Ranged based localization by Classified Bat Algorithm via Zigbee

Abstract

In the era of wireless network, wireless devices can be found in our daily life easily. Localization algorithms by using those devices are concerned since it can implement in medical, logistic or others practical usage. However, traditional algorithms perform with poor accuracy and long calculation period which is not benefit for typical usage. In this project, I purposed a method using probabilistic model to improve the accuracy of the localization algorithm. To achieve this, I used a hybrid localization method which merged passive method with active method. The localization area is focused into a smaller area which helps to minimize the range and error by using a passive method, Naive Bayes Classifier. After the focusing process, I used an optimization method called Bat Algorithm to search the best fit coordinate within the focused area. This combined algorithm is named Classified Bat Algorithm. To examine it, I have implemented this algorithm in two existing locations, including indoor and outdoor environment. The result shows that the performance has improved compared to the standalone active localization method. The overall accuracy and computation time have been improved by 25% and 41% respectively.