检索结果-内蒙古大学图书馆

Delhi Section Conference (DELCON), IEEE

作者： Manu Sharanya Bhadriraju Kishorebabu Dasari Computer Science and Engineering Department Keshav Memorial Institute of Technology Hyderabad Telangana India Computer Science and Engineering (AI&ML) Department Keshav Memorial Institute of Technology Hyderabad Telangana India

ISBN: (数字)9798331518592

ISBN: (纸本)9798331518608

One of the most destructive cyber-attacks nowadays is Distributed Denial of Service (DDoS). A Simple Service Discovery Protocol (SSDP) DDoS attack is established by using the advantage of holes in the Simple Service Discovery Protocol to overwhelm a victim network. Early SSDP DDoS attack detection is essential for minimizing consequences. The SSDP DDoS attack detection is analyzed in this work using various Naïve Bayes classifier types, including Gaussian, Bernoulli, Multinomial, and Complement. For feature selection, this study used various wrapper methods such as Forward Feature Selection, Backward Feature Elimination, and Recursive Feature Elimination. The CIC-DDoS2019 dataset is used in this study. The assessment measures used in this study were accuracy, K-Fold Cross-Validation accuracy, ROC-AUC, and log-loss values. Bernoulli Naïve Bayes classifier gives best accuracy value 99.96 with all feature subsets.

关键词： Accuracy Protocols Denial-of-service attack Feature extraction Reflection Naive Bayes methods Classification algorithms computer crime Cyberattack

来源：评论

学校读者我要写书评

暂无评论

Neural Networks Meet Neural Activity: Utilizing EEG for Mental Workload Estimation 27th

Neural Networks Meet Neural Activity: Utilizing EEG for Ment...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Siddhad, Gourav Roy, Partha Pratim Kim, Byung-Gyu Department of Computer Science and Engineering Indian Institute of Technology Roorkee Uttarakhand Roorkee247667 India Division of AI Engineering Sookmyung Women’s University Seoul04310 Korea Republic of

ISBN: (纸本)9783031781940

Electroencephalography (EEG) offers non-invasive, real-time mental workload assessment, which is crucial in high-stakes domains like aviation and medicine and for advancing brain-computer interface (BCI) technologies. This study introduces a customized ConvNeXt architecture, a powerful convolutional neural network, specifically adapted for EEG analysis. ConvNeXt addresses traditional EEG challenges like high dimensionality, noise, and variability, enhancing the precision of mental workload classification. Using the STEW dataset, the proposed ConvNeXt model is evaluated alongside SVM, EEGNet, and TSception on binary (No vs SIMKAP task) and ternary (SIMKAP multitask) class mental workload tasks. Results demonstrated that ConvNeXt significantly outperformed the other models, achieving accuracies of 95.76% for binary and 95.11% for multi-class classification. This demonstrates ConvNeXt’s resilience and efficiency for EEG data analysis, establishing new standards for mental workload evaluation. These findings represent a considerable advancement in EEG-based mental workload estimation, laying the foundation for future improvements in cognitive state measurements. This has broad implications for safety, efficiency, and user experience across various scenarios. Integrating powerful neural networks such as ConvNeXt is a critical step forward in non-invasive cognitive monitoring. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Smart Home Automation Using ai and IoT with High Security 2

Smart Home Automation Using AI and IoT with High Security

引用

2nd International Conference on Advancements in Smart, Secure and Intelligent Computing, ASSIC 2024

作者： Rani, K. Pushpa Sreedevi, Pogula Veeranjaneyulu, P. Kanth, M. Ravi Allam, Sangeetha Mohanty, Jnyana Ranjan Mlr Institute of Technology Department of Computer Science Engineering Hyderabad500043 India G.Pulla Reddy Engineering College Department of Computer Science and Engineering Kurnool518007 India and Ai&ds Hyderabad India Vnr Vignana Jyothi Institute of Engineering and Technology Department of Cse Hyderabad India Mlr Institute of Technology Department of Computer Science & Engineering Hyderabad India Kalinga Institute of Industrial Technology University India

ISBN: (纸本)9798350370188

A well-known and widely utilized technology is smart home automation. The project's primary goal is to create an android-based, Wi-Fi enabled home automation which makes our daily life simpler and easier. in every automation technology which uses internet of things which is a developing network of common items that can share information and carry out tasks while you are occupied with other activities, from industrial machinery to consumer goods. A system known as a Wireless Home Automation System (WHAS) integrating ai & IOT allows users to remotely control common home features and operations using PCs or mobile devices. Both human and electric energy are to be conserved. Because it permits, there is a difference between other systems and home automation systems. © 2024 IEEE.

