Phyx.io: Expert-Based Decision Making for the Selection of At-Home Rehabilitation Solutions for Active and Healthy Aging

Abstract

While the importance of physical activity in older adults is beyond doubt, there are significant barriers limiting the access of older adults to physical exercise. Existing technologies to support physical activity in older adults show that, despite their positive impacts on health and well-being, there is in general a lack of engagement due to the existing reluctance to the use of technology. Usefulness and usability are two major factors for user acceptance along with others, such as cost, privacy, equipment and maintenance requirements, support, etc. Nevertheless, the extent to which each factor impacts user acceptance remains unclear. Furthermore, other stakeholders, besides the end users, should be considered in the decision-making process to develop such technologies, including caregivers, therapists and technology providers. In this paper, and in the context of physical rehabilitation and exercise at home, four different alternatives with incremental characteristics have been defined and considered: a software-based platform for physical rehabilitation and exercise (Alternative 1), the same software platform with a conventional RGB camera and no exercise supervision (Alternative 2), the same software platform with a convention RGB camera and exercise supervision (Alternative 3) and finally, the same software platform with a depth camera and exercise supervision (Alternative 4). A multiple attribute decision-making methodology, based on the ordinal priority approach (OPA) method, is then applied using a group of experts, including end users, therapists and developers to rank the best alternative. The attributes considered in this method have been usefulness, cost, ease of use, ease of technical development, ease of maintenance and privacy, concluding that Alternative 3 has been ranked as the most appropriate.

Addressing Ergonomic Challenges in Agriculture through AI-Enabled Posture Classification

“…Among these models, Movenet [24] stands out as a promising option for application in various scenarios, due to its strong ability to detect key joint features using image information. It has been proved that MoveNet can be applied to create a software for monitoring physical activities in the elderly [25], and can be extended to the classification of stroke patients based on videos captured by smartphones [26]. In scenarios where precise and complex measuring instruments are challenging to use for posturee detection, MoveNet achieves more accurate results with simple image data alone, showcasing its immense application potential.…”