检索结果-内蒙古大学图书馆

IEEE Transactions on Artificial Intelligence 2024年第1期5卷 370-383页

作者： Feng, Qi He, Debiao Shen, Jian Luo, Min Choo, Kim-Kwang Raymond Wuhan University School of Cyber Science and Engineering Wuhan430072 China Shandong Provincial Key Laboratory of Computer Networks Jinan250014 China School of Information Science and Technology Zhejiang Sci-Tech University Hangzhou310018 China Shanghai Technology Innovation Centre of Distributed Privacy-Preserving Artificial Intelligence Matrix Elements Technologies Shanghai201204 China University of Texas at San Antonio Department of Information Systems and Cyber Security San AntonioTX78249 United States

By leveraging smart devices [e.g., industrial Internet of Things (IIoT)] and real-time data analytics, organizations, such as production plants can benefit from increased productivity, reduced costs, enhanced self-monitoring, and autonomous decision-making. In such a setting, machine learning plays an important role in data analytics, but the use of conventional centralized machine learning solutions may raise uncomfortable concerns about data privacy. Hence, one can explore the use of federated learning. In this article, we propose privacy-preserving deep neural network training (PpNNT), which is designed to support federated learning in the multiparty setting. To minimize the overall costs, we further design a hybrid architecture to fully maximize resource utilization. Our proposed design allows the PpNNT system to provide high security, efficiency, and scalability for IIoT data analytics, as evidenced by our theoretical security proof and experimental results on the CIFAR10 dataset. © 2020 IEEE.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

An enhanced LSTM-CRF based approach for Knowledge Integration based Sentiment Analysis

An enhanced LSTM-CRF based approach for Knowledge Integratio...

引用

International Symposium on Advanced Computing and Communication (ISACC)

作者： Allam Balaram M. SilpaRaj K. Likhitha Sree V. Pramodh Kumar D. Vinay Kumar K. Venu Kumar Reddy Department of Computer Science and Engineering MLR Institute of Technology Hyderabad India Department of Computer Science and Engineering (Cyber Security) CVR College of Engineering Hyderabad India

ISBN: (数字)9798331523893

ISBN: (纸本)9798331523909

Sentiment analysis is a key element for expert reviews but is at a loss in terms of detection of sarcasm and irony, which distort the actual sentiments. This paper proposes an approach that will fuse syntactic and contextual knowledge to respond to these requirements. Steps for preprocessing include tokenization, stop word removal, lemmatization, followed by feature extraction using BERT embedding. In addressing high-dimensional output, the Relief algorithm is then used to extract the relevant features. The classification model utilizes a combination of Deep Learning for sequence LSTM networks and Maximum entropy methods, i.e., Conditional Random Fields (CRF), and enables sequential dependency learning to give better accuracy. This application of data pertaining to time and context can effectively address subtle nuances such as sarcasm and irony and classify the text as positive, negative, or neutral. It brings several advancements with respect to traditional models, thus improving the understanding of emotion in text.

关键词： Sentiment analysis Accuracy Reviews Viterbi algorithm Syntactics Feature extraction Conditional random fields Tokenization Classification algorithms Long short term memory

来源：评论

学校读者我要写书评

暂无评论

Personalized Federated Learning for Heterogeneous Residential Load Forecasting

引用

Big Data Mining and Analytics 2023年第4期6卷 421-432页

作者： Xiaodong Qu Chengcheng Guan Gang Xie Zhiyi Tian Keshav Sood Chaoli Sun Lei Cui the Shanxi Key Laboratory of Advanced Control and Equipment Intelligence Taiyuan University of Science and TechnologyTaiyuan 030024China the Faculty of Engineering and Information Technology University of Technology SydneyUltimo 2007Australia the Centre for Cyber Security Research and Innovation Deakin UniversityMelbourne 3125Australia the School of Computer Science and Technology Taiyuan University of Science and TechnologyTaiyuan 030024China

