Rehab-Net: Deep Learning Framework for Arm Movement Classification Using Wearable Sensors for Stroke Rehabilitation
The DOI matches its Crossref record; 60 of the 62 references it cites were found in a registry or an index.
Abstract
In this paper, we present a deep learning framework “Rehab-Net” for effectively classifying three upper limb movements of the human arm, involving extension, flexion, and rotation of the forearm, which, over the time, could provide a measure of rehabilitation progress. The proposed framework, Rehab-Net is formulated with a personalized, light weight and low-complex, customized convolutional neural network (CNN) model, using two-layers of CNN, interleaved with pooling layers, followed by a fully connected layer that classifies the three movements from tri-axial acceleration input data collected from the wrist. The proposed Rehab-Net framework was validated on sensor data collected in two situations: 1) semi-naturalistic environment involving an archetypal activity of “making-tea” with four stroke survivors and 2) natural environment, where ten stroke survivors were free to perform any desired arm movement for the duration of 120 min. We achieved an overall accuracy of 97.89% on semi-naturalistic data and 88.87% on naturalistic data which exceeded state-of-the-art learning algorithms namely, linear discriminant analysis, support vector machines, and k-means clustering with an average accuracy of 48.89%, 44.14%, and 27.64%. Subsequently, a computational complexity analysis of the proposed model has been discussed with an eye toward hardware implementation. The clinical significance of this study is to accurately monitor the clinical progress of the rehabilitated subjects under t…
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
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?
In the citing paper
“In addition, in order to design efficient ML-based assessment systems that generalises to new users a large number of participants should take part with different and variant degrees of severity [43,48,49,69,70], which is not always available and taken into account.”
From Wearable sensors and machine learning in post-stroke rehabilitation assessment: A systematic review (2022) · cites this paper as [43]
In the citing paper
“Another ANN architecture that was employed is Convolutional Neural Network (CNN) Architectures [43,45,50,54].”
From Wearable sensors and machine learning in post-stroke rehabilitation assessment: A systematic review (2022) · cites this paper as [43]
In the citing paper
“many studies proved the possibility to design effective systems with a very small number of sensors (sometimes a single sensor is sufficient) as is the case in [43,51].”
From Wearable sensors and machine learning in post-stroke rehabilitation assessment: A systematic review (2022) · cites this paper as [43]
Citations
Cites
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946 · cited 1×
“Sparse categorical cross-entropy loss function and ‘Adam optimizer’ [56] is used to update the weights faster than the popularly used stochastic gradient descent (SGD).”
MethodHeart Disease and Stroke Statistics—2017 Update: A Report From the American Heart Association
Benjamin, E. J., Blaha, M. J., Chiuve, S. E., Cushman, M., Das, S. R., Deo, R., de Ferranti, S. D., Floyd, J., Fornage, M., Gillespie, C., et al. (2017) · Circulation · doi:10.1161/cir.0000000000000485 · Cited by 12,591 · cited 1×
“S TROKE is a global public health issue, being the second leading cause of death worldwide, besides post-stroke outcomes such as disability affects the quality of life [1], [2].”
BackgroundHan, S., Mao, H., & Dally, W. J. (2015) · arXiv · doi:10.48550/arxiv.1510.00149 · Cited by 4,662
Deep learning for healthcare: review, opportunities and challenges
Miotto, R., Wang, F., Wang, S., Jiang, X., & Dudley, J. T. (2018) · Briefings in Bioinformatics · doi:10.1093/bib/bbx044 · Cited by 3,076 · cited 1×
“[61].”
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 1×
“been covered in detail in the review [30], [45].”
BackgroundAPI design for machine learning software: experiences from the scikit-learn project
Buitinck, L., Louppe, G., Blondel, M., Pedregosa, F., Mueller, A., Grisel, O., Niculae, V., Prettenhofer, P., Gramfort, A., Grobler, J., et al. (2013) · arXiv (Cornell University) · doi:10.48550/arxiv.1309.0238 · Cited by 1,871
Activity recognition from accelerometer data
Ravi, N., Dandekar, N., Mysore, P., & Littman, M. L. (2005) · Innovative Applications of Artificial Intelligence · Cited by 1,775
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 1×
“nition is to identify human behavior in real time scenario to provide proactive assistance to users even outside the conventional clinical setting [10].”
