检索结果-内蒙古大学图书馆

3rd International Conference on Smart Generation Computing, Communication and Networking, SMART GENCON 2023

作者： Sahoo, Girija Shankar Sekaran, Ramesh Renuka, G. Dhabliya, Dharmesh Faujdar, Pramod Kumar Minhas, Deepak Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh India Faculty of Engineering and Technology Department of Computer Science and Engineering Karnataka Ramnagar562112 India Prince Shri Venkateshwara Padmavathy Engineering College Department of Electronics and Communication Engineering Chennai127 India Vishwakarma Institute of Information Technology Department of Information Technology Maharashtra Pune India Vivekananda Global University Department of Mechanical Engineering Jaipur India Chitkara University Institute of Engineering and Technology Chitkara University Centre of Interdisciplinary Research in Business and Technology Punjab India

ISBN: (纸本)9798350319125

This studies focuses on leveraging self-sustaining deep getting to know techniques for real-time records analysis in device getting to know. We propose a machine this is enabled by means of artificial intelligence to streamline the technique of extracting significant insights from sensor-based records. Our approach considers two middle components: interpreting data with recurrent neural networks and deploying a mastering agent to routinely whole the statistics analysis process. The getting to know agent's training is based on supervised mastering, enabling it to discover and traverse styles inside the information. The recurrent neural community (RNN) offers the functionality to seize temporal styles within the information, with its capacity to make predictions based on previous input. As a result, our system can produce fairly correct insights with minimal human intervention. This makes it suitable for time-sensitive information analysis situations in the industrial area in which decisions have to be taken in actual-time. © 2023 IEEE.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Resource Provisioning in Cloud Computing using Fuzzy Logic Control System: An adaptive approach 2

Resource Provisioning in Cloud Computing using Fuzzy Logic C...

引用

2nd International Conference on Business Analytics for Technology and Security, ICBATS 2023

作者： Alnawayseh, Saif. E. A. Muhammad, Muhammad Hassan Ghulam Hassan, Zahid Fatima, Mayraj Aslam, Muhammad Shoukat Ibrahim, Amer Ateeq, Karamath Mutah Univesity Faculty of Engineering Electrical Engineering Department Jordan NCBA&E School of Computer Science Lahore Pakistan Applied Science Private University Applied Science Research Center Amman11937 Jordan PMAS-Arid Agriculture University Rawalpindi Pakistan American University in Th Emirates College of Computer and Information Technology Dubai United Arab Emirates Skyline University BSIT Faculty Sharjah United Arab Emirates

ISBN: (纸本)9798350335644

The need for cloud computing has been increasing widely in this era since last two decades due to its continual benefits include security, disaster recovery, increased collaboration, cost saving and virtualization etc. This innovation introduces an enormous transformation of conventional applications in business industry. However, cloud users indulge themselves not acquiring a sufficient amount of computing resources caused by resource confliction. A challenging and significant problem in cloud computing is Resource Provisioning in virtualization environment that relates with selecting, deploying and run time management of software and hardware resources. On the contrary, such situations also exist where resources are found in virtual servers either under or over-utilization. In order to deal with these problems, proposed framework in this paper is demonstrated using Fuzzy Logic Control System towards characterization the processes' priorities by means of employing input parameters (workload, processing time, and process age) keeping in view of the fact that expert judgment is required for taking into account these parameters. © 2023 IEEE.

关键词： Virtualization

来源：评论

学校读者我要写书评

暂无评论

Exploring Large Scale Docker Image Vulnerability and Storage Performance Analysis Using High Performance Container-Based Docker Environment

Exploring Large Scale Docker Image Vulnerability and Storage...

引用

IEEE International Conference on System, Computation, Automation and Networking (ICSCAN)

作者： Kavya Sri. B K. Mahalakshmi Faculty of Information and Communication Engineering Anna university Chennai Department of Computer Science and Engineering KIT - Kalaignarkarunanidhi Institute of Technology Coimbatore India

ISBN: (数字)9798331510022

ISBN: (纸本)9798331510039

In modern cloud environments, Docker containers have become a cornerstone for efficient application deployment, enabling microservices architectures and seamless scalability. However, large-scale Docker environments present significant challenges, particularly in terms of security vulnerabilities and storage performance. This paper explores vulnerability analysis and storage performance optimization in high-performance, container-based Docker environments. Docker swarm is a container orchestration platform which could be very useful for maintaining the docker containers at scale even at distributed environment, these tools also provide us a great features for managing the rolling updates and health check in the lifecycle of containers. We perform a comprehensive evaluation of Docker image vulnerabilities using automated scanning tools, assessing common vulnerabilities and exposures (CVEs) across large image repositories. Additionally, we investigate storage performance bottlenecks and analyse the impact of various storage drivers on container efficiency. Our findings offer critical insights into balancing performance and security in high-scale Docker deployments, proposing strategies for mitigating risks and enhancing resource management. The results guide container orchestration decisions for enterprises aiming to deploy secure, high-performance systems.

