检索结果-内蒙古大学图书馆

5th IEEE International Conference for Emerging technology, INCET 2024

作者： Gowda, Dankan V. Prasad, V. Nuthan Agme, Vaishali N. Prasad, K.D.V. Kawale, Sheetalrani Rukmaji Mallikarjun, Shruti Department of Electronics and Communication Engineering BMS Institute of Technology and Management Karnataka Bangalore India Department of Electronic and Communication MSRIT Karnataka Bangalore India Department of Applied Science Bharati Vidyapeeth College of Engineering Maharashtra Navi Mumbai India Department of Research Symbiosis Institute of Business Management Hyderabad India Pune India Department of Computer Science Karnataka State Akkamahadevi Women University Karnataka Vijayapura India Department of Computer Science Karnataka State Akkamahadevi Women University Karnataka Vijayapura India

ISBN: (纸本)9798350361155

This paper focuses on the combination of ML algorithms for predictive maintenance through Internet of Things (IoT)-based smart safety helmets in order to increase not only the level of safety operations and but as well equipment life in industrial settings. We study the present helmet technologies and reveal the weaknesses by tomorrow foreseeing technologies which exist in current predictive maintenance strategies. Proposing a new technique, ML algorithms suite is applied as an analyzing tool to collected data from sensors within the helmets. The system architecture is real-time data processed by an IoT framework to predict and act on maintenance needs up front. The results of the experimental validation confirm the implementation of our approach, that shows the significant increase of the predictive accuracy and timeliness as compared to the traditional methods. The research has not only enabaled to create smart safety equipment but also a scalable approach that could be maximized across other Internet of things applications. © 2024 IEEE.

关键词： Accident prevention

来源：评论

学校读者我要写书评

暂无评论

A New Model Evaluation Framework for Tamil Handwritten Character Recognition 1

引用

2nd International Conference on Trends in Electronics and Health Informatics, TEHI 2022

作者： Kavitha, B.R. Shaffi, Noushath Mahmud, Mufti Hajamohideen, Faizal Narayanan, Priyalakshmi School of Information Technology and Engineering Vellore Institute of Technology Vellore India Department of Information Technology University of Technology and Applied Sciences-Sohar Sultanate of Oman SoharOM 311 Oman Department of Computer Science Nottingham Trent University NottinghamNG11 8NS United Kingdom CIRC and MTIF Nottingham Trent University NottinghamNG11 8NS United Kingdom Department of Computer Science University College London London United Kingdom

ISBN: (数字)9789819919161

ISBN: (纸本)9789819919154

The robustness of any pattern recognition model relies heavily on the availability of comprehensive samples. Until last year, the Tamil Handwritten Character Recognition (HWCR) works relied on the solitary HPL Tamil dataset [1]. Recently, a new benchmarking for Tamil HWCR was published [2] comprising 94000 samples in total. The efficiency of corroboration using multiple standardized databases is crucial in advancing any research area. Towards this aim, in this paper, we showed different ways of experimentation with these datasets. For this purpose, we utilized transfer learning, and a custom deep neural network, a recently published work for Tamil HWCR [3]. Different experimental setups were suggested that involved independent, cross-testing, and mixed modes of model building and evaluation using two standardized datasets. These setups form a rigorous testing framework for analyzing Tamil HWCR tasks. The work presented in this paper is the first to report the results of Tamil HWCR using two standardized datasets and sets a new model evaluation benchmark. For rapid reproducibility and dissemination, the code and materials used in this study are available at https://***/Kavitha-BR-VIT/Tamil-HWCR. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Machine learning based fraudulent detection system for financial transactions

Machine learning based fraudulent detection system for finan...

引用

2024 International Conference on IT and Industrial Technologies, ICIT 2024

作者： Alam, Wahaj Ali, Raja Hashim Ali, Nisar Imad, Muhammad ul Abideen, Zain Shah, Muhammad Huzaifa Department of Artificial Intelligence Faculty of Computer Science & Engineering GIK Institute of Engineering Sciences & Technology Topi23460 Pakistan Department of Business University of Europe for Applied Sciences Potsdam14476 Germany Faculty of Engineering and Applied Science University of Regina ReginaS4S0A2 Canada BCMaterials Basque Center for Materials Applications & Nanostructure Basque Country Leioa Spain

