17 May 2022 in IEEE Internet of Things Journal
Falls are fatal for the elderly, and timely detection after falls is crucial. As a contactless device, the radar sensor can monitor users’ falls with the advantage of not revealing their privacy. Today, the use of radar for fall detection has made a significant progress. However, most current methods cannot be used in real complex scenes. They usually collect fewer types of actions, and the ratio of the number of nonfall samples to the number of fall samples is small, which is not consistent with the real-life scene. In addition, the classifiers are usually trained and tested on the same environments and the same people, which cannot be easily extended to new environments and new people. We designed a robust fall detection system based on the frequency-modulated continuous-wave (FMCW) radar to solve these issues. The system detects the moment of human movement and calculates the range–velocity map, range–horizontal angle map, and range–vertical angle map of the radar signals, and creates three neural networks for these three signal maps. The stacking method of ensemble learning is used to fuse the time–space–velocity features extracted by the three neural networks to identify falls. The method was trained and tested on a data set consisting of ten scenes, 21 subjects, 52 nonfall action types, and 12 fall action types. The results show that on the test set containing only new environments and new subjects, the recall is 0.983 and the precision is 0.975.
13 August 2023 in Engineering Applications of Artificial Intelligence
4 August 2023 in IEEE Internet of Things Journal
It is necessary to detect the fall of the elderly in time. As a noncontact monitoring device, radar can monitor users without their knowledge and protect their privacy. The unsupervised fall detection method does not need to collect and label fall samples, which avoids the difficulty of collecting fall data and saves researchers time and cost. The current unsupervised fall detection studies consider fewer types of actions and do not test the generalization of their models in new environments and subjects. This article proposes a new unsupervised fall detection system, including a feature extractor and predictor. We first use 3-D convolution and 3-D transposed convolution to construct a feature extractor to extract the range–velocity–time features of radar signals. Then, we construct a predictor to learn the pattern of nonfall action. Finally, we design an unsupervised training method based on hard sample mining to improve the ability of the model to identify hard negative samples. We train the model using only unlabeled nonfall samples and test it in new scenarios. The system’s accuracy in the data set containing 52 kinds of nonfall actions and 12 kinds of fall actions is 95.54%, the false alarm rate is 1.07%, and the area under the receiver operating characteristic is 0.9974.
22 August 2024 in IEEE Sensors Journal
It is essential to find and treat the elderly in time after they fall. Millimeter wave radar sensor not only solves the problem of invasion of privacy caused by the camera but also avoids letting patients wear wearable devices, which has received more and more attention in the field of fall detection and motion recognition. Due to the different modulation of radar signals by different users and environments, the performance of the fall detection model is inevitably reduced. In this paper, we propose a highly generalized radar-based fall detection framework to improve the generalization of the fall detection system in the new domain. We use a feature extractor with a ResNet structure constructed from three-dimensional convolution to extract features of the signal, and a multilayer perceptron as a classifier for fall detection. We measure the cross-domain cross entropy of the features by setting subclassifiers for each domain to measure the cross-domain invariance of the features, enabling the feature extractor to extract domain-invariant features. We propose a specific data augmentation technology for radar time series signals, which is combined with the proposed model to achieve more generalized fall detection. We have conducted sufficient experiments to explore the relationship between the number of users and domains and the model’s generalization. The proposed method achieves an F1 score of 0.9747 on the proposed dataset containing 10 scenarios, 21 subjects, 52 non-falling actions and 12 falling actions, and an F1 score of 0.9949 on the public dataset, which shows superior effectiveness.
26 April 2024 in IEEE Sensors Journal
Multi-label electrocardiogram (ECG) classification is of great significance for the diagnosis of cardiovascular diseases, and it is also a challenging task because of the various of pathological patterns across different cardiac abnormalities. This paper analyzes the complex spatial-temporal variations information contained in the 12-lead ECG from a new perspective, and proposes an advanced deep neural network framework to accurately identify various multi-label ECG abnormalities. Firstly, the 12-lead ECG was modeled as 3-dimensional (3-D) spatial-temporal variations involving the intra-period, inter-period temporal dimensions, and cross-lead spatial dimension. Then, a 3-D spatial-temporal learning network (3D-STLNet) was carefully designed to extract the complex pathological features from the 3-D spatial-temporal variations. Secondly, the multi-head attention (MHA) mechanism was introduced into the proposed network to extract global temporal dependencies in ECG segments, which further improved the performance of the proposed network. By integrating a residual backbone network, a 3D-STLNet, and the MHA module, our proposed network allows end-to-end learning and prediction in a unified framework. The influence of several classic threshold selection strategies on the performance of multi-label ECG classification algorithm was also analyzed, which provides a reference for subsequent research on optimal threshold selection for multi-label ECG classification. Finally, our proposed network was evaluated on multiple large multi-label ECG public datasets, and the performance of our network outperforms that of current state-of-the-art networks, which demonstrates that our network has great competitiveness in identifying a wider range of multi-label ECG abnormalities.
1 April 2026 in IEEE Sensors Journal
The burgeoning field of radar-based vital sign sensing has seen significant advancements. However, practical aspects such as the impact of multi-person scenarios with diverse orientations in real-world environments are often overlooked and not fully verified. In realistic scenarios, the concurrent presence of multiple individuals within a single range bin is an inescapable aspect. And extracting the heart rates of multiple people at the same time in this scenario is challenging for small antenna arrays. This paper proposes a framework for frequency modulated continuous wave (FMCW) multiple input multiple output (MIMO) radar to achieve accurate heart rate monitoring of multiple targets in a single range bin. The framework consists of two main modules. The first module is vital sign mask, which adaptively generates mask vectors to minimize mutual interference between different targets. High resolution degree of arrival (DOA) estimation algorithm of coherent signal sources is combined with interference suppression beamforming to maximize the separation efficiency of small antenna arrays. The second part is the dynamic demodulation and base frequency heart rate (HR) estimation algorithm, which restores the heart waveform by dynamically compensating the DC offset and utilized the high-frequency harmonic of heartbeat to estimate the heart rate while minimizing the effect of respiration harmonics. In experiments of two-resident lying side-by-side with various posture, the overall RMSE is 1.9 bpm. The proposed framework achieved a minimum separable angle of 9 degrees via an 8-element array for dual-person and tracked HR of 4 residents with RMSE of 1.6 bpm, demonstrating capability to operate in daily multi-resident scenarios.