Accurate load forecasting is critical for electricity production,transmission,and *** learning(DL)model has replaced other classical models as the most popular prediction ***,the deep prediction model requires users to provide a large amount of private electricity consumption data,which has potential privacy *** nodes can federally train a global model through aggregation using federated learning(FL).As a novel distributed machine learning(ML)technique,it only exchanges model parameters without sharing raw ***,existing forecasting methods based on FL still face challenges from data heterogeneity and privacy ***,we propose a user-level load forecasting system based on personalized federated learning(PFL)to address these *** obtained personalized model outperforms the global model on local ***,we introduce a novel differential privacy(DP)algorithm in the proposed system to provide an additional privacy *** on the principle of generative adversarial network(GAN),the algorithm achieves the balance between privacy and prediction accuracy throughout the *** perform simulation experiments on the real-world dataset and the experimental results show that the proposed system can comply with the requirement for accuracy and privacy in real load forecasting scenarios.

关键词： load forecasting personalized federated learning differential privacy

来源：评论

学校读者我要写书评

暂无评论

An Intelligent Vehicle License Plate Detection for an Emergency Notification System 5

An Intelligent Vehicle License Plate Detection for an Emerge...

引用

5th International Conference on Smart Electronics and Communication, ICOSEC 2024

作者： Raja, Laxmi Bharathi, V.C. Ananthi, S. Sathya, R. Kathirvel, T. Razack, T. Shahin Abdul Karpagam Academy of Higher Education Faculty of Engineering Department of Cyber Security Coimbatore India VIT-AP University School of Computer Science and Engineering Andhra Pradesh Amaravati India Sri Eshwar College of Engineering Department of Cse Coimbatore India Kongunadu College of Engineering and Technology Department of It Tamil Nadu Trichy India

ISBN: (纸本)9798331504403

This research presents a vehicle license plate recognition and emergency notification system utilizing advanced image processing techniques. The system captures input images and employs Optical Character Recognition (OCR) to accurately extract license plate text. By cross-referencing the identified license plate number with a stored database, the system retrieves corresponding vehicle details. In the event of an emergency, the system leverages Twilio's SMS service to send notifications to designated emergency contacts. Developed using the Flask framework, the system offers a user-friendly web interface for easy interaction. This comprehensive approach enables rapid vehicle identification and facilitates timely emergency response, ensuring efficient assistance in critical situations. © 2024 IEEE.

关键词： Optical character recognition

来源：评论

学校读者我要写书评

暂无评论

An Ensemble Learning Approach to Improve Credit Scoring Accuracy for Imbalanced Data

An Ensemble Learning Approach to Improve Credit Scoring Accu...

引用

2023 International Conference on Integrated Intelligence and Communication Systems, ICIICS 2023

作者： Ranpara, Ripal D. Patel, Pratik S. Atmiya University Department of Computer Science & Information Technology Rajkot India Science University School of Cyber Security & Digital Forensic Gandhinagar India

ISBN: (纸本)9798350315455

The assessment of loan risks, known as credit scoring, is a critical procedure within the financial industry. However, this process often faces difficulties as a result of uneven data distributions. Imbalances are evident when one class has a much greater representation than the other, resulting in standard machine learning techniques displaying a bias towards the more prevalent class. The present work presents a new ensemble learning approach that aims to enhance the accuracy of credit scoring in situations when there are imbalanced class distributions. The proposed methodology incorporates a combination of several fundamental classifiers that have been trained on separate subsets of the initial dataset, resulting in a cohesive ensemble model. A series of experiments were done on a credit scoring dataset with unbalanced classes, exploring several ensemble methodologies like as bagging, boosting, and stacking. The results indicate that the ensemble strategy proposed in this study outperforms traditional techniques, exhibiting greater accuracy and F1 score. Furthermore, we conduct an analysis on the effects of various ensemble tactics on performance, offering significant insights into the process of ensemble learning for credit scoring data that is uneven. The technique proposed in this study offers a viable alternative to address the problem of imbalanced credit scoring data, hence improving the accuracy and fairness of credit scoring models in the financial industry. © 2023 IEEE.