ISBN: (纸本)9798331504465

Maintaining the integrity of financial systems and preventing people and organizations from suffering financial losses depend heavily on the ability to spot fraudulent financial transactions. Traditional rule-based fraud detection methods have trouble identifying intricate patterns and developing fraud tactics. Machine learning approaches have become powerful fraud detection tools in recent years, utilizing the strength of data-driven models to spot fraudulent actions. The Existing rule-based fraud detection has difficulty in identifying complex patterns and evolving fraud tactics. This study thoroughly investigates the use of machine learning techniques, including decision trees and random forests, for financial transaction fraud detection, while also exploring feature engineering approaches to extract essential data from transaction records such as temporal, spatial, and relational features. In this study, real-world financial transaction datasets are used to conduct experimental evaluations, comparing the performance of various machine learning models based on accuracy, precision, recall, and F1-score. The results indicate that certain algorithms outperform others, demonstrating promising and favorable outcomes for CatBoost algorithm. This significance of our study lies in showcasing the effectiveness of machine learning techniques, compared to traditional rule-based methods, for detecting fraud in financial transactions, leading to more promising outcomes and contributing to the integrity and security of financial systems. © 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

Combining the AIML Model with Acoustic Signal to Evaluate the Bowel Sound 2

Combining the AIML Model with Acoustic Signal to Evaluate th...

引用

2nd International Conference Computational and Characterization Techniques in Engineering and sciences, IC3TES 2024

作者： Kumar Reddy, S.Pavan Sreevani, N. Revathi, V. Babu, Samuel Singh, Navdeep Kareem, Ali Narsapur Campus Hyderabad India Hyderabad India New Horizon College of Engineering Department of Applied Sciences Bangalore India Mlr Institute of Technology Department of Computer Science and Engineering Hyderabad India Lovely Professional University Phagwara India Hilla University College Babylon Iraq

ISBN: (纸本)9798350364699

Automated methods for assessing bowel sounds (BS) were well developed by the early 2000s. Several teams, using diverse analytical techniques, achieved high levels of accuracy. BS has shown potential in doing non-invasive research on irritable bowel syndrome, studying gastrointestinal motility, and performing surgical procedures. This article introduces hybrid convolution and recursive neural networks that are used for BS analysis. It was among the first deep-learning approaches to be extensively studied. An experimental workflow and a novel dataset from a contact microphone device were used to assess the results. Data were obtained at night, the most neuro gastroenterological intriguing time. Previous studies solely preserved daytime information, ignoring this period. The programme accurately detects bowel noises. In addition, they acquired good diagnostic specificity. Medical professionals confirmed the data, supporting the clinical diagnosis. Medical professionals may submit patient recordings and have them analyzed online using the client-server solution. Technologies are established, but BS research needs a consistent methodology, a worldwide venue for debate, & a free platform for data interchange, hence it is not widely employed. A common BS research framework may start with the server. © 2024 IEEE.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

Digital Sovereignty in the Era of Industry 5.0: Challenges and Opportunities

引用

Procedia computer science 2025年 254卷 108-117页

作者： Sanjay Misra Kousik Barik Petter Kvalvik Department of Applied Data Science Institute for Energy Technology Halden Norway Department of Computer Sciences Universidad de Alcalá Alcalá de Henares Madrid Spain Digital Systems Institute for Energy Technology Halden Norway

This paper examines the core concept of digital sovereignty within the Industry 5.0 framework, highlighting the importance of sovereign control over data, digital infrastructure, and digital artifacts such as algorithms, models, and visualizations. Trustworthy, autonomous, distributed architectures are essential to building resilience and independence in a multipolar world. Through a comprehensive analysis of existing literature, this paper identifies key challenges and opportunities in achieving digital sovereignty, using a PRISMA chart to select relevant studies from six databases systematically. The article offers strategic insights on extending digital technologies to ensure digital sovereignty while encouraging independent and ethical innovation. By identifying research gaps and proposing future study areas, this work aims to inspire further exploration and development in securing digital sovereignty, supporting resilient digital value chains, and advancing the goals of Industry 5.0.

