A5075376655- Transportation Planning and Optimization
- Traffic control and management
- Traffic Prediction and Management Techniques
- Advanced Fiber Laser Technologies
- Human Mobility and Location-Based Analysis
- Privacy-Preserving Technologies in Data
- Advanced Neural Network Applications
- Mobile Crowdsensing and Crowdsourcing
- Quantum Information and Cryptography
- Neural Networks and Applications
- Privacy, Security, and Data Protection
- Vehicle emissions and performance
- Quantum Mechanics and Applications
- Nonlinear Optical Materials Studies
- Laser-Matter Interactions and Applications
- Photonic Crystal and Fiber Optics
- Network Security and Intrusion Detection
- IoT and Edge/Fog Computing
- Internet Traffic Analysis and Secure E-voting
- Mechanical and Optical Resonators
- Image Retrieval and Classification Techniques
- Catalytic C–H Functionalization Methods
- Cryptographic Implementations and Security
- Biometric Identification and Security
- Fuzzy Logic and Control Systems
Hunan University
2016-2025
Central South University
2006-2025
Central South University of Forestry and Technology
2022-2025
Xiangyang Central Hospital
2025
Hubei University of Arts and Science
2025
Huazhong University of Science and Technology
2024
Hangzhou Dianzi University
2024
Tianjin Research Institute of Electric Science (China)
2024
Delft University of Technology
2009-2023
Guangzhou University
2023
Diabetic retinopathy (DR) is a common eye disease and significant cause of blindness in diabetic patients. Regular screening with fundus photography timely intervention the most effective way to manage disease. The large population patients their massive requirements have generated interest computer-aided fully automatic diagnosis DR. Deep neural networks, on other hand, brought many breakthroughs various tasks recent years. To automate DR provide appropriate suggestions patients, we built...
Hashing plays a pivotal role in nearest-neighbor searching for large-scale image retrieval. Recently, deep learning-based hashing methods have achieved promising performance. However, most of these involve discriminative models, which require large-scale, labeled training datasets, thus hindering their real-world applications. In this paper, we propose novel strategy to exploit the semantic similarity data and design an efficient generative adversarial framework learn binary hash codes...
With the increasing popularity of location-based services (LBSs), it is paramount importance to preserve one's location privacy. The commonly used privacy preserving approach, k-anonymity, strives aggregate queries k nearby users within a so-called cloaked region via trusted third-party anonymizer. As such, probability identify every user involved no more than 1/k, thus offering preservation for users. One inherent limitation however, that all are assumed be and report their real locations....
A rule base covering the entire input domain is required for conventional Mamdani inference and Takagi–Sugeno–Kang (TSK) inference. Fuzzy interpolation enhances fuzzy systems by allowing use of sparse bases which certain inputs are not covered. Given that almost all existing approaches were developed to support inference, this paper presents a novel approach extends TSK This also proposes data-driven generation method extended system. The proposed system in two ways: (1) workable with...
The rhodium-catalyzed deoxygenation and borylation of ketones with B2pin2 have been developed, leading to efficient formation alkenes, vinylboronates, vinyldiboronates. These reactions feature mild reaction conditions, a broad substrate scope, excellent functional-group compatibility. Mechanistic studies support that the initially undergo Rh-catalyzed give alkenes via boron enolate intermediates, subsequent dehydrogenative leads vinylboronates diboration products, which is also supported by...
Abstract Background There are a variety of determinants that key to functional disability older adults. However, little is known regarding the relationship between cognitive frailty and among people. The aims this study were examine associations its six components with instrumental activities daily living (IADL) functioning in community-dwelling Methods A total 313 adults (aged ≥ 65 years) recruited from eight community centers central China. Cognitive was operationalized using Mini-Mental...
Fuel consumption and atmospheric pollution emissions of vehicles depend on driving conditions, the characteristics driver car. The influence style environmental aspects a car journey has been investigated. Driver were determined by Behaviour Questionnaire observed acceleration deceleration behaviour. That results in four types drivers with similar within type group. We measured 56 trajectories 28 using GPS devices. measurements done route 8.4 km an urban environment Chengdu (PR China). From...
The number of vehicles has increased year by year, especially individual vehicles. In addition to meeting basic transportation needs, are expected serve varied location-based services and applications for humans. However, it can constitute severe risks privacy. this article, we concentrate on one the most sensitive information, namely, social relationships, that be inferred from vehicle mobility data. We propose a relationship inference model, which provides new perspective privacy...
A rhodium-catalyzed remote C(sp3 )-H borylation of silyl enol ethers (SEEs, E/Z mixtures) by alkene isomerization and hydroboration is reported. The reaction exhibits mild conditions excellent functional-group tolerance. This method compatible with an array SEEs, including linear branched SEEs derived from aldehydes ketones, provides direct access to a broad range structurally diverse 1,n-borylethers in regioselectivities good yields. These compounds are precursors various valuable...
We demonstrate the highly stable soliton generation from a fiber laser mode-locked by VSe2 nanosheets experimentally. The prepared via liquid phase exfoliation method exhibit ultrafast relaxation time and excellent nonlinear optical behavior with saturation intensity modulation depth of 14.28 MW/cm2 19.11%, respectively. A Er3+-doped pulse duration 714 fs signal-to-noise ratio 78.44 dB has been delivered successfully based on saturable absorber. In addition, transition conventional to...
Flooding poses a significant risk to urban metro networks, leading station closures and service suspensions. By integrating the flood vulnerability of stations, this study evaluates robustness networks. Utilizing geographical, topological, socio-economic data, impact flooding on network is quantified. A composite index, which combines with topological properties, developed evaluate importance individual stations under conditions. The Changsha analyzed as case study, simulations conducted...
Abstract Convolutional neural network (CNN), as a prominent machine learning model, is crucial in image classification and feature extraction by completely utilizing the correlation information of data. Currently, CNN facing challenges slow computing speed, expanding data scale poor interpretation for rapidly increasing Hilbert space. Fortunately, quantum convolutional (QCNN) promises an elegant solution to improve efficiency processing combining superiority capability CNN. However, most...
Abstract The stability of the power system and fault detection classification are essential components in achieving intelligence systems. LSTM (Long Short-Term Memory) recurrent neural networks can effectively handle temporal nonlinear nature load data, making them suitable for short-term classification. A method based on is proposed. results demonstrate accuracy convenience model.
Glioma-associated epilepsy (GAE) is a common neurological symptom in glioma patients, which can worsen the condition and increase risk of death on basis primary injury. Given this, accurate prediction GAE crucial, this study aims to develop validate warning recognition model. We retrospectively collected MRI scan imaging data urine samples from 566 patients at Xiangyang Central Hospital, Affiliated Hospital Hubei University Arts Science August 2016 December 2023. Least Absolute Shrinkage...