检索结果-内蒙古大学图书馆

11th IEEE/ACM International Conference on Big Data Computing, Applications and Technologies, BDCAT 2024

作者： Inokuchi, Yuto Gonzalez, Pedro Henrique Aritsugi, Masayoshi Mendonca, Israel Kumamoto University Graduate School of Science and Technology Kumamoto Japan Federal University of Rio de Janeiro System Engineering and Computer Science Program Rio de Janeiro Brazil Kumamoto University Faculty of Advanced Science and Technology Kumamoto Japan

ISBN: (纸本)9798350367300

In this paper, we aim to reduce the number of nodes from Graph Neural Networks (GNNs), thereby simplifying models and reducing computational costs. GNNs are highly effective for various tasks, such as prediction, classification, and clustering, due to their ability to learn node and edge attributes and relationships, and they have been utilized for intelligent transportation systems recently by converting sensor networks into graph structures. Deep spatio-temporal neural networks, including Spatio-Temporal Graph Convolutional Networks (STGCNs), capture spatial and temporal dependencies, making them suitable for traffic speed forecasting, traffic demand prediction, and travel time estimation. Despite their success, GNNs face challenges in industrial applications due to significant memory usage and time consumption. In this paper, we propose a new approach to node reduction that outperforms existing methods in computational efficiency. Our experiments on two real-world traffic datasets demonstrate that using the heuristic and edge information to reduce nodes can cut computation time of optimization up to 95% and, by eliminating noise, can even enhance prediction accuracy. © 2024 IEEE.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Image Quality Assessment Based on Multi-model Ensemble Class-Imbalance Repair Algorithm for Diabetic Retinopathy UW-OCTA Images 25th

Image Quality Assessment Based on Multi-model Ensemble Class...

引用

25th International Conference on Medical Image Computing and computer-Assisted Intervention , MICCAI 2022

作者： Tan, Zhuoyi Madzin, Hizmawati Ding, Zeyu Faculty of Computer Science and Information Technology Universiti Putra Malaysia Serdang43400 Malaysia

ISBN: (纸本)9783031336577

In the diagnosis of diabetic retinopathy (DR), ultrawide optical coherence tomography angiography (UW-OCTA) has received extensive attention because it can non-invasively detect the changes of neovascularization in diabetic retinopathy images. However, in clinical application, UW-OCTA digital images will always suffer a variety of distortions due to a variety of uncontrollable factors, and then affect the diagnostic effect of DR. Therefore, screening images with better imaging quality is very crucial to improve the diagnostic efficiency of DR. In this paper, to promote the development of UW-OCTA DR image quality automatic assessment, we propose a multi-model ensemble class-imbalance repair (MMECIR) algorithm for UW-OCTA DR image quality grading assessment. The models integrated with this algorithm are ConvNeXt, EfficientNet v2, and Xception. The experimental results show that the MMECIR algorithm constructed in this paper can be well applied to UW-OCTA diabetic retinopathy image quality grading assessment (the quadratic weighted kappa of this algorithm is 0.6578). Our code is available at https://***/SupCodeTech/DRAC2022. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Optical tomography

来源：评论

学校读者我要写书评

暂无评论

Semi-supervised Semantic Segmentation Methods for UW-OCTA Diabetic Retinopathy Grade Assessment 25th

Semi-supervised Semantic Segmentation Methods for UW-OCTA D...

引用

25th International Conference on Medical Image Computing and computer-Assisted Intervention , MICCAI 2022

作者： Tan, Zhuoyi Madzin, Hizmawati Ding, Zeyu Faculty of Computer Science and Information Technology Universiti Putra Malaysia Serdang43400 Malaysia

