{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,4]],"date-time":"2025-10-04T04:43:20Z","timestamp":1759553000870,"version":"build-2065373602"},"reference-count":44,"publisher":"MDPI AG","issue":"19","license":[{"start":{"date-parts":[[2025,10,2]],"date-time":"2025-10-02T00:00:00Z","timestamp":1759363200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Council for Science, Technology and Innovation, \u201cCross-ministerial Strategic Innovation Promotion Program"},{"DOI":"10.13039\/501100003051","name":"NEDO","doi-asserted-by":"crossref","award":["JPJ012495"],"award-info":[{"award-number":["JPJ012495"]}],"id":[{"id":"10.13039\/501100003051","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["www.mdpi.com"],"crossmark-restriction":true},"short-container-title":["Sensors"],"abstract":"<jats:p>Lower limb functional degeneration has become prevalent, notably reducing the core strength that drives motor control. Squats are frequently used in lower limb training, improving overall muscle strength. However, performing continuously with improper techniques can lead to dynamic knee instability. It worsens with little to no motivation to perform these power training motions. Hence, it is crucial to have a gaming-based exercise tracking system to adaptively enhance the user experience without causing injury or falls. In this work, 28 healthy subjects performed exergame-based squat training, and dynamic kinematic features were recorded. The five features acquired from a depth camera-based inertial measurement unit (IMU) (1\u2014Knee shakiness, 2\u2014Knee distance, and 3\u2014Squat depth) and an Anima forceplate sensor (4\u2014Sway velocity and 5\u2014Sway area) were assessed using a Spearman correlation coefficient-based feature selection method. An input vector that defines knee instability is used to train and test the Long Short-Term Memory (LSTM) and Support Vector Machine (SVM) models for binary classification. The results showed that knee instability events can be successfully classified and achieved a high accuracy of 96% in both models with sets 1, 2, 3, 4, and 5 and 1, 2, and 3. The feature selection results indicate that the LSTM network with the proposed combination of input features from multimodal sensors can successfully perform real-time tracking of knee instability. Furthermore, the findings demonstrate that this multimodal approach yields improved classifier performance with enhanced accuracy compared to using features from a single modality during lower limb therapy.<\/jats:p>","DOI":"10.3390\/s25196074","type":"journal-article","created":{"date-parts":[[2025,10,3]],"date-time":"2025-10-03T07:57:27Z","timestamp":1759478247000},"page":"6074","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Preliminary Data-Driven Approach for Classifying Knee Instability During Subject-Specific Exercise-Based Game with Squat Motions"],"prefix":"10.3390","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2602-6498","authenticated-orcid":false,"given":"Priyanka","family":"Ramasamy","sequence":"first","affiliation":[{"name":"Graduate School of Advanced Science and Engineering, Hiroshima University, Hiroshima 739-8527, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2272-657X","authenticated-orcid":false,"given":"Poongavanam","family":"Palani","sequence":"additional","affiliation":[{"name":"Department of Engineering Design, Indian Institute of Technology Madras, Tamil Nadu 600-036, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0095-2808","authenticated-orcid":false,"given":"Gunarajulu","family":"Renganathan","sequence":"additional","affiliation":[{"name":"Cyber Physical Systems, Graduate School of Innovation and Practice for Smart Society, Hiroshima University, Hiroshima 739-8529, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1875-6071","authenticated-orcid":false,"given":"Koji","family":"Shimatani","sequence":"additional","affiliation":[{"name":"Department of Physical Therapy, Prefectural University of Hiroshima, Hiroshima 723-0053, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5474-3999","authenticated-orcid":false,"given":"Asokan","family":"Thondiyath","sequence":"additional","affiliation":[{"name":"Department of Engineering Design, Indian Institute of Technology Madras, Tamil Nadu 600-036, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7848-1460","authenticated-orcid":false,"given":"Yuichi","family":"Kurita","sequence":"additional","affiliation":[{"name":"Graduate School of Advanced Science and Engineering, Hiroshima University, Hiroshima 739-8527, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2025,10,2]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"1577","DOI":"10.1093\/gerona\/glab250","article-title":"Changes in the hierarchy of functional impairment from middle age to older age","volume":"77","author":"Brown","year":"2022","journal-title":"J. Gerontol. Ser. A"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"e38703","DOI":"10.2196\/38703","article-title":"Development of a novel home-based Exergame with on-body feedback: Usability study","volume":"10","author":"Pickles","year":"2022","journal-title":"JMIR Serious Games"},{"key":"ref_3","unstructured":"Rusu, L., Mocanu, I., Jecan, S., and Sitar, D. (2016). Monitoring adaptive exergame for seniors. J. Inf. Syst. Oper. Manag., 336."