Artificial immune system -a new approach for the long-term data monitoring in ambient assisted living

Abstract

This paper makes a case for the use of Artificial Immune Systems (AIS) in the area of Ambient Assisted Living (AAL) for anomaly detection and long-term data monitoring. The literature review of relevant solutions developed for AAL and the use of AIS in other fields is presented. It is further highlighted that so far AIS have not been used in the area of AAL. To advocate the use of AIS in this area, the authors compare the accuracy rate of detecting abnormal activity between a simple Signal Vector Magnitude (SVM)-based threshold algorithm, two Artificial Immune System (AIS)-based monitoring algorithms, and four supervised classification algorithms (KNN, J48, Naïve Bayes, and SMO). The results of the comparison, using precision, recall, and f-measure, showed good results for the two different AIS-based monitoring algorithms, warranting current and future work.