{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T21:17:35Z","timestamp":1777583855023,"version":"3.51.4"},"reference-count":45,"publisher":"Walter de Gruyter GmbH","issue":"4","license":[{"start":{"date-parts":[[2025,7,11]],"date-time":"2025-07-11T00:00:00Z","timestamp":1752192000000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    Accurately estimating spatio-temporal gait parameters such as stride height, stride length, stance time, swing time, and stride speed, is crucial for sports medicine and preventive healthcare. To enable users to measure their spatio-temporal gait parameters in real-life scenarios, several existing studies propose to install one inertial measurement unit (IMU) in each shoe, and design methods to estimate these gait parameters according to the readings of IMUs. Therefore, this paper proposes a novel ensemble method,\n                    <jats:italic>NEST<\/jats:italic>\n                    (standing for Novel Ensemble method for Spatio-Temporal gait parameters measurement), for the multi-task measurement of the aforementioned five spatio-temporal gait parameters.\n                    <jats:italic>NEST<\/jats:italic>\n                    consists of a\n                    <jats:italic>K-Nearest Neighbor (KNN) regressor<\/jats:italic>\n                    branch and a\n                    <jats:italic>deep learning<\/jats:italic>\n                    branch. The\n                    <jats:italic>KNN regressor<\/jats:italic>\n                    branch provides initial estimates, allowing other neural networks to learn to reduce the residual between these estimates and the ground truths. This helps\n                    <jats:italic>NEST<\/jats:italic>\n                    rapidly identify a good optimization direction during the early stage of fine-tuning and expedite convergence speed. The\n                    <jats:italic>deep learning<\/jats:italic>\n                    branch facilitates information sharing among multiple task-specific representations through\n                    <jats:italic>fully-connected layers<\/jats:italic>\n                    , effectively preserving the interdependencies among gait parameters. Several experiments are conducted to evaluate the performance of\n                    <jats:italic>NEST<\/jats:italic>\n                    and other prior methods. Compared to prior handcrafted-statistics-based methods,\n                    <jats:italic>NEST<\/jats:italic>\n                    demonstrates over 65.1% improvement in RMSE (Root-Mean-Square Error) when predicting spatial parameters.\n                  <\/jats:p>","DOI":"10.2478\/jaiscr-2025-0016","type":"journal-article","created":{"date-parts":[[2025,7,11]],"date-time":"2025-07-11T08:12:54Z","timestamp":1752221574000},"page":"319-336","source":"Crossref","is-referenced-by-count":1,"title":["NEST: A Novel Ensemble Method for Estimating Spatio-Temporal Gait Parameters Using Inertial Measurement Units"],"prefix":"10.2478","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-2343-6409","authenticated-orcid":false,"given":"Chih-Chao","family":"Hsu","sequence":"first","affiliation":[{"name":"Department of Computer Science , National Yang Ming Chiao Tung University , No. 1001, University Road, Hsinchu city 300093 , Taiwan"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-9690-8461","authenticated-orcid":false,"given":"Hsu-Chao","family":"Lai","sequence":"additional","affiliation":[{"name":"Department of Computer Science , National Yang Ming Chiao Tung University , No. 1001, University Road, Hsinchu city 300093 , Taiwan"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-9912-9336","authenticated-orcid":false,"given":"Guan-Yi","family":"Jhang","sequence":"additional","affiliation":[{"name":"Department of Computer Science , National Yang Ming Chiao Tung University , No. 1001, University Road, Hsinchu city 300093 , Taiwan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9471-7672","authenticated-orcid":false,"given":"Jiun-Long","family":"Huang","sequence":"additional","affiliation":[{"name":"Department of Computer Science , National Yang Ming Chiao Tung University , No. 1001, University Road, Hsinchu city 300093 , Taiwan"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-6102-448X","authenticated-orcid":false,"given":"Jun-Zhe","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Information Engineering , Graduate School of Engineering Science and Technology, National Yunlin University of Science and Technology , No. 123, Section 3, Daxue Road, Yunlin county 640301 , Taiwan"}]}],"member":"374","published-online":{"date-parts":[[2025,7,11]]},"reference":[{"key":"2026042814153321550_j_jaiscr-2025-0016_ref_001","doi-asserted-by":"crossref","unstructured":"A. Al-Kababji, F. Bensaali, and S. P. Dakua. Scheduling techniques for liver segmentation: Reducelronplateau vs onecyclelr. ArXiv, 2022.","DOI":"10.1007\/978-3-031-08277-1_17"},{"key":"2026042814153321550_j_jaiscr-2025-0016_ref_002","doi-asserted-by":"crossref","unstructured":"L. Alcock, B. Galna, R. Perkins, S. Lord, and L. Rochester. Step length determines minimum toe clearance in older adults and people with Parkinson\u2019s disease. Journal of Biomechanics, 71(1), 2018.","DOI":"10.1016\/j.jbiomech.2017.12.002"},{"key":"2026042814153321550_j_jaiscr-2025-0016_ref_003","doi-asserted-by":"crossref","unstructured":"B. Breine, P. Malcolm, E. C. Frederick, and D. De Clercq. Relationship between running speed and initial foot contact patterns. Medicine and Science in Sports and Exercise, 46(8), 2014.","DOI":"10.1249\/MSS.0000000000000267"},{"key":"2026042814153321550_j_jaiscr-2025-0016_ref_004","unstructured":"S. Butterworth. On the theory of filter amplifiers. Wireless Engineer, 7(6), 1930."},{"key":"2026042814153321550_j_jaiscr-2025-0016_ref_005","doi-asserted-by":"crossref","unstructured":"R. Caruana. Multi-task learning. Machine Learning, 28, 1997.","DOI":"10.1023\/A:1007379606734"},{"key":"2026042814153321550_j_jaiscr-2025-0016_ref_006","doi-asserted-by":"crossref","unstructured":"W. Chen, Z. Wang, H. Xie, and W. Yu. Characterization of surface EMG signal based on fuzzy entropy. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 15(2), 2007.","DOI":"10.1109\/TNSRE.2007.897025"},{"key":"2026042814153321550_j_jaiscr-2025-0016_ref_007","doi-asserted-by":"crossref","unstructured":"Y.-S. Cho, S.-H. Jang, J.-S. Cho, M.-J. Kim, H. D. Lee, S. Y. Lee, and S.-B. Moon. Evaluation of validity and reliability of inertial measurement unit-based gait analysis systems. Annals of Rehabilitation Medicine, 42(6), 2018.","DOI":"10.5535\/arm.2018.42.6.872"},{"key":"2026042814153321550_j_jaiscr-2025-0016_ref_008","doi-asserted-by":"crossref","unstructured":"I. Delimaris. Potential adverse biological effects of excessive exercise and overtraining among healthy individuals. Acta Medica Martiniana, 14(3), 2014.","DOI":"10.1515\/acm-2015-0001"},{"key":"2026042814153321550_j_jaiscr-2025-0016_ref_009","doi-asserted-by":"crossref","unstructured":"H. T. Duong, K. M. Hoang, H. V. Pham, and V. A. Trinh. High-performance stacked ensemble model for stride length estimation with potential application in indoor positioning systems. Journal of Communications, 17(8), 2022.","DOI":"10.12720\/jcm.17.8.652-660"},{"key":"2026042814153321550_j_jaiscr-2025-0016_ref_010","unstructured":"E. T. B. Ekanayake. Entropy analysis of kinetic and kinematic gait parameters as a potential tool to predict osteoarthritis onset. Master\u2019s thesis, University of Central Oklahoma, 2019."