检索结果-内蒙古大学图书馆

4th International Conference on Advances in Computing, Communication Control and Networking, ICAC3N 2022

作者： Kumar, Satish Srivastava, Archana Chaurasiya, Pawan Kumar Kushawaha, Arun Vishal, Vishal Babasaheb Bhimrao Ambedkar University Deptt. of Information Technology Lucknow India Babu Banarasi das University Deptt. of Computer Application Lucknow India

ISBN: (纸本)9781665474368

This paper technique provides security of medical image, imperceptibility, and robustness watermarking technique. The watermarking technique used in this paper applies a discrete cosine transform (DCT) and singular value decomposition (SVD) are applied to the two images as one cover medical image and original watermark image before the embedding process. DCT is applied to a cover medical image and original watermark image into four sub-bands (LL1, LH1, HL1, HH1), and apply Coefficients of the LL1 sub-band for embedding and extracting watermarking. Two images are tested for imperceptibility and robustness within experimental results, with better peak signal-to-noise ratio (PSNR) and high normalized correlation coefficient (NCC) metrics. PSNR of 45.76dB and NCC values of 0.9994 without any attacks, and using factors (α) values on 0.001 verifies the proposed method's the imperceptibility and robustness, also a comparison graph. © 2022 IEEE.

关键词： Singular value decomposition

来源：评论

学校读者我要写书评

暂无评论

Fine-grained distributed averaging for large-scale radio interferometric measurement sets

引用

Research in Astronomy and Astrophysics 2021年第4期21卷 93-100页

作者： Shou-Lin Wei Kai-Da Luo Feng Wang Hui Deng Ying Mei Faculty of Information Engineering and Automation Computer Technology Application Key Lab of Yunnan ProvinceKunming University of Science and TechnologyKunming 650500China Center for Astrophysics Guangzhou UniversityGuangzhou 510006China

The Square Kilometre Array(SKA)would be the world’s largest radio telescope with eventually over a square kilometre of collecting ***,there are enormous challenges in its data *** use of modern distributed computing techniques to solve the problem of massive data processing in the SKA is one of the most important *** this study,basing on the Dask distribution computational framework,and taking the visibility function integral processing as an example,we adopt a multi-level parallelism method to implement distributed averaging over time and *** Array was used to implement super large matrix or arrays with supported *** maximize the usage of memory,we further exploit the data parallelism provided by Dask that intelligently distributes the computational load across a network of computer agents and has a built-in fault tolerance *** validity of the proposed pattern was also verified by using the Common Astronomy Software application(CASA),wherein we analyze the smearing effects on images reconstructed from different resolution visibilities.

关键词： techniques:interferometric methods:data analysis methods:numerical instrumentation:interferometers

来源：评论

学校读者我要写书评

暂无评论

Big Data and the Internet of Things as Enablers for Business Digital Transformation Efforts 4

Big Data and the Internet of Things as Enablers for Business...

引用

4th International Conference on Innovative Practices in technology and Management, ICIPTM 2024

作者： Gomathi, B. Jannepally, Abbinaya Reddy Ghansela, Siddharth Sujatha, R. Kashyap, Amit Kumar Vidhya Shri Shankarlal Sundarbai Shasun Jain College for Women Department of Computer Science Chennai India Solutions Architect India Gb Pant Institute of Engineering and Technology Department of Computer Science and Application Uttarakhand India Psg College of Arts & Science Department of Information Technology Coimbatore India Nirma University Institute of Law Ahmedabad India Shri Shankarlal Sundarbai Shasun Jain College for Women Department of Computer Applications Chennai India

ISBN: (纸本)9798350307757

This comprehensive study delves into the transformative roles of Big Data and the Internet of Things (IoT) in facilitating digital transformation in businesses. It explores how the synergy between these technologies drives operational efficiency, enhances customer engagement, and fosters innovation. The research employs a mixed-method approach, including literature reviews, case studies, and empirical data analysis, to assess the impact of Big Data and IoT on business strategies and performance. The findings indicate that while Big Data and IoT significantly contribute to digital transformation, challenges like data security and infrastructure requirements need addressing. This study provides valuable insights for businesses aiming to leverage these technologies for competitive advantage. © 2024 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

FEMD: Feature Enhancement-aided Multimodal Feature Fusion Approach for Smart Contract Vulnerability Detection 30

FEMD: Feature Enhancement-aided Multimodal Feature Fusion Ap...

