检索结果-内蒙古大学图书馆

EFFECTS OF CUTTING AND WELDING ON ELECTRIC STEELS' FERROMAGNETIC MATERIAL

EFFECTS OF CUTTING AND WELDING ON ELECTRIC STEELS' FERROMAGN...

2024 International Conference on Sustainable Computing and Integrated Communication in Changing Landscape of ai, ICSCai 2024

作者： Agarhari, Abishek Singh, Thakur Meenu Balaji, N.V. Arul Antran Vijay, S. Borade, Monali Ravindra Department of Computer Science & Engineering Invertis University Uttar Pradesh Bareilly243123 India School of Mechenical Engineering Dev Bhoomi Uttarakhand University Uttarakhand 248007 India Department of Computer Science & Engineering School of Engineering & Technology K. R. Mangalam University Haryana Gurugram122103 India Department of Computer Science Karpagam Academy of Higher Education Coimbatore641021 India Department of Computer Science Engineering Karpagam College of Engineering Coimbatore641032 India AI & Ds Vishwakarma Institute of Information Technology Pune India

ISBN: (纸本)9798350355338

This study examines the crucial function that silicon steels, sometimes referred to as electric steels, serve in electromagnetic applications like transformers and motors. The need of preserving ferromagnetic characteristics for effective energy exchange is emphasized in particular. In order to fill in knowledge gaps about the precise effects of the two processes on these materials, this investigation presents a methodology that emphasizes the significance of careful material selection, thorough recording of the cutting and welding procedures, and an organized method of measurement and *** study recognizes the broad implications for industrial, power distribution, and automotive sectors, where ferromagnetic properties are necessary for electrical equipment to remain reliable. The study attempts to provide understanding of the unique effects of the two processes on electric steels, suggesting mitigating measures via a thorough analysis of the body of current literature. The transparent and reproducible technique presented in this study contributes to our knowledge of how electric steels behave in various contexts. The ultimate goal of the study is to improve production methods and guarantee that electromagnetic gear operates as well it can in our environment of growing electricity. © 2024 IEEE.

关键词： Automotive industry

来源：评论

学校读者我要写书评

暂无评论

Predictive Maintenance Model Using Hybrid Procedure of Improved Quantum Cat Swarm Optimisation for Asset Management in Industry 4.0

Predictive Maintenance Model Using Hybrid Procedure of Impro...

引用

International Conference on Data Analytics and Management, ICDAM 2023

作者： Kanchana, S. Rajan, Dhivya Mahaveerakannan, R. Sagar, K. V. Daya Subramanian, P. Rajakumar, B. Department of Computer Science Faculty of Science and Humanities SRM Institute of Science and Technology Tamil Nadu Kattankulathur603203 India Department of Computer Applications CMR Institute of Technology Bengaluru India Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Tamil Nadu Chennai India Department of Electronics and Computer Engineering Koneru Lakshmaiah Education Foundation Andhra Pradesh Vaddeswaram India Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai India Department of AI & DS JNN Institute of Engineering Chennai Periyapalayam Highway Tamil Nadu Thiruvallur601102 India

ISBN: (纸本)9789819965465

Contemporary manufacturing system design centres on the Industry 4.0 paradigm. A versatile platform secondary the efficient optimisation of manufacturing-related activities, such as predictive keep, is necessary for the successful mixing of cutting-edge technologies like the (IoT), cyber-physical schemes, computing. Predictive maintenance research that already exists often either develops a model without taking maintenance decisions into account or seeks to optimise maintenance in the light of the degradation replicas of the already-known scheme. With the use of predictive maintenance, a company's owner can make decisions like fixing or replacing a failing part of the manufacturing line before it actually fails. Because of this, Industry 4.0 necessitates efficient asset management in order to maximise the distribution of duties and the accuracy of predictive maintenance models. To address the issue of predictive maintenance in fog computing, this paper proposes an enhanced version of the quantum cat swarm optimisation (QCSO) algorithm by combining the quantum bit (Q-bit) and the cat swarm procedure (CSO) and updating the cats based on the quantum rotation angle site. Finally, the (MR) worth is chosen based on the sum of times the procedure is run. FogWorkflowsim uses simulated real-time datasets to evaluate the forecasting performance of QCSO and other existing models. The outcomes prove that the projected method is superior to the currently used predictive maintenance resource allocation methods. In comparison to the approximately 91% to 95% accuracy achieved by previous models, the proposed model has an accuracy of 96%, respectively. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2024.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Lightweight Meta-Learning BotNet Attack Detection

