检索结果-内蒙古大学图书馆

5th IEEE International Conference on Computing, Power, and Communication Technologies, IC2PCT 2024

作者： Singh, Devendra Bisht, Narendra Dobhal, Dinesh C. Pant, Janmejay Dhanik, Saurabh Graphic Era Deemed to Be University Department of Computer Science and Engineering Dehradun India Graphic Era Hill University Department of Management Studies Bhimtal India Graphic Era Deemed to Be University Department of Computer Application Uttarakhand Dehradun India Graphic Era Hill University Department of Computer Science and Engineering Bhimtal Campus India Graphic Era Hill University School of Computing Bhimtal Campus Uttarakhand India

ISBN: (纸本)9798350383522

Diabetic retinopathy, a serious complication of diabetes, can result in permanent blindness if not promptly detected. The difficulty in assessing the stages of the disease using fundus images by experienced human specialists impedes early identification. This problem has prompted researchers to turn toward convolutional neural networks (CNNs) to simplify the evaluation process. The incorporation of CNNs offers hope for a more effective and accurate distinguishing of the stages of diabetic retinopathy, which could help prevent permanent loss of vision. The objective of such an effective screening mechanism is to simplify procedures, and thus allow for early intervention soon after onset so that the precious gift of sight will not be lost. We suggest a classification system below along these lines. © 2024 IEEE.

关键词： Convolutional Neural Networks Diabetic Retinopathy (DR) Efficient Net ResNet-50

来源：评论

学校读者我要写书评

暂无评论

Improvised Text Classification by Hybrid Machine Learning Techniques

Improvised Text Classification by Hybrid Machine Learning Te...

引用

2024 OPJU International Technology Conference on Smart Computing for Innovation and Advancement in Industry 4.0, OTCON 2024

作者： Anitha, Cuddapah Kapruwan, Akanksha Shilpa, M. Dange, Jyoti Vekariya, Vipul Maranan, Ramya Mohan Babu University Erstwhile Sree Vidyanikethan Engineering College School of Computing Department of Computer Science and Engineering Andhra Pradesh Tirupati517102 India Graphic Era Deemed to Be University Department of Computer Science & Engineering Uttarakhand Dehradun248002 India Rns First Grade College Department of Computer Application Bangalore Karnataka Channasandra560098 India Atharva College of Engineering Department of Information Technology Malad West Maharashtra Mumbai400095 India Parul Institute of Engineering and Technology Parul University Department of Computer Science and Engineering Post Limda Gujarat Waghodia391760 India Saveetha School of Engineering Simats Department of Research and Innovation Tamil Nadu Chennai602105 India

ISBN: (纸本)9798350373783

To improve the performance of English-text classification, text classification systems aim to design appropriate algorithms for extracting features and auto-classifying texts with automatic semantic feature selection. Motivated by the efficiency of Attention mechanism (AM), the ways to use AMs at different levels in CNN and specific RNN organization are explored in this work and BLSTM based models to eliminate misinformation, obtain more accurate contextual information, and ultimately improve performance. Finally, all of the features are concatenated and fed into the softmax classifier. The BLSTM is primarily used to hold the sentence interdependencies, then CNN is selected to extract features for continuous modeling operations, and this model is evaluated by applying it to the ETC. Furthermore, the proposed integrated CNN and BLSTM with Attention mechanism (A-C-BLSTM) model achieves significant results through our evaluation and performs better than a wide range of baseline models. © 2024 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Mobile edge computing-enabled blockchain: contract-guided computation offloading

引用

Journal of Supercomputing 2023年第7期79卷 7970-7996页

作者： Li, Yijun Lin, Ziqiong Zhang, Wenjie Zheng, Yifeng Yang, Jingmin School of Computer Sciences Minnan Normal University Fujian Zhangzhou363000 China Key Laboratory of Data Science and Intelligence Application Fujian Province University Fujian Zhangzhou363000 China Department of Electronic Engineering National Taipei University of Technology Taipei106335 Taiwan

