检索结果-内蒙古大学图书馆

9th International Conference on computing and Informatics, ICOCI 2023

作者： Sharif, Nurul Atikah Mohd Harun, Nor Hazlyna Sharimi, Nur Azmielia Muhammad Bakar, Juhaida Abu Awang, Hapini Embong, Zunaina Data Science Research Lab School of Computing University Utara Malaysia Kedah Sintok06010 Malaysia Institute for Advanced and Smart Digital Opportunities School of Computing University Utara Malaysia Kedah Sintok06010 Malaysia Ophthalmologist Department of Ophthalmology School of Medical Sciences Health Campus Universiti Sains Malaysia Kelantan Kubang Kerian16150 Malaysia

ISBN: (纸本)9789819995912

Examining retinal fundus images is compulsory for ophthalmologists to spot features of eye diseases. Some problems, including low contrast and blurred retinal fundus image, may seriously affect the diagnostic procedure, leading to misdiagnosis. Low quality of retinal fundus image makes recognition of features for Diabetic Retinopathy (DR) to be harder for the ophthalmologist. Moreover, there is a lack of eye care facilities infrastructure with ophthalmologists to serve multi-morbid DR patients in rural areas, specifically Malaysia. Hence, this research proposed the development of an automated enhancement system based on computer vision and the Artificial Intelligence (AI) field to improve the quality of fundus images captured. The DR Enhancement System (DRES) helps ophthalmologists in the screening aspect by improving the detection of aberrant fundus images. Several methods for improving the fundus image are utilized: Retinex, Contrast Limited Adaptive Histogram Equalization (CLAHE), and Low-light enhancement. Results show that all methods performed better when improving low-contrast and blurred images. This study contributes to the screening process of DR by improving the quality of the retinal fundus image. The developed AI-based system can also help to solve healthcare logistics problems of reaching DR patients in rural areas. © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Rural areas

来源：评论

学校读者我要写书评

暂无评论

advanced Techniques for Protecting Privacy in Artificial Intelligence Powered Medical Systems 4

Advanced Techniques for Protecting Privacy in Artificial Int...

引用

4th IEEE International Conference on ICT in Business Industry and Government, ICTBIG 2024

作者： Baseera, A. Scaria, Jobin M Trivedi, Abha Sharma, Mayank Sharma, Preeti Saini, Preeti Vit Bhopal University School of Computing Science and Engineering Bhopal-Indore Highway -18 Kothrikalan Madhya Pradesh Sehore466114 India Ibs University School Of Information Technology PO Box 5181 Boroko National Capital District Port Moresby Papua New Guinea Vit Bhopal University School of Computing Science Engineering and Artificial Intelligence Bhopal-Indore Highway Sehore Madhya Pradesh Bhopal India Vit Bhopal University School of Advanced Sciences and Languages Bhopal-Indore Highway Sehore Madhya Pradesh Bhopal466114 India Bansal College of Engineering Bhopal India Manav Rachna International Institute of Research and Studies Haryana Faridabad India

ISBN: (纸本)9798331518981

Privacy protection is required when analyzing healthcare data and using it effectively. This work proposes a novel technique to secure private data in AI-powered medical systems while providing important data insights. The recommended method incorporates challenging techniques such as integrating Laplace distribution noise, managing secure data, and training group models. A privacy budget manages settings to balance analysis performance and individual contributions. The framework outperforms existing approaches in accuracy, precision, memory, F1 score, and privacy compliance. The technique improves data, models, training, and inference speeds, making it suitable for real-time healthcare applications. Iterative feedback enhances the model by modifying components based on real-world data. In addition to ensuring privacy, this entire design enables AI-powered medical systems to identify and anticipate findings. It provides a true, scalable solution that can adapt to healthcare demands, creating a new standard for AI app privacy and data usage. The technology provides a privacy-protected, highly efficient model that enhances decision-making and patient outcomes, enabling AI in healthcare. © 2024 IEEE.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

High-resolution Mo KαX-ray monochromatic backlight imaging using a toroidal crystal

