A5101941418- Software Testing and Debugging Techniques
- Software Engineering Research
- Software Reliability and Analysis Research
- Advanced Vision and Imaging
- Data Mining Algorithms and Applications
- Advanced Image and Video Retrieval Techniques
- Robotics and Sensor-Based Localization
- Software System Performance and Reliability
- Image Enhancement Techniques
- Image Retrieval and Classification Techniques
- Glaucoma and retinal disorders
- Complex Network Analysis Techniques
- Advanced Computational Techniques and Applications
- Image and Signal Denoising Methods
- Service-Oriented Architecture and Web Services
- Digital Imaging for Blood Diseases
- Medical Image Segmentation Techniques
- Heat shock proteins research
- Parallel Computing and Optimization Techniques
- Advanced Image Fusion Techniques
- Innovation Diffusion and Forecasting
- Wireless Signal Modulation Classification
- EEG and Brain-Computer Interfaces
- Blind Source Separation Techniques
- Ginseng Biological Effects and Applications
Nanjing University of Aeronautics and Astronautics
2012-2025
National University of Defense Technology
2014-2025
Hohai University
2009-2025
Tiangong University
2025
Xidian University
2008-2024
China Academy of Space Technology
2024
Jinan University
2009-2024
Sun Yat-sen Memorial Hospital
2024
Sun Yat-sen University
2024
Xi'an University of Technology
2024
Retinal fundus image is an important modality to document the health of retina and widely used diagnose ocular diseases such as glaucoma, diabetic retinopathy age-related macular degeneration. However, enormous amount retinal data obtained nowadays mostly stored locally; valuable embedded clinical knowledge not efficiently exploited. In this paper we present online depository, ORIGA(-light), which aims share groundtruth images with public; provide open access for researchers benchmark their...
Fault localization is essential for solving the issue of software faults. Aiming at improving fault localization, this paper proposes a deep learning-based with contextual information. Specifically, our approach uses neural network to construct suspiciousness evaluation model evaluate statement being faulty, and then leverages dynamic backward slicing extract The empirical results show that significantly outperforms state-of-the-art technique Dstar.
<i>Background:</i> High-resolution contrast-enhanced magnetic resonance imaging (CEMRI) has been proven to be an effective tool for the identification of carotid atherosclerotic vulnerable plaque, such as a large lipid core and thin fibrous cap. The aim this study was evaluate relationship between plaque characteristics types stroke in patients who had artery (CA) stenosis ≥50%. <i>Methods:</i> 102 consecutive subjects (mean age 67.2 ± 10.2 years; 73 males) initially...
The prognosis of acute promyelocytic leukemia (APL) in the elderly is poorer than that younger patients after treatment with all-trans retinoic acid plus chemotherapy, which current standard therapy for APL. A significantly higher mortality during consolidation was found, mainly due to deaths from sepsis following chemotherapy-induced myelosuppression.A total 33 aged 60 years or older de novo APL were treated single-agent arsenic trioxide (ATO) remission induction and postremission therapy....
Abstract Many fault localization approaches recently utilize deep learning to learn an effective model showing a fresh perspective with promising results. However, models are generally learned from class imbalance datasets; that is, the number of failing test cases is much fewer than passing cases. It may be highly susceptible affect accuracy models. Thus, in this paper, we explore using data resampling reduce negative effect imbalanced problem and improve deep‐learning‐based localization....
(1) Objective: As light propagates through water, it undergoes significant attenuation and scattering, causing underwater images to experience color distortion exhibit a bluish or greenish tint. Additionally, suspended particles in the water further degrade image quality. This paper proposes an improved U-Net network model for enhancement generate high-quality images. (2) Method: Instead of incorporating additional complex modules into networks, we opted simplify classic architecture....
Numerous fault localization techniques identify suspicious statements potentially responsible for program failures by discovering the statistical correlation between test results (i.e., <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">failing</i> or xmlns:xlink="http://www.w3.org/1999/xlink">passing</i> ) and executions of different a xmlns:xlink="http://www.w3.org/1999/xlink">covered</i> xmlns:xlink="http://www.w3.org/1999/xlink">not...