关键词： Performance evaluation Runtime Scalability Containers Software Security Image storage Resource management Optimization Secure storage

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Review of Large Language Models in Abstractive Summarization of News Articles

A Comprehensive Review of Large Language Models in Abstracti...

引用

Innovation in Technology (APCIT), Asia Pacific Conference on

作者： Bharathi Mohan G Akashvarma M Yashaswini G Keerthana E Siddharth S Saipooja K Prasanna Kumar G Srinath Doss Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Chennai Faculty of Engineering and Technology Botho University Botswana

ISBN: (数字)9798350361537

ISBN: (纸本)9798350361544

Recent years have seen significant advancements in Large Language Models (LLMs), particularly in their application to natural language processing tasks. One prominent application is the abstractive summarization of news articles, a process that distills extensive textual information into a succinct yet comprehensive representation. The significance of this task lies in its capacity to efficiently distill key information. This paper focuses on evaluating the performance of various LLMs—Llama-2-7b, T5, Bart, and Pegasus—specifically fine-tuned on the CNN Daily dataset of news articles. QLoRA and Prompt-Based Fine-Tuning Approaches are employed systematically to compare the efficacy of these models in generating summaries that capture the essence of news articles. Evaluation metrics, including ROUGE, BLEU, and cosine similarity, are utilized to assess summarization quality. The findings reveal distinctive results among the selected LLMs such that Llama-2 excels in ROUGE-1 and ROUGE-L with scoreS of 0.45 and 0.427, Pegasus demonstrates remarkable performance in ROUGE-2 and cosine similarity with scores 0.19 and 0.6 respectively.

关键词： Measurement Technological innovation Reviews Large language models Asia Natural language processing

来源：评论

学校读者我要写书评

暂无评论

Depth Estimation with Tilted Optics Using Split Color Filter Aperture

Depth Estimation with Tilted Optics Using Split Color Filter...

引用

Electrical, computer and Energy Technologies (ICECET), International Conference on

作者： Aoi Fukino Hiroshi Ikeoka Takavuki Hamamoto Information Processing Engineering Course Graduate School of Engineering Fukuyama University Hiroshima Japan Department of Computer Science Faculty of Engineering Fukuyama University Hiroshima Japan

ISBN: (数字)9798350395914

ISBN: (纸本)9798350395921

Camera-based depth estimation methods are useful for various automobile applications. For example, depth estimation methods based on stereo cameras triangulate the depth between objects and cameras. However, they are susceptible to baseline distortion owing to vibrations, aging, and thermal expansion. On the contrary, depth estimation methods based on a monocular camera, such as depth-from-defocus, use a focusing mechanism or spectroscopic optics to calculate the depth from the difference of defocus images. However, because the change in sharpness, which is the inverse of defocus, is slightly in the depth direction, it is unsuitable for deep-range estimation. Therefore, we are developing depth-estimation methods that use a monocular camera with special focus images obtained through tilted optics, which have no baseline distortion problem and have a deep estimation range. When tilted optics are used, the plane of sharp focus (POF) appears tilted, while the depth of field (DOF) lies and increases toward the depth direction. Moreover, to allow for the use of only one image-sensor, a one-shot, we studied a depth estimation method using tilted optics with two different aperture sizes for each color wavelength by introducing concentric color filter apertures. However, as with conventional methods, the Gaussian sharpness model does not strictly fit to the actual sharpness, resulting in reduced estimation accuracy. In this study, we propose a method for high-speed and high-accuracy depth estimation that involves adding a split color filter aperture to a tilted optic and using a different sharpness model for each DOF side.

