citationPires, I. M., Pombo, N., Garcia, N. M., & Flórez-Revuelta, F. (2018) · Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2018/859 · Cited by 8 · 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].”
BackgroundDaily activity recognition based on recurrent neural network using multi-modal signals
Tamamori, A., Hayashi, T., Toda, T., & Takeda, K. (2018) · APSIPA Transactions on Signal and Information Processing · doi:10.1017/atsip.2018.25 · Cited by 8 · 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].”
BackgroundAkbari, A., & Jafari, R. (2019) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2019.8682161 · Cited by 8 · cited 1×
“Additionally, autoencoders have been explored for feature extraction in domain transfer learning [10], detecting unseen data [147], and recognizing null classes [9].”
Backgroundde Andrade, F. H. C., Pereira, F. G., Resende, C. Z., & Cavalieri, D. C. (2019) · IFMBE Proceedings · doi:10.1007/978-981-13-2517-5_42 · Cited by 8 · cited 1×
“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].”
MethodAcross-Sensor Feature Learning for Energy-Efficient Activity Recognition on Mobile Devices
Gavrilin, Y., & Khan, A. (2019) · 2019 International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2019.8851977 · Cited by 8 · 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].”
BackgroundMethodAkbari, A., & Jafari, R. (2021) · IEEE Sensors Journal · doi:10.1109/jsen.2020.3023109 · Cited by 8 · cited 2×
“frequency dimension, will generally use 2D-CNN kernels [11].”
BackgroundMethodmDebugger: Assessing and Diagnosing the Fidelity and Yield of Mobile Sensor Data
Rahman, M., Ali, N., Bari, R., Saleheen, N., Al’Absi, M., Ertin, E., Kennedy, A., Preston, K. L., & Kumar, S. (2017) · Springer eBooks · doi:10.1007/978-3-319-51394-2_7 · Cited by 8
Chandrasekaran, R., de Godoy, D., Xia, S., et al. (2016) · doi:10.1145/2994551.2996547 · Cited by 7 · cited 1×
“DNN-based HAR systems can largely benefit by incorporating methodologies proposed by works such as [57, 81, 128, 201, 202, 304, 305, 307], that carefully partition computation and data across multiple devices and the cloud.”
MethodSelf-citationMahmoodzadeh, A. (2021) · Journal of Information Systems and Telecommunication (JIST) · doi:10.52547/jist.9.33.45 · Cited by 7 · cited 1×
“In later works, DBN is applied to publicly available datasets [6, 222, 326] [179].”
MethodZheng, L., Li, S., Zhu, C., & Gao, Y. (2019) · ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp) · doi:10.1145/3341162.3344851 · Cited by 6 · 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].”
BackgroundMethodInfluentialDemo Abstract: Wireless Glasses for Non-contact Facial Expression Monitoring
Hu, Y. C., Nie, J., Wang, Y., et al. (2020) · ACM/IEEE International Conference on Information Processing in Sensor Networks (IPSN) · doi:10.1109/ipsn48710.2020.000-1 · Cited by 6 · cited 1×
“DNN-based HAR systems can largely benefit by incorporating methodologies proposed by works such as [57, 81, 128, 201, 202, 304, 305, 307], that carefully partition computation and data across multiple devices and the cloud.”
MethodSelf-citationA Novel Multi-Centroid Template Matching Algorithm and Its Application to Cough Detection
Zhang, S., Nemati, E., Ahmed, T., Rahman, M. M., Kuang, J., & Gao, A. (2021) · 2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC) · doi:10.1109/embc46164.2021.9629993 · Cited by 5 · 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].”
BackgroundSelf-citationPlacement Effect of Motion Sensors for Human Activity Recognition using LSTM Network
Mekruksavanich, S., Jitpattanakul, A., & Thongkum, P. (2021) · 2021 Joint International Conference on Digital Arts, Media and Technology with ECTI Northern Section Conference on Electrical, Electronics, Computer and Telecommunication Engineering · doi:10.1109/ectidamtncon51128.2021.9425719 · Cited by 3 · cited 1×
“Researchers in [187] explored the placement effect of motion sensors and discovered that the chest position is ideal for physical activity identification.”
BackgroundHigh Accuracy Drug-Target Protein Interaction Prediction Method based on DBN
Gu, W., Wang, G., Zhang, Z., Mao, Y., Xie, X., & He, Y. (2020) · IEEE International Conference on Power, Intelligent Computing and Systems (ICPICS) · doi:10.1109/icpics50287.2020.9202120 · Cited by 1 · 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.”
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.