检索结果-内蒙古大学图书馆

35th GI-Workshop on Foundations of Database systems, GvDB 2024

作者： Zamankhani, Saba TU Ilmenau Department of Computer Science and Automation Databases and Information Systems Group Germany

Many physical systems in the real world exhibit complex behavior, making it difficult to identify their dynamics. To overcome this problem, prototypes are created to provide a better insight into the behavior of such systems. However, building these prototypes using traditional methods is often slow due to the computational intensity required to accurately capture the detailed complexities within these systems and the large parameter space that needs to be explored. Data-driven approaches, such as machine learning and deep learning frameworks, have the potential to significantly speed up this process by generalizing the model. In this study, we explore the use of such an approach to understand the complex and non-linear behavior of dynamical systems, using resistive random access memory (ReRAM) devices as a case study. It is important to emphasize that modeling ReRAM is only one specific example in our wider investigation, which aims to design predictive models for a range of non-linear dynamical systems. Our work attempts to overcome the limitations of traditional research and development by using neural networks to reproduce the complex behavior of ReRAM cells accurately. We introduce a hybrid dual-input neural network architecture (HDiNN), equipped with a custom loss function, to capture both spatial and temporal patterns, improving the predictability of cell behavior under different conditions. This involves integrating important factors such as material properties, device geometry, and electrical interactions into our model to explain the complexities of ReRAM technology. However, our ambitions extend far beyond ReRAM to develop methods to help create innovative, durable solutions in various fields. This study highlights the impact of predictive modeling in advancing materials science and demonstrates the transformative potential of neural networks in improving the design and optimization of future technologies. © 2024 Copyright for this paper by its authors.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

SonicGlass: An Obstacle Detection and Navigation System Using Smartglass-Based Ultrasonic Sensors 16

SonicGlass: An Obstacle Detection and Navigation System Usin...

引用

16th International Conference on COMmunication systems and NETworkS, COMSNETS 2024

作者： Kusneniwar, Hrishikesh Govindrao Ghosh, Surjya Sen, Sougata Bits Pilani Dept. of Computer Science and Information Systems Goa campus India

ISBN: (纸本)9798350383119

Enabling continuous obstacle detection and providing real-time navigational assistance for people with visual impairment allows them to navigate in an indoor space without dependence on others. In this paper, we present the design, development, and evaluation of SonicGlass, a wearable obstacle detection and indoor navigation system. SonicGlass consists of a custom 3D printed wearable smartglass that can replace the individual's existing smartglasses. The smartglass is embedded with multiple sensors and microcontrollers. We performed a user study with 10 participants to determine the performance of SonicGlass and observed that SonicGlass could easily guide individuals in an indoor space while detecting obstacles with an F1-score of 84.7% (at 100% precision), and yielded a localization error of 1.35 meters when using a very simplistic regression model. Overall, SonicGlass can be a helpful tool for people with visual impairment to navigate in indoor spaces without assistance. © 2024 IEEE.

关键词： Accessibility Indoor Navigation Obstacle Detection smartglass Wearable Sensing

来源：评论

学校读者我要写书评

暂无评论

A hybrid wrapper technique enabled Network Intrusion Detection System for Software defined networking based IoT networks 3

A hybrid wrapper technique enabled Network Intrusion Detecti...

引用

3rd International Conference on Artificial Intelligence For Internet of Things, AIIoT 2024

作者： Ramaiah, Mangayarkarasi Padma, Adla Vishnukumar, Ravula Rahamathulla, Mohemmed Yousuf Chithanuru, Vasavi Vellore Institute of Technology School of Computer Science Engineering and Information Systems Vellore India

ISBN: (纸本)9798350372120

In the age of smart era, usage of IoT devices is inevitable. As the number of IoT devices increases, the amount of data they generate also increases, which in turn leads to security breaches. Continuous monitoring through SDN is the appropriate solution to mitigate security breaches. SDN introduces a new architecture where the control plane operates independently of the data plane. While this design allows applications in the base plane to interact with network components via the controller, it also creates security concerns. An attacker could exploit vulnerabilities in the control plane, potentially leading to significant data breaches. Amid a lot of research in various venues to address the security aspects of SDN, a simple and robust Intrusion detection system is necessary for the current context. Hence, a hybrid-wrapped enabled feature selection RF-RFE has been included in determining the highly influential features upon the derived features and a fine-tuned machine learning-based model to detect the anomalies at the earliest possible in the context of SDN has been trained and tested on SDN-IoT dataset. The tested results reveal that RF-based RF-RFE-SDNIoT-NIDS obtained 99% of its binary and multi-classification accuracy using minimal features compared to other machine learning models. © 2024 IEEE.

