A5066405059- Crystallization and Solubility Studies
- X-ray Diffraction in Crystallography
- AI-based Problem Solving and Planning
- Crystallography and molecular interactions
- Industrial Technology and Control Systems
- Robotic Path Planning Algorithms
- Simulation and Modeling Applications
- Advanced Computational Techniques and Applications
- Constraint Satisfaction and Optimization
- Formal Methods in Verification
- Complex Network Analysis Techniques
- Image and Signal Denoising Methods
- Embedded Systems Design Techniques
- Data Management and Algorithms
- Synthesis of Organic Compounds
- Evaluation and Optimization Models
- Fault Detection and Control Systems
- Advanced Sensor and Control Systems
- Advanced Algorithms and Applications
- Model-Driven Software Engineering Techniques
- Blind Source Separation Techniques
- Copper Interconnects and Reliability
- AI in cancer detection
- Advanced Clustering Algorithms Research
- Machine Fault Diagnosis Techniques
Xidian University
2025
East China University of Science and Technology
2024
University of Electronic Science and Technology of China
2022-2024
National Supercomputing Center in Shenzhen
2021-2024
Shanghai Aerospace Automobile Electromechanical (China)
2024
University of Electro-Communications
2001-2023
Jiangsu University
2023
Chinese Academy of Sciences
2011-2022
Ningbo Institute of Industrial Technology
2022
Shenzhen Institutes of Advanced Technology
2016-2021
Recording runtime status via logs is common for almost every computer system, and detecting anomalies in crucial timely identifying malfunctions of systems. However, manually time-consuming, error-prone, infeasible. Existing automatic log anomaly detection approaches, using indexes rather than semantics templates, tend to cause false alarms. In this work, we propose LogAnomaly, a framework model unstructured stream as natural language sequence. Empowered by template2vec, novel, simple yet...
Atrial fibrillation, one of the most common persistent cardiac arrhythmias globally, is known for its rapid and irregular atrial rhythms. This study integrates temporal convolutional network (TCN) residual (ResNet) frameworks to effectively classify fibrillation in single-lead ECGs, thereby enhancing application neural networks this field. Our model demonstrated significant success detecting with experimental results showing an accuracy rate 97% F1 score 87%. These figures indicate model's...
Logs are one of the most valuable data sources for large-scale service (e.g., social network, search engine) maintenance. Log parsing serves as first step towards automated log analysis. However, current methods not adaptive. Without intra-service adaptiveness, cannot handle software/firmware upgrade because learned templates match new type logs. In addition, without cross-service logs a be accurately parsed when this is newly deployed. We propose LogParse, an adaptive framework, to support...
Human-machine interfaces that facilitate telepresence are speculated to improve performance with teleoperators. Unfortunately, there is little experimental evidence substantiate a direct link between the two. Further, limited data available on technological and psychological factors affect telepresence. The objective of present study was evaluate influence interface design configuration, control mode latency teleoperation performance, telepresence, workload in pick-and-place task. It...
Harmine (HAM) is a natural product with neuroprotective and antitumor activity. Its poor aqueous solubility the major factor limiting its clinical application. In this work, seven new organic acid salts of HAM were prepared systematically characterized. Their single crystals obtained, structures identified by single-crystal X-ray diffractometer. The corresponding solubilities in water determined temperature range 20–35 °C HPLC method. All showed significantly improved powder profiles...
The concept of Digital Twin (DT) is increasingly applied to systems on different levels abstraction across domains, support monitoring, analysis, diagnosis, decision making and automated control. Whilst the interest in applying DT growing, definition unclear, neither there a clear pathway develop fully realise its capacities. In this paper, we revise categorisation. We propose maturity matrix, based which model-based development methodology. also discuss how tools can be used methodology...
The wind power industry continues to experience rapid growth worldwide. However, the fluctuations in speed and direction complicate turbine control process hinder integration of into electrical grid. To maximize utilization, we propose precisely measure a three-dimensional (3D) space, thus facilitating control. Natural is regarded as 3D vector, whose magnitude correspond wind's speed. A semi-conical ultrasonic sensor array proposed simultaneously space. As signal transmitted between sensors...
Clustering aims to differentiate objects from different groups (clusters) by similarities or distances between pairs of objects. Numerous clustering algorithms have been proposed investigate what factors constitute a cluster and how efficiently find them. The fast search density peak algorithm is intuitively determine centers assign points corresponding partitions for complex datasets. This method incorporates simple structure due the noniterative logic less few parameters; however,...
Abstract Controlling an autonomous vehicle's unprotected left turn at intersection is a challenging task. Traditional rule‐based driving decision and control algorithms struggle to construct accurate trustworthy mathematical models for such circumstances, owing their considerable uncertainty unpredictability. To overcome this problem, rule‐constrained reinforcement learning (RCRL) method proposed in work driving. train controller with rule constraints, outcomes of the path planning module...
Medical image segmentation and video object are essential for diagnosing analyzing diseases by identifying measuring biological structures. Recent advances in natural domain have been driven foundation models like the Segment Anything Model 2 (SAM-2). To explore performance of SAM-2 biomedical applications, we designed three evaluation pipelines single-frame 2D segmentation, multi-frame 3D with varied prompt designs, revealing SAM-2's limitations medical contexts. Consequently, developed...
Biomedical image segmentation is crucial for accurately diagnosing and analyzing various diseases. However, Convolutional Neural Networks (CNNs) Transformers, the most commonly used architectures this task, struggle to effectively capture long-range dependencies due inherent locality of CNNs computational complexity Transformers. To address limitation, we introduce TTT-Unet, a novel framework that integrates Test-Time Training (TTT) layers into traditional U-Net architecture biomedical...
Distance-based and density-based clustering algorithms are often used on large spatial arbitrary shape of data sets. However, some well-known have troubles when distribution objects in the dataset varies, this may lead to a bad result. Such performances more dramatically significant high-dimensional dataset. Recently, Rodriguez Laio proposed an efficient algorithm based two essential indicators: density distance, which find cluster centers play important role process clustering. does not...
Epilepsy refers to a set of chronic neurologicalsyndromes characterized by transient and unexpected electrical disturbances the brain. Scalp Electroencephalogram (EEG) is common test that measures records activity brain, widely used in detection analysis epileptic seizures. However, it often difficult identify subtle changes EEG waveform visual inspection. Then, emerge large numbers research for biomedical engineers develop implement several intelligent algorithms identification such...