Behavior-based Outlier Detection for Indoor Environment

Abstract

In this paper, we introduce a system that can detect the space outlier utilization of residents in indoor environment at low cost. Our system facilitates autonomous data collection from mobile app logs and the Google app server and generates a high-dimensional dataset required to detect outlier behaviors. For this, we used density-based clustering algorithm with t-distributed stochastic neighbor embedding (t-SNE). Our system enables easy acquisition of large volumes of data required for outlier detection. Our methodology can assist spatial analysis for indoor environments housing residents and help reduce the cost of space utilization feedback.