BackgroundWearable Sensors for Human Activity Monitoring: A Review
Mukhopadhyay, S. C. (2015) · IEEE Sensors Journal · doi:10.1109/jsen.2014.2370945 · Cited by 1,401
Cited by
Emerging Wearable Interfaces and Algorithms for Hand Gesture Recognition: A Survey
Jiang, S., Kang, P., Song, X., Lo, B., & Shull, P. (2022) · IEEE Reviews in Biomedical Engineering · doi:10.1109/rbme.2021.3078190 · Cited by 270
PP-Net: A Deep Learning Framework for PPG-Based Blood Pressure and Heart Rate Estimation
Panwar, M., Gautam, A., Biswas, D., & Acharyya, A. (2020) · IEEE Sensors Journal · doi:10.1109/jsen.2020.2990864 · Cited by 237
Self-citationIslam, M. M., Nooruddin, S., Karray, F., & Muhammad, G. (2022) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2022.106060 · Cited by 217
Wearable sensors and machine learning in post-stroke rehabilitation assessment: A systematic review
Boukhennoufa, I., Zhai, X., Utti, V., Jackson, J., & McDonald-Maier, K. D. (2022) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2021.103197 · Cited by 180
“Other researchers covered activities for specific body parts like recognising different hand gestures [41], arm gestures [43] and some exercises to strengthen shoulders, and arms [48].”
BackgroundMethodInfluentialA Human-AI Collaborative Approach for Clinical Decision Making on Rehabilitation Assessment
Lee, M. H., Siewiorek, D. P., Smailagic, A., Bernardino, A., & Bermúdez i Badia, S. B. (2021) · Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3411764.3445472 · Cited by 137
“However, substantial prior work on technology-assisted systems for rehabilitation focuses on demonstrating the feasibility of collecting objective kinematic variables to quantify the performance of rehabilitation exercises [43, 62] and improving the performance of a machine learning model to assess the quality of moti…”
BackgroundMethodInfluentialA Novel Deep Learning Bi-GRU-I Model for Real-Time Human Activity Recognition Using Inertial Sensors
Tong, L., Ma, H., Lin, Q., He, J., & Peng, L. (2022) · IEEE Sensors Journal · doi:10.1109/jsen.2022.3148431 · Cited by 127
Gautam, A., Panwar, M., Biswas, D., & Acharyya, A. (2020) · IEEE Journal of Translational Engineering in Health and Medicine · doi:10.1109/jtehm.2020.2972523 · Cited by 142
“Equation (1) expresses the data augmentation technique adopted from [11], where Dv is virtual data, Do is the original input data and wgn is a weighting parameter generating an m-by-n matrix of white Gaussian noise samples and p is the power.”
BackgroundMethodInfluentialSelf-citationThe use of wearable sensors to assess and treat the upper extremity after stroke: a scoping review
Kim, G. J., Parnandi, A., Eva, S., & Schambra, H. M. (2021) · Disability and Rehabilitation · doi:10.1080/09638288.2021.1957027 · Cited by 110
AI-Driven Stroke Rehabilitation Systems and Assessment: A Systematic Review
Rahman, S., Sarker, S. C., Haque, A. K. M. N., Uttsha, M. M., Islam, M. F., & Deb, S. (2022) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2022.3219085 · Cited by 111
“RQ4: As to the answer to the following research question about the efficacy of such assessments, many of the works feature high agreement levels with the therapists’ assessments [91], [92], [93], as well as high accuracy [94], [96], [97] and F1 scores [88], [91] in exercise correctness classification.”
BackgroundInfluentialContrastive Self-supervised Learning for Sensor-based Human Activity Recognition
Khaertdinov, B., Ghaleb, E., & Asteriadis, S. (2021) · 2021 IEEE International Joint Conference on Biometrics (IJCB) · doi:10.1109/ijcb52358.2021.9484410 · Cited by 95
“Sensor-based HAR has found applications in areas of pervasive computing [18], ambient assisting living [2, 16] and automation in manufacturing industry [20].”
AI Applications in Adult Stroke Recovery and Rehabilitation: A Scoping Review Using AI
Senadheera, I., Hettiarachchi, P., Haslam, B. S., Nawaratne, R., Sheehan, J., Lockwood, K. J., Alahakoon, D., & Carey, L. M. (2024) · Sensors · doi:10.3390/s24206585 · Cited by 111
“Furthermore, Panwar et al. [117] introduced Rehab-Net, a deep learning framework that utilized wearable accelerometers to classify arm movements and provide real-time feedback during rehabilitation sessions.”
BackgroundMethodAn EEG motor imagery dataset for brain computer interface in acute stroke patients
Liu, H., Wei, P., Wang, H., Lv, X., Duan, W., Li, M., Zhao, Y., Wang, Q., Chen, X., Shi, G., et al. (2024) · Scientific Data · doi:10.1038/s41597-023-02787-8 · Cited by 107
“Other limitations of these existing datasets include short recording times, small sample sizes and small numbers of BCI signals 6,12,24–34 .”
