检索结果-内蒙古大学图书馆

5th International Conference on Nanoelectronics, Circuits and Communication Systems, NCCS 2019

作者： Satapathy, Ashutosh Jenila Livingston, L.M. School of Computing Science and Engineering Vellore Institute of Technology Vellore Chennai600127 India

ISBN: (纸本)9789811574856

From the last couple of decades, image denoisification is one of the challenging areas in the image processing and computer vision domains that adds clarity to images by removing noise and makes them suitable for further processing. Images or videos captured by various visual sensors are degenerated during various circumstances such as sensor temperature, light intensity, target environment, erroneous electric instruments, and interference in the communication channels and required to be enhanced by various filtering techniques. Most of the real-world applications like student monitoring, vigilance system, traffic analysis, target detection, and classification use image smoothing to reduce artifacts present in the captured images and additionally demand its quicker execution. In this paper, we have explained different types of noise models normally degrade the quality of an image and the three most popular frequency domain smoothing filters (ideal, Gaussian, and Butterworth) are available to remove those noises. In addition to that, OpenCL kernels of those filters have been implemented for rapid denoisification and can be easily portable on wide verities of parallel devices. At last, performance evaluation has been carried out for both the CPU and GPU implementations to seek out their productiveness on those noise models in terms of time and precision. Various performance assessment metrics like entropy, root-mean-squared error, peak signal-to-noise ratio, and mean absolute error are applied to determine the rightness of the above filters. © 2021, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Low pass filters

来源：评论

学校读者我要写书评

暂无评论

Deep Learning ResNet-50 Framework for Automatic Early Breast Cancer Diagnosis

Deep Learning ResNet-50 Framework for Automatic Early Breast...

引用

2024 International Conference on Communication, computing and Internet of Things, IC3IoT 2024

作者： Ashwini, A. Suji, M. Angel Merlin Prathaban, Banu Priya Shahila, D. Ferlin Deva Jency Rubia, J. Kumar, Narla Vinod Vel Tech Rangarajan Dr. Sagunthala R&d Institute Of Science And Technology Department Of Ece Chennai India St. Xavier's Catholic College Of Engineering Department of CSE Kanyakumari Nagercoil India School Of Computing Srm Institute Of Science And Technology Department Of Networking And Communication Kattankulathur Chennai India

ISBN: (纸本)9798350352689

The most serious disease that affect the women worldwide is breast cancer. Early identification of breast cancer contributes to lower death rates. Through the process of histopathological examination, a pathologist looks at the tissues' microscopic features to find different malignant patterns. However, the process of manual histological analysis is challenging, unreliable, and time-consuming. Therefore, in order to determine the malignancy, a computer-aided system created to analyze these images must take these two magnifications into account completely. As a result, this research suggests a distinct deep neural algorithms for the categorization of breast cancer histological images, designed to imitate a pathologist. ResNet-50 focuses on possible locations that are relevant for the precise classification of tumor images by utilizing global and local information in an integrated manner. Preprocessing of the images with nuclei is therefore regarded as the first stage in this procedure. To get an equalized preprocessing result, the input images are subjected to Color normalization. After additional processing, these pictures are divided into two group called benign and malignant. The efficacy of the suggested models in improving nuclei is demonstrated by experimental evaluation on both public and private datasets. The experimental evaluation shows the best result with the proposed research technique. © 2024 IEEE.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Efficient Data Transmission Scheme using Modified Wireless Communication Protocol Design

Efficient Data Transmission Scheme using Modified Wireless C...