关键词： Optical filters Image color analysis Computational modeling Estimation Optical distortion Apertures Optics Cameras Distortion Automobiles

来源：评论

学校读者我要写书评

暂无评论

Modernizing The Shopping Experience: The Smart Shopping Cart

Modernizing The Shopping Experience: The Smart Shopping Cart

引用

International Conference on engineering Technology and their Applications (IICETA)

作者： Aboothar Mahmood Shakir Yousif Mudhafar Abbas M. Ali Al-muqarm Computer Techniques Engineering Department College of Technical Engineering The Islamic University Najaf Iraq Department of Computer Science Faculty of Computer Science and Mathematics University of Kufa Najaf Iraq

The holiday season brings out the crowds at shopping centers in major cities. When there are substantial savings to be obtained, this becomes even more true. People today often fill their shopping carts with a wide selection of products. Once a customer has finished shopping, he or she should head to the counter to settle the payment. It takes time for the cashier to create the bill using a barcode scanner. Because of this, there are often substantial wait times at the cash registers. This project proposes a solution for retail centers to address the issues mentioned above. This might be accomplished by installing RFID tags on all mall merchandise and retrofitting all shopping carts with a radio-frequency identification reader and a liquid crystal display. Any item placed in the shopping cart will have its barcode scanned automatically, and the trolley's digital signboard will update to show the item's name and price. When an item is removed from a shopping cart, its cost is subtracted from the grand total, and the relevant data is transmitted to the central billing unit through radio-frequency (RF) modules. Customers may save a ton of time since billing can be done right on the tram. The researchers worked on developing a shopping cart, which is smart, and this system allows for faster checkout and payment of the bill in a secure manner, and the adoption of technology in the store increases the demand for it continuously, the computer will remember the barcode data you enter and compare it to its database, from which it will get the necessary data. The database and RF model will be connected through software. Small radio-frequency (RF) electrical modules called a “transmitter” and “receiver” can be used to transmit and receive signals between any two devices. The data is sent from the transmitter module to the receiver module, which then processes the data. The group believes that the intelligent shopping cart will result in a more dependable checkout procedure and

关键词：

来源：评论

学校读者我要写书评

暂无评论

Traffic Queuing Management in the Internet of Things: An Optimized RED Algorithm Based Approach

引用

computers, Materials & Continua 2021年第1期66卷 359-372页

作者： Abdul Waheed Naila Habib Khan Mahdi Zareei Shahab Ul Islam Latif Jan Arif Iqbal Umar Ehab Mahmoud Mohamed Department of Information Technology Hazara UniversityMansehra21120Pakistan School of Electrical and Computer Engineering Seoul National UniversitySeoul08826Korea Department of Computer Science Institute of Management SciencesPeshawar25000Pakistan Tecnologico de Monterrey School of Engineering and SciencesZapopan45201Mexico Department of Computer Science IQRA National UniversityPeshawar25124Pakistan Department of Electrical Engineering University of Engineering TechnologyPeshawar25120Pakistan Electrical Engineering Department College of EngineeringPrince Sattam Bin Abdulaziz UniversityWadi Addwasir11991Saudi Arabia Electrical Engineering Department Faculty of EngineeringAswan UniversityAswan81542Egypt

Congestion control is one of the main obstacles in cyberspace *** in internet traffic may cause several problems;such as high packet hold-up,high packet dropping,and low packet *** the course of data transmission for various applications in the Internet of things,such problems are usually generated relative to the *** tackle such problems,this paper presents an analytical model using an optimized Random Early Detection(RED)algorithm-based approach for internet traffic *** validity of the proposed model is checked through extensive simulation-based *** analysis is observed for different functions on internet *** performance metrics are taken into consideration,namely,the possibility of packet loss,throughput,mean queue length and mean queue *** sets of experiments are observed with varying simulation *** experiments are thoroughly analyzed and the best packet dropping operation with minimum packet loss is identified using the proposed model.

关键词： Random early detection(RED) active queue management(AQM) quality of service(QOS) throughput

来源：评论

学校读者我要写书评

暂无评论

Retraction Note: A Systematic Survey on Implementation of Fuzzy Regression Models for Real Life Applications

引用

Archives of Computational Methods in engineering 2025年 1-2页

作者： Khan, Mufala Kumar, Rakesh Aledaily, Arwa N. Kariri, Elham Viriyasitavat, Wattana Yadav, Kusum Dhiman, Gaurav Kaur, Amandeep Sharma, Ashutosh Vimal, S. Department of Mathematics Lovely Professional University Phagwara India College of Computer Science and Engineering University of Ha’il Hail Saudi Arabia College of Computer Science and Engineering Prince Sattam Bin Abdulaziz University Al‑Kharj Saudi Arabia Business Information Technology Division Department of Statistics Faculty of Commerce and Accountancy Chulalongkorn University Bangkok Thailand Department of Computer Science Government Bikram College of Commerce Patiala India Department of Electrical and Computer Engineering Lebanese American University Byblos Lebanon University Centre for Research and Development Department of Computer Science and Engineering Chandigarh University Gharuan India Department of Computer Science and Engineering Graphic Era Deemed to be University Dehradun India Chitkara University Institute of Engineering and Technology Chitkara University Rajpura India School of Computer Science University of Petroleum and Energy Studies Dehradun India Department of Artificial Intelligence and Data Science Ramco Institute of Technology Rajaplayam India

来源：评论

学校读者我要写书评

暂无评论

Multipath Routing Strategies for End-to-End Traffic Management in Underwater High Speed Networks 3

Multipath Routing Strategies for End-to-End Traffic Manageme...

