2021/04/30 by Julian Karoliny, Thomas Blazek, Karoliny, Julian +7
Computer Science · Engineering · #Distributed Sensor Networks and Detection Algorithms #Energy Efficient Wireless Sensor Networks #FOS: Computer and information sciences #FOS: Electrical engineering #Indoor and Outdoor Localization Technologies #Information Theory (cs.IT) #Signal Processing (eess.SP) #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2104.14865
openalex publication_date 2021/04/30 · openalex created_date 2022/07/25 · openalex updated_date 2026/07/28
Industrial wireless sensor networks are becoming crucial for modern\nmanufacturing. If the sensors in those networks are mobile, the position\ninformation, besides the sensor data itself, can be of high relevance. E.g.\nthis position information can increase the trustability of a wireless sensor\nmeasurement by assuring that the sensor is not physically removed, off track,\nor otherwise compromised.\n In certain applications, localization information at cell-level, whether the\nsensor is inside or outside a room or cell, is sufficient. For this,\nlocalization using Received Signal Strength Indicator (RSSI) measurements is\nvery popular since RSSI values are available in almost all existing\ntechnologies and no direct interaction with the mobile sensor node and its\ncommunication in the network is needed. For this scenario, we propose methods\nto improve the robustness and accuracy of common machine learning classifiers,\nby using features based on short-term moments and a second classification stage\nusing Hidden Markov Models. With the data from an extensive measurement\ncampaign, we show the applicability of our method and achieve a cell-level\nlocalization accuracy of 93.5 %.\n