检索结果-内蒙古大学图书馆

sentiment Analysis and Deep Learning (ICsADL), International Conference on

作者： b. Kiranmayee M. sharmila Devi Kalva susheela Raghu Dhumpati Kiran Kumar Reddy Penubaka U Ganesh Naidu Department of CSE (AI&ML) G Pulla Reddy Engineering College Kurnool India Department of CSE Santhiram Engineering College Nandyal India Department of Computer Science Sir C R Reddy College for Women Eluru India Department of CSE Bahrain Polytechnic College Bahrain Department of CSE-AIML MLR Institute of Technology Hyderabad India B V Raju Institute of Technology Medak Telangana India

ISBN: (数字)9798331523923

ISBN: (纸本)9798331523930

This paper proposes an integrated approach to build up IDs with proper effectiveness toward the rising need for strong network security. Network traffic anomaly detection and classification are one of the major aims and enhance the security layer against various types of cyber threats. This study is a methodical approach in which a diverse set of data is first extracted from Kaggle. The collected dataset is a comprehensive one that includes various kinds of network traffic data. The first step includes preprocessing the data, i.e., handling missing values, removing erroneous entries, and dealing with outliers using the Interquartile Range (IQR) method. To counter class imbalance, synthetic Minority Oversampling Technique (sMOTE) is utilized in generating synthetic samples in underrepresented classes for generalization of models. The feature selection algorithm relies on the Chi-square Lasso Feature selection method. This method unites Chi-square tests to select statistically significant features with Lasso regularization for feature dimension reduction with the goal of overfitting minimization. For building models, a hybrid of support vector Machine and K-Nearest Neighbors, which is termed as svNN, is used. by using soft voting to aggregate the outputs of svM and KNN, the proposed svNN model improves the prediction accuracy, the degree of robustness, and adaptability. The presented methodology has achieved high classification accuracy 93.28%, precision 93.49%, recall 93.28%, F1 score 93.23%, and low RMsE of 0.2592. These metrics demonstrate that the model is reliable and of practical use for intrusion detection in dynamic, high-dimensional environments of networks, providing a proper solution to modern security network challenges.

关键词： support vector machines Adaptation models Analytical models Accuracy Intrusion detection Telecommunication traffic Nearest neighbor methods Network security Feature extraction Data models

来源：评论

学校读者我要写书评

暂无评论

Network Traffic Prediction using Deep Learning Models: Reducing Latency in High-Demand scenarios

Network Traffic Prediction using Deep Learning Models: Reduc...

引用

Computing for sustainability and Intelligent Future (COMP-sIF), International Conference on

作者： b.J. Job Karuna sagar Divya M v Namita Kale Neetu Anand Kumar Gaurav shrividya shashidhara Department of CSE Joginpally B.R Engineering College Hyderabad Telangana Department of Computer Science East West Institute of Technology Bangalore India Department of Information Technology MET'S Institute Of Engineering Nashik India Department of Computer Applications Maharaja Surajmal Institute Delhi India Department of CSE BMS Institute of Technology and Management Bangalore India

ISBN: (数字)9798331538538

ISBN: (纸本)9798331538545

The availability of the internet and enhanced applications, more specifically, the utilization of more devices in networks, and improved computational applications has created complexity in the control of network traffic. Network traffic forecasting is an essential component in low-latency networks, as well as in real-time applications that deserve excellent service quality and efficient resource allocation. This study therefore focuses on identifying whether deep learning models can further improve the accuracy in forecasting traffic flows in a network. Therefore, with the help of LsTM networks and Convolutional Neural Networks, the work will build temporal dependencies and spatial correlations of network traffic data. There are major and minor adaptations to some classic methodologies that conform the proposed framework; moreover, it is applied to two real datasets to highlight the capacity of the model in anticipating traffic congestion with a higher level of accuracy than the traditional methodologies. Evaluation of models in dynamic network conditions is done through common parameters such as prediction accuracy, lowered latency, and scalability. saved models show that deep learning-based solutions reduce latency at high loads much more effectively, which will help network administrators in finding efficient solutions. This study demonstrate how deep learning can aid in the prediction of traffics, and the manner in which it is changing the efficiency and effectiveness of modern-day network systems. It makes the foundation for improved understanding of traffic patterns in order to apply it to optimize future generation of communication networks.

