检索结果-内蒙古大学图书馆

Adaptive Anomaly Detection for Secure Federated Learning in IIoT Environments

Procedia computer science 2025年 258卷 536-551页

作者： R C Karpagalakshmi J. Lenin P Rajaram V Balaji Rajasekar Rangasamy Akey Sungheetha School of Computer Science and Engineering Galgotias Universit India GITAM School of Technology GITAM University Bengaluru - 560010 India

Federated Learning (FL) systems train models collaboratively among Industrial Internet of Things (IIoT) devices but face prominent security issues, especially backdoor attacks due to diversified data. The presented work proposes an adaptive anomaly detection approach for security enhancement of FL in IIoT environments, considering model performance across diverse data contexts. The proposed approach leverages state-of-the-art graph-based data clustering together with differential privacy to classify data effectively into representative clusters, allowing it to detect anomalies in a localized fashion. It encompasses the most important components: hierarchical clustering, the adaptive anomaly identification module, and secure data aggregation protocol. These inventions reduce the possibility of backdoor attacks, enhance model robustness, and improve model accuracy. The role of this method was extensively validated with benchmark datasets such as Fashion-MNIST, Google Speech Commands, IoT-33, and Smart Manufacturing Systems SMS-IIOT in homogeneous and heterogeneous data settings. The results presented large reductions in backdoor attack success rates, firmly confirming the capability of the proposed solution for enhancing FL security and reliability in IIoT applications.

关键词： Federated learning anomaly detection method Industrial Internet of Things Smart Manufacturing Systems MNIST

来源：评论

学校读者我要写书评

暂无评论

Fraud Detection in Credit Card through the Machine Learning Algorithms 1

Fraud Detection in Credit Card through the Machine Learning ...

引用

1st IEEE International Conference on Advances in Computing, Communication and Networking, ICAC2N 2024

作者： Kummarikunta, Sandhya Muppagowni, Ganesh Karthik Patam, Keerthi Pennera, Mounika Patimeedi, Upendra Harshith Reddy, Poreddy Chandra Mohan Babu University School of Computing Dept. AIandML Tirupati India GITAM University-Bengaluru Campus GITAM School of Technology Department of CSE Bengaluru India Sree Vidyanikethan Engineering College Dept. Computer Science and Engineering Tirupati India

ISBN: (纸本)9798350356816

The threat of credit card fraud is high and so there should be efficient ways to combat it. The research is being employed to focus on how to enhance credit card fraud detection, machine learning methodologies can be employed. The major benefit of this structured design model is that it observes many transaction variables and find out any potential threat transaction since its trained to do so. To start the project, a large dataset of both authentic and fraudulent credit card transactions will be collected and preprocessed. For the machine to learn how we want it to extract correct location, time, date and users' behavior and an important amount of transaction has been made. This improves our dataset by adding relevant information. This research is based on identifying fake activities it will discuss how to XGBoost, CatBoost and Logistic Regression used for this purpose. © 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

An Initial Risk Assessment for Multimodal with LSTM-Based Trust Evaluation Framework for Autonomous Vehicle Security

引用

SN computer science 2025年第2期6卷 1-15页

作者： Renjith, P.N. Balasubramani, S. Ramesh, K. Patnala, Eswar School of Computer Science and Engineering Vellore Institute of Technology Chennai Campus Chennai India Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Andhra Pradesh Vaddeswaram India Department of Computer Science and Engineering Sri Krishna College of Engineering and Technology Coimbatore India

This research aims to develop a new approach to increase the safety and reliability of Autonomous Vehicle (AV) through the proposed risk assessment framework, supported by the trust evaluation approach derived from a machine learning algorithm. This work proposes a comprehensive risk assessment model with real-time sensor data, Vehicle-to-Vehicle (V2V), key communication reliability, environmental cognition, and Improved Long Short-Term Memory (I-LSTM). This framework is multidimensional compared to most conventional models, focusing primarily on assessing individual threat factors. Here, the machine learning portion is designed to evaluate and predict trust by quickly processing vast amounts of information from sensors, signals, and prior operation history. Such an approach to trust assessment enables the system to continuously evaluate the dependability of automated vehicle operation and identify threats to security with improved accuracy. The effectiveness of the performance of this method is substantiated by a number of stand-alone and live scenarios, where the model's performance is higher in perceiving possible risks, avoiding threats, and enhancing safety than the conventional approaches. The findings suggest that the safety regulations of the AVs will be improved by using a multi-dimensional risk assessment model and integrating the I-LSTM trust rating with 95.5% accuracy, 96.7% risk identification, and 180 ms response time. This will cause AV and its surrounding environment to be accepted by the public and used on the roads. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： Autonomous vehicles LSTM model Machine learning Risk assessment Trust evaluation

来源：评论

学校读者我要写书评

暂无评论

Automatic text inpainting and quality elevation in video sequences

引用

Multimedia Tools and Applications 2024年 1-34页

作者： Palivela, Lakshmi Harika Dharmalingam, Vivekanandan Gayathri, D. Bala School of Computer Science and Engineering Vellore Institute of Technology Chennai Vandalur-Kelambakkam Road Chennai600127 India Department of Information Technology Madras Institute of Technology Anna University Chennai India Department of Computer Science and Engineering B.S.Abdur Rahman Crescent Institute Of Science and Technology Chennai India

