[논문]Wi-Fi 환경에서 가상 Access Point를 이용한 실내 위치추정 알고리즘의 성능분석

이동명

doi:10.3745/ktccs.2017.6.3.113

초록
AI-Helper

실내 Wi-Fi환경에서 위치추정 정확도를 향상시키기 위한 위치추정에 대한 연구가 수년 동안 계속되어 오고 있다. 핑거프린트 기법 및 전파모델은 실내 위치추정에 있어서 매우 중요한 기술이다. 추가적인 하드웨어 없이 저비용으로 핑거프린트 기법을 사용하는 다양한 위치추정 시스템에 대한 연구가 진행되고 있다. 그러나 실내 위치추정 모델에서 VAP (virtual access points) 개념을 사용하여 이러한 목표를 실현한 사례는 매우 드물다. 본 논문은 Wi-Fi 환경의 핑거프린트 기반에서 VAP를 사용한 실내 위치추정 시스템의 아이디어를 제시하였다. 이 아이디어의 핵심은 실제 실내 Wi-Fi 환경에서 VAP를 사용하여 AP의 역할을 수행 할 수 있다. 제안 알고리즘의 성능분석을 위하여 4개의 시나리오를 사용하여 실험한 결과, 1개의 AP 대신에 2개의 VAP를 사용했을 때 가장 우수한 결과가 도출되었으며, 실험의 3번째 경우인 3개의 AP와 2개의 VAP를 사용했을 때 3.99 미터의 가장 낮은 위치오차가 발생하였음을 확인하였다.

Abstract ▼ AI-Helper

In recent years, indoor localization has been researched for the improvement of its localization accuracy capability in Wi-Fi environment. The fingerprint and RF propagation models has been the main approach in determining indoor positioning. With the use of fingerprint, a low-cost, versatile locali...

In recent years, indoor localization has been researched for the improvement of its localization accuracy capability in Wi-Fi environment. The fingerprint and RF propagation models has been the main approach in determining indoor positioning. With the use of fingerprint, a low-cost, versatile localization system can be achieved without the use of external hardware. However, only a few research have been made on virtual access points (VAPs) among indoor localization models. In this paper, the idea of indoor localization system using fingerprint with the addition of VAP in Wi-Fi environment is discussed. The idea is to virtually add APs in the existing indoor Wi-Fi system, this would mean additional virtually APs in the network. The experiments of the proposed algorithm shows the positive results when 2VAPs are used compared with only APs. A combination of 3APs and 2VAPs in the 3rd case had the lowest average error of 3.99 among its 4 scenarios.

주제어

AI 본문요약
AI-Helper

* AI 자동 식별 결과로 적합하지 않은 문장이 있을 수 있으니, 이용에 유의하시기 바랍니다.

문제 정의

This study proves that increasing of the AP count during localization improves the localization accuracy. Furthermore, additional AP can be achieved using VAPs making it possible to increase AP counts in a system with already fixed APs.

제안 방법

The functions of this system are divided into the training phase (offline phase) and the fingerprint based localization phase (online phase). A radio map is constructed based on the received signal strength (RSS) of existing APs in the indoor environment in the training phase, and the location is estimated by K-nearest neighbors (KNN) algorithm to find the nearest Euclidean distance of the radio map from the observed RSS vector in the localization phase, respectively.
This is mainly due to low correlation or VAPs with APs which was affected by the placement of the VAP. Due to these results another experiment was done to locate a better location of the VAPs.
It had been identified that the certain factors such as the weather conditions, building layout and frequency bandwidth significantly affects the accuracy of localization. The study also proposed the encouraging results on the use of VAPs as it has higher accuracy compared to using only APs. The addition of VAPs had indeed a positive impact to the study with minimal effort in preparation.
Two VAPs were added to the existing 3 APs, whereas one VAP was placed in the exact opposite of one existing AP and the other VAP was placed in the middle of the indoor environment. Though the experiments cause the best results, it was done with a series of trials and simulations in order to determine the VAP location. This was done during the data collection phase for the fingerprint map and takes more time than conventional data collection where RSSIs of the existing APs are collected.

데이터처리

During the fingerprinting based localization phase, VAPs will be powered off, leaving only the 3APs to provide the RSS for the mobile user. Once RSS is obtained by the user, the measured RSS of the 3 APs will also be used to calculate the VAP value with the help of the regression coefficient. Once the RSS of VAP is calculated, it will then be compared with the fingerprint map to determine the least Euclidian distance.
Even though the increasing of APs has been one of popular idea in order to improve the Wi-Fi fingerprint scheme, the VAP can be used to solve this problem for cost-effective solution. The VAP can be realized by a statistical model with correlation. However, because the creation of VAP requires a great amount of time, the indoor localization algorithm for decreasing the amount of time to make VAP is proposed to overcome this problem in this paper.

이론/모형

In order to make the VAP model, a statistical method will be used. The VAP related data added in the fingerprint map is the collected data during the data collection phase making one AP plus some VAPs matrix.

성능/효과

Several attempts for seizing the VAP placement was made and some locations has low correlation to existing APs causing low placement accuracy. It is confirmed that the VAP correlation with at least 1 or 2 APs is should be greater than 70% in order to achieve the desired placement accuracy.

참고문헌 (8)

Feng Xia, Laurence T. Yang, Lizhe Wang, and Alexey Vinel, "Internet of Things," International Journal of Communication Systems 25, Published online in Wiley Online Library (wileyonlinelibrary.com), DOI: 10.1002/dac.2417, pp.1101-1102, 2012.

