检索结果-内蒙古大学图书馆

6th IEEE International Conference on Communication and Electronics Systems, ICCES 2021

作者： Rajan, M.Sundar Arunkumar, J.R. Ramasamy, Anusuya Sisay, Berhanu Arbaminch Institute of Technology Arbaminch University Faculty of Electrical and Computer Engineering Ethiopia Arbaminch Institute of Technology Arbaminch University Faculty of Computing and Software Engineering Ethiopia

ISBN: (纸本)9781665435871

IoT is the network of thousands of individuals, resources and expertise interconnecting and sharing. IoT implementations are strongly validated by increased usability, reliability and automation. Authentication and recovery are important in order to set up an automated IoT environment for the protection and privacy of attacks. This research work presents a survey on the design and security of the IoT layer attack. In this thesis, security and privacy concerns will be detailed. This paper also performs a comprehensive overview on the security threats and sources of threat in IoT applications addressing current IoT security principles and IoT protection and privacy potential proposals. © 2021 IEEE.

关键词： Radio frequency identification (RFID)

来源：评论

学校读者我要写书评

暂无评论

Mi-Go: Test Framework which uses YouTube as Data Source for Evaluating Speech Recognition Models like OpenAI’s Whisper

arXiv

引用

arXiv 2023年

作者： Wojnar, Tomasz Hryszko, Jaroslaw Roman, Adam Jagiellonian University Faculty of Mathematics and Computer Science Division of Software Engineering Lojasiewicza 6 Krakow30-348 Poland

This article introduces Mi-Go, a novel testing framework aimed at evaluating the performance and adaptability of general-purpose speech recognition machine learning models across diverse real-world scenarios. The framework leverages YouTube as a rich and continuously updated data source, accounting for multiple languages, accents, dialects, speaking styles, and audio quality levels. To demonstrate the effectiveness of the framework, the Whisper model, developed by OpenAI, was employed as a test object. The tests involve using a total of 124 YouTube videos to test all Whisper model versions. The results underscore the utility of YouTube as a valuable testing platform for speech recognition models, ensuring their robustness, accuracy, and adaptability to diverse languages and acoustic conditions. Aditionally, by contrasting the machine-generated transcriptions against human-made subtitles, the Mi-Go framework can help pinpoint potential misuse of YouTube subtitles, like Search Engine Optimization. Copyright © 2023, The Authors. All rights reserved.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Enhancing Sovereign Allocation of Resources in Cloud Milieus Using a Causal Dilated Geometric Algebra Approach for Dynamic Scalability 2

Enhancing Sovereign Allocation of Resources in Cloud Milieus...

引用

2nd International Conference on Machine Learning and Autonomous Systems, ICMLAS 2025

作者： Katru, Chandrasekhar Rao Srinivasan, Sathish Kumar, Mohan Yadwad, Sunita Satish, G. Maranan, Ramya Lead Software Engineer Indian LandSC29707 United States Machine Learning & AI Development Oracle Cloud Infrastructure Division San FranciscoCA United States Nitte Meenakshi Institute of Technology Department of Information Science and Engineering Karnataka Bengaluru India Parul institute of Engineering and Technology Parul University Computer science and Engineering Faculty of Engineering and Technology Gujarat India Sree Dattha Institute of Engineering and Science Department of Electrical and Electronics Engineering Telangana Sheriguda India Saveetha School of Engineering SIMATS Department of Research and Innovation Tamil Nadu Chennai India

ISBN: (纸本)9798331505745

Cloud environments utilize availability and usage of resources as crucial components in order to produce scalability, reliability and low cost. Such resource capabilities require autonomous systems that can handle these resources dynamically in spite of fluctuating workloads and service delivery requirements. Static models of resource management suffer from scalability and inability to react on the fly and accurately predict the demand thus causing Service Level Agreement (SLA) breaches and affecting the Quality of Service (QoS) as well as energy consumption profile. Advanced and elaborative cloud workloads require an intelligent system that can analyse the temporal and spatial patterns without impacting the overall system's performance significantly. Inspired by these challenges, this research proposes a Causal Dilated Geometric Algebra Convolutional Transformer Network (CATNet) along with the Prairie-Dog Optimizer (P-DogO), referred to as CAT-DogNet to learn and predict the dynamic scalability. CATNet integrates Causal Dilated Convolutional Networks in time domain for temporal structure capturing and Geometric Algebra Transformer for spatial resource coding. P-DogO adjusts weight parameters and losses for resource allocation, enhancing them depending on a work environment. A set of comprehensive assessments demonstrate a 0.85% SLA violation rate, average response time of less than 10ms, and overall 12.3% less energy consumption than baseline methods. The system had favourable predictability rates over 99.4% for the resource demand estimate. CAT-DogN et presents a sound and agnostic architecture for autonomous resource allocation in cloud environment, which indeed extend the state of art by considering flexibility, power consumption and QoS compliance. © 2025 IEEE.

