arXiv subjects

Yali Zheng

Publications and source records attributed to Yali Zheng.

5 recordsLinked to original sources

arXiv2026

Collaborative Learning-Enhanced Lightweight Models for Predicting Arterial Blood Pressure Waveform in a Large-scale Perioperative Dataset

Noninvasive arterial blood pressure (ABP) monitoring is essential for patient management in critical care and perioperative settings, providing continuous assessment of cardiovascular hemodynamics with minimal risks. Numerous deep learning models have developed to reconstruct ABP waveform from noninvasively acquired physiological signals such as electrocardiogram and photoplethysmogram. However, limited research has addressed the issue of model performance and computational load for deployment on embedded systems. The study introduces a lightweight sInvResUNet, along with a collaborative learning scheme named KDCL_sInvResUNet. With only 0.89 million parameters and a computational load of 0.02 GFLOPS, real-time ABP estimation was successfully achieved on embedded devices with an inference time of just 8.49 milliseconds for a 10-second output. We performed subject-independent validation in a large-scale and heterogeneous perioperative dataset containing 1,257,141 data segments from 2,154 patients, with a wide BP range (41-257 mmHg for SBP, and 31-234 mmHg for DBP). The proposed KDCL_sInvResUNet achieved lightly better performance compared to large models, with a mean absolute error of 10.06 mmHg and mean Pearson correlation of 0.88 in tracking ABP changes. Despite these promising results, all deep learning models showed significant performance variations across different demographic and cardiovascular conditions, highlighting their limited ability to generalize across such a broad and diverse population. This study lays a foundation work for real-time, unobtrusive ABP monitoring in real-world perioperative settings, providing baseline for future advancements in this area.

cs.LG↗

arXiv2025

6D Movable Holographic Surface Assisted Integrated Data and Energy Transfer: A Sensing Enhanced Approach

Reconfigurable holographic surface (RHS) enables cost-effective large-scale arrays with high spatial gain. However, its amplitude-controlled holographic beamforming suffers from directional fluctuations, making it difficult to fully exploit the spatial gain of RHS. Fortunately, the promising 6D movable antenna (6DMA) provides a potential solution to this problem. In this paper, we study a 6D movable holographic surface (6DMHS) integrated data and energy transfer (IDET) system, where a three-stage protocol is proposed, consisting of an uplink sensing stage, an orientation adjustment stage and a downlink transmission stage, to coordinate the 6DMHS and effectively serve the IDET receivers. Firstly, the holographic-based sensing technology is proposed and the sensing information of the IDET receivers is exploited. Secondly, by fixing the rotations with the sensing information, the orientation optimization problem is formulated for designing the holographic beamforming of the RHS and adjusting the translations of the 6DMHS. As a result, the directions with maximum beamforming gain are aligned with each IDET receiver. Thirdly, by fixing the orientation of the 6DMHS and the holographic beamforming, the equivalent wireless channel is obtained. The IDET performance optimization problem is formulated for obtaining the optimal digital beamforming, power splitting factor and energy harvesting (EH) power. Simulation results demonstrate that the proposed scheme is capable of improving the IDET performance compared to the benchmarks.

eess.SP↗

arXiv2024

On the spectrality of a class of Moran measures

In this paper, we study the spectrality of a class of Moran measures $μ_{\mathcal{P},\mathcal{D}}$ on $\mathbb{R}$ generated by $\{(p_n,\mathcal{D}_n)\}_{n=1}^{\infty}$, where $\mathcal{P}=\{p_n\}_{n=1}^{\infty}$ is a sequence of positive integers with $p_n>1$ and $\mathcal{D}=\{\mathcal{D}_{n}\}_{n=1}^{\infty}$ is a sequence of digit sets of $\mathbb{N}$ with the cardinality $\#\mathcal{D}_{n}\in \{2,3,N_{n}\}$. We find a countable set $Λ\subset\mathbb{R}$ such that the set $\{e^{-2πi λx}|λ\inΛ\}$ is a orthonormal basis of $L^{2}(μ_{\mathcal{P},\mathcal{D}})$ under some conditions. As an application, we show that when $μ_{\mathcal{P},\mathcal{D}}$ is absolutely continuous, $μ_{\mathcal{P},\mathcal{D}}$ not only is a spectral measure, but also its support set tiles $\mathbb{R}$ with $\mathbb{Z}$.

math.CA↗

arXiv2023

Tiny-PPG: A Lightweight Deep Neural Network for Real-Time Detection of Motion Artifacts in Photoplethysmogram Signals on Edge Devices

Photoplethysmogram (PPG) signals are easily contaminated by motion artifacts in real-world settings, despite their widespread use in Internet-of-Things (IoT) based wearable and smart health devices for cardiovascular health monitoring. This study proposed a lightweight deep neural network, called Tiny-PPG, for accurate and real-time PPG artifact segmentation on IoT edge devices. The model was trained and tested on a public dataset, PPG DaLiA, which featured complex artifacts with diverse lengths and morphologies during various daily activities of 15 subjects using a watch-type device (Empatica E4). The model structure, training method and loss function were specifically designed to balance detection accuracy and speed for real-time PPG artifact detection in resource-constrained embedded devices. To optimize the model size and capability in multi-scale feature representation, the model employed depth-wise separable convolution and atrous spatial pyramid pooling modules, respectively. Additionally, the contrastive loss was also utilized to further optimize the feature embeddings. With additional model pruning, Tiny-PPG achieved state-of-the-art detection accuracy of 87.4% while only having 19,726 model parameters (0.15 megabytes), and was successfully deployed on an STM32 embedded system for real-time PPG artifact detection. Therefore, this study provides an effective solution for resource-constraint IoT smart health devices in PPG artifact detection.

eess.SP↗

arXiv2022

Self-Paced Deep Regression Forests with Consideration of Ranking Fairness

Deep discriminative models (DDMs), e.g. deep regression forests and deep decision forests, have been extensively studied recently to solve problems such as facial age estimation, head pose estimation, etc.. Due to a shortage of well-labeled data that does not have noise and imbalanced distribution problems, learning DDMs is always challenging. Existing methods usually tackle these challenges through learning more discriminative features or re-weighting samples. We argue that learning DDMs gradually, from easy to hard, is more reasonable, for two reasons. First, this is more consistent with the cognitive process of human beings. Second, noisy as well as underrepresented examples can be distinguished by virtue of previously learned knowledge. Thus, we resort to a gradual learning strategy -- self-paced learning (SPL). Then, a natural question arises: can SPL lead DDMs to achieve more robust and less biased solutions? To answer this question, this paper proposes a new SPL method: easy and underrepresented examples first, for learning DDMs. This tackles the fundamental ranking and selection problem in SPL from a new perspective: fairness. Our idea is fundamental and can be easily combined with a variety of DDMs. Extensive experimental results on three computer vision tasks, i.e., facial age estimation, head pose estimation, and gaze estimation, show our new method gains considerable performance improvement in both accuracy and fairness. Source code is available at https://github.com/learninginvision/SPU.

cs.CV↗