检索结果-内蒙古大学图书馆

2nd International Conference on Smart Technologies for Smart Nation, SmartTechCon 2023

作者： Mohamed, Aezeden Deepak, B.B.V.L. Mogili, Umamaheswara Rao Department of Mechanical Engineering PNG University of Technology Papua New Guinea Department of Industrial Design National Institute of Technology Rourkela India Department of Computer Science and Engineering University of Technology and Medical Sciences India

ISBN: (纸本)9798350305418

In recent years, hybrid machining techniques have gained popularity in processing materials that are notoriously tough to work with. This is due to the inherent benefits that hybrid machining techniques hold over individual machining methods. These operations need the coordinated use of a wide variety of machining equipment in a variety of configurations. This research uses a neural network-based Bayesian regularisation technique to investigate the possibility of transforming the problematic material Inconel into a superalloy. The depth of cut, spindle speed, and feed rate are the control elements examined in this study. The performance metric is the primary focus of the average surface roughness (Ra). The experimental testing and the coefficient of determination were used to evaluate the capabilities of the suggested neural network in modeling and forecasting. The findings indicate that there is only a 1.25 percent discrepancy, on average, between the predictions made by neural network-based modeling and the values that were obtained. The surface roughness (Ra) values discovered in the experimental data are identical to those predicted by these equations. © 2023 IEEE.

关键词： Cutting parameters Inconel Machining Neural network Surface roughness

来源：评论

学校读者我要写书评

暂无评论

Wireless Federated Learning With Hybrid Local and Centralized Training: A Latency Minimization design

引用

IEEE Journal on Selected Topics in Signal Processing 2023年第1期17卷 248-263页

作者： Huang, Ning Dai, Minghui Wu, Yuan Quek, Tony Q. S. Shen, Xuemin State Key Lab of Internet of Things for Smart City China University of Macau Department of Computer and Information Science China University of Macau State Key Laboratory of Internet of Things for Smart City The Department of Computer and Information Science China Zhuhai Um Science and Technology Research Institute Zhuhai519031 China Singapore University of Technology and Design Information Systems Technology and Design Pillar 487372 Singapore National Cheng Kung University Taiwan University of Waterloo Department of Electrical and Computer Engineering WaterlooONN2L 3G1 Canada

Wireless federated learning (FL) is a collaborative machine learning (ML) framework in which wireless client-devices independently train their ML models and send the locally trained models to the FL server for aggregation. In this paper, we consider the coexistence of privacy-sensitive client-devices and privacy-insensitive yet computing-resource constrained client-devices, and propose an FL framework with a hybrid centralized training and local training. Specifically, the privacy-sensitive client-devices perform local ML model training and send their local models to the FL server. Each privacy-insensitive client-device can have two options, i.e., (i) conducting a local training and then sending its local model to the FL server, and (ii) directly sending its local data to the FL server for the centralized training. The FL server, after collecting the data from the privacy-insensitive client-devices (which choose to upload the local data), conducts a centralized training with the received datasets. The global model is then generated by aggregating (i) the local models uploaded by the client-devices and (ii) the model trained by the FL server centrally. Focusing on this hybrid FL framework, we firstly analyze its convergence feature with respect to the client-devices' selections of local training or centralized training. We then formulate a joint optimization of client-devices' selections of the local training or centralized training, the FL training configuration (i.e., the number of the local iterations and the number of the global iterations), and the bandwidth allocations to the client-devices, with the objective of minimizing the overall latency for reaching the FL convergence. Despite the non-convexity of the joint optimization problem, we identify its layered structure and propose an efficient algorithm to solve it. Numerical results demonstrate the advantage of our proposed FL framework with the hybrid local and centralized training as well as our proposed alg

关键词： Information management

来源：评论

学校读者我要写书评

暂无评论

Surface Roughness Prediction in Turning of Super Alloy through the Scaled Conjugate Gradient Model 2

Surface Roughness Prediction in Turning of Super Alloy throu...

