MEMS based eating and drinking gesture spotting using machine learning techniques

Abstract

An effective human-computer interaction for collaborative, collective and brilliant computing is provided by the Gesture recognition. Our study uses a single 3-axis accelerometer and 3-axis gyroscope for acquiring the data. Dynamic Time Warping (DTW), time and frequency domain and gesture discrepancy features are extracted from the raw data and these features are subjected to supervised machine learning algorithms such as KNN, SVM, RF and ANN. The system is evaluated depending on the data base of more than 10,000 traces obtained from five subsets. Through this study, we intend to identify eating and drinking gestures and more broadly short activities on real time environment. Many approaches for gesture recognition in specific settings have already been explored and studied using the combined interaction of several sensors. Despite these powerful hypotheses, gesture interpretation is still fragile and often depends on the individual’s positioning relative to the cameras not with the sensors.