ISBN: (纸本)9783031336577

People with diabetes are more likely to develop diabetic retinopathy (DR) than healthy people. However, DR is the leading cause of blindness. At present, the diagnosis of diabetic retinopathy mainly relies on the experienced clinician to recognize the fine features in color fundus images. This is a time-consuming task. Therefore, in this paper, to promote the development of UW-OCTA DR automatic detection, we propose a novel semi-supervised semantic segmentation method for UW-OCTA DR image grade assessment. This method, first, uses the MAE algorithm to perform semi-supervised pre-training on the UW-OCTA DR grade assessment dataset to mine the supervised information in the UW-OCTA images, thereby alleviating the need for labeled data. Secondly, to more fully mine the lesion features of each region in the UW-OCTA image, this paper constructs a cross-algorithm ensemble DR tissue segmentation algorithm by deploying three algorithms with different visual feature processing strategies. The algorithm contains three sub-algorithms, namely pre-trained MAE, ConvNeXt, and SegFormer. Based on the initials of these three sub-algorithms, the algorithm can be named MCS-DRNet. Finally, we use the MCS-DRNet algorithm as an inspector to check and revise the results of the preliminary evaluation of the DR grade evaluation algorithm. The experimental results show that the mean dice similarity coefficient of MCS-DRNet v1 and v2 are 0.5161 and 0.5544, respectively. The quadratic weighted kappa of the DR grading evaluation is 0.7559. Our code is available at https://***/SupCodeTech/DRAC2022. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

The Combination of the Leiden Algorithm and Graph Coloring for Influencers Detection in Large Scale Social Networks

The Combination of the Leiden Algorithm and Graph Coloring f...

引用

computer sciences, Engineering, and technology Innovation (ICoCSETI), International Conference on

作者： Handrizal Poltak Sihombing Erna Budhiarti Nababan Mohammad Andri Budiman Doctoral Program in Computer Science Faculty of Computer Science and Information Technology Universitas Sumatera Utara Medan Indonesia Department of Computer Science Faculty of Computer Science and Information Technology Universitas Sumatera Utara Medan Indonesia Department of Information Technology Faculty of Computer Science and Information Technology Universitas Sumatera Utara Medan Indonesia

ISBN: (数字)9798331508616

ISBN: (纸本)9798331508623

The role of influencers, especially on social media platforms, has grown significantly. A commonly used feature among business professionals today is follower grouping. However, this feature is limited to identifying influencers based solely on mutual followership, underscoring the need for a more sophisticated approach to influencer *** study proposes a new method for influencer detection that integrates the Leiden Coloring Algorithm and Matrix Centrality. This approach leverages network analysis to identify patterns and relationships in large-scale datasets. First, the Leiden Coloring Algorithm partitions the network into various communities, which are considered potential influencer groups. Furthermore, Eigenvector and Degree Centrality augment this process by identifying nodes with high connectivity, representing potential *** proposed method is validated using crawled data from the Twitter (X) social media platform with the keyword "GarudaIndonesia." The results of the Leiden Coloring Algorithm recommend 10 accounts as influencers. Based on Eigenvector Centrality and Degree Centrality for a dataset of 1,000 rows, it is observed that the first and second ranks consistently identify the same influencers, namely IndonesiaGaruda and GarudaCares. However, the third to tenth ranks suggest different influencers. For a dataset of 5,000 rows, both methods again identify IndonesiaGaruda as the top-ranked influencer, while the second to tenth ranks differ between the two *** modularity value for the first test scenario is 0.9396, while for the second test scenario, it is 0.9381. The processing time for the first test scenario is 29.5493 seconds, compared to 434.1838 seconds for the second test scenario. Additionally, the number of communities identified by the Leiden Coloring Algorithm increases with dataset size, with 505 communities for the first test scenario and 1,969 communities for the second. This demonstrates that larger datasets res

关键词： Technological innovation Social networking (online) Blogs Network analyzers Feature extraction Partitioning algorithms Business

来源：评论

学校读者我要写书评

暂无评论

A Comparative Analysis of Louvain and Leiden Coloring Algorithms in Influencer Detection

A Comparative Analysis of Louvain and Leiden Coloring Algori...

引用

computer sciences, Engineering, and technology Innovation (ICoCSETI), International Conference on

ISBN: (数字)9798331508616

ISBN: (纸本)9798331508623

In today's digital era, the influence of social media influencers has grown significantly. A commonly used feature by business professionals today is follower grouping. However, this feature is limited to identifying influencers based solely on mutual followership, highlighting the need for a more sophisticated approach to influencer detection. This study proposes a novel method for influencer detection that integrates the Leiden coloring algorithm and Degree centrality. This approach leverages network analysis to identify patterns and relationships within large-scale datasets. First, the Leiden coloring algorithm is employed to partition the network into distinct communities, identifying potential influencer clusters. Subsequently, Degree centrality is utilized to identify nodes within these communities exhibiting high connectivity, indicating individuals with significant influence. The proposed method was validated using data crawled from Twitter (X) social media, employing the keyword "GarudaIndonesia." The data was collected using Tweet-Harvest between January 1, 2020, and October 16, 2024, resulting in a dataset of 22,623 rows. The proposed method was compared to the Louvain coloring method, demonstrating an increase in the modularity value of the Leiden coloring algorithm by 0.0195, a reduction in processing time by 13.93 seconds, and a decrease in the number of communities by 649.