关键词： AdaBoost Area under the curve (AUC) Bagging Boosting Credit scoring Ensemble learning Gradient boosting Machine learning Random forest Receiver operating characteristic (ROC) XGBoost

来源：评论

学校读者我要写书评

暂无评论

cybersecurity in Piezoelectric Biosensor for Sensing Application

Cybersecurity in Piezoelectric Biosensor for Sensing Applica...

引用

2024 Innovations in Intelligent Systems and Applications Conference, ASYU 2024

作者： Görmüş, Ahmet Faruk Markūnienė, Ieva Şenturk, Kenan Gönen, Serkan Barışkan, Mehmet Ali Karacayılmaz, Gökçe Yılmaz, Ercan Nurcan Technology Transfer Office Istanbul Gelisim University Istanbul Turkey Mechanical Engineering Kaunas University of Technology Kaunas Lithuania Mechatronic Engineering Istanbul Gelisim University Istanbul Turkey Software Engineering Cyber Security Research and Application Center Istanbul Gelisim University Istanbul Turkey Computer Engineering Cyber Security Research and Application Center Istanbul Gelisim University Istanbul Turkey Computer Engineeringr Istanbul Gelisim University Istanbul Turkey Electrical - Electronics Engineering Gazi University Ankara Turkey

ISBN: (纸本)9798350379433

Biosensors play a crucial role in various healthcare applications such as continuous health monitoring, targeted drug delivery, and nanosurgery. Enhancing the performance of biosensors involves integrating them with higher bandwidth external networks like 5G, necessitating a seamless connection between the biological environment and technological infrastructure to convert biochemical signals into electromagnetic signals. While sensor technologies provide real-time monitoring of vital parameters like pulse, blood pressure, and body temperature, their reliance on wireless communication networks poses security risks. This study investigates the security vulnerabilities in wireless communication infrastructure within the healthcare sector. Using an infrastructure model of an instant patient pulse monitoring system, the study identifies open ports via port scanning and conducts attacks, including Distributed Denial of Service (DDoS) and Man-in-the-Middle (MITM) attacks, resulting in data interception and potential exposure of patient information. The analysis of these attacks leads to proposed solutions aimed at addressing system vulnerabilities and fortifying the wireless communication infrastructure's security. Additionally, a model utilizing artificial intelligence is developed to detect and prevent future attacks, contributing significantly to enhancing overall system security. © 2024 IEEE.

关键词： cybersecurity

来源：评论

学校读者我要写书评

暂无评论

Combating cyberbullied Images in the Real World: A Comparative Study of CNN Architectures 21

Combating Cyberbullied Images in the Real World: A Comparati...

引用

21st International Conference on Networking, Sensing and Control, ICNSC 2024

作者： Shui, Heyun Lu, Liming Shao, Luyi Xu, Qingyi Lu, Xiaoyu Sean Kang, Qi School of Cyber Science and Engineering Nanjing University of Science and Technology Nanjing China New Jersey Institute of Technology Department of Electrical and Computer Engineering NewarkNJ United States

ISBN: (纸本)9798350365221

Image-based cyberbullying brings more complexity compared to text-based forms, presenting new challenges that tra-ditional methods struggle to address. Owing to the rapid advancement of deep learning, computer vision technology has become a powerful tool to address this issue. In recent years, Convolutional Neural Networks (CNNs) have gained prominence for image processing and recognition because of their excellent feature extraction abilities. Initially, this paper conducts a comprehensive review of the literature in the fields of computer vision and cyberbullying detection and provides an extensive comparison of the performance among different CNN architectures, including VGG, ResNet, and WRNs, on a dataset of cyberbullying images. It shows and discusses that the VGG architecture outperforms other architectures in terms of performance and computational efficiency. © 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

Get A Sense of Accomplishment in Doing Exercises: A Reinforcement Learning Perspective 25

Get A Sense of Accomplishment in Doing Exercises: A Reinforc...

