A5100330109- Software Engineering Research
- Radiomics and Machine Learning in Medical Imaging
- Face and Expression Recognition
- COVID-19 diagnosis using AI
- Advanced Image and Video Retrieval Techniques
- Software Reliability and Analysis Research
- Lung Cancer Diagnosis and Treatment
- Software System Performance and Reliability
- Software Engineering Techniques and Practices
- Image Retrieval and Classification Techniques
- Higher Education and Teaching Methods
- Image and Video Stabilization
- Advanced Neural Network Applications
- Neural Networks Stability and Synchronization
- Software Testing and Debugging Techniques
- Advanced Measurement and Detection Methods
- Robotics and Sensor-Based Localization
- Medical Image Segmentation Techniques
- Image and Object Detection Techniques
- Chaos control and synchronization
- Web Data Mining and Analysis
- Remote-Sensing Image Classification
- Recommender Systems and Techniques
- AI in cancer detection
- Anomaly Detection Techniques and Applications
Chongqing University
2016-2025
Jinzhong University
2022-2025
Wuhan University
2024-2025
Gansu Coalfield Geology Bureau
2025
Hangzhou Dianzi University
2024
University of Electronic Science and Technology of China
2024
City Institute, Dalian University of Technology
2024
Guangdong Pharmaceutical University
2024
Shanghai Dianji University
2024
State Key Laboratory of Information Engineering in Surveying Mapping and Remote Sensing
2024
Cage stability directly affects the dynamic performance of rolling bearing, which, in turn, operating state rotating equipment. The random collision between elements and cage pocket is main reason for instability. In this paper, from perspective relative sliding velocity bearing raceway, interactions pockets were analyzed, four zones with different features defined. On basis, on basis dynamics model, interaction two adjacent a’–b’ area discussed, peak impact force balls was investigated...
Automated code generation can be a powerful technique for software development, significantly reducing developers' efforts and time required to create new by generating it automatically based on requirements. Recently, OpenAI's language model ChatGPT has emerged as tool human-like responses wide range of textual inputs (i.e., prompts), including those related generation. However, the effectiveness is not well understood, performance could heavily influenced choice prompt. To answer these...
Background: Software defect models can help software quality assurance teams to allocate testing or code review resources. A variety of techniques have been used build prediction models, including supervised and unsupervised methods. Recently, Yang et al. [1] surprisingly find that perform statistically significantly better than in effort-aware change-level prediction. However, little is known about relative performance for file-level Goal: Inspired by their work, we aim investigate whether...
Cloud service providers conservatively provision excessive resources to ensure level objectives (SLOs) are met. They often set lower CPU utilization targets quality is not degraded, even when the workload varies significantly. Not only does this potentially waste resources, but it can also consume power in large-scale cloud deployments. This paper aims minimize resource costs while ensuring SLO requirements met a dynamically varying, production microservice environment. We propose...
With the development of global social economy and deepening aging population, diseases related to have received increasing attention. The pathogenesis many respiratory remains unclear, lung is an independent risk factor for diseases. mechanism may be involved in occurrence Aging-induced immune, oxidative stress, inflammation, telomere changes can directly induce promote aging. Meanwhile, also further aggravates immune stress inflammatory response diseases; two mutually affect each other...
Retinal blood vessels structure plays an important role in the early diagnosis of diabetic retinopathy, which is a cause blindness globally. However, precise segmentation retinal often extremely challenging due to low contrast and noise capillaries. In this paper, we propose novel model deep coarse-to-fine supervision network (CTF-Net) solve problem. This consists two U-shaped architecture(coarse fine segNet). The coarse segNet, learns predict probability retina map from input patchs, while...
Programming question and answer (Q&A) websites, such as Stack Overflow, gathered knowledge expertise of developers from all over the world, this reflects some insight into development activities. To comprehend actual thoughts needs developers, we analyzed non-functional requirements (NFRs) on Overflow. In paper, acquired textual content Overflow discussions, utilized topic model, latent Dirichlet allocation (LDA), to discover main topics used wordlists find relationship between discussions...
Open-source platform (e.g., GitHub) creates a tremendous opportunity for developers to learn and build experience. Contribution open source can be rewarding advocates the evolutionary progress of open-source software. However, finding suitable project contribute intimidating because enormous possible choices. Due various social technical barriers, might fail successfully. Frequent unsuccessful onboarding hampers not only developers' individual advancement but also projects. To mitigate...
Just-in-time (JIT) bug prediction is an effective quality assurance activity that identifies whether a code commit will introduce bugs into the mobile app, aiming to provide prompt feedback practitioners for priority review. Since collecting sufficient labeled data not always feasible some apps, one possible approach leverage cross-app models. In this work, we propose new cross-triplet deep feature embedding method, called CDFE, JIT task. The CDFE method incorporates state-of-the-art loss...
The important cues for a realistic lung nodule synthesis include the diversity in shape and background, controllability of semantic feature levels, overall CT image quality. To incorporate these as multiple learning targets, we introduce <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Multi-Target Co-Guided Adversarial Mechanism</i> , which utilizes foreground background mask to guide tissues, takes advantage mediastinal window guidance...
Logs are widely used for system behavior diagnosis by automatic log mining. Log parsing is an important data preprocessing step that converts semi-structured messages into structured as the feature input Currently, many studies devoted to proposing new parsers. However, best of our knowledge, no previous study comprehensively investigates effectiveness parsers in industrial practice. To investigate practice, this paper, we conduct empirical on six state-of-the-art 10 microservice...
In a biometric recognition task, the manifold of data is result interactions between sub-manifold dynamic factors subjects and static subjects. Therefore, instead directly constructing graph Laplacian samples, we firstly divide each subject into part (subject-invariant part) (intra-subject variations) then jointly learn their Laplacians to yield new Laplcian. We use this replace original Locality Preserving Projections (LPP) present supervised dimensionality reduction algorithm. name...