检索结果-内蒙古大学图书馆

4th International Conference on Embedded and Distributed systems, EDiS 2024

作者： Khiat, Salim Ould Ali, Yasmine Polytechnic National School of Oran Computer Systems Engineering Department Oran31000 Algeria Polytechnic National School of Oran Computer Systems Engineering Department Oran31000 Algeria

ISBN: (数字)9798331519872

ISBN: (纸本)9798331519872

Decision tree algorithms are very useful approaches in data mining. Indeed, the C4.5 algorithm is a popular data classifier for machine learning. Nowadays there is a wide range of Big Data frameworks such as Hadoop and Apache spark. In this article, we present a comparative study of different implementations of the C4.5 algorithm in a Big Data environment. Then a new approach is proposed for the implementation of the parallel version of the C4.5 algorithm (PC4.5) based on the Apache Spark framework. Experimental results show the superiority of the proposed PC4.5 algorithm over its sequential version and the version on the Hadoop platform. © 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

Blockchain based Single Path and Multi-Path Routing in Payment Channel Network using Artificial Intelligence Techniques 2

Blockchain based Single Path and Multi-Path Routing in Payme...

引用

2nd IEEE International Conference on Integrated Intelligence and Communication systems, ICIICS 2024

作者： Swathi, Pothurajula Rao, Kasukurthi Venkata Department of Computer Science & Systems Engineering Andhra University College of Engineering Visakhapatnam India

ISBN: (纸本)9798331504960

Blockchain-based Payment Channel Network (PCN) routing for payment transactions includes the transfer of funds between multiple parties through a network of interconnected payment channels. These channels permit off-chain transactions, balance payment channels, enhance speed, and reduce the transaction costs. However, finding the best route for transactions between parties is challenging due to the dynamic nature of the network. The routing concept for PCN is divided as single-path routing and multi-path routing to enhance transactions based on the requirements of the users/organizations. Channel-based strategy, off-chain transactions, channel rebalancing techniques, and payment execution methods are considered essential in PCN transactions for an efficient routing. This study analyses the following methodologies: Deep Neural Network (DNN), Deep Reinforcement Learning (DRL), Graph NN (GNN), as well as genetic optimization algorithm utilized for efficient routing. Currently, distance-based methods like Markov chain-based routing are also being employed in PCN for finding an optimal path for payments. This survey examines the strengths and challenges of these Deep Reinforcement learning-based routing approaches. © 2024 IEEE.

关键词： Markov chains

来源：评论

学校读者我要写书评

暂无评论

GHA: a Gated Hierarchical Attention Mechanism for the Detection of Abusive Language in Social Media

引用

IEEE Transactions on Affective Computing 2024年第2期16卷 946-959页

作者： Jarquin-Vasquez, Horacio Escalante, Hugo Jair Montes-Y-Gomez, Manuel Gonzalez, Fabio A. Department of Computer Science Instituto Nacional de Astrofisica Óptica y Electrónica Puebla Mexico Department of Computer Systems and Industrial Engineering Universidad Nacional de Colombia Bogotá Colombia

The use of attention mechanisms in deep learning solutions has become popular within natural language processing tasks. The use of these mechanisms allows managing the relevance of the elements of a sequence in accordance with their context, however, this relevance has been observed independently between the pairs of elements of a sequence (self-attention) or between the application domain of a sequence (contextual attention), leading to the loss of relevant information and limiting the representation of the sequences. To tackle these particular issues, we propose a dual attention mechanism, which trades off the previous limitations, by considering the internal and contextual relationships between the elements of the sequence. Additionally, we propose the extension of the dual attention mechanism into a multi-layer perspective, through the weighted fusion of the different encoding layers of deep architectures. As the interpretation of abusive language is highly contextdependent, its identification is an ideal task to evaluate the proposed attention mechanism. Accordingly, we considered six standard collections for the abusive language identification task. The obtained results are encouraging;the proposed hierarchical attention mechanism outperformed the current self-attention and contextual attention mechanisms coupled with recurrent neural networks and Transformers, as well as, state-of-the-art approaches in detecting abusive language. © 2010-2012 IEEE.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Improvement of dynamic phosphene presentation for a cortical visual prosthesis is task-specific 46

Improvement of dynamic phosphene presentation for a cortical...

