1 : (Sunmin Lee et al.: Design and Implementation of Indoor Location Recognition System based on Fingerprint and Random Forest)., [1][2]. GPS(Global P

Size: px

Start display at page:

Download "1 : (Sunmin Lee et al.: Design and Implementation of Indoor Location Recognition System based on Fingerprint and Random Forest)., [1][2]. GPS(Global P"

민경 뇌
6 years ago
Views:

1 (JBE Vol. 23, No. 1, January 2018) (Regular Paper) 23 1, (JBE Vol. 23, No. 1, January 2018) ISSN (Online) ISSN (Print) a), a) Design and Implementation of Indoor Location Recognition System based on Fingerprint and Random Forest Sunmin Lee a) and Nammee Moon a). WiFi, Bluetooth, WiFi WiFi. WiFi Ensemble learning method. Mac %. Abstract As the number of smartphone users increases, research on indoor location recognition service is necessary. Access to indoor locations is predominantly WiFi, Bluetooth, etc., but in most quarters, WiFi is equipped with WiFi functionality, which uses WiFi features to provide WiFi functionality. The study uses the random forest algorithm, which employs the fingerprint index of the acquired WiFi and the use of the multi-value classification method, which employs the receiver signal strength of the acquired WiFi. As the data of the fingerprint, a total of 4 radio maps using the Mac address together with the received signal strength were used. The experiment was conducted in a limited indoor space and compared to an indoor location recognition system using an existing random forest, similar to the method proposed in this study for experimental analysis. Experiments have shown that the system's positioning accuracy as suggested by this study is approximately 5.8 % higher than that of a conventional indoor location recognition system using a random forest, and that its location recognition speed is consistent and faster than that of a study. Keyword : Random Forest, Fingerprint,, WiFi a) (Department of Electronic Display Engineering, Hoseo University) Corresponding Author : (Nammee Moon) mnm@hoseo.edu Tel: ORCID: ( ) (No ). Manuscript received December 12, 2017; Revised January 10, 2018; Accepted January 10, Copyright 2017 Korean Institute of Broadcast and Media Engineers. All rights reserved. This is an Open-Access article distributed under the terms of the Creative Commons BY-NC-ND ( which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited and not altered.

2 1 : (Sunmin Lee et al.: Design and Implementation of Indoor Location Recognition System based on Fingerprint and Random Forest)., [1][2]. GPS(Global Positioning System), GPS [3][4]., GPS. [5]. WiFi(Wireless Fidelity), Bluetooth, RFID(Radio frequency identification). WiFi WiFi AP [6-11]. WiFi AP, WiFi. WiFi Bluetooth Beacon. WiFi Bluetooth Beacon. Bluetooth WiFi WiFi AP Bluetooth Beacon. Bluetooth Beacon WiFi AP Bluetooth Beacon. RFID WiFi [12]. RFID. Bluetooth Beacon, RFID.,, WiFi. II. 1. WiFi 1. 2 (Step1, Step2). 1 Step1 (Location Learning). (RSSI, BSSID). 4 RSSI(Received signal strength indication, RSSI) (Step1. A), BSSID(Basic service set identifier, BSSID) (Step1.B), (Step1.C), BSSID (Step1.D). (Location Recognition) 1 Step2.. Step2.D BSSID 1. Step2.C. Step2.B BSSID 2. RSSI [13][14].. 2m. 2m 2m. WiFi WiFi AP. WiFi 3 WiFi AP.

3 (JBE Vol. 23, No. 1, January 2018) 1. Fig 1. Suggested location leaning method 3. WiFi. WiFi Google API Nexus 7. WiFi 2.4GHz 5GHz [15]. WiFi (RSSI, BSSID) 4 4 SSID RSSI Table 1. Radio map that stores RSSI values SSID WiFi AP RSSI. WiFi AP WiFi AP WiFi AP. WiFi AP,.. 2 WiFi AP. 2 5, , 20. WiFi AP 3

2 BSSID. BSSID D4:16: F2:34, 13:1F:F2:17, 52:C2:25:BD, 47:A3:2B:D2, 89:5T: C2:12. 4 AP1 13:1F:F2:17 AP2 D4:16:F2:34., BSSID RSSI 1:1.

4 1 : (Sunmin Lee et al.: Design and Implementation of Indoor Location Recognition System based on Fingerprint and Random Forest) 2. WiFi Table 2 Location accuracy and execution speed according to place learning frequency and number of learning WiFi, WiFi AP WiFi AP 5 WiFi AP. 2 BSSID. BSSID D4:16: F2:34, 13:1F:F2:17, 52:C2:25:BD, 47:A3:2B:D2, 89:5T: C2:12. 4 AP1 13:1F:F2:17 AP2 D4:16:F2:34., BSSID RSSI 1:1. D4:16:F2:34 WiFi AP, 13:1F:F2:17 WiFi AP. 2 47:A3:2B:D2 13:1F: F2:17, 47:A3:2B:D2 13:1F: F2: BSSID List. WiFi BSSID List 3 X21 X23, X30 BSSID X BSSID Fig 2. Example using BSSID radio map

0GB, Windows 10 pro 64bit, JAVA_FX., 2 3 WiFi AP 5 20. WIFI 4. Table 4. Experiment environment III.