关键词： Infrastructure as a service (IaaS)

来源：评论

学校读者我要写书评

暂无评论

A Proposal for a New E-Waste Image Dataset Based on the UNU-KEYS Classification

A Proposal for a New E-Waste Image Dataset Based on the UNU-...

引用

International Symposium on Electrical Apparatus and Technologies (SIELA)

作者： Dimitar I. Iliev Marin B. Marinov Frank Ortmeier Faculty of German Engineering and Industrial Management Technical University of Sofia Sofia Bulgaria Department of Electronics Faculty of Electronic Engineering and Technologies Technical University of Sofia Sofia Bulgaria Faculty of Computer Science Chair of Software Engineering Otto-von-Guericke- University Magdeburg Magdeburg Germany

ISBN: (数字)9798350382365

ISBN: (纸本)9798350382372

This paper introduces the largest and most diverse e-waste dataset to date, consisting of 19,613 pictures, 28,941 annotations, and 77 classes, where each class represents one visually distinctive type of electronic device. Furthermore, our dataset was structured using the United Nations University's UNU-KEYS classification, which ensures the compatibility of our dataset with the different e-waste classifications used worldwide and allowed us to choose more relevant dataset classes. The proposed methodology for image collection, annotation, and labeling is explained. The advantages and disadvantages of this dataset and how it can be improved in the future are presented. This dataset has been made open source with a permissive CC by 4.0 license so that it can be used to stimulate scientific progress in the field of automatic e-waste recognition, with the end goal of solving the global e-waste problem. The dataset is available online at https://***/electronic-waste-detection/e-waste-dataset-r0ojc.

关键词： Annotations Data acquisition Documentation Electronic waste Licenses Planning Proposals

来源：评论

学校读者我要写书评

暂无评论

Performance Improvement in Blood Cell Segmentation with Deep Learning-based Image Fusion Approach

Performance Improvement in Blood Cell Segmentation with Deep...

引用

International Artificial Intelligence and Data Processing Symposium (IDAP)

作者： Fatma Tuana Dogu Hulya Dogan Ramazan Ozgur Dogan F. Sena Sezen Department of Electrical and Electronics Engineering Faculty of Engineering Karadeniz Technical University Trabzon Turkey Department of Software Engineering Faculty of Engineering Karadeniz Technical University Trabzon Turkey Department of Artificial Intelligence Engineering Faculty of Computer and Information Sciences Trabzon University Trabzon Turkey Department of Pharmacology Faculty of Pharmacy Karadeniz Technical University Trabzon Turkey

ISBN: (数字)9798331531492

ISBN: (纸本)9798331531508

To overcome the limitations of examining blood cells under a microscope, several investigations have been carried out using artificial intelligence techniques. These investigations aim to automate the processes of detecting, counting, segmenting, and classifying blood cells. Typically, these investigations employ two-dimensional (2D) images to apply artificial intelligence and image processing techniques. Nevertheless, these 2D images occasionally lack optimal focus as a result of the microscope’s depth of focus (DOF). Inadequate achievement of optimally focused imaging has a detrimental impact on the efficiency of automated processes. In this context, the objective of this study is founded around two primary roles. The first of these is the performance improvement of blood cell segmentation by developing a deep learning-based image fusion approach. The second is the preparation of new data sets containing images with different focuses for optimally focused imaging of blood cells. In the study, four different performance evaluation criteria, namely Accuracy (ACC), Sensitivity (SEN), Specificity (SPE), and Jaccard, are utilized to demonstrate the efficacy of the deep learning-based image fusion approach in blood cell segmentation. Both the experimental results of the performance evaluation criteria and the visual findings obtained in the study indicate that the performance in blood cell segmentation is improved with a deep learning-based approach.

关键词： Performance evaluation Image segmentation Visualization Accuracy Microscopy Two-dimensional displays Cells (biology) Artificial intelligence Blood Image fusion

来源：评论

学校读者我要写书评

暂无评论

A Novel Trust Assessment System for Online Social Networking Environment Using Learning Assisted Classification Model

A Novel Trust Assessment System for Online Social Networking...

