检索结果-内蒙古大学图书馆

Enhanced Diabetic Retinopathy Detection: An Explainable Semi-Supervised Approach Using Contrastive Learning

IEEE Journal of Biomedical and Health informatics 2025年 PP卷 PP页

作者： Ali, Rashid Khan, Fiaz Gul Rehman, Zia Ur Kwak, Daehan Ali, Farman Comsats University Islamabad Department of Computer Science Abbottabad Campus KPK Abbottabad22060 Pakistan Kean University Department of Computer Science and Technology NJ07083 United States Sungkyunkwan University Department of Applied Ai School of Convergence College of Computing and Informatics Seoul03063 Korea Republic of

Diabetic retinopathy (DR) is a leading cause of blindness and represents a critical challenge to global vision health. Early detection is essential to preventing irreversible eye damage. Automated medical image analysis plays a pivotal role in enabling timely diagnosis. However, the development of robust diagnostic models is challenged by the scarcity of labeled data and the prevalence of imbalanced and unlabeled datasets. Semi-supervised learning offers a potential solution by leveraging unlabeled data to enhance model performance. However, it is often limited by challenges such as unreliable pseudo-labeling, the exclusion of low-confidence data, and biases introduced by imbalanced datasets. To address these limitations, we propose a novel semi-supervised learning framework for DR detection that combines similarity and contrastive learning. Our approach utilizes class prototypes and an ensemble of classifiers to generate reliable pseudo-labels for unlabeled data. Unlike traditional methods that discard unreliable samples, our framework integrates them into the training process using contrastive learning. This allows us to extract valuable features and improve overall performance. Furthermore, we enhance the model's transparency and interpretability by incorporating the explainable AI technique GradCAM, which provides insights into the model's predictions for specific images. We evaluated the proposed method on the publicly available Kaggle DR dataset for diabetic retinopathy classification. Experimental results demonstrate that our approach achieves improved performance compared to existing semi-supervised learning methods. It also effectively leverages unreliable samples, highlighting its potential to advance DR diagnosis. © 2013 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

A Comparison of Regression Techniques for Prediction of Air Quality in Smart Cities

A Comparison of Regression Techniques for Prediction of Air ...

引用

Advanced Innovations in Smart Cities (ICAISC), International Conference on

作者： Kamal Deep Garg Manik Gupta Bhisham Sharma Imed Ben Dhaou Chitkara University Institute of Engineering and Technology Chitkara University Punjab India Department of Computer Science Hekma School of Engineering Computing and Informatics Dar Al-Hekma University Jeddah Saudi Arabia

The expansion of the internet of things (IoT) and Big Data are two factors that have contributed to the rise in popularity of smart cities. The ability to anticipate the quality of the air in an area with precision and efficiency is one of the fundamental building blocks of a smart city. The amount of polluted air found in smart cities throughout the world has been gradually growing. Because of this, there has been a rise in the concentration of several air pollutants in the environment, including particulate matter (PM 10), sulphur dioxide (SO2), and PM 2.5, amongst others. Because of the possibility of uncontrollable repercussions, such as an increase in the severity of asthma and cardiovascular disease, this situation poses a risk to the country and to the people who live in it. Heavy industry and vehicle exhaust have been major contributors to the growth of air pollution in smart cities such as New Delhi, Bombay, Chandigarh, and Bengaluru in India. The purpose of this investigation is to compare and contrast the efficiency of a variety of machine learning methods in order to assess the precision of the air quality index (AQI) projection of PM 2.5 in Chandigarh, India. Models for predicting AQI are trained and tested using a variety of statistical techniques like Linear regression, Lasso regression, KNN regression, and Random Forest regression This Root Mean Square Error (RMSE) found for Linear regression, Lasso regression, KNN regression, and Random Forest regression are 31.01, 29,45, 37.09 and 28.3. From all four models, random forest regression was more accurate than the other three regression models in estimating PM 2.5 levels in India’s smart city.