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Gerling, K.M., Schild, J., and Masuch, M. (2010, January 17\u201319). Exergame design for elderly users: The case study of SilverBalance. Proceedings of the 7th International Conference on Advances in Computer Entertainment Technology, Taipei, Taiwan.","DOI":"10.1145\/1971630.1971650"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Zhang, H., Miao, C., Wu, Q., Tao, X., and Shen, Z. (2019). The effect of familiarity on older adults\u2019 engagement in exergames. Human Aspects of IT for the Aged Population. Social Media, Games and Assistive Environments, Proceedings of the 5th International Conference, ITAP 2019, Held as Part of the 21st HCI International Conference, HCII 2019, Orlando, FL, USA, 26\u201331 July 2019, Springer. Proceedings, Part II 21.","DOI":"10.1007\/978-3-030-22015-0_22"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Sinclair, J., Hingston, P., and Masek, M. (2007, January 1\u20134). Considerations for the design of exergames. Proceedings of the 5th International Conference on Computer Graphics and Interactive Techniques in Australia and Southeast Asia, Perth, Australia.","DOI":"10.1145\/1321261.1321313"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"2829","DOI":"10.1519\/JSC.0b013e318267918b","article-title":"Comparison of the angles and corresponding moments in the knee and hip during restricted and unrestricted squats","volume":"26","author":"Lorenzetti","year":"2012","journal-title":"J. Strength Cond. Res."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1097\/00005768-200101000-00020","article-title":"Knee biomechanics of the dynamic squat exercise","volume":"33","author":"Escamilla","year":"2001","journal-title":"Med. Sci. Sport. Exerc."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"1552","DOI":"10.1097\/00005768-200109000-00020","article-title":"Effects of technique variations on knee biomechanics during the squat and leg press","volume":"33","author":"Escamilla","year":"2001","journal-title":"Med. Sci. Sport. Exerc."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"363","DOI":"10.1080\/15438627.2022.2113879","article-title":"Knee wobbling during the single-leg-squat-and-hold test reflects dynamic knee instability in patients with anterior cruciate ligament injury","volume":"32","author":"He","year":"2024","journal-title":"Res. Sport. Med."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"30","DOI":"10.1080\/23335432.2021.1936175","article-title":"Detection of knee wobbling as a screen to identify athletes who may be at high risk for ACL injury","volume":"8","author":"Aoki","year":"2021","journal-title":"Int. Biomech."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Ramasamy, P., Das, S., and Kurita, Y. (2021, January 24\u201329). Ski for squat: A squat exergame with pneumatic gel muscle-based dynamic difficulty adjustment. Proceedings of the International Conference on Human-Computer Interaction, Virtual Event.","DOI":"10.1007\/978-3-030-78095-1_33"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"6371","DOI":"10.1109\/LRA.2023.3306285","article-title":"Force Feedback-Based Gamification: Performance Validation of Squat Exergame Using Pneumatic Gel Muscles and Dynamic Difficulty Adjustment","volume":"8","author":"Ramasamy","year":"2023","journal-title":"IEEE Robot. Autom. Lett."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Okumura, T., and Kurita, Y. (2021). Cross-modal effect of presenting visual and force feedback that create the illusion of stair-climbing. Appl. Sci., 11.","DOI":"10.3390\/app11072987"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Zapata, B., Narv\u00e1ez, F., Garc\u00eda, M.T., and Zapata, D. (2023, January 26\u201328). Automatic Classification of Squat Execution Based on Inertial Sensors and Machine Learning. Proceedings of the International Conference on Science, Technology and Innovation for Society, Guayaquil, Ecuador.","DOI":"10.1007\/978-3-031-52090-7_28"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Liu, H. (2023). Value evaluation of knee joint sports injury detection model-aided diagnosis based on machine learning. Front. Phys., 