检索结果-内蒙古大学图书馆

3rd International Conference on Intelligent Systems, Advanced Computing, and Communication, ISACC 2025

作者： Muthukumar, Sai Smrithi Gandham, Bhavika Vijayekkumaran, Trisha Jyotsna, C. Aiswariya Milan, K. Amrita School of Computing Dept. of Computer Science and Engineering Bengaluru India

ISBN: (纸本)9798331523893

Chest X-ray images are widely used in diagnosing medical conditions, however, due to radiologist fatigue and shortage of resources the possibility of spotting peculiarities increases. This work proposes an explainable AI system to identify, quantify, and explain the pathology found in chest x-ray images. It builds credibility, enhances medical judgment, and reflects efficient utilization of radiology assets. This study used ResNet for the chest X-ray image classification and compared it with other related models like EfficientNetB0, DenseNet, VGGNet, and MobileNet. ResNet had the best AUC value of 0.826 thereby garnering it the best classification accuracy hence validating its selection as the main model. Moreover, ResNet adapted explainability to provide visual and textual interpretations and to classify diseases where such actionable insights could improve the reliability of diagnosis and patient outcomes. © 2025 IEEE.

关键词： CheXpert Explainable AI Grad-CAM ResNet X-ray masks X-rays

来源：评论

学校读者我要写书评

暂无评论

A review on 3D image reconstruction on specific and generic objects

引用

Materials Today: Proceedings 2023年 80卷 2400-2405页

作者： Shalma, H. Selvaraj, P. Dept. of Computer Science and Engineering SRM Institute of Science and Technology Kattankulathur Chennai India Dept. of Information Technology SRM Institute of Science and Technology Kattankulathur Chennai India

With the emergence of various techniques involved in deep learning the researchers of computer vision tends to focus on the strategies such as object recognition and segmentation of image. This has inclined to accomplish the deep learning techniques in 3D reconstruction of both specific and generic objects. As the space for reconstruction of 3D images either in single or multi view has envisioned the researchers to concentrate on the available technologies used for reconstruction. With the available built in methods and technologies in deep learning, the performance of the proposed methods were reviewed and analyzed using several parameters. As the remaking of 2D images is still in the beginning stage, it is important to study the 3D shape representations, various network architecture, methodologies and approaches behind 3D reconstruction. In this work a review of deep learning methods for single or multiple RGB images of specific and generic object 3D reconstruction was done. Several methods and their importance were also discussed along with the challenges encountered and with further research directions. This paper critically analyzes the various 3D Shaped Representations, 3D Data Network Architectures, dept. Estimation methods, Multi View Representations and the Data Representation Techniques. © 2021

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

Innovative Approaches to CT Image Enhancement: Deep Learning Solutions for Denoising and Deblurring

Innovative Approaches to CT Image Enhancement: Deep Learning...

引用

2025 International Conference on Ambient Intelligence in Health Care, ICAIHC 2025

作者： Prajapat, Gopal Krishan Yadav, Dharmendra Bikaner Technical University Dept. of Computer Science and Engineering Bikaner India

ISBN: (纸本)9798331530259

Computed Tomography (CT) is essential in medical diagnostics, providing detailed images of internal structures. Noise and blur introduced during image acquisition can com-promise diagnostic accuracy, especially in low-dose CT (LDCT) scans aimed at reducing radiation exposure. Deep learning methods have emerged as effective solutions for addressing these challenges, with significant advancements in both denoising and deblurring techniques. This paper reviews recent deep learning approaches for CT image enhancement, covering supervised and self-supervised methods. The paper also explores emerging trends such as diffusion models and transformer-based architectures that offer improved image quality and restoration efficiency. Simultaneous denoising and deblurring techniques are examined for their potential in clinical applications. Promising future directions include the use of large-scale pretrained models, zero-shot learning, and prompt-based frameworks, which have the potential to further enhance CT image quality while maintaining low radiation exposure, thereby advancing diagnostic capabilities. © 2025 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Solving Task-Select Problems Using a Quantum Annealer

Solving Task-Select Problems Using a Quantum Annealer

引用

2025 IEEE International Conference on Consumer Electronics, ICCE 2025

作者： Mita, Koki Yachi, Yuta Fukada, Keisuke Togawa, Nozomu Dept. of Computer Science and Communications Engineering Waseda University Tokyo Japan

ISBN: (纸本)9798331521165

To tackle environmental and social challenges, we face numerous tasks that need to be solved. However, due to limited time and resources, it is unrealistic to solve all tasks. Therefore, prioritizing tasks to ensure efficient handling and meeting criteria is essential. When the number of tasks is large, prioritizing the optimal combination of tasks on classical computers becomes highly time-consuming. We define this prioritization as a combinatorial optimization problem, termed the task-select problem, and address it using a quantum annealer. A quantum annealer is specialized hardware designed to efficiently solve combinatorial optimization problems by transforming them into Quadratic Unconstrained Binary Optimization (QUBO) problems. In this paper, we propose a QUBO formulation for the task-select problem. Experimental evaluations demonstrate that our approach enables solving the task-select problem with up to 100 items using a real quantum annealer. © 2025 IEEE.

