준 지도식 GAN을 이용한 와이파이 전자지문 기반 실내 위치 인식 = Semi-supervised Generative Adversarial Network for Wi-Fi Fingerprint Based Indoor Location Awareness

다국어 초록 (Multilingual Abstract)

Indoor positioning systems are attracting increasing attention due to the demand for accurate location awareness in areas where the Global Navigation Satellite System (GNSS) does not work. The Wi-Fi access points (APs) built in to many constructions can be used to develop a Wi-Fi-fingerprint-based indoor localization method. However, such a localization method needs large amounts of fingerprint data samples to achieve superior positioning performance, which increases the costs of data collection and calibration. To reduce these resource requirements, in this paper, we propose a new semi-supervised generative adversarial network (GAN) approach that can learn an accurate positioning model by using only a small number of training samples. The proposed semi-supervised GAN is extended from a general unsupervised GAN in a way to generate fake labeled samples and to involve a classification model for realizing localization without employing an additional positioning mechanism. Based on the results of indoor experiments conducted in multi-story buildings, the proposed method outperformed a supervised deep-learning-based localization method when room-size landmark positioning was conducted.

다국어 초록 (Multilingual Abstract)

.

참고문헌 (Reference)

1 김예준, "적응형 키프레임 문턱값 기반 영상-관성 오도메트리" 제어·로봇·시스템학회 26 (26): 747-753, 2020

2 조성윤, "와이파이 수신신호세기를 사용하는 실내위치추정의 성능 향상을 위한 수정된 잔차 기반 확장 칼만 필터" 제어·로봇·시스템학회 21 (21): 684-690, 2015

3 "https://www.tensorflow.org/"

4 J. H. Yoo, "WiFi RSS-based loop closure for indoor localization using smartphone" 2015

5 M. Abbas, "WiDeep: WiFi-based accurate and robust indoor localization system using deep learning" 1-10, 2019

6 M. Arjovsky, "Wasserstein gan"

7 M. Nabati, "Using synthetic data to enhance the accuracy of fingerprint-based localization: a deep learning approach" 4 (4): 2020

8 J. Yoo, "Time-series Laplacian semi-supervised learning for indoor localization" 19 (19): 2019

9 A. Odena, "Semi-supervised learning with generative adversarial networks"

10 K. M. Chen, "Semi-supervised learning with gans for device-free fingerprinting indoor localization"

11 H. Zhang, "Selfattention generative adversarial networks" 2019

12 A. Belmonte-Hern´andez, "Recurrent model for wireless indoor tracking and positioning recovering using generative networks" 20 (20): 3356-3365, 2019

13 F. Gu, "Landmark Graph-based indoor localization" 7 (7): 8343-8355, 2020

14 J. H. Yoo, "Indoor localization without a prior map by trajectory learning from crowdsourced measurements" 66 (66): 2825-2835, 2017

15 박소영, "Hidden Markov Model을 이용한 스마트폰 다중 동작에서의 보행 항법 이동방향 개선 알고리즘" 제어·로봇·시스템학회 26 (26): 754-759, 2020

16 임덕원, "GPS 전파교란원 위치 추정을 위한 TDOA/AOA 복합 기법 설계" 제어·로봇·시스템학회 20 (20): 101-105, 2014

17 J. H. Yoo, "Feature representation of Wi-Fi signal strength for indoor location awareness" 1498-1502, 2019

18 X. Jiang, "FSELM : fusion semi-supervised extreme learning machine for indoor localization with Wi-Fi and Bluetooth fingerprints" 22 : 3621-3635, 2018

19 R. Zhou, "Device-free presence detection and localization with SVM and CSI fingerprinting" 17 (17): 7990-7999, 2017

20 X. Wang, "CSI-based fingerprinting for indoor localization : A deep learning approach" 66 (66): 763-776, 2017

21 J. Liu, "AutLoc: deep autoencoder for indoor localization with RSS fingerprinting" 1-6, 2018

22 김아솔, "AP 상대위치 정보를 고려한 향상된 WLAN RSSI 기반 실내 측위 알고리즘" 제어·로봇·시스템학회 19 (19): 146-151, 2013

23 Q. Li, "AFDCGAN: Amplitude Feature Deep Convolutional GAN for fingerprint construction in indoor localization systems" 2019