关键词： Deep learning Technological innovation Smart cities Atmospheric modeling Linear regression Air pollution Prediction algorithms

来源：评论

学校读者我要写书评

暂无评论

Single-cell technologies: current and near future

引用

Science China(Life Sciences) 2025年第1期68卷 1-4页

作者： Chenfei Wang Qi Liu Xiaohui Fan Tieliu Shi KeyLaboratory of Spine and Spinal CordInjury Repairand Regeneration Ministry of EducationOrthopedics DepartmentTongji HospitalBioinformatics DepartmentSchoolofLifeSciencesandTechnologyTongji UniversityShanghai 200082China Frontier Science Center for Stem Cells School of Life Sciences and TechnologyTongji UniversityShanghai 200092China Translational Medical Center for Stem Cell Therapy and Institute for Regenerative Medicine Shanghai East HospitalBioinformatics DepartmentSchool of Life Sciences and TechnologyTongji UniversityShanghai 200082China Research Institute of Intelligent Computing Zhejiang LabHangzhou 311121China Pharmaceutical Informatics Institute College of Pharmaceutical SciencesZhejiang UniversityHangzhou 310058China National Key Laboratory of Chinese Medicine Modernization Innovation Center of Yangtze River DeltaZhejiang UniversityJiaxing 314103China Center for Bioinformatics and Computational Biology Shanghai Key Laboratory of Regulatory Biologythe Institute of Biomedical Sciences and School of Life SciencesEast China Normal UniversityShanghai 200241China Key Laboratory of Advanced Theory and Application in Statistics and Data Science(MOE) School of StatisticsEast China Normal UniversityShanghai 200062China

Single-cell technologies enable the indepth exploration of multiple biological hierarchies at the scale of individual cells,which have deepened our knowledge of cellular diversity,tissue organization,and overall organism function(Sun et al.,2024).In 2009,single-cell RNA sequencing(scRNA-seq)was first developed as a powerful tool to dissect gene expression and uncover transcriptional *** the rapid advancement of technology,single-cell approaches have expanded to encompass other omics,such as genomics,epigenomics,proteomics,and ***,multimodal technologies including spatially resolved transcriptomics and clustered regularly interspaced short palindromic repeats(CRISPR)screening at the single-cell level further advanced our ability to comprehensively understand cellular ***-cell methods provide deeper insights into disease mechanisms across various conditions,including cancer,developmental disorders,and aging-associated *** this issue,we focus on topics related to single-cell methods,covering the following four aspects:(i)single-cell multi-omic sequencing technology;(ii)single-cell spatial technology;(iii)singlecell CRISPR screening technology;(iv)applications of single-cell technology.

关键词： expanded enable insight

来源：评论

学校读者我要写书评

暂无评论

A Bi-level Globalization Strategy for Non-convex Consensus ADMM and ALADIN

arXiv

引用

arXiv 2023年

作者： Du, Xu Wang, Jingzhe Zhou, Xiaohua Mao, Yijie The Institute of Mathematics HNAS Henan Academy of Science Zhengzhou China The Department of Informatics & Networked Systems School of Computing and Information University of Pittsburgh PittsburghPA United States The School of Information Science and Technology ShanghaiTech University China

In this paper, we formally analyze global convergence in the realm of distributed consensus optimization. Current solutions have explored such analysis, particularly focusing on consensus alternating direction method of multipliers (C-ADMM), including convex and non-convex cases. While such efforts on non-convexity offer elegant theory guaranteeing global convergence, they entail strong assumptions and complicated proof techniques that are increasingly pose challenges when adopted to real-world applications. To resolve such tension, we propose a novel bi-level globalization strategy that not only guarantees global convergence but also provides succinct proofs, all while requiring mild assumptions. We begin by adopting such a strategy to perform global convergence analysis for the non-convex cases in C-ADMM. Then, we employ our proposed strategy in consensus augmented Lagrangian based alternating direction inexact Newton method (C-ALADIN), a more recent and generalization of C-ADMM. Surprisingly, our analysis shows that C-ALADIN globally converges to local optimizer, complementary to the prior work on C-ALADIN, which had primarily focused on analyzing local convergence for non-convex cases. © 2023, CC0.

