A5045537492- Video Surveillance and Tracking Methods
- Advanced Vision and Imaging
- Topic Modeling
- Hip and Femur Fractures
- Musculoskeletal synovial abnormalities and treatments
- Text and Document Classification Technologies
- Gait Recognition and Analysis
- Image Processing Techniques and Applications
- Energy Load and Power Forecasting
- Power System Reliability and Maintenance
- Traffic control and management
- Cardiac, Anesthesia and Surgical Outcomes
- Optical measurement and interference techniques
- Venous Thromboembolism Diagnosis and Management
- Shoulder Injury and Treatment
- Face recognition and analysis
- Multimodal Machine Learning Applications
- Urban Transport and Accessibility
- IoT Networks and Protocols
- Land Use and Ecosystem Services
- Human Mobility and Location-Based Analysis
- Energy Harvesting in Wireless Networks
- Data Quality and Management
- IoT and Edge/Fog Computing
- Chronic Disease Management Strategies
Zhejiang Energy Group (China)
2023-2024
State Key Laboratory of Industrial Control Technology
2019-2023
Zhejiang University
2018-2023
Zhejiang Energy Research Institute
2023
Zhejiang Chinese Medical University
2021
Zhejiang University of Technology
2019
Recurrent neural networks (RNN) are efficient in modeling sequences for generation and classification, but their training is obstructed by the vanishing exploding gradient issues. In this paper, we reformulate RNN unit to learn residual functions with reference hidden state instead of conventional gated mechanisms such as long short-term memory (LSTM) recurrent (GRU). The structure has two main highlights: firstly, it solves issues large time-distributed scales; secondly, promotes...
This paper describes a dynamic trajectory planning method for lane-changing maneuver of connected and automated vehicles (CAVs). The proposed (DLTP) model adopts vehicle-to-vehicle (V2V) communication to generate an with avoiding potential collisions rollovers during the process. novelty this is that DLTP combines detailed velocity strategy considers more complete driving environment information. Besides, safety monitoring algorithm starting-point determination are presented guarantee...
Monocular depth estimation is a foundation task of three-dimensional (3D) reconstruction which used to improve the accuracy environment perception. Because simpler hardware requirement, it more suitable than other multi-view methods. In this study, new monocular algorithm based on graph convolution network (GCN) proposed. The pixel-wise relationship introduced into conventional neural (CNN) make up disadvantage processing non-Euclidian data. And remaining topological information spatial...
A binocular vision system is a common perception component of an intelligent vehicle. Benefiting from the biomimetic structure, simple and effective. Which are extremely snesitive on external factors, especially missing signals. In this paper, virtual view-generation algorithm based generative adversarial networks (GAN) proposed to enhance robustness systems. The model consists two parts: network discriminator network. To improve quality view, structure 3D convolutional neural (3D-CNN)...
There is a rising need for sensors under an IoT network to identify and monitor the environment as more devices services are made accessible use. This movement presents challenges such proliferation of data scarcity energy. research strategy enhancing service provision capabilities WSN-aided applications by combining mobile edge computation with wireless signal control transmission. In order reduce overall system energy consumption while maintaining transmission rate power needs, new...
Wind power ramp events (WPREs) are a common phenomenon in wind generation. This unavoidable poses great harm to the balance of active and stability frequency supply system, which seriously threatens safety, stability, economic operation grid. In order deal with impact events, accurate rapid detection is significance for formulation response measures. However, some attribute information ignored previous studies, laws characteristics difficult present intuitively. this paper, we propose...
To explore the effect of metabolic syndrome on 15 days postoperative adverse events femoral intertrochanteric fractures with internal fixation.From January 2011 to June 2019, 986 elderly patients fracture were treated fixation, including 312 males and 674 females, an average age of(77.71± 7.58) years old. And there 97 889 without syndrome. Through electronic medical record system, patient's age, gender, type, cause trauma, body mass index, smoking history, preoperative comorbidities,...
PurposeTo inveatigate how effective LMWH was at preventing venous thromboembolism (VTE), major bleeding events, and minor events after simple knee arthroscopic surgery anterior cruciate ligament reconstruction (ACLR).MethodsWe conducted a comprehensive search of PubMed, EMBASE, Cochrane Library, the CNKI database for potentially eligible articles. The outcomes were evaluated in terms odds ratio (OR) associated 95% confidence intervals (CIs). Meta-analysis performed using Stata software...
Entity extraction is widely used in power fault diagnosis to extract valuable knowledge from a large amount of data, supporting and prevention. Traditional entity methods mainly rely on fixed rules procedures, which cannot be dynamically learned or changed with new data knowledge. When dealing complex variable plant traditional have limitations. This paper proposes text mining-based method that updates the model by learning characteristics. makes more adaptive flexible cope data. We compared...