检索结果-内蒙古大学图书馆

Mechanical System Vulnerabilities: Advanced Fusion Machine Learning Model for Detecting Ethereum Attack Patterns in IIoT-5.0 Environments 1

引用

7th International Conference on Intelligent Computing and Optimization, ICO 2023

作者： Sulakhe, Vishal N. Goyal, S.B. Gadekar, Amit Wasnik, Manisha Agarkar, Pankaj Rajawat, Anand Singh Mechanical Engineering Department Sandip University Nashik422213 India Faculty of Information Technology City University Petaling Jaya46100 Malaysia Sandip Institute of Technology and Research Centre Nashik India Ajeenkya D Y Patil School of Engineering Charoli Lohegaon Maharashtra Pune412105 India School of Computer Science and Engineering Sandip University Nashik422213 India

ISBN: (数字)9783031733185

ISBN: (纸本)9783031733178

It is of the utmost significance to keep the reliability and confidentiality of these systems in check in light of the coming advent of Industry 5.0 as well as the growing penetration of the Industrial Internet of Things (IIoT) into complicated mechanical systems. The broad adoption of blockchain technology, and in particular Ethereum, brings with it a new set of opportunities as well as hazards that have an impact on the complicated dynamic that exists between machines, data, and decentralized applications. This research investigates an advanced fusion machine learning model with the intention of locating dangerous patterns and likely attack vectors that target Ethereum transactions and contracts within IIoT-5.0 systems. The results of this investigation are intended to be used in future research. The detection of these patterns and vectors is the primary focus of the model. In an era in which there is a transition taking place in the industrial sector, this research presents a novel technique for improving cybersecurity. Examining the specific flaws that may exist in mechanical systems after they have been integrated with blockchain solutions is the strategy that will be utilized. Our model shows tremendous promise in recognizing abnormalities and potential dangers by utilizing a combination of supervised learning techniques and unsupervised learning approaches. These techniques allow for the model to develop without being directly monitored by a human. This paves the way for preventative safety precautions to be included in the design of the future generation of industrial systems. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Ethereum

来源：评论

学校读者我要写书评

暂无评论

Harmful algal bloom forecasting. A comparison between stream and batch learning

arXiv

引用

arXiv 2024年

作者： Molares-Ulloa, Andres Rivero, Daniel Fernandez, Enrique Padin, Xosé A. Rocruz, Elisabet Nolasco, Rita Dubert, Jesús Universidade da Coruña Department of Computer Science and Information Technology Faculty of Computer Science A Coruña15071 Spain Centro de investigación CITIC Department of Computer Science and Information Technology University of A Coruña A Coruña15071 Spain Vigo Spain Department of Physics Centro de Estudos do Ambiente e do Mar University of Aveiro Aveiro Portugal

Diarrhetic Shellfish Poisoning (DSP) is a global health threat arising from shellfish contaminated with toxins produced by dinoflagellates. The condition, with its widespread incidence, high morbidity rate, and persistent shellfish toxicity, poses risks to public health and the shellfish industry. High biomass of toxin-producing algae such as DSP are known as Harmful Algal Blooms (HABs). Monitoring and forecasting systems are crucial for mitigating HABs impact. The study of phytoplankton blooms and their causes is challenging, prompting the exploration of advanced machine learning techniques. Predicting harmful algal blooms involves a time-series-based problem with a strong historical seasonal component, however, recent anomalies due to changes in meteorological and oceanographic events have been observed. Stream Learning stands out as one of the most promising approaches for addressing time-series-based problems with concept drifts. However, its efficacy in predicting HABs remains unproven and needs to be tested in comparison with Batch Learning. Historical data availability is a critical point in developing predictive systems. In oceanography, the available data collection can have some constrains and limitations, which has led to exploring new tools to obtain more exhaustive time series. Ocean hydrodynamic models, such as CROCO, has proven its ability to reproduce the ocean conditions with a high temporal and spatial frequency. Model explainability is increasingly crucial for decision acceptance, particularly in the context of alarm systems like HAB forecasting. In this study, a machine learning workflow for predicting the number of cells of a toxic dinoflagellate, Dinophysis acuminata, was developed with several key advancements. Seven machine learning algorithms were compared within two learning paradigms. Notably, the output data from CROCO, the ocean hydrodynamic model, was employed as the primary dataset, palliating the limitation of time-continuous historic

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Leveraging Support Vector Machine for Sports Injury Classification

Leveraging Support Vector Machine for Sports Injury Classifi...

