The decline of the motoric and cognitive functions of the elderly and the high risk of changes in their vital signs lead to some disabilities that inconvenience them. This paper aims to assist the elderly in their daily lives through personalized and seamless technologies.
The authors developed a personalized adaptive system for elderly care in a smart home using a fuzzy inference system (FIS), which consists of a predictive positioning system, reflexive alert system and adaptive conditioning system. Reflexive sensing is obtained from a body sensor and environmental sensor networks. Three methods comprising the FIS generation algorithm – fuzzy subtractive clustering (FSC), grid partitioning and fuzzy c-means clustering (FCM) – were compared to obtain the best prediction accuracy.
The results of the experiment showed that FSC produced the best F1-score (96 per cent positioning accuracy, 94 per cent reflexive alert accuracy, 96 per cent air conditioning accuracy and 95 per cent lighting conditioning accuracy), whereas others failed to predict some classes and had lower validation accuracy results. Therefore, it is concluded that FSC is the best FIS generation method for our proposed system.
Personalized and seamless technologies for elderly implies life-share awareness, stakeholder awareness and community awareness.
This paper presents a model of personalized adaptive system based on their preferences and medical reference, which consists of a predictive positioning system, reflexive alert system and adaptive conditioning system.