引用

IEEE Internet of Things Journal 2023年第10期10卷 8455-8466页

作者： Fadhilla, Cut Alna Alfikri, Muhammad Dany Kaliski, Rafael National Taiwan University of Science and Technology Department of Computer Science and Information Engineering Taipei106 Taiwan Wiz.AI Central Region Singapore Singapore National Sun Yat-sen University Department of Electrical Engineering Kaohsiung804 Taiwan

Modern society is increasingly dependent on numerous Internet of Things (IoT) devices to assist in a variety of scenarios, such as smart homes and cities, healthcare systems, and cyber-physical systems. Despite IoT's increasing popularity, IoT security remains a challenge due to the multitude of attack vectors. Existing cyber-attack defense methods attempt to protect the network from both within and outside the network. Network intrusion detection systems (NIDSs) act as device borders within network security and offer a potential defense methodology. This research analyzes the performance of an Artificial Intelligent Internet of Things (aioT) lightweight botnet attack detection model by deploying meta-learning ensemble botnet detection models and evaluates the capability of a single-board system in addressing cyber-attack threats. The Aposemat IoT-23 [1], UC Irvine KDD99 [2], and UNSW TON [3] data sets provide IoT and network traffic network flow captures which are used to evaluate the proposed meta-learning methodologies. Experiments show that deployment of our proposed methodologies on edge devices exhibits similar results to PC-based Desktop CPU-trained models. Over the three data sets, when considering a binary classifier (benign versus malignant), our models can consistently achieve above 97.9% accuracy with a false positive rate (FPR) less than 3.8% and an inference time less than 3.95 s. In this work, we show that for binary classification our meta-learners provide consistently stable high accuracy low FPR performance across all three data sets, while maintaining reasonable inference times. © 2014 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Learning for Optimizing Route Planning in Urban Traffic

Deep Reinforcement Learning for Optimizing Route Planning in...

引用

Computational, Communication and Information Technology (ICCCIT), International Conference on

作者： Mudit Mittal Archana Sehgal Neeraj Varshney Sunil Prashanth Kumar Nandini Shirish Boob R. Akhilesh Reddy Department of Computer Science & Engineering Graphic Era Deemed to be University Dehradun Lovely Professional University Phagwara Department of Computer Engineering and Applications GLA University Mathura Department of Mechanical Engineering New Horizon College of Engineering Bangalore Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai Tamilnadu Department of CSE-AI&ML MLR Institute of Technology Hyderabad Telangana

ISBN: (数字)9798331512965

ISBN: (纸本)9798331512972

Urban traffic networks are efficient route design problems due to the intricacy and dynamic character of contemporary cities. Conventional methods hamper real time adjustment to continually changing traffic conditions, thereby providing suboptimal routes, a greater burden on the roadways, and greater air pollution. This thesis presents a novel deep reinforcement learning (DRL) method to optimize the route planning for urban traffic networks. With this rendering of real time traffic data, we use DRL to make autonomous decisions to reduce travel time and congestion of routes. One advantage of using sophisticated neural networks for feature extraction and policy learning is that, since the model is so adaptable to changing traffic patterns, the model guarantees that. And, in comparison to common routing algorithms, the results of simulations using real world traffic data show that this method is able to greatly enhance route efficiency and overall traffic flow management. The suggested DRL based system is feasible as a smart city program based on intelligent transportation system which can scale to grand metropolitan regions. The research presents that DRL can enhance the commuter run experience, reduce the environmental effect, and alter urban transportation. Future study will also investigate how this system can be better optimized when integrated with traffic infrastructure enabled by the Internet of Things.

关键词： Adaptation models Smart cities Computational modeling Scalability Transportation Traffic control Deep reinforcement learning Real-time systems Planning Internet of Things

来源：评论

学校读者我要写书评

暂无评论

A Conceptual Evaluation of the Data as Partner (DAP) Framework 9

A Conceptual Evaluation of the Data as Partner (DAP) Framewo...