关键词： Newton-Raphson method

来源：评论

学校读者我要写书评

暂无评论

Diversity and stylization of the contemporary user-generated visual arts in the complexity-entropy plane

arXiv

引用

arXiv 2024年

作者： Kim, Seunghwan Lee, Byunghwee Lee, Wonjae Graduate School of Culture Technology KAIST Daejeon34141 Korea Republic of Center for Complex Networks and Systems Research Luddy School of Informatics Computing and Engineering Indiana University BloomingtonIN47408 United States Institute of Basic Science Sungkyunkwan University Suwon16419 Korea Republic of

The advent of computational and numerical methods in recent times has provided new avenues for analyzing art historiographical narratives and tracing the evolution of art styles therein. Here, we investigate an evolutionary process underpinning the emergence and stylization of contemporary user-generated visual art styles using the complexity-entropy (C-H) plane, which quantifies local structures in paintings. Informatizing 149,780 images curated in DeviantArt and Bēhance platforms from 2010 to 2020, we analyze the relationship between local information of the C-H space and multi-level image features generated by a deep neural network and a feature extraction algorithm. The results reveal significant statistical relationships between the C-H information of visual artistic styles and the dissimilarities of the multi-level image features over time within groups of artworks. By disclosing a particular C-H region where the diversity of image representations is noticeably manifested, our analyses reveal an empirical condition of emerging styles that are both novel in the C-H plane and characterized by greater stylistic diversity. Our research shows that visual art analyses combined with physics-inspired methodologies and machine learning, can provide macroscopic insights into quantitatively mapping relevant characteristics of an evolutionary process underpinning the creative stylization of uncharted visual arts of given groups and time. © 2024, CC BY.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Analysis of self-directed learning ability, reading outcomes, and personalized planning behavior for self-directed extensive reading

引用

Interactive Learning Environments 2023年第6期31卷 3613-3632页

作者： Huiyong Li Rwitajit Majumdar Mei-Rong Alice Chen Yuanyuan Yang Hiroaki Ogata a Academic Center for Computing and Media Studies Kyoto University Kyoto Japan b Graduate Institute of Digital Learning and Education National Taiwan University of Science and Technology Taipei City Taiwan c Graduate School of Informatics Kyoto University Kyoto Japan

ABSTRACTSelf-directed learning (SDL) ability, its usefulness in higher education and life-long learning have been highlighted in previous literature. However, there has been much less understanding of the effects of SDL ability in the school settings, specifically the effects on learners’ SDL behaviors and processes. To address this limitation, this study investigated the relations between SDL ability, SDL behaviors, and reading outcomes and further explored the process of planning behaviors in SDL. This study examined the context of SDL for extensive reading using a goal-oriented active learning system, GOAL. The results showed that the high SDL ability students demonstrated significantly more reading outcomes in terms of books completed and the number of days read than those with low SDL ability. The high SDL ability students engaged significantly more in planning behaviors, that were found to be significantly correlated with reading outcomes, than the low SDL ability students. Cluster analysis and transition analysis also differentiate groups of learners with different planning behaviors. These findings suggested that the learning behaviors and outcomes facilitated by the environment were affected to varying degrees by the levels of students’ SDL ability, and personalized feedback can be created using the SDL behavioral variables and patterns in the environment.

关键词： Self-directed learning extensive reading learning behavior planning behavior secondary school

来源：评论

学校读者我要写书评

暂无评论

Numerical Simulation of a Primary Air Pollution Process in Beijing-Tianjin-Hebei Region based on WRF-Chem

Numerical Simulation of a Primary Air Pollution Process in B...

引用

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Jian Gao Xiaolu Ling Wenhao Liu Yong Xue Zeyu Tang School of Environment and Spatial Informatics China University of Mining and Technology Xuzhou China Jiangsu Key Laboratory of Coal-Based Greenhouse Gas Control and Utilization China University of Mining and Technology Xuzhou China School of Electronics Computing and Mathematics College of Engineering and Technology University of Derby Derby UK

A typical heavy pollution weather in Beijing-Tianjin-Hebei region from October 5 to 12, 2014 was selected for numerical simulation based on WRF-Chem model, using environmental monitoring data, meteorological observation data and reanalysis data to analyze the meteorological impact factors of the pollution process and the spatial and temporal variation characteristics of pollutants.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Improved Decision Support for Product Returns using Probabilistic Prediction

Improved Decision Support for Product Returns using Probabil...

