检索结果-内蒙古大学图书馆

3rd IEEE International Conference on Robotics, Automation, Artificial-Intelligence and Internet-of-Things, RAAICON 2024

作者： Hossain Sarkar, Md. Mosharrof Afrin, Sadiha Reza, Md Tuhin Bokshi, Md Abid Hasan Roni Mim, Sharmin Sultana Faridpur Engineering College Department of Computer Science and Engineering Faridpur Bangladesh Faridpur Engineering College Department of Electrical and Electronic Engineering Faridpur Bangladesh

ISBN: (纸本)9798331534400

Lung cancer requires accurate risk assessment and early detection due to its high prevalence and fatality rate. The simultaneous analysis of clinical symptoms and etiological factors using Machine Learning revolutionizes our understanding of lung cancer and patient outcomes. Machine Learning models are built on comprehensive patient data, including lifestyle, symptoms, and 12 variables. We used ten models for precise lung cancer diagnosis, including Decision Tree (DT), K-nearest neighbors (KNN), Support Vector Machine (SVM), Random Forest (RF), Logistic Regression (LR), Naive Bayes (NB), XGBoost, Gradient Boost, CatBoost and AdaBoost. At the National Institute of Cancer Research & Hospital (NICRH) in Mohakhali, TB Gate Road, Dhaka, Bangladesh, we collected 346 data directly from patients using questionnaires, with permission from the director. For every model, we performed parameter tuning to determine the ideal ratio of complexity to accuracy. Notably, with the best accuracy of 98.43% and an excellent area under the curve (AUC) of 0.983, the Decision Tree (DT) performed better than any other classifier. The motivation behind this research is to predict the risk assignment of lung cancer using various machine learning models. © 2024 IEEE.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

DGeC: Dynamically and Globally Enhanced Convolution

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2025年第4期6卷 921-933页

作者： Zhang, Zihang Liu, Yuling Zhou, Zhili Yang, Gaobo Liao, Xin Wu, Q. M. Jonathan Hunan University College of Computer Science and Electronic Engineering Changsha410082 China Guangzhou University Institute of Artificial Intelligence and Blockchain Guangzhou510006 China University of Windsor Department of Electrical and Computer Engineering WindsorON250101 Canada

We explore the reasons for the poorer feature extraction ability of vanilla convolution and discover that there mainly exist three key factors that restrict its representation capability, i.e., regular sampling, static aggregation, and limited receptive field. With the cost of extra parameters and computations, existing approaches merely alleviate part of the limitations. It drives us to seek a more lightweight operator to further improve the extracted image features. Through a closer examination of the convolution process, we discover that it is composed of two distinct interactions: spatial-wise interaction and channel-wise interaction. Based on this discovery, we decouple the convolutional blocks into these two interactions which not only reduces the parameters and computations but also enables a richer ensemble of interactions. Then, we propose the dynamically and globally enhanced convolution (DGeC), which includes several components as follows: a dynamic area perceptor block (DAP) that dynamically samples spatial cues, an adaptive global context block (AGC) that introduces the location-aware global image information, and a channel attention perceptor block (CAP) that merges different channel-wise features. The experiments on ImageNet for image classification and on COCO-2017 for object detection validate the effectiveness of DGeC. As a result, our proposed method consistently improves the performance with fewer parameters and computations. In particular, DGeC achieves a 3.1% improvement in top-1 accuracy on ImageNet dataset compared to ResNet50. Moreover, with Faster RCNN and RetinaNet, our DGeC-ResNet50 also consistently outperforms ResNet and ResNeXt. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

THE EFFICIENCY AND SECURITY OF MULTI-UNMANNED AERIAL VEHICLE COMMUNICATION NETWORKS: FEDERATED LEARNING BASED ON LIGHTWEIGHT BLOCKCHAIN