关键词： Intrusion detection

来源：评论

学校读者我要写书评

暂无评论

Developing and Applying a Neural Network System for Text Plagiarism Detection in Higher Education 4

Developing and Applying a Neural Network System for Text Pla...

引用

4th International Conference on Technology Enhanced Learning in Higher Education, TELE 2024

作者： Kuksa, Vitaliy Polyakov, Maxim Volgograd State University Depart. of Information Systems and Computer Modeling Volgograd Russia

ISBN: (纸本)9798350353532

This article focuses on the development and features of applying a neural network system for text plagiarism detection in higher education. In the context of the rapid growth in the availability of open information resources, the problem of academic honesty is becoming increasingly important. This article presents an approach that uses machine learning techniques, specifically a fully-connected neural network, to automatically detect plagiarism in academic and research works. The main stages of dataset creation, model development, and training are discussed, and the results of applying the model in practice are analyzed. Based on the test results, the average absolute error for the architecture with two hidden layers was found to be 9.38. The results of the study demonstrate the effectiveness of the proposed system in identifying plagiarism, making it a valuable tool to promote academic integrity and ensure educational quality. © 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

Evaluation of Modern Generative Networks for EchoCG Image Generation

引用

computers, Materials & Continua 2024年第12期81卷 4503-4523页

作者： Sabina Rakhmetulayeva Zhandos Zhanabekov Aigerim Bolshibayeva Department of Cybersecurity Information Processing and StorageSatbayev UniversityAlmaty050000Kazakhstan Department of Mathematical Computer Modeling International IT UniversityAlmaty050000Kazakhstan Department of Information Systems International IT UniversityAlmaty050000Kazakhstan

The applications of machine learning(ML)in the medical domain are often hindered by the limited availability of high-quality *** address this challenge,we explore the synthetic generation of echocardiography images(echoCG)using state-of-the-art generative *** conduct a comprehensive evaluation of three prominent methods:Cycle-consistent generative adversarial network(CycleGAN),Contrastive Unpaired Translation(CUT),and Stable Diffusion 1.5 with Low-Rank Adaptation(LoRA).Our research presents the data generation methodol-ogy,image samples,and evaluation strategy,followed by an extensive user study involving licensed cardiologists and surgeons who assess the perceived quality and medical soundness of the generated *** findings indicate that Stable Diffusion outperforms both CycleGAN and CUT in generating images that are nearly indistinguishable from real echoCG images,making it a promising tool for augmenting medical ***,we also identify limitations in the synthetic images generated by CycleGAN and CUT,which are easily distinguishable as non-realistic by medical *** study highlights the potential of diffusion models in medical imaging and their applicability in addressing data scarcity,while also outlining the areas for future improvement.

关键词： Synthetic image generation synthetic echogcardiography generative adversarial networks CycleGAN latent diffusion models stable diffusion

来源：评论

学校读者我要写书评

暂无评论

Dynamic and Energy Efficient Data Traffic Scheduling for Earlier Forest Fire Detection using WSN 2

Dynamic and Energy Efficient Data Traffic Scheduling for Ear...

引用

2nd International Conference on Emerging Trends in information Technology and Engineering, ic-ETITE 2024

作者： Swetha, R. Navaneethan, C. School of Computer Science Engineering and Information Systems Vellore Institute of Technology Vellore India

ISBN: (纸本)9798350328202

In general, data traffic volume is significant in sensor networks, and communication often occurs with variable capacity during early forest fire detection using Wireless Sensor Networks (WSN). Initially, optimal routes are determined by selecting the best prime nodes. Subsequently, packets are dynamically scheduled based on the severity of the data traffic associated with detecting forest fires. The selection of dominant weighted nodes is a crucial initial stage, and these nodes are chosen for optimal routing, taking into consideration factors such as distance and energy criteria. The second stage involves the dynamic scheduling of packets, ensuring that they are sent based on packet priority, queue index value, and the urgency of forest fire detection. This process aims to minimize congestion and prevent unnecessary transmission delays, contributing to the efficient and timely detection of forest fires using WSN. © 2024 IEEE.