关键词： Deep learning Adaptation models Accuracy Telecommunication traffic Predictive models Throughput Convolutional neural networks Forecasting Long short term memory Load modeling

来源：评论

学校读者我要写书评

暂无评论

vehicle-Assisted service Caching for Task Offloading in vehicular Edge Computing

引用

IEEE Transactions on Mobile Computing 2025年

作者： Jiang, Hongbo Cai, Jianghao Xiao, Zhu Yang, Kehua Chen, Hongyang Liu, Jiangchuan Hunan University College of Computer Science and Electronic Engineering Hunan Changsha China Hunan University Shenzhen Research Institute Shenzhen518055 China Zhejiang Laboratory Research Center for Graph Computing Hangzhou311100 China Simon Fraser University School of Computing Science BurnabyBCV5A 1S6 Canada

The development of artificial intelligence (AI) enables vehicular edge computing (vEC) servers to be able to provide more intelligent services. However, the limited storage resources of vEC servers constrain the deployment of intelligent service contents, which greatly restricts the intelligence level of the vEC network. To resolve this problem, we first design a novel vehicle-assisted vEC network architecture and further propose vaCo, a vehicle-assisted Collaborative caching system. vaCo allows vEC servers to download the cached service content from any vehicle in the vEC network to support task offloading. vaCo mainly considers the real-time scheduling problem of vehicle storage resources under the dynamic vEC network and the benefit problem caused by invoking vehicle resources under the highly dynamic load environment. vaCo models the vehicle storage resources as an independent resource pool and deploys a cross-vEC server content retrieval mechanism to achieve unified and efficient management of the storage resources of the vehicle cluster and the vEC server cluster. Then, we propose a multi-swarm collaborative optimization scheme to jointly optimize the service failure rate and cost, and further propose a Pareto-based optimization scheme to ensuring that vaCo can correctly evaluate the benefits of invoking vehicle resources in a dynamic vEC network. Finally, we implement vaCo and conduct extensive evaluations on real-world dataset. The experimental results on the real trajectory dataset show that vaCo can effectively utilize vehicle resources and ensure the benefits of both vehicles and vEC servers simultaneously. © 2002-2012 IEEE.

关键词： Mobile edge computing

来源：评论

学校读者我要写书评

暂无评论

Leveraging an Optimized Deep Convolutional Neural Network Architecture for the Automated Diagnosis of Pathological Conditions Through Acoustic Analysis of Human Cough signatures

Leveraging an Optimized Deep Convolutional Neural Network Ar...

引用

smart systems for applications in Electrical sciences (ICssEs), International Conference on

作者： Tamilarasan M Keshavamurthy T G vidya K v Nicy siby sriraksha Devaraj Revanna b R Department of Computer Science and Engineering Dr.N.G.P Institute of Technology Coimbatore Anna University Tamil Nadu India Department of Electronics and Communication Engineering Sri Siddhartha Institute of Technology Sri Siddhartha Academy of Higher Education Tumkur Karnataka India Department of Electronics and Communication and Engineering B.M.S College of Engineering Affiliated to Visvesvaraya Technological University Belgavi Bangalore Karnataka India

ISBN: (数字)9798331507671

ISBN: (纸本)9798331507688

The usage of artificial intelligence (AI) techniques particularly deep learning algorithms, has recently increased dramatically and the healthcare sector is only one of many industries affected Using deep convolutional neural networks (CNNs) enhanced with human auditory inputs we present a novel approach to disease detection in this paper The proposed system aims to provide an effective economical and non invasive method of early disease detection we employ a deep convolutional neural network (CNN) architecture that has been optimized for audio input processing. Further more we use data augmentation methodologies to strengthen the model's capacity to generalize and handle varied patient groups and diseases more effectively. Our all encompassing approach incorporates denoising techniques using Wavelet transform denoising segmentation via K-mean clustering, feature extraction using Recursive Feature Elimination (RFE) and classification using Enhanced Deep Convolutional Neural Networks (EDCNN) which improves the accuracy and dependability of the system in identifying diseases based on human sound signatures.

关键词： Deep learning Accuracy Noise reduction Medical services Feature extraction Data augmentation Data models Convolutional neural networks Artificial intelligence Diseases

来源：评论

学校读者我要写书评

暂无评论

Joint Adaptation for Mobile 360-Degree video streaming and Enhancement

引用

IEEE Transactions on Mobile Computing 2025年

作者： Guo, Haotian Wang, Feng Zhang, Wei Zhu, Yifei Cui, Laizhong Liu, Jiangchuan Yu, F. Richard Zhang, Lei Shenzhen University College of Computer Science and Software Engineering Guangdong Shenzhen518060 China The University of Mississippi Department of Computer and Information Science MS38677 United States ByteDance Guangdong Shenzhen518060 China University of Michigan-Shanghai Jiao Tong University Joint Institute Shanghai200240 China School of Computing Science Simon Fraser University BurnabyBCV5A 1S6 Canada Carleton University School of Information Technology OttawaONK1S 5B6 Canada

