Machine learning applications for wheelchair user well-being: a systematic literature review and taxonomy

There are currently approximately 132 million wheelchair users worldwide, and technology plays a crucial role in addressing various aspects of health and well-being for persons who rely on wheelchairs. This systematic review highlights solutions and technologies developed using machine learning to enhance the well-being of wheelchair users, focusing on the benefits achieved. The research filtered and discussed 26 articles published between January 2012 and August 2023 from an initial corpus of 2,167 articles, using the academic databases ACM, IEEE, JMIR, PubMed, Science Direct, Scopus, Springer, and Wiley. This article addresses the contributions of different technologies, such as systems for mapping accessible routes and posture analysis models. In addition, this research discusses the use of machine learning to improve the quality of life and well-being of wheelchair users. The review proposes a taxonomy that presents the subject distribution, such as which machine learning models are most used, which technologies were applied to collect data in work, and which concepts may represent the well-being of wheelchair users. The studies focus on physical activities, showing the absence of studies focusing on mental health.