{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T10:30:28Z","timestamp":1774002628184,"version":"3.50.1"},"reference-count":49,"publisher":"PeerJ","license":[{"start":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T00:00:00Z","timestamp":1773964800000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"abstract":"<jats:p>Robot vision is one of the viable technologies for health-hazardous situations. Robots are good coworkers of humans. So, human action recognition is one of the focused areas of Robot vision. The more accurate identification during a medical emergency is a very crucial issue. For identification accuracy, the current empirical research study considers a novel approach. This study proposes a novel fusion framework model based on Convolutional Neural Network and Recurrent Neural Network to identify and classify health-hazardous situations through human actions. A novel technique of the Modular key frame selection is proposed to bring innovation to the research. To verify the effectiveness of the proposed model, experiments are performed on datasets of the NTU RGBD-60 Skeleton dataset. The research observes and compares the effect of key frame selection on the recognition of actions during medical emergencies by considering the least available frames frequently. To the best of our knowledge, the key frame selection is never considered for action recognition of medical situations. By focusing on this vital issue, observation of key frame selection is conducted precisely. The features have been extracted in three different frame rates per second 3 fps, 6 fps, and 10 fps. While the data is available in 30 fps originally, the results of the empirical study reveal the impact of key frame selection on Skeleton data. The empirical study results from 90.56, 91.12, and 92.01, respectively. In comparison with state-of-the-art research, the current empirical study findings are much better for accurate classification, in circumstances when the data is not available in a constant fashion.<\/jats:p>","DOI":"10.7717\/peerj-cs.2859","type":"journal-article","created":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T08:00:21Z","timestamp":1773993621000},"page":"e2859","source":"Crossref","is-referenced-by-count":0,"title":["Key frame snippet influence on Robot vision in health hazardous circumstances using modular skeleton joints sampling technique"],"prefix":"10.7717","volume":"12","author":[{"given":"Saima","family":"Sultana","sequence":"first","affiliation":[{"name":"Malaysian Institute of Information Technology, Universiti Kuala Lumpur, Kuala Lumpur, Malaysia"},{"name":"College of Computer Science and Information Systems, Institute of Business Management, Karachi, Pakistan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Muhammad Mansoor","family":"Alam","sequence":"additional","affiliation":[{"name":"Faculty of Computing, Riphah International University, Islamabad, Islamabad, FATA, Pakistan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7745-9667","authenticated-orcid":true,"given":"Mukesh","family":"Prasad","sequence":"additional","affiliation":[{"name":"Faculty of Engineering and IT, University of Technology Sydney, Sydney, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jawahir Che","family":"Mustapha","sequence":"additional","affiliation":[{"name":"Malaysian Institute of Information Technology, Universiti Kuala Lumpur, Kuala Lumpur, Malaysia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-6046-469X","authenticated-orcid":true,"given":"Mazliham Mohd","family":"Su ud","sequence":"additional","affiliation":[{"name":"Department of Information Technology, Multimedia University, Cyberjaya, Kuala Lumpur, Malaysia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"4443","published-online":{"date-parts":[[2026,3,20]]},"reference":[{"issue":"6","key":"10.7717\/peerj-cs.2859\/ref-1","doi-asserted-by":"publisher","first-page":"1433","DOI":"10.1109\/tmm.2019.2944745","article-title":"2D