关键词： Industry 5.0 Digital Sovereignty Privacy Cybersecurity AI tools

来源：评论

学校读者我要写书评

暂无评论

Spam Text Detection using Machine Learning Model

Spam Text Detection using Machine Learning Model

引用

2023 International Technical Conference on Circuits/Systems, computers, and Communications, ITC-CSCC 2023

作者： Ketcham, Mahasak Ganokratanaa, Thittaporn Pramkeaw, Patiyuth Chumuang, Narumol King Mongkut's University of Technology North Bangkok Dept. of Information Technology Management Bangkok Thailand King Mongkut's University of Technology Thonburi Applied Computer Science Program Bangkok Thailand King Mongkut's University of Technology Thonburi Media Technology Program Bangkok Thailand Dept. of Digital Media Technology Thailand

ISBN: (纸本)9798350326413

This research presents a classification between spam and non-spam messages by removing duplicate sentences or words. meaningless word and various marks The data is then classified by machine learning techniques and compared by differences between the data sets. Quantitative transformations were performed on each model to find the most efficient model. which can filter spam messages efficiently and quickly By getting the best comparison results in terms of information. quantitative conversion and model use The experimental results showed that Of all the tests, the model that performed best was Random Forest, with an average accuracy of 97 © 2023 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Challenges in Recycling Lead Acid Battery and Lithium-Ion Battery: A Comprehensive Review

Challenges in Recycling Lead Acid Battery and Lithium-Ion Ba...

引用

Smart Systems for Electrical, Electronics, Communication and computer Engineering (ICSSEECC), International Conference on

作者： S Anuradha R. Manimegalai M. Devasena Department of Computer Science PSG Institute of Technology and Applied Research Coimbatore India Global Sanitation Centre of Excellence Indian Institute of Technology Palakkad India

ISBN: (数字)9798350378177

ISBN: (纸本)9798350378184

Battery recycling has become essential due to the rising demand for batteries and the associated risk to the environment caused by the disposal of batteries in various industries. It has become a global concern to recover significant minerals and metals from discarded batteries. The rapid expansion of the electric vehicle market causes a significant challenge in managing battery waste where Lithium-ion batteries (LIBs) are used. Lithium-ion batteries are the best alternative to energy storage devices, which encourages the development of electric vehicles, which in turn reduces greenhouse gas emissions (GHG) pollution in the transportation sector. 28 % of greenhouse gas emissions and 24% of the world's energy consumption are due to the transportation industry globally. The increasing usage of LIBs can result in the accumulation of spent LIBs. To prevent improper disposal of battery waste, recycling approaches can be adopted, which can in turn help reduce landfill waste and enhance environmental quality. This study compares the difficulties of recycling Lead Acid Battery (LAB) and Lithium-Ion Battery (LIB) wastes, emphasizing the need to implement efficient battery recycling procedures towards a circular economy.

关键词： Lithium-ion batteries Lead acid batteries Wind energy Transportation industry Transportation Recycling Batteries

来源：评论

学校读者我要写书评

暂无评论

A Real-Time Privacy System for Electric Vehicles using Blockchain technology 5

A Real-Time Privacy System for Electric Vehicles using Block...

引用

5th International Conference on Information technology for Education and Development, ITED 2022

作者： Omaji, Samuel Acheme, Ijegwa David Makinde, Ayodeji Samuel Akogwu, Blessing Omojo Yahaya, Adamu Sani Alhakami, Hosam Alhakami, Wajdi Edo State University Uzairue Department of Computer Science Edo State Nigeria Advanced Research Centre SHESTCO Applied Mathematics and Simulation Abuja Nigeria Bayero University Department of Information Technology Kano Nigeria College of Computer and Information Systems Umm Al-Qura University Department of Computer Science Makkah Saudi Arabia College of Computers and Information Technology Taif University Department of Information Technology Saudi Arabia

ISBN: (纸本)9781509064229

In a vehicular energy network (VEN), an efficient transfer of energy among vehicles is realized while increasing the mobility of vehicles in a large geographic location. However, the security and privacy of vehicle owners are not fully explored in the existing literature. Today, because of the exponential rise in the number of vehicle owners in VEN, the problems of traffic congestion, energy consumption, etc., are created. The issues can be alleviated if certain information about vehicles such as the speed, energy consumption price, and location, is efficiently collected. Besides, effective communication is required for ensuring proper and authentic dissemination of traffic information among vehicles while preserving their data privacy. As a consequence, our study suggests a blockchain-based system for privacy preservation. In the proposed system, trust among vehicles is achieved using the Nash bargaining optimization method. The method is employed to maximize the payoffs of vehicles. Additionally, an improved super-increasing weighted sequence is used to preserve the privacy of vehicles by considering two essential parameters: energy consumption and price. Furthermore, the Paillier encryption mechanism is employed to securely transmit vehicles' information across the network. The proposed system has undergone a security study, which reveals that it is resistant to privacy and security-related threats. The performance of the proposed system shows that the system is efficient and reliable. © 2022 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Autonomous Electric Vehicles as Mobile Green Energy Sources