引用

International Journal of Electrical engineering 2024年第1期31卷 23-31页

作者： Chung, Hao-Tse Wang, Li-Chun Cheng, Shao-Hung Institute of Electrical and Computer Engineering National Yang Ming Chiao Tung University Taiwan Department of Electrical and Electronic Engineering Chung Cheng Institute of Technology NDU Taiwan

This study develops an innovative federated learning framework specifically designed for multi-unmanned aerial vehicles (UAVs), utilizing blockchain technology to achieve lightweight, secure, and efficient data processing. In this architecture, UAVs directly participate in federated learning without the need for a central server. Instead, a series of base stations execute blockchain nodes to process gradient information and maintain the system. We eliminate single points of failure by transferring gradient aggregation from the central server to blockchain nodes, thereby enhancing the system’s stability and reliability. Furthermore, the use of a private Inter Planetary File System (IPFS) reduces storage and communication costs. A Byzantine Fault Tolerance (BFT) consensus mechanism is adopted to improve system efficiency and security. Experiments confirm that our proposed architecture effectively prevents model poisoning attacks, even in scenarios where malicious blockchain nodes are in the majority, thus ensuring learning performance. Finally, a node reputation selection mechanism based on the Multi-Krum algorithm is introduced to increase the likelihood of nodes submitting high-quality gradients, thereby enhancing overall system efficiency. © 2024, Chinese Institute of Electrical engineering. All rights reserved.

关键词： Aircraft communication

来源：评论

学校读者我要写书评

暂无评论

Real-time Resource Management Mechanism for Mobile IoT Devices in 5G-enabled Edge Computing 13

Real-time Resource Management Mechanism for Mobile IoT Devic...

引用

13th International Conference on computer Technologies and Development, TechDev 2024

作者： Alqahtani, Abdullah M. Jazan University Collage of Engineering and Computer Science Department of Electrical and Electronic Engineering Saudi Arabia

ISBN: (纸本)9798331539771

The time-sensitive Internet of Things (IoT) applications within 5G and edge computing environments presents unique challenges in network resource management. Current systems struggle with efficiently managing the high-density and variable conditions typical in such mobile networks. This study aims to address these challenges by introducing the Federated Learning-Enhanced Resource Management System for Mobile IoT networks (FLERMS-IoT). The proposed FLERMS-IoT system incorporates a novel federated learning framework that incorporates localized data processing at the edge to reduce latency and bandwidth usage. It includes algorithms that adaptively manage computational and network resources. The core of the system is a dual-module approach that dynamically adjusts to network conditions, enhancing both stability and scalability. Empirical evaluations demonstrate significant enhancements in resource utilization efficiency, with FLERMS-IoT achieving 90% in high-density scenarios and 85% in variable network conditions in comparison with 5GTFF, JCSR, and SKUNK. © 2024 IEEE.

关键词： Mobile edge computing

来源：评论

学校读者我要写书评

暂无评论

Advances, Application and Challenges of Lithography Techniques 5

Advances, Application and Challenges of Lithography Techniqu...

引用

5th International Conference on Advancements in Computational Sciences, ICACS 2024

作者： Raza, Ali Saeed, Zubair Aslam, Adnan Nizami, Syeda Mehwish Habib, Kanwal Malik, Ahmad Nazir National University of Technology Department of Computer Engineering Islamabad Pakistan University of Engineering and Technology Department of Computer Engineering Taxila Pakistan University of Engineering and Technology Department of Electronic Engineering Taxila Pakistan University of Engineering and Technology Department of Electrical Engineering Taxila Pakistan Hitec University Department of Computer Engineering Taxila Pakistan

ISBN: (纸本)9798350394764

Miniaturization of the transistor has resulted in novel patterning techniques to come into account. To alleviate the resolution limits of photolithography, various promising techniques have been developed with high resolution, throughput, overlay accuracy, low line edge roughness, and low defectivity. This paper reviews major nanolithography techniques including conventional photolithography, Extreme ultraviolet lithography, Nanoimprint lithography, and additional techniques. All these lithographic methods are key technologies to manufacture ICs, microchips, and MEMS (micro-electromechanical system) devices. This paper also presents various challenges, status, and applications of NGL (next-generation lithography). In the end, a comparative analysis of these techniques is also discussed. © 2024 IEEE.

