Wi-Fi Parmak İzi Kullanan İç Mekan Konum Belirleme Yöntemlerinin Karşılaştırılması

Yıl 2024, Cilt: 6 Sayı: 3

Muhammed Fahri Ünlerşen , Mustafa Yağcı

Öz

Navigasyon sistemleri günlük hayatımızın vazgeçilmez bir parçası haline gelmiştir. Bunun gerçekleştirile bilinmesi için ise yerel konumun tespiti gereklidir. En yaygın kullanılan konum tespit metodu Global Konumlama Sistemidir (GPS). GPS sinyalleri kapalı alanlara çoğu zaman giremez. Bu sebeple kapalı alanlarda navigasyon için GPS kullanımı verimli değildir. Bu sebeple kapalı alanlarda navigasyon için konum belirleme işlemi için farklı metotlar geliştirilmiştir. Bunların başta gelen metodu Wi-Fi parmak izi ile pozisyon tahminidir. Bu konuda yapılmış birçok çalışma mevcuttur. Bu makalede, kablosuz ağ sinyal gücüne dayalı iç mekân konum tahmininde farklı makine öğrenimi yöntemlerinin performansı incelenmiştir. Bir veri kümesi kullanılarak yapay sinir ağları, k-NN, doğrusal regresyon, destek vektör makineleri, karar ağacı ve rastgele orman gibi yöntemlerin uygulanması ve sonuçların karşılaştırılması yapılmıştır. Kullanılan veri tabanı detaylı olarak açıklanmıştır. Bu veri tabanının makine öğrenme algoritmalarına nasıl uygulandığı izah edilmektedir. Sonuçlarda en başarılı metot ve başarıya etki eden faktörler değerlendirilmiştir.

Anahtar Kelimeler

Wi-Fi parmak izi, Kapalı alan konum kestirimi, Yapay zekâ, Sinir ağları

Comparison of Indoor Location Determination Methods That Use Wi-Fi Fingerprinting

Öz

Navigation systems have become an indispensable part of our daily lives. In order for this to be achieved, it is necessary to determine the local location. The most commonly used location determination method is the Global Positioning System (GPS). GPS signals often cannot penetrate closed areas. For this reason, using GPS for navigation in closed areas is not efficient. For this reason, different methods have been developed for position determination for navigation in closed areas. The primary method of these is position estimation via Wi-Fi fingerprint. There are many studies done on this subject. In this article, the performance of different machine learning methods in indoor location estimation based on wireless network signal strength is examined. Using a dataset, methods such as artificial neural networks, k-NN, linear regression, support vector machines, decision trees, and random forests were applied, and the results were compared. The database used is explained in detail. It is explained how this database is applied to machine learning algorithms. In the results, the most successful method and the factors affecting success were evaluated.

Anahtar Kelimeler

Wi-Fi fingerprint, Indoor location estimation, Artificial intelligence, Neural network