BackgroundSong, X., Ven, S. S. V. D., Liu, L., Wouda, F. J., Wang, H., & Shull, P. B. (2022) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2022.3156387 · Cited by 70
Rani, G. J., Hashmi, M. F., & Gupta, A. D. (2023) · IEEE Access · doi:10.1109/access.2023.3316509 · Cited by 84
“Recognition of human activities systems is utilized in a wide range of health care applications, including automatic fall detection [179], emergency response systems for detecting unintentional and offering immediate support, respiratory actions modeling applications for identifying and diagnosing…”
Gautam, A., Panwar, M., Wankhede, A., Arjunan, S. P., Naik, G. R., Acharyya, A., & Kumar, D. K. (2020) · IEEE Journal of Translational Engineering in Health and Medicine · doi:10.1109/jtehm.2020.3023898 · Cited by 62
“The proposed model was formulated after exploring the hyper-parameter tuning [35] with different hyper-parameters where 2 convolutional layers, 7 filters of size 5 × 1, stride rate of 1 in both convolutional layers and FIGURE 4.”
Self-citationMeng, Z., Zhang, M., Guo, C., Fan, Q., Zhang, H., Gao, N., & Zhang, Z. (2020) · Electronics · doi:10.3390/electronics9091357 · Cited by 67
“Their weaknesses are the monotonousness and implicity of information provided by the sensors which requires specialized processing.”
Lee, M. H., Siewiorek, D. P., Smailagic, A., Bernardino, A., & Bermúdez i Badia, S. (2020) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3415227 · Cited by 57
“However, significant recent research has focused on improving the accuracy of monitoring an exercise and replicating clinician’s decision making with a complex algorithm [35, 46, 49].”
BackgroundJaén-Vargas, M., Leiva, K. M. R., Fernandes, F., Gonçalves, S. B., Silva, M. T., Lopes, D. S., & Olmedo, J. J. S. (2022) · PeerJ Computer Science · doi:10.7717/peerj-cs.1052 · Cited by 73
A Wearable Human Motion Tracking Device Using Micro Flow Sensor Incorporating a Micro Accelerometer
Liu, S., Zhang, J. C., & Zhu, R. (2019) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2019.2924689 · Cited by 57
“Accelerometers working as pedometers with a complex machine learning [4], [21], [22] have been widely used in physical activities assessments, but not applicable to limb motion tracking.”
MethodHybridized Hierarchical Deep Convolutional Neural Network for Sports Rehabilitation Exercises
Tang, D. (2020) · IEEE Access · doi:10.1109/access.2020.3005189 · Cited by 56
“Patients perform a series of prescribed exercises in their home [8].”
BackgroundZhang, L., Yu, J., Gao, Z., & Ni, Q. (2024) · Alexandria Engineering Journal · doi:10.1016/j.aej.2024.01.030 · Cited by 61
A graphene-coated silk-spandex fabric strain sensor for human movement monitoring and recognition
Song, X., Liu, X., Peng, Y., Xu, Z. Y., Liu, W., Pang, K., Wang, J., Zhong, L., Yang, Q., & Meng, J. (2021) · Nanotechnology · doi:10.1088/1361-6528/abe788 · Cited by 50
Identifying Stroke Indicators Using Rough Sets
Pathan, M. S., Zhang, J., John, D., Nag, A., & Dev, S. (2020) · IEEE Access · doi:10.1109/access.2020.3039439 · Cited by 52
“Models like support vector machine [18], decision trees [19], deep neural network [20], and ensemble methods [21] have achieved notable results to classify stroke outcomes when provided with relevant data.”
BackgroundRecent Advances in Pedestrian Navigation Activity Recognition: A Review
Wang, Q., Luo, H., Wang, Q., Sun, L., Ma, Z., Zhang, C., Fu, M., & Zhao, F. (2022) · IEEE Sensors Journal · doi:10.1109/jsen.2022.3153610 · Cited by 50
Research on sEMG-Based Gesture Recognition by Dual-View Deep Learning
Zhang, Y., Yang, F., Fan, Q., Yang, A., & Li, X. (2022) · IEEE Access · doi:10.1109/access.2022.3158667 · Cited by 53
Deep Triplet Networks with Attention for Sensor-based Human Activity Recognition
Khaertdinov, B., Ghaleb, E., & Asteriadis, S. (2021) · IEEE International Conference on Pervasive Computing and Communications · doi:10.1109/percom50583.2021.9439116 · Cited by 52
“Modern Activity Recognition algorithms are used in various application areas which include but are not limited to health monitoring [1], smart homes [2] and manufacturing automation [3].”
MethodBiomedical Sensors and Applications of Wearable Technologies on Arm and Hand
Seçkin, M., Seçkin, A. Ç., & Gençer, Ç. (2022) · Biomedical Materials & Devices · doi:10.1007/s44174-022-00002-7 · Cited by 43
Cai, S., Li, G., Su, E., Wei, X., Huang, S., Ma, K., Zheng, H., & Xie, L. (2020) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2019.2963365 · Cited by 43
“In wearable sensor systems, accelerometers [9], inertial measurement units [10] or other sensors are placed on the patients with stroke to monitor the posture and upper limb motions during rehabilitation [11].”
