A method of Efficient Prediction Analysis of Sleep Duration in Smart Home Based on Using PIR sensors
- 주제(키워드) Activities of Daily living(ADL) , Binary sensors , Fuzzy logic Model , sleeping duration
- 발행기관 아주대학교
- 지도교수 CHO WE DUKE
- 발행년도 2018
- 학위수여년월 2018. 2
- 학위명 석사
- 학과 및 전공 일반대학원 전자공학과
- 실제URI http://www.dcollection.net/handler/ajou/000000027171
- 본문언어 영어
- 저작권 아주대학교 논문은 저작권에 의해 보호받습니다.
초록/요약
Activities of Daily Living(ADL) refer to the activities carried out by individuals in their everyday living. ADL’s are good indicators of the health status of individuals. Proper monitoring of these activities can be achieved by attaching state-change sensors to objects in the home which gives a reflection of the object interaction, usage and subsequently the ongoing activity. The increase in the elderly Population nowadays will lead to an increase in the cost of elderly care.Also there is increase decline in sleep durations nowadays short sleep durations (≤6h) could have Cardiovascular disease risk than long sleep durations(≥7h).In this thesis by using PIR sensors and other Binary sensors from Uci binary data set and our proposed fuzzy logic model expert system we efficiently predicted activities of daily living and Sleeping duration in the home based on the acquired binary sensor data. We obtained 96.5% accuracy for Daily Living Activity Prediction and 100% accuracy Sleep duration based on our Fuzzy logic model and binary sensors data. Conclusively, with our method we can effectively predict daily living activity in the home and the sleeping duration class of the elderly home user as a means of improving the care situation of the user.
more목차
Chapter One 1
1.1 Introduction 1
1.2 Research Motivation 3
1.3 Research Questions 4
1.4 Research aim 4
1.5 Delimitation and Scope 4
1.6 Thesis Outline 5
Chapter Two 6
2.1Binary SENSORS 6
2.1.1 PIR Sensors 6
2.1.2 Pressure sensors. 7
2.1.3 Magnetic Sensor 7
2.1.4 Flush Sensor 7
2.1.5 Appliance Status Sensor 7
2.2 Fuzzy Logic 7
2.2.1 What is Fuzzy Logic? 7
2.2.2 Basic Conceptions of Fuzzy Logic 8
2.3 Logical Operation 10
2.4Linguistic Variables and Fuzzy IF-Then Rules 10
2.5 Fuzzy Inference Systems 11
2.6Defuzzification 13
2.6.1 Centroid of AreazCOA 13
2.6.2Mean-Max Method(Middle of the Maxima MOM Method) 13
2.6.3 First of Maxima (FOM) method 13
2.6.4 Last of Maxima(LOM) 13
Chapter Three 14
3.1 Data Acquisition 14
3.2Fuzzy Logic Model 15
3.3 Fuzzification 16
3.3.1 Fuzzify 16
3.4 Constructing Knowledge Base Rules 20
3.5 Defuzzification 21
Chapter Four 22
4.1 Results and Discussion 22
4.2 Method Evaluation. 33
Chapter Five 36
5.1 Summary and Conclusions 36
5.2 Future Works 36
References 37