},{"key":"2026042814153321550_j_jaiscr-2025-0016_ref_011","doi-asserted-by":"crossref","unstructured":"M. Falbriard, F. Meyer, B. Mariani, G. P. Millet, and K. Aminian. Accurate estimation of running temporal parameters using foot-worn inertial sensors. Frontiers in Physiology, 9(1), 2018.","DOI":"10.3389\/fphys.2018.00610"},{"key":"2026042814153321550_j_jaiscr-2025-0016_ref_012","doi-asserted-by":"crossref","unstructured":"A. Ferrari, D. Micucci, M. Mobilio, and P. Napoletano. Hand-crafted features vs residual networks for human activities recognition using accelerometer. In Proceedings of IEEE International Symposium on Consumer Technologies, 2019.","DOI":"10.1109\/ISCE.2019.8901021"},{"key":"2026042814153321550_j_jaiscr-2025-0016_ref_013","doi-asserted-by":"crossref","unstructured":"F. Fritsch and R. Carlson. Monotone piecewise cubic interpolation. SIAM Journal on Numerical Analysis, 17(2), 1980.","DOI":"10.1137\/0717021"},{"key":"2026042814153321550_j_jaiscr-2025-0016_ref_014","doi-asserted-by":"crossref","unstructured":"J. Hannink, T. Kautz, C. F. Pasluosta, J. Barth, S. Sch\u00fclein, K.-G. Ga\u00dfmann, J. Klucken, and B. M. Eskofier. Mobile stride length estimation with deep convolutional neural networks. IEEE Journal of Biomedical and Health Informatics, 22(2), 2017.","DOI":"10.1109\/JBHI.2017.2679486"},{"key":"2026042814153321550_j_jaiscr-2025-0016_ref_015","doi-asserted-by":"crossref","unstructured":"J. Hannink, T. Kautz, C. F. Pasluosta, K.-G. Ga\u00df-mann, J. Klucken, and B. M. Eskofier. Sensor-based gait parameter extraction with deep convolutional neural networks. IEEE Journal of Biomedical and Health Informatics, 21(1), 2017.","DOI":"10.1109\/JBHI.2016.2636456"},{"key":"2026042814153321550_j_jaiscr-2025-0016_ref_016","doi-asserted-by":"crossref","unstructured":"H. Huang, P. Zhou, Y. Li, and F. Sun. A lightweight attention-based CNN model for efficient gait recognition with wearable IMU sensors. Sensors, 21(8), 2021.","DOI":"10.3390\/s21082866"},{"key":"2026042814153321550_j_jaiscr-2025-0016_ref_017","doi-asserted-by":"crossref","unstructured":"I. Hunter and G. Smith. Preferred and optimal stride frequency, stiffness and economy: Changes with fatigue during a 1-h high-intensity run. European Journal of Applied Physiology, 100(6), 2007.","DOI":"10.1007\/s00421-007-0456-1"},{"key":"2026042814153321550_j_jaiscr-2025-0016_ref_018","doi-asserted-by":"crossref","unstructured":"C. Ison, C. Neilsen, J. DeBerardinis, M. B. Trabia, and J. S. Dufek. Use of pressure-measuring insoles to characterize gait parameters in simulated reduced-gravity conditions. Sensors, 21(18), 2021.","DOI":"10.3390\/s21186244"},{"key":"2026042814153321550_j_jaiscr-2025-0016_ref_019","doi-asserted-by":"crossref","unstructured":"\u0141. Kidzi\u0144ski, B. Yang, J. L. Hicks, A. Rajagopal, S. L. Delp, and M. H. Schwartz. Deep neural networks enable quantitative movement analysis using single-camera videos. Nature Communications, 11(1), 2020.","DOI":"10.1038\/s41467-020-17807-z"},{"key":"2026042814153321550_j_jaiscr-2025-0016_ref_020","doi-asserted-by":"crossref","unstructured":"J. Kim, H. Jang, D.-H. Hwang, and C. Park. A step, stride and heading determination for the pedestrian navigation system. Journal of Global Positioning Systems, 3(1-2), 2004.","DOI":"10.5081\/jgps.3.1.273"},{"key":"2026042814153321550_j_jaiscr-2025-0016_ref_021","unstructured":"D. P. Kingma and J. Ba. Adam: A method for stochastic optimization. In Proceedings of International Conference on Learning Representations, 2015."},{"key":"2026042814153321550_j_jaiscr-2025-0016_ref_022","unstructured":"Q. Ladetto. On foot navigation: continuous step calibration using both complementary recursive prediction and adaptive Kalman filtering. In Proceedings of International Technical Meeting of the Satellite Division of The Institute of Navigation, 2000."