pose-based real-time human action recognition with occlusion-handling","volume":"22","author":"Angelini","year":"2020","journal-title":"IEEE Transactions on Multimedia"},{"issue":"1","key":"10.7717\/peerj-cs.2859\/ref-2","doi-asserted-by":"publisher","first-page":"106324","DOI":"10.1016\/j.cmpb.2021.106324","article-title":"Postural control assessment via Microsoft Azure Kinect DK: an evaluation study","volume":"209","author":"Antico","year":"2021","journal-title":"Computer Methods and Programs in Biomedicine"},{"issue":"12","key":"10.7717\/peerj-cs.2859\/ref-3","doi-asserted-by":"publisher","first-page":"3601","DOI":"10.1007\/s13042-019-00947-0","article-title":"Multi-level features fusion and selection for human gait recognition: an optimized framework of Bayesian model and binomial distribution","volume":"10","author":"Arshad","year":"2019","journal-title":"International Journal of Machine Learning and Cybernetics"},{"issue":"3","key":"10.7717\/peerj-cs.2859\/ref-4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3377552","article-title":"Learning three-dimensional skeleton data from sign language video","volume":"11","author":"Brock","year":"2020","journal-title":"ACM Transactions on Intelligent Systems and Technology (TIST)"},{"issue":"3","key":"10.7717\/peerj-cs.2859\/ref-5","doi-asserted-by":"publisher","first-page":"3522","DOI":"10.1109\/tpami.2022.3177813","article-title":"MMNet: a model-based multimodal network for human action recognition in RGB-D videos","volume":"45","author":"Bruce","year":"2022","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"10","key":"10.7717\/peerj-cs.2859\/ref-6","doi-asserted-by":"publisher","first-page":"564","DOI":"10.1145\/360349.360357","article-title":"Interactive skeleton techniques for enhancing motion dynamics in key frame animation","volume":"19","author":"Burtnyk","year":"1976","journal-title":"Communications of the ACM"},{"key":"10.7717\/peerj-cs.2859\/ref-7","doi-asserted-by":"crossref","DOI":"10.1109\/ICCVW.2013.19","article-title":"Fusion of skeletal and silhouette-based features for human action recognition with RGB-D devices","author":"Chaaraoui","year":"2013"},{"issue":"4","key":"10.7717\/peerj-cs.2859\/ref-8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s40747-024-01403-5","article-title":"An optimization method of human skeleton keyframes selection for action recognition","volume":"10","author":"Chen","year":"2024","journal-title":"Complex & Intelligent Systems"},{"key":"10.7717\/peerj-cs.2859\/ref-9","doi-asserted-by":"publisher","first-page":"168297\u2013168308","DOI":"10.1109\/access.2020.3023599","article-title":"Infrared and 3D skeleton feature fusion for RGB-D action recognition","volume":"8","author":"De Boissiere","year":"2020","journal-title":"IEEE Access"},{"issue":"4","key":"10.7717\/peerj-cs.2859\/ref-10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3657030","article-title":"A survey of multimodal perception methods for human\u2013robot interaction in social environments","volume":"13","author":"Duncan","year":"2024","journal-title":"ACM Transactions on Human\u2013Robot Interaction"},{"issue":"1","key":"10.7717\/peerj-cs.2859\/ref-11","doi-asserted-by":"publisher","first-page":"97","DOI":"10.5566\/ias.3087","article-title":"Advancing fall detection utilizing skeletal joint image representation and deformable layers","volume":"43","author":"Erg\u00fcder","year":"2024","journal-title":"Image Analysis and Stereology"},{"issue":"6","key":"10.7717\/peerj-cs.2859\/ref-12","doi-asserted-by":"publisher","first-page":"429","DOI":"10.1007\/s42979-021-00814-2","article-title":"Smoothing skeleton avatar visualizations using signal processing technology","volume":"2","author":"Gauss","year":"2021","journal-title":"SN Computer