Intelligent detection of possible risk situations of wheelchair users in transport
DOI:
https://doi.org/10.17979/ja-cea.2025.46.12084Keywords:
Assistive technology and rehabilitation engineering, Information and sensor fusion, Artificial intelligence techniques, Experiment design, Design methodologiesAbstract
The use of transportation can generate risk situations for wheelchair users that may negatively impact their functional status.
Therefore, it is essential to identify the conditions they are exposed to during travel. This study presents an AI-based identifier
of potential risk situations for wheelchair users, structured in two stages. First, it classifies whether the user is in rail transport,
wheeled transport, or stationary. Then, it detects whether the vehicle is moving, turning, or braking. Two intelligent techniques,
KNN and ANN, have been evaluated. Both achieve an accuracy rate of 98.7% in the first stage. In the second stage, KNN
shows better results, with precision rates above 92 %, while ANN presents values exceeding 81 %. The system enables the
contextualization of postural data collected during the users’ daily activities, facilitating clinical interpretation and supporting
treatment decisions.
References
Chen, Y., Wang, L., Wang, Z., Jia, N. & Chen, Q. Whole-body vibration exposure characterization in bus drivers of Haikou City: A comparison between two health risk assessment methods. Journal of Environmental and Occupational Medicine. 40, 1264-1269 (2023)
Crawford, A., Armstrong, K., Loparo, K., Audu, M., & Triolo, R. Detecting destabilizing wheelchair conditions for maintaining seated posture isabil Rehabil Assist Technolgy. 13, 178-185 (2018)
Garcia-Mendez Y., Pearlman J., Boninger M. & Cooper R. Health risks of vibration exposure to wheelchair users in the community. The Journal of Spinal Cord Medicine. 36(4), 365-75 (2013,3)
Halder, R.K., Uddin, M.N., Uddin, M.A., & others. Enhancing K-nearest neighbor algorithm: a comprehensive review and performance analysis of modifications. Journal of Big Data. 11, 113 (2024).
Ma, C., Li, W., Cao, J., Du, J., Li, Q., Gravina, R. Adaptive sliding window based activity recognition for assisted livings. Information Fusion. 53, 55–65 (2020).
Molina Men´endez, E. & Parraga-Alava, J. Artificial Neural Networks for Classification Tasks: A Systematic Literature Review. Enfoque UTE. 15, 1–10 (2024).
K. Lepoglavec, O. Papeš, V. Lovrić, A. Raspudić, H. Nevečerel. Accessibility of Urban Forests and Parks for People with Disabilities in Wheelchairs, Considering the Surface and Longitudinal Slope of the Trails. Multidisciplinary Digital Publishing Institute. 15 (2023)
Luna-Perejón, F., Montes-Sánchez, J.M., Durán-López, L., Vázquez-Baeza, A., Beasley-Bohórquez, I., Sevillano-Ramos, J.L. IoT device for sitting posture classification using artificial neural networks. Electronics. 10, 1825 (2021).
Perez, N., Mancisidor, A., Cabanes, I., Vermander, P. Sitting Posture Monitoring Device for People with Low Degree of Autonomy. Converging Clinical and Engineering Research on Neurorehabilitation IV. ICNR 2020. (2022)
Perez, N., Mancisidor, A., Cabanes, I., Vermander, P., Portillo, E., Zubizarreta, A. Sistema de monitorizaci´on de entornos para usuarios de sillas de ruedas. Jornadas de Automarica 2024 45 (24)
Perez, N., Mancisidor, A., Cabanes, I., Vermander, P., Gonzalez, J. Continuous postural and movement monitoring system for wheelchair users assessment. Measurement (2024)
M. Shyam, K. Abinash, A. Jeevan Mathew, P. R. Akash Ram, S. Kaushik, M. Kishore. A Contemporary Voice Assisted LIDAR Based Self Piloting Intelligent Wheelchair for Both Elderly And Disabled. 2023 IEEE International Conference on Research Methodologies in Knowledge Management, Artificial Intelligence and Telecommunication Engineering. (2023)
Zhang, P., Chen, W., Wang, H., Li, Z., Li, X., Liu, B., Adam, S., Jalil, N., Razali, K., Kumar, R., Sharma, R., Kumar, V. & Khan, A. Predictors of Whole-Body Vibration Exposure among Indian Bus and Truck Drivers. Journal Of Physics: Conference Series. 1854, 012033 (2021,4)
Zhou, J., Wu, Z., Fan, C., Yu, T., Yi, S., Li, Y. & Peng, Y. Evaluation and prediction method of railway passenger long-term vibration comfort under complex operating conditions. Ergonomics. (2023)
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Nerea Perez, Aitziber Mancisidor, Itziar Cabanes, Patrick Vermander
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