引用

30th IEEE International Conference on Parallel and Distributed Systems, ICPADS 2024

作者： Li, Juan Li, Rui Lu, Youshui Cai, Bowen Cao, Yulin Lin, Hang Li, Xingxing Li, Chan Qinghai Normal University School of Computer Science Xining China Xidian University The State Key Laboratory of Tibetan Intelligent Information Processing and Application School of Computer Science Qinghai Normal University School of Computer Science and Technology Xian China School of the Instrument Science and Technology School of Electrical Engineering Xi'an Jiaotong University Xian China School of Science and Engineering University of Minnesota - Twin City Minneapolis United States

ISBN: (纸本)9798331515966

Smart contracts, due to their immutability and transparency upon deployment, entail significant economic and systemic risks from any vulnerabilities present. Traditional vulnerability detection methods suffer from low automation and high false positive rates, while existing deep learning-based approaches inadequately extract contract features, thereby limiting detection accuracy. To address these issues, this paper proposes FEMD: a feature-enhanced aided multimodal feature fusion method for smart contract vulnerability detection. Building on the foundation of addressing the low automation of traditional detection tools, our method improves the model's feature extraction performance and detection capabilities. Specifically, we construct a contract graph through Comprehensive Expert-Graph Fusion, combining multi-modal feature fusion using a multi-head attention mechanism with expert patterns to ensure the capture and effective preservation of all critical information during the fusion process. To delve deeper into potential information within smart contract graphs, we employ a Feature Enhancer that leverages transpose operations on feature matrices to extract complex interaction patterns across different dimensions. Our approach is validated through batches of experiments on the Ethereum open dataset focusing on reentrancy and timestamp dependency vulnerabilities, demonstrating significant improvements in detection accuracy and robustness. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

A Method for Assigning Weight to the Assessment Indicators of Computational Thinking with XGBoost 5

A Method for Assigning Weight to the Assessment Indicators o...

引用

5th International Workshop on Artificial Intelligence and Education, WAIE 2023

作者： Zeng, Xinyao Zhang, Wei Chen, Yi Chen, Hao Central China Normal University Faculty of Artificial Intelligence in Education Wuhan China School of Computer Science Central China Normal University Wuhan China School of Information Technology Application Innovation Wuhan Polytechnic Wuhan China

ISBN: (纸本)9798350307061

Computational thinking (CT) assessment indicator assignment is an important strategy for optimizing assessment and an effective method for exploring differences in the importance of assessment indicators. However, the objectivity of the previous methods for assigning assessment indicators of CT is insufficient. Therefore, the paper proposed to use the XGBoost machine learning model to fit the assessment data, fully explore the data features and realize the weighting of CT assessment indicators. The CT assessment indicators are used as the features of XGBoost model training and the assessment levels are used as the training labels to obtain the feature weights through XGBoost model training. The feature weights are used as the CT assessment indicator weights to realize the weighting of assessment indicators of CT in reverse. From the analysis of the CT assessment indicator assignment results, the analysis of the importance of the assessment indicators and the comparative analysis of the assessment results before and after the indicator assignment, it is found that the CT assessment after the indicator assignment has higher robustness and credibility. © 2023 IEEE.

关键词： Assessment indicators Computational thinking Indicator weight XGBoost

来源：评论

学校读者我要写书评

暂无评论

Exploiting Convolutional Neural Networks for Automated Pathology Image Classification

Exploiting Convolutional Neural Networks for Automated Patho...

