Study of Fingerprinting Positioning Technique using Deep Neural Network : Deep Neural Network Fingerprinting 를 이용한 측위 기술 연구)
- 주제(키워드) Indoor positioning and navigation based on deep neural network
- 발행기관 아주대학교
- 지도교수 Chaewoo Lee
- 발행년도 2019
- 학위수여년월 2019. 8
- 학위명 석사
- 학과 및 전공 일반대학원 전자공학과
- 실제URI http://www.dcollection.net/handler/ajou/000000029275
- 본문언어 영어
- 저작권 아주대학교 논문은 저작권에 의해 보호받습니다.
초록/요약
Nowadays, there is a growing demand of location based services for indoor environments. Unfortunately, the commonly used Global Positioning System (GPS) is inefficient in most indoor environments. Since, several indoor localization methods have been investigated to address this problem. Among these methods, methods based on the receiver signal strength have been widely investigated due to their simplicity and easy implementation. Specifically, the receiver signal strength indicator (RSSI) based method known as fingerprinting localization approach has attracted significant interest due to its performance at low cost. This method does not require a specific hardware and network infrastructure. However, due to the RSSI fluctuation, most fingerprinting localization approaches do not achieve good performance as expected. This thesis first examines the performance of some artificial neural network based fingerprinting localization methods. In this part, we proposed a multiple neural network based fingerprinting localization model whose performance has been compared to those of a K-nearer neighbor (KNN) and a deep neural network based fingerprinting localization approach that exploits deep auto-encoder method to extract feature data. In the second part, we proposed a wavelet scattering transform based feature extraction method to improve the performance of deep neural network based fingerprinting method. The merit of the wavelet scattering transform based feature extraction is that the wavelet scattering transform provides multi-scale information of the RSSI data. Through different experiments, the proposed methods have achieved good localization performance compared to others state-of-the art existing fingerprinting approaches used in this study.
more목차
Contents
Abbreviations vi
Symbols vi
1 Introduction 1
1.1 Background and motivation 1
1.2 Objective 5
1.3 Outline 6
2 Related works and Preliminaries 7
2.1 Related works 7
2.2 Preliminaries 9
2.2.1 Overview of artificial neural network (ANN) 9
2.2.2 KNN-based fingerprinting localization method 12
3 Performance Comparison of Indoor Fingerprinting Techniques Based on Artificial Neural Network 14
3.1 Neural Network based fingerprinting 14
3.1.1 Single neural network model with Auto Encoder 14
3.1.2 Proposed Multiple neural networks model (MNN) 16
3.2 Position estimation and positioning error 18
3.3 Experimental comparison 19
3.3.1 Corridor environment 19
3.3.2 Office environment 21
3.3.3 Performance evaluation on publicly available dataset 22
3.4 Summary 24
4 A Wavelet Scattering Feature Extraction Approach for Deep Neural Network Based Indoor Fingerprinting Localization 25
4.1 Wavelets 25
4.2 Materials and Methods 25
4.2.1 Wavelet Scattering Transform 26
4.2.2 Neural Network Architecture 31
4.3 Experimentation Results and Analysis 32
4.3.1 Local Corridor Experiment 32
4.3.2 Experiment with a Publicly Available Dataset 33
4.4 Discussion 35
4.5 Summary 36
5 Conclusion 38
References 38
6 국문 요약 46
