Real-Time Implementation of Locality Sensitive Hashing Using NI WSN and LabVIEW for Outlier Detection in Wireless Sensor Networks

Outlier detection is one of the major challenges in wireless sensor networks. To the best of our knowledge, not many have evaluated the performance of outlier detection algorithms in real time. This paper proposes a real time hardware implementation of outlier detection using locality sensitive hashing algorithm for temperature data and evaluated both in indoor and outdoor environments. NI WSN 3202 programmable nodes and NI 9792 programmable gateway is used for hardware implementation of the algorithm and LabVIEWTM software is used for programming the nodes. The LSH technique detects outliers based on the threshold value. Hence the outlier detection accuracy and precision are analyzed for various threshold values and the optimal threshold value is selected.