상세보기
P. Bahl and V. Padmanabhan, "RADAR: an in-building RF-based user location and tracking system," in Proc. INFOCOM'00: Nineteenth Annual Joint Conference of the IEEE Computer and Communications Societies, Vol.2, Tel Aviv, Israel, pp.775-784, 2000.
A. K. M. Mahtab Hossain, Hien Nguyen Van and Wee-Seng Soh "Fingerprint-Based Location Estimation with Virtual Access Points," 2008 Proceedings of 17th International Conference on Computer Communications and Networks, pp.1-6, Aug., 2008.
S. Sen et al., "Precise Indoor Localization Using PHY Layer Information," Proc. 10th ACM Workshop. Hot Topics in Networks, pp.18:1-18:6, 2011.
Arsham Farshad, Jiwei Li, and Mahesh K. Marina, "A Microscopic Look at WiFi Fingerprinting for Indoor Mobile Phone Localization in Diverse Environments," 2013 International Conference on Indoor Positioning and Indoor Navigation, pp.1-10, 28-31 Oct., 2013.
K. Kaemarungsia and P. Krishnamurthy, "Analysis of WLANs Received Signal Strength Indication for Indoor Location Fingerprinting," Pervasive and Mobile Computing, Vol.8, No.2, pp.292-316, 2011.
B. Labinghisa and D. M. Lee, "A Study on Indoor Localization Model based on Access Points and Virtual Access Points in Wi-Fi Environment," in Proceedings of Summer Conference of KICS, pp.145-146, Jun., 2016.
B. Labinghisa and D. M. Lee, "Indoor Localization Algorithm using Virtual Access Points in Wi-Fi Environment," KIPS Fall Conference Proceedings, Vol.23, Issue 2, pp.168-171, Nov., 2016.

이 논문을 인용한 문헌

저자의 다른 논문 :

LOADING...

내보내기 구분	파일저장 인쇄 메일전송
구성항목	기본정보 상세정보 관리번호, 논문명, 저널/프로시딩명, 저자 , 발행년, 권, 호, 시작페이지, 끝페이지, 발행기관 관리번호, 논문명, 대등논문명, 저자 , 저널/프로시딩명, 발행기관, 발행년, 발행언어, 권, 호, 시작페이지, 끝페이지, ISBN, ISSN, 주제분야, 키워드, 초록(한글), 초록(영문), 저자(소속기관)
저장형식	Text(ASCII format) Excel format RefWorks Direct Export RIS format (for Reference Manager, ProCite, EndNote), Scholar's Aids, Mendeley
메일정보	받는사람 (필수) @ 보내는사람 (선택) @ 제목 내용 KISTI 검색결과 이메일 서비스
안내	총 건의 자료가 검색되었습니다. 다운받으실 자료의 인덱스를 입력하세요. (1-10,000) 검색결과의 순서대로 최대 10,000건 까지 다운로드가 가능합니다. 데이타가 많을 경우 속도가 느려질 수 있습니다.(최대 2~3분 소요) 다운로드 파일은 UTF-8 형태로 저장됩니다. 파일의 내용이 제대로 보이지 않을실 때는 웹브라우저 상단의 보기 -> 인코딩 -> 자동선택 여부를 확인하십시오. ~ Text(ASCII format) Excel format

연합인증

Wi-Fi 환경에서 가상 Access Point를 이용한 실내 위치추정 알고리즘의 성능분석
Performance Analysis of Indoor Localization Algorithm Using Virtual Access Points in Wi-Fi Environment 원문보기

초록
AI-Helper

Abstract ▼ AI-Helper

주제어

AI 본문요약
AI-Helper

문제 정의

제안 방법

데이터처리

이론/모형

성능/효과

참고문헌 (8)

이 논문을 인용한 문헌

저자의 다른 논문 :

연구과제 타임라인

관련 콘텐츠

원문 보기

원문 URL 링크

오픈액세스(OA) 유형

이 논문과 함께 이용한 콘텐츠

AI-Helper ※ AI-Helper는 오픈소스 모델을 사용합니다.

선택된 텍스트

연합인증

Wi-Fi 환경에서 가상 Access Point를 이용한 실내 위치추정 알고리즘의 성능분석 Performance Analysis of Indoor Localization Algorithm Using Virtual Access Points in Wi-Fi Environment 원문보기

초록 용어보기논문에서 용어와 풀이말을 자동 추출한 결과로, 시범 서비스 중입니다. AI-Helper

Abstract ▼ AI-Helper

주제어

AI 본문요약 엑셀 다운로드 AI-Helper

문제 정의

제안 방법

데이터처리

이론/모형

성능/효과

참고문헌 (8)

이 논문을 인용한 문헌

저자의 다른 논문 :

이동명 (36)

연구과제 타임라인

전체(0) 논문(0) 특허(0) 보고서(0)

전체(0) 논문(0) 특허(0) 보고서(0)

관련 콘텐츠

원문 보기

원문 URL 링크

오픈액세스(OA) 유형

이 논문과 함께 이용한 콘텐츠

AI-Helper ※ AI-Helper는 오픈소스 모델을 사용합니다.

선택된 텍스트

Wi-Fi 환경에서 가상 Access Point를 이용한 실내 위치추정 알고리즘의 성능분석
Performance Analysis of Indoor Localization Algorithm Using Virtual Access Points in Wi-Fi Environment 원문보기

초록
AI-Helper

AI 본문요약
AI-Helper