Autonomous Electric Vehicles as Mobile Green Energy Sources

引用

IEEE Workshop on High Performance Switching and Routing

作者： Xin Liu Yangming Zhao Adel Sadek Chunming Qiao School of Engineering and Applied Sciences State University of New York at Buffalo School of Computer Science and Technology University of Science and Technology of China

We envision a wide deployment of battery-operated edge devices such as data kiosk, to provide pervasive data collection and dissemination services. Although these data kiosks can be powered by green energy sources, their batteries may deplete overtime, and have to recharged frequently to prevent power outages and potential loss of critical data. In this paper, we propose an edge device recharging system using autonomous electric vehicles as Mobile Chargers (MCs). First, we determine the numbers and locations of Dispatching Centers (DCs) for these MCs, each of which will be responsible for recharging some edge devices in a surrounding area. Then, we plan optimal routes of the MCs in order to minimize the number of MCs needed to recharge all edge devices before a deadline. To reduce the time complexity involved in optimizing the routes, we cluster the edge devices and propose efficient algorithms to plan the route of MCs for each cluster based on the relaxation and rounding of a Mixed Integer Linear Programming (MILP) model. Extensive simulations show that our approach can reduce the number of MCs required to recharge all edge devices before a deadline by up to 71.93% compared with greedy-based heuristic algorithms.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A New Multi-Agent Feature Wrapper Machine Learning Approach for Heart Disease Diagnosis

引用

computers, Materials & Continua 2021年第4期67卷 51-71页

作者： Mohamed Elhoseny Mazin Abed Mohammed Salama A.Mostafa Karrar Hameed Abdulkareem Mashael S.Maashi Begonya Garcia-Zapirain Ammar Awad Mutlag Marwah Suliman Maashi Department of Computer Science College of Computer Information TechnologyAmerican University in the Emirates503000United Arab Emirates College of Computer Science and Information Technology University of AnbarRamadi31001Iraq Faculty of Computer Science and Information Technology Universiti Tun Hussein Onn MalaysiaJohor86400Malaysia College of Agriculture Al-Muthanna UniversitySamawah66001Iraq Department of Software Engineering College of Computer and Information SciencesKing Saud UniversityRiyadh11451Saudi Arabia eVIDA Lab University of DeustoBilbao48007Spain Department of Pure Science Ministry of EducationGeneral Directorate of CurriculaBaghdadIraq Department of Medical Laboratory Science Faculty of Applied Medical ScienceKing Abdulaziz UniversityJeddah21589Saudi Arabia

Heart disease(HD)is a serious widespread life-threatening *** heart of patients with HD fails to pump sufcient amounts of blood to the entire *** the occurrence of HD early and efciently may prevent the manifestation of the debilitating effects of this disease and aid in its effective *** methods for diagnosing HD are sometimes unreliable and insufcient in analyzing the related *** an alternative,noninvasive medical procedures based on machine learning(ML)methods provide reliable HD diagnosis and efcient prediction of HD ***,the existing models of automated ML-based HD diagnostic methods cannot satisfy clinical evaluation criteria because of their inability to recognize anomalies in extracted symptoms represented as classication features from patients with *** this study,we propose an automated heart disease diagnosis(AHDD)system that integrates a binary convolutional neural network(CNN)with a new multi-agent feature wrapper(MAFW)*** MAFW model consists of four software agents that operate a genetic algorithm(GA),a support vector machine(SVM),and Naïve Bayes(NB).The agents instruct the GA to perform a global search on HD features and adjust the weights of SVM and BN during initial classication.A nal tuning to CNN is then performed to ensure that the best set of features are included in HD *** CNN consists of ve layers that categorize patients as healthy or with HD according to the analysis of optimized HD *** evaluate the classication performance of the proposed AHDD system via 12 common ML techniques and conventional CNN models by using across-validation technique and by assessing six evaluation *** AHDD system achieves the highest accuracy of 90.1%,whereas the other ML and conventional CNN models attain only 72.3%–83.8%accuracy on ***,the AHDD system proposed herein has the highest capability to identify patients with *** system can be used by medical

关键词： Heart disease machine learning multi-agent feature wrapper model heart disease diagnosis HD cleveland datasets convolutional neural network

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：