Science"},{"issue":"19","key":"10.7717\/peerj-cs.2859\/ref-13","doi-asserted-by":"publisher","first-page":"8982","DOI":"10.1007\/s10489-024-05645-1","article-title":"Deep learning for computer vision based activity recognition and fall detection of the elderly: a systematic review","volume":"54","author":"Gaya-Morey","year":"2024","journal-title":"Applied Intelligence"},{"key":"10.7717\/peerj-cs.2859\/ref-14","doi-asserted-by":"crossref","DOI":"10.1145\/3453892.3461337","article-title":"A study on the effect of occlusion in human activity recognition","author":"Giannakos","year":"2021"},{"key":"10.7717\/peerj-cs.2859\/ref-15","doi-asserted-by":"publisher","DOI":"10.1109\/MAPR.2019.8743545","article-title":"3D skeleton-based action recognition with convolutional neural networks","author":"Hoang","year":"2019"},{"issue":"4","key":"10.7717\/peerj-cs.2859\/ref-16","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2897824.2925975","article-title":"A deep learning framework for character motion synthesis and editing","volume":"35","author":"Holden","year":"2016","journal-title":"ACM Transactions on Graphics (TOG)"},{"issue":"20","key":"10.7717\/peerj-cs.2859\/ref-17","doi-asserted-by":"publisher","first-page":"16868","DOI":"10.1109\/access.2024.3359234","article-title":"Multi-scale adaptive graph convolution network for skeleton-based action recognition","volume":"12","author":"Hu","year":"2024","journal-title":"IEEE Access"},{"key":"10.7717\/peerj-cs.2859\/ref-18","doi-asserted-by":"crossref","DOI":"10.1109\/IROS45743.2020.9341160","article-title":"ETRI-Activity3D: a large-scale RGB-D dataset for robots to recognize daily activities of the elderly","author":"Jang","year":"2020"},{"issue":"3","key":"10.7717\/peerj-cs.2859\/ref-19","doi-asserted-by":"publisher","first-page":"2995","DOI":"10.32604\/csse.2023.036778","article-title":"A novel computationally efficient approach to identify visually interpretable medical conditions from 2D skeletal data","volume":"46","author":"Jesudhas","year":"2023","journal-title":"Computer Systems Science & Engineering"},{"key":"10.7717\/peerj-cs.2859\/ref-20","doi-asserted-by":"publisher","first-page":"104928","DOI":"10.1016\/j.imavis.2024.104928","article-title":"Deep learning methods for single camera based clinical in-bed movement action recognition","volume":"143","author":"Kar\u00e1csony","year":"2024","journal-title":"Image and Vision Computing"},{"issue":"11","key":"10.7717\/peerj-cs.2859\/ref-21","doi-asserted-by":"publisher","first-page":"113045","DOI":"10.1016\/j.knosys.2025.113045","article-title":"AGMS-GCN: attention-guided multi-scale graph convolutional networks for skeleton-based action recognition","volume":"311","author":"Kilic","year":"2025","journal-title":"Knowledge-Based Systems"},{"key":"10.7717\/peerj-cs.2859\/ref-22","doi-asserted-by":"crossref","DOI":"10.1109\/EMBC46164.2021.9630438","article-title":"Vision-based human joint angular velocity estimation during squat and walking on a treadmill actions","author":"Kumar","year":"2021"},{"issue":"11","key":"10.7717\/peerj-cs.2859\/ref-23","doi-asserted-by":"publisher","first-page":"5455","DOI":"10.3390\/app12115455","article-title":"KFSENet: a key frame-based skeleton feature estimation and action recognition network for improved robot vision with face and emotion recognition","volume":"12","author":"Le","year":"2022","journal-title":"Applied Sciences"},{"key":"10.7717\/peerj-cs.2859\/ref-24","doi-asserted-by":"publisher","DOI":"10.48550\/arxiv.2310.03288","article-title":"PoseAction: action recognition for patients in the ward using deep learning approaches","author":"Li","year":"2023"},{"key":"10.7717\/peerj-cs.2859\/ref-25","article-title":"Comparison of activity recognition using 2D and 3D skeletal joint data","author":"Marshall","year":"2019"},{"issue":"4","key":"10.7717\/peerj-cs.2859\/ref-26","doi-asserted-by":"publisher","first-page":"108482","DOI":"10.1016\/j.chb.2024.108482","article-title":"Extended