Parvin Malekzadeh, Mohammad Salimibeni, M. Atashi, Mihai Barbulescu, K. Plataniotis, Arash Mohammadi
{"title":"基于高斯混合的蓝牙低能量传感器室内定位","authors":"Parvin Malekzadeh, Mohammad Salimibeni, M. Atashi, Mihai Barbulescu, K. Plataniotis, Arash Mohammadi","doi":"10.1109/SENSORS43011.2019.8956950","DOIUrl":null,"url":null,"abstract":"A probabilistic Gaussian mixture model (GMM) of the Received Signal Strength Indicator (RSSI) is proposed to perform indoor localization via Bluetooth Low Energy (BLE) sensors. More specifically, to deal with the fact that RSSI-based solutions are prone to drastic fluctuations, GMMs are trained to more accurately represent the underlying distribution of the RSSI values. For assigning real-time observed RSSI vectors to different zones, first a Kalman Filter is applied to smooth the RSSI vector and form its Gaussian model, which is then compared in distribution with learned GMMs based on Bhattacharyya distance (BD) and via a weighted K-Nearest Neighbor (K-NN) approach.","PeriodicalId":6710,"journal":{"name":"2019 IEEE SENSORS","volume":"147 1","pages":"1-4"},"PeriodicalIF":0.0000,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"3","resultStr":"{\"title\":\"Gaussian Mixture-based Indoor Localization via Bluetooth Low Energy Sensors\",\"authors\":\"Parvin Malekzadeh, Mohammad Salimibeni, M. Atashi, Mihai Barbulescu, K. Plataniotis, Arash Mohammadi\",\"doi\":\"10.1109/SENSORS43011.2019.8956950\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"A probabilistic Gaussian mixture model (GMM) of the Received Signal Strength Indicator (RSSI) is proposed to perform indoor localization via Bluetooth Low Energy (BLE) sensors. More specifically, to deal with the fact that RSSI-based solutions are prone to drastic fluctuations, GMMs are trained to more accurately represent the underlying distribution of the RSSI values. For assigning real-time observed RSSI vectors to different zones, first a Kalman Filter is applied to smooth the RSSI vector and form its Gaussian model, which is then compared in distribution with learned GMMs based on Bhattacharyya distance (BD) and via a weighted K-Nearest Neighbor (K-NN) approach.\",\"PeriodicalId\":6710,\"journal\":{\"name\":\"2019 IEEE SENSORS\",\"volume\":\"147 1\",\"pages\":\"1-4\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2019-10-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"3\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2019 IEEE SENSORS\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/SENSORS43011.2019.8956950\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2019 IEEE SENSORS","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/SENSORS43011.2019.8956950","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Gaussian Mixture-based Indoor Localization via Bluetooth Low Energy Sensors
A probabilistic Gaussian mixture model (GMM) of the Received Signal Strength Indicator (RSSI) is proposed to perform indoor localization via Bluetooth Low Energy (BLE) sensors. More specifically, to deal with the fact that RSSI-based solutions are prone to drastic fluctuations, GMMs are trained to more accurately represent the underlying distribution of the RSSI values. For assigning real-time observed RSSI vectors to different zones, first a Kalman Filter is applied to smooth the RSSI vector and form its Gaussian model, which is then compared in distribution with learned GMMs based on Bhattacharyya distance (BD) and via a weighted K-Nearest Neighbor (K-NN) approach.