引用

Chinese Optics Letters 2023年第10期21卷 114-118页

作者：司昊轩单连强杜慧瑶蒋励伊圣振周维民王占山 Institute of Precision Optical Engineering MOE Key Laboratory of Advanced Micro-Structured MaterialsShanghai Frontiers Science Center of Digital OpticsShanghai Professional Technical Service Platform for Full-Spectrum and High-Performance Optical Thin Film Devices and ApplicationsSchool of Physics Science and EngineeringTongji UniversityShanghai 200092China Research Center of Laser Fusion China Academy of Engineering PhysicsMianyang 621900China

Curved crystal imaging is an important means of plasma *** to the short wavelengths of high-energy X rays and the fixed lattice constant of the spherical crystal,it is difficult to apply the spherical crystal in high-energy X-ray *** this study,we have developed a high-energy,high-resolution X-ray imager based on a toroidal crystal that can effectively correct *** prepared a Ge<511>toroidal crystal for backlighting Mo Kα1 characteristic lines(∼17.48 keV)and verified its high-resolution imaging ability in high-energy X-ray region,achieving a spatial resolution of 5–10μm in a field of view larger than 1.0 mm.

关键词： laser plasma diagnostics toroidal crystal monochromatic X-ray imaging

来源：评论

学校读者我要写书评

暂无评论

DPA-2:a large atomic model as a multitask learner

引用

npj Computational Materials 2024年第1期10卷 185-199页

作者： Duo Zhang Xinzijian Liu Xiangyu Zhang Chengqian Zhang Chun Cai Hangrui Bi Yiming Du Xuejian Qin Anyang Peng Jiameng Huang Bowen Li Yifan Shan Jinzhe Zeng Yuzhi Zhang Siyuan Liu Yifan Li Junhan Chang Xinyan Wang Shuo Zhou Jianchuan Liu Xiaoshan Luo Zhenyu Wang Wanrun Jiang Jing Wu Yudi Yang Jiyuan Yang Manyi Yang Fu-Qiang Gong Linshuang Zhang Mengchao Shi Fu-Zhi Dai Darrin M.York Shi Liu Tong Zhu Zhicheng Zhong Jian Lv Jun Cheng Weile Jia Mohan Chen Guolin Ke Weinan E Linfeng Zhang Han Wang AI for Science Institute BeijingP.R.China DP Technology BeijingP.R.China Academy for Advanced Interdisciplinary Studies Peking UniversityBeijingP.R.China State Key Lab of Processors Institute of Computing TechnologyChinese Academy of SciencesBeijingP.R.China University of Chinese Academy of Sciences BeijingP.R.China HEDPS CAPTCollege of EngineeringPeking UniversityBeijingP.R.China Ningbo Institute of Materials Technology and Engineering Chinese Academy of SciencesNingboP.R.China CAS Key Laboratory of Magnetic Materials and Devices and Zhejiang Province Key Laboratory of Magnetic Materials and Application Technology Chinese Academy of SciencesNingboP.R.China School of Electronics Engineering and Computer Science Peking UniversityBeijingP.R.China Shanghai Engineering Research Center of Molecular Therapeutics&New Drug Development School of Chemistry and Molecular EngineeringEast China Normal UniversityShanghaiP.R.China Laboratory for Biomolecular Simulation Research Institute for Quantitative Biomedicine and Department of Chemistry and Chemical BiologyRutgers UniversityPiscatawayNJUSA Department of Chemistry Princeton UniversityPrincetonNJUSA College of Chemistry and Molecular Engineering Peking UniversityBeijingP.R.China Yuanpei College Peking UniversityBeijingP.R.China School of Electrical Engineering and Electronic Information Xihua UniversityChengduP.R.China State Key Laboratory of Superhard Materials College of PhysicsJilin UniversityChangchunP.R.China Key Laboratory of Material Simulation Methods&Software of Ministry of Education College of PhysicsJilin UniversityChangchunP.R.China International Center of Future Science Jilin UniversityChangchunP.R.China Key Laboratory for Quantum Materialsof Zhejiang Province Department of PhysicsSchool of ScienceWestlake UniversityHangzhouP.R.China Atomistic Simulations Italian Institute of TechnologyGenovaItaly State Key Laboratory of Physical Chemistry of Solid Surface iChEMCollege of Chemistry and Chemical EngineeringXiame