引用

9th IEEE International Smart Cities Conference, ISC2 2023

作者： Hassan, Sonia Sobnath, Drishty Snell, Esther Isiaq, Olufemi Solent University Department of Science and Engineering Southampton United Kingdom Creative Computing Institute Universiy of Arts Department of Computer and Data Science and Ai United Kingdom

ISBN: (纸本)9798350397758

This paper explores the innovative Data As Partner (DAP) philosophy as a transformative approach to organisational data strategy, drawing upon established concepts of information value, technology acceptance, and inclusivity for people with disabilities (PwD) in smart cities. The study conducted a comprehensive systematic review, after meticulous screening, 20 eligible papers were selected, forming the foundation for deriving the key components of the DAP framework. Subsequently, a qualitative focus group study engaged 18 participants from diverse sectors to evaluate the practical applicability of the DAP conceptual framework. Thematic analysis of the focus group sessions revealed five key themes: practical value, pragmatic performance, ethical perspective, clarity of the framework, and enhancement tools. These findings offer valuable insights for refining the DAP framework and optimising its integration into real-world scenarios, in empowering individuals in smart cities, especially those with disabilities. Future research should explore larger and more diverse samples to generalise findings and assess the framework's long-term impact through longitudinal evaluations. By adopting user-centred methodologies, the DAP framework can be further enhanced as a strategic tool, empowering data to actively participate in organisational decision-making processes. © 2023 IEEE.

关键词： Smart city

来源：评论

学校读者我要写书评

暂无评论

Noise2Seg: Automatic Few-Shot Selection from Noisy Web Data for Underwater Tropical Fishes Segmentation

Noise2Seg: Automatic Few-Shot Selection from Noisy Web Data ...

引用

2023 International Symposium on Networks, computers and Communications, ISNCC 2023

作者： Gilal, Nauman Ullah Majeed, Fahad Al-Thelaya, Khaled Khan, Mehak Schneider, Jens Agus, Marco College of Science and Engineering Hamad Bin Khalifa University Doha Qatar Oslo Metropolitan University AI Lab Department of Computer Science Norway

ISBN: (纸本)9798350335590

We present a novel automatic few-shot selection (FSS) approach with a noisy web-collected dataset for underwater tropical fishes. Underwater image segmentation is of utmost importance in marine biology and underwater robotics. However, obtaining high-quality annotated underwater images is a challenging task due to the scarcity of underwater imaging systems and the high cost of data acquisition. Alternatively, web data is a readily available source of images, but it frequently contains web-corrupted noisy labels, making it challenging to curate a clean dataset for underwater tropical fish segmentation. Generally, the manual selection of high-quality images from web data requires human supervision and expert proofreading, which is both expensive and time-consuming. To address this issue, we propose Noise2Seg, an automatic processing framework composed by: (i) an automated web scrapping tool, (ii) a robust and automatic FSS process using a loss ranking scheme;(iii) a manual annotation component using 'Roboflow', (iv) the latest You Only Look Once version 8 (YOLOv8) for underwater fish detection and segmentation. Additionally, we curated and annotated a novel dataset for the segmentation of tropical fishes from Qatar marine ecosystem (Qatar Tropical Fishes-10 QTF-10). We compared the performance of manual and automatic FSS using mean average precision (mAP) score;manual FSS achieved all mAP (91.5%, 93.4%), and minimum mAP (19.5%, 54.8%), while automatic FSS achieved all mAP (92%, 99.5%), and minimum mAP (24.9%, 99.5%) with 5 and 10 images per class, respectively. The code and dataset related to this paper can be found on GitHub11https://***/GilalNauman/Automatic-Few-shot-Selction-ISNCC/tree/main, accessed on 1st of March 2023. © 2023 IEEE.