关键词： MEMS

来源：评论

学校读者我要写书评

暂无评论

Analytical Modeling and Performance Evaluation of Beam-Based Random Access Protocol for 5G Beamforming Networks

引用

IEEE Internet of Things Journal 2023年第24期10卷 22246-22255页

作者： Lin, Ting-An Cheng, Ray-Guang National Taiwan University of Science and Technology Department of Electronic and Computer Engineering Taipei106335 Taiwan

Access parameters, user equipment (UE) density, system load, and channel conditions significantly impact the performance of random-access (RA) protocols, influencing network capacity, latency, and robustness. In 3GPP standard, the prach-ConfigurationIndex access parameter is used to designate reserved RA channel occasions (ROs) for each beam, enabling UEs to derive beam mapping patterns and select desired beams through a beam-based RA protocol. This article addresses the challenge of bursty arrivals from massive Internet of Things (IoT) devices with sporadic traffic patterns in 5G beamforming networks. We propose an analytical model to evaluate the performance of the beam-based RA protocol for any beam mapping pattern. Extensive computer simulations are conducted to validate the accuracy and effectiveness of our model across various scenarios. The results demonstrate that our model provides valuable insights into the behavior and performance of the beam-based RA protocol and offers a reliable tool to evaluate and optimize beam mapping patterns in practical 5G network deployments. © 2014 IEEE.

关键词： Analytical models

来源：评论

学校读者我要写书评

暂无评论

Handwritten Signature Recognition Using Siamese Neural Network

Handwritten Signature Recognition Using Siamese Neural Netwo...

引用

2024 International Conference on computer engineering, Network and Intelligent Multimedia, CENIM 2024

作者： Setiowati, Yuliana Fariza, Arna Luthfi Ramadhan, Muhamad Rifqi Politeknik Elektronika Negeri Surabaya Informatics and Computer Engineering Department Surabaya Indonesia

ISBN: (纸本)9798350368802

This research proposes a novel approach to addressing the issue of signature authenticity identification by implementing Deep Metric Learning (DML). The aim of this study is to develop a DML model with high accuracy in training and testing processes that can be integrated with a mobile application for signature authenticity verification. The data used in this research are signature images from 90 individuals, divided into two categories: genuine signatures and forged signatures. Testing results show that the developed model has an accuracy of 85.7%, with high precision for the forged signature class at 95.9% and recall for the genuine signature class at 94.9%. The conclusion of this research is that the developed DML model is reliable for signature verification, although further development is needed to improve the model's performance, especially in detecting forged signatures. Suggestions for future research include increasing the amount and variety of training data, integrating the model with a mobile application, and testing the model under various conditions and on different devices. © 2024 IEEE.

关键词： Authentication Protocol

来源：评论

学校读者我要写书评

暂无评论

Satu Sehat Interoperability Agent

Satu Sehat Interoperability Agent

引用

2024 International Conference on Information Technology Systems and Innovation, ICITSI 2024

作者： Martono, Hero Yudo Yunanto, Andhik Ampuh Santoso, Dian Septiani Politeknik Elektronika Negeri Surabaya Department of Informatics and Computer Engineering Surabaya Indonesia

ISBN: (纸本)9798331511470

Data integration from all health care facilities in Indonesia to the Satu Sehat platform is an obligation that must be carried out, but it turns out that until early October 2024, around 57% of health care facilities have not succeeded in carrying out this integration. With this condition, it can be concluded that there are difficulties for health care facilities to carry out integration and this is estimated to be due to differences in data formats between health care facilities and Satu Sehat. For this reason, an interoperability agent is needed to bridge health care facilities with Satu Sehat. We built the first version of the interoperability agent that bridges this integration. This agent works by entering the client database, searching for the appropriate data in each health care facility, creating a data format that matches the Satu Sehat format, and then sending the format to Satu Sehat. This agent application will evolve over time. For the first version, this interoperability agent has been able to produce Satu Sehat data formats for eight types of resource types including encounter, procedure, condition, composition, medication, medication_request and medication_dispense. Trials have been carried out on each resource type and have run smoothly. In the future, this interoperability agent will be developed so that the number of resource types is in accordance with that determined by Satu Sehat. © 2024 IEEE.