The core problem of blockchain is to solve the proof-of-work puzzle, which is a high energy-consumption task. To address the resource limit problem, the combination of blockchain and mobile edge computing (MEC) has attracted widespread concern. In this paper, we consider a resource trading problem for a MEC-enabled blockchain system with multiple miners and one edge computing service provider (ESP), in which ESP has no previous knowledge of miners’ private information. We focus on how to perform resource trading between miners and ESP to maximize ESP’s profit under incomplete information? To tackle this problem, the resource trading process is modeled as a monopoly market using contract theory. The ESP acts as a monopolist and needs to set a contract containing service time and price for the miners. The miners can be classified into multiple types based on the private information and select one contract item designed for its type. We first analyze the necessary and sufficient conditions for feasible contracts and derive the optimal contract that maximizes the ESP’s profit for complete information scenario. For incomplete information, the service demand and the number of transactions contained in the block are the private information of miners and not known by ESP, we explore the properties of a feasible contract to reduce the complexity and propose a Lagrange multiplier algorithm to obtain the optimal contract in this scenario. Finally, the feasibility and optimality of the contract have been shown through simulation results. In addition, our proposed method can achieve results close to that of complete information scenario and has a maximum performance improvement of 17.19% comparing with linear pricing strategy in incomplete information scenario. © 2022, The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Wolf Algorithm Based Routing and Adamic Adar Trust for Secured IOT Network 1st

Wolf Algorithm Based Routing and Adamic Adar Trust for Secur...

引用

1st International Conference on Artificial Intelligence and Data science, ICAIDS 2021

作者： Tiwari, Shailendra Kumar Mannepalli, Praveen Kumar Department of Computer Application LNCT University Madhya Pradesh Bhopal India Department of Computer Science and Engineering LNCT University Madhya Pradesh Bhopal India

ISBN: (纸本)9783031213847

IoT network increases the utilization of the spectrum, by transferring data on blank channels. In order to reduce the robustness of the network from different attacks, many of researcher proposed various models. This paper has developed a secure routing technique to improved the spectrum utilization in IoT network. Routing of the packet was done by wolf genetic algorithm. IoT network is dynamic in nature hence genetic algorithm find good set of sequential node from sender device to receiver device. To identify malicious node in the network Adamic Adar trust value was estimate by the system. Neighbor relation was used in the function for the trust evaluation in virtual environment. Experiment was done on MATLAB platform and result shows that proposed model has increases the parameter values as compared to existing models. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Supervised Code-Mixed Data Sentiment Analysis 1

Supervised Code-Mixed Data Sentiment Analysis

引用

1st International Conference on Computational Intelligence and Sustainable engineering Solution, CISES 2022

作者： Singh, Neelam Upadhyay, Yogesh Rawat, Vandana Graphic Era Deemed to Be University Department of Computer Science and Engineering Dehradun India Graphic Era Deemed to Be University Department of Computer Application Dehradun India

ISBN: (数字)9781665480048

ISBN: (纸本)9781665480048

Sentiment Analysis of data extracted from social media is a very important and necessary task gaining popularity for many years applicable on various fields like opinion mining. Analyzing code-mixed English data is a typical task due to the complication of dataset. Machine Learning procedures has paved the way to handle these datasets with utmost ease and efficiency. In this research paper Sentiment Analysis on code-mixed tweets of English by means of different Machine Learning Classification techniques is implemented after pre-processing the gathered data using Count Vectorizer and Tf-Idf Vectorizer. The classification of a tweet or tweets into subjectivity, polarity and its analysis is our main objective. Supervised learning models like SVM, Decision Tree, Logistic Regression and K-nearest neighbor are instigated for analyzing the tweets and the result based on evaluation metrics like F1-score, and accuracy is used to find the most appropriate and efficient technique. © 2022 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

RANSACs for 3D Rigid Registration:A Comparative Evaluation

引用

IEEE/CAA Journal of Automatica Sinica 2022年第10期9卷 1861-1878页

作者： Jiaqi Yang Zhiqiang Huang Siwen Quan Zhiguo Cao Yanning Zhang the National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology School of Computer ScienceNorthwestern Polytechnical UniversityXi’an 710072China the School of Electronic and Control Engineering Chang’an UniversityXi’an 710064China the School of Artificial Intelligence and Automation Huazhong University of Science and TechnologyWuhan 430074China IEEE

