Main Article Content
Researchers have explored many methods and techniques for human detection and identification in diverse contexts. One such approach is studying variations of Radio Frequency (RF) signals (e.g., Received Signal Strength Indicator (RSSI)). RSSI based techniques have been widely used in human detection, but not for recognizing the identity of a person from a group of people due to its noisy nature. This research focused on investigating the possibilities and limitations of device-free human identification using WiFi RSSI data with machine learning-based classification techniques. To inspect the characteristics of WiFi RSSI data, the authors have conducted multiple statistical analyses. A Kalman filter was applied to minimize the noise in WiFi RSSI data, followed by a feature extraction process. Furthermore, the authors have conducted several research experiments in different configurations of receivers and participant numbers. The experimental results show that the human identification accuracy level increases with the number of receivers used for the data collection. Moreover, the authors have identified that human identification accuracy can be further improved by leveraging proper noise reduction methods and feature extraction processes. For a Kalman filter applied and feature-extracted WiFi RSSI dataset of 20 people, the Support Vector Machine (SVM) - Radial Kernel model recorded the highest average identification accuracy of 99.58%.
Select the Journal Issue