引用

International Conference on information technology and Electrical Engineering (ICITEE)

作者： Thattapon Surasak Phornnatee Praking Kotcharat Kitchat Dept. of Computer and Information Science Faculty of Applied Science King Mongkut's University of Technology North Bangkok Bangkok Thailand Dept. of Computer Science and Information Engineering National Central University Taoyuan Taiwan

This study explores the utility of Support Vector Machines (SVM) for the classification of injuries in Athletes including tennis, table tennis, and badminton. The primary objective of this research was to develop an automated method to detect between normal and injury pose, providing a poten-tially powerful tool for early detection. In other words, this research is the pioneer study to represent one another solution for sports injury classification using the image data apart from the current approaches that might be focused on the sensor-based. Therefore, we collect a dataset from various social media across the three sports, labeled into two categories: “Normal” and “Injury”. The SVM model was trained on this dataset, and tuned to optimize its performance in distinguishing the two classes. Achieving an accuracy of 96.63%, the result demonstrates that the SVM model can effectively identify injury patterns in the considered sports. The implications of this study are sig-nificant, presenting the initial steps towards applying computer vision tasks in sports topics. By demonstrating the feasibility of an SVM-based approach to injury detection in these racket sports.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Best Lecturer Decision Support System Using Method Analytical Hierarchy Process (AHP) and Simple Adaptive Weighting (SAW) 9

Best Lecturer Decision Support System Using Method Analytica...

引用

9th International Conference on Electrical Engineering, computer science and Informatics, EECSI 2022

作者： Pebrianti, Dwi Nurhayati Bayuaji, Luhur Syafrullah, Mohammad Universitas Budi Luhur Magister of Computer Science Faculty of Information Technology Jakarta Indonesia International Islamic University Malaysia Faculty of Engineering Dept. of Mechanical Aerospace Engineering Gombak Malaysia Universitas Budi Luhur Faculty of Information Technology Department of Information System Jakarta Indonesia

ISBN: (数字)9786239213565

ISBN: (纸本)9781665470438

Data processing as one of information technology area has wide range of applications including the selection of best lecturer in universities. Best Lecturer Assessment is required by the university to identify qualified human resources and in the future this process will give motivations to the lectures to be more productive and increase the quality of doing their jobs. In Buana Perjuangan University, Karawang, the selection of best lecturer is still conducted manually, where giving result to be subjective and questionable. Additionally, decision support system method has not been applied in determining the best lecturer. In this study, we proposed hybrid method which combines Analytical Hierarchy Process (AHP) and Simple Additive Weighting (SAW) to determine the best lecturer by using five criteria, namely attendance at lecture meetings, academic rank, number of publications, additional assignments, and education levels. The data sample used were obtained using a random sampling technique on lecturer data, provided by the University Data and information Center. The study involves two phases. Phase 1 involves in developing a questionnaire that contains a list of criteria that a best lecturer must have. In Phase 2, an AHP decision matrix is developed, and the candidates will be ranked based on the selected criteria obtained from Phase 1 and their weight values. The result will then be ranked by using SAW to obtain even more accurate decision of best lecturer. The results obtained indicate that the value of the Consistency Index (CI) for all respondents is consistent, 0.8 in average. Then, the CI result is used to determine the Consistency Ratio (CR), where the result is also consistent for all of the respondents,-0.7 in average. These result shows that the proposed method has the same output with the expert (respondents) decisions. © 2022 Institute of Advanced Engineering and science (IAES).

关键词： AHP Best Lecturer Ranking SAW SPK

来源：评论

学校读者我要写书评

暂无评论

A Fine-Tuned Large Language Model for Domain-Specific with Reinforcement Learning

A Fine-Tuned Large Language Model for Domain-Specific with R...

引用

Creative Communication and Innovative technology (ICCIT), IEEE

作者： Amelia Ritahani Ismail Amira Shazleen Aminuddin Afiqa Nurul Noor Azura Zakaria Wafa Haussain Nasser Fadaaq Department of Computer Science Kulliyyah of Information and Communication Technology International Islamic University Malaysia Kuala Lumpur Malaysia Faculty of Computer Studies Arab Open University Riyadh Saudi Arabia

ISBN: (数字)9798350367492

ISBN: (纸本)9798350367508

Large Language Models (LLMs) like GPT-3 and BERT have significantly shown advancement in natural language processing by providing robust tools for understanding and generating human languages. However, their broad but shallow knowledge across many domains often leads to less effective performance in domain-specific tasks, where detailed and special-ized knowledge is needed. To address this limitation, this paper investigates the effectiveness of fine-tuning LLMs for specific domains. The approach incorporates reinforcement learning to integrate user feedback, allowing the model to dynamically adjust and refine its responses. This will ensure the model adapts iteratively, improving communication and interaction with users. The fine-tuned model’s performance is evaluated using two domain-specific datasets—medical and dental. Evaluation metrics such as Levenshtein distance and cosine similarity are used to assess the textual accuracy and semantic relevance of the fine-tuned model. The results from the dental the medical datasets indicate a low level of textual differences and strong semantic alignment, respectively. These suggest that the fine-tuned model effectively processes and preserves the integrity of domain-specific content with the potential of fine-tuning LLMs to enhance their applicability in specific domains.