Tile-based streaming and super resolution (sR) are two representative technologies adopted to improve bandwidth efficiency of 360° video streaming. The former allows selective downloading of contents in the user viewport by splitting the video into multiple independently decodable tiles. The latter leverages client-side computation to enhance the received video to higher quality using advanced neural network models. In this work, we propose a Collaborated streaming and Enhancement (CsE) adaptation framework for mobile 360° videos, which integrates super resolution with tile-based streaming to optimize the user experience with dynamic bandwidth and limited computing capability. To effectively enhance the tile-based video streaming through sR, we propose to adaptively group the tiles for quality enhancement adapting to the content similarity. We also identify and address several key design issues to integrate sR into tile-based video streaming including unified video quality assessment, computational complexity model for super resolution, and buffer analysis considering the interplay between transmission and enhancement. We further formulate the quality-of-experience (QoE) maximization problem for mobile 360° video streaming and propose a rate adaptation algorithm to make the best decisions for download and for enhancement based on the Lyapunov optimization theory. Extensive evaluation results validate the superiority of our proposed approach, which demonstrates stable performance with considerable QoE improvement, while enabling a trade-off between playback smoothness and video quality. © 2002-2012 IEEE.

关键词： video streaming

来源：评论

学校读者我要写书评

暂无评论

Assessing synergies between thermal energy and torrefaction severity index of wood spruce sawdust via machine learning algorithms

引用

Journal of Analytical and Applied Pyrolysis 2025年 190卷

作者： Šafář, Michal Raclavska, Helena Růžičková, Jana Ali, Imtiaz Naqvi, salman Raza scala, Fabrizio CEET/ENET Centre VŠB – Technical University of Ostrava Ostrava-Poruba708 00 Czech Republic Department of Chemical Engineering College of Engineering Prince Mohammad Bin Fahd University Al Khobar Saudi Arabia Department of Engineering and Chemical Sciences Karlstad University Karlstad Sweden Faculty of Electrical Engineering and Computer Science VŠB-Technical University of Ostrava 17. Listopadu 2172/15 Poruba Ostrava708 00 Czech Republic DICMaPI Università di Napoli Federico II P.le Tecchio 80 Napoli80125 Italy STEMS CNR P.le Tecchio 80 Napoli80125 Italy

Assessing the synergies between thermal energy and the torrefaction severity index by elucidating the effects of biomass torrefaction conditions on product characteristics is still a relevant research question. This study explores the optimization of torrefaction of spruce wood sawdust by analyzing the chemical and physical features of the resultant material. The study employs thermogravimetric analysis and Thermal Desorption-Gas Chromatography/Mass spectrometry (TD-GC/Ms) to examine the changes in the components during torrefaction. The torrefaction process has a profound effect on the composition, causing conversion of up to 30 % of the initial mass to volatile organic compounds and incondensable gases when subjected to a temperature of 300 °C. The correlation matrix highlights the relationships between variables, including time, temperature, heating value, mass yield, energy yield, and ratios of C, H, and O. The matrix visually represents the interplay between these factors during the torrefaction process. Principal component analysis (PCA) and hierarchical cluster analysis (HCA) revealed that torrefaction severity index, cellulose, lignin, torrefaction time, and temperature correlate positively, while H/C, O/C, and hemicellulose content correlate negatively. The ANN model exhibited superior predictive accuracy (R² = 0.99982, RMsE = 0.00359), surpassing C&RT (R² = 0.99483, RMsE = 0.01943), KNN (R² = 0.99467, RMsE = 0.01974), and svM (R² = 0.99022, RMsE = 0.02674), thus validating the efficacy of machine learning for precise torrefaction severity index (TsI) prediction. This finding enhances the efficiency of biomass processing and provides reliable tools for future research in the field, thereby informing and guiding future studies and industrial applications. © 2025 The Authors

关键词： Hierarchical clustering

来源：评论

学校读者我要写书评

暂无评论

Advancing HRM with AI Powered Recruitment Performance Management and Employee Engagement Using One Class svMs

Advancing HRM with AI Powered Recruitment Performance Manage...