BackgroundChaki, J., & Woźniak, M. (2024) · IEEE Access · doi:10.1109/access.2024.3383140 · Cited by 50
“Panwar et al. [83] utilized Rehab-Net to efficiently identify three types of human arm motions, including forearm flexion, extension, and rotation, which give a measure of post-brain stroke rehabilitation progress over time.”
BackgroundChen, Y., Zhang, D., Karimi, H. R., Deng, C., & Yin, W. (2022) · Neural Networks · doi:10.1016/j.neunet.2022.04.017 · Cited by 43
Lobo, P. L. S., Morais, P., Murray, P., & Vilaça, J. L. (2024) · Sensors · doi:10.3390/s24247973 · Cited by 53
A Survey of Wearable Sensors and Machine Learning Algorithms for Automated Stroke Rehabilitation
Sengupta, N., Rao, A. S., Yan, B., & Palaniswami, M. S. (2024) · IEEE Access · doi:10.1109/access.2024.3373910 · Cited by 40
“Panwar et al. [90] proposed a ‘‘Rehab-Net’’ framework to classify three upper limb movements from wrist-based accelerometer data.”
BackgroundMethodArtificial intelligence assisted nanogenerator applications
Xu, S., Manshaii, F., Xiao, X., & Chen, J. (2024) · Journal of Materials Chemistry A · doi:10.1039/d4ta07127a · Cited by 38
Yen, C.-T., Chang, S., & Liao, C.-H. (2022) · IEEE Access · doi:10.1109/access.2022.3195857 · Cited by 44
Dutta, D., Aruchamy, S., Mandal, S., & Sen, S. (2021) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2021.3110432 · Cited by 36
Deep learning model for classifying shoulder pain rehabilitation exercises using IMU sensor
Lee, K., Kim, J., Hong, H. T., Jeong, Y., Ryu, H. B., Kim, H., & Lee, S.-U. (2024) · Journal of NeuroEngineering and Rehabilitation · doi:10.1186/s12984-024-01343-8 · Cited by 41
“Monitoring the movement during shoulder exercise therapy using an IMU sensor has been reported [16, 17].”
MethodKhaertdinov, B., Asteriadis, S., & Ghaleb, E. (2022) · IEEE Transactions on Biometrics Behavior and Identity Science · doi:10.1109/tbiom.2022.3180591 · Cited by 40
“HUMAN Activity Recognition (HAR) is a crucial problem of human-computer interaction and ubiquitous computing addressed in smart manufacturing [1], health applications [2], [3] and ambient intelligence [4], [5].”
BackgroundZhou, Y., & Stewart, R. (2022) · Polymers for Advanced Technologies · doi:10.1002/pat.5856 · Cited by 35
Wearable Assistive Rehabilitation Robotic Devices—A Comprehensive Review
Lingampally, P. K., Ramanathan, K. C., Shanmugam, R., Čepová, L., & Salunkhe, S. S. (2024) · Machines · doi:10.3390/machines12060415 · Cited by 36
Peng, Y., Song, X., Pang, K., Yang, Q., Xu, Z. Y., & Zhang, M. (2020) · IEEE Sensors Journal · doi:10.1109/jsen.2020.3002916 · Cited by 27
“These devices have already been broadly employed in the field of professional sports, applied ergonomics, human-machine interaction, smart medical systems, etc [4]–[7].”
BackgroundContrastive Learning with Cross-Modal Knowledge Mining for Multimodal Human Activity Recognition
Brinzea, R., Khaertdinov, B., & Asteriadis, S. (2022) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn55064.2022.9892522 · Cited by 37
“many areas, such as smart homes [1], [2], health monitoring [3], manufacturing automation [4] and sport analytics [5].”
Park, C., Yi, C., Choi, W. J., Lim, H.-S., Yoon, H. U., & You, S. H. (2023) · Digital Health · doi:10.1177/20552076231217817 · Cited by 34
Luvizutto, G. J., Silva, G. F., Nascimento, M. R., Santos, K. C. S., Appelt, P. A., Neto, E. D. M., de Souza, J. T., Winckler, F. C., Miranda, L. A., Filho, P. T. H., et al. (2021) · Topics in Stroke Rehabilitation · doi:10.1080/10749357.2021.1926149 · Cited by 29
A Physiology-Based Flexible Strap Sensor for Gesture Recognition by Sensing Tendon Deformation
Peng, Y., Wang, J., Pang, K., Liu, W., Meng, J., & Li, B. (2021) · IEEE Sensors Journal · doi:10.1109/jsen.2021.3054562 · Cited by 26
AI in therapeutic and assistive exoskeletons and exosuits: Influences on performance and autonomy
van der Kooij, H., van Asseldonk, E. H. F., Sartori, M., Basla, C., Esser, A., & Riener, R. (2025) · Science Robotics · doi:10.1126/scirobotics.adt7329 · Cited by 27
Yen, J. M., & Lim, J. H. (2023) · Sensors · doi:10.3390/s23010536 · Cited by 28
“Aşuroğlu T et al. demonstrated that signals from ground reaction force (GRF) sensors analyzed with a deep learning approach, a combination of Convolutional Neural Networks (CNN) and Locally Weighted Random Forest (LWRF), were used successfully in disease detection and severity assessment of PD [8].”
