Ye Qiu

Ye Qiu

Auto-generated profile, based on publicly available information

Ye Qiu

Sun Yat-sen University

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
21 December 2022 in Frontiers in Psychiatry
Verified
Journal Article
Open access
DLD Liu
D Liu
BLBowen Liu
Bowen Liu
TLTao Lin
Tao Lin
GLGuangya Liu
Guangya Liu
GYGuoyu Yang
Guoyu Yang
Hai LinHai Lin
Hai Lin
Introduction: Real-time evaluations of the severity of depressive symptoms are of great significance for the diagnosis and treatment of patients with major depressive disorder (MDD). In clinical practice, the evaluation approaches are mainly based on psychological scales and doctor-patient interviews, which are time-consuming and labor-intensive. Also, the accuracy of results mainly depends on the subjective judgment of the clinician. With the development of artificial intelligence (AI) technology, more and more machine learning methods are used to diagnose depression by appearance characteristics. Most of the previous research focused on the study of single-modal data; however, in recent years, many studies have shown that multi-modal data has better prediction performance than single-modal data. This study aimed to develop a measurement of depression severity from expression and action features and to assess its validity among the patients with MDD.Methods: We proposed a multi-modal deep convolutional neural network (CNN) to evaluate the severity of depressive symptoms in real-time, which was based on the detection of patients’ facial expression and body movement from videos captured by ordinary cameras. We established behavioral depression degree (BDD) metrics, which combines expression entropy and action entropy to measure the depression severity of MDD patients.Results: We found that the information extracted from different modes, when integrated in appropriate proportions, can significantly improve the accuracy of the evaluation, which has not been reported in previous studies. This method presented an over 74% Pearson similarity between BDD and self-rating depression scale (SDS), self-rating anxiety scale (SAS), and Hamilton depression scale (HAMD). In addition, we tracked and evaluated the changes of BDD in patients at different stages of a course of treatment and the results obtained were in agreement with the evaluation from the scales.Discussion: The BDD can effectively measure the current state of patients’ depression and its changing trend according to the patient’s expression and action features. Our model may provide an automatic auxiliary tool for the diagnosis and treatment of MDD.

14 May 2024 in IEEE Journal of Biomedical and Health Informatics
Verified
Journal Article
Closed access
YQYe Qiu
Ye Qiu
XMXinjie Ma
Xinjie Ma
XLXinglong Li
Xinglong Li
SFShaocan Fan
Shaocan Fan
ZDZhenmiao Deng
Zhenmiao Deng
XHXiaohong Huang
Xiaohong Huang
This study introduces a contactless blood pressure monitoring approach that combines conventional radar signal processing with novel deep learning architectures. During the preprocessing phase, datasets suitable for synchronization are created by integrating Kalman filtering, multiscale bandpass filters, and a periodic extraction method in the time domain. These data comprise data on chest micro variations, encapsulating a complex array of physiological and biomedical information reflective of cardiac micromotions. The Radar-based Stacked Deformable convolution Network (RSD-Net) integrates channel and spatial self attention mechanisms within a deformable convolutional framework to enhance feature extraction from radar signals. The network architecture systematically employs deformable convolutions for initial deep feature extraction from individual signals. Subsequently, continuous blood pressure estimation is conducted using self attention mechanisms on feature map from single source coupled with multi-feature map channel attention. The performance of model is corroborated via the open-source dataset procured using a non-invasive 24GHz six-port continuous wave radar system. The dataset, encompassing readings from 30 healthy individuals subjected to diverse conditions including rest, the Valsalva maneuver, apnea, and tilt-table examinations. It serves to substantiate the validity and resilience of the proposed method in the non-contact assessment of continuous blood pressure. Evaluation metrics reveal Pearson correlation coefficients of 0.838 for systolic and 0.797 for diastolic blood pressure predictions. The Mean Error (ME) and Standard Deviation (SD) for systolic and diastolic blood pressure measurements are -0.32 $\pm$ 6.14mmHg and -0.20 $\pm$ 5.50mmHg, respectively. The ablation study assesses the contribution of different structural components of the RSD-Net, validating their significance in the overall of model performance.

4 November 2024 in IEEE Internet of Things Journal
Verified
Journal Article
Closed access
XLXinglong Li
Xinglong Li
YQYe Qiu
Ye Qiu
ZDZhenmiao Deng
Zhenmiao Deng
XLXinyu Liu
Xinyu Liu
XHXiaohong Huang
Xiaohong Huang
Human activity recognition (HAR) based on radar has garnered wide interest due to its privacy-friendly and lighting-independent nature. Despite advancements, challenges like response speed and real-world applicability persist. To address these issues, data from different orientations utilizing frequency-modulated continuous-wave (FMCW) radar was collected to better reflect real-world conditions. In terms of data preprocessing, a sliding time-window non-local means filter is proposed to effectively remove the noise while retaining the micro-Doppler features. Subsequently, a multi-attention enhanced fusion network (MAEF-Net) is proposed for HAR. MAEF-Net, an efficient and lightweight architecture, integrates multiple attention mechanisms to enhance robustness in omnidirectional HAR. It achieves high-accuracy omnidirectional activity recognition by simultaneously focusing on local and global features. Experimental results showcase MAEF-Net achieving 98.3% accuracy in testing, surpassing existing methods, thereby demonstrating its effectiveness in real-world scenarios.