引用

2nd International Conference on Smart Technologies for Smart Nation, SmartTechCon 2023

ISBN: (纸本)9798350305418

Surface roughness (Ra) is an important quality characteristic in the machining process since it influences the performance and functionality of the machined components. The Scaled Conjugate Gradient (SCG) technique is used in this study to estimate surface roughness during the turning process of Duplex stainless steel. The proposed model incorporates the SCG algorithm and the empirical data obtained from turning tests conducted with duplex stainless steel. The output variable is the value of the surface roughness once it has been measured. The model educates itself on the fundamental link between the input parameters and the surface roughness, then adjusts its weights and biases to achieve the best possible accuracy in its predictions. Statistical metrics such as mean absolute error (MAE), root mean square error (RMSE), and coefficient of determination (R2) are utilized to quantify prediction. The findings indicate that during the turning process, the SCG model can accurately predict the surface roughness of duplex stainless steel. Manufacturers can utilize these predictive skills to optimize machining parameters, attain the desired surface quality, and raise production while reducing costs. In conclusion, this study focuses on using the SCG model for surface roughness prediction during the turning process of duplex stainless steel. The proposed model provides valuable insights for process optimization, enabling manufacturers to improve machining productivity and achieve high-quality surface finishes. © 2023 IEEE.

关键词： Duplex stainless steel Prediction Root mean square error Scaled Conjugate Gradient Surface Roughness

来源：评论

学校读者我要写书评

暂无评论

Deepfake Detection System Using a Hybrid Model 14

Deepfake Detection System Using a Hybrid Model

引用

14th International Conference on Computing Communication and Networking Technologies, ICCCNT 2023

作者： Sudharson, S. Kokil, Priyanka Sasikala, D. Swamy, Penta Aravinda Vellore Institute of Technology Computer Science and Engineering Chennai India Indian Institute of Information Technology Design and Manufacturing Electronics and Communication Engineering Chennai600127 India Amrita School of Computing Chennai601103 India

ISBN: (纸本)9798350335095

There has been a rapid advancement in deep fake technology in recent years, which makes it increasingly difficult to detect fake images, especially those involving human faces, which have become difficult to detect. The traditional methods of detecting deep fake images are usually based on a human-crafted feature or a rule-based system, which can be easily beaten with simple cheating techniques. Intending to detect deepfake face images, we present a novel method that uses CapsNet and EfficientNet as feature extractors to detect deepfake face images. They are well suited to detect deepfake images that have undergone geometric transformations or variations as they can learn the spatial relationship between those features. Using EfficientNet, a powerful and efficient deep learning architecture, as a feature extractor, we extract high-level characteristics from an input image to create a more accurate image *** on our experiments,it was found that this method demonstrated the capability to detect various types of deep fake images with an accuracy rate of 99.64%, including those fabricated through face swapping and re-enacting. This method could be applied to a wide range of real-world applications, including in media forensics, law enforcement, and online media verification, so that it could be applied in many different contexts. © 2023 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

A design Framework for Preserving Cultural Heritage with AR Technology—An Innovative Exploration on Ethnic Motifs and Its Symbolism of the Naga Tribes 9th

A Design Framework for Preserving Cultural Heritage with AR ...

引用

9th International Conference on Research into design, ICoRD 2023

作者： Roy, Susmita Singh, Pankaj Pratap Padun, Abhijit Dept. of Multimedia Communication and Design CIT Kokrajhar Assam BTAD Kokrajhar India Dept. of Computer Science and Engineering CIT Kokrajhar Assam BTAD Kokrajhar India

ISBN: (纸本)9789819902927

The strong sense of immersion and interaction of advanced technology have an immense contribution towards cultural preservation in this digital era. Presently, the augmented technology is preferable and very popular from the aspect of the cultural heritage domain to revive and preserve cultural assets. This article presents a design-based framework to revive the original essence and significance of ethnic motifs and symbolism embedded in the Naga woven fabrics with Augmented Reality (AR) technology. This design framework proposes a smartphone-based application to decodes and interpret the meaning and symbolism of the motifs & patterns from Naga traditional woven fabric. This framework uses AR technology to scan and extract motifs & patterns from the traditional woven fabrics, thereby displaying the story on the visual screen. The information related to the motifs and patterns is delivered with authentic interpretations of the Naga ancient core. This application further explores the possibility of implementing it for cultural education which may create a unique identity of the hand woven fabrics of Naga tribes on digital platform. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2023.