InfluentialAn Exploratory Study on Techniques for Quantitative Assessment of Stroke Rehabilitation Exercises
Lee, M. H., Siewiorek, D. P., Smailagic, A., Bernardino, A. J. M., & Badia, S. B. I. (2020) · ACM Conference on User Modeling, Adaptation and Personalization (UMAP) · doi:10.1145/3340631.3394872 · Cited by 25
“…work on modeling and understanding human activities (e.g. exercises) that focuses on improving the performance of a model by applying a complex deep learning model [9, 15, 19], our work highlights the importance on creating an ex-plainable model to support the deployment of a model in practice.”
BackgroundGonzález-Alonso, J., Oviedo-Pastor, D., Aguado, H. J., Pernas, F. J. D., González‐Ortega, D., & Martínez‐Zarzuela, M. (2021) · Sensors · doi:10.3390/s21196642 · Cited by 28
Temporal Feature Alignment in Contrastive Self-Supervised Learning for Human Activity Recognition
Khaertdinov, B., & Asteriadis, S. (2022) · IEEE International Joint Conference on Biometrics (IJCB) · doi:10.1109/ijcb54206.2022.10007984 · Cited by 28
Guo, L., Zhang, B., Wang, J., Wu, Q., Li, X., Zhou, L., & Xiong, D. (2022) · Journal of Clinical Medicine · doi:10.3390/jcm11247467 · Cited by 22
PrimSeq: A deep learning-based pipeline to quantitate rehabilitation training
Parnandi, A., Kaku, A., Venkatesan, A., Pandit, N. G., Wirtanen, A., Rajamohan, H. R., Venkataramanan, K., Nilsen, D. M., Fernandez‐Granda, C., & Schambra, H. M. (2022) · PLOS Digital Health · doi:10.1371/journal.pdig.0000044 · Cited by 24
“This approach uses wearable sensors and deep learning to identify or grade UE joint motions, with the goal of remotely monitoring rehabilitation training or ADL execution at home [21,22].”
Recognizing wearable upper-limb rehabilitation gestures by a hybrid multi-feature neural network
Wang, S., Liu, J., Chen, S., Wang, S., Peng, Y., Liao, C., & Liu, L. (2023) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2023.107424 · Cited by 21
Transferable multi-modal fusion in knee angles and gait phases for their continuous prediction
Guo, Z., Zheng, H., Wu, H., Zhang, J., Zhou, G., & Long, J. (2023) · Journal of Neural Engineering · doi:10.1088/1741-2552/accd22 · Cited by 18
Russell, B. K., McDaid, A., Toscano, W. B., & Hume, P. A. (2021) · Sensors · doi:10.3390/s21020654 · Cited by 20
“Panwar [22] used a wrist sensor to measure reaching tasks on stroke patients, achieving an 88.”
MethodQuantitative Upper Limb Impairment Assessment for Stroke Rehabilitation: A Review
Wang, X., Zhang, J., Xie, S. Q., Shi, C., Li, J., & Zhang, Z. (2024) · IEEE Sensors Journal · doi:10.1109/jsen.2024.3359811 · Cited by 23
“…extract features and classify them from the raw sensor data, and it also has a good performance in the study of quantitative impairment assessment after stroke [111], [112]. b) CNN-based model: CNN could achieve excellent performance in image classification and visual data recognition [111].”
BackgroundZhang, B., Xu, H., Xiong, H., Sun, X., Shi, L., Fan, S., & Li, J. (2020) · Journal of Ambient Intelligence and Humanized Computing · doi:10.1007/s12652-020-02526-6 · Cited by 17
Lee, M. H., Siewiorek, D. P., Smailagic, A., Bernardino, A., & Bermúdez i Badia, S. (2022) · 27th International Conference on Intelligent User Interfaces · doi:10.1145/3490099.3511112 · Cited by 19
“An alternative approach is to utilize machine learning algorithms with labeled sensor data and learn a model to assess the quality of motion [39, 48].”
BackgroundMethodOptimizing Stroke Detection Using Evidential Networks and Uncertainty-Based Refinement
Akbarifar, F., Dukelow, S. P., Jin, A. Y., Mousavi, P., & Scott, S. H. (2025) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2025.3531768 · Cited by 17
Chung, C., Su, M., Lee, S.-H., Wu, E. H., Tang, L.-H., & Yeh, S. (2022) · IEEE Journal of Translational Engineering in Health and Medicine · doi:10.1109/jtehm.2022.3213348 · Cited by 18
Wang, S., Zhang, T., Li, Y., Li, P., Wu, H., & Li, K. (2024) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2024.3440381 · Cited by 16
“Panwar et al. [38] proposed a lightweight DL framework: Rehab Net.”