21 October 2024 in IEEE Transactions on Aerospace and Electronic Systems
Verified
Journal Article
Closed access
JZJiachen Zhu
Jiachen Zhu
XHXiaohong Huang
Xiaohong Huang
ZDZhenmiao Deng
Zhenmiao Deng
YQYe Qiu
Ye Qiu
This article proposes a human pose recognition (HPR) system based on millimeter-wave (mmWave) radar (mRadHPRS). It includes an adaptive method for generating 3D point clouds of human bodies, a data augmentation method for sparse point clouds, and an HPR network based on mmWave radar (mmRadHPR). This study seeks to address a deficiency in current HPR research, which predominantly emphasizes various deep learning variants and often pays less attention to the accurate extraction of features from radar signals. The proposed system considers factors such as multipath effects in radar echoes and designs data augmentation methods tailored to the sparse distribution characteristics of mmWave radar point clouds. Additionally, a hierarchical point cloud processing network incorporating cross- and self-attention mechanisms is devised to extract human pose features. To evaluate the performance of the proposed model, we constructed a dataset with 10 different postures using mmWave radar. Experimental results demonstrate that the overall accuracy and average classification accuracy achieved by our method are 88.38% and 88.63%, respectively, significantly outperforming the three baseline methods. The system robustness experiment further validates the generalization ability and effectiveness of our approach.

10 June 2024 in IEEE Transactions on Aerospace and Electronic Systems
Verified
Journal Article
Closed access
YQYe Qiu
Ye Qiu
XLXinglong Li
Xinglong Li
ZDZhenmiao Deng
Zhenmiao Deng
XHXiaohong Huang
Xiaohong Huang
PPPingping Pan
Pingping Pan
XMXinjie Ma
Xinjie Ma
To overcome the limitations of LiDAR and camera systems in cost and weather-resilient performance, millimeter-wave radar has emerged as a complementary solution for object identification and surveillance. Previous studies have indicated promising prospects for Frequency-Modulated Continuous Wave (FMCW) radar in action recognition tasks, primarily through classifying micro-Doppler features in the radar's slow-time dimension. However, these features are highly sensitive to the direction of target motion, causing significant variations when observed from different angles. To address these challenges while enhancing cost-efficiency and environmental robustness, we introduce a Stacked Dual-Path Feature Fusion Network (SDP-Net). The design of the model is validated using an unsupervised image clustering algorithm. We also present lightweight variants of SDP-Net to ensure broad hardware compatibility and demonstrate robust omnidirectional motion recognition using monostatic radar. Comparative evaluation on both simulated and measured data sets confirms that our approach outperforms existing recognition methods.

6 October 2025 in IEEE Transactions on Aerospace and Electronic Systems
Verified
Journal Article
Closed access
YQYe Qiu
Ye Qiu
XMXinjie Ma
Xinjie Ma
XLXinglong Li
Xinglong Li
ZDZhenmiao Deng
Zhenmiao Deng
XHXiaohong Huang
Xiaohong Huang
PPPingping Pan
Pingping Pan
Time-frequency analysis (TFA) is valuable in crucial application domains such as biomedical sciences, communication systems, and environmental monitoring. Existing TFA approaches, including those based on neural network algorithms and Synchrosqueezing Transform (SST), exhibit limitations when dealing with intersecting strong and weak Instantaneous Frequency (IF). To address this issue, we introduce an end-to-end neural network specifically designed for weak signal detection, WeakSig-TFANet (WTFA-Net), guided by traditional weak signal processing schemes. The network employs a combination of time-domain and convolutional windows to attenuate the sidelobes of strong signals in the convolutional input, demonstrating exceptional recognition capabilities in scenarios involving weak signals such as faint respiratory and cardiac signals. To enhance resolution in cases of IF intersections, the proposed model structure further integrates complex attention modules and multi-coarse estimation basis pixel-level attention mechanisms. These mechanisms counteract the decline in the ability to detect adjacent signals, a decline caused by the widening of the main lobe due to time-domain windowing of strong signals. Through experiments across multiple application scenarios, including both simulated and real-world signals, WTFA-Net is shown to outperform existing methods in weak signal detection performance in vital sign monitoring, underwater acoustic detection, channel state information (CSI) of Wi-Fi and Inverse Synthetic Aperture Radar (ISAR) image generation.