引用

2024 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems, ICSES 2024

作者： Nithya, S. Deepa, D. Babu, Vunnava Dinesh Pallavi, G. Fawareh, Hamed Kayalvizhy, R.D. Saveetha Engineering College Department of Computer Science Engineering Chennai India St. Joseph's College of Engineering Department of Cse Chennai India Rv Institute of Technology Department of Cse Guntur India Laxminarayan Innovation Technological University Department of Civil Engineering Nagpur India Zarqa University Faculty of Information Technology Software Engineering Dept Zarqa Jordan University of Business and Technology Jeddah21448 Saudi Arabia R.M.K. Engineering College Department of Electronics and Communication Engineering Tamil Nadu Kavaraipettai India

ISBN: (纸本)9798331543617

Trust is essential in the constantly developing environment of online social networks. The Nexus Terroism Impact and Intro Trust facilitate the communication, decision-making, and maintenance of digital communities among individuals. Trust-based Learning with Classification Principle (TLCP) is introduced in this research to improve the assessment of trust in social networks. To ascertain its efficacy, our proposed methodology undergoes a 10-fold cross-validation against the Trust Assessment Methodology (TAM). The traditional Trust Assessment Model (TAM) evaluates and regulates trust in Internet social networking. This method incorporates trust assessment factors to generate a user dependability judgment that is both discriminatory and dynamic. The Trustworthy Account Management (TAM) challenge is designed to enhance digital trust by addressing disinformation, deception, and hostile conduct. The TLCP is able to accurately evaluate trust by utilizing reputation scoring, community analysis, and user behavior metrics. Trust levels are dynamically adjusted as a result of the identification of trustworthy behavioral patterns and danger indicators by machine learning algorithms and social media data. This research examines the connections between trust management and digital interactions and suggests a general solution to alleviate specific trust evaluation issues across online social networks. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Training Artificial Neural Networks by Coordinate Search Algorithm

Training Artificial Neural Networks by Coordinate Search Alg...

引用

2023 IEEE Symposium Series on Computational Intelligence, SSCI 2023

作者： Rokhsatyazdi, Ehsan Rahnamayan, Shahryar Miyandoab, Sevil Zanjani Bidgoli, Azam Asilian Tizhoosh, H.R. Lab Ontario Tech University Department of Electrical Computer and Software Engineering OshawaON Canada Brock University Department of Engineering St. CatharinesON Canada Wilfrid Laurier University Faculty of Science WaterlooON Canada Rhazes Lab Mayo Clinic Department of Artificial Intelligence and Informatics RochesterMN United States

ISBN: (纸本)9781665430654

Training Artificial Neural Networks (ANNs) poses a challenging and critical problem in machine learning. Despite the effectiveness of gradient-based learning methods, such as Stochastic Gradient Descent (SGD), in training neural networks, they do have several limitations. For instance, they require differentiable activation functions, and cannot optimize a model based on several independent non-differentiable loss functions simultaneously;for example, the F1-score, which is used during testing, can be used during training when a gradient-free optimization algorithm is utilized. Furthermore, the training (i.e., optimization of weights) in any DNN can be possible with a small size of the training dataset. To address these concerns, we propose an efficient version of the gradient-free Coordinate Search (CS) algorithm, an instance of General Pattern Search (GPS) methods, for training (i.e., optimizing) neural networks. The proposed algorithm can be used with non-differentiable activation functions and tailored to multi-objective/multi-loss problems. Finding the optimal values for weights of ANNs is a large-scale optimization problem. Therefore instead of finding the optimal value for each variable, which is the common technique in classical CS, we accelerate optimization and convergence by bundling the variables (i.e., weights). In fact, this strategy is a form of dimension reduction for optimization problems. Based on the experimental results, the proposed method is comparable with the SGD algorithm, and in some cases, it outperforms the gradient-based approach. Particularly, in situations with insufficient labeled training data, the proposed CS method performs better. The performance plots demonstrate a high convergence rate, highlighting the capability of our suggested method to find a reasonable solution with fewer function calls. As of now, the only practical and efficient way of training ANNs with hundreds of thousands of weights is gradient-based algorithms such

关键词： Artificial Neural Network (ANN) Coordinate Search Expensive Optimization Gradient-free Large-Scale Optimization Stochastic Gradient Descent (SGD)

来源：评论

学校读者我要写书评

暂无评论

Modified Metaheuristics with Transfer Learning Based Insect Pest Classification for Agricultural Crops