},{"key":"2026042814153321550_j_jaiscr-2025-0016_ref_023","doi-asserted-by":"crossref","unstructured":"C. Liu and G. Jia. Industrial big data and computational sustainability: Multi-method comparison driven by high-dimensional data for improving reliability and sustainability of complex systems. Sustainability, 11(17), 2019.","DOI":"10.3390\/su11174557"},{"key":"2026042814153321550_j_jaiscr-2025-0016_ref_024","unstructured":"Y. Ma, B. Sheng, R. Hart, and Y. Zhang. The validity of a dual azure kinect-based motion capture system for gait analysis: A preliminary study. In Proceedings of Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, 2020."},{"key":"2026042814153321550_j_jaiscr-2025-0016_ref_025","doi-asserted-by":"crossref","unstructured":"B. Mariani, C. Hoskovec, S. Rochat, C. B\u00fcla, J. Penders, and K. Aminian. 3d gait assessment in young and elderly subjects using foot-worn inertial sensors. Journal of Biomechanics, 43(15), 2010.","DOI":"10.1016\/j.jbiomech.2010.07.003"},{"key":"2026042814153321550_j_jaiscr-2025-0016_ref_026","doi-asserted-by":"crossref","unstructured":"B. Mariani, S. Rochat, C. B\u00fcla, and K. Aminian. Heel and toe clearance estimation for gait analysis using wireless inertial sensors. IEEE Transactions on Bio-medical Engineering, 59(11), 2012.","DOI":"10.1109\/TBME.2012.2216263"},{"key":"2026042814153321550_j_jaiscr-2025-0016_ref_027","doi-asserted-by":"crossref","unstructured":"B. Mariani, H. Rouhani, X. Crevoisier, and K. Aminian. Quantitative estimation of foot-flat and stance phase of gait using foot-worn inertial sensors. Gait and Posture, 37(2), 2013.","DOI":"10.1016\/j.gaitpost.2012.07.012"},{"key":"2026042814153321550_j_jaiscr-2025-0016_ref_028","doi-asserted-by":"crossref","unstructured":"E. Martini, T. Fiumalbi, F. Dell\u2019Agnello, Z. Ivani\u0107, M. Munih, N. Vitiello, and S. Crea. Pressure-sensitive insoles for real-time gait-related applications. Sensors, 20(5), 2020.","DOI":"10.3390\/s20051448"},{"key":"2026042814153321550_j_jaiscr-2025-0016_ref_029","doi-asserted-by":"crossref","unstructured":"H. Masum, S. Chattopadhyay, R. Ray, and S. Bhaumik. Measurement of walking speed from gait data using kurtosis and skewness based approximate and detailed coefficients. IET Science, Measurement and Technology, 12(4), 2018.","DOI":"10.1049\/iet-smt.2017.0233"},{"key":"2026042814153321550_j_jaiscr-2025-0016_ref_030","doi-asserted-by":"crossref","unstructured":"W. Ng, B. Minasny, W. de Sousa Mendes, and J. Dematt\u00ea. The influence of training sample size on the accuracy of deep learning models for the prediction of soil properties with near-infrared spectroscopy data. SOIL, 6(2), 2020.","DOI":"10.5194\/soil-6-565-2020"},{"key":"2026042814153321550_j_jaiscr-2025-0016_ref_031","doi-asserted-by":"crossref","unstructured":"E. Panero, E. Digo, V. Agostini, and L. Gastaldi. Comparison of different motion capture setups for gait analysis : Validation of spatio-temporal parameters estimation. In Proceedings of IEEE International Symposium on Medical Measurements and Applications, 2018.","DOI":"10.1109\/MeMeA.2018.8438653"},{"key":"2026042814153321550_j_jaiscr-2025-0016_ref_032","doi-asserted-by":"crossref","unstructured":"S. Qin, X. Chen, P. Li, W. Li, Z. Wu, H. Jiang, Z. Liu, and R. Zhang. Modeling and evaluating full-cycle natural gait detection based on human electrostatic field. IEEE Transactions on Instrumentation and Measurement, 72, 2023.","DOI":"10.1109\/TIM.2023.3315405"},{"key":"2026042814153321550_j_jaiscr-2025-0016_ref_033","doi-asserted-by":"crossref","unstructured":"O. Ronneberger, P. Fischer, and T. Brox. U-net: Convolutional networks for biomedical image segmentation. In Proceedings of International Conference on Medical Image Computing and Computer-Assisted Intervention, 2015.