Kaynakça

• S.A. Celtek, M. Durgun, H. Soy, Internet of things based smart home system design through wireless sensor / actuator networks, 2nd International Conference on Advanced Information and Communication Technologies, AICT 2017- Proceedings. (2017) 15-18. doi:10.1109/AIACT.2017.8020054
• S. Altunkaya, S. Kara, N. Görmüş, S. Herdem, Comparison of first and second heart sounds after mechanical heart valve replacement, Computer Methods in Biomechanics and Biomedical Engineering. 16 (2013), 368-380. doi:10.1080/10255842.2011.623672
• T.F. Ateş, H. Açıkgöz, A.O. Özkan, Pasif RFID Etiket konumunu belirlemeye yönelik UHF anten tasarımı, Necmettin Erbakan Üniversitesi Fen ve Mühendislik Bilimleri Dergisi. 1 (2019), 112-117.
• E. Jonuzi, H.Z. Selvi, Enhancing map comprehension via symbols: Developing symbols for thematic maps based on children’s cognitive development, Necmettin Erbakan Üniversitesi Fen ve Mühendislik Bilimleri Dergisi. 5 (2023), 88-110. doi:10.47112/NEUFMBD.2023.12
• A. Akkaş, M. Özcan, Askılı kumlama makinesinin PLC ile kontrolü sayesinde elde edilen kazanımlar, Necmettin Erbakan Üniversitesi Fen ve Mühendislik Bilimleri Dergisi. 1 (2019) 118-127
• M.S. Endiz, M. Özcan, M.A. Erismis, M. Yagci, H. Günay, The simulation and production of glow plugs based on thermal modeling, Turkish Journal of Electrical Engineering and Computer Sciences. 23 (2015), 2197-2207. doi:10.3906/elk-1307-5.
• M. Demirtas, M.A. Erismis, S. Gunes, A Lossy Capacitance Measurement Circuit Based on Analog Lock-in Detection, Elektronika ir Elektrotechnika. 26 (2020), 4-10. doi:10.5755/J01.EIE.26.5.25809
• E. Madenci, Fonksiyonel derecelendirilmiş malzeme plakların statik analizinde mikro-mekanik modellerin katkısı, Necmettin Erbakan Üniversitesi Fen ve Mühendislik Bilimleri Dergisi. 5 (2023), 23-37.
• S. Zaidman, Global Positioning System Wide Area Augmentation System (WAAS) Performance Standard, 1st bs, Washington, DC, 2008.
• J.G. Grimes, Global Positioning System Standard Positioning Service Performance Standard, Washington, 2008.
• A. Sha, 5 GPS Alternatives You Should Know, Beebom. (2020).
• Satellite Navigation - GPS - How It Works | Federal Aviation Administration, (t.y.). https://www.faa.gov/about/office_org/headquarters_offices/ato/service_units/techops/navservices/gnss/gps/howitworks (erişim 29 Ekim 2023).
• S. Öğütçü, B.N. Özdemir, S. Alçay, İ. Buğdaycı, GPS, GLONASS, Galileo ve BeiDou GNSS sistemlerinin 1. ve 2. temel frekanslarının doluluk analizi, Necmettin Erbakan Üniversitesi Fen ve Mühendislik Bilimleri Dergisi. 5 (2023), 14-22.
• İ.D. Argun, B. Nalbant, Using classification algorithms in data mining in diagnosing breast cancer, Advances in Artificial Intelligence Research. 2 (2022), 65-70. doi:10.54569/AAIR.1142519
• M.F. Unlersen, K. Sabanci, M. Özcan, Determining cervical cancer possibility by using machine learning methods, International Journal of Latest Research in Engineering and Technology (IJLRET). 03 (2017), 65-71.
• M.E. Sonmez, K. Sabanci, N. Aydin, Convolutional neural network-support vector machine-based approach for identification of wheat hybrids, European Food Research and Technology. 250 (2024), 1353-1362. doi:10.1007/S00217-024-04473-4/FIGURES/6
• E. Atagün, I.D. Argun, Performance analysis of data mining software with parametric changes, International Journal of Forensic Software Engineering. 1 (2020), 115. doi:10.1504/IJFSE.2020.110624
• T. King, S. Kopf, T. Haenselmann, C. Lubberger, W. Effelsberg, COMPASS: A probabilistic indoor positioning system based on 802.11 and digital compasses, WiNTECH 2006 - Proceedings of the First ACM International Workshop on Wireless Network Testbeds, Experimental Evaluation and Characterization (co-located with MobiCom 2006). 2006 (2006), 34-40. doi:10.1145/1160987.1160995
• J. Torres-Sospedra, R. Montoliu, A. Martinez-Uso, J.P. Avariento, T.J. Arnau, M. Benedito-Bordonau, J. Huerta, UJIIndoorLoc: A new multi-building and multi-floor database for WLAN fingerprint-based indoor localization problems, IPIN 2014 - 2014 International Conference on Indoor Positioning and Indoor Navigation. (2014), 261-270. doi:10.1109/IPIN.2014.7275492