BackgroundCardioNet: Deep Learning Framework for Prediction of CVD Risk Factors
Panwar, M., Gautam, A., Dutt, R., & Acharyya, A. (2020) · IEEE International Symposium on Circuits and Systems proceedings · doi:10.1109/iscas45731.2020.9180636 · Cited by 20
Self-citationOubre, B., & Lee, S. I. (2023) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2023.3337156 · Cited by 18
“We chose to employ a CNN instead of a recurrent network or transformer because 1) a similar model was validated by prior work [21], 2) P2P movements are brief and thus detection may not significantly benefit from adjacent temporal context, and 3) additional model complexity and a larger parameter…”
MethodInfluentialAdaptive Recognition of Motion Posture in Sports Video Based on Evolution Equation
Yuan, R., Zhang, Z., Le, Y., & Chen, E. (2021) · Advances in Mathematical Physics · doi:10.1155/2021/2148062 · Cited by 15
“[24] divided the acceleration data of the human body into six states according to the characteristics of acceleration.”
BackgroundChang, C.-Y., Hsieh, C.-Y., Huang, H.-Y., Wu, Y., Chen, L., Chan, C.-T., & Liu, K.-C. (2020) · Sensors · doi:10.3390/s21010106 · Cited by 16
“Additionally, diverse deep learning approaches are widely applied to movement segmentation [28] and human activity recognition [29], e.”
BackgroundJiménez‐Grande, D., Atashzar, S. F., Devecchi, V., Martinez‐Valdes, E., & Falla, D. (2022) · Gait & Posture · doi:10.1016/j.gaitpost.2022.05.015 · Cited by 13
Jia, Q., Guo, J. M., Yang, P., & Yang, Y. (2023) · Complex & Intelligent Systems · doi:10.1007/s40747-023-01218-w · Cited by 16
“Due to its real-time characteristic and portability, HAR is widely used in rehabilitation monitoring [2], geriatric monitoring [3], and other fields [4].”
Convolutional neural network in upper limb functional motion analysis after stroke
Szczęsna, A., Błaszczyszyn, M., & Kawala‐Sterniuk, A. (2020) · PeerJ · doi:10.7717/peerj.10124 · Cited by 13
Leng, J., Wang, D., Ma, X., Yu, P. Y., Li, W., & Chen, W. (2022) · Applied Intelligence · doi:10.1007/s10489-022-03222-y · Cited by 14
“Rehabilitation progress Rehabilitation CNN Movement data [16]”
Razfar, N., Kashef, R. F., & Mohammadi, F. A. (2023) · Sensors · doi:10.3390/s23125513 · Cited by 16
SmartCare—A comprehensive wearable sensor-based remote health monitoring and rehabilitation system
Raja, G. B. (2025) · Elsevier eBooks · doi:10.1016/b978-0-443-21505-6.00011-6 · Cited by 13
Artificial Perception of the Beverages: An In-Depth Review of the Tea Sample
Patil, A. B., Bachute, M. R., & Kotecha, K. V. (2021) · IEEE Access · doi:10.1109/access.2021.3086038 · Cited by 12
Vasanthi, S., & Jayasree, T. (2020) · Proceedings of the Institution of Mechanical Engineers Part H Journal of Engineering in Medicine · doi:10.1177/0954411920912119 · Cited by 10
“Panwar et al. 27 presented a two-layer convolution neural network (CNN), a type of deep learning neural network (DLNN) for classifying the upper limb movements of the human arm.”
BackgroundMiao, S. J., Dang, Y., Zhu, Q., Li, S., Shorfuzzaman, M., & Lv, H. (2021) · IEEE Access · doi:10.1109/access.2021.3080592 · Cited by 13
Ventura, R. B., Hughes, K. S., Nov, O., Raghavan, P., Marín, M. R., & Porfiri, M. (2021) · JMIR Serious Games · doi:10.2196/27597 · Cited by 12
“Additional work to recognize upper limb movement was carried out using k-means clustering and convolutional neural networks [68,69].”
MethodPatients Arms Segmentation and Gesture Identification Using Standalone 3-D LiDAR Sensors
Rinchi, O., Nisbett, N., & Alsharoa, A. (2023) · IEEE Sensors Letters · doi:10.1109/lsens.2023.3303081 · Cited by 10
Mourchid, Y., & Slama, R. (2023) · IEEE International Workshop on Multimedia Signal Processing (MMSP) · doi:10.1109/mmsp59012.2023.10337711 · Cited by 10
“Deep learning approaches [5]–[7] , including CNNs, RNNs, and GCNs, have received attention in the physical rehabilitation field for their ability to automatically assess patients’ exercise performance by analyzing sensor data or video footage.”