关键词： Fires

来源：评论

学校读者我要写书评

暂无评论

Optimizing Real-Time Bidding Strategies: An Experimental Analysis of Reinforcement Learning and Machine Learning Techniques 2

Optimizing Real-Time Bidding Strategies: An Experimental Ana...

引用

2nd International Conference on Machine Learning and Data Engineering, ICMLDE 2023

作者： Jha, Arti Jain, Harshit Sharma, Parikshit Sharma, Yashvardhan Tiwari, Kamlesh Department of Computer Science and Information Systems Birla Institute of Technology and Science Pilani India

This research provides an experimental analysis and comparison of several RTB (real-time bidding) methods. These experiments are based on practical validation through the utilization of real-world datasets, with the primary attention being placed on the dynamic and complex nature of the RTB ecosystem. Simulations are run on various real-world advertising campaigns as part of the experimentation. These simulations take into account different campaign budgets, bid request dynamics, and user interaction pattern variations. The efficiency of each algorithm is evaluated based on performance indicators such as click-through rates (CTRs), conversion rates (CR), return on investment (ROI), win rates, cost per mille (CPM), and effective cost per click (E-CPC). The results provide useful insights into the advantages and disadvantages of each technique used, and the experimental analysis indicates the Constrained Markov Decision Process (CMDP)-based model as a promising and superior technique for RTB optimization. It provides valuable information on applications of reinforcement learning in the dynamic RTB ecosystem. Hence, via these comparisons, this paper aims to contribute to the advancement of RTB methodologies and proposes a viable route for future research. © 2024 Elsevier B.V.. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Automated Autism Spectral Disorder Classification Using Optimal Machine Learning Model

引用

computers, Materials & Continua 2023年第3期74卷 5251-5265页

作者： Hanan Abdullah Mengash Hamed Alqahtani Mohammed Maray Mohamed K.Nour Radwa Marzouk Mohammed Abdullah Al-Hagery Heba Mohsen Mesfer Al Duhayyim Department of Information Systems College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Information Systems College of Computer ScienceCenter of Artificial Intelligence and Unit of CybersecurityKing Khalid UniversityAbhaSaudi Arabia Department of Information Systems College of Computer ScienceKing Khalid UniversityAbhaSaudi Arabia Department of Computer Sciences College of Computing and Information SystemUmm Al-Qura UniversitySaudi Arabia Department of Computer Science College of ComputerQassim UniversitySaudi Arabia Department of Computer Science Faculty of Computers and Information TechnologyFuture University in EgyptNew Cairo11835Egypt Department of Computer Science College of Sciences and Humanities-AflajPrince Sattam bin Abdulaziz UniversitySaudi Arabia

Autism Spectrum Disorder (ASD) refers to a neuro-disorder wherean individual has long-lasting effects on communication and interaction *** information technologywhich employs artificial intelligence(AI) model has assisted in early identify ASD by using pattern *** advances of AI models assist in the automated identification andclassification of ASD, which helps to reduce the severity of the *** study introduces an automated ASD classification using owl searchalgorithm with machine learning (ASDC-OSAML) model. The proposedASDC-OSAML model majorly focuses on the identification and classificationof ASD. To attain this, the presentedASDC-OSAML model follows minmaxnormalization approach as a pre-processing stage. Next, the owl searchalgorithm (OSA)-based feature selection (OSA-FS) model is used to derivefeature subsets. Then, beetle swarm antenna search (BSAS) algorithm withIterative Dichotomiser 3 (ID3) classification method was implied for ASDdetection and classification. The design of BSAS algorithm helps to determinethe parameter values of the ID3 classifier. The performance analysis of theASDC-OSAML model is performed using benchmark dataset. An extensivecomparison study highlighted the supremacy of the ASDC-OSAML modelover recent state of art approaches.

