A5031291553- Emotion and Mood Recognition
- EEG and Brain-Computer Interfaces
- Heart Rate Variability and Autonomic Control
- Mental Health Research Topics
- Face and Expression Recognition
- Neural dynamics and brain function
- Functional Brain Connectivity Studies
- Color perception and design
- Esophageal Cancer Research and Treatment
- Non-Invasive Vital Sign Monitoring
- X-ray Diffraction in Crystallography
- Crystallization and Solubility Studies
- Service-Oriented Architecture and Web Services
- Gastric Cancer Management and Outcomes
- Neuroscience and Music Perception
- Advanced Sensor and Control Systems
- Metaheuristic Optimization Algorithms Research
- ECG Monitoring and Analysis
- Gaze Tracking and Assistive Technology
- Neural Networks and Applications
- Advanced Software Engineering Methodologies
- Advanced Algorithms and Applications
- Blind Source Separation Techniques
- Advanced Computational Techniques and Applications
- Neural and Behavioral Psychology Studies
Southwest University
2016-2025
Hebei Medical University
2016-2025
Chinese Academy of Medical Sciences & Peking Union Medical College
2007-2025
Wenzhou Medical University
2024-2025
Nanyang Technological University
2025
Guizhou University
2025
Sichuan Cancer Hospital
2012-2024
University of Electronic Science and Technology of China
1997-2024
Hohai University
2022-2024
China Aerodynamics Research and Development Center
2012-2024
Immune checkpoint inhibitors (ICIs) are effective in the treatment of advanced esophageal squamous cell carcinoma (ESCC); however, their efficacy locally resectable ESCC and potential predictive biomarkers have limited data.In this study, patients were enrolled received neoadjuvant toripalimab (240 mg, day 1) plus paclitaxel (135 mg/m2, carboplatin (area under curve 5 mg/mL per min, each 3-week cycle for 2 cycles, followed by esophagectomy planned 4-6 weeks after preoperative therapy. The...
Facial micro-expression is a brief involuntary facial movement and can reveal the genuine emotion that people try to conceal. Traditional methods of spontaneous recognition rely excessively on sophisticated hand-crafted feature design rate not high enough for its practical application. In this paper, we proposed Dual Temporal Scale Convolutional Neural Network (DTSCNN) micro-expressions recognition. The DTSCNN two-stream network. Different stream used adapt different frame video clips. Each...
Recent developments in graph theory have heightened the need for investigating disruptions topological structure of functional brain network major depressive disorder (MDD). In this study, we employed resting-state magnetic resonance imaging (fMRI) and to examine whole-brain networks among 42 MDD patients healthy controls. Our results showed that compared with controls, higher local efficiency modularity. Furthermore, altered nodal centralities many regions, including hippocampus, temporal...
Emotion recognition based on affective physiological changes is a pattern problem, and selecting specific signals necessary helpful to recognize the emotions. Fingertip blood oxygen saturation (OXY), galvanic skin response (GSR) heart rate (HR) are acquired while amusement, anger, grief fear of 101 subjects individually elicited by films. The in multi-subject GSR, first derivative GSR (FD_GSR) HR detected multi-variant correlation method. analysis reveals that HR, FD_GSR fluctuations...
Emotion recognition using electroencephalogram (EEG) signals has attracted significant research attention. However, it is difficult to improve the emotional effect across subjects. In response this difficulty, in study, multiple features were extracted for formation of high-dimensional features. Based on features, an effective method cross-subject emotion was then developed, which integrated significance test/sequential backward selection and support vector machine (ST-SBSSVM). The...
Background: The incidence and mortality of esophageal cancer are high. Therefore, we aimed to investigate how the number dissected lymph nodes during esophagectomy for squamous cell carcinoma impacts overall survival, particularly that patients with positive nodes. Materials methods: Data from 2010 2017 were obtained Sichuan Cancer Hospital Institute Esophageal Case Management Database. Participants divided into two groups: negative (N0) (N+). median resected surgery was 24; therefore, 15 23...
The detection of stress at early stages is beneficial to both individuals and communities. However, traditional methods that use physiological signals are contact-based require sensors be in contact with test subjects for measurement. In this paper, we present a method detect psychological non-contact manner using human response. particular, utilize hyperspectral imaging (HSI) technique extract the tissue oxygen saturation (StO2) value as feature detection. Our experimental results indicate...
