Multi-disciplinary Design and In-Home Evaluation of Kinect-Based Exercise Coaching System for Elderly

Virtual Coaches for Older Adults’ Wellbeing: A Systematic Review

“…Randomized trial [2,3,11,48,55,56] Pilot study [12,13,14,21,26,31,35,39,40,43,44,45,46,47,53,54] Observational study [28,30] Preliminary studies for assessing usability or codesign choices [1,5,9,15,18,20,23,24,27,34,49] System proposal (no user study) [6,16,17,19,22,25,29,36,52] Study protocol [4,7,8,32,33,41] Field study [10,…”

“…Hence, because of a limited understanding of how to design and implement e-coaching interventions for older adults, as well as limited evidence regarding their effectiveness in promoting healthrelated outcomes, we refrained from excluding further papers and kept all 56 for our analysis. In fact, among the 56 papers selected as eligible for the analysis, five reported results of randomized controlled trials [2,3,11,55,56] and one study was a clinical trial [48], six reported protocols for future randomized trials [4, 7, 8, 32, 33, 41], 16 presented results of pilot studies [12,13,14,21,26,31,35,39,40,43,44,45,46,47,53,54] and two were observational studies [28,30], while [38] presented a pre-post intervention study. Eleven presented the results of a preliminary assessment of a system in terms of usability or co-design choice [1,5,9,15,18,20,23,24,27,34,49], four [10,42,50,51] presented a field study for deriving the requirements of a coaching system, and nine presented only a proposal of a coaching system or an architectural implementation, without any user study [6,…”

“…Finally, a single paper [37] presented a quasi-experimental prospective study. It is worth noting that papers [1,23], [12,14], [33,34], [49,45], [10,50,51] and [55,56] were related to the same project, but presenting different versions of the same system. Also, in papers [2,3,11,21] different versions of the same embodied conversational agent were used as intervention medium.…”

“…However, from Table II, we can conclude that the personalization of content is the most frequent technique implemented in the analyzed studies. Examples of content personalization in some research papers are: history of previous interaction of the user [2,11,19,20,25,47], barriers negotiation with users [3,30], ability of users to choose modalities for the interaction [6,12], content display based on personal needs and preferences [41,32,33,34,49,47,40], local news information [16], advice and recommendations for behavioral change based on the user's preferences and needs [26,49,50,51,55], or other [10,17,35]. It is worth noting that articles [24,38,34,53] had a minimized personalization of content (e.g., the system using only the user's name in its communication), and this was considered in the analysis but noted as a low degree of content personalization.…”

“…Techniques for recognizing user activities are diverse: a step counter [1,2,3,11,18,32], self-monitoring [36], goal achievement [37], weight measurement and blood pressure with weekly telephone calls by a nurse [4], motion capture [12] and more specifically a camera [27], as well as a Microsoft Kinect camera to assess the movement of the user [35,42]. In [39], Razer Hydra and a Microsoft Kinect camera were used for activity recognition, whereas in [14], Microsoft Kinect V2 camera was used to recognize and provide real time feedback on body posture of the trainee and the ideal postures that trainees should imitate.…”