关键词： Ising model

来源：评论

学校读者我要写书评

暂无评论

Advances in Remote Sensing Technologies for Ecological Monitoring and Applications in Carbon Stock Estimation 3

Advances in Remote Sensing Technologies for Ecological Monit...

引用

3rd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2025

作者： Sadhasivam, Shankaripriya Gayathri, G. Poongothai, P. Pavithra, S. Dept. of Computer Science and Engineering Chennai Institute of technology Chennai India

ISBN: (数字)9798331527549

ISBN: (纸本)9798331527549

This review explores recent advancements that are made in remote sensing, enabling detailed analysis of our ecosystem through high resolution and multispectral imaging. The recent advancements in remote sensing includes developments useful for generation of synthetic images using GAN such as StyleGAN3 and for estimation of carbon stocks in forest using OBIA. Ecotones like mangroves and saltmarsh are crucial for carbon sequestration but mapping them accurately was challenging due to spectral similarity and seasonal variations. Focusing on coastal protection by this review examines the mapping methodologies such as random forest classification, OBIA and FID for habitat distinction, canopy area assessment and analysis. Through these technologies data accuracy can be enhanced for better monitoring. This review concludes with a discussion of AI-powered image synthesis and classification. © 2025 IEEE.

关键词： Carbon sequestration

来源：评论

学校读者我要写书评

暂无评论

Machine Learning - Driven Approaches for Detection and Analysis of Phishing attacks: A Robust Framework for Cybersecurity 7

Machine Learning - Driven Approaches for Detection and Analy...

引用

7th International Conference on Inventive Computation Technologies, ICICT 2024

作者： Sarvan, N.D.S.S. Sai Ram Reddy, Venkata Jain, Darshan Rakesh, Guntupalli Anguraj, Dinesh Kumar Kl University Dept. of Computer Science Engineering Guntur India

ISBN: (纸本)9798350359299

Phishing is the attempt to trick someone into disclosing confidential and private information by using internet communication, such as bank account details, passwords, credit/debit card details, and usernames. The accuracy of foreseeing such phishing assaults can be substantially enhanced through utilizing these algorithms. The primary objective of this research work is to enhance internet security by providing a dependable and productive method for detecting phishing websites. To achieve this, a machine learning-based approach was employed, utilizing various models trained on a dataset of phishing website attributes. The study evaluated a range of machine learning algorithms and classifiers, including Naive Bayes, Support Vector Machine, K-Nearest Neighbors, Gradient Boosting, Decision Tree, Random Forest, Bagging, Voting, and AdaBoost Classifiers. These evaluation parameters are used to determine the efficiency of the machine learning models including F1 Score, Accuracy, Precision, and Recall values. By training the dataset with key variables from credible websites, the Bagging Classifier algorithm demonstrated a substantial improvement, achieving an accuracy rate of 98.4% resulting in a significant enhancement in phishing website detection compared to other methods. © 2024 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Design and Development of Expense App

Design and Development of Expense App

引用

2024 International Conference on Advances in Computing Research on science engineering and Technology, ACROSET 2024

作者： Girdhar, Gunit Kumar, Sachin Bhardwaj, Anuj Sharma, Megha Chandigarh University Dept. of Computer Science & Engineering Mohali India

ISBN: (纸本)9798350388800

With the help of Expense Tracker, you can easily and intuitively manage your revenue and costs while keeping track of your everyday, weekly, monthly, and annual spending. Users may choose the kind of expenditure, add location, upload more data, choose the amount of expense, and more. Additionally, the relational database will save this data. Users have the option to see and sort spending weekly, monthly, or annually. We may track the spending and minimize the amount of human computations for their costs by employing this. This allows a user to enter their income to get an estimate of their daily costs, and the results are saved for each individual user. Individuals who frequently go on excursions or to the theatre with friends might use this tracker to keep tabs on their spending. They will find it simple to split the bill using this tracker. This will show graphs according to the chosen perspective. Additionally, a user may write in this TR his monthly income or monthly expenditure cap. An integrated feature set is offered by this tracker system to assist you in managing your spending and cash flow. © 2024 IEEE.

