{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T16:16:19Z","timestamp":1784736979036,"version":"3.55.0"},"reference-count":56,"publisher":"MDPI AG","issue":"22","license":[{"start":{"date-parts":[[2021,11,17]],"date-time":"2021-11-17T00:00:00Z","timestamp":1637107200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>In this study, a wearable inertial measurement unit system was introduced to assess patients via the Berg balance scale (BBS), a clinical test for balance assessment. For this purpose, an automatic scoring algorithm was developed. The principal aim of this study is to improve the performance of the machine-learning-based method by introducing a deep-learning algorithm. A one-dimensional (1D) convolutional neural network (CNN) and a gated recurrent unit (GRU) that shows good performance in multivariate time-series data were used as model components to find the optimal ensemble model. Various structures were tested, and a stacking ensemble model with a simple meta-learner after two 1D-CNN heads and one GRU head showed the best performance. Additionally, model performance was enhanced by improving the dataset via preprocessing. The data were down sampled, an appropriate sampling rate was found, and the training and evaluation times of the model were improved. Using an augmentation process, the data imbalance problem was solved, and model accuracy was improved. The maximum accuracy of 14 BBS tasks using the model was 98.4%, which is superior to the results of previous studies.<\/jats:p>","DOI":"10.3390\/s21227628","type":"journal-article","created":{"date-parts":[[2021,11,17]],"date-time":"2021-11-17T09:16:11Z","timestamp":1637140571000},"page":"7628","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":58,"title":["Wearable IMU-Based Human Activity Recognition Algorithm for Clinical Balance Assessment Using 1D-CNN and GRU Ensemble Model"],"prefix":"10.3390","volume":"21","author":[{"given":"Yeon-Wook","family":"Kim","sequence":"first","affiliation":[{"name":"Department of Smart Engineering Program in Biomedical Science & Engineering, Inha University, Incheon 22212, Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kyung-Lim","family":"Joa","sequence":"additional","affiliation":[{"name":"Department of Physical and Rehabilitation Medicine, Inha University Hospital, Incheon 22332, Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1428-9821","authenticated-orcid":false,"given":"Han-Young","family":"Jeong","sequence":"additional","affiliation":[{"name":"Department of Physical and Rehabilitation Medicine, Inha University Hospital, Incheon 22332, Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sangmin","family":"Lee","sequence":"additional","affiliation":[{"name":"Department of Smart Engineering Program in Biomedical Science & Engineering, Inha University, Incheon 22212, Korea"},{"name":"Department of Electronic Engineering, Inha University, Incheon 22212, Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2021,11,17]]},"reference":[{"key":"ref_1","first-page":"847","article-title":"Falls in patients with vestibular deficits","volume":"21","author":"Herdman","year":"2000","journal-title":"Otol. Neurotol."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"649","DOI":"10.1016\/S0749-0690(18)30930-3","article-title":"Gait and balance in the elderly: Two functional capacities that link sensory and motor ability to falls","volume":"1","author":"Wolfson","year":"1985","journal-title":"Clin. Geriatr. Med."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"114","DOI":"10.1016\/j.bspc.2015.10.005","article-title":"Automatic berg balance scale assessment system based on accelerometric signals","volume":"24","author":"Badura","year":"2016","journal-title":"Biomed. Signal Process. Control"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Mohammadian Rad, N., Van Laarhoven, T., Furlanello, C., and Marchiori, E. (2018). Novelty detection using deep normative modeling for imu-based abnormal movement monitoring in parkinson\u2019s disease and autism spectrum disorders. Sensors, 18.","DOI":"10.3390\/s18103533"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s12984-021-00828-0","article-title":"Validation of IMU-based gait event detection during curved walking and turning in older adults and Parkinson\u2019s Disease patients","volume":"18","author":"Romijnders","year":"2021","journal-title":"J. Neuroeng. Rehabil."