检索结果-内蒙古大学图书馆

DICNet: A Novel CNN Model based on DenseNet with Interleaved Convolutional Block Attention Module for the Classification of Breast Cancer Histopathology Images

DICNet: A Novel CNN Model based on DenseNet with Interleaved...

引用

2024 International Conference on Smart Systems for Applications in Electrical sciences, ICSSES 2024

作者： Kumar, Arvind Singh, Chandan Sachan, Manoj Kumar Sant longowal Institute of Engineering and Technology Department of Computer Science and Engineering Sangrur India Punjabi University Department of Computer Science Patiala India

ISBN: (纸本)9798350364040

Histopathology image analysis is crucial for the accurate diagnosis of breast cancer (BC), which is the most prevalent cancer among women. The prompt secondary opinions based on automated analysis can assist pathologists, reduce workload, and minimize interobserver variability. This paper introduces the DICNet, a novel convolutional neural network (CNN) architecture based on DenseNet with interleaved convolutional block attention module (CBAM) to classify the BC histopathology images. Specifically, the interleaved attention mechanism utilizes inter-channel and inter-spatial relationships among convolutional features to accentuate more informative and discriminative features. Furthermore, the pooled responses from multiple convolutional layers with varying spatial resolutions are concatenated to obtain a multi-scale representation. The classification performance of the proposed model is evaluated on the publicly available benchmark BreaKHis dataset with four magnification levels. The proposed DICNet model achieves an overall best classification accuracy of 94.02 % at the 40× magnification level. Additionally, DICNet demonstrates enhanced classification performance at every magnification level, and significantly outperforms existing state-of-the-art approaches. © 2024 IEEE.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

GRA: Graph Representation Alignment for Semi-Supervised Action Recognition

引用

IEEE Transactions on Neural Networks and Learning Systems 2024年第9期35卷 11896-11905页

作者： Huang, Kuan-Hung Huang, Yao-Bang Lin, Yong-Xiang Hua, Kai-Lung Tanveer, M. Lu, Xuequan Razzak, Imran National Taiwan University of Science and Technology Department of Computer Science and Information Engineering Taipei10607 Taiwan Indian Institute of Technology Indore Department of Mathematics Indore Simrol453552 India La Trobe University Department of Computer Science and IT MelbourneVIC3086 Australia University of New South Wales School of Computer Science and Engineering SydneyNSW2052 Australia

Graph convolutional networks (GCNs) have emerged as a powerful tool for action recognition, leveraging skeletal graphs to encapsulate human motion. Despite their efficacy, a significant challenge remains the dependency on huge labeled datasets. Acquiring such datasets is often prohibitive, and the frequent occurrence of incomplete skeleton data, typified by absent joints and frames, complicates the testing phase. To tackle these issues, we present graph representation alignment (GRA), a novel approach with two main contributions: 1) a self-training (ST) paradigm that substantially reduces the need for labeled data by generating high-quality pseudo-labels, ensuring model stability even with minimal labeled inputs and 2) a representation alignment (RA) technique that utilizes consistency regularization to effectively reduce the impact of missing data components. Our extensive evaluations on the NTU RGB+D and Northwestern-UCLA (N-UCLA) benchmarks demonstrate that GRA not only improves GCN performance in data-constrained environments but also retains impressive performance in the face of data incompleteness. © 2012 IEEE.

关键词： Alignment

来源：评论

学校读者我要写书评

暂无评论

Enhancing Logistics Efficiency With ML-driven ERP Prediction For Distribution Management in Smart Transportation Systems 8

Enhancing Logistics Efficiency With ML-driven ERP Prediction...

引用

8th IET Smart Cities Symposium, SCS 2024

作者： Gangajaliya, K. Gajjar, J. Darji, K. Gupta, Rajesh Magotra, Bhagyalakshmi Tanwar, Sudeep Department of Computer Science and Engineering Institute of Technology Nirma University Gujarat Ahmedabad India Department of Computer Engineering Model Institute of Engineering and Technology J&K Jammu India

ISBN: (纸本)9781837242672

This research paper analyzes the use of machine learning techniques to predict effective radiated power (ERP) and enhance logistics efficiency in distribution management for smart transportation systems (STS). Three regression models, namely Linear regression, Bayesian Ridge regression, and automatic relevance determination (ARD) regression, have been employed to predict the ERP values based on the extracted features. The performance of each of these models has been assessed using established regression metrics, including mean squared error (MSE) and R-squared (R2). To determine the best-performing model, techniques such as marginal-log-likelihood comparison have been utilized. Additionally, we employ cross-validation techniques to ensure the reliability and generalization capability of the models. The comparative analysis of regression metrics and the cross-validation outcomes further validate the suitability of machine-learning approaches for ERP prediction in distribution management scenarios. The obtained results demonstrate the effectiveness of machine learning in accurately predicting ERP values, thereby significantly improving logistics operations by optimized route planning, minimized transportation costs, and enhancing overall operational performance within distribution networks. © The Institution of engineering & technology 2024.