引用

Computer Science, Computer Engineering, & Applied computing (CSCE), Congress in

作者： Dirar Sweidan Ulf Johansson Beatrice Alenljung Anders Gidenstam School of Informatics University of Skövde Sweden Dept. of Information Technology University of Borås Sweden Department of Computing Jönköping University Jönköping Sweden School of Informatics University of Skövde Skövde Sweden Dept. of Information Technology University of Borås Borås Sweden

Product returns are not only costly for e-tailers, but the unnecessary transports also impact the environment. Consequently, online retailers have started to formulate policies to reduce the number of returns. Determining when and how to act is, however, a delicate matter, since a too harsh approach may lead to not only the order being cancelled, but also the customer leaving the business. Being able to accurately predict which orders that will lead to a return would be a strong tool, guiding which actions to be taken. This paper addresses the problem of data-driven product return prediction, by conducting a case study using a large real-world data set. The main results are that well-calibrated probabilistic predictors are essential for providing predictions with high precision and reasonable recall. This implies that utilizing calibrated models to predict some instances, while rejecting to predict others can be recommended. In practice, this would make it possible for a decision-maker to only act upon a subset of all predicted returns, where the risk of a return is very high.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Evaluation of Chinese electronic enterprise from business and customers perspectives 2

Evaluation of Chinese electronic enterprise from business an...

引用

2nd International Conference on Smart computing and Electronic Enterprise, ICSCEE 2021

作者： Bamansoor, Samer El-Ebiary, Yousef A. Baker Yusoff, Fakhrul Hazman Pathmanathan, P. Ravindran Saany, Syarilla Iryani Ahmad Bakar, Zainab Binti Abu Aseh, Khairi Pande, Bishwajeet Al Moaiad, Yazeed MEDIU Faculty of Computer and Information Technology Malaysia University of Aden Aden Yemen UniSZA Faculty of Informatics and Computing Malaysia Universiti Teknologi MARA Malaysia International Institute of Applied Science Swiss School of Management Netherlands UniSZA Faculty of Informatics and Computing Malaysia MEDIU Faculty of Computer and Information Technology Malaysia Gyancity Research Consultancy Pvt Ltd Motihari India

ISBN: (纸本)9781665432221

The evaluation of companies in the era of modern technologies is due to how and to what extent these companies use such technologies. Provided that modern technologies are dealt with in all aspects of the company, internally and externally. Also, the first company to provide market data and information for free to all shoppers and visitors to its online platform around the world is the Alibaba Group. Alibaba also has its own mission of making the process of buying or marketing everything in the world uncomplicated for everyone, but specifically to introduce Chinese business to the people of the world serving China's vision of conquering the world with its products. Alibaba Group revenues are rising as it reaches more demand than its opponent in the global market. Besides that, the Alibaba Group communication system and how the business connects with the retailer is very interesting. Their business approach has made them famous and distinguished in Asia. Internationally, it is important for Alibaba to gain a higher connection to join well-known western brands, especially luxury and luxury brands, due to the unfulfilled requirements among Chinese customers for the brand that cannot be reached in China. So, it is also possible for Alibaba to be a lucrative brand for retailers around the world to sell their products and as the world grows, that could also be for the Business to Business (B2B) or Customer to Customer (C2C) marketplace. © 2021 IEEE.

关键词： Electronic commerce

来源：评论

学校读者我要写书评

暂无评论

Learning a Simple Low-Light Image Enhancer from Paired Low-Light Instances

Learning a Simple Low-Light Image Enhancer from Paired Low-L...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Zhenqi Fu Yan Yang Xiaotong Tu Yue Huang Xinghao Ding Kai-Kuang Ma Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China School of Informatics Xiamen University China School of Computer Science and Technology Hangzhou Dianzi University China School of Electrical and Electronic Engineering Nanyang Technological University Singapore

Low-light Image Enhancement (LIE) aims at improving contrast and restoring details for images captured in lowlight conditions. Most of the previous LIE algorithms adjust illumination using a single input image with several handcrafted priors. Those solutions, however, often fail in revealing image details due to the limited information in a single image and the poor adaptability of handcrafted priors. To this end, we propose PairLIE, an unsupervised approach that learns adaptive priors from low-light image pairs. First, the network is expected to generate the same clean images as the two inputs share the same image content. To achieve this, we impose the network with the Retinex theory and make the two reflectance components consistent. Second, to assist the Retinex decomposition, we propose to remove inappropriate features in the raw image with a simple self-supervised mechanism. Extensive experiments on public datasets show that the proposed PairLIE achieves comparable performance against the state-of-the-art approaches with a simpler network and fewer handcrafted priors. Code is available at: https://***/zhenqifu/PairLIE.

关键词：

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：