关键词： Technological innovation Social networking (online) Blogs Clustering algorithms Network analyzers Feature extraction Partitioning algorithms Business

来源：评论

学校读者我要写书评

暂无评论

Maintaining Image Size by Developing the Cropping Rectangle Method on CT-Scan Images 12

Maintaining Image Size by Developing the Cropping Rectangle ...

引用

12th IEEE International Conference on Communication, Networks and Satellite, COMNETSAT 2023

作者： Guslendra Yuhandri Defit, Sarjon Universitas Putra Indonesia Yptk Computer Science Faculty Department of Information System Padang Indonesia Universitas Putra Indonesia Yptk Computer Science Faculty Department of Information Technology Padang Indonesia

ISBN: (纸本)9798350341102

CT-Scan is a computer-based imaging technology, but it presents certain weaknesses, including interpretation challenges, lengthy analysis times, and visualization limitations. The progress in digital image processing science empowers computers to identify objects through recognizing distinctive features. To facilitate further data processing, an image cropping method is essential to narrow down the area of interest, as not all parts of an object require processing. However, using a rectangular cropping method can lead to a reduction in image size, potentially compromising image quality and causing blurring when displayed on the same axes. To uphold image quality and avert blurring, maintaining the cropped image's size becomes crucial. The developed rectangular cropping method successfully preserves the cropped image's size by adjusting the intensity values of pixels surrounding the cutting point. Coordinate points within the cropping rectangle delineate the region where pixel intensity values are modified. In this study, input images were sourced from CT-scan images of M. Djamil Hospital, Padang, West Sumatra, in jpg format. The developed algorithm underwent testing using the Matlab program, employing the rectangle method for image cropping to ensure the image size remained constant. The study's outcomes reveal no disparity in the number of pixels obtained when employing the developed rectangular cropping method. Based on the experiments carried out in this study using 8 input images that were successfully maintained, the size of the image from the cropped image was 8 images and 0 images were unsuccessful, so the accuracy obtained in this study was 100%. © 2023 IEEE.

关键词： Image quality

来源：评论

学校读者我要写书评

暂无评论

Development of Control programming and Data Analytics on The Controlled Automatic Sorting Simulation System 7

Development of Control Programming and Data Analytics on The...

引用

7th International Conference on information technology, InCIT 2023

作者： Bundasak, Supaporn Chomchan, Iya Kasetsart University Sriracha Campus Faculty of Science at Sriracha Computer Science and Information Technology Department Chonburi Thailand

ISBN: (纸本)9798350358698

The faculty of science, Sriracha Campus is in the Eastern Economic Corridor (EEC) to recognize the importance of the development of Industry4.0, Therefore it has been developed a control and data analysis program based on a controlled automatic sorting simulation system to disseminate the technology of PLC and data analysis to develop into a smart factory. By developing personnel to have knowledge and developing the capabilities of machines for Industry4.0. Automated machines for smart factories, such as production systems, can be adjusted according to the situation by responding in real time. Moreover, by creating intelligent machines, trackers and forecasters can analyze production data by receiving information from machines to prevent errors from occurring. Being able to develop a machine status monitoring program can help extend the working life of machines. Therefore, developing a training set to program and study data analysis in factory machinery. It is important to develop technological knowledge and understanding in developing smart factory systems such as automatic control. Machine maintenance through data analysis from various sensors using production data to analyze production rates or detecting work controls through sensors that have complex functions from various research developments through studies on this simulation set in the future. © 2023 IEEE.

关键词： Data Analytics

来源：评论

学校读者我要写书评

暂无评论

Bamboo Forest Growth Optimization Algorithm for Night Image Enhancement 15th

Bamboo Forest Growth Optimization Algorithm for Night Image...