关键词： Linear regression

来源：评论

学校读者我要写书评

暂无评论

Enhanced Web based Multi-Platform E-voting Solution 5

Enhanced Web based Multi-Platform E-voting Solution

引用

5th International Conference on Smart Electronics and Communication, ICOSEC 2024

作者： Nallapareddy, Anusha Swapna, T. Shanmugam, Sundaramurthy Shabu, Jany Refonaa, J. Hyderabad India G Narayanamma Institute of Technology and Science Department of Computer Science and Engineering Hyderabad India Srm Institute of Science and Technology Department of Computing Technologies Chennai India Sathyabama Institute of Science and Technology Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798331504403

In democratic nations such as India, the act of voting is a basic right that grants individuals the power to choose their leaders. Traditionally, voting has typically taken place at specific locations called polling booths, either in centralized or distributed. Every Indian citizen above 18 years of age has the right to vote and participate in choosing their representatives. Voters go to the polling booths where they can cast their votes under the observation of authorized individuals. However, this traditional voting system has various challenges such as low voter turnout and instances of fraudulent voting. To address these issues, a secure multi-platform E-Voting system is proposed in this research, developed using the Flutter framework and Firebase backend services. The system aims to verify each voter before they can cast their vote, employing multiple levels of verification. The proposed application consists of an administrator (admin) interface and a voter interface. The admin interface allows for the addition of elections, candidates, and constituencies, while the voter interface requires voters to register, log in, and cast their vote. The verification process includes One Time Password (OTP) authentication, face recognition, fingerprint verification, and validation through government-issued identification cards. Two commonly used identification cards in India are the Aadhaar card and the Permanent Account Number (PAN) card, which are unique to each citizen. By utilizing this proposed online voting application, eligible voters can conveniently cast their votes from anywhere in the world, using internet-connected devices like mobile phones or tablets. The primary objectives of the proposed system are to increase voter turnout and reduce instances of fraudulent voting. Furthermore, conducting elections through this application also helps reduce the required workforce. © 2024 IEEE.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

QMCS-IAS: Quantum mechanism and compression sensing-based image authentication and security technique

引用

Multimedia Tools and Applications 2024年 1-27页

作者： Singh, Ranjeet Kumar Tripathi, Kuldeep Narayan Kaur, Gagandeep Agrawal, Rohit Department of Computer Science and Engineering Madhav Institute of Technology & ampScience Race Course Road MP Gwalior474005 India

Ensuring the security and protection of digital content transmitted over a network is a critical challenge, as data can take various forms, such as text, images, audio, and videos, all of which can be easily manipulated by hackers. Watermarking is one of the practical approaches to address data authentication, copyright protection, and document ownership issues. The primary objective of this research is to develop hybrid watermark encryption and as well as compression of watermark embedding mechanism that ensures secure and efficient watermarking of images using quantum chaos maps and discrete wavelet transformation. This study also introduces a novel dual watermarking approach combining quantum chaos-based encryption and discrete wavelet transformation to achieve robust watermark embedding, also its maintain the capacity of watermarked images. The method involves encrypting watermark components using measurement matrices derived from quantum chaos maps, followed by pixel exchange procedures and embedding into specific frequency sub-bands of the host image, thereby enhancing both the security and quality of watermarking. The objective of this work is to maintain the capacity of watermarked images during the dual embedding process using a compression mechanism. Experimental results show the proposed approach consistently outperforms the existing approach in terms of watermark image quality and robustness. The correlation coefficient (CC) coefficients for the proposed algorithm generally range between 0.95 and 0.99, indicating superior watermark preservation and retrieval capabilities. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

The Evolution and Impact of Price Comparison Websites: A Technological and Economic Analysis 4

The Evolution and Impact of Price Comparison Websites: A Tec...