引用

25th IEEE International Conference on computer Supported Cooperative Work in Design, CSCWD 2022

作者： Niu, Songdeng Cao, Sheng University of Electronic Science and Technology of China School of Computer Science and Engineering Institute for Cyber Security China

ISBN: (纸本)9781665405270

Doing exercises is vital to improving students' learning effects. Setting reasonable rewards in the process of doing exercises can promote students' problem-solving interests. Reinforcement learning has been employed on optimal instructional sequencing in education for decades. Existing reinforcement-learning-induced policies in instructional sequencing mainly pay attention to how students take actions in learning activities while attention to the setting of rewards in doing exercises has been little. To redress this imbalance, we first propose a set of calculation formulas of reward function closely associated with the difficulty of each exercise item and the consuming-time of each student. We put forward the confidence index of students as another important parameter in our reward function, which represents how sure each student is that he/she could do the exercises right. We then propose and prove a reward shaping scheme based on dynamic potential function, which can not only ensure invariance of the optimal policy of acquiring exercise-doing rewards but also accelerate the convergence of the exercise-doing process. This scheme provides a new paradigm for motivating students to do exercises in the e-learning environment, which helps to enhance students' learning enthusiasm, so as to improve their learning efficiencies impressively. © 2022 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A Behavior-Aware Scheme for Personalized Credit Computing 25

A Behavior-Aware Scheme for Personalized Credit Computing

引用

25th IEEE International Conference on computer Supported Cooperative Work in Design, CSCWD 2022

作者： Dang, Sixuan Cao, Sheng Institute for Cyber Security University of Electronic Science and Technology of China School of Computer Science and Engineering China

ISBN: (纸本)9781665405270

Quality of Service (QoS) and Quality of Experience (QoE) are employed to characterize network performance to improve network resource utilization in web/internet-based services. However, user credit that also contributes to efficient network resources allocation is ignored. Analyzing users' behaviors to estimate user credit is a common denominator studied in decades, yet they analyze incomplete attributes of users' behaviors. A general user credit computing method is urgent and challenging. Thus, we propose Quality of Credit (QoC) and define three metrics to systematically achieve user credit computing. Detailed QoC calculation and differential pricing scheme are proposed to regulate users' behaviors to improve network resource utilization, which is defined as Credit Level Agreement (CLA). We conduct extensive experiments to demonstrate the effectiveness and feasibility of QoC. Actually, QoS and QoE describe network performance metrics, while QoC depicts the credibility of users, so that they can complement each other, and jointly provide support for collaborative computing and various applications at a higher perspective than ever. © 2022 IEEE.

关键词： Network performance

来源：评论

学校读者我要写书评

暂无评论

Feature Fusion for Malware Traffic Detection Using Image Visualization and Transfer Learning 10

Feature Fusion for Malware Traffic Detection Using Image Vis...

引用

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

作者： Kumar, Sanjeev Sapru, Yudhishthira Purushottama Rao, K. Centre For Development of Advanced Computing Cyber Security Technology Division Mohali India CERT-In Indian Computer Emergency Response Team Delhi India Nit Department of Computer Applications Tamil Nadu Tiruchirappalli India

ISBN: (纸本)9798350353068

Malware threats have become increasingly sophisticated and more complex, making detecting and preventing them difficult. Traditional malware detection methods, such as signature-based detection, are no longer effective against new malware variants. Deep learning, especially convolution neural networks, has evolved significantly as end-to-end malware detection without much requirement of domain expert analysis for feature engineering. This research paper proposes a new image visualization-based malware detection and classification using transfer learning and machine learning classifiers. At first, the network traffic dumps (PCAPs) are transformed into grayscale images. After that, pre-trained CNN models, including VGG16, VGG19, EfficientNetB0, EfficientNetB1, and Xception, are customized to extract the textural features via transfer learning by adding a fully connected layer of different dimensions. Feature fusion is performed by stacking the extracted feature maps from different pre-trained models to form a single feature map. Finally, the fused feature maps are fed to train three machine learning models to obtain the best classifier. The hyperparameter optimization of all classifiers is performed using grid-search and randomized search algorithms. This study performs intensive experiments using 913 public image datasets, and the proposed method obtained 94.71% accuracy, which is an excellent performance even using a smaller dataset. The experiment results reveal that the proposed method is well-suited to deal with live malware traffic in real-world industrial IoT environments. © 2024 IEEE.

关键词： Malware

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：