An Indoor Fall Monitoring System: Robust, Multistatic Radar Sensing and Explainable, Feature-Resonated Deep Neural Network

Abstract

Indoor fall monitoring is challenging for community-dwelling older adults due to the need for high accuracy and privacy concerns. Doppler radar is promising, given its low cost and contactless sensing mechanism. However, the line-of-sight restriction limits the application of radar sensing in practice, as the Doppler signature will vary when the sensing angle changes, and signal strength will be substantially degraded with large aspect angles. Additionally, the similarity of the Doppler signatures among different fall types makes it extremely challenging for classification. To address these problems, in this paper we first present a comprehensive experimental study to obtain Doppler radar signals under large and arbitrary aspect angles for diverse types of simulated falls and daily living activities. We then develop a novel, explainable, multi-stream, feature-resonated neural network (eMSFRNet) that achieves fall detection and a pioneering study of classifying seven fall types. eMSFRNet is robust to both radar sensing angles and subjects. It is also the first method that can resonate and enhance feature information from noisy/weak Doppler signatures. The multiple feature extractors -including partial pre-trained layers from ResNet, DenseNet, and VGGNet -extracts diverse feature information with various spatial abstractions from a pair of Doppler signals. The feature-resonated-fusion design translates the multi-stream features to a single salient feature that is critical to fall detection and classification. eMSFRNet achieved 99.3% accuracy detecting falls and 76.8% accuracy for classifying seven fall types. Our work is the first effective multistatic robust sensing system that overcomes the challenges associated with Doppler signatures under large and arbitrary aspect angles, via our comprehensible feature-resonated deep neural network. Our work also demonstrates the potential to accommodate different radar monitoring tasks that demand precise and robust sensing.

ORACLE: Occlusion-Resilient and Self-Calibrating mmWave Radar Network for People Tracking

“…Using multiple radar receivers with synchronized clocks enables coherent analysis of the received signals, which yields significant processing gains due to spatial diversity [15]. Existing works have leveraged this principle for drone detection [16] and people tracking [8], [17]- [19].…”

“…Our aim is to develop automatic calibration and sensor fusion algorithms to enable the quick deployment of multiple, jointly operating radars with no human intervention and no accurate synchronization between the devices. Multistatic radars used in, e.g., [8], [9], require synchronizing the devices' clocks in order to allow coherent processing of the received signals. This is highly impractical, as it mandates clock distribution through an optical connection to be set up, jeopardizing the ease and speed of deployment.…”

Revolutionizing Geriatric Care: Radar and Digital Twin Technology for Fall Severity Detection

“…Radar sensors emerge as a promising solution [19] due to their efficacy in preserving privacy, ensuring accuracy, operating independently of illumination levels, and detecting even slow falls that might be missed by wearables [1,4,13,14,20,21,22,23,24,25]. Machine learning algorithms such as Support Vector Machines(SVM) [13], Random Forests, K-Nearest Neighbours(KNN), K-Means, Linear Discriminant Analysis(LDA) [26] and and deep learning such as Long Short-Term Memory(LSTM) [27], Convolutional Neural Network(CNN) [22] and Gated recurrent unit(GRU) [28] have been used for fall detection [22].…”

IntNet: Lightweight yet High-Performance Deep Learning System for Intuitive Radar Patterns Analysis and Human Fall Detection

“…1 (c). Moreover, these systems mostly rely on convolutional neural networks [44] (CNNs) to capture both spatial and temporal information, despite CNNs being less suitable for temporal data. This results in an inefficient increase in the classifier's size to capture time-varying behaviors [40].…”