引用

Optimization Computing and Wireless Communication (ICOCWC), International Conference on

作者： Sunil Sharma C Menaka Akhilendra Pratap Singh Department of Computer Science & Application Vivekananda Global University Jaipur India Department of Computer Science and Information Technology Jain (Deemed to be University) Bangalore India Maharishi School of Engineering & Technology Maharishi University of Information Technology Uttar Pradesh India

Convolutional neural networks (CNNs) are a deep mastering method for the computerized pathology photograph category. With the improvement of superior imaging techniques, the quantity of virtual and representable pathology pix has increased notably. Automatic picture evaluation has become increasingly crucial to exploit those photographs for clinical selections. CNNs have attracted huge interest and were established to be very powerful for automated photograph classification and object detection. The improvement of deep getting-to-know based on Convolutional Neural Networks (CNNs) for computerized pathology photo classes has been a focal point of research in current years. This paper critiques the recent advances in CNNs in automatic pathology image type. The key architectures and algorithms for CNNs are summarized, and their capability applicability in pathology picture classification is discussed. This overview also introduces the maximum hit CNN methods that have been proposed and have proven promising consequences in pathology photograph category duties. The paper concludes with a dialogue of future research directions in this area. Convolutional neural networks (CNNs) are a deep mastering method for the computerized pathology photograph category. With the improvement of superior imaging techniques, the quantity of virtual and representable pathology pix has increased notably. To exploit those photographs for clinical selections, automatic picture evaluation has grown to be an increasingly number of crucial. CNNs have attracted huge interest and were established to be very powerful for automated photograph classification and object detection. The improvement of deep getting-to-know based on Convolutional Neural Networks (CNNs) for computerized pathology photo classes has been a focal point of research in current years. This paper critiques the recent advances in CNNs in automatic pathology image type. The key architectures and algorithms for CNNs are summarized,

关键词：

来源：评论

学校读者我要写书评

暂无评论

Node Localization Performance Evaluation and Tracking using Kalman Filter in Wireless Sensor Networks

Node Localization Performance Evaluation and Tracking using ...

引用

Integrated Intelligence and Communication Systems (ICIICS), International Conference on

作者： Nimmala Gangothri Gadagi Omkar Radharapu Vishal Saroja Kumar Rout Kottu Santosh Kumar Babu Reddy Mukkamalla Department of Information Technology Vardhaman College of Engineering (Autonomous) Hyderabad India Department of Computer Application Krishna University Machilipatnam India

ISBN: (数字)9798331504960

ISBN: (纸本)9798331504977

Wireless Sensor Networks (WSNs) are crucial in smart environments where precise node location is necessary for efficient data processing and communication. Present-day localization methods frequently provide an average accuracy of about 11.3%, which degrades network performance as a whole. The proposed research work presents a hybrid method to increase localization accuracy by merging the Kalman Filter (KF) with Random Fourier Feature (RFF) and Support Vector Machine (SVM). By using the RFF for feature mapping and the KF for effective tracking, this technique greatly lowers localization errors. The Mean Absolute Error(MAE) reduced from 7.74 to 3.87 for the first trajectory, 8.41 to 4.31 for the second, and 9.47 to 8.31 for the third trajectory. By improving WSN's accuracy and dependability, the suggested method increases their usefulness in intelligent applications.

关键词： Location awareness Support vector machines Wireless sensor networks Accuracy Filtering Vectors Trajectory Kalman filters Reliability State estimation

来源：评论

学校读者我要写书评

暂无评论

Semi-Supervised Gland Segmentation via Feature-Enhanced Contrastive Learning and Dual-Consistency Strategy

引用

IEEE Journal of Biomedical and Health Informatics 2025年第6期29卷 4314-4324页

作者： Yu, Jiejiang Li, Bingbing Pan, Xipeng Shi, Zhenwei Wang, Huadeng Lan, Rushi Luo, Xiaonan Guilin University of Electronic Technology School of Computer Science and Information Security Guilin541004 China Ganzhou Municipal Hospital Department of Pathology Ganzhou341000 China Southern Medical University Department of Radiology Guangdong Provincial People's Hospital Guangdong Academy of Medical Sciences Guangzhou510080 China Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application Guangzhou510080 China