Estimating an accurate six-degree-of-freedom(6-Do F)pose from correspondences with outliers remains a critical issue to 3D rigid *** sample consensus(RANSAC)and its variants are popular solutions to this *** there have been a number of RANSAC-fashion estimators,two issues remain ***,it is unclear which estimator is more appropriate to a particular ***,the impacts of different sampling strategies,hypothesis generation methods,hypothesis evaluation metrics,and stop criteria on the overall estimators remain *** work fills these gaps by first considering six existing RANSAC-fashion methods and then proposing eight variants for a comprehensive *** objective is to thoroughly compare estimators in the RANSAC family,and evaluate the effects of each key stage on the eventual 6-Do F pose estimation *** have been carried out on four standard datasets with different application scenarios,data modalities,and *** provide us with input correspondence sets with a variety of inlier ratios,spatial distributions,and *** on the experimental results,we summarize remarkable outcomes and valuable findings,so as to give practical instructions to real-world applications,and highlight current bottlenecks and potential solutions in this research realm.

关键词： 3D rigid registration performance evaluation point cloud pose estimation

来源：评论

学校读者我要写书评

暂无评论

An Efficient Feature Extraction Technique and Novel Normalization Method to Improve EMG Signal Classification 3

An Efficient Feature Extraction Technique and Novel Normaliz...

引用

3rd International Conference on Intelligent engineering and Management, ICIEM 2022

作者： Jain, Reema Garg, Vijay Kumar Lovely Professional University Department of Computer Application Punjab Phagwara India Lovely Professional University Department of Computer Science & Engineering Punjab Phagwara India

ISBN: (数字)9781665467568

ISBN: (纸本)9781665467568

Electromyography (EMG) is one of the medical diagnostic techniques that is widely used to investigate muscular health status. Medical and paramedical professional's record EMG signals as myoelectric signals that need some processing to improve their apt analysis and interpretation. In the present paper, the authors have integrated feature extraction and normalization step to improve the overall EMG signal classification. The process involves 12 feature extraction matrices that are used for the normalization of the recorded signals. The processed signals are fed to a binary classifier, Support Vector Machine (SVM) for categorization into pain and normal classes. Performance analysis is performed using 100 simulation rounds and the observations are summarized in terms of precision, sensitivity, specificity, and accuracy of classification of EMG signals. The simulation analysis demonstrated that with the integration of feature extraction and normalization step, an improvement of 3% is observed in the EMG signal classification accuracy. © 2022 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Analysis of the Effects to Recognize the use of Effective Green Cloud-Based Solutions Using Tiny Smart Grid to Light Web Data Centres 11

Analysis of the Effects to Recognize the use of Effective Gr...

引用

11th International Conference on System Modeling and Advancement in Research Trends, SMART 2022

作者： Kumar, Rajat Ali Khan, Mizan Chandigarh School of Business Department of Master of Computer Application Jhanjeri India Sanskriti University Department of Computer Science Engineering Uttar Pradesh Mathura India

ISBN: (纸本)9781665487320

Recent years have seen two significant advancements in the ICT industry: green technology and data storage. According to going green, the information and communication technology (Cmc) industry now consumes a significant amount of energy and thus produces a significant amount of CO2 emissions. IT gear may be purchased as an utility via cloud services with no up-front costs. Based on previously reported studies that demonstrate that csps are the most ecofriendly option for delivering, the intersection of these two advances cloud be investigated first in this study. Outsourcing private cloud hosting enables companies to run more efficiently. Three instances of innovative businesses offering sustainable web hosting are also offered, and the factors affecting their resource growth are looked at. The results demonstrate that there is no longer a need for green virtual private servers since low costs are the main driver of company decisions. Environmental network operators should create green service levels, negotiate on lushness, and use unambiguous economic measures to show their vegetation. Therefore, it is up to affected customers to push for more environmentally friendly internet services, which will increase the need for green public cloud and sustainable software solutions. © 2022 IEEE.

