No abstract

No abstract

In recent years, there is a growing interest about assisted living environments especially for the elderly who live alone, due to the increasing number of aged people. In order for them to live safe and healthy, we need to detect abnormal behavior that may cause severe and emergent situations for the elderly. In this work, we suggest a method that detects abnormal behavior using wireless sensor networks. We model an episode that is a series of events, which includes spatial and temporal information about the subject being monitored. We define a similarity scoring function that compares two episodes taking into consideration temporal aspects. We propose a way to determine a threshold to divide episodes into two groups that reduces wrong classification. Weights on individual functions that consist the similarity function are determined experimentally so that they can produce the good results in terms of area under curve in receiver operating characteristic (ROC) curve.

Abstract-Sensor networks are often used to monitor sensitive information from the environment or track sensitive objects' movements. Anonymity has become an important problem in sensor networks, and has been widely researched in wireless ad hoc and wired networks. The limited capacity and resources of current sensor networks have brought new challenges to anonymity research. In this paper, two efficient methods are proposed based on using a one-way hash chain to dynamically change the identity of sensor nodes in order to provide anonymity, and their anonymity properties are analyzed and compared.