Similarity measure for anomaly detection and comparing human behaviors

A Framework for Detecting and Analyzing Behavior Changes of Elderly People over Time Using Learning Techniques

A sensor-rich environment can be exploited for elder healthcare applications. In this work, our objective was to conduct a continuous and long-term analysis of elderly's behavior for detecting changes. We indeed did not study snapshots of the behavior but, rather, analyzed the overall behavior evolution over long periods of time in order to detect anomalies. Therefore, we proposed a learning method and formalize a normal behavior pattern for elderly people related to her/his Activities of Daily Living (ADL). We also defined a temporal similarity score between activities that allows detecting behavior changes over time. During the periods of time when behavior changes occurred, we then focused on each activity to identify anomalies. Finally, when a behavior change occurred, it was also necessary to help caregivers and/or family members understand the possible pathology detected in order for them to react accordingly. Therefore, the framework presented in this article includes a fuzzy logic-based decision support system that provides information about the suspected disease and its severity.

Early anomaly detection in smart home: A causal association rule-based approach

As the world's population grows older, an increasing number of people are facing health issues. For the elderly, living alone can be difficult and dangerous. Consequently, smart homes are becoming increasingly popular. A sensor-rich environment can be exploited for healthcare applications, in particular, anomaly detection (AD). The literature review for this paper showed that few works consider environmental factors to detect anomalies. Instead, the focus is on user activity and checking whether it is abnormal, i.e., does not conform to expected behavior. Furthermore, reducing the number of anomalies using early detection is a major issue in many applications. In this context, anomaly-cause discovery may be helpful in recommending actions that may prevent risk. In this paper, we present a novel approach for detecting the risk of anomalies occurring in the environment regarding user activities. The method relies on anomaly-cause extraction from a given dataset using causal association rules mining. These anomaly causes are utilized afterward for real-time analysis to detect the risk of anomalies using the Markov logic network machine learning method. The detected risk allows the method to recommend suitable actions to perform in order to avoid the occurrence of an actual anomaly. The proposed approach is implemented, tested, and evaluated for each contribution using real data obtained from an intelligent environment platform and real data from a clinical datasets. Experimental results prove our approach to be efficient in terms of recognition rate.

An Extension of Fuzzy Linguistic Summarization Considering Probabilistic Uncertainty

Linguistic summarization provides to express large volumes of quantitative data in easy understandable natural language based forms. While various methods have been recommended for linguistic summarization, there is not any approach for linguistic summarization where possibilistic and probabilistic uncertainties exist together in data. In this study, we establish a tie between Z-number concept and type-I and type-II quantified sentences in order to calculate the truth degree of a linguistic summary covering possibilistic and probabilistic information. The proposed approach employs copulas to obtain a joint probability distribution of the variables included in type-II quantified sentence.