A5063891979- Recommender Systems and Techniques
- Advanced Graph Neural Networks
- Topic Modeling
- Complex Network Analysis Techniques
- Sentiment Analysis and Opinion Mining
- Advanced Text Analysis Techniques
- Human Mobility and Location-Based Analysis
- Face recognition and analysis
- Plant Pathogens and Fungal Diseases
- Advanced Image and Video Retrieval Techniques
- Mycotoxins in Agriculture and Food
- Mobile Crowdsensing and Crowdsourcing
- Fungal Plant Pathogen Control
- Advanced Neural Network Applications
- Data Management and Algorithms
- Generative Adversarial Networks and Image Synthesis
- Geographic Information Systems Studies
- Advanced Bandit Algorithms Research
- Bioinformatics and Genomic Networks
- Network Security and Intrusion Detection
- IoT-based Smart Home Systems
- Industrial Vision Systems and Defect Detection
- Music and Audio Processing
- Indoor and Outdoor Localization Technologies
- Machine Learning and Algorithms
Beijing University of Posts and Telecommunications
2017-2025
Fuzhou University
2025
Wuzhou University
2024
Xi'an Jiaotong University
2024
Shanghai Zhangjiang Laboratory
2024
Yangzhou University
2024
Suzhou Traditional Chinese Medicine Hospital
2024
Foshan University
2024
Xiamen University of Technology
2017-2023
Guangdong University of Technology
2022-2023
Many studies utilized machine learning schemes to improve network intrusion detection systems recently. Most of the research is based on manually extracted features, but this approach not only requires a lot labor costs also loses information in original data, resulting low judgment accuracy and cannot be deployed actual situations. This paper develops DL-IDS (deep learning-based system), which uses hybrid Convolutional Neural Network (CNN) Long Short-Term Memory (LSTM) extract spatial...
Constructing the magnesium alloy with fine grains, low density of dislocations, and weak crystal orientation is crucial importance to enhance its comprehensive performance as anode for Mg-air battery. However, this unique microstructure can hardly be achieved conventional plastic deformation such rolling or extrusion. Herein, we tailor Mg-Al-Sn-RE by using friction stir processing, which obviously refines grains without increasing dislocation strengthening orientation. The battery processed...
Sparse mobile crowdsensing (SMCS) has emerged as a promising sensing paradigm for urban sensing, leveraging the spatial and temporal correlation among data sensed in distinct sub-areas to cut expenses dramatically. It intelligently selects only tiny portion of target regions accurately infers remaining unsensed areas. SMCS confronts numerous challenges, such cell selection missing inference, when compared crowdsensing. Researchers recent years have proposed plenty strategies solve these...
Fusarium head blight, also called scab, is caused by graminearum and one of the most important destructive diseases wheat. The frequency carbendazim resistance in 1,132 isolates F. recovered from fields different regions Henan Province 2016, 2017, 2018 was determined. A total 31 resistant to were detected, including 30 moderately highly isolate. 2.7%. range effective concentration (EC50) values 1,101 sensitive 0.08 0.98 μg ml-1 2.73 13.28 ml-1, respectively. mean ± SD EC50 value 0.55 0.13...
Path planning is critical to realizing a high-performance unmanned aerial vehicle (UAV) crowdsensing system, which can be deployed carry out large-scale tasks in the physical world, especially emergency scenarios, such as earthquakes and mudslides. Deep reinforcement learning (DRL) has recently proven its superiority path design. However, it often applied under assumption that entire status of target region available, hard achieve practice. Instead, efforts should made ensure efficient...
Abstract Semiconductor lasers hold significant promise for space laser communication. However, excessive radiation in can cause failures. In principle, quantum dot (QD) are more radiation‐resistant than traditional semiconductor because of their superior carrier confinement and smaller active regions. the multifaceted nature effects on QDs result ongoing controversies. this work, comprehensive tests under simulated conditions InAs/GaAs is conducted to validate performance. The results reveal...
Personality detection aims to deduce a user’s personality from their published posts. The goal of this task is map posts specific types. Existing methods encode post information obtain user vectors, which are then mapped labels. However, existing face two main issues: first, only using small models makes it hard accurately extract semantic features multiple long documents. Second, the relationship between vectors and labels not fully considered. To address issue poor representation, we...
With the tight coupling of multi-energy systems, accurate multiple-load forecasting will be primary premise for optimal operation integrated energy systems. Therefore, this paper proposes a Copula correlation analysis combined with deep bidirectional long and short-term memory neural network model. First, is used to conduct on multiple loads various influencing factors. The factors that have great were screened out as input feature set model eliminate influence interfering Then, was...
Abstract Fusarium head blight (FHB) is caused by graminearum , which contributes serious economic losses to crop yields, and an epidemic disease of wheat. The resistance tebuconazole 1,118 F . strains obtained from different areas Henan Province in 2018–2020 was determined the discriminatory doses 5.0 μg/ml. A total 362 resistant were detected, frequency F. 30.7%. EC 50 90 values calculated according mycelial growth inhibition population. range 756 sensitive 0.01–0.69 0.02–3.31 μg/ml,...