关键词： Automation

来源：评论

学校读者我要写书评

暂无评论

Sentiment Analysis for E-Commerce Product Reviews Using CNN-LSTM 1

Sentiment Analysis for E-Commerce Product Reviews Using CNN-...

引用

1st International Conference for Women in Computing, InCoWoCo 2024

作者： Paul, Priti Acharya, Soubhik Misra, Bitan Majumder, Soumi Dey, Nilanjan Pise, Priya Techno International New Town West Bengal Department of Computer Science and Engineering India Lincoln University Department of Business Malaysia Indira College of Engineering and Management Department of AI &dS Pune India

ISBN: (纸本)9798331518943

Due to the exponential growth of the number of user-generated reviews on e-commerce platforms, sentiment analysis has emerged for analyzing consumer opinions. This study aims to classify consumer sentiment by analyzing reviews from a product review dataset collected from a public repository. The aim is to develop a novel hybrid convolutional neural network (CNN) - long short-term memory (LSTM) model for classifying product reviews into positive, negative, and neutral sentiment categories. The proposed methodology of this study includes data preprocessing and feature extraction via natural language processing techniques to ensure that the data that are fed into the model can capture intricate patterns for the classification of sentiments. The CNN-LSTM hybrid model was employed for the sentiment classification of customer reviews because it combines the architecture of CNNs to handle spatial dependencies and LSTMs to address long-term dependencies, which leads to increased overall performance and efficiency in the text data. The findings indicate that the hybrid CNN-LSTM model significantly outperforms traditional methods and other state-of-the-art architectures in terms of accuracy, precision, recall, and an F1 score of 98%. This investigation contributes to the field by providing evidence from empirical studies on an effective approach toward sentiment classification, which can further assist business organizations in making strategic decisions on the basis of customer feedback. © 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

Human Activity Recognition Using Improved Cat Swarm Optimization Algorithm and Convolutional Neural Network 2

Human Activity Recognition Using Improved Cat Swarm Optimiza...

引用

2nd IEEE International Conference on Networks, Multimedia and Information Technology, NMITCON 2024

作者： Chanti, Yerrolla Shnain, Ammar Hameed Banoth, Ramesh Rupavath, Rana Veer Samara Sihman Brahmatej Sushama, C. Sr University School of Computer Science & Artificial Intelligence Warangal India The Islamic University College of Technical Engineering Department of Computers Techniques Engineering Najaf Iraq Gokaraju Rangaraju Institute of Engineering and Technology Department of Ai & Ml Bachupally Hyderabad India Indiana Wesleyan University Marion United States Mohan Babu University School of Computing Department of Cse Tirupati India

ISBN: (纸本)9798350372892

Widespread computing has a lot of ability to offer users customised services and support, especially as more people use smartphones for everyday tasks. In the past ten years, there has been a significant advancement in Sensor-Based Human Activity Recognition (HAR), which detects the movements of the user and emerged as a crucial component of pervasive computing. Thus, accurate HAR plays a significant role in numerous applications. For accurate HAR, the current research proposes an Improved Cat Swarm Optimization Algorithm based Convolutional Neural Network (ICSO-CNN) for tuning the parameters of CNN for optimal solution. Using various performance measures, the present research examines the performance of the proposed ICSO-CNN algorithm. The test results demonstrated that the ICSO-CNN outperforms the compared methods, including CNN with Long Short-Term Memory (CNN-LSTM), Particle Swarm Optimization based CNN (PSO-CNN), and CNN-BiLSTM with an accuracy of 99.79%. © 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

Shrinking VOD Traffic via Rényi-Entropic Optimal Transport

引用

Performance Evaluation Review 2024年第1期52卷 75-76页

作者： Lo, Chi-Jen Marina, Mahesh K. Sastry, Nishanth Xu, Kai Fadaei, Saeed Li, Yong Department of Engineering University of Cambridge United Kingdom School of Informatics The University of Edinburgh United Kingdom School of Computer Science University of Surrey United Kingdom MIT-IBM Watson AI Lab CambridgeMA United States Department of Electronic Engineering Tsinghua University China

In response to the exponential surge in Video on Demand (VOD) traffic, numerous research endeavors have concentrated on optimizing and enhancing infrastructure efficiency. In contrast, this paper explores whether users' demand patterns can be shaped to reduce the pressure on infrastructure. Our main idea is to design a mechanism that alters the distribution of user requests to another distribution which is much more cache-efficient, but still remains 'close enough' (in terms of cost) to fulfil individual user's preference. © 2024 Owner/Author.

