Parameters weighting in elderly monitoring based on multi-criteria methods

The continuous increase in the number of elderly people today poses important challenges for countries as they have to ensure that social and health systems are aligned with the needs of the elderly. In this paper is considered the problem of older adult health monitoring based on IoT monitoring platforms and clinical systems. A large amount of data of a very diverse nature is obtained and this data comes from various sources: wearable sensors, ambient sensors, questionnaires, clinical and para-clinical investigations. This data sources are tools for health parameters monitoring. A better classification of the information achieved from monitoring of the elderly, is presented. A subset of parameters is selected to be monitored in a specific monitoring IoT based system for elderly. In order to obtain weights of parameters a weighting method is chosen from a set of weighting methods. The parameters are evaluated against the selected method. Methods often used for weighting are multi-criteria decision analysis (MCDA) methods. Using the weighting method selected, the parameters weights are calculated. The uncertainty resulting from expert's evaluations can be modeled with rough sets. Considering these aspects, a Rough AHP method for weighting parameters is proposed. These weights can be used in data analysis, creating elderly profiles, calculating health indicators and making recommendations.