WKNN indoor Wi-Fi localization method using k-means clustering based radio mapping
Siyang Liu, Raul de Lacerda, Jocelyn Fiorina
Abstract
Wifi fingerprinting using received signal strength has been widely studied for indoor localization. Classic similarity-based methods like weighted K-nearest neighbor (WKNN) localize targets by searching for the best matching fingerprint in the dataset. Performance of these methods suffers from RSS variance and they are slow under a large size of fingerprint dataset. In this paper, we propose a WKNN localization strategy using k-means clustering radio mapping that balances localization precision and computational complexity.
Topics & Concepts
RSSFingerprint (computing)Computer scienceCluster analysisSignal strengthSimilarity (geometry)Matching (statistics)Fingerprint recognitionk-nearest neighbors algorithmPattern recognition (psychology)Artificial intelligenceVariance (accounting)Data miningWireless sensor networkMathematicsComputer networkStatisticsImage (mathematics)Operating systemAccountingBusinessIndoor and Outdoor Localization TechnologiesSpeech and Audio ProcessingEnergy Efficient Wireless Sensor Networks