The rapid advancements in artificial intelligence(AI)are catalyzing transformative changes in atomic modeling,simulation,and ***-driven potential energy models havedemonstrated the capability to conduct large-scale,long-duration simulations with the accuracy of ab initio electronic structure ***,the model generation process remains a bottleneck for large-scale *** propose a shift towards a model-centric ecosystem,wherein a large atomic model(LAM),pretrained across multiple disciplines,can be efficiently fine-tuned and distilled for various downstream tasks,thereby establishing a new framework for molecular *** this study,we introduce the DPA-2 architecture as a prototype for ***-trained on a diverse array of chemical and materials systemsusing a multi-task approach,DPA-2demonstrates superior generalization capabilities across multiple downstream tasks compared to the traditional single-task pre-training and fine-tuning *** approach sets the stage for the development and broad application of LAMs in molecular and materials simulation research.

关键词： DPA establishing thereby

来源：评论

学校读者我要写书评

暂无评论

Current AAV-mediated gene therapy in sensorineural hearing loss

引用

Fundamental research 2025年第1期5卷 192-202页

作者： Jieyu Qi Xiaolong Fu Liyan Zhang Fangzhi Tan Nianci Li Qiuhan Sun Xiaojie Hu Zuhong He Ming Xia Renjie Chai State Key Laboratory of Digital Medical Engineering Department of Otolaryngology Head and Neck SurgeryZhongda HospitalSchool of Life Sciences and TechnologySchool of MedicineAdvanced Institute for Life and HealthJiangsu Province High-Tech Key Laboratory for Bio-Medical ResearchSoutheast UniversityNanjing 210096China Department of Neurology Aerospace Center HospitalSchool of Life ScienceBeijing Institute of TechnologyBeijing 100081China State Key Laboratory of Hearing and Balance Science Beijing Institute of TechnologyBeijing 100081China Advanced Technology Research Institute Beijing Institute of TechnologyJinan 250300China Department of Otorhinolaryngology-Head and Neck Surgery Zhongnan Hospital of Wuhan UniversityWuhan 430071China Department of Otolaryngology Shandong Provincial Hospital Affiliated to Shandong First Medical UniversityJinan 250021China Medical Science and Technology Innovation Center Shandong First Medical University&Shandong Academy of Medical SciencesJinan 250021China Co-Innovation Center of Neuroregeneration Nantong UniversityNantong 226001China Department of Otolaryngology Head and Neck Surgery Sichuan Provincial People's HospitalUniversity of Electronic Science and Technology of ChinaChengdu 610072China Southeast University Shenzhen Research Institute Shenzhen 518063China

The number of patients with hearing loss is on the rise due to congenital abnormalities,degenerative changes in old age,and acquired injuries such as virus or ototoxic drug-induced *** loss is a refractory and disabling disease that has serious negative effects on quality of *** pathology of hearing loss in the inner ear is characterized by varying degrees of damage to the cochlear sensory epithelium cells(such as hair cells and supporting cells),stria vascularis(including marginal,intermediate and basal cells)and spiral ganglion *** or direct repair of damaged cells in the inner ear is an effective way to treat sensorineural *** is currently possible to regenerate hair cells to treat sensorineural hearing loss by FX-322,a small molecule drug in clinical *** the development of genetic engineering technology,gene therapy has brought a promising treatment strategy for many previously intractable *** therapy has been regarded as a promising method in the treatment and rehabilitation of sensorineural hearing loss,and recombinant adeno-associated virus gene therapy has been widely used in fundamental research into hearing loss *** present,gene therapy for hearing loss is transitioning from feasibility studies to explorations of its safety and its therapeutic *** present article reviews the concepts,strategies,and applications of gene therapy mediated by recombinant adeno-associated viruses in the field of hearing loss treatment.

关键词： Hearing loss Cochlea Gene therapy Adeno-associated virus Auditory repair

来源：评论

学校读者我要写书评

暂无评论

Infomaxformer: Maximum Entropy Transformer for Long Time-Series Forecasting Problem 22

Infomaxformer: Maximum Entropy Transformer for Long Time-Ser...