引用

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

作者： Patidar, Mukesh Vekariya, Daxa Pradhan, Preeti Gupta, Kartik Patidar, Praveen Kumar Khan, Pirmohammad Parul University Parul Institute of Engineering and Technology Department of Computer Science & Engineering Gujarat Vadodara India Madhya Pradesh Indore India Acropolis Institute of Technology and Research Department of Computer Science and Engineering Madhya Pradesh Indore India Parul University Parul Institute of Technology Department of Computer Science & Engineering Gujarat Vadodara India

ISBN: (纸本)9798331518981

Price comparison websites (PCWs) have become integral to the online shopping experience, enabling consumers to make informed decisions by comparing prices, features, and reviews from multiple retailers. These platforms not only benefit consumers by saving time and money but also influence market competition by increasing pricing transparency and driving businesses to optimize their strategies. This research explores the evolution of PCWs, their technological infrastructure, and their business models. Moreover, it examines their impact on consumer behavior, the challenges they pose for retailers, and the future trends shaping the industry. Through an analysis of current practices, technological innovations, and economic effects, this work highlights the growing importance of PCWs in the global e-commerce ecosystem. © 2024 IEEE.

关键词： Marketplaces

来源：评论

学校读者我要写书评

暂无评论

Enhanced Visuals through Software-Optimized Memory Pipeline 2

Enhanced Visuals through Software-Optimized Memory Pipeline

引用

2nd International Conference on computer, Communication and Control, IC4 2024

作者： Ramesh, P.S. Senthilvadivu, S. Sudha, I. Kumar, T. Rajesh Naveen, V. Nagarajan, B. Vel Tech Rangarajan Dr.Sagunthala R&d Institute of Science and Technology Department of Computer Science and Engineering Chennai India Saveetha University Saveetha Institute of Medical and Technical Sciences Department of Computer Science and Engineering Tamil Nadu Chennai India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Simats Department of Computer Science and Engineering Tamil Nadu Chennai India Madanapalle Institute of Technology and Science Department of Computer Science and Technology Madanapalle India Kpr Institute of Engineering and Technology Department of Computer Science and Engineering Tamilnadu Coimbatore India

ISBN: (纸本)9798350387933

Image processing algorithms, which supply the image quality, are used by modern mobile devices to capture images. These methods need more RAM to process an image and fix these problems. Software pipelines are utilized to reduce memory usage as much as feasible while maintaining the highest level of flexibility and affordability. Our method uses a line-based buffer software pipeline, which improves image quality and runs at a minimal cost. By transferring only the output to the next phase, the algorithm operates on an individual basis. Each step is completed in less time. Using picture enhancement and noise reduction techniques results in increased productivity, reduced memory consumption, and greater image quality. The applied framework demonstrates noise reduction with the PSNR algorithm and yields good results. © 2024 IEEE.

关键词： Image quality

来源：评论

学校读者我要写书评

暂无评论

Incipient motion of sediment by turbulent kinetic energy in the presence of emergent vegetation in the outer sidewall of a bend

引用

ISH Journal of Hydraulic engineering 2025年第2期31卷 139-147页

作者： Rismani, Nasim Afzalimehr, Hossein Asghari-Pari, Seyed-Amin Nazari-Sharabian, Mohammad Karakouzian, Moses Department of Civil Engineering Iran University of Science and Technology Tehran Iran Department of Civil Engineering Behbahan Khatam Alanbia University of Technology Behbahan Iran Department of Mathematics Engineering and Computer Science West Virginia State University Institute WV United States Department of Civil and Environmental Engineering and Construction University of Nevada Las Vegas NV United States

This study examines the influence of vegetation on sediment movement in a 180° river bend with rigid emergent vegetation on the outer side. Using an Acoustic Doppler Velocimeter, researchers collected 504 velocity profiles under conditions with and without vegetation, across four different vegetation densities. The findings indicate that vegetation reduces the critical velocity needed for sediment movement by 59%. Additionally, the presence of vegetation increases turbulent kinetic energy, with the highest levels observed at the lowest vegetation density, and decreasing as vegetation density increases. This pattern suggests that vegetation not only modifies flow dynamics but also affects the threshold conditions for sediment transport, especially on the outer side of the bend. For example, turbulent kinetic energy is amplified 18 times at a 150-degree angle. In contrast, the bare bed exhibited minimal turbulent kinetic energy, underscoring the significant role of vegetation in altering flow structures. This study highlights the critical importance of emergent vegetation in river management and sediment control, demonstrating a more pronounced effect on the outer bend than the inner side, thus contributing to the sustainability and management of natural streams. © 2024 Indian Society for Hydraulics.