关键词： Fish

来源：评论

学校读者我要写书评

暂无评论

Secure and fast mobility handover scheme for IoMT in 5 G and future 6 G networks

引用

Alexandria engineering Journal 2025年 128卷 127-143页

作者： Islam, Shayla Topazal, S.M. Hasan, Mohammad Kamrul Kolandaisamy, Raenu AL Abbas, Huda Saleh Vo, Nguyen Thakkar, Rahul Khan, Muhammad Attique Gupta, Deepak AlHammadi, Dina Abdulaziz Institute of Computer Science and Digital Innovation UCSI University Kuala Lumpur56000 Malaysia Center for Cyber Security Faculty of Information Science and Technology the National University of Malaysia Selangor Bangi43600 Malaysia Department of computer science College of Computer Science and Engineering Taibah University Madina Saudi Arabia Victorian Institute of Technology Melbourne Australia Center of AI College of Computer Engineering and Science Prince Mohammad Bin Fahd University Al-Khobar Saudi Arabia Maharaja Agrasen Institute of Technology Delhi India Department of Information Systems College of Computer and Information Sciences Princess Nourah bint Abdulrahman University P.O.Box 84428 Riyadh11671 Saudi Arabia

The emergence of 5 G and 6 G networks promises significant advancements in the Internet of Medical Things (IoMT) by enabling real-time medical data transmission and continuous connectivity for mobile healthcare devices. However, traditional Handover (HO) mechanisms face latency, security, energy consumption, and scalability challenges when supporting fast-moving and dense IoMT environments. This paper presents a secure and fast mobility handover scheme for IoMT in 5 G and future 6 G networks, incorporating a predictive algorithm, Blockchain-Based (BC-B) decentralized authentication mechanism, and ai-driven anomaly detection. The predictive algorithm anticipates device movement and pre-allocates resources at the target Base Station (BS), reducing HO latency by 20–30 % in 5 G and up to 40 % in 6 G. Meanwhile, blockchain-based authentication ensures tamper-proof and decentralized security, reducing vulnerability to cyberattacks by 90 % compared to traditional methods. Additionally, the energy consumption during HO events is reduced by 20–35 %, dropping from 15 mJ in traditional schemes to 12 mJ in 5 G and further to 10 mJ in 6 G. The scheme also incorporates ai-driven anomaly detection, achieving an accuracy of 96.7 %, ensuring proactive identification and mitigation of potential security threats. The analyzed scheme maintains consistent throughput with less than 5 % reduction and scales effectively for up to 300 devices per cell. The simulation results demonstrate significant improvements across key performance metrics, including latency, security, energy efficiency, and scalability, making this approach highly suitable for critical IoMT applications such as telesurgery, remote patient monitoring, and innovative healthcare environments. These advancements position the analyzed framework as a cornerstone for next-generation (NG) healthcare networks. © 2025 The Authors

关键词： Remote patient monitoring

来源：评论

学校读者我要写书评

暂无评论

Optimizing Tomato Leaf Disease Detection through Transfer Learning and Model Compression: A Comprehensive Survey 4

Optimizing Tomato Leaf Disease Detection through Transfer Le...

引用

4th International Conference on Advancement in Electronics and Communication engineering, AECE 2024

作者： Devi, G.Uma Yamsani, Nagendar Perla, Someswari Maram, Balajee Maram, Rohan Raj Kumar, Pinnamraju Veeresh University of Engineering and Management Computer Science and Engineering Department Jaipur India Sr University School of Computer Science and Artificial Intelligence Warangal India Gmr Institute of Technology Department of Cseai&ml Andhra Pradesh Rajam India Sr University School of Computer Science and Artificial Intelligence Telangana Warangal506371 India Chitkara University Becse HP Baddi India K K R and K S R Institute of Technology and Sciences Computer Science Engineering India

ISBN: (纸本)9798350364729

Maximise Tomato Leaf Disease Detection by Synergistic Model Compression Techniques and Transfer Learning. Basically, it is true that as technology continues to be integrated into agriculture, methods for identifying diseases have become accurate and reliable for the management of crops. The two main such approaches that have evolved are model compression, which reduces the processing requirements of deep neural network models, and transfer learning, which reuses already pretrained models. This work investigates the impact of different transfer learning strategies on model performance and efficiency. It explains the key fundamentals of transfer learning with regard to the tomato leaf disease detection application domain and covers different kinds of pretrained models. It investigates the application of model compression techniques, such as quantization, pruning, and knowledge distillation, and provides their impact on agricultural image analysis optimization. This survey is going to put forward common challenges, clarify the pros and cons of various methods, and offer reallife examples or success stories through a comparative review of prior work. © 2024 IEEE.

