Ai-based next-generation sensors for enhanced rehabilitation monitoring and analysis

Abstract

With advancements in technology and healthcare, the increasing aging population necessitates effective solutions to restore autonomy in elderly individuals suffering from conditions like stroke, cerebral hemorrhage, and muscle atrophy. In order to solve this problem this article is proposing AI-based next-generation sensors for enhanced rehabilitation monitoring and analysis along with other AI based automated tools. By employing precise motion recognition algorithms based on machine intelligence, these sensors accurately capture gait data from the elderly and allows the customization of individualized rehabilitation plans based on their unique needs. They offer a range of visual and auditory stimuli within virtual rehabilitative environments in order to stimulate interest and foster active engagement for enhancing the effectiveness of rehabilitation training in elderly people. Experimental results demonstrate that the rehabilitative effects achieved within virtual environments are comparable to real-world settings and exhibit successful outcomes. With the aid of this technology, adjustable lower limb exoskeleton medical equipment is designed to accommodate individual differences and rehabilitation progress. By seamlessly integrating virtual spaces and next generation smart sensors, the proposed research offer a dynamic and tangible rehabilitation solution. PGWBI score, balance ability score, gait improvement, blood pressure, heart rate and statistical metrics such as R2 score, mean value and standard deviation and confidence intervals are considered for performance evaluation of the proposed rehabilitation monitoring and analysis method. The proposed research is also addressing the challenges posed by an aging society while aligning with the goals of the information and digital era. The research findings hold significant theoretical and practical value in advancing rehabilitation practices.