5 (JBE Vol. 23, No. 1, January 2018) 3. BSSID List Fig 3. Example using BSSID List radio map 3. Table 3. A radio map that stores an index of another radio map RSSI BSSID.,.,.. 4.0GB, Android 7.0(Nougat) Android 4.4(KitKat). Intel Core i7-7700k 4.20GHz CPU, 16.0GB, Windows 10 pro 64bit, JAVA_FX., 2 3 WiFi AP WIFI 4. Table 4. Experiment environment III. CPU Measurement Environment of WIFI Information Samsung Exynos 8890 Mali T880 MP12 Server Experiment Environment Intel Core i7-7700k 4.20 GHz 1. WIFI 4 S7, Samsung Exynos 8890 Mali T880 MP12 CPU, Memory 4.00 GB GB OS API & Application Android Nougat 7.0 Android 4.4 (API19) Windows 10 pro 64 bit JAVA_FX

6 1 : (Sunmin Lee et al.: Design and Implementation of Indoor Location Recognition System based on Fingerprint and Random Forest) WIFI, WiFi (A), 4(B) %, % 85%. RSSI 89.17%, 100% 80%.. BSSID, %, 100% 85.00%. RSSI 89.72%, % 82.50% (A) (B) Fig 4. Location accuracy of each place(a) and Measurement time according to the number of learned data(b) 5. (A) (B)2 Fig 5. Location accuracy of each place(a) and measurement time according to the number of learned data(b)2

7 (JBE Vol. 23, No. 1, January 2018). (RSSI, BSSID) 4. WiFi. WiFi... WiFi. WiFi. (References) [1] D. Han, and S. Jung, "global indoor location recognition and indoor / outdoor integrated navigation system," The Journal of The Korean Institute of Communication Sciences, Vol.32, No.2, pp , January [2] Status of Wireless Communication Service Statistics, Ministry of science and ICT, Aug 2017, fn=650ecd0147b4ea3d5adceac f&rs=/synap/sn3hcv/result/201801/ [3] J. Im, E. Lee, H. Kim, and K. Kim, Image Grouping Technology based on Camera Sensors for Efficient Stitching of Multiple Images, The Journal of Broadcast Engineering, Vol.22, No.6, Nov [4] J. Kim, G. Jeong, Y. Hwang, P. Park, S. Park, and K. Kim, Video Similarity Generating Algorithm Improving the Speed of Various Multi-Angle Image Composition, Summer Conference of the Korean Society of Broad Engineers, Jeju, Korea, pp June [5] S. Park, Trends in Indoor Location and Service Development, Electronics and Telecommunications Research Institute, Vol.34, No.4, pp.3-9, April [6] S. Park, Y. Cho, M. Ji, and J. Kim, A Study on the trend of LBS technology and market, Electronics and Telecommunications Research Institute, Dec [7] M. Kim, B. Kim, Y. Ko, and K. Bang, Indoor Location Tracking System of Low Energy Beacon using Gaussian Filter, The Journal of Korean Institute of Information Technology, Vol.14, No.6, pp.67-74, [8] C. Yoon, T. Kim, H. Kim, and Y. Hong, Indoor Positioning Using RFID Technique, Journal of the Korea Institute of Information and Communication Engineering, Vol.20, No.1, pp , [9] S. Choi, H. Park, S. Lee, M. Son, Y. Koo, K. Park, and T. Kim, An indoor location recognition scheme combining the triangulation method and fingerprinting, Korean Institute of Information Scientists and Engineers, Vol.38, No.2, pp , [10] T. Kim and D. Lee, The Indoor Localization Algorithm using the Difference Means based on Fingerprint in Moving Wi-Fi Environment, The Journal of Korean Institute of Communications and Information Sciences, Vol.41, No.11, pp , [11] S. Son, Y. Park, B. Kim, and Y. Baek, Wi-Fi Fingerprint Location Estimation System Based on Reliability, The Journal of Korean Institute of Communications and Information Sciences, Vol.38, No.6, pp , [12] J. Kim and N. Moon, Multiple Object Tracking and Identification System Using CCTV and RFID, Korea Information Processing Society (KIPS), Vol.6, No.2, pp.51-58, [13] J. Jeong, K. Jang, and J. Kim, Target Classification Method Using Random Forest and Genetic Algorithm, Conference of the Proceeding of The Institue of Elec. and Info. Engineers, Daegu, Korea, pp , [14] R. Malhotra, R. Jangra, "Prediction & Assessment of Change Prone Classes Using Statistical & Machine Learning Techniques," Journal of Information Processing System (JIPS), pp , Aug [15] J. Choi, W. Ahn, and B. Seo, An Efficient Classification of Digitally Modulated Signals Using Bandwidth Estimation, Journal of broadcast engineering, pp , Vol.22, No.2, Mar 2017.

Random Forest) - 2016 : - 2016 ~ : - ORCID : http://orcid.

8 1 : (Sunmin Lee et al.: Design and Implementation of Indoor Location Recognition System based on Fingerprint and Random Forest) : ~ : - ORCID : - :,, (AI) : : : ~ 2003 : ~ 2008 : ~ : - ORCID : - : Social Learning,, HCI,, User Centric

<30312DC1A4BAB8C5EBBDC5C7E0C1A4B9D7C1A4C3A52DC1A4BFB5C3B62E687770>

<30312DC1A4BAB8C5EBBDC5C7E0C1A4B9D7C1A4C3A52DC1A4BFB5C3B62E687770> Journal of the Korea Institute of Information and Communication Engineering 한국정보통신학회논문지(J. Korea Inst. Inf. Commun. Eng.) Vol. 19, No. 2 : 258~264 Feb. 2015 ID3 알고리즘 기반의 귀납적 추론을 활용한 모바일 OS의 성공과 실패에 대한