引用

Integrated Circuits and Communication systems (ICICACs), IEEE International Conference on

作者： Rafiya banu Ruchi Tripathi saumya sharma Loganathan Chenniappan K. Chandrasekaran Umanesan R Department of Commerce B. S. Abdur Rahman Crescent Institute of Science and Technology Chennai India Faculty of Management Studies SRM-IST Ghaziabad India Department of Management & Commerce The Northcap University Gurugram India Business Administration IBRI Sultanate of Oman Department of Mechanical Engineering K.S.R College of Engineering Tiruchengode India Department of Computer Science and Engineering School of Computing Vel Tech Rangarajan Dr Sagunthala R&D Institute of Science and Technology Chennai India

ISBN: (数字)9798331508456

ISBN: (纸本)9798331508463

AI is making labour-intensive HRM operations like hiring, performance review, and employee engagement more efficient and effective. The incorporation of AI technology in HRM could change several sectors. Through efficient applicant sourcing, screening, and selection, AI-driven solutions simplify hiring processes and ensure fair and accurate picks. Performance management using AI-powered solutions provides data-driven feedback and customized development plans to align individual progress with organizational goals. Predictive analytics improve employee engagement by personalizing experiences and meeting needs. The method focuses on preprocessing and model training. Data are cleansed, ordinal and categorical variables encoded, scaling characteristics and engineering features applied, and dimensional homogeneity assured before processing. For model training, the simple and robust one-class svM technique is used. One-class svM model outperformed others with 95.28%. This method worked best compared to GAN and GRU models. AI could improve HRM by improving decision-making and offering data-driven solutions. The findings show that the proposed model outperforms current options, providing the framework for HRM AI applications.

关键词： support vector machines Training Productivity Accuracy Uncertainty Reviews Artificial intelligence Integrated circuit modeling Predictive analytics Recruitment

来源：评论

学校读者我要写书评

暂无评论

AI-Powered Anomaly Detection to strengthen Internet of Things security and Forestall Cyber Attacks in Networked Device Environments

AI-Powered Anomaly Detection to Strengthen Internet of Thing...

引用

Advancement in Computation & computer Technologies (InCACCT), International Conference on

作者： s. varalakshmi suresh Kottur R sasikumar K saravanan Tanaya Kanungo balamurugan Annamalai Department of ECE Bharath Institute of Higher Education and Research Chennai Tamil Nadu India IT Infrastructure Architect/IT Systems V-Soft Consulting Group Inc Louisville KY United States of America Department of Computer Science & Engineering R.M.D Engineering College Kavaraipettai Tamil Nadu India Department of Information Technology R.M.K Engineering College Kavaraipettai Tamil Nadu India Department of ECE St. Peter's College of Engineering and Technology Avadi Tamil Nadu India Department of EEE Shree Sathyam College of Engineering and Technology Sangagiri Tamil Nadu India

ISBN: (数字)9798331543891

ISBN: (纸本)9798331543907

As millions of devices are linked, the IoT has revolutionized numerous businesses by automating and data-driven decision-making. Due to the proliferation of linked devices, cybercriminals target IoT environments for security breaches. This research examines AI-powered anomaly detection systems for real-time threat discovery and mitigation in IoT security. Advanced machine learning and deep learning models based on artificial intelligence can detect suspicious activity in networked environments and early security breaches. Artificial intelligence systems learn from network traffic and device behaviors to respond to emerging cyber threats, unlike rule-based security solutions. The study found that AI-driven anomaly detection can prevent data breaches, malware outbreaks, and DDos attacks. This study compares artificial intelligence algorithms for real-time anomaly detection across IoT frameworks. supervised, unsupervised, and hybrid learning models are used. It also discusses the challenges of large-scale AI system deployment, including the need for high-quality labelled datasets for training and computational resource constraints. The results suggest that AI-enabled anomaly detection could become a crucial part of IoT security, adapting to the growing number of connected devices.

关键词： Accuracy Computational modeling biological system modeling Real-time systems Malware Internet of Things security Hybrid learning Artificial intelligence Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

study of thermal radiation and dissipation effects on MHD Prandtl hybrid nanofluid flow past an exponential stretched porous device

引用

Thermal science and engineering Progress 2025年 62卷

作者： Mane, Parshuram s. Patil, vishwambhar s. Patil, Amar b. Humane, Pooja P. Maharudrappa, Ishwar sankad, G.C. Department of Mathematics Shivaji University Kolhapur 416004 India Department of Mathematics Govt. College of Engineering Karad415124 India Department of Mathematics The New College Kolhapur416012 India Department of Mathematics School of Computer Science and Artificial Intelligence SR University Telangana Warangal506371 India Basaveshwar Engineering College Bagalkote587102 India Department of Mathematics BLDEA's V.P. Dr. P. G. Halakatti College of Engineering and Technology Vijayapur586103 India