关键词： Performance evaluation Adaptation models Accuracy Large language models Semantics Refining Reinforcement learning Natural language processing Dentistry

来源：评论

学校读者我要写书评

暂无评论

A Highly-Accurate Robot Calibration Method with Line Constraint

A Highly-Accurate Robot Calibration Method with Line Constra...

引用

IEEE International Conference on Networking, Sensing and Control

作者： Tinghui Chen Shuai Li Xin Luo School of Computer Science and Technology Chongqing University of Posts and Telecommunications Chongqing China Faculty of Information Technology and Electrical Engineering University of Oulu Technology Research Center of Finland (VTT) Oulu Finland College of Computer and Information Science Southwest University Chongqing China

For the application of industrial robots, positioning accuracy is a significant indicator of their performance. Aiming at the issues of low positioning accuracy, the calibration techniques are employed to obtain the real kinematic parameters for effectively enhancing its accuracy. However, in practical scenarios, for the restriction of the robot workspace, the samples collected during the robot calibration process cannot cover the entire space of the entire space, resulting in an impact on data integrity. To address the above issues, we develop a calibrator integrating the MCS method (measurement configurations selection) and LM algorithm (Levenberg-Marquardt) with a spatial line constraint (LMLC), which contains three-fold: a) selecting a set of most representative measurement configurations according to the observability index for enhancing the stability of calibration results; b) develop an LM algorithm with line constraint to solve the problem of spatial restriction of robot sampling; c) presenting a robot calibrator that combines MCS and LMLC for efficiently improving the robot calibration accuracy. Experiments illustrate that the MCS-LMLC calibrator outperforms state-of-the-art calibrators on an industrial robot’s calibration accuracy and computational efficiency.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Challenges and Factors Affecting Cloud Computing Adoption in Higher Technical Education Institutions in Libya 1

Challenges and Factors Affecting Cloud Computing Adoption in...

引用

1st IEEE International Maghreb Meeting of the Conference on sciences and Techniques of Automatic Control and computer Engineering, MI-STA 2021

作者： Abdelkader, K. Aki, Rawda Yedder, Sumaya Arfa, R. Higher Institute of Science and Tecnology-Ghadames Dept. Computer Science Ghadames Libya Faculty of Information Technology Tripoli Libya

ISBN: (纸本)9781665418560

Cloud computing has attracted more attention in the recent years from industry and academic as new technology paradigm. It is a model that provides services on-demand over the internet. With the spread of Corona pandemic around the world, it has restricted the movement of the people. Therefore, it becomes necessary to find alternative methods for service provisions. In spite of the apparent economic crises in Libya, there has been increasing pressure for higher technical educations sector to deliver better services using minimal resources. The aim of this study is to investigate the main factors and barriers which may affect or prohibit cloud adoption in the higher technical educational institutions of national board of technical and vocational education in Libya. A cross-sectional design method is used to answer the research questions based on Technological Organizational and Environmental (TOE) framework. In this study, the main factors that affect the cloud computing adoption in technical colleges and higher institutions where characterized and tested using SPSS software, robust analysis tool for hypothesis testing approach. The results of this study showed that the technological readiness and complexity of the technology were the most factors affecting the adoption of cloud computing in the technical institutes. The most barriers preventing the adoption of cloud are almost 59.7% the Internet connectivity, robustness and availability. Finally, the preferred cloud computing services to be adopted in the technical colleges and institutes is 52.11% IaaS. © 2021 IEEE.

关键词： Cloud computing

来源：评论

学校读者我要写书评

暂无评论

Metaheuristics Algorithm for Tuning of PID Controller of Mobile Robot System

引用

computers, Materials & Continua 2022年第8期72卷 3481-3492页

作者： Harsh Goud Prakash Chandra Sharma Kashif Nisar Muhammad Reazul Haque Ag.Asri Ag.Ibrahim Narendra Singh Yadav Pankaj Swarnkar Manoj Gupta Laxmi Chand Indian Institute of Information Technology NagpurIndia School of Computing&Information Technology Manipal UniversityJaipurRajasthanIndia Faculty of Computing and Informatics University Malaysia SabahJalan UMSKota Kinabalu88400SabahMalaysia Faculty of Computing&Informatics Multimedia UniversityPersiaran MultimediaCyberjaya63100SelangorMalaysia Maulana Azad National Institute of Technology BhopalIndia Department of Electronics and Communication Engineering JECRC UniversityJaipurRajasthanIndia Department of Computer Science and Engineering Hanyang UniversitySeongdong-guSeoul04763Korea

