Classification of Restlessness Level by Deep Learning of Visual Geometry Group Convolution Neural Network with Acoustic Speech and Visual Face Sensor Data for Smart Care Applications

Ing-Jr Ding,Nai-Wei Zheng

doi:10.18494/sam.2020.2881

Abstract

Classification of Restlessness Level by Deep Learning of Visual Geometry Group Convolution Neural Network with Acoustic Speech and Visual Face Sensor Data for Smart Care Applications

Highlights

The efficient utilization of sensors will bring much intelligent assistance into our everyday lives
Emotions, a deep learning strategy of using a Visual Geometry Group (VGG) convolution neural network (CNN) with acoustic speech and visual face sensor data for classifying the restlessness level is presented in this work
(2) We effectively extend CNN deep learning model applications to the area of continuous-time emotion recognition using three different types of input sensor data modality: acousticsbased vocal data, vision-based facial data, and combined vocal and facial sensor data

Summary

Introduction

The efficient utilization of sensors will bring much intelligent assistance into our everyday lives. Emotions, a deep learning strategy of using a Visual Geometry Group (VGG) convolution neural network (CNN) with acoustic speech and visual face sensor data for classifying the restlessness level is presented in this work. By using this emotion recognition system, occurrences of unexpected or dangerous events will be significantly decreased, and people experiencing restlessness will be able to receive immediate care in home, office, laboratory, and other indoor environments. Most works related to CNN- or RNN-based deep learning models achieved intuitive recognition without affection or cognition computing, such as vehicle type classification,(16) medical image segmentation,(17) speech recognition,(18) and speech reconstruction.[19]

Results

Discussion

Conclusion