A5100624785- Pain Mechanisms and Treatments
- Pharmacological Effects of Natural Compounds
- Gait Recognition and Analysis
- Human Pose and Action Recognition
- Geoscience and Mining Technology
- Technology and Security Systems
- Blind Source Separation Techniques
- Anomaly Detection Techniques and Applications
- Context-Aware Activity Recognition Systems
- Natural Language Processing Techniques
- AI-based Problem Solving and Planning
- Industrial Vision Systems and Defect Detection
- Coal Properties and Utilization
- Recommender Systems and Techniques
- QR Code Applications and Technologies
- Cardiac Valve Diseases and Treatments
- Image Retrieval and Classification Techniques
- Nuclear Materials and Properties
- Advanced Algorithms and Applications
- Stress Responses and Cortisol
- Coal and Coke Industries Research
- Spam and Phishing Detection
- Domain Adaptation and Few-Shot Learning
- Robotics and Automated Systems
- Underwater Acoustics Research
State Key Laboratory of Medical Neurobiology
2024
Shandong First Medical University
2024
Fudan University
2019-2024
Beijing Sport University
2024
Shanghai Medical College of Fudan University
2024
Zhengzhou University
2023
Zhongshan Hospital
2022
University of Chinese Academy of Sciences
2021
Institute of Information Engineering
2021
Chinese Academy of Sciences
2021
BACKGROUND: Exercise has been proven to be an efficient intervention in attenuating neuropathic pain. However, the underlying mechanisms that drive exercise analgesia remain unknown. In this study, we aimed examine role of complement component 3 (C3) pain and whether antinociceptive effects are produced by via regulating C3 mice. METHODS: using a spared nerve injury (SNI)-induced mice model, C57BL/6J were divided into groups: Sham mice, SNI + (Ex) with 30-minute low-intensity aerobic...
Due to the movement expressiveness and privacy assurance of human skeleton data, 3D skeleton-based action inference is becoming popular in healthcare applications. These scenarios call for more advanced performance application-specific algorithms efficient hardware support. Warnings on health emergencies sensitive response speed require low latency output early detection capabilities. Medical monitoring that works an always-on edge platform needs system processor have extreme energy...
Progress in skeleton-based action recognition has enabled the contactless, ceaseless and portable surveillance on human daily behaviors which helps to reveal health hazards. Human datasets like NTU RGB+D have provided medical-condition-related categories. Hence, this paper, we propose an optimized view adaptive LSTM (VA-LSTM) with additional classification regression subnetworks such medical condition detection (MCD). We surpass previous works a model accuracy of 79.6% (cross-subject) 88.2%...
While grasp detection is an important part of any robotic manipulation pipeline, reliable and accurate in $SE(3)$ remains a research challenge. Many robotics applications unstructured environments such as the home or warehouse would benefit lot from better performance. This paper proposes novel framework for detecting poses based on point cloud input. Our main contribution to propose $SE(3)$-equivariant model that maps each continuous quality function over 2-sphere $S^2$ using spherical...
We construct two models to derive the optimal plan. successfully utilize our determine best online sales strategy and identify potentially important design features that would enhance product desirability. establish Genetic Algorithm-Optimized BP Neural Network Model find relationship between time-based measures within data sets reputation of products. After quantifying all indicators, we take as a fitting platform fit forecast reputation-timeline figure. To degrade influence because slow...
Personalized news recommendation system aims to screen out the that users are interested in from explosion amount of for display. In recent years, deep learning methods have been widely used system. However, whether traditional or advanced models, most them only modeled after feature extraction titles adding user preferences. There two problems: insufficient expression and exploration implicit meaning users, continuous behavior. Therefore, this paper, we propose a model based on...
Patients with aortic stenosis and low left ventricular ejection fraction (LVEF) would benefit from transcatheter valve replacement. However, the safety efficacy of replacement in patients regurgitation dysfunction remains unknown.
In recent years, the growth of Industrial Internet Things has enabled automated data collection and analysis, leading to re-emerging predictive maintenance. However, IIoT devices have insufficient computing power for computationally intensive maintenance tasks. Consequently, Mobile Edge Computing (MEC) been introduced relieve computation burden. This paper focuses on task offloading resource allocation optimization based Deep Deterministic Policy Gradient (DDPG). An Artificial Bee Colony...
In the presence of non-gaussian noise, we propose a method for detection underwater ship-radiated signal. The wavelet decomposition signal yields natural tree structure, which is further modeled by Hidden Markov Tree (HMT). Therefore, represented as parameter correspondent HMT. We analysis likelihood defined on parameters and form new criteria. Experimental results demonstrate reliable robust solution our method.
Text-to-speech synthesis is a promising human- computer interaction technology. Google launched the TTS model Tacotron, which can directly convert raw text to speech. The encoder module one of most important components Tacotron. It extracts context features in and generate time series. contains Recurrent Neural Network (RNN) Convolutional (CNN). There are few hardware accelerators support these hybrid algorithm parallel architecture calculations. To this end, we designed hardware-efficient...
Based on the research and application of transmission equipment asset life intelligent control technology, this paper introduces current problems traditional management, construction cycle information coding system expected results. In order to accelerate digitization new power intelligence management work whole improve flexibility efficiency builds encoding using Interactive Location Code, Item Information Equipment Code Check uses digital scanning device QR code technology break data...