关键词： Cost benefit analysis

来源：评论

学校读者我要写书评

暂无评论

A Framework to Find Single Language Version Using Pattern Analysis in Mixed Script Queries 2

A Framework to Find Single Language Version Using Pattern An...

引用

2nd International Conference on Disruptive Technologies, ICDT 2024

作者： Chaudhary, Anu Shekhar, Shashi Gla University Dept. of Computer Science and Engineering Mathura India

ISBN: (纸本)9798350371055

Pattern analysis for converting a complete mixed code into a single language after determining confidence levels is a systematic approach crucial for applications requiring language uniformity. The process begins by tokenizing the mixed code into individual words or segments and employing a language identification algorithm to assign potential languages with associated confidence scores to each segment. Establishment of a confidence threshold allows for the reliable selection of dominant languages within the mixed code. Segmentation based on confidence levels and the application of a majority language rule ensures the prioritization of the most reliable language segments. In cases where confidence falls below the threshold or ambiguity arises, a fallback mechanism can be implemented, offering options like defaulting to a predefined language or flagging for manual review. The conversion strategy is then formulated based on the identified dominant language, utilizing tools such as machine translation services or language-specific processing libraries. The final output is a unified, single-language version of the mixed code, providing consistency and reliability in diverse linguistic contexts. The bulk of the words are Hindi, it has been noted after handing to the model. This is the reason these mixed codes need to be translated into majority language script. Make a table of replacements to swap out the unclear acronym with the matching term. There are 79 words in all, and 1 of those words are erroneous;thus, the correctness of the work is (78 / 79) × 100=98.73 %, and the mistake rate is (1/79)× 100=1.27%. © 2024 IEEE.

关键词： Dominant language Pattern analysis Segmentation Single language version

来源：评论

学校读者我要写书评

暂无评论

Elastic Vertical Memory Management for Container-based Stateful Applications in Kubernetes 25

Elastic Vertical Memory Management for Container-based State...

引用

40th Annual ACM Symposium on Applied Computing, SAC 2025

作者： Kang, Taeshin Yu, Heonchang Dept. of Computer Science and Engineering Korea University Seoul Korea Republic of

ISBN: (纸本)9798400706295

Cloud service providers offer horizontal auto-scaling to prevent wasting resources by overprovisioning containers. However, this approach struggles to respond immediately to unexpected spikes in resource usage and has limitations in optimizing resource utilization. Vertical auto-scaling overcomes these limitations. Vertical elasticity has become increasingly important in recent years to provide instant resource elasticity for stateful and real-time critical applications. Nevertheless, vertical elasticity is not actively researched and implemented due to limitations in achieving it. This paper proposes Elastic Vertical Memory Management (EVMM) for stateful applications in the Kubernetes environment, which is the de facto standard in the container orchestration space. We compared EVMM to an existing Kubernetes environment without vertical elasticity and found that it reduced the total execution time of container workflows by up to 35% and memory resource utilization on nodes improved by 1.5x. Copyright © 2025 held by the owner/author(s).

关键词： auto-scaling

来源：评论

学校读者我要写书评

暂无评论

Performance Comparison of Machine Learning Algorithms for Parkinson's Disease Detection 14

Performance Comparison of Machine Learning Algorithms for Pa...

引用

14th International Conference on Cloud Computing, Data science and engineering, Confluence 2024

作者： Gupta, Ipsha Vashisth, Dhwani Garg, Rakesh Amity University Dept. of Computer Science and Engineering UP India

ISBN: (纸本)9798350344837

Parkinson's Disease affects the neural system and can be detected using biomarkers, physiological and motor disruptions exhibited by patients. Several advancements and research on Machine Learning approaches have been carried out and tested to diagnose PD in the early stages of its inception by continuous monitoring of physical actions of patients. In this study we: (a) conduct a comprehensive analysis of existing machine learning algorithms to detect PD patients, (b) summarize and categorize the findings of efficiency of these algorithms, (c) test these algorithms on speech recordings of patients, (d) provide the model with best accuracy with an overview of all the models previously researched or currently in use. The benefits and shortcomings of the referenced models are thoroughly contrasted and explored for better accessibility for future research. © 2024 IEEE.

关键词： Support vector machines

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：