关键词： Fruits

来源：评论

学校读者我要写书评

暂无评论

Agriculture Crop Recommendation System Using Machine learning 2

Agriculture Crop Recommendation System Using Machine learnin...

引用

2nd International Conference on Advancements in Smart, Secure and Intelligent Computing, ASSIC 2024

作者： Allam, Sangeetha Manjusha, Bollimuntha Vuyyuru, Asha Veeranjaneyulu, P. Rani, K. Pushpa Mishra, Sushruta Mlr Institute of Technology Department of Computer Science & Engineering Hyderabad India Hyderabad India and Ai&ds Hyderabad India Mlr Institute of Technology Department of Computer Science and Engineering Hyderabad Dundigal500043 India Kalinga Institute of Industrial Technology Deemed to Be University India

ISBN: (纸本)9798350370188

India's socioeconomic system is mostly dependent on agriculture. Farmers used to rely on word-of-mouth, but the current climate prevents them from doing so. The IT industry has grown in order to provide farmers with precise agricultural information, which has resulted in several advancements in the field of agriculture sciences. In the current climate, having access to contemporary technologies for agriculture is desirable. [1] Using machine learning methods, it is feasible to make predictions and create a precise model from the data. There are solutions for agricultural problems such crop rotation, crop forecasts, water and fertilizer needs, and crop protection. Due to the environment's unpredictable climatic elements, an effective method is required to expedite crop cultivation and support farmers in their production and management. It's possible that aspiring farmers can now engage in improved agriculture. [2] A farmer can receive a number of recommendations to aid with crop yield. Based on the properties of the soil, the timing of the sowing, and the location, farmers occasionally choose the incorrect crops. [3]Many as a result commit suicide, stop farming, and go to cities in search of employment. By taking into account all relevant aspects, including the planting season, soil, and geographic location, this research effort has developed a method to assist farmers in choosing crops. Following a careful review of crop data gathering, crop recommendations were given. © 2024 IEEE.

关键词： Crops

来源：评论

学校读者我要写书评

暂无评论

An Efficient Wafer Semiconductor Surface Defect Inspection Using Radial Basis Functional Neural Network 2

An Efficient Wafer Semiconductor Surface Defect Inspection U...

引用

2nd International Conference on Data science and Information System, ICDSIS 2024

作者： Dineshkumar, R. Kumar, Komuravelly Sudheer Murugan, Chitra Al-Fatlawy, Ramy Riad Harshitha, P. Saveetha Institute Of Medical And Technical Sciences Saveetha University Saveetha School Of Engineering Department Of Ece Chennai India Sr University School Of Computer Science & Artificial Intelligence Telangana Warangal India Rajalakshmi Institute Of Technology Department Of Electronics And Communication Engineering Chennai India The Islamic University College Of Technical Engineering Department Of Computers Techniques Engineering Najaf Iraq Nitte Menashaki Institute Of Technology Department Of Ai Ml Bengaluru India

ISBN: (纸本)9798350381665

Semiconductor wafer discoveries widespread application in unmanned material delivery vehicles, repairing robots, spray androids, and recognition station sensors. the semiconductor cracker's flaws, such as holes, husks, cuts, and stains that are created during the production process have a negative impact on the quality of products that are produced later. As a result, it was authoritative to inspect wafer defects. Conventional techniques for inspecting semiconductor wafer defects that rely on handcrafted features are limited in some application scenarios and strongly dependent on experience. This research proposes a unique approach for semiconductor wafer surface defect inspection using deep convolutional neural networks. Initially, in order to excerpt features and create feature maps, a innovative structure for feature pyramid networks with atrous convolution (FPNAC) is designed. Secondly, region proposals are generated by feeding the feature plots into the region proposal network (RPN). In order to correctly categorize and segment the flaws, the region recommendations are finally associated to matching size by way of the inputs of a Radial Basis Functional Neural Network (RBFNN), which consists of three branches. The suggested RBFNN produces good overall performance, as evidenced by the experimental findings, which show Mean Intersection over Union (MIoU) of 90.06% and Mean Pixel Accuracy (MPA) of 94.97%. © 2024 IEEE.

关键词： Convolution

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：