multi-stream temporal-attention module for skeleton-based human action recognition (HAR)","volume":"163","author":"Mehmood","year":"2025","journal-title":"Computers in Human Behavior"},{"key":"10.7717\/peerj-cs.2859\/ref-27","article-title":"Deep learning for skeletal character animation: topology editing, retargeting and cleaning","author":"Mourot","year":"2023"},{"key":"10.7717\/peerj-cs.2859\/ref-28","doi-asserted-by":"publisher","first-page":"4","DOI":"10.22967\/HCIS.2024.14.004","article-title":"Attention-based deep learning framework for action recognition in a dark environment","volume":"14","author":"Munsif","year":"2024","journal-title":"Human-Centric Computing and Information Sciences"},{"key":"10.7717\/peerj-cs.2859\/ref-29","doi-asserted-by":"publisher","first-page":"1203901","DOI":"10.3389\/fcomp.2023.1203901","article-title":"SKELTER: unsupervised skeleton action denoising and recognition using transformers","volume":"5","author":"Paoletti","year":"2023","journal-title":"Frontiers in Computer Science"},{"key":"10.7717\/peerj-cs.2859\/ref-30","doi-asserted-by":"crossref","DOI":"10.1109\/RIVF51545.2021.9642132","article-title":"Key frame and skeleton extraction for deep learning-based human action recognition","author":"Phan","year":"2021"},{"issue":"5","key":"10.7717\/peerj-cs.2859\/ref-31","doi-asserted-by":"publisher","first-page":"650","DOI":"10.1109\/thms.2014.2325871","article-title":"Human action recognition with video data: research and evaluation challenges","volume":"44","author":"Ramanathan","year":"2014","journal-title":"IEEE Transactions on Human\u2013Machine Systems"},{"issue":"11","key":"10.7717\/peerj-cs.2859\/ref-32","doi-asserted-by":"publisher","first-page":"e0100","DOI":"10.34133\/cbsystems.0100","article-title":"A survey on 3D skeleton-based action recognition using learning method","volume":"5","author":"Ren","year":"2024","journal-title":"Cyborg and Bionic Systems"},{"issue":"2","key":"10.7717\/peerj-cs.2859\/ref-33","doi-asserted-by":"publisher","first-page":"133","DOI":"10.1007\/s42979-025-03660-8","article-title":"TriModNet: a hybrid view-invariant three-pronged model for patient activity monitoring in indoor environment","volume":"6","author":"Sain","year":"2025","journal-title":"SN Computer Science"},{"key":"10.7717\/peerj-cs.2859\/ref-34","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR.2008.4587730","article-title":"Action snippets: how many frames does human action recognition require?","author":"Schindler","year":"2008"},{"key":"10.7717\/peerj-cs.2859\/ref-35","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR.2016.115","article-title":"NTU RGB+D: a large scale dataset for 3D human activity analysis","author":"Shahroudy","year":"2016"},{"issue":"10","key":"10.7717\/peerj-cs.2859\/ref-36","doi-asserted-by":"publisher","first-page":"2986","DOI":"10.1109\/tcsvt.2018.2871660","article-title":"A hierarchical model for human action recognition from body-parts","volume":"29","author":"Shao","year":"2018","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"10.7717\/peerj-cs.2859\/ref-37","article-title":"A hybrid deep learning approach for human action recognition","author":"Stylianou-Nikolaidou","year":"2021"},{"key":"10.7717\/peerj-cs.2859\/ref-38","doi-asserted-by":"publisher","first-page":"2134","DOI":"10.1109\/tnsre.2024.3409197","article-title":"A rapid response system for elderly safety monitoring using progressive hierarchical action recognition","volume":"32","author":"Sun","year":"2024","journal-title":"IEEE Transactions on Neural Systems and Rehabilitation Engineering"},{"issue":"3","key":"10.7717\/peerj-cs.2859\/ref-39","doi-asserted-by":"publisher","first-page":"49","DOI":"10.3390\/inventions5030049","article-title":"Deep learning-based action recognition using 3D skeleton joints