检索结果-内蒙古大学图书馆

20th International Conference on Frontiers of Information technology, FIT 2023

作者： Naeem, Faiza Malik, Asad Waqar Abbas Khan, Safdar Jabeen, Farzana National University of Science and Technology School of Electrical Engineering and Computer Sciences Islamabad Pakistan

ISBN: (纸本)9798350395785

An efficient and productive IoT application may ease some real-time tasks however, it is at risk of cyber-attack. Intrusion Detection Systems (IDS) are of significant importance for the security measures of IoT applications. IoT/IIoT devices that deal with large data volumes are at risk of malicious attacks and as a result, anomaly-based IDS are developed. Anomaly-based intrusion detection systems perform more efficaciously than other methods. But, the question that arises is whether the performance of models meets the required standards. The research intends to improve the efficiency of IDS with a focus on the Telemetry data of IoT/IIoT sensors data from the ToN_IoT dataset. It includes data about seven IoT/IIoT devices. Federated Learning based on Deep auto-encoder is adopted to design a model with efficiently identifies attacks while solving the issue of privacy concerns. Hybrid models use Machine Learning algorithms with increased detection rates. The algorithms used for the Hybrid model are Random Forest and XGBoost. The XGBoost algorithm improves the accuracy of the Hybrid model with better predictions. The hybrid model ensures efficient pre-processing and feature selection for intrusion detection. The accuracy percentage of the Federated model is 97% on the dataset of Garage Door and 88% on the Motion Light dataset while the Hybrid model outperforms on all IoT/IIoT devices with an average accuracy score of 99.99%. © 2023 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Federated Learning-Based Network Intrusion Detection Using Deep Auto Encoder 6

Federated Learning-Based Network Intrusion Detection Using D...

引用

6th International Conference on Recent Trends in Advance Computing, ICRTAC 2023

作者： Jeyavim Sherin, R.C. Parkavi, K. Vit University School of Computer Science and Engineering Vellore Institute of Technology Chennai India

ISBN: (纸本)9798350394702

The progress of information technology is directly related to different elements of daily life, providing people with services that make living more comfortable. As the network infrastructure grows to support new services, it necessarily produces various weak points that cybercriminals might exploit. Building a reliable network intrusion detection system with deep learning methodologies demands a substantial dataset. In the past, the conventional approach involved collecting data for centralized learning, which was then transmitted to a central server for model training. Nevertheless, this approach raises valid concerns regarding the potential exposure of personal information contained within raw data, which could lead to legal repercussions for data providers. Consequently, this study presents a Modified FedAvg algorithm to enhance the existing FedAvg algorithm for network intrusion detection models. This modified approach maximizes the potential of federated learning, enhancing data privacy and minimizing the transmission of model weights. Employing a Deep Auto Encoder within a federated setting, we evaluated our methodology using the CICIDDoS 2019 dataset, attaining a notable accuracy rate of 98.82% in effectively identifying intrusions. © 2023 IEEE.

关键词： Network security

来源：评论

学校读者我要写书评

暂无评论

Weather Classification for Autonomous Vehicles under Adverse Conditions Using Multi-Level Knowledge Distillation

引用

computers, Materials & Continua 2024年第12期81卷 4327-4347页

作者： Parthasarathi Manivannan Palaniyappan Sathyaprakash Vaithiyashankar Jayakumar Jayakumar Chandrasekaran Bragadeesh Srinivasan Ananthanarayanan Md Shohel Sayeed School of Computing SASTRA Deemed to be UniversityThanjavur613401India School of Computer science&Engineering Presidency UniversityBengaluru560064India Dr.A.P.J.Abdul Kalam School of Engineering Garden City UniversityBengaluru560049India Independent Researcher OxnardCA 93036USA Faculty of Information Science and Technology Multimedia UniversityMelaka75450Malaysia

Achieving reliable and efficient weather classification for autonomous vehicles is crucial for ensuring safety and operational ***,accurately classifying diverse and complex weather conditions remains a significant *** advanced techniques such as Vision Transformers have been developed,they face key limitations,including high computational costs and limited generalization across varying weather *** challenges present a critical research gap,particularly in applications where scalable and efficient solutions are needed to handle weather phenomena’intricate and dynamic nature in *** address this gap,we propose a Multi-level Knowledge Distillation(MLKD)framework,which leverages the complementary strengths of state-of-the-art pre-trained models to enhance classification performance while minimizing computational ***,we employ ResNet50V2 and EfficientNetV2B3 as teacher models,known for their ability to capture complex image features and distil their knowledge into a custom lightweight Convolutional Neural Network(CNN)student *** framework balances the trade-off between high classification accuracy and efficient resource consumption,ensuring real-time applicability in autonomous *** Response-based Multi-level Knowledge Distillation(R-MLKD)approach effectively transfers rich,high-level feature representations from the teacher models to the student model,allowing the student to perform robustly with significantly fewer parameters and lower computational *** proposed method was evaluated on three public datasets(DAWN,BDD100K,and CITS traffic alerts),each containing seven weather classes with 2000 samples per *** results demonstrate the effectiveness of MLKD,achieving a 97.3%accuracy,which surpasses conventional deep learning *** work improves classification accuracy and tackles the practical challenges of model complexity,resource consumption,and real-time deployment,of

