A Deep Learning and RSSI Based Approach for Indoor Positioning

Yuksel K. D., Töreyin B. U.

26th IEEE Signal Processing and Communications Applications Conference (SIU), İzmir, Türkiye, 2 - 05 Mayıs 2018 identifier identifier

  • Yayın Türü: Bildiri / Tam Metin Bildiri
  • Cilt numarası:
  • Doi Numarası: 10.1109/siu.2018.8404614
  • Basıldığı Şehir: İzmir
  • Basıldığı Ülke: Türkiye
  • İstanbul Teknik Üniversitesi Adresli: Evet

Özet

Indoor positioning and navigation systems are getting popular nowadays. There are different types of products in the way of accuracy, cost and power consumption in the field. Especially in the last couple of years, RSSI (Received Signal Strength Indicator) based positioning algorithms have studied but the results are not sufficient and there is no exact way decided to overcome this problem. In this paper, we will explain a method that combines Deep Learning and BLE (Bluetooth Low Energy) Fingerprinting method to get better accurate results.