Meningiomas are the most common primary intracranial tumors in adults. Low-grade meningiomas have a low recurrence rate, whereas high-grade highly aggressive and recurrent. Therefore, pathological grading information is crucial for treatment, as well follow-up prognostic guidance. Most previous studies used radiomics or deep learning methods to extract feature meningiomas. However, some features pixel-level that can be influenced by factors such image resolution sharpness. Additionally,...
What is the central question of this study? Previous studies have shown that hypersympathetic nerve activity results in ventricular electrophysiological changes and facilitates occurrence arrhythmias. Vagus stimulation has therapeutic potential for myocardial infarction-induced However, actions vagus on activity-induced are still unknown. main finding its importance? We show able to reverse suppress fibrillation. These findings further suggest may be an effective treatment option...
Trace data is critical for fault localization (FL) to analyze suspicious statements potentially responsible a failure. However, existing trace representation meets its bottleneck mainly in two aspects: (1) the information of statement restricted local context (i.e., test case) without consideration global all cases suite); (2) it just uses ‘occurrence’ strong FL semantics. Thus, we propose UNITE : an infl U ential co N text-Gu I ded T race r E presentation, representing from both and...
Abstract Heat shock protein 90 (Hsp90) is a tumor marker that accelerates cancer growth by disrupting homeostasis. However, concerns such as low clinical efficacy and drug resistance continue to be obstacles the successful marketing of Hsp90 inhibitors. The cytoprotective function autophagy has been identified one mechanisms which cells gain chemotherapy. JD‐02 was new inhibitor suppressed colorectal (CRC) lowering client levels in vivo vitro. We found increased cellular autophagy, inhibited...
The primary objective of this study is to understand the regulatory role epigenetics in thyroid-associated ophthalmopathy (TAO) using multi-omics sequencing data. We utilized tRFs data, DNA methylation and lncRNA/circRNA/mRNA as well several RNA target prediction websites, analyze effect methylation, non-coding RNA, on TAO-associated genes. Through differential expression analysis, we identified 1019 differentially expressed genes, 985 methylated 2601 RNA. Functional analysis showed that...
Background and objectives: Stroke is a major cause of disability. Certain experimental studies have suggested that combination almitrine + raubasine (Duxil) increases the supply oxygen to cerebral tissues may be beneficial in post-stroke rehabilitation. This multicentre clinical study was carried out order assess efficacy this on Methods: The trial randomised, double-blind, placebo-controlled study. Patients had experienced an ischaemic cerebrovascular accident (confirmed by CT scan) were...
In this paper, an edge extraction model based on artificial bee colony algorithm has been proposed to overcome the problems of concrete defect detection in complex underwater environment specialized dam cracks detection. To enhance weak-object gray contrast under different brightness, adaptive enhancement method is presented which a concept two-dimensional lateral inhibitory network introduced and border highlighting rule designed. Furthermore, increase effective, improved used optimization...
A test suite is indispensable for conducting effective fault localization, and has two classes of tests: passing tests failing tests. However, in practice, heavily outnumber regarding a fault, leading to being minority class contrast Previous work empirically shown that the lack leads class-balanced suite, which tends hamper localization effectiveness.To address this issue, we propose MSGen: Model-domain Synthesized Failing Test Generation approach. MSGen utilizes widely used information...
Verification of hardware design code is crucial for the quality assurance products. Being an indispensable part verification, localizing bugs in significant development but often regarded as a notoriously difficult and time-consuming task. Thus, automated bug localization techniques that could assist manual debugging have attracted much attention community. However, existing approaches are hampered by challenge achieving both demanding accuracy facile automation single method....
The verification of hardware design code is a critical aspect in ensuring the quality and reliability products. Finding bugs important for development frequently considered as notoriously challenging time-consuming activity while being an essential verification. Thus, bug localization techniques that could assist manual debugging have attracted much attention community. However, there exists unpredictable time span between precise origin its detected manifestation prior work without costly...