关键词： EfficientNetV2B3 multi-level knowledge distillation RestNet50V2 weather classification

来源：评论

学校读者我要写书评

暂无评论

Dependency Tree Distance for Aspect Level Sentiment Analysis 4

Dependency Tree Distance for Aspect Level Sentiment Analysis

引用

4th International Conference on computer engineering and Application, ICCEA 2023

作者： Zhao, Yifan Zhang, Xinping Wang, Junhua School of Computer Science and Engineering Changchun University of Technology Jilin Province Changchun China

ISBN: (纸本)9798350347548

When dealing with complex statements containing multiple aspects in the existing model, most of them ignore the dependencies between context and aspect words, this makes it difficult for the model to learn local information about aspects. To solve this problem, an aspect-level emotion analysis model based on dependency tree distance is proposed. It can calculate the dependency tree distance between aspect words and other context words according to their position in the syntactic dependency tree structure, then the sentence is divided into local information based on dependency tree distance. In the design of the model structure, the fusion learning method is used. The multi-head attention mechanism is used to fuse the local information, global information and aspect information, and the hidden state containing rich sentence expression is obtained as the classification basis. To verify the effectiveness of the model, experiments are carried out on three benchmark datasets, including Restaurant and Laptop datasets of SemEval 2014, and Twitter datasets. In addition, a comparative experiment is designed for the two processing methods and the multi-group dependency tree distance threshold, and the processing method and the optimal threshold suitable for different datasets are selected. © 2023 IEEE.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Design and Analysis of DC-DC Two-Phase Interleaved Buck Converter for EV Charging Applications 18

Design and Analysis of DC-DC Two-Phase Interleaved Buck Conv...

引用

18th IEEE International Conference on Emerging Technologies, ICET 2023

作者： Yousuf, Muhammad Zeb, Kamran School of Electrical Engineering and Computer Science National University of Sciences and Technology Islamabad Pakistan

ISBN: (纸本)9798350328172

While the world is booming with Electric Vehicles (EVs), countries where bikes are a common mode of transport still require adequate charging infrastructure to cope up with the slow EV growth. Efficient power conversion is necessary for EV chargers to be feasible. This paper presents an efficient solution for the DC-DC stage of the EV chargers for two wheelers by designing a two-phase Interleaved Buck Converter (IBC). The converter has been equipped with a PI controller for corrective measures against the disturbances, reducing the steady state error and the settling time of the system. The designed PI controller eliminates the need for an additional controller for current balancing between the two branches of the IBC. With significant advantages of reduced ripple, mitigated stress on the components and efficient conversion of power, IBC looks out as a great breakthrough to shift the dynamics of two-wheeler chargers. IBC in this paper has been designed using MATLAB/Simulink and is evaluated in Proteus with the non-ideal components that can be used in the prototype along with a small-scale hardware validation of 12W prototype. © 2023 IEEE.

关键词： Controllers

来源：评论

学校读者我要写书评

暂无评论

Enhancing Telecom Customer Loyalty Through Churn Prediction Models 8

Enhancing Telecom Customer Loyalty Through Churn Prediction ...

引用

8th International Conference on Electronics, Communication and Aerospace technology, ICECA 2024

作者： Thanam, A. Malchijah Raj, M.S. Joel, M. Robinson Shanthakumar, P. Jacson, J. Joel Department of Computer Science and Engineering Chennai India Saveetha Institute of Medical and Technical Sciences Saveetha University Saveetha School of Engineering Department of Mathematics Tamil Nadu Chennai602105 India Kcg College of Technology Department of Computer Science and Engineering Chennai India Nehru Institute of Technology Department of Computer Science and Engineering Coimbatore India Kings Engineering College Department of Information Technology Chennai India

ISBN: (纸本)9798350367904

In the rapidly evolving telecommunications sector, maintaining profitability and growth depends on customer retention. With the goal of identifying the critical elements influencing customer attrition and creating a useful predictive model, this study offers a thorough investigation of customer churn prediction using a telecom dataset. This study uses a dataset that contains a variety of client features, such as account details, demographic data, and service consumption trends. Here, the data preparation techniques are used to manage anomalies, missing values, and data normalisation. The study uses a range of machine learning methods to forecast churn, such as support vector machines, random forests, decision trees, logistic regression, and gradient boosting. Metrics including accuracy, then precision, also the recall, then F1 score, and also the area under the curve of receiver operating characteristic are used to assess each model's performance (AUC-ROC). By use of cross-validation and hyperparameter adjustment, we guarantee the models' resilience and generalizability. Significant churn predictors, including contract type, duration, monthly costs, and customer support interactions, are identified by our investigation. According to the research, month-to-month contract holders who have higher monthly fees and frequent contact with customer service are more likely to experience customer attrition. The model with the highest degree of prediction accuracy is the random forest, which has an AUC-ROC of 0.85, making it the best-performing model. This paper offers a useful foundation for putting churn prediction models into practice in addition to highlighting the important variables causing customer churn in the telecom industry. Telecom firms may lower churn rates by creating focused retention tactics, such personalised offers and better customer care, by proactively identifying at-risk clients. The findings highlight how crucial it is to use machine learning and data a