11.","DOI":"10.3389\/fphy.2023.1166275"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Girase, H., Nyayapati, P., Booker, J., Lotz, J.C., Bailey, J.F., and Matthew, R.P. (2021). Automated assessment and classification of spine, hip, and knee pathologies from sit-to-stand movements collected in clinical practice. J. Biomech., 128.","DOI":"10.1016\/j.jbiomech.2021.110786"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Taborri, J., Molinaro, L., Santospagnuolo, A., Vetrano, M., Vulpiani, M.C., and Rossi, S. (2021). A machine-learning approach to measure the anterior cruciate ligament injury risk in female basketball players. Sensors, 21.","DOI":"10.3390\/s21093141"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"95","DOI":"10.1186\/s13634-021-00796-6","article-title":"The impact of feature extraction and selection for the classification of gait patterns between ACL deficient and intact knees based on different classification models","volume":"2021","author":"Zeng","year":"2021","journal-title":"EURASIP J. Adv. Signal Process."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Vijayvargiya, A., Kumar, R., Dey, N., and Tavares, J.M.R. (2020, January 30\u201331). Comparative analysis of machine learning techniques for the classification of knee abnormality. Proceedings of the 2020 IEEE 5th International Conference on Computing Communication and Automation (ICCCA), Greater Noida, India.","DOI":"10.1109\/ICCCA49541.2020.9250799"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Liu, B., Chen, Z., and Hu, Y. (2020, January 20\u201322). Lower limb motion recognition by integrating multi-modal features based on machine learning method. Proceedings of the 4th International Conference on Computer Science and Application Engineering, Sanya, China.","DOI":"10.1145\/3424978.3425120"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Moghadam, S.M., Yeung, T., and Choisne, J. (2023). A comparison of machine learning models\u2019 accuracy in predicting lower-limb joints\u2019 kinematics, kinetics, and muscle forces from wearable sensors. Sci. Rep., 13.","DOI":"10.1038\/s41598-023-31906-z"},{"key":"ref_23","first-page":"74","article-title":"Development of squat posture guidance system using kinect and wii balance board","volume":"17","author":"Oh","year":"2019","journal-title":"J. Inf. Commun. Converg. Eng."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"1087","DOI":"10.1007\/s11760-022-02315-y","article-title":"sEMG-based deep learning framework for the automatic detection of knee abnormality","volume":"17","author":"Vijayvargiya","year":"2023","journal-title":"Signal, Image Video Process."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Narayan, J., Johri, S., and Dwivedy, S.K. (2022). LSTM neural network-based classification of sensory signals for healthy and unhealthy gait assessment. Predictive Modeling in Biomedical Data Mining and Analysis, Elsevier.","DOI":"10.1016\/B978-0-323-99864-2.00010-X"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"98","DOI":"10.1007\/s44196-023-00280-z","article-title":"Motion tracking in diagnosis: Gait disorders classification with a dual-head attentional transformer-LSTM","volume":"16","author":"Shayestegan","year":"2023","journal-title":"Int. J. Comput. Intell. Syst."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"47","DOI":"10.1016\/j.cag.2018.08.003","article-title":"Classification of motor errors to provide real-time feedback for sports coaching in virtual reality\u2014A case study in squats and Tai Chi pushes","volume":"76","author":"Hammer","year":"2018","journal-title":"Comput. Graph."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"106551","DOI":"10.1016\/j.ssci.2024.106551","article-title":"Fall-risk assessment of aged workers using wearable inertial measurement units based on machine learning","volume":"176","author":"Kou","year":"2024","journal-title":"Saf. Sci."},{"key":"ref_29","first-page":"23","article-title":"Control strategies and artificial intelligence in rehabilitation robotics","volume":"36","author":"Novak","year":"2015","journal-title":"Ai Mag."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Tadayon, R., Vega Ramirez, A., Das, S., Kishishita, Y., Yamamoto, M., and Kurita, Y. (2019). Automatic exercise assistance for the elderly using real-time adaptation to performance and affect. Universal Access in Human-Computer Interaction. Multimodality and Assistive Environments, Proceedings of the 13th International Conference, UAHCI 2019, Held as Part of the 21st HCI International Conference, HCII 2019, Orlando, FL, USA, 26\u201331 July 2019, Springer. Proceedings, Part II 21.","DOI":"10.1007\/978-3-030-23563-5_44"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Cary, F., Postolache, O., and Girao, P.S. (2014, January 11\u201312). Kinect based system and artificial neural networks classifiers for physiotherapy assessment. Proceedings of the 2014 IEEE International Symposium on Medical Measurements and Applications (MeMeA), Lisboa, Portugal.","DOI":"10.1109\/MeMeA.2014.6860146"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"242","DOI":"10.1109\/THMS.2021.3059716","article-title":"Assessment of Machine Learning Models for Classification of Movement Patterns During a Weight-Shifting Exergame","volume":"51","author":"Vonstad","year":"2021","journal-title":"IEEE Trans. Hum.