引用

46th Annual International Conference of the IEEE engineering in Medicine and Biology Society, EMBC 2024

作者： Wang, Haozhe Zac Wong, Yan Tat Monash University Department of Electrical and Computer Systems Engineering ClaytonVIC3800 Australia Monash University Department of Electrical and Computer Systems Engineering Department of Physiology ClaytonVIC3800 Australia

ISBN: (纸本)9798350371499

Cortical visual prostheses can restore vision by directly stimulating the neurons in the visual cortex. The goal of these prostheses is to elicit sufficient light perception, known as phosphenes, to represent complex scenes. However, stimulating a large number of electrodes in cortical visual prostheses can be problematic. This may result in distorted visual perception and failure to present the desired visual stimuli. Previous studies have successfully presented simple patterns, such as letters, by dynamically utilizing a single phosphene. To represent more complex scenes, we propose a new method of information presentation. This method limits the number of phosphenes elicited simultaneously while sequentially presenting the contours of a visual scene. We evaluated its effectiveness with 8 participants across four different tasks. We found that the improvement provided by this method is task-specific. Our findings underscore the importance of considering the temporal features of prosthetic vision in future designs. © 2024 IEEE.

关键词： Prosthetics

来源：评论

学校读者我要写书评

暂无评论

Deploying Hybrid Ensemble Machine Learning Techniques for Effective Cross-Site Scripting(XSS)Attack Detection

引用

computers, Materials & Continua 2024年第10期81卷 707-748页

作者： Noor Ullah Bacha Songfeng Lu Attiq Ur Rehman Muhammad Idrees Yazeed Yasin Ghadi Tahani Jaser Alahmadi School of Cyber Science and Engineering Huazhong University of Science and TechnologyWuhan430073China Department of Computer Science and Engineering University of Engineering and TechnologyLahore54000Pakistan Department of Computer Science and Software Engineering Al Ain UniversityAl Ain12555Abu Dhabi Department of Information Systems College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityRiyadh84428Saudi Arabia

Cross-Site Scripting(XSS)remains a significant threat to web application security,exploiting vulnerabilities to hijack user sessions and steal sensitive *** detection methods often fail to keep pace with the evolving sophistication of cyber *** paper introduces a novel hybrid ensemble learning framework that leverages a combination of advanced machine learning algorithms—Logistic Regression(LR),Support Vector Machines(SVM),eXtreme Gradient Boosting(XGBoost),Categorical Boosting(CatBoost),and Deep Neural Networks(DNN).Utilizing the XSS-Attacks-2021 dataset,which comprises 460 instances across various real-world trafficrelated scenarios,this framework significantly enhances XSS attack *** approach,which includes rigorous feature engineering and model tuning,not only optimizes accuracy but also effectively minimizes false positives(FP)(0.13%)and false negatives(FN)(0.19%).This comprehensive methodology has been rigorously validated,achieving an unprecedented accuracy of 99.87%.The proposed system is scalable and efficient,capable of adapting to the increasing number of web applications and user demands without a decline in *** demonstrates exceptional real-time capabilities,with the ability to detect XSS attacks dynamically,maintaining high accuracy and low latency even under significant ***,despite the computational complexity introduced by the hybrid ensemble approach,strategic use of parallel processing and algorithm tuning ensures that the system remains scalable and performs robustly in real-time *** for easy integration with existing web security systems,our framework supports adaptable Application Programming Interfaces(APIs)and a modular design,facilitating seamless augmentation of current *** innovation represents a significant advancement in cybersecurity,offering a scalable and effective solution for securing modern web applications against evolving threats.

关键词： Cross-site scripting machine learning XSS detection stacking ensemble learning hybrid learning

来源：评论

学校读者我要写书评

暂无评论

CNN based Android Application for Accurate Fruit Classification 15

CNN based Android Application for Accurate Fruit Classificat...