关键词： Data Analytics

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Remora Optimization Algorithm with Variable Neighborhood Search for the Flexible Job Shop Scheduling Problem 7

A Hybrid Remora Optimization Algorithm with Variable Neighbo...

引用

7th International Conference on Advanced Algorithms and Control engineering, ICAACE 2024

作者： Yang, Zheng Liang, Xiaodan Li, Yajing Wang, Haoyue School Of Computer Science And Technology Tiangong University Tianjin China Engineering Research Center Of Integration And Application Of Digital Learning Technology Ministry Of Education The Open University Of China Beijing China College Of Artificial Intelligence Tianjin University Of Science And Technology Beijing China

ISBN: (纸本)9798350361445

Reducing the production makespan of modern small-batch, multi-variety jobs can be abstracted into a flexible job shop scheduling problem (FJSP). The organization can greatly improve production efficiency by scheduling according to the optimal solution of FJSP. However, due to the high computational complexity of FJSP, it is often difficult to achieve higher performance in actual production. To optimize the makespan of the FJSP, a hybrid remora optimization algorithm with variable neighborhood search (HROA-VNS) is proposed in this work. A hybrid initialization method based on machine load balancing is utilized to improve the quality of the initial population. To solve discrete FJSP, a conversion method for individual positions and scheduling solutions is proposed, and a host switching mechanism (HSM) is designed to enhance the development and exploration capabilities of the algorithm. Furthermore, for enhancing the accuracy and effectiveness of the optimal solution, a variable neighborhood search (VNS) strategy which contains multiple structures is designed for local search. According to the experimental data, compared with the basic algorithm, the HROA-VNS reduced the makespan by an average of 33.02% and 14.40% on the two benchmark test sets respectively, and it shows better performance than related algorithms. © 2024 IEEE.

关键词： Evolutionary algorithms

来源：评论

学校读者我要写书评

暂无评论

Tomato Leaf Disease Classification Using Supervised Learning Techniques: Contrasting Analysis

Tomato Leaf Disease Classification Using Supervised Learning...

引用

2022 International Conference on Advances in Computing, Communication and Materials, ICACCM 2022

作者： Rawat, Vandana Singh, Neelam Kaur, Bhavleen Bora, Saksham Graphic Era Deemed to Be University Department of Computer Science and Engineering Dehradun India Graphic Era Deemed to Be University Department of Computer Application Dehradun India

ISBN: (纸本)9781665474399

Presently hydroponic methods of growing different varieties of crops are acquiring acceptance in different parts of the world. It is a technique of growing plants with the help of water. Traditional methods of farming are facing different types of threats like lack of farming lands, expansion of urban areas, change in climatic conditions and extensive use of chemical fertilizers and toxicants which is exhausting the fertility of the soil and transforming cultivable lands into barren lands. With the tremendous growth of population nowadays it is quite difficult to supply all the human race with an adequate amount of food by growing them on the basis of traditional methods. The farming land is also changing in residential areas to meet the demand of the growing population in order to provide them a place for living. As a result, different methods of farming need to be adopted. In this study, hydroponic methods are explained with the help of machine learning algorithms. This system works on the principle of KNN and Lasso Regression algorithm to automatically provide them with nutrients dissolved in water with the help of roots. With the help of this technique, we can overcome the issues of food scarcity by growing an ample number of crops of different types, all year round. Hydroponics is a technique for the cultivation of plants without using soil. Earlier this method was practiced manually by keeping an eye on the nutritional needs of plants by maintaining a balance of various factors such as acidity or basic (pH), electrical conductivity (EC), temperature and the value of total dissolved solids(TDS). In this research Machine, Learning Methods are used that help us to measure pH, TDS, and nutrient temperature value in the nutrient film technique (NFT) by using some sensors. In this research, tomato is an object of an experiment, and Comparison is done using Machine Learning Algorithms to speculate the categorization of nutrient conditions for it. © 2022 IEEE.

关键词： Hydroponics

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：