关键词： Augmented reality

来源：评论

学校读者我要写书评

暂无评论

Protection Mechanism in JavaScript Attacks 6

Protection Mechanism in JavaScript Attacks

引用

6th IEEE Eurasian Conference on Educational Innovation, ECEI 2023

作者： Wu, Min-Hao Chiu, Chen-Yu Huang, Jian-Hung Chen, Jian-Xin Wang, Hao-Jyun Lin, Ying School of Information Engineering Guangzhou Panyu Polytechnic Guangdong China School of Art & Design Guangzhou Panyu Polytechnic Guangdong China Department of Computer Science & Information Engineering National Central University Taoyuan Taiwan

ISBN: (纸本)9798350334289

Web pages are increasing due to the rapid development of information technology. Many tasks were previously only possible by installing software on the computer. However, cloud service satisfies cross-platform requirements with the arrival of the multi-device age. Original technologies such as Flash and other proprietary technologies from different manufacturers have made complex content simple, but they also have cross-platform problems. JavaScript is a common user-side scripting language to support the standardization of online pages. Using JavaScript arouses concern over its security. Hackers frequently change their attack strategies. Therefore, it is crucial to learn how to effectively and promptly fight against them. Thus, the defense of JavaScript on the client side is the main topic of this research. By integrating VirusTotal, a cloud security analysis service on the browser is developed for users to use the most recent malware database and examine different JavaScript files online to prevent harmful code from being executed. © 2023 IEEE.

关键词： Websites

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Detection of Ransomware by Lightweight Mini-filters 6

Machine Learning Detection of Ransomware by Lightweight Mini...

引用

6th IEEE Eurasian Conference on Educational Innovation, ECEI 2023

作者： Chiu, Chen-Yu Wu, Min-Hao Huang, Jian-Hung Chen, Jian-Xin Wang, Hao-Jyun School of Art & Design Guangzhou Panyu Polytechnic Guangdong China School of Information Engineering Guangzhou Panyu Polytechnic Guangdong China Department of Computer Science & Information Engineering National Central University Taoyuan Taiwan

ISBN: (纸本)9798350334289

Users are more at risk from ransomware as time goes on. Invading users' computers with ransomware aims to encrypt their data and demand payment. Although anti-virus software may identify ransomware assaults on computers, it cannot prevent them until they are identified. Since many users may have already been hit by ransomware during this viral window period, safeguarding users during this time becomes a priority. We present a way to identify suspected ransomware in real-time. It would integrate into the Windows mini-filter driver to fight against ransomware assaults. This approach makes it challenging for ransomware to evade our detection. Our technology allows consumers to terminate the currently running application or put it on the whitelist once it has been flagged as potentially malicious software. Our solution enables users to edit the software and recovers the altered files when they choose to end the application, lessening their loss. © 2023 IEEE.

关键词： Application programs

来源：评论

学校读者我要写书评

暂无评论

Deep Learning for Automated Classification of Kidney Lesions in Chronic Kidney Disease Patients 2

Deep Learning for Automated Classification of Kidney Lesions...

引用

2nd IEEE International Conference on Integrated Circuits and Communication Systems, ICICACS 2024

作者： Lakshmi, B. Seetha Anand, Vijay Omotunde, Habeeb Birundadevi, M. Mahalakshmi, S. Brahmam, Madala Guru Sri Shanmugha College of Engineering and Technology Department of Artificial Intelligence and Data Science Tamilnadu Namakkal India School of Computer Science Engineering & Information Systems Vellore Institute of Technology Vellore India College of Computer and Information Sciences Imam Mohammad Ibn Saud Islamic University Department of Information Systems Riyadh Saudi Arabia Sri Sairam Siddha Medical College and Research Centre Department of Maruthuvam Chennai India R.M.K. Engineering College Department of Computer Science and Design Tamilnadu Chennai India