引用

15th International Conference on Advances in Computing, Control, and Telecommunication Technologies, ACT 2024

作者： Lalitha, A.S. Nageswararao, K. Department of Computer Science and Engineering Andhra University Visakhapatnam India Department of Computer Science and Systems Engineering Andhra University Visakhapatnam India

ISBN: (纸本)9798331300579

This exploration paper presents a versatile application created involving Android Studio for organic product characterization, supporting ranchers in effectively classifying organic products in view of their visual elements. The Android application is based on Android Studio 8.0.1, a strong incorporated improvement device intended for the Android working framework. The essential goal of the portable application is to work with the arrangement of natural products as new, ready, or spoiled. The application incorporates a custom Convolutional Neural Network (CNN) model for precise classification. The CNN model is prepared on a dataset containing different natural product pictures, empowering it to perceive The application permits ranchers to catch pictures of natural products utilizing their gadget's camera or select pictures from the exhibition. The caught pictures are then handled through the coordinated CNN model, giving ongoing grouping results to *** innovation driven arrangement engages ranchers to settle on educated conclusions about the quality regarding their produce, subsequently upgrading agrarian administration and limiting waste. It is accessible and beneficial to farmers in a variety of settings due to the user-friendly interface's seamless usability. The paper digs into the application's improvement cycle, including its design and CNN model reconciliation. Specific consideration is given to upgrading execution across different Android gadgets, guaranteeing solid usefulness in pragmatic situations. This study is a significant step toward incorporating cutting-edge technology into agriculture, transforming farmer processes for fruit classification. The application's adequacy and exactness feature its capability to upgrade dynamic cycles and generally rural efficiency. © Grenze Scientific Society, 2024.

关键词： Fruits

来源：评论

学校读者我要写书评

暂无评论

ROUTESENSE - An AI powered solution to Car pooling systems 10

ROUTESENSE - An AI powered solution to Car pooling systems

引用

10th International Conference on Communication and Signal Processing, ICCSP 2024

作者： Poornimathi, K. Deepak Kumar, A. Srinithi, A. Rajalakshmi Engineering College Department of Computer Science and Business Systems India

ISBN: (纸本)9798350353068

Revolutionizing the urban commuting by introducing a ground-breaking AI-powered carpooling portal. This comprehensive platform provides an ultimate solution combining all the latest technologies for transportation challenges. The system ensures effortless scalability and real-time synchronization of user profiles, tip histories and route information across devices. Using the integration of emerging technologies such as Artificial intelligence and Machine learning algorithms, commuters are given a unique advantage of having a seamless travel and an optimized cost for the travel using AI and ML models and they are matched based on their preferences, schedules and historical data that makes the travel more convenient. The system also provides enhanced route security by analyzing the geospatial information to suggest the safest and most efficient routes for carpooling groups. It also streamlines the billing process by introducing Robotic process automation (RPA), ensuring accurate and tamper-free billing process for the carpooling groups. This combination of different technologies makes carpooling into a sophisticated, seamless and efficient mode of sustainable transportation that also is secure while delivering unparalleled convenience and peace of mind to its users. © 2024 IEEE.

关键词： Robotics

来源：评论

学校读者我要写书评

暂无评论

Revitalizing Paddy Yields with computer Vision 2

Revitalizing Paddy Yields with Computer Vision

引用

2nd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2024

作者： Siva M.e, K.P. Vibin, K.C. Kaarnika, A. Ramkumar, T.R. Priyanka, D. SriEshwarCollege of Engineering Department of Computer Science and Business Systems Coimbatore India

ISBN: (纸本)9798350327533

A groundbreaking innovation in the field of plant science revolutionizes the precise identification of nutrient deficiencies in paddy plants through meticulous leaf analysis. The methodology commences by breaking down input leaf images into manageable blocks, subsequently subjecting them to rigorous evaluation using specialized convolutional neural networks (CNNs), each meticulously trained to discern specific nutrient deficiencies. The advanced network architecture systematically scrutinizes these blocks for characteristic deficiency symptoms. To achieve an all-encompassing evaluation of the leaf's condition, the responses generated by all CNNs are aggregated, and a multi-layer perceptron synthesizes them into a singular block response. The proposed approach results in a comprehensive assessment of the overall leaf health. In a comprehensive study encompassing seven different deficiency types - including Nitrogen (N), Phosphorus (P), Potassium (K), and Zinc (Zn) deficiencies - a vast dataset comprising 2,750 carefully collected leaf images was employed. The results demonstrate the proposed method's superiority, surpassing the accuracy of expert human assessments in identifying various nutrient deficiencies. The proposed method harnesses the power of CNNs, effectively merging the image analysis, machine learning, and Convolutional Neural Networks (CNNs) to propel nutrient deficiency analysis in paddy plants to unprecedented heights. © 2024 IEEE.

