High-precision human activity classification via radar micro-doppler signatures based on deep neural network

2021 ◽  
Author(s):  
J. Li ◽  
X. Chen ◽  
G. Yu ◽  
X. Wu ◽  
J. Guan
Keyword(s):  
Neural Network ◽  
High Precision ◽  
Human Activity ◽  
Deep Neural Network ◽  
Activity Classification

scholarly journals Parametric Convolutional Neural Network for Radar-based Human Activity Classification Using Raw ADC Data

2020 ◽  
Author(s):  
Thomas Stadelmayer ◽  
Avik Santra
Keyword(s):  
Neural Network ◽  
Human Activity ◽  
Recognition System ◽  
Radar Data ◽  
Fast Time ◽  
Activity Classification ◽  
Radar Sensors ◽  
Equivalent State ◽  
Machine Interface

Radar sensors offer a promising and effective sensing modality for<br>human activity classification. Human activity classification enables several smart<br>homes applications for energy saving, human-machine interface for gesture<br>controlled appliances and elderly fall-motion recognition. Present radar-based<br>activity recognition system exploit micro-Doppler signature by generating Doppler<br>spectrograms or video of range-Doppler images (RDIs), followed by deep neural<br>network or machine learning for classification. Although, deep convolutional neural<br>networks (DCNN) have been shown to implicitly learn features from raw sensor<br>data in other fields, such as camera and speech, yet for the case of radar DCNN<br>preprocessing followed by feature image generation, such as video of RDI or<br>Doppler spectrogram, is required to develop a scalable and robust classification<br>or regression application. In this paper, we propose a parametric convolutional<br>neural network that mimics the radar preprocessing across fast-time and slow-time<br>radar data through 2D sinc filter or 2D wavelet filter kernels to extract features for<br>classification of various human activities. It is demonstrated that our proposed<br>solution shows improved results compared to equivalent state-of-art DCNN solutions<br>that rely on Doppler spectrogram or video of RDIs as feature images.

Human Activity Classification Using Deep Convolutional Neural Network

2021 ◽  
pp. 41-50
Author(s):  
Aniket Verma ◽  
Amit Suman ◽  
Vidyadevi G. Biradar ◽  
S. Brunda
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Human Activity ◽  
Deep Convolutional Neural Network ◽  
Activity Classification

scholarly journals Human Activity Recognition Based on Deep Learning Techniques

Proceedings ◽  
2019 ◽  
Vol 42 (1) ◽  
pp. 15
Author(s):  
Manuel Gil-Martín ◽  
Marcos Sánchez-Hernández ◽  
Rubén San-Segundo
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Activity Recognition ◽  
Human Activity ◽  
Deep Neural Network ◽  
Human Activity Recognition ◽  
Support Vector ◽  
Daily Life Activities ◽  
Learning Techniques ◽  
The Fourier Transform

Deep learning techniques are being widely applied to Human Activity Recognition (HAR). This paper describes the implementation and evaluation of a HAR system for daily life activities using the accelerometer of an iPhone 6S. This system is based on a deep neural network including convolutional layers for feature extraction from accelerations and fully-connected layers for classification. Different transformations have been applied to the acceleration signals in order to find the appropriate input data to the deep neural network. This study has used acceleration recordings from the MotionSense dataset, where 24 subjects performed 6 activities: walking downstairs, walking upstairs, sitting, standing, walking and jogging. The evaluation has been performed using a subject-wise cross-validation: recordings from the same subject do not appear in training and testing sets at the same time. The proposed system has obtained a 9% improvement in accuracy compared to the baseline system based on Support Vector Machines. The best results have been obtained using raw data as input to a deep neural network composed of two convolutional and two max-pooling layers with decreasing kernel sizes. Results suggest that using the module of the Fourier transform as inputs provides better results when classifying only between dynamic activities.

Sign in / Sign up

Export Citation Format

Share Document