Scene text removal is a recent development in computer vision that replaces text patches in natural images with the appropriate background. Text removal is a difficult process leading to faulty areas of text containing text strokes with their hazy backgrounds. Text in the real world uses a variety of font kinds, some of which are difficult to localize due to their chaotic shapes, varied shading degrees, and orientation *** text erasing may include the subtasks of text detection as well as text inpainting. Both subtasks require a large amount of data to be successful;but, existing approaches were limited by insufficient real-world data for scene-text elimination. Eventhough the existing works produced considerable performance improvement in scene text removal, they often leave many text remains like text strokes, thus producinglow-quality visual outcomes. Therefore, this paper proposes an automatic text inpainting and video quality elevation model by using the Improved Convolutional Network-based ***, the video samples are collected from the diverse datasets and then converted into frames. Next, the frames are deblurred using an enhanced Convolutional Neural Network (CNN) model that has three convolutional layers for accurately localizing the texts in frames. Subsequently, the texts are detected by utilizing the CLARA-based VGG-16 network. Afterward, the text strokes are removed using a convolutional Encoder and decoder network to eliminate the presence of text on complex backgrounds and textures. Here, the coordinates of text in the deblurred frames are used to crop out the text stroke regions. So, the texts are in-painted, and then, the text in-painted regions are pasted back to their original positions in the frames. Furthermore, the video quality is elevated with the help of the DenseNet-centric Enhancement network. The experimental outcomes demonstrate that the proposed model effectively removed scene texts and enhanced the video qu

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Design an optimization based ensemble machine learning framework for detecting rice leaf diseases

引用

Multimedia Tools and Applications 2024年第36期83卷 84401-84424页

作者： Rajasekhar, Veeramreddy Arulselvi, Gnanasekaran Babu, K. Suresh Department of Computer Science Engineering Annamalai University Tamilnadu Chidambaram India Department of Computer Science and Engineering Faculty of Engineering and Technology Annamalai University Tamil Nadu Chidambaram India International School of Technology and Sciences for Women East Gonagudem Rajanagaram A.P Rajamahendravaram India

The agriculture industry is currently dealing with serious issues with rice plants as a result of illnesses that decrease the quantity and output of the harvest. Numerous fungi and bacteria diseases harm plants that affect the growth of yield. So identification of the detection of crop diseases is essential for enhancing the productivity of crops. Many techniques have been developed to improve disease detection in crops but there are still some issues such as noise, time consumption, delay, poor segmentation, and less accuracy. To overcome these issues, this paper, designed a Spider Monkey-based Random Forest (SMbRF) model for accurate detection and classification of rice leaf diseases and the designed model was implemented in the Python system. The main aim is to develop an optimization-based random forest technique for accurate prediction of rice leaf disease by exact segmentation. Initially, preprocessing is performed to enhance the data quality and remove errors. Furthermore, separate the lesions using mean shift image segmentation and extract the shape and color features to improve the detection results of the developed model. As well, spider monkey fitness is updated in the RF classification layer for accurate classification of diseases and improves accuracy with less execution time. The experiment results show the reliability and efficiency of the designed model, it attains better performance in accuracy, sensitivity, specificity, and precision. The designed model attained 99.29% accuracy, 99.52% sensitivity, 98.76% precision, and 99% specificity proving the scalability of the designed model. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

A New Alliance of Machine Learning and Quantum Computing: Concepts, Attacks, and Challenges in IoT Networks

引用

IEEE Internet of Things Journal 2025年第12期12卷 18865-18886页

作者： Rishiwal, Vinay Agarwal, Udit Yadav, Mano Tanwar, Sudeep Garg, Deepak Guizani, Mohsen MJP Rohilkhand University Department of Computer Science and Information Technology Bareilly India Bareilly College Bareilly Department of Computer Science India Nirma University Institute of Technology Department of Computer Science and Engineering Gujarat Ahmedabad382481 India SR University School of Computer Science and Artificial Intelligence Telangana- Warangal506371 India Abu Dhabi United Arab Emirates

The Internet of Things (IoT) is a constantly expanding system connecting countless devices for seamless data collection and exchange. This has transformed decision-making with data-driven insights across different domains. However, challenges arise concerning security and computational limitations. To strengthen IoT against cyber threats and optimize resource usage, combining Quantum Computing with Machine Learning (ML) is a promising approach. ML enables computers to learn from data and detect patterns without explicit programming. By leveraging ML algorithms, vast datasets from IoT devices can be analyzed, identifying anomalies and forecasting potential security breaches. Yet, conventional ML algorithms may need help with the complexity and scale of IoT data. Quantum Computing, based on quantum mechanics, offers unparalleled computational speed and scale. Quantum ML algorithms can quickly analyze IoT datasets, identifying patterns and potential threats. This study examines the ideas behind ML, quantum computing, and their potential collaboration within IoT networks. The research focuses on the possibility of improving the security of IoT networks by integrating quantum computing approaches with ML. It also addresses the challenges and limitations of integrating ML and quantum computing in the context of IoT networks. These obstacles include hardware constraints, algorithm complexities, and the need for specialized knowledge. © 2025 IEEE.