引用

2022 IEEE International Conference on Advances in computing, Communication and Applied Informatics, ACCAI 2022

作者： Nagaraju, V. Kumar, N. Jagadish Ali, Ahmed Mudassar Bapu, Tapas B R Partheeban, N. Saveetha School of Engineering SIMATS Department of CSE Chennai India Velammal Institute of Technology Department of IT Chennai India S. A. Engineering College Department of Information Technology Chennai India S. A. Engineering College Department of ECE Chennai India School of Computing Science and Engineering Galgotias University Delhi India

ISBN: (纸本)9781665495295

In this digital world, each and every communication needs depends upon the wireless communication model and every single individual as well as the firms highly dependent on this wireless communication field. So that a robust data transmission model is required to achieve the fault free communication as well as the scheme should support the communication over all the regions/entities such as disaster zones, application data monitoring, rural/urban areas and other surveillance related fields. Environmental sustainability is the most important concern and the concern regards monitoring, analyzing, mapping and regulating are just few of the many advances in wireless communication networks with sensor associations now-A-days. Because they operate in an open ground and use wireless data transmission technologies, remote wireless data transmission networks necessitate extremely secure data transmission. This is possible to reduce the power consumption of a wirelessly monitoring network by applying various technologies or techniques. In this research, a novel Data Aggregation Protocol Model (DAPM) is designed to help the Wireless Sensor based Communication Networks to and energy and provide robust support to clients to satisfy their communication needs. It is possible to decrease the quantity of transmission power and energy expenditure in a large wireless sensor networks by accumulating information at relay node (that is, merging incomplete outcomes throughout work system). Wireless Communication based Sensor Networks require secured information delivery and constant routing assistance to nodes presented into the network region. This paper is intended to design a new protocol to carry the data packets to destination without any flaw over the communication pathway, in which the proposed DAPM provides such facility to the wireless networks to achieve flaw free communications in good manner. The recommended protocol design is shown to be efficient through the use of computati

关键词： Data communication systems

来源：评论

学校读者我要写书评

暂无评论

A New Method for Predefined-Time Synchronization Control of Memristive Cohen-Grossberg Neural Networks

A New Method for Predefined-Time Synchronization Control of ...

引用

Memristive computing and Applications (ICMCA), IEEE International Conference on

作者： Aidi Liu Wenyue Yu Lili Huang Jian Guo Tengfei Lei Hui Zhao School of Computer and Information Engineering Qilu Institute of Technology Jinan China School of Computer and Information Engineering Qilu Institute of Technology Collaborative Innovation Center of Memristive Computing Application School of Computer and Information Engineering Qilu Institute of Technology Shandong Provincial Key Laboratory of Network Based Intelligent Computing School of Information Science and Engineering University of Jinan Jinan China

This article mainly conducts a series of research on the synchronization control of Cohen-Grossberg neural networks. Firstly, a memristive Cohen-Grossberg neural network model with time-varying delay was constructed, and an equivalent system was obtained by combining inverse function theory, differential inclusion, and set-valued mapping. Secondly, a new predefined-time stability theorem was proposed, and sufficient conditions were obtained to ensure that the drive-response system achieves predefined-time synchronization by designing appropriate control strategy. The simulation results show that the stability time of the error system can be adjusted by the user, verifying the correctness and of the theory.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Algorithms for Auto Insurance Fraud detection: Comparative Study 1

Machine Learning Algorithms for Auto Insurance Fraud detecti...

引用

1st IEEE International Conference on Green Industrial Electronics and Sustainable Technologies, GIEST 2024

作者： Gupta, Prashant K. Bhatnagar, Risabh Tyagi, Shalu Jain, Achin Panwar, Arvind Dubey, Arun Kumar Bennett University School of Computer Science & Engineering Technology Uttar Pradesh India Bharati Vidyapeeth College of Engineering Delhi India Raj Kumar Goel Institute of Technology Ghaziabad India Galgotias University School of Computing Science Engineering India

ISBN: (纸本)9798331540142

Insurance fraud is a massive burden for the industry and causes billions in economic damage yearly. This research deals with the difficulties in fraud detection of insurance companies, focusing on machine learning approaches. Based on factual data from an insurance company the study kind use SVM, Decision Tree model, Random Forest Ada Boost Gradient Boosting and Stochastic Gradient Boosting, XGBoosts Extra Trees in this case. The assessment of this models is through various proper analysis which include confusion matrix and main performance metrics like accuracy, precision, recall, F1 and so on. This study aims to provide insights that would be beneficial to improve the fraud detection strategy in insurance industry by comparing the performance of models used. © 2024 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

IDeploySmart: A Machine Learning-Based Approach for Predicting the Deployment Type of Identity Servers

IDeploySmart: A Machine Learning-Based Approach for Predicti...