Robots in the medical industry are becoming more common in daily life because of various advantages such as quick response,less human interference,high dependability,improved hygiene,and reduced aging *** is why,in recent years,robotic aid has emerged as a blossoming solution to many challenges in the medical *** this manuscript,meta-heuristics(MH)algorithms,specifically the Firefly Algorithm(FF)and Genetic Algorithm(GA),are applied to tune PID controller constraints such as Proportional gain Kp Integral gain Ki and Derivative gain *** controller is used to control Mobile Robot System(MRS)at the required set *** FF arrangements are made based on various pre-analysis.A detailed simulation study indicates that the proposed PID controller tuned with Firefly Algorithm(FF-PID)for MRSis beneficial and suitable to achieve desired closed-loop system *** FF is touted as providing an easy,reliable,and efficient tuning technique for PID *** most suitable ideal performance is accomplished with FF-PID,according to the display in the time ***,the observed response is compared to those received by applying GA and conventional off-line tuning *** comparison of all tuning methods exhibits supremacy of FF-PID tuning of the given nonlinear Mobile Robot System than GA-PID tuning and conventional controller.

关键词： Metaheuristic algorithm genetic algorithm PID controller mobile robot system firefly algorithm

来源：评论

学校读者我要写书评

暂无评论

Sentiment Analysis of ChatGPT Healthcare Discourse: Insights from Twitter Data

Sentiment Analysis of ChatGPT Healthcare Discourse: Insights...

引用

International Conference on Software, Knowledge information, Industrial Management and Applications (SKIMA)

作者： Roshan Kumar Ramesh Kumar Ayyasamy Anbuselvan Sangodiah Kesavan Krishnan Abdulkarim Kanaan Jebna Lim Jit Theam Faculty of Information and Comunication Technology Universiti Tunku Abdul Rahman Kampar Malaysia Faculty of Computing and Engineering Quest International University Ipoh Malaysia Faculty of Computer Science and Information Technology Universiti Malaya Kuala Lumpur Malaysia

This paper explores the application of Chat Generative Pretrained Transformer (ChatGPT) in the healthcare domain, introducing a sentiment analysis model to evaluate ChatGPT-related tweets in healthcare contexts. The study aims to uncover predominant sentiments, thematic content, and diverse perspectives concerning ChatGPT's integration into healthcare, utilizing an extensive dataset from Twitter comprising 10,330 healthcare-related tweets. Leveraging advanced Natural Language Processing (NLP) techniques, we systematically categorized topics and emotional content within these tweets. Additionally, we conducted a comprehensive analysis of frequently occurring words in tweets expressing positive and negative sentiments. The findings reveal that the majority of healthcare-related ChatGPT tweets express either positive or negative sentiments, with a minor proportion conveying neutral viewpoints. Furthermore, to enhance our comprehension of sentiment dynamics in healthcare discussions involving ChatGPT, we applied four machine learning classifiers Support Vector Machine, K-Nearest Neighbors, Naive Bayes and Random Forest. Remarkably, the SVM classifier demonstrated the highest accuracy at 85.6%, affirming its efficacy in healthcare sentiment analysis. In summary, this research sheds light on prevailing sentiments and perspectives regarding ChatGPT in the healthcare sector, highlighting its predominantly positive and neutral reception on platforms like Twitter. Additionally, the success of SVM as a sentiment analysis tool underscores its potential for discerning sentiments in healthcare-related ChatGPT discussions, contributing to ongoing debates on AI integration in healthcare and guiding future endeavors in this evolving field.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Sampled-Data H∞Control for Nonlinear Dynamical Intelligent Fuzzy Systems with Time-Varying Delay 34

Sampled-Data H∞Control for Nonlinear Dynamical Intelligent ...

引用

34th Chinese Control and Decision Conference, CCDC 2022

作者： Qu, Zifang Du, Zhenbin Zhang, Guangyong Shandong Technology and Business University School of Mathematics and Information Science Yantai264003 China Yantai University School of Computer and Control Engineering Yantai264005 China Wuxi University Faculty of Science Wuxi214105 China

ISBN: (纸本)9781665478960

The manuscript explores the issue of the sampled-data H∞ control for the nonlinear intelligent fuzzy system which has time-varying delay. A T-S fuzzy model is employed to portray the system and the fuzzy controller is a sampled-data signal implemented by a zero-order holder. According to the stability theory of Lyapunov-Krasovskii functional, a fuzzy sampled-data H∞ control algorithm is gained. Moreover, by adopting linear matrix inequalities (LMIs), some sufficient conditions for the controller are acquired, which ensure the H∞ performance under a prescribed level. Furthermore, an application example of a mechanical system displays the proposed design. © 2022 IEEE.

关键词： Linear matrix inequalities

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：