Analyzing Daily-life Activities and Power Consumptions Using Tablet Sensors and Activity Annotation Web SystemReviewed
Xincheng Pan, Tomohiro Minezaki, Tatsuya Isoda, Shota Tanaka, Yuri Uchino, Sozo Inoue,
Ubicomp Workshop for Human Activity Sensing Corpus and its Application (HASCA)
This paper describes the result of concrete analysis of cor- relation between in-house activities and power consump- tions that has been conducted in order to reduce the home power consumption. Recently, various studies on power consumptions are conducted. In this study, we have exe- cuted system development, experiments by subjects, analy- sis of correlation between life-pattern and power consump- tions and proposal of electrical power reduction for the pur- pose of reducing home power consumption. A present, we are working on analysis of correlation between a life pat- tern and electrical power consumption of the residents. We asked the residents for inputting their activities for around several minutes per day using a system that we have de- veloped. We were able to collect approximately 11,745 activity inputs, approximately 7.14GB of sensor data, and power consumption data of 237,280 hours corresponding to about 4 months from 35 homes. Using the collected data, we carried out the multiple regression analysis taking an es- timated time of activity and sustained period as explanation variables and average power consumption per day as an objective variable. As the result, it was known that there is correlation between life-pattern and power consumption. In this paper, we will show that it becomes possible to execute concrete analysis of relationship between power consump- tion and activities of residents by using the label data of resident’s life pattern.