引用

International Conference on Information technology Research (ICITR)

作者： Mamoru D. L. S. Amjadh Ifthikar Computer Science and Engineering University of Westminster London United Kingdom School of Computing Informatics Institute of Technology Colombo Sri Lanka

ISBN: (数字)9798331511425

ISBN: (纸本)9798331511432

Identity servers are integral to modern Information technology (IT) infrastructures, managing secure access to critical applications through authentication and authorization processes. However, determining the optimal deployment strategy for these servers in complex environments remains challenging, especially when considering factors like performance, scalability, and security. This paper introduces IDeploySmart, a machine learning-based system designed to predict the most efficient deployment type of identity servers. By employing Gradient Boosting Regressor, IDeploySmart achieves a prediction accuracy of 92.5%, surpassing industry benchmarks. The system was tested across multiple deployment scenarios, showing significant improvements in system performance, scalability, and security. This paper details the system's design, data preprocessing techniques, model evaluations, and real-world applications, providing insights into how machine learning can enhance identity server deployment strategies in modern IT infrastructure.

关键词： Industries Scalability System performance Data preprocessing Predictive models Boosting Data models Servers Security Information technology

来源：评论

学校读者我要写书评

暂无评论

Real-Time Dynamic Cloud Workflow Scheduling for Volatile Resources in Clouds

SSRN

引用

SSRN 2024年

作者： Wang, Yun Zuo, Xingquan Wang, Hui Wu, Zhiqiang The School of Information Engineering Nanchang Institute of Technology Nanchang330099 China The School of Computing Science Beijing University of Posts and Telecommunications Beijing100876 China

Cloud providers offer multiple resource leasing modes to users, such as on-demand instances and spot instances. Compared with on-demand instances, users using spot instances can save up to 90% of the cost, which significantly reduces economic costs for users. However, spot instances have high unreliability because of their random interruption and acquisition delay, which brings challenges to the cloud workflow scheduling of spot instances. This paper studies the real-time dynamic cloud workflow scheduling problem with hybrid leasing mode (hybrid use of spot instances and on-demand instances), which aims to reduce the execution cost of the workflow while satisfying deadline constraint. The fulfillment and interruption rates are used to describe the unreliability of spot instances. A two-stage hybrid scheduling method combing static pre-planning and dynamic scheduling (HySpot) is proposed to solve the problem. In the static pre-planning stage, an improved list scheduling algorithm is used to pre-scheduling workflow onto spot instances. In the dynamic scheduling stage, a task dynamic rescheduling strategy is proposed to adaptively reschedule interrupted tasks to other spot or on-demand instances. Experimental results show that HySpot performs better than the comparative algorithms in terms of minimizing the execution cost and meeting the deadlines. © 2024, The Authors. All rights reserved.

关键词： Cost reduction

来源：评论

学校读者我要写书评

暂无评论

Secure Host Login Technique based Key Agreement protocol for Software Defined Network 4

Secure Host Login Technique based Key Agreement protocol for...

引用

4th International Conference on Inventive Research in computing Applications, ICIRCA 2022

作者： Bhardwaj, Aditya Mutaher, Hamza International Inistitute of Technology Dept. Computer Science and Engineering Bhubaneswar India School of Computing and Innovative Technologies British University Vietnam Hanoi Viet Nam

ISBN: (数字)9781665497077

ISBN: (纸本)9781665497077

Scalability is one of the Software Defined Network features that makes it more efficient than the traditional network. Due to this feature, a huge number of hosts connect to the network and require network rules and policies from the network controller. The huge number of connected hosts makes the network vulnerable to unauthorized access, which may cause network damage. In this paper, a secure hosts login technique is proposed to assure the authenticity of the hosts that need to access the network and use its resources. The proposed technique uses the key agreement protocol to allow the hosts and controller to establish secure communication. Then the procedure moves to the registration phase and login phase, which are responsible for creating and verifying the hosts' credentials while claiming network access. The secrecy and authenticity of the proposed technique was simulated, verified, and proved using AVISPA tool. The result of the simulation also proved the immunity of the proposed technique against MITM and replay attacks. © 2022 IEEE.