关键词： Video on demand

来源：评论

学校读者我要写书评

暂无评论

A Predictive Analytics Approach to Traceability in Digital Forensics Using Time Series Analysis 2

A Predictive Analytics Approach to Traceability in Digital F...

引用

2nd IEEE International Conference on IoT, Communication and Automation Technology, ICICAT 2024

作者： Raju, K Srujan Ahila, R. Al-Farouni, Mohammed Karuna, Gotlur Yadav, Kanchan Kumar, Neelam Sanjeev Department of CSE CMR Technical Campus Telangana Hyderabad India New Prince Shri Bhavani College of Engineering and Technology Department of CSE Tamil Nadu Chennai600073 India The Islamic University College of Technical Engineering Department of Computers Techniques Engineering Najaf Iraq GRIET Bachupally Department of AI&ML Telangana Hyderabad India GLA University Department of Electrical Engineering Mathura India SRM Institute of Science & Technology Vadapalani Department of Computer Science & Engineering Chennai26 India

ISBN: (纸本)9798350368109

Digital forensics is essential to cybersecurity and the examination of virtual activities -particularly criminal ones. This research outlines a predictive analytical technique in his based on the time series to improve digital forensics traceability. The performance of the research is assessed by using the Digital Forensic Investigation Dataset (DFID) which contains application logs, network traffic files and file system images derived from inv You can download simulated forensic cases which are time stamped application logs, network traffic records and file system snapshots which are used to evaluate the performance of the research through Digital Forensic Investigation Dataset (DFID). In this regard, machine learning and deep learning algorithms such as Random Forest, Support Vector Machines, Long Short-Term Memory Networks were used to anticipate and detect the notion of suspicious action. Concerning the results of the Random Forest model, it yielded a high accuracy of 95% and precision of 94%, along with a recall of 96%, F1-score of 95%, and AUC of 0. 98. The feature importance analysis emphasized the most important features in the forensic process such as time, Internet protocol addresses, file hashes, and types of events. This research contributes to enhancing the knowledge base in the field of digital forensics by proposing the use of predictive analytics for early identification and mitigation of threats;this forms part of making Investigations efficient. The results support the notion that informational knowledge, as well as currently practiced and emerging computational methods, should play a central role in forensic practices. Some of the areas of further work are the attempt to combine the approaches and the refinement of the deep learning schemes to faces more complicated circumstances that can be encountered in forensics, as well as the integration of legal and ethical issues to the use of predictive models within digital environment of forensic invest

关键词： Predictive analytics

来源：评论

学校读者我要写书评

暂无评论

Virtual Machine Security Issues and Solutions When it is in Host

Virtual Machine Security Issues and Solutions When it is in ...

引用

International Conference on Advanced Computing and Communication Systems (ICACCS)

作者： Rakesh Reddy Gurrala T.Sampath Kumar K. Anuradha Department of Computer science and Engineering SR University Warangal Telangana India Department of CSE(AI&ML) CVR College of Engineering Hyderabad Telangana India

ISBN: (数字)9798350384369

ISBN: (纸本)9798350384376

In the current era, there are huge trending network intensive applications are running in virtual environment such as Cloud-based services and Internet servers, and machine's physical and the network resources shares by VM's running on same machine. Virtual machines (VMs) have become a cornerstone of modern computing, enabling efficient resource utilization, scalability, and flexibility in various domains such as cloud computing, data Centre's, and development environments. However, this proliferation of VMs has also introduced a range of security challenges that necessitate careful consideration and mitigation strategies. The paper provides an overview of the issues related to security and associated with virtual machines when it is in Host. It begins by delineating the fundamental concepts of virtualization technology, highlighting the layered architecture of VMs and the critical components involved. Subsequently, the paper delves into the key security concerns, categorizing them into four main areas: isolation, privilege escalation, resource contention, and vulnerability to attacks. In addition to identifying these security issues, the paper provides an analysis of existing mitigation techniques and best practices. These include measures such as hypervisor hardening, secure configuration management, network segmentation, and the use of security monitoring.

