检索结果-内蒙古大学图书馆

2024 international conference on knowledge engineering and Communication systems, ICKECS 2024

作者： Kaur, Kirandeep Venkatesh, R. Pundir, Sumit Brindha, S. Arul Mary Rexy, V. Singh, Ramanjeet University School of Business Chandigarh University Mohali Punjab Gharuan India Karpagam College of Engineering Department of Computer Science and Engineering Tamil Nadu Coimbatore India Graphic Era Deemed to Be University Department of Computer Science Engineering Uttrakhand Dehradun India Kpr Institute of Engineering and Technology Department of English Tamil Nadu Coimbatore India Saveetha College of Liberal Arts and Sciences Simats Department of Commerce General Tamil Nadu Chennai India Chandigarh University Mohali Punjab Gharuan India

ISBN: (纸本)9798350359688

Fraud detection in blockchain transactions is critical as the technology becomes more integrated into financial systems. Traditional rule-based systems have become ineffective against new fraudulent tactics. To solve these problems, a unique machine learning-based approach for detecting fraud in blockchain transactions is proposed in the study. Advanced machine learning techniques such as Random Forests, Support Vector Machines, and Isolation Forest are used to overcome existing systems' limitations. The data are collected meticulously and preprocessed, feature engineering is employed, and the models are trained to improve accuracy and adaptability. Compared to existing systems, the proposed technique outperforms with an accuracy of 0.98, precision of 0.94, recall of 0.93, and a false positive rate of 0.06. It also has an average processing time of 70 milliseconds, improving computational efficiency. The study represents a significant step forward in blockchain transaction security, providing dynamic protection against fraudulent activity and bolstering the integrity of decentralized financial ecosystems. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Leveraging GANs to Generate Synthetic Log Files for Smart-Troubleshooting in Industry 4.0 50

Leveraging GANs to Generate Synthetic Log Files for Smart-Tr...

引用

50th Euromicro conference on Software engineering and Advanced Applications

作者： Partovian, Sania Flammini, Francesco Bucaioni, Alessio Malardalen Univ Sch Innovat Design & Engn Vasteras Sweden Sigma Technol Informat Stockholm Sweden

ISBN: (纸本)9798350380279;9798350380262

In this paper, we tackle the challenge of generating synthetic log files using generative adversarial networks to support smart-troubleshooting experimentation. Log files are critical for implementing monitoring systems for smart-troubleshooting, as they capture valuable information about the activities and events occurring within the monitored system. Analyzing these logs is crucial for effective smart-troubleshooting, enhancing the overall efficiency, reliability, and security of smart manufacturing processes. However, accessing public log data is difficult due to privacy concerns and the need to protect sensitive information. Moreover, for the purpose of effective troubleshooting, it is essential to have datasets that include fault, error, and failure logs as well as standard logs. In recent years, synthetic log files have emerged as a promising solution to augment limited real-world datasets and facilitate the development and evaluation of anomaly detection techniques. Building on this concept of synthetic data, we have developed a specific log generation technique and dataset tailored for testing smart-troubleshooting techniques in heterogeneous connected systems environments, such as industrial cyber-physical systems and the internet of things. First, we propose a methodology that generates synthetic log files based on generative adversarial networks. Later, we instantiate this methodology using different Generative Adversarial Network implementations and present a validation and a comprehensive comparative analysis of their performance. Eventually, we provide a robust dataset for anomaly detection and threat analysis in cyberspace security. Based on the results of our comparison, CTGAN has shown superior performance in generating high-quality synthetic log files.

关键词： Generative Adversarial Network Synthetic data Log Files Industry 4.0 Smart-Troubleshooting

来源：评论

学校读者我要写书评

暂无评论

Application of Enterprise Master data Management System in the Informatization of Electric Power Enterprises

Application of Enterprise Master Data Management System in t...

引用

2024 international conference on Electrical Drives, Power Electronics and engineering, EDPEE 2024

作者： Hu, Liu Jianhong, Pan Zhuang, Cui Zhonglong, Zheng Lu, Shu State Grid Corporation Of China Hebei056000 China State Grid Jilin Electric Power Co. Ltd. Jilin132400 China State Grid Xintong Yili Technology Co. Ltd Liaoning 121200 China

ISBN: (纸本)9798350395631

In order to improve efficiency and reduce costs, large organizations are building key systems, such as enterprise resource planning (ERP), manufacturing execution system, human resource management (HRM) and customer relationship management (CRM). These core systems pose new challenges in terms of data consistency, integrity, accuracy, and auditability across departments, systems, and fields, and even in terms of organizational consistency requirements. In the early stages of enterprise IT (Information Technology) development, companies often lacked comprehensive planning for data standards and data exchange between enterprise systems, so it was necessary to implement Master data Management (MDM) systems. This article explored the application of enterprise level master data management system in the informatization of power enterprises. Firstly, the enterprise level master data management system and power enterprise informatization were introduced, and then the improvement of enterprise level master data management system in enterprise database operation efficiency was verified through experiments (the reading and calling efficiency of experimental databases was generally higher than 80%, higher than traditional data reading efficiency). © 2024 IEEE.