引用

22nd International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2023

作者： Tang, Peiwang Zhang, Xianchao Institute of Advanced Technology University of Science and Technology of China Hefei230026 China G60 STI Valley Industry & Innovation Institute Jiaxing University Jiaxing314001 China Key Laboratory of Medical Electronics and Digital Health of Zhejiang Province Jiaxing University Jiaxing314001 China Engineering Research Center of Intelligent Human Health Situation Awareness of Zhejiang Provincey Jiaxing University Jiaxing314001 China

The Transformer architecture yields state-of-the-art results in many tasks such as natural language processing (NLP) and computer vision (CV), since the ability to efficiently capture the precise long-range dependency coupling between input sequences. With this advanced capability, however, the quadratic time complexity and high memory usage prevents the Transformer from dealing with long time-series forecasting problem (LTFP). To address these difficulties: (i) we revisit the learned attention patterns of the vanilla self-attention, redesigned the calculation method of self-attention based the Maximum Entropy Principle. (ii) we propose a new method to sparse the self-attention, which can prevent the loss of more important self-attention scores due to random sampling.(iii) We propose Keys/Values Distilling method motivated that a large amount of feature in the original self-attention map is redundant, which can further reduce the time and spatial complexity and make it possible to input longer time-series. Finally, we propose a method that combines the encoder-decoder architecture with seasonal-trend decomposition, i.e., using the encoder-decoder architecture to capture more specific seasonal parts. A large number of experiments on several large-scale datasets show that our Infomaxformer is obviously superior to the existing methods. We expect this to open up a new solution for Transformer to solve LTFP, and exploring the ability of the Transformer architecture to capture much longer temporal dependencies. © 2023 International Foundation for Autonomous Agents and Multiagent Systems (***). All rights reserved.

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

EDA: Enhanced Domain-Adversarial Training for Anatomical Landmark Detection 22

EDA: Enhanced Domain-Adversarial Training for Anatomical Lan...

引用

22nd IEEE International Symposium on Biomedical Imaging, ISBI 2025

作者： Yang, Fan Zhou, S. Kevin School of Biomedical Engineering Division of Life Sciences and Medicine University of Science and Technology of China Anhui Hefei 230026 China Center for Medical Imaging Robotics Analytic Computing & Learning (MIRACLE) Suzhou Institute for Advanced Research University of Science and Technology of China Jiangsu Suzhou 215123 China Key Laboratory of Precision and Intelligent Chemistry Ustc Anhui Hefei 230026 China Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology Cas Beijing 100190 China

ISBN: (纸本)9798331520526

Manually annotating anatomical landmarks in medical images requires experienced clinicians and is a labor-intensive process. However, recent AI-assisted methods for landmark detection often rely on the training and test data originating from the same domain. This work introduces a novel unsupervised domain adaptation (UDA) framework aimed at anatomical landmark detection from a medical image, designed to bridge the gap between a source domain with labels and an unlabeled target domain. Specifically, we have developed a new Domain-Adversarial Network that incorporates skip connections to transfer and fuse high-resolution feature maps. Additionally, we proposed Dynamic Gaussian Learning, which allows the model to escape from local error regions. We carry out experiments on landmark detection for both head and chest, and the results demonstrate that our method achieves state-of-the-art performances in each experiment. © 2025 IEEE.

关键词： Anatomical Landmark Detection Unsupervised Domain Adaptation

来源：评论

学校读者我要写书评

暂无评论

Development and Dynamic Numerical Evaluation of a Lightweight Sports Helmet Using Topology Optimization and advanced Architected Materials

引用

Designs 2025年第2期9卷 28-28页

作者： Kladovasilakis, Nikolaos Tsongas, Konstantinos Pechlivani, Eleftheria Maria Tzetzis, Dimitrios Digital Manufacturing and Materials Characterization Laboratory Department of Science and Technology International Hellenic University Thessaloniki57001 Greece Centre for Research & Technology Hellas Information Technologies Institute Thessaloniki57001 Greece Advanced Materials and Manufacturing Technologies Laboratory Department of Industrial Engineering and Management School of Engineering International Hellenic University Thessaloniki57001 Greece