BackgroundShen, C., Ning, X., Zhu, Q., Miao, S. J., & Lv, H. (2021) · Sustainable Computing Informatics and Systems · doi:10.1016/j.suscom.2021.100624 · Cited by 11
Tiwari, A. K., Pai, A., & Joshi, D. (2020) · Measurement · doi:10.1016/j.measurement.2020.108458 · Cited by 10
Okita, S., Yakunin, R., Korrapati, J., Ibrahim, M., de Lucena, D. S., Chan, V., & Reinkensmeyer, D. J. (2023) · Sensors · doi:10.3390/s23125690 · Cited by 9
“We also compared HARCS to three other machine learning approaches: the support vector machine (SVM), k-nearest neighbor (kNN), and a multi-layer perceptron, following the approaches by [28,29], and implementing the algorithms in scikit-learn [30].”
MethodOh, Y., Choi, S.-A., Shin, Y., Jeong, Y., Lim, J., & Kim, S. (2023) · Sensors · doi:10.3390/s24010210 · Cited by 20
Blood Pressure and Heart Rate Measurements Using Photoplethysmography with Modified LRCN
Mostafa, S. M., Idris, S. A., & Kaur, M. (2021) · Computers, materials & continua/Computers, materials & continua (Print) · doi:10.32604/cmc.2022.022679 · Cited by 9
Towards improved human arm movement analysis: Advanced feature engineering and model optimization
Benachour, Y., Rehman, M. U., & Flitti, F. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.111194 · Cited by 8
Nunes, A. S., Potter, İ. Y., Mishra, R. K., Bonato, P., & Vaziri, A. (2024) · Frontiers in Neurology · doi:10.3389/fneur.2023.1295132 · Cited by 13
A Two-stream Convolutional Network for Musculoskeletal and Neurological Disorders Prediction
Zhu, M., Men, Q., Ho, E. S. L., Leung, H. W. H., & Shum, H. P. H. (2022) · Journal of Medical Systems · doi:10.1007/s10916-022-01857-5 · Cited by 8
“Mixup [26] fits better to our dataset compared to data agumentation methods such as Gaussian noise [27] and SMOTE [28].”
MethodUsing wearable sensors and machine learning to assess upper limb function in Huntington’s disease
Nunes, A. S., Potter, İ. Y., Mishra, R. K., Casado, J., Dana, N., Geronimo, A. M., Tarolli, C. G., Schneider, R. B., Dorsey, E. R., Adams, J., et al. (2025) · Communications Medicine · doi:10.1038/s43856-025-00770-5 · Cited by 13
“Recent advancements in machine learning have propelled the development of robust techniques for automated GDM detection from accelerometer data 23 – 26 .”
Griškevičius, J., Daunoravičienė, K., Petrauskas, L., Apšega, A., & Alekna, V. (2025) · Sensors · doi:10.3390/s25113351 · Cited by 7
“Combining both analyses can enhance understanding of gait characteristics, particularly in pathological conditions like Parkinson’s disease, stroke, or frailty [35–38].”
Razfar, N., Kashef, R. F., & Mohammadi, F. A. (2021) · IEEE International Conference on High Performance Computing and Communications; IEEE International Conference on Smart City; IEEE International Conference on Data Science and Systems (HPCC/SmartCity/DSS) · doi:10.1109/hpcc-dss-smartcity-dependsys53884.2021.00205 · Cited by 9
Grammatical Evolution-Based Feature Extraction for Hemiplegia Type Detection
Christou, V., Tsoulos, I. G., Arjmand, A., Dimopoulos, D., Varvarousis, D., Tzallas, A. T., Gogos, C., Tsipouras, M. G., Glavas, E., Ploumis, A., et al. (2022) · Signals · doi:10.3390/signals3040044 · Cited by 6
“Panwar et al. [44] created a framework based on deep learning that can classify three upper limb arm movements (extension, flexion, and forearm rotation).”
Classification of Human Movements with Motion Capture Data in a Motor Rehabilitation Context
Rodrigues, L. G. S., Dias, D. R. C., Guimarães, M. D. P., Brandão, A. F., da Rocha, L. C. D., Iope, R. L., & Brega, J. R. F. (2021) · Symposium on Virtual and Augmented Reality (SVR) · doi:10.1145/3488162.3488210 · Cited by 6
“Similarly, Panwar et al. [19] developed a movement classification model using a wearable sensor that provides 3D information at a particular frequency, and this data stream is also reduced.”
BackgroundMethodStructure, sensing and control of pneumatic upper limb rehabilitation system: Review and prospect
Zhang, Y., Zhang, S., Cai, M., Shi, Y. X., Yu, Q., Wei, F., Li, S., & Liu, C. (2025) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2025.110714 · Cited by 5
Exercise Monitoring and Assessment System for Home-Based Respiratory Rehabilitation
Fan, D., Yang, X., Zhao, N., Guan, L., & Abbasi, Q. H. (2022) · IEEE Sensors Journal · doi:10.1109/jsen.2022.3200984 · Cited by 6
“uate rehabilitation exercises for the shoulder [10], [11], upper 67 limb [12], [13], and lower limb exercises [14].”