• M.F. Unlersen, ABC-ANN Based Indoor Position Estimation Using Preprocessed RSSI, Electronics (Switzerland). 11 (2022). doi:10.3390/ELECTRONICS11234054
• X. Yang, J. Wang, D. Song, B. Feng, H. Ye, A novel NLOS error compensation method based IMU for UWB ındoor positioning system, IEEE Sensors Journal. 21 (2021), 11203-11212. doi:10.1109/JSEN.2021.3061468
• M. Luo, J. Zheng, W. Sun, X. Zhang, WiFi-based ındoor localization using clustering and fusion fingerprint, (2021). doi:10.23919/CCC52363.2021.9549410
• F. Qin, T. Zuo, X. Wang, CCpos: WiFi fingerprint ındoor positioning system based on CDAE-CNN, (2021). doi:10.3390/s21041114
• M. Anjum, M.A. Khan, A. Hassan, A. Mahmood, H.K. Qureshi, M. Gidlund, RSSI fingerprinting-based localization using machine learning in LoRa networks, IEEE Internet of Things Magazine. 3 (2020). doi:10.1109/IOTM.0001.2000019
• L. Polak, S. Rozum, M. Slanina, T. Bravenec, T. Fryza, A. Pikrakis, Received signal strength fingerprinting-based ındoor location estimation employing machine learning, Sensors. 21 (2021), 4605. doi:10.3390/S21134605
• Ö. Yildiz, T. Dayanan, and İ. D. Argun, “Comparison of accuracy values of biomedical data with different applications decision tree method,” in 2018 Electric Electronics, Computer Science, Biomedical Engineerings’ Meeting (EBBT), 2018, pp. 1–4. doi: 10.1109/EBBT.2018.8391439
• S. Xia, Y. Liu, G. Yuan, M. Zhu, Z. Wang, S. Zlatanova, K. Khoshelham, G. Sithole, W. Kainz, Indoor Fingerprint Positioning Based on Wi-Fi: An Overview, ISPRS International Journal of Geo-Information. 6 (2017). doi:10.3390/ijgi6050135
• S. He, S..-H.G. Chan, Wi-Fi Fingerprint-Based ındoor positioning: Recent advances and comparisons, IEEE Communications Surveys & Tutorials. 18 (2016), 466-490. doi:10.1109/COMST.2015.2464084
• M. Zhou, Y. Long, W. Zhang, Q. Pu, Y. Wang, W. Nie, W. He, Adaptive genetic algorithm-aided neural network with channel state ınformation tensor decomposition for ındoor localization, IEEE Transactions on Evolutionary Computation. 25 (2021), 913-927. doi:10.1109/TEVC.2021.3085906
• J. Bi, Y. Wang, B. Yu, H. Cao, T. Shi, L. Huang, Supplementary open dataset for WiFi indoor localization based on received signal strength, Satellite Navigation. 3 (2022), 1-15. doi:10.1186/S43020-022-00086-Y/FIGURES/7
• K. Sabancı, M.F. Ünlersen, K. Polat, Classification of different forest types with machine learning algorithms, içinde: 22nd Annual ınternational scientific conference research for rural development, Latvia Univ Life Sciences & Technologies, 2016: ss. 254-260.
• M.F. Unlersen, E. Yaldiz, Direction of arrival estimation by using artificial neural networks, Proceedings - UKSim-AMSS 2016: 10th European Modelling Symposium on Computer Modelling and Simulation. (2017) 242-245. doi:10.1109/EMS.2016.049
• M. Hacıbeyoğlu, M. Çeli̇k, Ö. Erdaş Çi̇çek, K en yakın komşu algoritması ile binalarda enerji verimliliği tahmini, Necmettin Erbakan Üniversitesi Fen ve Mühendislik Bilimleri Dergisi. 5 (2023), 65-74. doi:10.47112/NEUFMBD.2023.10
• X. Su, X. Yan, C.L. Tsai, Linear regression, Wiley Interdisciplinary Reviews: Computational Statistics. 4 (2012), 275-294. doi:10.1002/WICS.1198
• K. Sabancı, M. Akkaya, Classification of different wheat varieties by using data mining algorithms, International Journal of Intelligent Systems and Applications in Engineering. 4 (2016), 40-44. doi:10.18201/IJISAE.62843
• C.D. Kumral, A. Topal, M. Ersoy, R. Çolak, T. Yiğit, Random forest algoritmasının FPGA üzerinde gerçekleştirilerek performans analizinin yapılması, El-Cezeri. 9 (2022) 1315-1327. doi:10.31202/ECJSE.1134799
• L.S. Lin, Z.Y. Chen, Y. Wang, L.W. Jiang, Improving anomaly detection in IoT-sed solar energy system using SMOTE-PSO and SVM Model, içinde: Frontiers in Artificial Intelligence and Applications, IOS Press BV, 2022: ss. 123-131. doi:10.3233/FAIA220434
• W.S. Noble, What is a support vector machine?, Nature Biotechnology. 24 (2006), 1565-1567. doi:10.1038/NBT1206-1565
• J. Demšar, T. Curk, A. Erjavec, Č. Gorup, T. Hočevar, M. Milutinovič, M. Možina, M. Polajnar, M. Toplak, A. Starič, M. Štajdohar, L. Umek, L. Žagar, J. Žbontar, M. Žitnik, B. Zupan, Orange: data mining toolbox in Python, The Journal of Machine Learning Research. 14 (2013), 2349-2353.