关键词： Sales

来源：评论

学校读者我要写书评

暂无评论

Research on Network Security Game Based on System Dynamics 24

Research on Network Security Game Based on System Dynamics

引用

2nd International Conference on Artificial Intelligence, Systems and Network Security, AISNS 2024

作者： Zeng, Qiufen Pei, Tingrui School of Mechanical Engineering and Mechanics Xiangtan University Hunan Xiangtan China School of Information Science and Engineering Hunan Institute of Engineering Hunan Xiangtan China College of Information Science and Technology Jinan University Guangdong Zhuhai China School of Computer Science School of Cyberspace Science Xiangtan University Hunan Xiangtan China

ISBN: (纸本)9798400711237

Network security game was usually considered as attack-defense confrontation;however, we need to think out of the box because any network entity may get a chance to launch an attack. The problem of network security which was described as the game between regulatory authority and network entity needs to be analyzed from the perspective of macro management. The model of system dynamic which was combined with traditional game theory was established. Several strategies which were most commonly used were verified and evaluated through simulation model. In order to weaken the instability of network security game, selective punishment strategy was proposed and the simulation result showed that not only in astringency but also in network security maintenance the proposed strategy can achieve good results. © 2024 Copyright held by the owner/author(s).

关键词： System theory

来源：评论

学校读者我要写书评

暂无评论

Safely Knowledge Transfer from Source Models via an Iterative Pruning Based Learning Approach

Safely Knowledge Transfer from Source Models via an Iterativ...

引用

2024 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2024

作者： Lu, Xiaoyu Sean Zhang, Jianan Yao, Siya Huang, Bo School of Cyber Science and Engineering Nanjing University of Science and Technology Nanjing210000 China College of Information and Electronic Engineering Zhejiang Gongshang University Hangzhou310018 China Nanjing University of Science and Technology Computer Science and Engineering Nanjing210000 China

ISBN: (纸本)9781665410205

Transfer learning has become a key technique in deep learning, widely adopted in the industry and academia for developing customized models, especially for specific and downstream tasks solving. Despite the prevalence of transfer learning, the target model can easily inherit defects from the source model during the learning process, such as vulnerability to backdoor attacks and adversarial attacks. Thus, this work proposes a novel approach, iterative pruning learning approach (IPLA), that reduces the inheritance of potential defects during the transfer learning process. In order to reduce the vulnerability to attacks and improve the robustness of target model, IPLA evaluates the importance of weights from the source model and retains ones that are critical to the target task, then prunes the redundant weights through an iterative pruning process. Experiments are performed on 4 datasets over 2 backbone source models. Results demonstrate the satisfactory performance of our proposed method. © 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

Graph Based Frequent Item Set Generation in Association Rule Mining

Graph Based Frequent Item Set Generation in Association Rule...

引用

2023 IEEE International Conference on Next Generation Electronics, NEleX 2023

作者： Amalanathan, Geetha Mary School of Computer Science and Engineering Vellore Institute of Technology Tamil Nadu Vellore India

ISBN: (纸本)9798350319088

This research proposes a new technique that uses a reconstruction strategy for categorical datasets to preserve the privacy of the association rules. In order to identify all frequent item association sets and determine sets comprising frequent items based on the association sets, the suggested technique takes advantage of the two-item permutation set to create an association part. The enhanced method scans the database only once, addressing a flaw in the conventional approach that scans the database twice and so increasing scanning costs. The database and association sets can be mined using the two-item permutation set, which has the advantages of operating more quickly, requiring less memory, and being simple to maintain. © 2023 IEEE.

关键词： Association rules

来源：评论

学校读者我要写书评

暂无评论

Index-Based Mode Adjustment for Energy Saving of Service Vehicles and Robots in Vehicular Networks 9

Index-Based Mode Adjustment for Energy Saving of Service Veh...

引用

9th International Conference on computer and Communications, ICCC 2023

作者： Yan, Degao Wang, Lusheng Kai, Caihong Peng, Min Hefei University of Technology School of Computer Science and Information Engineering Hefei230601 China

ISBN: (纸本)9798350317251

Vehicular networks with service robots and vehicles have been widely studied in the past few years, and a large number of these vehicles and robots may appear in people's lives, such as in science and technology park, university town, restaurant, and public transportation hub. Energy-saving in vehicular networks becomes a key issue in these scenarios for ensuring the endurance time of vehicles and robots, so it is useful to dynamically adjust their working modes based on the pedestrian flow density around them. In this paper, we predict the peaks and troughs of the pedestrian flow based on four technical indexes, and adjust between active and ordinary modes for the vehicles and robots to save their energy while still guaranteeing their services. Simulation results show that the used technical indexes can predict the peaks and troughs of a pedestrian flow, hence the proposal effectively reduces the energy consumption of the vehicular networks. © 2023 IEEE.

关键词： Vehicles

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：