关键词： Controllers

来源：评论

学校读者我要写书评

暂无评论

Multi layer segmentation method for ophthalmic OCT images based on Gabor filtering 23

Multi layer segmentation method for ophthalmic OCT images ba...

引用

2023 International Conference on Computer, Vision and Intelligent technology, ICCVIT 2023

作者： Liu, Jiayike Li, Qingbo Liu, Ailin Liu, Dong Liu, Yang Zhang, Tianqiao School of Information and Communication Guilin University of Electronic Technology Guilin541000 China School of Computer and Artificial Intelligence Xiangnan University Chenzhou423000 China Hunan Engineering Research Center of Advanced Embedded Computing and Intelligent Medical Systems Xiangnan University Chenzhou423000 China School of Life and Environmental Sciences Guilin University of Electronic Technology Guilin541000 China

ISBN: (纸本)9798400708701

Optical coherence tomography is a non-destructive optical signal acquisition and processing method for imaging surface tissue structure. OCT has become an important and innovative corneal measurement and diagnostic technology. Propose a multi-layer detection method for ophthalmic OCT retinal images. Firstly, perform 2D Gabor filtering on the OCT image, then binarize the filtered image, and finally perform eight neighborhood contour localization. To provide reference for the quantitative analysis of the thickness of different physiological layers in the anterior segment in the clinical diagnosis and lesion assessment of ophthalmic diseases. © 2023 ACM.

关键词： Optical tomography

来源：评论

学校读者我要写书评

暂无评论

Fire Hawk Optimization based Multi-objective Dynamic Load Balancing in Cloud computing 2

Fire Hawk Optimization based Multi-objective Dynamic Load Ba...

引用

2nd International Conference on Distributed computing and Optimization Techniques, ICDCOT 2024

作者： Kumari, K. Aruna Soujanya, Thota Alsalami, Zaid Rohini, I. Bala Dhandayuthapani, V. Srkr Engineering College Department of Cse Chinaamiram Bhimavaram India School of Agricultural Sciences Sr University Telangana Warangal India The Islamic University Najaf Iraq Malla Reddy Engineering College for Women Dept of Eee Telangana India College of Computing and Information Sciences University of Technology and Applied Sciences Shinas Branch Department of It Oman

ISBN: (纸本)9798350382952

Load Balancing (LB) of the tasks on Cloud computing (CC) is the significant characteristics of distribution of the resources from data center. LB has to be taken out in such a way that every Virtual Machines (VMs) must have balanced the load to attain an optimal utilization of its capabilities. As an outcome, the LB of tasks on VM is examined as a significant thing of task scheduling in the cloud. The LB in cloud faced various challenges like fault tolerance as well as data security. In this research, Fire Hawk Optimization (FHO) algorithm is proposed for the dynamic LB in cloud environment. The aim of this research is to enhance the system performance and it considers the multi-objective functions named Makespan, Resource Utilization (RU), Response Time (RT), Degree of Imbalance as well as throughput. The experimental results proven that the proposed FHO-based LB had obtained the 2246, 6.7, 134.23, 141 and 5.5 in the number of tasks of 1500 using nakespan, RT, RU, DOI and throughput. These results show better enhancement when compared to the previous approaches like Particle Swarm Optimization (PSO), Q-learning Modified PSO (QMPSO) and Binary JAYA algorithm. © 2024 IEEE.

关键词： Cloud computing

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：