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Yu, B., Liu, Y., and Chan, K. (2020, January 2\u20134). A Survey of Sensor Modalities for Human Activity Recognition. Proceedings of the 12th International Joint Conference on Knowledge Discovery, Budapest, Hungary.","DOI":"10.5220\/0010145202760288"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"263","DOI":"10.1016\/j.sna.2018.10.005","article-title":"Human motion recognition using SWCNT textile sensor and fuzzy inference system based smart wearable","volume":"283","author":"Vu","year":"2018","journal-title":"Sens. Actuators A"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Rodrigues, S.M., Fiedler, P., K\u00fcchler, N., Domingues, P.R., Lopes, C., Borges, J., Haueisen, J., and Vaz, F. (2020). Dry electrodes for surface electromyography based on architectured titanium thin films. Materials, 13.","DOI":"10.3390\/ma13092135"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"46","DOI":"10.1109\/MIM.2021.9513637","article-title":"Human Activity Recognition with Device-Free Sensors for Well-Being Assessment in Smart Homes","volume":"24","author":"Raeis","year":"2021","journal-title":"IEEE Instrum. Meas. Mag."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"167","DOI":"10.1016\/j.eswa.2019.04.057","article-title":"A survey on wearable sensor modality centred human activity recognition in health care","volume":"137","author":"Wang","year":"2019","journal-title":"Expert Syst. Appl."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Ponciano, V., Pires, I.M., Ribeiro, F.R., Marques, G., Villasana, M.V., Garcia, N.M., Zdravevski, E., and Spinsante, S. (2020). Identification of Diseases Based on the Use of Inertial Sensors: A Systematic Review. Electronics, 9.","DOI":"10.3390\/electronics9050778"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Digo, E., Agostini, V., Pastorelli, S., Gastaldi, L., and Panero, E. (2021, January 11\u201313). Gait Phases Detection in Elderly using Trunk-MIMU System. Proceedings of the 14th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2021), Vienna, Austria.","DOI":"10.5220\/0010256400002865"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"16852","DOI":"10.1109\/JSEN.2021.3077563","article-title":"Physique-based Human Activity Recognition using Ensemble Learning and Smartphone Sensors","volume":"21","author":"Choudhury","year":"2021","journal-title":"IEEE Sens. J."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Nan, Y., Lovell, N.H., Redmond, S.J., Wang, K., Delbaere, K., and van Schooten, K.S. (2020). Deep Learning for Activity Recognition in Older People Using a Pocket-Worn Smartphone. Sensors, 20.","DOI":"10.3390\/s20247195"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Wu, B., Ma, C., Poslad, S., and Selviah, D.R. (2021). An Adaptive Human Activity-Aided Hand-Held Smartphone-Based Pedestrian Dead Reckoning Positioning System. Remote Sens., 13.","DOI":"10.3390\/rs13112137"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"1192","DOI":"10.1109\/SURV.2012.110112.00192","article-title":"A survey on human activity recognition using wearable sensors","volume":"15","author":"Lara","year":"2012","journal-title":"IEEE Commun. Surv. Tutor."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"11137","DOI":"10.1109\/JIOT.2020.2995940","article-title":"Efficient Human Activity Recognition Using a Single Wearable Sensor","volume":"7","author":"Lu","year":"2020","journal-title":"IEEE Internet Things J."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"1001","DOI":"10.1109\/JBHI.2017.2722870","article-title":"Assessment of homomorphic analysis for human activity recognition from acceleration signals","volume":"22","author":"Vanrell","year":"2017","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1016\/j.patrec.2018.02.010","article-title":"Deep learning for sensor-based activity recognition: A survey","volume":"119","author":"Wang","year":"2019","journal-title":"Pattern Recognit. Lett."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s12984-019-0550-8","article-title":"Dynamic neural network approach to targeted balance assessment of individuals with and without neurological disease during non-steady-state locomotion","volume":"16","author":"Pickle","year":"2019","journal-title":"J. Neuroeng. Rehabil."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Chung, S., Lim, J., Noh, K.J., Kim, G., and Jeong, H. (2019). Sensor data acquisition and multimodal sensor fusion for human activity recognition using deep learning. Sensors, 19.","DOI":"10.3390\/s19071716"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"13029","DOI":"10.1109\/JSEN.2021.3069927","article-title":"Human activity recognition with smartphone and wearable sensors using deep learning techniques: A review","volume":"21","author":"Ramanujam","year":"2021","journal-title":"IEEE Sens. J."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Mekruksavanich, S., and Jitpattanakul, A. (2021). LSTM networks using smartphone data for sensor-based human activity recognition in smart homes. Sensors, 21.","DOI":"10.3390\/s21051636"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Mekruksavanich, S., and Jitpattanakul, A. (2021). Deep Convolutional Neural Network with RNNs for Complex Activity Recognition Using Wrist-Worn Wearable Sensor Data. Electronics, 10.","DOI":"10.3390\/electronics10141685"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"559","DOI":"10.2522\/ptj.20070205","article-title":"Usefulness of the Berg Balance Scale in stroke rehabilitation: A systematic review","volume":"88","author":"Blum","year":"2008","journal-title":"Phys. Ther."