BackgroundZhang, W. (2025) · ITM Web of Conferences · doi:10.1051/itmconf/20257002025 · Cited by 6
Evaluation of Physiotherapy Exercise by Motion Capturing Based on Artificial Intelligence: A Review
Abdullah, N. Y., & Alkazzaz, S. A. (2023) · Maǧallaẗ al-handasaẗ al-rāfidayn · doi:10.33899/rengj.2023.138562.1235 · Cited by 9
“Several studies [70], [75]-[79] have been developing automated systems to assess the rehabilitation of Parkinson's and stroke patients.”
BackgroundDeep learning in disability research: A bibliometric analysis
Khan, H., Sohail, S. S., Madsen, D. Ø., & Nafis, M. T. (2025) · Digital engineering. · doi:10.1016/j.dte.2025.100046 · Cited by 6
Cui, M., Poovendran, P., & Stewart Kirubakaran, S. (2021) · Technology and Health Care · doi:10.3233/thc-213007 · Cited by 9
Oh, Y., Choi, S.-A., Shin, Y., Jeong, Y., Lim, J., & Kim, S. (2023) · doi:10.2196/preprints.53479 · Cited by 5
Klamroth-Marganska, V., Giovanoli, S., Easthope, C. A., & Schönhammer, J. G. (2022) · Springer eBooks · doi:10.1007/978-3-031-08995-4_25 · Cited by 6
Joshi, D. K., Yadao, S., Das, P., Bhange, P., Pandu, S. K., Mankari, K., Sridhar, K., Acharyya, S. G., & Acharyya, A. (2023) · IEEE International Ultrasonics Symposium · doi:10.1109/ius51837.2023.10306380 · Cited by 4
“Specifically, the field of fault detection, diagnostics, and classification has embraced the effectiveness of Deep Neural Networks (DNNs) with relevant examples in the literature [14]–[17].”
BackgroundSelf-citationPanwar, M., Hari, N. S., Biswas, D., & Acharyya, A. (2020) · Circuits Systems and Signal Processing · doi:10.1007/s00034-020-01534-3 · Cited by 4
“TheseIoTdevicesareusuallybatterypowered orrelyonenergyharvester,havinglimitedenergysourcesowingtolowcostand portabilityissues[8,10,28].”
Self-citationSensing Technologies for Hand Gesture Recognition in Human–Robot Interaction: A Review
Liang, B., Li, N., Li, G., Huang, J., Yu, Z., & Zhao, X. (2025) · IEEE Sensors Journal · doi:10.1109/jsen.2025.3635622 · Cited by 5
“D images to effectively process diverse sensor data, including using 1D-CNNs for IMU signals [108], 3D-CNNs to capture the temporal evolution of EMG images [109], and multistream architectures for hierarchical feature fusion [110].”
Metadata
- Authors
- Panwar, M., Biswas, D., Bajaj, H., Jobges, M., Turk, R., Maharatna, K., & Acharyya, A.
- Affiliations
- Indian Institute of Technology Hyderabad (IN)
- IMEC (BE)
- National Institute of Technology Tiruchirappalli (IN)
- University of Southampton (GB)
- Venue
- IEEE Transactions on Biomedical Engineering
- Published
- 2019-11
- Volume
- 66
- Issue
- 11
- Pages
- 3026-3037
- ISSN
- 0018-9294 (ISSN-L)
- 1558-2531
- OpenAlex
- W2916879374
- Cited by
- 158
- References
- 62
- Citations by year
- 2026: 9 · 2025: 22 · 2024: 26 · 2023: 24 · 2022: 28 · 2021: 29 · 2020: 18 · 2019: 2
- FWCI
- 8.62
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- Locations
- IEEE Transactions on Biomedical Engineering (publishedVersion)
- PubMed (publishedVersion)
- ePrints Soton (University of Southampton) (acceptedVersion)
- Research Archive of Indian Institute of Technology Hyderabad (Indian Institute of Technology Hyderabad) (submittedVersion)
- Funders
- Science and Engineering Research Board (ECR/2015/000148)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Context-Aware Activity Recognition Systems
- Health Sciences › Medicine › Rehabilitation › Stroke Rehabilitation and Recovery
- Life Sciences › Neuroscience › Cognitive Neuroscience › EEG and Brain-Computer Interfaces
- Keywords
- stroke rehabilitation, upper limb movement classification, wearable sensors, triaxial accelerometer, convolutional neural networks, rehabilitation progress monitoring, outpatient rehabilitation, forearm rotation
- MeSH terms
- Stroke Rehabilitation, Wearable Electronic Devices, Deep Learning, Aged, Algorithms, Arm, Female, Humans, Human Activities, Male, Middle Aged, Movement, Cluster Analysis, Support Vector Machine
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.
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.