- Heart Rate Variability and Autonomic Control
- Blood Pressure and Hypertension Studies
- Non-Invasive Vital Sign Monitoring
- EEG and Brain-Computer Interfaces
- Software Engineering Research
- Information and Cyber Security
- ECG Monitoring and Analysis
- Machine Learning in Healthcare
- Animal Behavior and Welfare Studies
- Microbial Inactivation Methods
- Advanced Statistical Methods and Models
- Cardiovascular Health and Disease Prevention
- Software-Defined Networks and 5G
- Face and Expression Recognition
- Image Processing and 3D Reconstruction
- Magnetic and Electromagnetic Effects
- Image Retrieval and Classification Techniques
- Hemodynamic Monitoring and Therapy
- Advanced Data Processing Techniques
- Telecommunications and Broadcasting Technologies
- Traditional Chinese Medicine Analysis
- Bayesian Methods and Mixture Models
- Image and Video Quality Assessment
- Handwritten Text Recognition Techniques
- Plant Genetic and Mutation Studies
Chongqing University
2024-2025
Shanxi Agricultural University
2023-2024
University of Electronic Science and Technology of China
2024
Tianjin University
2024
Sun Yat-sen University
2024
University of Shanghai for Science and Technology
2021
Central Michigan University
2006
Abstract This study underscores the paramount importance of facial expressions in pigs, serving as a sophisticated mode communication to gauge their emotions, physical well-being, and intentions. Given inherent challenges deciphering such due pigs' rudimentary muscle structure, we introduced an avant-garde pig expression recognition model named CReToNeXt-YOLOv5. The proposed encompasses several refinements tailored for heightened accuracy adeptness detection. Primarily, transition from CIOU...
To explore the effects of pulsed electric field treatment on germination Scutellaria baicalensis seeds and growth seedlings, this study used response surface methodology to design working parameters treated cultured seeds. The results showed that was beneficial for seeds, improving metabolic activity stress resistance seedlings. When treatment’s were 0.5 kV·cm−1, 120 μs, 99 pulses, potential significantly increased by 29.25% index 20.65%, compared control. From 5th 15th day, activities SOD,...
Despite extensive studies on cuffless continuous blood pressure (BP) estimation through machine learning models, those models are typically constrained by a one-off training strategy resulting in fixed model parameters and inadequate adaptation response to new patterns of data. BP is dynamic vital sign with concept drift characteristic. With static trained datasets traditional (TL) technique, the performance would degrade when to-be predicted distributions deviate from ones. In this paper,...
Abstract Objective. Pulse transit time (PTT) is a popular indicator of blood pressure (BP) changes. However, the relationship between PTT and BP somehow individual dependent, resulting in inaccuracy PTT-based estimation. Confounding factors, e.g., heart rate (HR), could be primary cause. In this study we attempt to explore impact HR as window look at influence confounding factors on BP. Approach. We investigated systolic (SBP) different levels by introducing heterogeneous treatment effects...
When assessing the potential security risks that exist in features of different operating systems, there is not a common set metrics. As result, it very difficult to objectively assess associated with specific feature system. In this paper, we propose simple metrics quantify and measure or configuration any systems. We present how Windows can be quantified measured formula have developed study. Further more, also applicable other systems such as Linux.
In this work, we propose a lightweight Hierarchical Node-wise Localized Diffusion-Convolutional Network (HNLDCNet) for motor imagery (MI) and mental arithmetic (MA) classification tasks based on EEG-fNIRS data. The proposed HNLDCNet utilizes layer-adaptive agglomerative clustering algorithm to construct graph hierarchy of spatial information from channels, enhancing the feature extraction signals. By incorporating philosophy node-wise localized mapping DiffPooling, employ learnable directed...
Aim: We propose to examine the causal relationship between noninvasive features represented by pulse transit time (PTT) and blood pressure (BP), with aim of mitigating impact confounding factor(s) thus improving performance BP estimation. Methods: identified graph important extracted from electrocardiogram (ECG) photoplethysmogram (PPG) via fast inference (FCI) algorithm, orientations edges in being determined generative neural networks (CGNN) algorithm. With knowledge obtained graph, we...
<sec> <title>BACKGROUND</title> Hypertension is a leading cause of cardiovascular disease and premature death worldwide it puts heavy burden on the healthcare system. It is, therefore, very important to detect evaluate hypertension related events so as for early prevention, detection management. can be evaluated in real time with wearable noninvasive cardiac signals, such electrocardiogram (ECG) photoplethysmogram (PPG). Most previous studies predicted from ECG PPG signals extracted features...
This study introduces a parameter-efficient Hierarchical Spatial Temporal Network (HiSTN) specifically designed for the task of emotion classification using multi-channel electroencephalogram data. The network incorporates graph hierarchy constructed from bottom-up at various abstraction levels, offering dual advantages enhanced task-relevant deep feature extraction and lightweight design. model's effectiveness is further amplified when used in conjunction with proposed unique label...
Abstract Background Hypertension is a leading cause of cardiovascular disease and premature death worldwide, it puts heavy burden on the healthcare system. Therefore, very important to detect evaluate hypertension related events enable early prevention, detection, management. can be detected in timely manner with cardiac signals, such as through an electrocardiogram (ECG) photoplethysmogram (PPG) , which observed via wearable sensors. Most previous studies predicted from ECG PPG signals...
The key to cuffless blood pressure (BP) estimation lies in identifying the efficient noninvasive features or signals that can indicate BP changes. Most these are identified based on their correlation with BP. However, does not imply causation, as there might be confounders impacting relationship between and In this study, we introduce causal inference identify possibly affect accuracy of commonly studied pulse transit time (PTT) estimation. We further propose a hierarchical regression model...
In recent years, the objectification of tongue image in Traditional Chinese Medicine (TCM) has become a topic extensive discussion. As an important reference index TCM diagnosis, features play role disease prevention and diagnosis. Among them, how to achieve standardization accurate segmentation extracting quantitative feature information key issue that restricts objective development This article mainly reviews two aspects color processing methods. Review currently widely used methods,...
Abstract The study focused on the significance of facial expressions in pigs as a mode communication for assessing their emotions, physical status, and intentions. To address challenges recognizing due to simple muscle group structure pigs, novel pig expression recognition model called CReToNeXt-YOLOv5 was proposed. Several improvements were made enhance accuracy detection ability model. Firstly, CIOU loss function replaced with EIOU optimize training achieve more accurate regression. This...
Many programming bugs can lead to privilege escalation, which is a major security concern. However, there are times when the concern proves be false positive. In previous paper, "An Approach Analyzing Windows and Linux Security Models", set of metrics was proposed assess risks quantitatively Xinyue Song, et al (2006). with risk quantified, still not clearly defined way distinguishing between true positives on continuum risks. An effective method needs developed solve this problem. new...