information","volume":"5","author":"Tasnim","year":"2020","journal-title":"Inventions"},{"issue":"2","key":"10.7717\/peerj-cs.2859\/ref-40","doi-asserted-by":"publisher","first-page":"286","DOI":"10.4218\/etrij.2020-0101","article-title":"Three-dimensional human activity recognition by forming a movement polygon using posture skeletal data from depth sensor","volume":"44","author":"Vishwakarma","year":"2022","journal-title":"ETRI Journal"},{"key":"10.7717\/peerj-cs.2859\/ref-41","doi-asserted-by":"publisher","DOI":"10.48550\/arxiv.2112.12668","article-title":"3D skeleton-based few-shot action recognition with JEANIE is not so Na\u00efve","author":"Wang","year":"2021"},{"issue":"11","key":"10.7717\/peerj-cs.2859\/ref-42","doi-asserted-by":"publisher","first-page":"110427","DOI":"10.2139\/ssrn.4498134","article-title":"Spatial-temporal hypergraph based on dual-stage attention network for multi-view data lightweight action recognition","volume":"151","author":"Wu","year":"2024","journal-title":"Pattern Recognition"},{"key":"10.7717\/peerj-cs.2859\/ref-43","doi-asserted-by":"publisher","DOI":"10.48550\/arxiv.2309.15635","article-title":"Position and orientation-aware one-shot learning for medical action recognition from signal data","author":"Xie","year":"2023"},{"issue":"2","key":"10.7717\/peerj-cs.2859\/ref-44","doi-asserted-by":"publisher","first-page":"877","DOI":"10.1007\/s00500-021-06238-7","article-title":"Skeleton-based human activity recognition using ConvLSTM and guided feature learning","volume":"26","author":"Yadav","year":"2022","journal-title":"Soft Computing"},{"issue":"8","key":"10.7717\/peerj-cs.2859\/ref-45","doi-asserted-by":"publisher","first-page":"2226","DOI":"10.3390\/s20082226","article-title":"Keys for action: an efficient keyframe-based approach for 3D action recognition using a deep neural network","volume":"20","author":"Yasin","year":"2020","journal-title":"Sensors"},{"key":"10.7717\/peerj-cs.2859\/ref-46","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1109\/BIOCAS.2019.8919161","article-title":"A skeleton-based action recognition system for medical condition detection","author":"Yin","year":"2019"},{"issue":"4","key":"10.7717\/peerj-cs.2859\/ref-47","doi-asserted-by":"publisher","first-page":"1189","DOI":"10.3390\/s24041189","article-title":"Advancing human motion recognition with skeletonCLIP++: weighted video feature integration and enhanced contrastive sample discrimination","volume":"24","author":"Yuan","year":"2024","journal-title":"Sensors"},{"issue":"1","key":"10.7717\/peerj-cs.2859\/ref-48","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1097\/nr9.0000000000000052","article-title":"Aging with robots: a brief review on eldercare automation","volume":"3","author":"Zhang","year":"2024","journal-title":"Interdisciplinary Nursing Research"},{"key":"10.7717\/peerj-cs.2859\/ref-49","doi-asserted-by":"publisher","first-page":"11733","DOI":"10.1109\/access.2024.3353622","article-title":"3D graph convolutional feature selection and dense pre-estimation for skeleton action recognition","volume":"12","author":"Zhang","year":"2024","journal-title":"IEEE Access"}],"container-title":["PeerJ Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/peerj.com\/articles\/cs-2859.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-2859.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-2859.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-2859.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T08:00:32Z","timestamp":1773993632000},"score":1,"resource":{"primary":{"URL":"https:\/\/peerj.com\/articles\/cs-2859"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,20]]},"references-count":49,"alternative-id":["10.7717\/peerj-cs.2859"],"URL":"https:\/\/doi.org\/10.7717\/peerj-cs.2859","archive":["CLOCKSS","LOCKSS","Portico"],"relation":{},"ISSN":["2376-5992"],"issn-type":[{"value":"2376-5992","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,20]]},"article-number":"e2859"}}