environmental perception technology based onWiFi, and some state-of-the-art techniques haveemerged. The wide application of small-scale motion recognition has aroused people’s concern.Handwritten letter is a kind of small scale motion, and the recognition for small-scale motion basedon WiFi has two characteristics. Small-scale action has little impact on WiFi signals changes inthe environment. The writing trajectories of certain uppercase letters are the same as the writingtrajectories of their corresponding lowercase letters, but they are different in size. These characteristicsbring challenges to small-scale motion recognition. The system for recognizing small-scale motion inmultiple classes with high accuracy urgently needs to be studied. Therefore, we propose MCSM-Wri,a device-free handwritten letter recognition system using WiFi, which leverages channel stateinformation (CSI) values extracted from WiFi packets to recognize handwritten letters, includinguppercase letters and lowercase letters. Firstly, we conducted data preproccessing to provide moreabundant information for recognition. Secondly, we proposed a ten-layers convolutional neuralnetwork (CNN) to solve the problem of the poor recognition due to small impact of small-scaleactions on environmental changes, and it also can solve the problem of identifying actions with thesame trajectory and different sizes by virtue of its multi-scale characteristics. Finally, we collected6240 instances for 52 kinds of handwritten letters from 6 volunteers. There are 3120 instances fromthe lab and 3120 instances are from the utility room. Using 10-fold cross-validation, the accuracyof MCSM-Wri is 95.31%, 96.68%, and 97.70% for the lab, the utility room, and the lab+utility room,respectively. Compared with Wi-Wri and SignFi, we increased the accuracy from 8.96% to 18.13% forrecognizing handwritten letters.
Spatio‐temporal multi‐scale motion descriptor from a spatially‐constrained decomposition for online action recognition
