检索结果-内蒙古大学图书馆

6th International Congress on Blockchain and Applications, BLOCKCHAIN 2024

作者： Hernando-Corrochano, Jesús Pastor-Vargas, Rafael Hernández-Berlinches, Roberto Computer Science Department UC3M Getafe Spain Communications and Control Systems Department ETSII UNED Madrid Spain

ISBN: (纸本)9783031819278

The inheritance of digital assets is a complex issue requiring various regulations. Individuals leave behind vast digital footprints, including sensitive information that needs careful management after death. The article suggests using Blockchain technology and smart contracts for digital inheritance. It introduces roles like the digital executor and protocols for managing consent. This framework is currently being developed by the Spanish government. By planning your digital estate with these solutions, you can secure its management for future generations. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

A Comparative Study of Convolutional Neural Networks for Oregano Diseases Classification in A Novel Dataset 31

A Comparative Study of Convolutional Neural Networks for Ore...

引用

31st IEEE International Conference on Electronics, Electrical engineering and Computing, INTERCON 2024

作者： Chaparro-Cruz, Israel N. Santana-Carbajal, Oliver I. Osco-Mamani, Erbert F. Universidad Nacional Jorge Basadre Grohmann Department of Computer Science and Systems Engineering Tacna Peru

ISBN: (纸本)9798350378344

Peru is South America's largest producer and ex-porter of oregano (Origanum vulgare L.), with the Tacna region being the most significant contributor, cultivating 2,499 hectares and producing 11,946 tons, accounting for 65% of the national production. To mitigate the impact of oregano diseases, which lead to substantial crop losses and negatively affect the economy, it is crucial to develop and upgrade technologies for disease management. Accurate classification of oregano diseases can prevent quality deterioration and yield reductions. However, the availability of data and the use of advanced technologies in oregano cultivation are still in their early stages. This study addresses these shortcomings by developing and publishing a novel public dataset for the classification of the most common oregano diseases-Alternaria, Powdery Mildew (Oidium), and Mosaic-using crops from Susapaya - Tarata in Tacna, Peru. To classify oregano diseases, we conducted a comprehensive comparative study, applying Transfer Learning and Fine-Tuning techniques to evaluate the performance of VGG16, MobileNet, MobileNetV2, and NasNetLarge architectures with modifications in the classifier. The experiments revealed that: (i) Fine-Tuning improved validation set accuracy by 4.47% compared to Transfer Learning, (ii) the VGG16 architecture achieved the highest accuracy at 0.993921, (iii) MobileNet and MobileNetV2 models performed similarly, (iv) the NASNetLarge model showed poor performance when only Transfer Learning was applied, and (v) there was a strong significant relationship (R2= 0.84) between the number of parameters and size (in MB) with the performance of the architectures on our dataset. We ensure the reproducibility of the results by making the novel dataset and the best model publicly available on GitHub. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Comparative Study of Facial Expression Recognition Using Facial Landmark in e-Learning System 11

Comparative Study of Facial Expression Recognition Using Fac...

引用

11th International Conference on Electrical engineering, computer science and Informatics, EECSI 2024

作者： Bachtiar, Fitra Abdurrachman Nainggolan, Cesilia Natasya Soetedjo, Riza Setiawan Rokhmawati, Retno Indah Muflikhah, Lailil Brawijaya University Department of Informatics Engineering Faculty of Computer Science Malang Indonesia Brawijaya University Faculty of Computer Science Department of Information Systems Malang Indonesia

ISBN: (纸本)9798350355314

The e-Iearning system or distance learning system has become important, especially during the COVID-19 pan-demic. Several tertiary institutions have made the e-Iearning system an alternative teaching and learning activity. Research on the use of e-Iearning needs to be explored to obtain innovative, creative, and fun learning. One aspect that can be examined in e-learning is students' emotional response to the learning activities. The emotional state of students directly or indirectly affects the learning process. The student's emotional responses can be measured by their facial expressions. In this study, an exploration was carried out on the facial expressions shown by students in HSS Learning, an e-Iearning for learning web programming. The student's facial expressions were extracted using 68 pairs of facial landmarks and additional 6 facial feature vectors. The total number of features used is 142. Machine learning methods for classification are applied to determine the performance of several classification models, including the k-Nearest Neighbor (k- NN) algorithm, Logistic Regression, and Support Vector Machine (SVM). Machine learning performance evaluation is done using the Fl-score and confusion matrix. The results show that the accuracy of the k-NN, Logistic Regression, and SVM are 91.4%, 92.2%, and 92.1 %, respectively. However, the Fl-score macro values are relatively low due to data imbalance with the k- NN, Logistic Regression, and SVM models are 0.250, 0.272, and 0.243, respectively. While the study provides insight into the student learning experience in e-Iearning settings, this study needs to be explored more. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Skill Mastery Solutions: Your Path to Excellence 10