关键词： electronic health record

来源：评论

学校读者我要写书评

暂无评论

Secure & Traceable Companies File Management System Using Blockchain and IPFS 1

Secure & Traceable Companies File Management System Using Bl...

引用

1st IEEE International Symposium on Consumer Technology, ISCT 2024

作者： Arissabarno, Cahyo Sukaridhoto, Sritrusta Winarno, Idris Politeknik Elektronika Negeri Surabaya Department of Informatics and Computer Engineering Surabaya Indonesia

ISBN: (纸本)9798350365191

With the advancement of cloud-based file management platforms, sharing and storing files in the company's area can be easily achieved through a variety of file-sharing platforms. However, these platforms often lack of security and adequate access logs or activity records for the shared files, resulting in a lack of control and traceability for users. This research proposes an traceable and secure system for managing files in companies using blockchain and IPFS. The content ID of uploaded files to IPFS will be stored on the blockchain along with user access rights and access logs. Integration with the existing company file management system is also facilitated by the use of the change data capture method. Experimental findings demonstrate that the system offers the desired traceability of access and activity while also meeting data security requirements such as confidentiality, integrity, and availability. Furthermore, performance tests indicate satisfactory outcomes with 0.8 seconds per MB for file storage on IPFS, and 4.1 seconds per transaction for data storage on Blockchain. The experimental results revealed that the proposed system, integrating blockchain and IPFS, successfully addressed the need for traceability of access and activity for the company's data, providing a significant improvement in data security and management over existing solutions. © 2024 IEEE.

关键词： Cloud platforms

来源：评论

学校读者我要写书评

暂无评论

Modeling Hybrid Feature-Based Phishing Websites Detection Using Machine Learning Techniques

引用

Annals of Data Science 2024年第1期11卷 217-242页

作者： Das Guptta, Sumitra Shahriar, Khandaker Tayef Alqahtani, Hamed Alsalman, Dheyaaldin Sarker, Iqbal H. Department of Computer Science and Engineering Chittagong University of Engineering & ampTechnology Chittagong4349 Bangladesh Unit of Cybersecurity Department of Computer Science Center of Artificial Intelligence King Khalid University Abha Saudi Arabia School of Engineering Computing and Informatics Dar Al-Hekma University Jeddah Saudi Arabia

In this paper, we mainly present a machine learning based approach to detect real-time phishing websites by taking into account URL and hyperlink based hybrid features to achieve high accuracy without relying on any third-party systems. In phishing, the attackers typically try to deceive internet users by masking a webpage as an official genuine webpage to steal sensitive information such as usernames, passwords, social security numbers, credit card information, etc. Anti-phishing solutions like blacklist or whitelist, heuristic, and visual similarity based methods cannot detect zero-hour phishing attacks or brand-new websites. Moreover, earlier approaches are complex and unsuitable for real-time environments due to the dependency on third-party sources, such as a search engine. Hence, detecting recently developed phishing websites in a real-time environment is a great challenge in the domain of cybersecurity. To overcome these problems, this paper proposes a hybrid feature based anti-phishing strategy that extracts features from URL and hyperlink information of client-side only. We also develop a new dataset for the purpose of conducting experiments using popular machine learning classification techniques. Our experimental result shows that the proposed phishing detection approach is more effective having higher detection accuracy of 99.17% with the XG Boost technique than traditional approaches. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2022.

关键词： Search engines

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：