关键词： Autism spectral disorder machine learning owl search algorithm feature selection id3 classifier

来源：评论

学校读者我要写书评

暂无评论

Intelligent Connected Vehicle Intrusion Detection and Mitigation: An Analysis of Explainable AI 4

Intelligent Connected Vehicle Intrusion Detection and Mitiga...

引用

4th IEEE International Conference on Emerging Techniques in Computational Intelligence, ICETCI 2024

作者： Vishnukumar, Ravula Padma, Adla Ramaiah, Mangayarkarasi School of Computer Science Engineering and Information Systems Vellore Institute of Technology Vellore India

ISBN: (纸本)9798350387063

IoT and AI created a Transportation Management System, resulting in the Internet of Vehicles. Intelligent vehicles are combined with contemporary communication technologies (5G) to achieve automated driving and adequate mobility. IoV faces security issues in the next five (5) areas: data safety, V2X communication safety, platform safety, Intermediate Commercial Vehicles (ICV) safety, and intelligent device safety. Numerous types of AI models have been created to reduce the outcome infiltration risks on ICVs. The need to integrate confidence, transparency, and repeatability into the creation of Artificial Intelligence (AI) for the safety of ICV and to deliver harmless transport systems, on the other hand, has led to an increase in explainable AI (XAI). Therefore, the space of this analysis protected the XAI models employed in ICV intrusion detection systems (IDSs), their taxonomies, and available research concerns. The study's findings demonstrate that, despite its relatively recent submission to ICV, XAI is a potential explore area for those looking to increase the net effect of ICVs. The paper also demonstrates that XAI's greater transparency will help it gain acceptance in the vehicle industry. © 2024 IEEE.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

GA-Stacking:A New Stacking-Based Ensemble Learning Method to Forecast the COVID-19 Outbreak

引用

computers, Materials & Continua 2023年第2期74卷 3945-3976页

作者： Walaa N.Ismail Hessah A.Alsalamah Ebtesam Mohamed Department of Management Information Systems College of Business AdministrationAl Yamamah UniversityRiyadh11512Saudi Arabia Faculty of Computers and Information Minia UniversityMinia61519Egypt Information Systems Department College of Computer and Information SciencesKing Saud UniversityRiyadh4545Saudi Arabia Computer Engineering Department College of Engineering and ArchitectureAl Yamamah UniversityRiyadh11512Saudi Arabia

As a result of the increased number of COVID-19 cases,Ensemble Machine Learning(EML)would be an effective tool for combatting this pandemic *** ensemble of classifiers can improve the performance of single machine learning(ML)classifiers,especially stacking-based ensemble *** utilizes heterogeneous-base learners trained in parallel and combines their predictions using a meta-model to determine the final prediction ***,building an ensemble often causes the model performance to decrease due to the increasing number of learners that are not being properly ***,the goal of this paper is to develop and evaluate a generic,data-independent predictive method using stacked-based ensemble learning(GA-Stacking)optimized by aGenetic Algorithm(GA)for outbreak prediction and health decision aided ***-Stacking utilizes five well-known classifiers,including Decision Tree(DT),Random Forest(RF),RIGID regression,Least Absolute Shrinkage and Selection Operator(LASSO),and eXtreme Gradient Boosting(XGBoost),at its first *** also introduces GA to identify comparisons to forecast the number,combination,and trust of these base classifiers based on theMean Squared Error(MSE)as a fitness *** the second level of the stacked ensemblemodel,a Linear Regression(LR)classifier is used to produce the final *** performance of the model was evaluated using a publicly available dataset from the Center for systems Science and Engineering,Johns Hopkins University,which consisted of 10,722 data *** experimental results indicated that the GA-Stacking model achieved outstanding performance with an overall accuracy of 99.99%for the three selected ***,the proposed model achieved good performance when compared with existing baggingbased *** proposed model can be used to predict the pandemic outbreak correctly and may be applied as a generic data-independent model 3946 CMC,2023,vol.74,no.2 to pre

关键词： COVID-19 ensemble machine learning genetic algorithm machine learning stacking ensemble unbalanced dataset vaccine

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：