ISBN: (纸本)9798350317558

Deep Learning was utilized to autonomously classify renal abnormalities, which improved the diagnostic accuracy for individuals with chronic kidney disease (CKD), according to this study. During training on a meticulously selected dataset, the proposed model outperformed the most recent approaches. By utilizing medical imaging data - specifically quantitative and qualitative data - to differentiate between discrete kidney abnormalities, the model demonstrated exceptional levels of accuracy, precision, and recall. Furthermore, apart from effectively resolving ethical considerations pertaining to data privacy, this innovative methodology has the potential to fundamentally transform the existing landscape of chronic kidney disease (CKD) diagnosis and treatment. The results demonstrate that the model effectively manages intricate renal disorders, signifying a noteworthy progression in the field of medical image processing. This research paves the way for additional fruitful lines of inquiry, which ought to enhance nephrology diagnostics and patient care. © 2024 IEEE.

关键词： Automated Classification Chronic Kidney Disease Deep Learning Diagnostic Accuracy Kidney Lesions Medical Image Analysis

来源：评论

学校读者我要写书评

暂无评论

Enhancing Intrusion Prevention with Explainable Convolutional Neural Networks: Recent Developments and Promising Applications 8

Enhancing Intrusion Prevention with Explainable Convolutiona...

引用

8th International Conference on Communication and Electronics Systems, ICCES 2023

作者： Chitnis, Ajay Chandre, Pankaj Pathan, Shafi DevOps Architect Hcl Technologies Uk Limited Pune India Mit Art Design & Technology University Mit School of Computing Department of Computer Science & Engineering Pune India

ISBN: (纸本)9798350396638

The proliferation of cyberattacks in recent years has led to an increased demand for effective intrusion prevention systems (IPS). Convolutional Neural Networks (CNNs) have shown promise in improving the accuracy of IPS, but their lack of interpretability hinders their wider adoption. Explainable AI (XAI) techniques have emerged to address this issue, allowing users to understand the reasoning behind a model's predictions. This survey paper provides an overview of recent developments in enhancing IPS with XAI techniques in CNNs. This study reviews state-of-the-art research on integrating interpretability into CNN models, including methods such as attention mechanisms, saliency maps, and LIME. Also, this study discusses about the promising applications of CNN-based IPS with XAI, including network traffic analysis, malware detection, and anomaly detection. Finally, we highlight some of the challenges and opportunities for future research in this area, including the need for standardized evaluation metrics and the potential for combining XAI techniques with other AI methods such as reinforcement learning. Overall, this survey paper aims to provide a comprehensive understanding of the recent advances in using CNNs with XAI for enhancing IPS, and to identify promising directions for future research in this field. © 2023 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Mechanisms for Enhancing Network Services by Live Migration in the Network 6

Mechanisms for Enhancing Network Services by Live Migration ...

引用

6th IEEE Eurasian Conference on Educational Innovation, ECEI 2023

作者： Wu, Min-Hao Chiu, Chen-Yu Wu, Ji-Zheng Huang, Jian-Hung Chen, Jian-Xin Wang, Hao-Jyun School of Information Engineering Guangzhou Panyu Polytechnic Guangdong China School of Art & Design Guangzhou Panyu Polytechnic Guangdong China Department of Computer Science & Information Engineering National Central University Taoyuan Taiwan

ISBN: (纸本)9798350334289

It has become more crucial for Infrastructure as a Service (IaaS) providers to offer an operational environment with high stability and availability due to the fast expansion of the IaaS industry. Maintaining network connectivity after real-time virtual machine migration is a crucial challenge. In this study, we provide a Handover technique to keep users' TCP connections active following real-time wide-area network migration. Most Unix-based operating systems support handover. Furthermore, they include a protection mechanism against Distributed Denial of Service. We develop a reliable method of thwarting DDoS assaults with the implementation of handover and the remaining parts of the DDoS defense system. We also implement a false three-way handover to prevent the connection from being blocked by the NAT router after the changeover. Most Unix-based operating systems support handover. © 2023 IEEE.

关键词： Wide area networks

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：