Performance of Weighted Random Reference Patterns on Wireless Channel Model for Gesture Recognition

In recent years, wireless sensor devices have become able to perform multiple functions such as detecting human sleep conditions, blood pressure, heartbeat, and running paths. We use the wireless channel model of a wearable Zigbee wireless sensing node to conduct research on human posture recognition. The received signal strength indicator (RSSI) obtained through the transmission and reception of wireless signals is used to obtain the model of the wireless channel. The wireless sensor nodes receive different RSSI patterns of human gesture based on which they recognize a gesture through their respective wireless channels by performing distance processing on the collected signal data. However, in this paper, we propose a weighted random reference pattern (WRRP) to achieve a higher recognition accuracy. Experimental results show that WRRP can achieve a recognition accuracy of 98%.