检索结果-内蒙古大学图书馆

Levy Flight Adopted Particle Swarm Optimization-based Resource Allocation Strategy in Fog Computing

Chinese Journal of Electronics 2023年

作者： Sharmila Patil(Karpe) Brahmananda S H Research Scholar Department of Computer Science and Engineering GITAM School of Technology GITAM Deemed University Professor Department of Computer Science and Engineering GITAM Bengaluru

The prevalence of the Internet of Things(Io T) is unsteady in the context of cloud computing, it is difficult to identify fog and cloud resource scheduling policies that will satisfy users' Qo S need. As a result, it increases the efficiency of resource usage and boosts user and resource supplier profit. This research intends to introduce a novel strategy for computing fog via emergencyoriented resource allotment, which aims and determines the effective process under different parameters. The modeling of a non-linear functionality that is subjected to an objective function and incorporates needs or factors like Service response rate, Execution efficiency, and Reboot rate allows for the resource allocation of cloud to fog computing in this work. Apart from this, the proposed system considers the resource allocation in emergency priority situations that must cope-up with the immediate resource allocation as well. Security in resource allocation is also taken into consideration with this strategy. Thus the multi-objective function considers 3 objectives such as Service response rate, Execution efficiency, and Reboot rate. All these strategies in resource allocation are fulfilled by Levy Flight adopted Particle Swarm Optimization(LF-PSO). The evaluation is performed to determine whether the developed strategy is superior to numerous traditional schemes. The cost function attained by the adopted technique is 120, which is 19.17%, 5%, and 2.5%greater than the conventional schemes like GWSO, EHO,and PSO, when the number of iterations is 50.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A comparative analysis of different cloud computing method for scheduling healthcare tasks

A comparative analysis of different cloud computing method f...

引用

Signal Processing and Advance Research in Computing (SPARC), International Conference on

作者： Pallab Banerjee Shavi Snehal Sonam Kumari Biresh Kumar Kanika Thakur Manorama Patnaik Computer Science Engineering Amity University Ranchi Jharkhand India Amity School of Information Technology Amity University Ranchi Jharkhand India Computer Science and Engineering Galgotia University Greater Noida campus

ISBN: (数字)9798350385205

ISBN: (纸本)9798350385212

The problem of efficient task scheduling in cloud-integrated, Internet of Things-based healthcare monitoring systems is examined in this work. We suggest Prioritized Sorted Task-Based Allocation (PSTBA), a novel scheduling method, to enhance task execution and boost system performance. In order to guarantee that vital healthcare monitoring tasks are finished on time, PSTBA ranks jobs according to their criticality, expected processing time (EPT), and virtual machine wait time. The process entails putting PSTBA into practice in an IoT cloud context and assessing its effectiveness using in-depth CloudSim simulations. The findings show that PSTBA works noticeably better than the current techniques, such as First-Come, First-Served (FCFS) and Sorted Task-Based Allocation (STBA) PSTBA specifically lowers the failure rate by 20% and 35.6%, raises the guarantee ratio by 2.5% and 4.8%, and decreases latency by 12.6% compared to STBA and 79.2% compared to FCFS. Moreover, PSTBA successfully reduces the number of key activities missed by 14.9% when compared to STBA and 51% when compared to FCFS. To sum up, PSTBA is a very successful scheduling method that improves job prioritizing and system stability for IoT-based healthcare systems.

关键词： Cloud computing Visualization Processor scheduling Medical services Quality of service Virtual machines Workstations Resource management Time factors Monitoring

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

2024 Asia Pacific Conference on Innovation in technology, APCIT 2024

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

ISBN: (纸本)9798350361537

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. © 2024 IEEE.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

TUTNet - A Segmentation Network for Fabric Sewing Thread in the Texture Background 7

TUTNet - A Segmentation Network for Fabric Sewing Thread in ...

引用

7th International Conference on Pattern Recognition and Artificial Intelligence, PRAI 2024

作者： Liang, Xi Yu, Ye Chen, Fengxin Wang, Zilong Li, Xin Lu, Qiang School of Computer Science and Information Hefei University of Technology Hefei China School of Electrical Engineering and Automation Hefei University of Technology Hefei China

ISBN: (纸本)9798350350890

Sewing thread segmentation can help locate the defects in fabric sewing process, which is a challenging problem in factory quality control. In this paper, we propose a twin U-shaped Transformer Network (TUTNet) for sewing thread segmentation. To learn high-dimensional abstract features and capture the sewing direction while ensuring the smoothness of segmentation, we propose a Twin-Attention Module (TAM), which is composed of Sewing Thread Direction (STD) and Sewing Thread Smoothness (STS) blocks. To better combine low-dimensional features with fine-grained features, and generate more continuous results, we propose a Scaled Feature Fusion Module (SFFM), which is used to calculate losses at multiple levels. We also propose a large-scale sewing thread segmentation (STSeg) dataset, which is collected from real clothing production factory. Finally, we conduct experiments on both STSeg and DGRE datasets to verify the effectiveness of our method for sewing thread and other linear object segmentation. © 2024 IEEE.