Micro-expression is a subtle and involuntary facial expression that may reveal the hidden emotion of human beings. Spotting micro-expression means to locate moment when happens, which primary step for recognition. Previous work in spotting focus on from short video, with hand-crafted features. In this paper, we present methodology long videos. Specifically, new convolutional neural network named was designed extracting features video clips, first time deep learning used spotting. Then,...
Near-infrared (NIR) face recognition has attracted increasing attention because of its advantage illumination invariance. However, traditional methods based on NIR are designed for and tested in cooperative-user applications. In this paper, we present a convolutional neural network (CNN) (specifically identification) non-cooperative-user The proposed NIRFaceNet is modified from GoogLeNet, but more compact structure specifically the Chinese Academy Sciences Institute Automation (CASIA)...
Tempo is an important musical element that affects human's emotional processes during music listening. However, it remains unclear how tempo and training affect individuals' experience. To explore the neural underpinnings of effects on music-evoked emotion, with fast tempo, medium slow were collected to compare differences in responses functional magnetic resonance imaging(fMRI) activity between musicians non-musicians. Behaviorally, perceived higher valence than non-musicians did. The main...
A method for recognizing the emotion states of subjects based on 30 features extracted from their Galvanic Skin Response (GSR) signals was proposed. GSR were acquired by means experiments attended those subjects. Next data normalized with calm signal same subject after being de-noised. Then before step feature selection. Immune Hybrid Particle Swarm Optimization (IH-PSO) proposed to select subsets different emotions. Classifier selection evaluated correct recognition as well number selected...
An efficient and straightforward three-component synthetic protocol was developed to synthesize 1,2,3,4-tetrahydropyridine derivatives or thiochromeno[2,3-b]pyridine from β-aroylthioacetanilides β-(2-haloaroyl)thioacetanilides, aldehydes, aroyl acetonitriles via DABCO-catalyzed tandem [3 + 2 1] annulation SNAr reaction. This approach has the prominent features of high chemo-, stereo- (or enantio-), unusual regioselectivity. In domino processes, at least seven reactive sites were involved, up...
Studies have demonstrated that there are widespread significant differences in spontaneous brain activity between eyes-open (EO) and eyes-closed (EC) resting states. However, it remains largely unclear whether is effectively related to EO EC The amplitude, local functional concordance, inter-hemisphere synchronization, network centrality of were measured by the fraction amplitude low frequency fluctuation (fALFF), regional homogeneity (ReHo), voxel-mirrored homotopic connectivity (VMHC),...
Social anxiety is a negative emotion which may impair the health of heart and social functioning an individual. This work analyzes influence on autonomic nerve control in two exposure events: public speaking thesis defending. In experiment speaking, 59 human subjects were tested, 11 conventional heartbeat measures measure named range local Hurst exponents (RLHE) evaluated for their capabilities to reveal onset anxiety. Two-sample t-test between baseline data high shows that significantly...
An unprecedented Ir-catalyzed oxidative coupling of benzoic acids with trifluoromethylated alkynes was successfully developed to provide diverse isocoumarins in moderate good yields. This new practical procedure highlighted by mild reaction conditions, broad substrate scope, regioselectivity, high efficiency, and easy operation.
The matching of cognitive load and working memory is the key for effective learning, effort in learning process has nervous responses which can be quantified various physiological parameters. Therefore, it meaningful to explore automatic pattern recognition by using measures. Firstly, this work extracted 33 commonly used features quantify autonomic central activities. Secondly, we selected a critical feature subset sequential backward selection particle swarm optimization algorithms....
Non-restorative sleep is prevalent among individuals with depression and strongly associated the severity of condition. Therefore, identifying non-restorative can aid in early screening depression. Investigating necessitates long-term monitoring under naturalistic conditions. In this study, we recruited 149 participants collected electrocardiogram triaxial acceleration from them, resulting a total 761 nights data. The period midnight to 6:30 AM was segmented into 78 five-minute intervals,...
The rapid advancement of immersive technologies has propelled the development Metaverse, where convergence virtual and physical realities necessitates generation high-quality, photorealistic images to enhance user experience. However, generating these images, especially through Generative Diffusion Models (GDMs), in mobile edge computing environments presents significant challenges due limited resources devices dynamic nature wireless networks. This paper proposes a novel framework that...
Mobile edge Large Language Model (LLM) deployments face inherent constraints, such as limited computational resources and network bandwidth. Although Retrieval-Augmented Generation (RAG) mitigates some challenges by integrating external knowledge bases, inefficient cache management can still result in high retrieval latency frequent updates. To address these issues, we propose an Adaptive Contextual Caching (ACC) framework that anticipates user needs proactively caching semantically relevant...