关键词： Informatization

来源：评论

学校读者我要写书评

暂无评论

Study on the reliability allocation of machining centers based on data envelopment analysis method 2

Study on the reliability allocation of machining centers bas...

引用

2nd international conference on Advanced manufacturing Technology and manufacturing systems, ICAMTMS 2023

作者： Jin, Guang-Yu Jin, Sheng-Jie Wang, De-Chao Piao, Cheng-Dao Yin, Feng-Zhe Engineering College of Yanbian University Yanji133002 China

ISBN: (纸本)9781510667327

For the problem that it is difficult to determine the type of failure occurring in machining centers, Minitab software is used to process and analyze the failure data, and the type of failure distribution is found to obey the Weibull distribution. Based on the CCR model in the data envelope method, the reliability index is applied to allocate the reliability of the machining center, and according to the practical applicability of the allocation method, the redistribution problem of reliability is better improved, and the reliability level of the whole machine is improved. © 2023 SPIE.

关键词： Machining centers

来源：评论

学校读者我要写书评

暂无评论

Selection of Industry 4.0 Technology to Support Lean manufacturing from the Perspective of Enterprise Interoperability 32nd

Selection of Industry 4.0 Technology to Support Lean Manufac...

引用

32nd international conference on Flexible Automation and Intelligent manufacturing

作者： Martins, G. R. D. N. Ramos, L. F. P. Loures, E. F. R. Deschamps, F. Loures, L. R. Pontifical Catholic Univ Parana PUC PR Curitiba Parana Brazil

ISBN: (纸本)9783031381645;9783031381652

Faced with paradigm shifts in the global manufacturing context promoted by the Fourth Industrial Revolution, many organizations are seeking to meet customer needs through the integration of Lean manufacturing (LM) philosophy principles with Industry 4.0 (I4.0) technologies. When there is the integration of technological enablers from I4.0 and deep advances in efficiency and productivity with LM, these systems tend to offer enhanced and more assertive results, since they are complementary concepts. The main goal of this paper is the selection of I4.0 technologies to support the LM system, considering the perspectives and barriers of Enterprise Interoperability (EI) and using multicriteria methods (MCDM) to support decision-making. Using the DEMATEL multicriteria method, it was possible to develop a diagnostic evaluation, analyze the existing influences between the elements of the LM, and support the elicitation of weights in the decisional evaluation, with the FITradeoff method. In this way, the decisional evaluation indicated as the I4.0 technology that must be implemented as a priority to raise the level of organizational maturity in LM is Big data Analytics. Big data integrated with Business Analytics (BA) can offer several advantages, such as assertiveness in decision-making;Keeping the company updated about the market;Indicating risks and improving data security;Promotes alignment between marketing and sales, among others.

关键词： Lean manufacturing Industry 4.0 Enterprise Interoperability MCDM methods

来源：评论

学校读者我要写书评

暂无评论

Collaborative Teaching with Attention Distillation for Multiple Cross-Domain Few-Shot Learning 14

Collaborative Teaching with Attention Distillation for Multi...

引用

14th IEEE international conference on Cyber Technology in Automation, Control, and Intelligent systems, CYBER 2024

作者： Shang, Zhenduo Liu, Xiyao Xie, Xing Han, Zhi State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences The Institutes for Robotics and Intelligent Manufacturing The University of Chinese Academy of Sciences China Shenyang Institute of Automation Chinese Academy of Sciences The Institutes for Robotics and Intelligent Manufacturing State Key Laboratory of Robotics China

ISBN: (纸本)9798331506056

Multiple Cross-Domain Few-Shot Learning (MCD-FSL) aims to improve the generalization ability of the model across unseen domains by utilizing the diverse knowledge of different teacher networks. knowledge transferring among multiple domains is complex and difficult due to significantly different data distributions. In current tasks, effectively utilizing knowledge from multiple domains to improve model generalization in an unseen domain remains challenging. Therefore, we propose Collaborative Teaching with Attention Distillation (CTAD-Net), exploring a collaborative strategy among multiple teacher networks of teachers to address this issue. Specifically, we introduce a weight allocation (WA) module and a deep fusion (DF) module for distilling knowledge from the teacher networks to a single student network. Additionally, our CTAD-Net combines attention mechanisms and employs both response-based and relation-based knowledge distillation to transfer more comprehensive and effective knowledge. The experimental results on four fine-grained datasets have demonstrated the effectiveness of our proposed CTAD-Net approach. © 2024 IEEE.

关键词： Collaborative learning

来源：评论

学校读者我要写书评

暂无评论

Enhancing Large Language Models with Google knowledge Integration for Rapid Response in Healthcare Emergencies

Enhancing Large Language Models with Google Knowledge Integr...