-Mach. Syst."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"102438","DOI":"10.1016\/j.xcrp.2025.102438","article-title":"Intelligent wearable system design for personalized knee motion and swelling monitoring in osteoarthritis care","volume":"6","author":"Ma","year":"2025","journal-title":"Cell Rep. Phys. Sci."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"985","DOI":"10.1007\/s00521-020-05370-z","article-title":"Knee joint vibration signal classification algorithm based on machine learning","volume":"33","author":"Zheng","year":"2021","journal-title":"Neural Comput. Appl."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Liu, Y., Su, Z., Li, H., and Zhang, Y. (2019, January 19\u201321). An LSTM based classification method for time series trend forecasting. Proceedings of the 2019 14th IEEE Conference on Industrial Electronics and Applications (ICIEA), Xi\u2019an, China.","DOI":"10.1109\/ICIEA.2019.8833725"},{"key":"ref_36","first-page":"490","article-title":"A biomechanical review of the squat exercise: Implications for clinical practice","volume":"19","author":"Straub","year":"2024","journal-title":"Int. J. Sport. Phys. Ther."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"e15067","DOI":"10.14814\/phy2.15067","article-title":"A review of center of pressure (COP) variables to quantify standing balance in elderly people: Algorithms and open-access code","volume":"9","author":"Quijoux","year":"2021","journal-title":"Physiol. Rep."},{"key":"ref_38","unstructured":"(2025, July 02). Q4E Case Study 30\u2014Squat\u2014Stable\/Unstable Base. Proposed Usage in Sports Science\/Physiotherapy\/Postural Management (A\/AS Level\/Degree Yr 1\/2 Sports Science\/Rehabilitation). Available online: https:\/\/www.quinticsports.com\/case-study\/q4e-case-study-30-squat-stable-unstable-base\/."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"123633","DOI":"10.1016\/j.eswa.2024.123633","article-title":"Feature selection for classification with Spearman\u2019s rank correlation coefficient-based self-information in divergence-based fuzzy rough sets","volume":"249","author":"Jiang","year":"2024","journal-title":"Expert Syst. Appl."},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Muhuri, P.S., Chatterjee, P., Yuan, X., Roy, K., and Esterline, A. (2020). Using a Long Short-Term Memory Recurrent Neural Network (LSTM-RNN) to Classify Network Attacks. Information, 11.","DOI":"10.3390\/info11050243"},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long Short-Term Memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Comput."},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Kianifar, R., Lee, A., Raina, S., and Kuli\u0107, D. (2016, January 16\u201320). Classification of squat quality with inertial measurement units in the single leg squat mobility test. Proceedings of the 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Orlando, FL, USA.","DOI":"10.1109\/EMBC.2016.7592162"},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"107135","DOI":"10.1109\/ACCESS.2023.3316009","article-title":"AI trainer: Autoencoder based approach for squat analysis and correction","volume":"11","author":"Chariar","year":"2023","journal-title":"IEEE Access"},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"189","DOI":"10.1016\/j.neucom.2019.10.118","article-title":"A comprehensive survey on support vector machine classification: Applications, challenges and trends","volume":"408","author":"Cervantes","year":"2020","journal-title":"Neurocomputing"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/25\/19\/6074\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,4]],"date-time":"2025-10-04T04:23:26Z","timestamp":1759551806000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/25\/19\/6074"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,2]]},"references-count":44,"journal-issue":{"issue":"19","published-online":{"date-parts":[[2025,10]]}},"alternative-id":["s25196074"],"URL":"https:\/\/doi.org\/10.3390\/s25196074","relation":{},"ISSN":["1424-8220"],"issn-type":[{"type":"electronic","value":"1424-8220"}],"subject":[],"published":{"date-parts":[[2025,10,2]]}}}