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"2026042814153321550_j_jaiscr-2025-0016_ref_034","doi-asserted-by":"crossref","unstructured":"N. Roth, A. K\u00fcderle, D. Prossel, H. Gassner, B. M. Eskoer, and F. Kluge. An inertial sensor-based gait analysis pipeline for the assessment of real-world stair ambulation parameters. Sensors, 21(19), 2021.","DOI":"10.3390\/s21196559"},{"key":"2026042814153321550_j_jaiscr-2025-0016_ref_035","doi-asserted-by":"crossref","unstructured":"M. Sarshar, S. Polturi, and L. Schega. Gait phase estimation by using LSTM in IMU-based gait analysis\u2014proof of concept. Sensors, 21(17), 2021.","DOI":"10.3390\/s21175749"},{"key":"2026042814153321550_j_jaiscr-2025-0016_ref_036","unstructured":"J. Scarlett. Enhancing the performance of pedometers using a single accelerometer. Application Note, Analog Devices, 41(1), 2007."},{"key":"2026042814153321550_j_jaiscr-2025-0016_ref_037","doi-asserted-by":"crossref","unstructured":"J.-D. Sui and T.-S. Chang. IMU based deep stride length estimation with self-supervised learning. IEEE Sensors Journal, 21(6), 2021.","DOI":"10.1109\/JSEN.2021.3049523"},{"key":"2026042814153321550_j_jaiscr-2025-0016_ref_038","doi-asserted-by":"crossref","unstructured":"E. Suter, B. Marti, and F. Gutzwiller. Jogging or walking\u2014comparison of health effects. Annals of Epidemiology, 4(5), 1994.","DOI":"10.1016\/1047-2797(94)90072-8"},{"key":"2026042814153321550_j_jaiscr-2025-0016_ref_039","doi-asserted-by":"crossref","unstructured":"R. Vaishya and A. Vaish. Falls in older adults are serious. Indian Journal of Orthopaedics, 54(1), 2020.","DOI":"10.1007\/s43465-019-00037-x"},{"key":"2026042814153321550_j_jaiscr-2025-0016_ref_040","doi-asserted-by":"crossref","unstructured":"Q. Wang, L. Ye, H. Luo, A. Men, F. Zhao, and Y. Huang. Pedestrian stride-length estimation based on LSTM and denoising autoencoders. Sensors, 19(4), 2019.","DOI":"10.3390\/s19040840"},{"key":"2026042814153321550_j_jaiscr-2025-0016_ref_041","unstructured":"H. Weinberg. Using the ADXL202 in pedometer and personal navigation applications. Analog Devices AN-602 Application Note, 2(2), 2002."},{"key":"2026042814153321550_j_jaiscr-2025-0016_ref_042","doi-asserted-by":"crossref","unstructured":"M. Zhang, Y. Gan, X. Wang, Z. Wang, T. Feng, and Y. Zhang. Gait performance and non-motor symptoms burden during dual-task condition in Parkinson\u2019s disease. Neurological Sciences, 44(1), 2023.","DOI":"10.1007\/s10072-022-06411-2"},{"key":"2026042814153321550_j_jaiscr-2025-0016_ref_043","doi-asserted-by":"crossref","unstructured":"M. Zhang, Q. Wang, D. Liu, B. Zhao, J. Tang, and J. Sun. Real-time gait phase recognition based on time domain features of multi-mems inertial sensors. IEEE Transactions on Instrumentation and Measurement, 70, 2021.","DOI":"10.1109\/TIM.2021.3108174"},{"key":"2026042814153321550_j_jaiscr-2025-0016_ref_044","doi-asserted-by":"crossref","unstructured":"X. Zhu, J. Gao, Y. Dai, J. Zhang, W. Zhang, D. Sun, and W. Gu. Three steps from grid-less pressure sensors to gait recognition. IEEE Transactions on Instrumentation and Measurement, 72, 2023.","DOI":"10.1109\/TIM.2023.3307173"},{"key":"2026042814153321550_j_jaiscr-2025-0016_ref_045","doi-asserted-by":"crossref","unstructured":"M. Zrenner, S. Gradl, U. Jensen, M. Ullrich, and B. M. Eskofier. Comparison of different algorithms for calculating velocity and stride length in running using inertial measurement units. Sensors, 18(12), 2018.","DOI":"10.3390\/s18124194"}],"container-title":["Journal of Artificial Intelligence and Soft Computing Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/reference-global.com\/pdf\/10.2478\/jaiscr-2025-0016","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T19:52:47Z","timestamp":1777405967000},"score":1,"resource":{"primary":{"URL":"https:\/\/reference-global.com\/article\/10.2478\/jaiscr-2025-0016"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,11]]},"references-count":45,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2025,7,11]]},"published-print":{"date-parts":[[2025,10,1]]}},"alternative-id":["10.2478\/jaiscr-2025-0016"],"URL":"https:\/\/doi.org\/10.2478\/jaiscr-2025-0016","relation":{},"ISSN":["2449-6499"],"issn-type":[{"value":"2449-6499","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,11]]}}}