Skill Mastery Solutions: Your Path to Excellence

引用

10th International Conference on Advanced Computing and Communication systems, ICACCS 2024

作者： Saranya, E. Ajay, K. Hardika, S. Jayasudha, C. Kishore, R.E. Sri Eshwar College of Engineering and Technology Department of Computer Science and Business Systems Coimbatore India

ISBN: (数字)9798350384369

ISBN: (纸本)9798350384369

'Skillstorm' is an innovative and competitive website that harnesses the power of cutting-edge technologies to create a safe and engaging online environment. Developed primarily using Python and Flask, Skillstorm integrates machine learning algorithms to combat cyberbullying, ensuring a positive user experience. This project leverages HashMaps for efficient data management and employs a dynamic front-end interface built with HTML, CSS, and JavaScript. The backend of Skillstorm is powered by Python and Flask, providing a robust and scalable foundation for handling user data, interactions, and website functionality. Skillstorm utilizes machine learning techniques to automatically detect and mitigate instances of cyberbullying and harassment. This proactive approach ensures a safe and welcoming environment for all users. HashMaps are employed for efficient data storage and retrieval, optimizing the performance of the website and enhancing user experience. 'Skillstorm' represents a forward-thinking and comprehensive project that combines Python, Flask, machine learning, HashMaps, HTML, CSS, and JavaScript to create a competitive website that prioritizes user safety and positive interactions in an increasingly digital world. Powered by cutting-edge Python frameworks, we have created a dynamic and immersive experience that will ignite your passion, inspire excellence, and propel you to new heights of achievement. At SkillStorm, we believe that true talent knows no borders. © 2024 IEEE.

关键词： Python

来源：评论

学校读者我要写书评

暂无评论

Integrated Web-Based Platform for AI-Enhanced Autism Assessment 2

Integrated Web-Based Platform for AI-Enhanced Autism Assessm...

引用

2nd IEEE International Conference on Emerging Research in Computational science, ICERCS 2024

作者： Yasir Abdullah, R. Rk, Kamesh Kavin Prabu, S. Sri Subiksha, T. Venkatraman, P. Sri Krishna College of Engineering and Technology Department of Computer Science and Business Systems Coimbatore India

ISBN: (纸本)9798331534950

This research presents a novel web-based platform that leverages facial and vocal tracking to enhance the preliminary screening process for Autism Spectrum Disorder (ASD). By incorporating advanced machine learning algorithms to analyze multimodal data, the platform offers a non-invasive, accessible, and cost-effective solution for initial ASD evaluation. The system demonstrates high diagnostic accuracy, achieving 90% in facial pattern analysis, 85% in vocal pattern analysis, and 95% accuracy when both analyses are combined. Additionally, it includes communication features designed to foster a supportive environment for individuals with ASD. This paper provides an overview of the platform's development, functionality, and future potential, with an emphasis on its capacity to improve existing diagnostic methods and its accessibility for underserved communities. © 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

A Secure and Transparent Voting System Framework Using Finger Vein and Blockchain Technology 16

A Secure and Transparent Voting System Framework Using Finge...

