Human Activity Classification With Radar: Optimization and Noise Robustness With Iterative Convolutional Neural Networks Followed With Random Forests

Abstract

The accurate classification of activity patterns based on radar signatures is still an open problem and is key to detect anomalous behavior for security and health applications. This paper presents a novel iterative convolutional neural networks strategy with an autocorrelation pre-processing instead of the traditional micro-Doppler image pre-processing to classify activities or subjects accurately. The proposed strategy uses an iterative deep learning framework for the automatic definition and extraction of features. This is followed by a traditional supervised learning classifier to label the different activities. Using three human subjects and their real motion captured data, twelve thousand radar signatures were simulated by varying additive white Gaussian noise. Additionally, 6720 experimental radar signatures were captured with a frequency-modulated continuous radar at 5.8GHz with 400M Hz of instantaneous bandwidth from seven activities using one subject and 4800 signatures from five subjects while walking. The simulated and experimental data were both used to validate our proposed method. With SNR varying from −20 to 20dB with 88.74% average accuracy at −10dB and 100% peak accuracy at 15dB. The proposed Iterative Convolutional Neural Networks followed with Random Forests (ICNNRF) does not only outperform the feature-based methods using micro-Doppler images but also the classification methods using other types of supervised classifiers after our proposed iterative convolutional neural network.

Room-Level Fall Detection Based on Ultra-Wideband (UWB) Monostatic Radar and Convolutional Long Short-Term Memory (LSTM)

“…Non-fall samples must be classified as the corresponding activity to contribute to TN count. We compared the proposed method with the classic Lenet-5 architecture, which has been adopted in similar research [32,35]. Three kinds of classifiers, SoftMax, K-nearest neighbors (KNN), and random forest (RF), were selected to test the performance of the proposed method when using different classifiers.…”

“…Wearable-device-based fall detection Many researchers have adopted this new tool in fall detection research and acquired good results. The work of Y. Lin et al [32] used an iterative convolutional neural network (ICNN) followed by random forests to deal with radar signals. Sadreazami et al employed a deep convolutional neural network [33] and a deep residual neural network [34] to learn features from radar time-series signals.…”

Elderly Care: Using Deep Learning for Multi-Domain Activity Classification

“…In [7,8], the authors used deep learning approaches with the help of spectrogram only for activities classification. Algorithms have difficulties finding effective boundaries to separate those classes effectively, especially when it comes to Convolutional Neural Network (CNN) because they did not exploit different radar data domains.…”

Fusion of Deep Representations in Multistatic Radar Networks to Counteract the Presence of Synthetic Jamming

“…Deep learning is derived from the same fundamental concepts which ML is based upon, specifically neural networks (NN), however it differs in that it consists of multiple processing layers of diverse dimensions, each designed to perform a certain task within the context of the network optimally. An extensive variety of structures and topologies have been rigorously researched, to name but a few examples: Convolutional Neural Networks (CNN), Long Short Term Memory (LSTM), Deep Belief Network (DBN) and DNN [11]- [16]; these enable high classification accuracies to be obtained over large data sets of images.…”