Feature Selection and Activity Recognition to Detect Water Waste from Water Tap Usage

In this paper, water tap usage is examined based on water sound analysis. We focus on detecting "water waste" to make persuasion of water savings effective, where two types of water waste are defined: inter-activity water waste and intra-activity water waste. Based on a preliminary user survey, four types of basin-related activities are identified that occur with water waste. We apply a spectrum subtraction method for feature selection and propose cascaded classifiers for activity recognition. The result of an evaluation presents that the aggregate accuracies to identify inter-activity water waste and intra-activity one are 100.0 % and 81.1%, respectively.