Location estimation on mobile networks

---

Tezin Türü: Yüksek Lisans

Tezin Yürütüldüğü Kurum: İstanbul Ticaret Üniversitesi, Fen Bilimleri Enstitüsü, Türkiye

Tezin Onay Tarihi: 2021

Tezin Dili: Türkçe

Öğrenci: AHMED HAKAN KILIÇ

Danışman: BOYACI ALİ

Özet:

ÖZET Bu tez, Baz İstasyonu (BTS) verilerini kullanarak Mobil ağlarda konum tahminini raporlamaktadır. İşlenen veriler sahadan TA (Timing Advance), RSRP (Reference Signal Received Power) ve RSRQ (Reference Signal Received Quality) ölçümleri olarak toplanmıştır. Ölçümlere karşılık gelen Global Konumlandırma Sistemi (GPS) verileri de toplanmıştır. Lokasyon tahminleri gerçek lokasyonla (GPS) karşılaştırılmıştır. Anahtar Kelimeler: Baz istasyonu, GPS, mobil ağlar, makine öğrenmesi, RSRP, RSRQ, timing advance (TA). ABSTRACT This thesis reports the location estimation on Mobile networks using Base Station (BTS) data. Processed data have been collected from the field as TA (Timing Advance), RSRP (Reference Signal Received Power), and RSRQ (Reference Signal Received Quality) measurements. We also gathered the corresponding Global Positioning System (GPS) to the measurements. Location estimation results compared to the actual location. Keywords: Base station, GPS, mobile networks, machine learning, RSRP, RSRQ, timing advance (TA). CONTENTS CONTENTS . i ABSTRACT . ii ÖZET. iii ACKNOWLEDGEMENTS . iv FIGURES . v TABLES . vii SYMBOLS AND ABBREVIATIONS . viii 1. INTRODUCTION . 1 2. LITERATURE REVIEW . 2 3. DATA AND PROBLEM . 4 4. METHODOLOGY . 6 4. 2 Machine Learning Algorithms . 6 4. 2. 1 Gaussian process regression . 7 4. 2. 2 KNeighbor regression (KNN) . 7 4. 2. 3 Linear regression. 8 4. 2. 4 Automatic relevance determination regression (ARD) . 8 4. 2. 5 Least angle regression lasso (LARS) . 8 4. 2. 6 Least absolute shrinkage and selection operator (LASSO) . 8 4. 2. 7 Ridge regression . 9 4. 2. 8 Bayesian ridge regression . 9 4. 3 Regression metrics . 9 4. 3. 1 Explained variance . 10 4. 3. 2 Mean squared logarithmic error (MSLE) . 14 4. 3. 3 R2 error . 19 4. 3. 4 Mean absolute error (MAE) . 23 4. 3. 5 Mean squared error (MSE) . 28 4. 3. 6 Root mean squared error (RMSE) . 32 4. 4 Histogram of the Algorithms . 37 5. CONCLUSION AND IMPLICATIONS . 38 REFERENCES . 40 APPENDICES . 42 Appendix A. Source Code . 42 BIBLIOGRAPHY . 47