In the field of gland segmentation in histopathology, deep-learning methods have made significant progress. However, most existing methods not only require a large amount of high-quality annotated data but also tend to confuse the internal of the gland with the background. To address this challenge, we propose a new semi-supervised method named DCCL-Seg for gland segmentation, which follows the teacher-student framework. Our approach can be divided into follows steps. First, we design a contrastive learning module to improve the ability of the student model's feature extractor to distinguish between gland and background features. Then, we introduce a Signed Distance Field (SDF) prediction task and employ dual-consistency strategy (across tasks and models) to better reinforce the learning of gland internal. Next, we proposed a pseudo label filtering and reweighting mechanism, which filters and reweights the pseudo labels generated by the teacher model based on confidence. However, even after reweighting, the pseudo labels may still be influenced by unreliable pixels. Finally, we further designed an assistant predictor to learn the reweighted pseudo labels, which do not interfere with the student model's predictor and ensure the reliability of the student model's predictions. Experimental results on the publicly available GlaS and CRAG datasets demonstrate that our method outperforms other semi-supervised medical image segmentation methods. © 2013 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Prediction of Reliability of Data in Underwater Communication Network Using Fuzzy Logic

Prediction of Reliability of Data in Underwater Communicatio...

引用

Optimization Computing and Wireless Communication (ICOCWC), International Conference on

作者： Surendra Yadav Gobi N Rakesh Kumar Yadav Department of Computer Science & Application Vivekananda Global University Jaipur India Department of Computer Science and Information Technology Jain (Deemed to be University) Bangalore India Maharishi School of Engineering & Technology Maharishi University of Information Technology Uttar Pradesh India

This paper uses fuzzy logic to propose a reliability prediction set of rules for the underwater communication community. The set of rules uses fixed fuzzy rules to expect communication reliability among nodes in an underwater environment. Those fuzzy rules are derived from a reliability model based on the characteristics of an ordinary underwater conversation system, such as physical and environmental elements. The algorithm is then examined using accurate statistics from an underwater communication test. The effects imply that this approach is promising in predicting the reliability of the community. It has also been discovered that reliability prediction accuracy can be advanced if the bushy guidelines include extra factors, the sign channel's records rate, and the machine's performance parameters. This study offers a practical approach to improving the performance and reliability of underwater communique networks.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Presentation Analysis of Reasoning Radio-Based Routing Protocols in Wireless Mesh Networks

Presentation Analysis of Reasoning Radio-Based Routing Proto...

引用

Optimization Computing and Wireless Communication (ICOCWC), International Conference on

作者： Ritesh Kumar Vikas Kumar Kharbas Deepak Mehta Maharishi School of Engineering & Technology Maharishi University of Information Technology Uttar Pradesh India Department of Computer Science & Application Vivekananda Global University Jaipur India Department of Computer Science and Information Technology Jain (Deemed to be University) Bangalore India

Reasoning radio-based total routing protocols present a promising technique for permitting powerful conversation in wi-fi mesh networks. By using the spectrum sensing capabilities of Reasoning radio, routers can intelligently pick out and pick out spectrum assets to ahead records, thereby allowing for improved network throughput and reliability. In this paper, we carry out a comprehensive Presentation evaluation of routing protocols primarily based on Reasoning radio in wi-fi mesh networks. Mainly, we Presentation metrics including packet shipping fee, latency, jitter, and energy Presentation. We examine various routing protocols from an empirical and theoretical angle and speak about the strengths and weaknesses of every technique. Subsequently, our consequences provide insights into the capability advantages and tradeoffs of Reasoning radio-based routing protocols in wireless mesh networks, offering practical steerage to designers and engineers within the subject.

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：