Sports activities often carry a high risk of injury, varying in severity, making the use of protective equipment, such as helmets and kneecaps, essential in many cases. Among all potential injuries, head injuries are the most crucial due to their severity. Hence, in the last decades, the scientific interest has been focused on establishing head injury criteria and improving the helmet design with the ultimate goal of the reduction in injury probability and increasing the athlete’s performance. In this context, the current study aims to develop a lightweight sports helmet with increased safety performance, utilizing topology optimization processes and advanced architected materials. In detail, the design of a conventional helmet was developed and modified applying in specific regions advanced architected materials, such as triply periodic minimal surfaces (TPMS) and hybrid structures, with functionally graded configurations to produce sandwich-like structures capable of absorbing mechanical energy from impacts. The developed helmet’s designs were numerically evaluated through dynamic finite element analyses (FEA), simulating the helmet’s impact on a wall with a specific velocity. Through these analyses, the plastic deformation of the designed helmets was observed, coupled with the stress concentration contours. Furthermore, the results of FEAs were utilized in order to calculate the values of the head injury criterion (HIC). Finally, the developed topologically optimized helmet design incorporating the hybrid lattice structure revealed increased energy absorption, reaching a HIC of 1618, improved by around 14% compared to the conventional design configuration. © 2025 by the authors.

关键词： Shape optimization

来源：评论

学校读者我要写书评

暂无评论

Developing Methods to Evaluate Content Quality of Dementia Websites 15

Developing Methods to Evaluate Content Quality of Dementia W...

引用

15th International Congress in Nursing Informatics: Nurses and Midwives in the digital Age, NI 2021

作者： Zhu, Yunshu Song, Ting Yu, Ping Centre for Digital Transformation School of Computing and Information Technology Faculty of Engineering and Information Sciences University of Wollongong Wollongong Australia Illawarra Health and Medical Research Institute University of Wollongong Australia

ISBN: (纸本)9781643682204

With the popularity of the Internet, consumers are likely to resort to websites for dementia information. However, they may not have the knowledge or experience in distinguishing quality information from opinion pieces. This study investigated the developing methods, instruments and parameters for evaluating the content quality of dementia websites. By reviewing 18 existing instruments from the relevant literature, we identified four developing methods - questionnaire survey, automatic evaluation, Delphi method and focus group discussion. These instruments include six parameters - reliability, currency, readability, disclosure, objectivity and relevance - to evaluate the content quality. With the significant social and economic impact of dementia, developing specific instruments to measure the content quality of dementia websites is necessary. © 2021 International Medical Informatics Association (IMIA) and IOS Press.

关键词： Websites

来源：评论

学校读者我要写书评

暂无评论

Implementation of a Hip Fracture Classification Network Based on CT Tomography Scans

Implementation of a Hip Fracture Classification Network Base...

引用

International Conference on Computer and Communications (ICCC)

作者： Kui Zhao Meng Yang Ti Zhang Die Hu Shenyang Institute of Computing Technology Chinese Academy of Sciences Liaoning Province Human-Computer Interaction System Engineering Research Center Based on Digital Twin Shenyang China Shenyang Institute of Computing Technology Chinese Academy of Science University of Chinese Academy of Science Shenyang China Department of Orthopedics Peking University Third Hospital Beijing China

ISBN: (数字)9798331507077

ISBN: (纸本)9798331507084

Hip fractures is the most common hip clinical trauma. The majority of elderly patients experience a decrease in bone density due to osteoporosis, making them highly prone to various types of hip fractures. In this context, accurate diagnosis and classification of hip fractures are crucial for guiding clinical decision-making and ensuring the best possible patient outcomes. The BV C- N et proposed in this study is a two-stage model for the identification of hip fracture types, which is based on the integration of the V-Net and ConvNeXt architectures. First, deep learning segmentation model is trained to generate candidate fracture regions, and then, a deep learning classification model is trained in the second stage to classify the segmented local fracture regions according to the candidate fracture regions generated in the first stage to ascertain the type of fracture. The results show that the two-stage deep learning model proposed in this study enhances the accuracy of hip fracture type recognition and reduces the time required for manual classification, which can better assist doctors in fracture region recognition.

关键词： Deep learning Image segmentation Adaptation models Osteoporosis Accuracy Computed tomography Transfer learning Predictive models Older adults Hip

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：