引用

16th IEEE International Conference on Computational Intelligence and Communication Networks, CICN 2024

作者： Padal, Chittapuli Bhupathi Vatsavayi, Valli Kumari Andhra University College of Engineering Department of Computer Science and Systems Engieering Visakhapatnam530003 India

ISBN: (纸本)9798331505264

The traditional voting system faces widespread mistrust due to its vulnerability to exploitation, lack of transparency, and limited reliability, leading to concerns about the security of democratic rights. Attempts to digitize voting have also faced challenges, with current digital systems often failing to ensure the transparency and security necessary for fair elections. Both traditional and current digital voting systems are susceptible to exploitation, and their inherent weaknesses often lead to mistrust and vulnerability. This proposed solution is secure and transparent voting system framework that leverages finger vein recognition technique integrated with block chain technology to ensure the integrity and confidentiality of votes. Blockchain technology to create a more secure, transparent and reliable voting system. By utilizing blockchain, we aim to address the issues in both physical and digital voting systems, ensuring a fair election process that upholds voters' democratic rights. Blockchain technology offers a platform that maximizes transparency and reliability, fostering a trustworthy relationship between voters and election authorities. each Voter will be registered with Finger Vein as the password and this finger vein will be encrypted and secured by using Pepper-Salt algorithm. Our proposed framework allows voting activities to be conducted entirely online through blockchain, removing the need for physical polling stations. The system employs a scalable blockchain supported by flexible consensus algorithms, with a Chain Security Algorithm to enhance transaction security. © 2024 IEEE.

关键词： Voting machines

来源：评论

学校读者我要写书评

暂无评论

Recognition of American sign language using modified deep residual CNN with modified canny edge segmentation

引用

Multimedia Tools and Applications 2025年 1-28页

作者： Hariharan, U. Devarajan, Devikanniga Kumar, P. Santhosh Rajkumar, K. Meena, M. Akilan, T. Department of Computer Science and Engineering Apex Institute of Technology Chandigarh University Punjab Mohali140413 India Department of Computer Science and Engineering GITAM University Karnataka Bengaluru561203 India Department of Information Technology Faculty of Engineering and technology SRM Institute of Science and Technology Ramapuram Tamil Nadu Chennai600089 India Department of Data Science and Business Systems School of Computing Faculty of Engineering and Technology SRM Institute of Science and Technology Kattankulathur Tamil Nadu Chennai603203 India Department of Computer Science and Engineering Sri Sairam Engineering College Tamil Nadu Tambaram602109 India Research Coordinator Dept. of IQAC Amity University Kolkata West Bengal 700135 India

American Sign Language (ASL) recognition aims to recognize hand gestures, and it is a crucial solution to communicating between the deaf community and hearing people. However, existing sign language recognition algorithms still have some drawbacks, such as difficulty recognizing hand movements and low recognition accuracy for most sign language recognition. A Modified Convolutional Neural Network (MCNN) deep residual 101 classifier-based American Sign Language identification system has been developed to address this problem. There are three main parts presents in the method. The first part is pre-processing the images to remove the noise, enhance the contrast of the picture, adjust the contrast level and smoothen the picture using various filters. The second part is the segmentation, and it’s used to partition the image using a modified canny edge detection method by removing all weak edges present in the image. Finally, classification will be done using the Modified CNN deep residual 101 classifiers. By classifying the image, the American Sign Language is accurately identified. This process is conducted through images. The outcome shows that the suggested approach has a 0.97% accuracy and a 0.05% False Positive Rate. Other CNN architectures such as resNet 50 and resNet 18 reached 0.90% and 0.80% accuracy, respectively, which is lower than our proposed method. In addition, the resNet 101 classifier effectively recognizes the difficult hand gestures through the image data. It obtains high recognition accuracy for 36 signs is 0 to 9 numbers and a to z alphabets from American Sign Language. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

CounterFair: Group Counterfactuals for Bias Detection, Mitigation and Subgroup Identification 24

CounterFair: Group Counterfactuals for Bias Detection, Mitig...