关键词： Large datasets

来源：评论

学校读者我要写书评

暂无评论

Evaluation of Vehicle Sensor Performance for Vulnerable User Detection through Vehicle Speed Measurement

Evaluation of Vehicle Sensor Performance for Vulnerable User...

引用

2024 IEEE International Conference on Signal Processing and Advance Research in Computing, SPARC 2024

作者： Rathnakar, G. Kothiyal, Arnav Shwetha, H.R. Harikeerthan, M.K. Parikh, Swapnil Maranan, Ramya JSS Science and Technology University Department of Mechanical Engineering Karnataka 570006 India Graphic Era Deemed to Be University Department of Computer Science & Engineering Uttarakhand 248 002 India JNN College of Engineering Department of Electronics and Communication Engineering Shivamogga577204 India Dayananda Sagar Academy of Technology and Management Department of Civil Engineering Karnataka 560082 India Parul Institute of Engineering and Technology Department of Computer Science and Engineering Parul University Gujarat India Saveetha School of Engineering Department of Research and Innovation SIMATS Tamil Nadu 602105 India

ISBN: (纸本)9798350385199

This work involves the successful utilization of magnetic sensors for vehicle speed measurement and also emphasizes the potential of such technology in enhancing safety for vulnerable road users. The device, with its wide voltage range compatibility (3.5-60 V) and robust industrial box housing, is equipped with a wireless module, enabling versatile deployment options. The vehicle detection system using MMC5883MA and HMC1021z sensors showed higher amplitudes for nearer lanes, suggesting a need to relocate the device further from the road. Challenges included close vehicle passes and inconsistent speeds, affecting accuracy, with an average error of 5.5 km / h, reduced to 3 km / h under ideal conditions. Despite fluctuations in some vehicles like the Citroen C3, 63% of measurements had deviations under 5 km / h, and 80% under 10 km / h. © 2024 IEEE.

关键词： Highway administration

来源：评论

学校读者我要写书评

暂无评论

3D Based CNN for Improved Segmentation from the Hyperspectral Images 1

3D Based CNN for Improved Segmentation from the Hyperspectra...

引用

1st International Conference on computer science and Emerging Technologies, CSET 2023

作者： Narmadha, T. Arockia Raj, A. Saravanan, P. Kumar, A. Suresh Sekaran, Ramesh Gowri Shankar, J. School of Computer Science and Engineering Jain Deemed to Be University Bengaluru India Madanapalle Institute of Technology and Science Department of Computer Science and Engineering - Data Science Madanapalle India School of Computing Science and Engineering Galgotias University Delhi NCR India

ISBN: (纸本)9798350341737

In this paper, we develop a 3D based CNN for Improved Segmentation of Paddy Fields from the HSI. Within the scope of this research, we will investigate a unique deep learning model, specifically 3D-CNN. In order to evaluate the validity of the model, it is applied to three separate datasets, each of which is then subjected to one of four distinct dimensionality reduction strategies. The purpose of this is to determine which of these four models is the most effective at reducing the number of dimensions. According to the findings, the 3D-CNN model is superior to both the AlexNet and CNN models in terms of the accuracy of its segmentations. In addition to this, the findings demonstrate that the 3D-CNN models perform better than the other approaches in terms of segmentation accuracy with a smaller number of datasets. © 2023 IEEE.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Disturbance Rejection Target Tracking Control for Snake Robots in the Presence of Obstacles 3

Disturbance Rejection Target Tracking Control for Snake Robo...

引用

3rd IEEE Industrial Electronics Society Annual On-Line Conference, ONCON 2024

作者： Li, Ningwei Chu, Yiming Ren, Shanjun Wang, Chaoli Wang, Gang Li, Peng Institude of Machine Intelligence University of Shanghai for Science and Technology Shanghai China School of Optical Electrical and Computer Engineering University of Shanghai for Science and Technology Shanghai China School of Mechanical Engineering and Automation Harbin Institute of Technology Shenzhen China

ISBN: (纸本)9798331540319

In this paper, a collision-free target tracking control approach utilizing guided vector field guidance is proposed. In particular, a synthesized vector field is designed to direct the snake robot toward the target while simultaneously navigating around multiple obstacles. In addition, a saturated guidance law is designed to compute a reference angular velocity to prevent damage to the robot joints. A dynamics control law is designed based on a reduced-order structure-modified expansion state observer to compensate for external disturbances and realize the robust target tracking and tracing control of the snake robot. Simulation results show the effectiveness of the proposed guidance and control method. © 2024 IEEE.