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"449","DOI":"10.2522\/ptj.20070251","article-title":"Use of the Berg Balance Scale for predicting multiple falls in community-dwelling elderly people: A prospective study","volume":"88","author":"Muir","year":"2008","journal-title":"Phys. Ther."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"2040011","DOI":"10.1142\/S0219519420400114","article-title":"A New Auto-Scoring Algorithm for Bance Assessment with Wearable IMU Device Based on Nonlinear Model","volume":"20","author":"Kim","year":"2020","journal-title":"J. Mech. Med. Biol."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"903","DOI":"10.1098\/rspa.1998.0193","article-title":"The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis","volume":"454","author":"Huang","year":"1998","journal-title":"Proc. R. Soc. Lond. Ser. A"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1016\/j.patrec.2016.01.001","article-title":"Optimising sampling rates for accelerometer-based human activity recognition","volume":"73","author":"Khan","year":"2016","journal-title":"Pattern Recognit. Lett."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"1701","DOI":"10.1109\/PROC.1967.5962","article-title":"Sampling, data transmission, and the Nyquist rate","volume":"55","author":"Landau","year":"1967","journal-title":"Proc. IEEE"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"109960","DOI":"10.1109\/ACCESS.2021.3102399","article-title":"A Comparative Performance Analysis of Data Resampling Methods on Imbalance Medical Data","volume":"9","author":"Khushi","year":"2021","journal-title":"IEEE Access"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Liu, Z., Cao, W., Gao, Z., Bian, J., Chen, H., Chang, Y., and Liu, T.Y. (2020, January 20\u201324). Self-paced ensemble for highly imbalanced massive data classification. Proceedings of the 2020 IEEE 36th International Conference on Data Engineering (ICDE), Dallas, TX, USA.","DOI":"10.1109\/ICDE48307.2020.00078"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"429","DOI":"10.1016\/j.ins.2019.11.004","article-title":"Data imbalance in classification: Experimental evaluation","volume":"513","author":"Thabtah","year":"2020","journal-title":"Inf. Sci."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"76","DOI":"10.1016\/j.ins.2017.10.017","article-title":"Imbalanced enterprise credit evaluation with DTE-SBD: Decision tree ensemble based on SMOTE and bagging with differentiated sampling rates","volume":"425","author":"Sun","year":"2018","journal-title":"Inf. Sci."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"103465","DOI":"10.1016\/j.jbi.2020.103465","article-title":"A hybrid sampling algorithm combining M-SMOTE and ENN based on random forest for medical imbalanced data","volume":"107","author":"Xu","year":"2020","journal-title":"J. Biomed. Inform."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"59475","DOI":"10.1109\/ACCESS.2018.2874063","article-title":"Cervical cancer diagnosis using random forest classifier with SMOTE and feature reduction techniques","volume":"6","author":"Abdoh","year":"2018","journal-title":"IEEE Access"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1613\/jair.953","article-title":"SMOTE: Synthetic minority over-sampling technique","volume":"16","author":"Chawla","year":"2002","journal-title":"J. Artif. Intell. Res."},{"key":"ref_38","unstructured":"Khorshidi, H.A., and Aickelin, U. (2020). Synthetic Over-sampling with the Minority and Majority classes for imbalance problems. arXiv, in preprint."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"246","DOI":"10.1016\/j.neucom.2019.07.034","article-title":"Multi-head CNN\u2013RNN for multi-time series anomaly detection: An industrial case study","volume":"363","author":"Canizo","year":"2019","journal-title":"Neurocomputing"},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Jiang, Z., Lai, Y., Zhang, J., Zhao, H., and Mao, Z. (2019). Multi-factor operating condition recognition using 1D convolutional long short-term network. Sensors, 19.","DOI":"10.3390\/s19245488"},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"88348","DOI":"10.1109\/ACCESS.2020.2993335","article-title":"Multivariate abnormal detection for industrial control systems using 1D CNN and GRU","volume":"8","author":"Xie","year":"2020","journal-title":"IEEE Access"},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Pasupa, K., and Sunhem, W. (2016, January 5\u20136). A comparison between shallow and deep architecture classifiers