关键词： Convolutional Neural Networks Image Segmentation Leaf Analysis Machine Learning Nutrient Deficiency

来源：评论

学校读者我要写书评

暂无评论

SIMULATION-BASED OPTIMIZATION FOR DRIVING INNOVATION IN MANUAL ORDER PICKING FOR A WHOLESALE COMPANY 38

SIMULATION-BASED OPTIMIZATION FOR DRIVING INNOVATION IN MANU...

引用

38th ECMS International Conference on Modelling and Simulation, ECMS 2024

作者： Legato, Pasquale Mazza, Rina Mary Department of Computer Engineering Modeling Electronics and Systems University of Calabria Italy

This paper considers organization and practice innovation in a typical warehousing system which acts as a distribution site for groceries and miscellaneous to final retailers. The need of integrating tactical decisions regarding storage positions in a rack-based system with operational decisions for retrieving palletized items, under an S-shape policy, calls for a simulation-based optimization approach. The unavoidable stochastic features in order arrivals and composition, coupled with the natural uncertainty related to the human operated order-picking process under interferences and queueing, suggests resorting to a detailed discrete-event simulation. We propose a system-generating algorithm to integrate the combinatorial tactical choices for storage positions. The search process for the best storage configurations is the core of our simulation optimization framework in conjunction with an effective ranking and selection procedure. Numerical results on scenario comparison and possible improvements in productivity for a specific order-picking process are presented, using data and rules from a real wholesale company. ©ECMS Daniel Grzonka, Natalia Rylko, Grazyna Suchacka, Vladimir Mityushev (Editors) 2024.

关键词： Warehouses

来源：评论

学校读者我要写书评

暂无评论

A sentiment analysis of the Ukraine-Russia War tweets using knowledge graph convolutional networks

引用

International Journal of Information Technology (Singapore) 2025年 1-18页

作者： Menaouer, Brahami Fairouz, Safa Meriem, Mohammed Boulekbachi Mohammed, Sabri Nada, Matta LABAB Laboratory Computer Systems Engineering Department National Polytechnic School of Oran Oran Algeria Computer Systems Engineering Department National Polytechnic School of Oran Oran Algeria TechCICO Laboratory University of Technology of Troyes Troyes France

Nowadays, social networks play a critical role in online social discourse, particularly during major events such as elections, health crises, and wars. Furthermore, individuals have spent significant time on social networks that consume news and express their opinions and viewpoints on various topics, namely, the Russia-Ukraine War. The Ukraine-Russia War is one of the most complicated and unfortunate events of this decade, with many aspects to be considered to have an informed opinion. For this reason, sentiment analysis research can be useful in analyzing sentiments or opinions about the Ukraine-Russia war, such as Twitter (X) posts. In this study, we propose a new deep learning-based sentiment classification model called "Knowledge Graph Convolutional Networks" that predicts and analyzes sentiments concerning the Russia-Ukraine war. There were 500,000 tweets collected in total, however only 410,428 were left for sentiment analysis after cleaning, lemmatization stemming, and deleting duplicate tweets. Results show that "war", "people", "world", "putin", "energy", "gas", "weapon", and "peace" were some of the most frequently occurring words in the tweets. The main aim of this work is to develop a robust system that provides an understanding of public sentiment towards the Russia-Ukraine war on the X platform. Experimental results demonstrate that it is possible to obtain more accurate sentiment classification results by the proposed method. They also have managerial, economic, and research implications. © Bharati Vidyapeeth's Institute of computer Applications and Management 2024.

关键词： Classification Decision support systems Graph Convolutional Networks (GCN) Knowledge graph Knowledge management Opinion mining Twitter sentiment analysis Ukraine-Russia War

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：