引用

computer Systems Science & engineering 2023年第9期46卷 3847-3864页

作者： Saud Yonbawi Sultan Alahmari T.Satyanarayana murthy Ravuri Daniel E.Laxmi Lydia Mohamad Khairi Ishak Hend Khalid Alkahtani Ayman Aljarbouh Samih M.Mostafa Department of Software Engineering College of Computer Science and EngineeringUniversity of JeddahJeddahSaudi Arabia King Abdul Aziz City for Science and Technology RiyadhKingdom of Saudi Arabia Chaitanya Bharathi Institute of Technology HyderabadTelanganaIndia Department of Computer Science and Engineering Prasad V.Potluri Siddhartha Institute of TechnologyVijayawadaIndia Department of Computer Science and Engineering GMR Institute of TechnologyAndhra PradeshRajamIndia School of Electrical and Electronic Engineering Engineering CampusUniversiti Sains Malaysia(USM)Nibong TebalPenangMalaysia Department of Information Systems College of Computer and Information SciencesPrincess Nourah Bint Abdulrahman UniversitySaudi Arabia Department of Computer Science University of Central AsiaNarynKyrgyzstan Faculty of Computers and Information South Valley UniversityQenaEgypt

Crop insect detection becomes a tedious process for agronomists because a substantial part of the crops is damaged,and due to the pest attacks,the quality is *** are the major reason behind crop quality degradation and diminished crop ***,accurate pest detection is essential to guarantee safety and crop *** identification of insects necessitates highly trained taxonomists to detect insects precisely based on morphological ***,some progress has been made in agriculture by employing machine learning(ML)to classify and detect *** study introduces a Modified Metaheuristics with Transfer Learning based Insect Pest Classification for Agricultural Crops(MMTL-IPCAC)*** presented MMTL-IPCAC technique applies contrast limited adaptive histogram equalization(CLAHE)approach for image *** neural architectural search network(NASNet)model is applied for feature extraction,and a modified grey wolf optimization(MGWO)algorithm is employed for the hyperparameter tuning process,showing the novelty of the *** last,the extreme gradient boosting(XGBoost)model is utilized to carry out the insect classification *** simulation analysis stated the enhanced performance of the MMTL-IPCAC technique in the insect classification process with maximum accuracy of 98.73%.

关键词： Sustainable agriculture crop monitoring pest management insect classification computer vision

来源：评论

学校读者我要写书评

暂无评论

Tools for Refactoring to Microservices: A Preliminary Usability Report

arXiv

引用

arXiv 2023年

作者： Fritzsch, Jonas Correia, Filipe Bogner, Justus Wagner, Stefan Institute of Software Engineering University of Stuttgart Germany Faculty of Engineering University of Porto Portugal Department of Computer Science Vrije Universiteit Amsterdam Netherlands

While Microservices are a preferred choice for modern cloud-based applications, the migration and architectural refactoring of existing legacy systems is still a major challenge in industry. To address this, academia has proposed many strategies and approaches that aim to automate the process of decomposing a monolith into functional units. In this study, we review existing migration approaches regarding techniques used and tool support. From 91 publications, we extracted 22 tools, 7 of which address service decomposition. To assess them from an end-user perspective, we investigated their underlying techniques, installation, documentation, usability and support. For 5 of them, we generated service cuts using reference applications. The results of our preliminary work suggest that the inspected tools pursue promising concepts, but lack maturity and generalizability for reliable use by industry. © 2023, CC BY.

关键词： Decomposition

来源：评论

学校读者我要写书评

暂无评论

Real-time Efficacy of Features Extraction using Machine Learning and Deep Learning for Frontal Alpha Asymmetry. 5

Real-time Efficacy of Features Extraction using Machine Lear...

引用

5th IEEE International Symposium in Robotics and Manufacturing Automation, ROMA 2022

作者： Hafeez, Yasir Ali, Syed Saad Azhar Amin, Hafeez Ullah Naqvi, Syed Faraz Adil, Syed Hasan Boon, Tang Tong University of Nottingham Malaysia School of Computer Science Faculty of Science and Engineering Semenyih43500 Malaysia Universiti Teknologi Petronas Centre for Intelligent Signal and Imaging Research Electrical and Electronics Engineering Department Perak Seri Iskandar32610 Malaysia University of Nottingham Malaysia Faculty of Science and Engineering School of Computer Science Semenyih43500 Malaysia Iqra University Software Engineering Department Karachi Pakistan

ISBN: (数字)9781665459327

ISBN: (纸本)9781665459327

The frontal alpha asymmetry represents as the neuromarker for stress. Stress is the psycho-physiological state of brain in response to some event or a demand. The continuous monitoring of mental stress is necessary to avoid chronic health issues. The real-time monitoring of frontal alpha asymmetry is necessary in daily life and to help in the therapy for example neurofeedback. In this paper, different approaches of machine learning and deep learning were adopted to extract the frontal alpha asymmetry features. The results analysis was based on the efficacy and the comparison of techniques for feature extraction has also been presented. © 2022 IEEE.

关键词： Feature extraction

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：