关键词： Kinetic energy

来源：评论

学校读者我要写书评

暂无评论

Marine Life Analysis Based on Ocean Water Level Rise and Climate Change Using Underwater Imaging Techniques

引用

Remote Sensing in Earth Systems sciences 2024年第4期7卷 657-669页

作者： Mate, Anuja Dinesh Arulananth, T.S. Sathiya, T. Jyothi, B. Swarna Raja, A. Wasim Yalawar, Mrutyunjaya S. Computer Technology Sou.Venutai Chavan Polytechnic Pune India Department of Electronics and Communication Engineering MLR Institute of Technology Telangana Hyderabad 500043 India Department of Computer Science and Engineering Sona College of Technology Tamil Nadu Salem India Computer Science & amp Engineering Madanapalle Institute of Technology & amp Science Andhra Pradesh Madanapalle India Artificial Intelligence and Data Science Sri Krishna College of Engineering and Technology Coimbatore India Department of Computer Science and Engineering CMR Engineering College Hyderabad India

Forecasting sea levels is crucial for harbour operations and coastal structure design. The oceans make up two-thirds of Earth’s surface;therefore, historically, the marine economy has been extremely diversified as well as abundant. In order to explore as well as harness this difficult environment, prominent businesses and ecological groups are developing and deploying novel gadgets backed by state-of-the-art marine mechatronics solutions. This research proposes a novel method of marine life monitoring with ocean water level rise analysis based on climate changes by underwater imaging using machine learning techniques. Here, the input has been collected as underwater images as well as processed for noise removal and normalisation. Then, these images were segmented for monitoring marine life using U-Net graph cut fuzzy clustering with a spatial neural network. Then this segmented image has been classified using multilayer region-based Q-belief vector neural networks for the analysis of sea level rise analysis based on climate change training. Experimental analysis has been carried out for various marine life monitoring datasets and climate change datasets in terms of training accuracy, specificity, recall, AUC, and Kappa-coefficient. Proposed techniques achieved specificity 93%, training accuracy 91%, AUC 95%, recall 96%, and Kappa-coefficient 90%. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2024.

关键词： Climate changes Machine learning techniques Marine life monitoring Q-belief vector Water level rise analysis

来源：评论

学校读者我要写书评

暂无评论

A deep Q-learning model for sequential task offloading in edge AI systems

引用

Intelligent and Converged Networks 2024年第3期5卷 207-221页

作者： Dong Liu Shiheng Gu Xinyu Fan Xu Zheng Department of Computer Science and Engineering University of Electronic Science and Technology of ChinaChengdu 610000China Shenzhen Institute for Advanced Study University of Electronic Science and Technology of ChinaShenzhen 515100China Department of Information and Software Engineering University of Electronic Science and Technology of ChinaChengdu 610000China

Currently,edge Artificial Intelligence(AI)systems have significantly facilitated the functionalities of intelligent devices such as smartphones and smart cars,and supported diverse applications and *** fundamental supports come from continuous data analysis and computation over these *** the resource constraints of terminal devices,multi-layer edge artificial intelligence systems improve the overall computing power of the system by scheduling computing tasks to edge and cloud servers for *** efforts tend to ignore the nature of strong pipelined characteristics of processing tasks in edge AI systems,such as the encryption,decryption and consensus algorithm supporting the implementation of Blockchain ***,this paper proposes a new pipelined task scheduling algorithm(referred to as PTS-RDQN),which utilizes the system representation ability of deep reinforcement learning and integrates multiple dimensional information to achieve global task ***,a co-optimization strategy based on Rainbow Deep Q-Learning(RainbowDQN)is proposed to allocate computation tasks for mobile devices,edge and cloud servers,which is able to comprehensively consider the balance of task turnaround time,link quality,and other factors,thus effectively improving system performance and user *** addition,a task scheduling strategy based on PTS-RDQN is proposed,which is capable of realizing dynamic task allocation according to device *** results based on many simulation experiments show that the proposed method can effectively improve the resource utilization,and provide an effective task scheduling strategy for the edge computing system with cloud-edge-end architecture.

关键词： edge computing task scheduling reinforcement learning Rainbow Deep Q-Learning(RainbowDQN)

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：