A5101497500- Video Surveillance and Tracking Methods
- MRI in cancer diagnosis
- Prostate Cancer Diagnosis and Treatment
- Seismic Imaging and Inversion Techniques
- Seismic Waves and Analysis
- Radiomics and Machine Learning in Medical Imaging
- Semantic Web and Ontologies
- Structural Health Monitoring Techniques
- Image Processing Techniques and Applications
- Monoclonal and Polyclonal Antibodies Research
- Advanced Image and Video Retrieval Techniques
- Geophysical Methods and Applications
- Machine Learning in Bioinformatics
- Optical measurement and interference techniques
- Prostate Cancer Treatment and Research
- Face and Expression Recognition
- Data Management and Algorithms
- Recommender Systems and Techniques
- Control and Dynamics of Mobile Robots
- Plant biochemistry and biosynthesis
- Natural Language Processing Techniques
- Innovative Teaching and Learning Methods
- Distributed Control Multi-Agent Systems
- vaccines and immunoinformatics approaches
- RNA modifications and cancer
Chongqing University
2020-2025
Chongqing Cancer Hospital
2014-2025
North China Research Institute of Electro-optics
2024
State Grid Corporation of China (China)
2023-2024
University of Electronic Science and Technology of China
2022-2024
Northwestern Polytechnical University
2022-2023
Ningbo Polytechnic
2023
Anhui Agricultural University
2009-2023
University of Science and Technology of China
2016-2023
Linyi University
2023
Abstract While active efforts are advancing medical artificial intelligence (AI) model development and clinical translation, safety issues of the AI models emerge, but little research has been done. We perform a study to investigate behaviors an diagnosis under adversarial images generated by Generative Adversarial Network (GAN) evaluate effects on human experts when visually identifying potential images. Our GAN makes intentional modifications diagnosis-sensitive contents mammogram in deep...
A tree similarity algorithm for match‐making of agents in e‐Business environments is presented. Product/service descriptions seller and buyer are represented as node‐labeled, arc‐labeled, arc‐weighted trees. such trees developed the basis semantic a virtual marketplace. The exchanged using an XML serialization Object‐Oriented RuleML. Correspondingly, we use declarative language Relfun to implement parameterized, recursive functional program. Three main functions perform top‐down traversal...
In this article, an event-triggered adaptive control strategy is proposed to achieve the leaderless-following consensus for a class of cyber–physical systems under direct topology. Because deception attacks, state time delay, and unknown external disturbance appear simultaneously, existing method hard apply directly. The difficulty issue lies in that actual system states are unavailable efficiencies unknown, which caused by attack. So as tackle these knotty problems, Nussbaum gain functions...
Abstract Background Early diagnosis of prostate cancer improves its prognosis, while it is essential to upgrade screening tools. This study aimed explore the value a novel functional magnetic resonance imaging (MRI) technique, namely amide proton transfer (APT)-weighted MRI, combined with serum prostate-specific antigen (PSA) levels differentiate malignant lesions from benign lesions. Methods Data patients who underwent examinations at Chongqing University Cancer Hospital between July 2019...
Background: Early diagnosis of prostate cancer can improve the survival rate patients on premise high-quality images. The prerequisite for early is ZOOMit a method high-resolution, zoomed FOV imaging, allowing diffusion-weighted images with high contrast and resolution in short acquisition times. RESOLVE DWI an advanced MRI technique developed to obtain high-resolution diffusionweighted reduced susceptibility-related artifacts. Objective: This study aimed compare image quality conventional...
Renal cell carcinoma (RCC) is a heterogeneous group of kidney cancers. capsule invasion an essential factor for RCC staging. To develop radiomics models from CT images the preoperative prediction in patients. This retrospective study included patients with admitted to Chongqing University Cancer Hospital (01/2011-05/2019). We built model distinguish grouped as versus non-capsule invasion, using scans. evaluated effects three imaging phases, i.e., unenhanced phases (UP), corticomedullary...
Abstract Background A B-cell epitope is a group of residues on the surface an antigen which stimulates humoral responses. Locating these epitopes antigens important for purpose effective vaccine design. In recent years, mapping affinity-selected peptides screened from random phage display library to native has become popular in prediction. These peptides, also known as mimotopes, share similar structure and function with corresponding epitopes. Great effort been made using this similarity...
One of the key tasks related to proteins is similarity comparison protein sequences in area bioinformatics and molecular biology, which helps prediction classification structure function. It a significant open issue find similar from large scale database efficiently. This paper presents new distance based analysis using encoding method sequence on fractal dimension. The are first represented into 1-dimensional feature vectors by their biochemical quantities. A series Hybrid involving...
In this work, we propose a large-scale dataset, VRAI, and an effective Orientation Adaptive Salience Attentive (OASA) Network for vehicle re-identification (ReID) in aerial imagery. The VRAI dataset includes two subsets: VRAI-Image, which contains over 137,000 images of 13,000 instances, VRAI-Video, comprises more than 14,000 video trajectories 7,000 identities. To our best knowledge, is the largest UAV-based ReID, first proposed video-based ReID under UAV views. Based on design OASA network...
We have proposed and implemented AgentMatcher, an architecture for match‐making in e‐Business applications. It uses arc‐labeled arc‐weighted trees to match buyers sellers via our novel similarity algorithm. This paper adapts the between learners learning objects (LOs). Canadian Learning Object Metadata (CanLOM) repository of eduSource e‐Learning project. Through AgentMatcher’s new indexing component, known as Generator (LOMGen), metadata is extracted from HTML LOs use CanLOM. LOMGen...
Long-tail learning has garnered widespread attention and achieved significant progress in recent times. However, even with pre-trained prior knowledge, models still exhibit weaker generalization performance on tail classes. The promising Sharpness-Aware Minimization (SAM) can effectively improve the capability of by seeking out flat minima loss landscape, which, however, comes at cost doubling computational time. Since update rule SAM necessitates two consecutive (non-parallelizable) forward...
Abstract Osteoporosis is a significant health and economic issue, as it predisposes patients to higher risk of bone fracture. Measuring mineral density has been shown be an accurate way assess the for osteoporosis. The most common testing dual-energy X-ray absorptiometry (DEXA) scan, which may recommended with increased Radiograph imaging widely available in clinical settings acquired many reasons, such trauma or pain. goal this project extract radiomics information from pelvic X-rays (both...
A high false-positive rate remains a technical glitch hindering the broad spectrum of application deep-learning-based diagnostic tools in routine radiological practice from assisting diagnosing rib fractures.To examine performance two versions software aiding radiologists fractures on chest computed tomography (CT) images.In total, 123 patients (708 fractures) were included this retrospective study. Two groups with different experience levels retrospectively reviewed images for concurrent...
Suspension design is one of the important parts in research field on lunar rover mobile system. To conduct detailed dynamic analysis new type suspension, this paper presents a six link double ring suspension model based ADAMS virtual simulation software. And , designs path tracking neural network controller. Simulation and test results show that has strong ground adaptability, obstacle surmounting capability anti-overturning ability compared to classic controller good ability. The provide...
This paper aims to present and discuss the similarity among users in a social network based on CF (Collaborative Filtering) algorithm SimRank (Similarity Based Random Walk) algorithm. The used predict relationship between user rating items (movies books) user's profile. calculates through finding nearest neighbors for each network. At last, combination of these two algorithms will be get "people may interest other" from users' database. In experimental analysis, data set "DouBan" (a is...