Fluid dynamics requires a comprehensive understanding of energy dissipation, heat and mass transfer phenomena, since it directly impacts thermal efficiency, flow stability, and energy conservation in various industrial and engineering applications. With this motivation, the present study investigates the magnetized flow of Prandtl mixed hybrid nanofluids across an exponentially stretched surface. The hybrid nanofluid is formed with nanoparticles of Titanium oxide (TiO2) and Copper (Cu) in water as the base fluid. The governing set of equations is formulated as an extension of the Prandtl fluid model to investigate the physical effects of chemical processes, heat radiation, bioconvection, and energy dissipation. The nonlinear ordinary differential equations are derived after successfully implementing appropriate transformations on governing equations and are solved numerically via the Differential Transform Method (DTM). The graphical illustration of non-dimensional velocity, temperature, and concentration is obtained through MATLAb and discussed with proper physical justification for various terms such as magnetic parameter, chemical reaction, radiation parameter, sherwood number, Nusselt number, and friction parameter. The outcomes are validated with a comparison of previous published work. Results reveal that hybrid nanofluids significantly enhance heat transfer efficiency compared to conventional nanofluids. Increasing the Eckert and biot numbers raises temperature, while a stronger magnetic field reduces fluid velocity. Increasing magnetic parameter reduces velocity by 42 % (NF) and 37.5 % (HNF), while increasing Eckert number raises temperature by 67 % (NF) and 53 % (HNF), highlighting strong magnetic and viscous dissipation effects. The findings of this study have significant applications in oil extraction, heat exchanger optimization, and MHD propulsion systems, where energy dissipation and thermal radiation play a crucial role. © 2025 Elsevier Ltd

关键词： Magnetohydrodynamics

来源：评论

学校读者我要写书评

暂无评论

African buffalo optimization with deep learning-based intrusion detection in cyber-physical systems

引用

scientific Reports 2025年第1期15卷 1-19页

作者： Laxmi Lydia, E. Ramesh, sripada N. s. v. s. C. Denisovich, veronika Moses, G. Jose Cho, seongsoo Acharya, srijana Yoon, Cheolhee Department of Computer Science and Engineering Vignan’s Institute of Engineering for Women Andhra Pradesh Visakhapatnam 530046 India Department of Computer Science and Engineering Aditya College of Engineering and Technology Andhra Pradesh Surampalem India Institute of Digital Technologies and Law Kazan Innovative University named after V. G. Timiryasov 42 Moskovskaya str. Kazan 420111 Russian Federation Department of Computer Science and Engineering School of Engineering Malla Reddy University Hyderabad India Department of Convergence Science Kongju National University Gongju 32588 South Korea Laboratory of Autonomous Vehicle and Block-Chain Korean National Police University Asan 31539 South Korea

Cyber-physical system (CPs) incorporates several computing resources, networking units, interconnected physical processes, and monitoring the development and application of the computing system. Interconnection between the cyber and physical worlds initiates attacks on security problems, particularly with the enhancing complications of transmission networks. Despite the efforts to combat these problems, analyzing and detecting cyber-physical attacks from the complex CPs is challenging. Machine learning (ML)-researcher workers implemented based techniques to examine cyber-physical security systems. A competent network intrusion detection system (IDs) is essential to avoid these attacks. Generally, IDs uses ML techniques to classify attacks. However, the features used for classification are not frequently appropriate or adequate. Moreover, the number of intrusions is much lower than that of non-intrusions. This research presents an African buffalo Optimizer Algorithm with a Deep Learning Intrusion Detection (AbOADL-IDs) model in a CPs environment. The main intention of the AbOADL-IDs model is to utilize the Fs with an optimal DL approach for the intrusion recognition and identification procedure. Initially, the AbOADL-IDs model performs the data normalization process. Furthermore, the AbOADL-IDs model utilizes the AbO technique for feature selection. Moreover, the stacked deep belief network (sDbN) technique is employed for intrusion detection and identification. To improve the sDbN technique solution, the seagull optimization (sGO) technique is implemented for the hyperparameter selection. The assessment of the AbOADL-IDs technique is accomplished under NsLKDD2015 and CICIDs2015 datasets. The performance validation of the AbOADL-IDs technique illustrated a superior accuracy value of 99.28% over existing models concerning various measures. © The Author(s) 2025.

关键词： African buffalo optimization Cyber-physical systems Deep learning Feature selection Intrusion detection system

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：