引用

24th IEEE International Conference on Data Mining, ICDM 2024

作者： Kuratomi, Alejandro Lee, Zed Tsaparas, Panayiotis Junior, Guilherme Dinis Pitoura, Evaggelia Lindgren, Tony Papapetrou, Panagiotis Stockholm University Department of Computer and Systems Sciences Sweden University of Ioannina and Archimedes/Athena RC Department of Computer Science and Engineering Greece

ISBN: (纸本)9798331506681

Counterfactual explanations can be used as a means to explain a models decision process and to provide recommendations to users on how to improve their current status. The difficulty to apply these counterfactual recommendations from the users perspective, also known as burden, may be used to assess the models algorithmic fairness and to provide fair recommendations among different sensitive feature groups. We propose a novel model-agnostic, mathematical programming-based, group counterfactual algorithm that can: (1) detect biases via group counterfactual burden, (2) produce fair recommendations among sensitive groups and (3) identify relevant subgroups of instances through shared counterfactuals. We analyze these capabilities from the perspective of recourse fairness, and empirically compare our proposed method with the state-of-the-art algorithms for group counterfactual generation in order to assess the bias identification and the capabilities in group counterfactual effectiveness and burden minimization. © 2024 IEEE.

关键词： Algorithmic Fairness Counterfactual explanations Group counterfactuals Local explainability

来源：评论

学校读者我要写书评

暂无评论

Multi-Objective Optimization of Multi-Product Parallel Disassembly Line Balancing Problem Considering Multi-Skilled Workers Using a Discrete Chemical Reaction Optimization Algorithm

引用

computers, Materials & Continua 2024年第9期80卷 4475-4496页

作者： Xiwang Guo Liangbo Zhou Zhiwei Zhang Liang Qi Jiacun Wang Shujin Qin Jinrui Cao College of Information and Control Engineering Liaoning Petrochemical UniversityFushun113000China Department of Computer Science and Technology Shandong University of Science and TechnologyQingdao266590China Department of Computer Science and Software Engineering Monmouth UniversityWest Long BranchNJ 07764USA Research Center of the Economic and Social Development of Henan East Provincial Joint Shangqiu Normal UniversityShangqiu476000China Department of Computer Science New Jersey City UniversityJersey CityNJ 07305USA

This work investigates a multi-product parallel disassembly line balancing problem considering multi-skilled workers.A mathematical model for the parallel disassembly line is established to achieve maximized disassembly profit and minimized workstation cycle *** on a product’s AND/OR graph,matrices for task-skill,worker-skill,precedence relationships,and disassembly correlations are developed.A multi-objective discrete chemical reaction optimization algorithm is *** enhance solution diversity,improvements are made to four reactions:decomposition,synthesis,intermolecular ineffective collision,and wall invalid collision reaction,completing the evolution of molecular *** established model and improved algorithm are applied to ball pen,flashlight,washing machine,and radio combinations,*** a Collaborative Resource Allocation(CRA)strategy based on a Decomposition-Based Multi-Objective Evolutionary Algorithm,the experimental results are compared with four classical algorithms:MOEA/D,MOEAD-CRA,Non-dominated Sorting Genetic Algorithm Ⅱ(NSGA-Ⅱ),and Non-dominated Sorting Genetic Algorithm Ⅲ(NSGA-Ⅲ).This validates the feasibility and superiority of the proposed algorithm in parallel disassembly production lines.

关键词： Parallel disassembly line balancing problem multi-product multiskilled workers discrete chemical reaction optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Enhanced cyber-physical system with semantic technologies and machine learning to support smart farming 24

Enhanced cyber-physical system with semantic technologies an...

引用

24th International Conference on control systems and computer science, CSCS 2023

作者： Ciolofan, Sorin N. Dragoicea, Monica Popeanga, Daniel-Catalin Politehnica University of Bucharest Department of Computer Science Bucharest Romania Politehnica University of Bucharest Department of Automatic Control and Systems Engineering Bucharest Romania

ISBN: (纸本)9798350313390

An important aspect related to the effects of agricultural activities on the environment is represented by the nutrient loss in water and air (specifically nitrogen). The interactions between catchments hydrological processes, management of farm activities, climate changes and nitrogen losses constitute a complex phenomenon yet not well understood, being an important concern from the sustainable agriculture perspective. Nitrogen can be lost with water as leaching or runoff, or as gas as ammonia volatilization. Nitrous oxide (N2O) is particularly problematic because it is also a powerful greenhouse gas. The goal of the current article is to present innovative digital techniques to advance in understanding of this phenomena through an Information System that integrates Artificial Intelligence techniques such as Semantic Technologies and Machine Learning (ML) into Cyber-Physical systems (CPS) to support smart farming and sustainable agriculture. © 2023 IEEE.

关键词： Semantics

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：