引用

3rd International Conference on Smart Generation Computing, Communication and Networking, SMART GENCON 2023

作者： Singh, Akhilendra Pratap Srisathirapathy, S. Dhabliya, Dharmesh Kaur, Ashmeet Mamatha, G.N. Seth, Jyoti Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh India Prince Shri Venkateshwara Padmavathy Engineering College Department of Mechanical Engineering Chennai127 India Vishwakarma Institute of Information Technology Department of Information Technology Maharashtra Pune India Chitkara University Institute of Engineering and Technology Chitkara University Centre of Interdisciplinary Research in Business and Technology Punjab India Faculty of Engineering and Technology Department of Electronics and Communication Engineering Karnataka Bangalore India Vivekananda Global University Department of Computer Science & Engineering Jaipur India

ISBN: (纸本)9798350319125

Underwater high-speed networks (HSN s) use several environmental, operational, and technical demanding situations, making their layout and efficient operation challenging. The underwater medium introduces variabilities on the acoustic channels that, in turn, increase the complexity of the routing and site visitors' control. Multipath routing has been proposed to manage agile, nice-grain, and actual-time cease-to-end visitors in these networks. This painting provides and evaluates several multipath routing techniques for excessive velocity Underwater Networks (HSUN s), The proposed algorithms originate from direction Vector protocols and think about link metrics, hop to be counted, put-off jitter, packet loss fee, and other applicable parameters. We examine the performance of the proposed multipath routing strategies, based totally on the standard packet put-off, packet loss fee, and jitter average in a large-scale natural experiment carried out using acoustic modems underneath controlled channel conditions in an underwater tunnel. The experiment results show vast enhancements in the performance of the network when compared to single-route routing. Furthermore, the effects display the strong effect of the multipath routing techniques on the community's overall performance. In step with the acquired outcomes, the offered multipath routing techniques may be increased and used to enhance the throughput and first-rate service of excessive-velocity underwater networks. © 2023 IEEE.

关键词： controlled demonstrate experiment improvements performance

来源：评论

学校读者我要写书评

暂无评论

Privacy-Secure and Decentralized Biometric Authentication Models Using Federated Learning Frameworks

Privacy-Secure and Decentralized Biometric Authentication Mo...

引用

IEEE International Conference on System, Computation, Automation and Networking (ICSCAN)

作者： Mathivanan. P K. Mahalakshmi Faculty of Information and Communication Engineering Anna university Chennai Department of Computer Science and Engineering KIT - Kalaignarkarunanidhi Institute of Technology Coimbatore India

ISBN: (数字)9798331510022

ISBN: (纸本)9798331510039

A biometric identifier, in contrast to other identifiers used for authentication, is a quantitative evaluation of an individual's physical attributes that is successfully used to confirm or validate the identification. Because of its remarkable and consistent texture variation, iris recognition is thought to be the most dependable biometric recognition. Concerns about security, authentication, and identification are growing in importance across all domains as technology advances daily. High-security applications use these unique patterns for iris recognition. To increase the security of biometric applications without jeopardizing individual privacy, this research suggests a novel FL technique for privacy-preserving iris detection. Traditional biometric systems rely on centralised data storage and processing, which threatens data security and misuse. Federated Learning: decentralized model training that allows multiple federated clients (like mobile devices or edge servers) to collaboratively train a global model without sharing their raw iris data. We explore how this architecture can be applied to iris detection systems, maintaining accuracy while mitigating privacy risks. Our method ensures that iris features are learned locally on individual devices, and only encrypted model updates are shared with the central server. To strengthen privacy, we incorporate differential privacy and secure aggregation techniques to prevent data leakage during model training. Experimental results demonstrate the effectiveness of the proposed framework in maintaining high detection accuracy, low communication overhead, and robust privacy guarantees.

关键词： Training Privacy Differential privacy Accuracy Federated learning Biological system modeling Data models Object recognition Servers Iris recognition

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：