引用

15th International Conference on Genetic and Evolutionary Computing, ICGEC 2023

作者： Shi, Hao-Jie Pan, Jeng-Shyang Chu, Shu-Chuan Kong, Lingping Snášel, Václav College of Computer Science and Engineering Shandong University of Science and Technology Qingdao266590 China Innovative Information Industry Research Center Harbin Institute of Technology Shenzhen Graduate School Shenzhen China Faculty of Electrical Engineering and Computer Science VSB-Technical University of Ostrava Ostrava Czech Republic Department of Information Management Chaoyang University of Technology Taichung41349 Taiwan

ISBN: (纸本)9789819700677

The Bamboo Forest Growth Optimization(BFGO) algorithm is an algorithm proposed by the growth law of bamboo forest, which has the advantages of fast convergence and not easily falling into local optimum. In this paper we have experimented the BFGO with several other population intelligence optimization algorithms on 23 benchmark test functions and proved its superiority. Also we apply the bamboo forest optimization algorithm to nighttime image enhancement in this paper, and the algorithm achieves better results on this application. © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Generating A New Shilling Attack for Recommendation Systems

引用

computers, Materials & Continua 2022年第5期71卷 2827-2846页

作者： Pradeep Kumar Singh Pijush Kanti Dutta Pramanik Madhumita Sardar Anand Nayyar Mehedi Masud Prasenjit Choudhury Department of Computer Science&Engineering National Institute of TechnologyDurgapurIndia Graduate School Duy Tan UniversityDa NangVietnam Faculty of Information Technology Duy Tan UniversityDa NangVietnam Department of Computer Science College of Computers and Information TechnologyTaif UniversityTaif21944Saudi Arabia

A collaborative filtering-based recommendation system has been an integral part of e-commerce and *** keep the recommendation systems reliable,authentic,and superior,the security of these systems is very *** the existing shilling attack detection methods in collaborative filtering are able to detect the standard attacks,in this paper,we prove that they fail to detect a new or unknown *** develop a new attack model,named Obscure attack,with unknown features and observed that it has been successful in biasing the overall top-N list of the target users as *** Obscure attack is able to push target items to the top-N list as well as remove the actual rated items from the *** proposed attack is more effective at a smaller number of k in top-k similar user as compared to other existing *** effectivity of the proposed attack model is tested on the MovieLens dataset,where various classifiers like SVM,J48,random forest,and naïve Bayes are utilized.

关键词： Shilling attack recommendation system collaborative filtering top-N recommendation biasing shuffling hit ratio

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Driven Anomaly Detection for IoMT-Based Smart Healthcare Systems

引用

computer Modeling in Engineering & sciences 2024年第12期141卷 2121-2141页

作者： Attiya Khan Muhammad Rizwan Ovidiu Bagdasar Abdulatif Alabdulatif Sulaiman Alamro Abdullah Alnajim Department of Computer Science Kinnaird College for WomenLahore54000Pakistan School of Computing University of DerbyDerbyDE221GBUK Department of Mathematics Faculty of Exact Sciences“1 Decembrie 1918”University of Alba IuliaAlba Iulia510009Romania Department of Computer Science College of ComputerQassim UniversityBuraydah52571Saudi Arabia Department of Information Technology College of ComputerQassim UniversityBuraydah52571Saudi Arabia

The Internet of Medical Things(IoMT)is an emerging technology that combines the Internet of Things(IoT)into the healthcare sector,which brings remarkable benefits to facilitate remote patient monitoring and reduce treatment *** IoMT devices become more scalable,Smart Healthcare Systems(SHS)have become increasingly vulnerable to *** Detection Systems(IDS)play a crucial role in maintaining network *** IDS monitors systems or networks for suspicious activities or potential threats,safeguarding internal *** paper presents the development of an IDS based on deep learning techniques utilizing benchmark *** propose a multilayer perceptron-based framework for intrusion detection within the smart healthcare *** primary objective of our work is to protect smart healthcare devices and networks from malicious attacks and security *** employ the NSL-KDD and UNSW-NB15 intrusion detection datasets to evaluate our proposed security *** proposed framework achieved an accuracy of 95.0674%,surpassing that of comparable deep learning models in smart healthcare while also reducing the false positive *** results indicate the feasibility of using a multilayer perceptron,achieving superior performance against cybersecurity threats in the smart healthcare domain.

关键词： Anomaly detection deep learning Internet of Things(IoT) health care

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：