Title :
Feature Selection and Activity Recognition to Detect Water Waste from Water Tap Usage
Author :
Trang Thuy Vu ; Sokan, Akifumi ; Nakajo, H. ; Fujinami, Kenta ; Suutala, Jaakko ; Siirtola, Pekka ; Alasalmi, T. ; Pitkanen, A. ; Roning, Juha
Author_Institution :
Dept. of Comput. & Inf. Sci., Tokyo Unversity of Agric. & Technol., Tokyo, Japan
Abstract :
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.
Keywords :
environmental science computing; learning (artificial intelligence); pattern classification; wastewater; activity recognition; feature selection; inter-activity water waste; intra-activity water waste; spectrum subtraction method; water sound analysis; water tap usage; water waste detection; Accuracy; Error analysis; Microphones; Monitoring; Real time systems; Sensors; Water conservation;
Conference_Titel :
Embedded and Real-Time Computing Systems and Applications (RTCSA), 2011 IEEE 17th International Conference on
Conference_Location :
Toyama
Print_ISBN :
978-1-4577-1118-3
DOI :
10.1109/RTCSA.2011.47