关键词： Cloud computing Virtual machine monitors Program processors Prevention and mitigation Scalability Security Proposals Servers Resource management Optimization

来源：评论

学校读者我要写书评

暂无评论

Aerial Image Segmentation Using YOLO v8 and SAM Pipeline

Aerial Image Segmentation Using YOLO v8 and SAM Pipeline

引用

Silchar Subsection Conference (SILCON), IEEE

作者： Karthik K Pai Monika Agarwal Aparajita Sinha Mary Jasmine Jagrath Chengappa K N Department of Computer Science And Engineering (AI&ML) Dayananda Sagar University Bangalore India Department of Computer Science And Engineering National Institute of Technology Agartala India Department of Computer Science And Engineering Christ University Bangalore India Department of Computer Science And Engineering Dayananda Sagar University Bangalore India

ISBN: (数字)9798331540821

ISBN: (纸本)9798331540838

Aerial image segmentation, important for understanding image content, faces significant challenges such as feature scale variation, resolution issues, spectral inconsistencies, and class imbalance. This paper introduces a robust pipeline that combines YOLOv8 for object detection and the Segment Anything Model (SAM) for refining segmentation. The study addresses detection attributes, augmentation methods, and dataset creation for reliable modelling. Trained on a custom sub-meter aerial image dataset, the model achieves moderate accuracy with MAP@50 of 0.68 and MAP@50-95 of 0.51. It demonstrates strong potential for applications in urban planning, disaster management, and geospatial analysis. By enhancing segmentation accuracy and efficiency through cutting-edge deep learning techniques, this method supports critical geospatial applications.

关键词： YOLO Training Image segmentation Accuracy Image resolution Pipelines Urban planning Robustness Geospatial analysis Resource management

来源：评论

学校读者我要写书评

暂无评论

Harnessing The Power of Artificial Intelligence for Disaster Response and Crisis Management

Harnessing The Power of Artificial Intelligence for Disaster...

引用

2024 International Conference on Communication, computer sciences and engineering, IC3SE 2024

作者： Harika, Ala Balan, Gunapriya Thethi, H. Pal Rana, Ajay Rajkumar, K. Varada Al-Allak, Mustafa Abdulhussein Institute Of Aeronautical Engineering Department Of Computer Science And Engineering Telangana Hyderabad India New Horizon College Of Engineering Department Of Electrical And Electronics Engineering Bangalore India Lovely Professional University Phagwara India Amity University Greater Noida India Mlr Institute Of Technology Department Of CSE-AI&ML Telangana Hyderabad India College Of Medical Technology The Islamic University Najaf Iraq

ISBN: (纸本)9798350366846

People on every continent today have to deal with the continual threat of disasters, both natural and man-made. Therefore, novel approaches are required to mitigate their negative impacts and ensure the preservation of life. This article investigates the potential ways in which artificial intelligence (ai) could revolutionize the management of crises and the allocation of resources following disasters. When it comes to catastrophe preparedness, response, and recovery, several different types of ai are being utilized. Natural language processing, predictive modeling, computer vision, and machine learning are a few examples. By contrasting the efficacy of conventional approaches with that of ai-driven systems and programs, this study hopes to arrive at the optimal strategy. The approaches being presented are shown to work using real-world data and case studies. The study begins with a comprehensive review of the various approaches and resources utilized in disaster management. Next, we'll go over our proposed solution, which incorporates ai to facilitate data analysis, decision-making, resource allocation, and emergency communication. We test our technique against established gold standards, such as expert opinion and manual data analysis, to ensure it delivers the expected results. Evaluations of ai-based therapies take a variety of aspects into account. Time to respond, precision, distribution of resources, and adaptability are a few of these aspects. Researching this topic further, we came to the conclusion that ai-driven solutions are useful for crisis management and catastrophe response. Programs built using ai can swiftly process and evaluate massive volumes of data. Individuals are able to make wiser choices in less time because of this. Getting meaningful information from disorganized data, like as social media postings and satellite images, makes it simpler to comprehend what's happening in the world around you. Artificial intelligence systems can also change

关键词： Machine learning

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：