on small dataset. Proceedings of the 2016 8th International Conference on Information Technology and Electrical Engineering (ICITEE), Yogyakarta, Indonesia.","DOI":"10.1109\/ICITEED.2016.7863293"},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Brigato, L., and Iocchi, L. (2021, January 10\u201315). A close look at deep learning with small data. Proceedings of the 2020 25th International Conference on Pattern Recognition (ICPR), Milan, Italy.","DOI":"10.1109\/ICPR48806.2021.9412492"},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Cho, K., Van Merri\u00ebnboer, B., Bahdanau, D., and Bengio, Y. (2014). On the properties of neural machine translation: Encoder-decoder approaches. arXiv, in preprint.","DOI":"10.3115\/v1\/W14-4012"},{"key":"ref_45","first-page":"e13","article-title":"Experimental Comparison of Classification Methods under Class Imbalance","volume":"sis18","author":"Chen","year":"2021","journal-title":"EAI Trans. Scalable Inf. Syst."},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Ordo\u00f1ez, F.J., and Roggen, D. (2016). Deep convolutional and lstm recurrent neural networks for multimodal wearable activity recognition. Sensors, 16.","DOI":"10.3390\/s16010115"},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"2263","DOI":"10.1109\/TASLP.2016.2602884","article-title":"Very deep convolutional neural networks for noise robust speech recognition","volume":"24","author":"Qian","year":"2016","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"76","DOI":"10.1016\/j.neucom.2016.12.088","article-title":"An analysis of convolutional long short-term memory recurrent neural networks for gesture recognition","volume":"268","author":"Tsironi","year":"2017","journal-title":"Neurocomputing"},{"key":"ref_49","doi-asserted-by":"crossref","unstructured":"Ahmad, W., Kazmi, B.M., and Ali, H. (2019, January 2\u20133). Human activity recognition using multi-head CNN followed by LSTM. Proceedings of the 2019 15th international conference on emerging technologies (ICET), Peshawar, Pakistan.","DOI":"10.1109\/ICET48972.2019.8994412"},{"key":"ref_50","unstructured":"Perenda, E., Rajendran, S., and Pollin, S. (2019, January 10\u201312). Automatic modulation classification using parallel fusion of convolutional neural networks. Proceedings of the 2019 3rd International Balkan Conference on Communications and Networking (IBCCN) (BalkanCom\u201919), Skopje, North Macedonia."},{"key":"ref_51","doi-asserted-by":"crossref","unstructured":"Lee, K., Kim, J.K., Kim, J., Hur, K., and Kim, H. (2018, January 23\u201327). CNN and GRU combination scheme for bearing anomaly detection in rotating machinery health monitoring. Proceedings of the 2018 1st IEEE International Conference on Knowledge Innovation and Invention (ICKII), Jeju Island, Korea.","DOI":"10.1109\/ICKII.2018.8569155"},{"key":"ref_52","doi-asserted-by":"crossref","unstructured":"Hamad, R.A., Yang, L., Woo, W.L., and Wei, B. (2020). Joint learning of temporal models to handle imbalanced data for human activity recognition. Appl. Sci., 10.","DOI":"10.3390\/app10155293"},{"key":"ref_53","doi-asserted-by":"crossref","first-page":"387","DOI":"10.1109\/JBHI.2019.2918412","article-title":"Efficient activity recognition in smart homes using delayed fuzzy temporal windows on binary sensors","volume":"24","author":"Hamad","year":"2019","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"ref_54","doi-asserted-by":"crossref","unstructured":"Xu, M., Yin, Z., Wu, M., Wu, Z., Zhao, Y., and Gao, Z. (July, January 25). Spectrum sensing based on parallel cnn-lstm network. Proceedings of the 2020 IEEE 91st Vehicular Technology Conference (VTC2020-Spring), Virtual, Antwerp, Begium.","DOI":"10.1109\/VTC2020-Spring48590.2020.9129229"},{"key":"ref_55","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1016\/j.asoc.2013.09.014","article-title":"A hybrid classifier combining SMOTE with PSO to estimate 5-year survivability of breast cancer patients","volume":"20","author":"Wang","year":"2014","journal-title":"Appl. Soft Comput."},{"key":"ref_56","doi-asserted-by":"crossref","first-page":"863","DOI":"10.1613\/jair.1.11192","article-title":"SMOTE for learning from imbalanced data: Progress and challenges, marking the 15-year anniversary","volume":"61","author":"Garcia","year":"2018","journal-title":"J. Artif. Intell. Res."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/22\/7628\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T07:31:27Z","timestamp":1760167887000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/22\/7628"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,11,17]]},"references-count":56,"journal-issue":{"issue":"22","published-online":{"date-parts":[[2021,11]]}},"alternative-id":["s21227628"],"URL":"https:\/\/doi.org\/10.3390\/s21227628","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,11,17]]}}}