关键词： Disturbance rejection

来源：评论

学校读者我要写书评

暂无评论

Spider Silk: Biosynthesis, Properties & Bioengineering

引用

Current Nanomaterials 2024年第2期9卷 83-91页

作者： Singh, Shivendra Sharma, Shivangi Das, Snigdha Das, Amlan Kumar Department of Applied Chemistry Amity School of Engineering & Technology Amity University Maharajpura Dang Madhya Pradesh Gwalior474 005 India VBERC Vidya Bhawan Society Fatehpura Udaipur313001 India Department of Chemistry School of Liberal Arts and Sciences Mody University of Science and Technology Laksh-managrh Rajasthan Sikar332 311 India

Due to the remarkable and unique qualities of spider silk, it has much applicability in the coming days. The complicated diversity and structure of spider silk ensure its use in both nature and industry. Based on the uniqueness and distinctive qualities associated with spider silks, advancements in cloning and expression of these silks are a growing area of research and industrial use. The environmentally triggered spider silk assembly and further disassembly, the creation of fibers, films, and novel chimeric composite materials from genetically modified spider silks are interesting areas of research in nanotechnology. In this context, we have discussed the creation of hybrids made of spider silk that combine with organic nanoparticles, both naturally occurring and bioengineered spider silk proteins. The diversity of spider silk, its composition and architecture, the distinctions between spider silk and silkworm silk, and the biosynthesis of natural silk are also discussed. This article describes the current issues and expected outcomes using biochemical data and processes. © 2024 Bentham science Publishers.

关键词： Proteins

来源：评论

学校读者我要写书评

暂无评论

MCROR: A Two-Step Framework for Class Imbalance and Overlap Reduction in Binary Classification 3

MCROR: A Two-Step Framework for Class Imbalance and Overlap ...

引用

3rd International Conference on Communication, Control, and Intelligent Systems, CCIS 2024

作者： Kumar, Sunil Singh, S.K. Nagar, Vishal Aiit Amity University Department of Information Techhnology Uttar Pradesh India Pranveer Singh Institute of Technology Department of Computer Science and Engineering Uttar Pradesh Kanpur India

ISBN: (纸本)9798331528201

Class imbalance and overlap present significant challenges in binary classification tasks, particularly in domains such as medical diagnosis and fraud detection. The disproportionate representation of classes and the overlapping regions between them lead to biased classifiers that favor the majority class and exhibit poor generalization. In this paper, we introduce MCROR (Majority Class Reduction and Overlap Removal), a novel two-step framework designed to mitigate class imbalance and reduce overlaps in binary classification. The first step of the proposed approach reduces the number of majority class instances by partitioning the dataset into regions and selectively replacing instances with their mean values. In the second step, overlapping instances are removed by calculating the Euclidean distance between instances and eliminating those that fall within a critical distance threshold. We evaluate MCROR on synthetic imbalanced and overlapped datasets and compare its performance with existing resampling techniques, such as SMOTE, ADASYN, and Random Under-Sampling. The results demonstrate that MCROR achieves competitive accuracy (92%) while significantly improving recall (92.59%) and AUC-ROC (96.57%), outperforming other methods in terms of identifying minority class instances. The proposed method shows promise for applications in imbalanced datasets, particularly in medical and anomaly detection tasks. © 2024 IEEE.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Space robotics hybrid conceptual model for tracking and estimation using IoRT and AI-based control system

Space robotics hybrid conceptual model for tracking and esti...

引用

作者： Sinha, Anurag Garg, Namit Singh, N.K. Kumar, Biresh Banerjee, Pallab Verma, Achyut Kumar Department of Computer Science IGNOU Delhi India Department of Mathematics and Computing Indian Institute of Technology Kanpur India Department of Computer Science and Engineering Birla Institute of Technology Mesra Ranchi India Department of Computer Science and Engineering Amity University Jharkhand Ranchi Jharkhand India Department of Chemical Engineering Indian Institute of Technology Kanpur India

Robotics is an amalgamation of mechanical engineering and computer science. Mechanical engineering helps to design and develop mechanical parts and devices for control systems in robots. Space robots and robotics are known as devices that can enhance the manipulation, functionalities, and control exercised by astronauts, and thus can be called their artificial assistants for real-time exploration of space conditions. Control systems in robots like gestures and action become predominant for control, thus human-robot interaction comes into existence. AI and reinforcement learning have been used to control functionality in robots in various fields, but IoRT (Internet of robotic Things) is an emerging area of IoT that has the capabilities to monitor a variety of courses of action in robots. In this paper, we are proposing a conceptual framework based on an IoRT control system integrated with AI and reinforcement learning algorithms, which has been accessed based on multiple papers in the same domain, and it will help future researchers develop and simulate such a prototype. We are also using AKF (Adaptive Kalman Filtering) for robot tracking and noise deduction in sensors integrated with the A* algorithm. Overall, this is a concept-based framework to be designed and simulated. © 2023

关键词： Reinforcement learning

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：