引用

2024 IEEE international conference on Intelligent systems and Advanced Applications, ICISAA 2024

作者： Das, Suparna Khondakar, Kamil Reza Mazumdar, Hirak Woxsen University School of Technology Hyderabad India Woxsen University School of Science Hyderabad India Adamas University Department of Computer Science and Engineering Kolkata India

ISBN: (纸本)9798331539948

We propose a novel framework that leverages knowledge from Google and utilizes Generative Pretrained Trans-former (GPT) to enhance the capabilities of GPT. The GPT's knowledge and the responses generated from it are based on the data till 2021, it may generate incorrect responses for the questions that require knowledge after the year 2021. With the proposed architecture Large Language Models (LLMs) like GPT can be enhanced to produce responses without a knowledge barrier. Also, it is expected to provide much better answers as having access to Google as the knowledge regarding the specific domain would have been more informative. Emerging diseases and global health crises require rapid, precise, and adaptive responses. While advanced Artificial Intelligence (AI) systems, like GPT, can provide valuable support in many aspects of healthcare, they are not a substitute for the expertise, experience, and real-time decision-making abilities of healthcare professionals and epidemiologists. The response to novel and recent diseases often necessitates extensive collaboration among scientists, healthcare workers, and public health organizations, as well as access to specialized medical knowledge and resources. AI systems can assist in data analysis, information retrieval, and decision support, but ultimately, it is the collective human effort that drives effective responses to these complex challenges, especially when the situation is rapidly evolving or novel in nature. © 2024 IEEE.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Ontological knowledge-Based Representation System to Prevent Web Attacks in iMANET's

Ontological Knowledge-Based Representation System to Prevent...

引用

2024 international conference on Communication, Computer Sciences and engineering, IC3SE 2024

作者： Chandani, Priyanka Gupta, Anand Kumar Manivasagam Noida Institute Of Engineering And Technology Department Of Data Science Uttar Pradesh Greater Noida India Tula's Institute Department Of Computer Science And Engineering Dehradun India Department Of Computer Science And Information Technology Bangalore India

ISBN: (纸本)9798350366846

This paper implies securing Internet-based Mobile Ad-hoc Networks (iMANETs) with semantic web techniques. To illustrate safety issues, ontologies will be utilised rather than taxonomies. These ontologies can be added to an intrusion detection system's (IDS) information repository. By employing inference based on semantic relations, intrusion detection systems can identify and incorporate upcoming attacks into their current knowledge base. © 2024 IEEE.

关键词： Ontology

来源：评论

学校读者我要写书评

暂无评论

A critical review of contribution of evolutionary techniques to machining parameter optimisation

引用

international Journal of Mechatronics and manufacturing systems 2024年第4期17卷 411-448页

作者： Dixit, Uday Shanker Sharma, Faladrum Department of Mechanical Engineering Indian Institute of Technology Guwahati Guwahati781 039 India Centre for Indian Knowledge Systems Indian Institute of Technology Guwahati Guwahati781 039 India

Optimisation of machining processes has been an active research area for over six decades. In the last three decades, several evolutionary optimisation methods have been utilised. This paper offers a brief history of optimisation in machining followed by a detailed discussion on the application of evolutionary optimisation methods. The focus is narrowed down to traditional machining processes, where a wedge shaped material removes the material in the form of chips. The paper highlights the challenges in choosing a suitable algorithm, given the empirical nature of available comparative studies lacking a solid mathematical basis. Further research is needed to understand the similarities and contrasts among evolutionary optimisation methods. It is also prudent to focus on the proper modelling of the processes (preferably with the help of big data), integrating the machine tools with proper sensors and developing strategies for online optimisation. Copyright © 2024 Inderscience Enterprises Ltd.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

An ontology-based semantic integration approach for dynamic scheduling in cyber-physical production system

An ontology-based semantic integration approach for dynamic ...

引用

2024 IEEE international conference on Industrial engineering and engineering Management, IEEM 2024

作者： Chen, Mingzhi Hu, Xiaofeng Zhang, Yahui Xia, Mingyuan School of Mechanical Engineering Shanghai Jiao Tong University Shanghai200240 China Shanghai Changxing Marine Laboratory Shanghai200245 China Research Center of Marine Digital Twin Manufacturing Technology Institute of Marine Equipment Shanghai Jiao Tong University Shanghai200240 China

ISBN: (纸本)9798350386097

The Cyber-Physical Production System (CPPS) integrates information technology with physical manufacturing processes to enhance production control flexibility. However, the prevalent issue in manufacturing systems is the heterogeneity of data from multiple sources. CPPS fails to acquire comprehensive information from the current manufacturing system, making it difficult to promptly formulate accurate production schedules. In response to this challenge, the article presents an ontology-based semantic integration and dynamic scheduling framework, achieving semantic interoperability within CPPS. This framework proposes methodologies for constructing ontology models, data models, and rule models of workshop scheduling, thereby providing semantic context, data integration guidance, and scheduling rule description for CPPS construction. Sequentially, under the guidance of the data model, a real-time data integration platform is established to achieve semantic data integration of data in industrial software, which is the key to supporting the dynamic scheduling of CPPS. Finally, employing a sub-assembly construction workshop as an illustrative case, a CPPS prototype is constructed to verify the efficacy of the proposed methodology. © 2024 IEEE.

关键词： Ontology

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：