关键词： Quantum computers

来源：评论

学校读者我要写书评

暂无评论

Glioma Segmentation in MR Images Using 2D Double U-Net: An Empirical Investigation 10th

Glioma Segmentation in MR Images Using 2D Double U-Net: An ...

引用

10th International Conference on Innovations in computer science and engineering, ICICSE 2022

作者： Webber, Julian L. Nancy Noella, R.S. Mehbodniya, Abolfazl Ramachandran, V. Stalin David, D. Rangasamy, Rajasekar Sengan, Sudhakar Doha Kuwait Department of Computer Science and Engineering Sathyabama Institute of Science and Technology Tamil Nadu Chennai600119 India Department of Computer Science and Engineering GITAM University Karnataka Bengaluru561203 India Department of Information Technology Vel Tech Multi Tech Dr. Rangarajan Dr. Sakunthala Engineering College Tamil Nadu Chennai600072 India Department of Computer Science and Engineering GITAM School of Technology GITAM University Karnataka Bengaluru561203 India Department of Computer Science and Engineering PSN College of Engineering and Technology Tamil Nadu Tirunelveli627152 India

ISBN: (纸本)9789811974540

Glioma develops inside the brain. Automatic glioma segmentation reduces computational time and increases survival owing to previous treatment preparations—2D double U-Net segments glioblastoma from multi-modal MRI images (MRI). 2D brain models need fewer computational resources than 3D models. Residual U-Net (RU-Net) and dilated convolution U-Net make up the Double U-Net design (RU-Net). RU-residual Net’s route contains three 33 convolution kernels. DU-Net contains three 33 and 55 convolution kernels with a two dilation rate. RU-Net is more uncomplicated to optimise than deep networks and makes fewer training mistakes than deep networks. DU-Net gathers contextual information and creates details. The suggested model was assessed using the BraTS 2017 training dataset and attained dice similarity coefficients of 0.91, 0.85, and 0.88 for total, enhanced, and tumour core (TC), respectively. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Tumors

来源：评论

学校读者我要写书评

暂无评论

Hybrid Bacterial Foraging Optimization with Sparse Autoencoder for Energy Systems

引用

computer Systems science & engineering 2023年第4期45卷 701-714页

作者： Helen Josephine V L Ramchand Vedaiyan V.M.Arul Xavier Joy Winston J A.Jegatheesan D.Lakshmi Joshua Samuel Raj Business Analytics School of Business and ManagementChrist UniversityBangalore560029India Department of Computer Science and IT School of SciencesJain Deemed to be UniversityBangalore560027India Department of Computer Science and Engineering Karunya Institute of Technology and SciencesCoimbatore641114India College of Computer Studies University of Technology Bahrain18041Bahrain Institute of Computer Science and Engineering Saveetha School of EngineeringSaveetha Institute of Medical and Technical SciencesChennai602105India Department of Computer Science and Engineering Panimalar Institute of TechnologyChennai600123India Department of Information Science&Engineering CMR Institute of TechnologyBengaluru560037India

The Internet of Things(IoT)technologies has gained significant interest in the design of smart grids(SGs).The increasing amount of distributed generations,maturity of existing grid infrastructures,and demand network transformation have received maximum *** essential energy storing model mostly the electrical energy stored methods are developing as the diagnoses for its procedure was becoming further *** dynamic electrical energy stored model using Electric Vehicles(EVs)is comparatively standard because of its excellent electrical property and flexibility however the chance of damage to its battery was there in event of overcharging or deep discharging and its mass penetration deeply influences the *** paper offers a new Hybridization of Bacterial foraging optimization with Sparse Autoencoder(HBFOA-SAE)model for IoT Enabled energy *** proposed HBFOA-SAE model majorly intends to effectually estimate the state of charge(SOC)values in the IoT based energy *** accomplish this,the SAE technique was executed to proper determination of the SOC values in the energy ***,for improving the performance of the SOC estimation process,the HBFOA is *** addition,the HBFOA technique is derived by the integration of the hill climbing(HC)concepts with the BFOA to improve the overall *** ensuring better outcomes for the HBFOA-SAE model,a comprehensive set of simulations were performed and the outcomes are inspected under several *** experimental results reported the supremacy of the HBFOA-SAE model over the recent state of art approaches.

关键词： Internet of things energy systems state of charge estimation machine learning deep learning metaheuristics

来源：评论

学校读者我要写书评

暂无评论

Development of a Real-time Location Monitoring App with Emergency Alert Features for Android Devices 4

Development of a Real-time Location Monitoring App with Emer...

引用

4th IEEE Global Conference for Advancement in technology, GCAT 2023

作者： Gowda, Dankan V. Prasad, K.D.V. Shekhar, R. Srinivas, Rachakonda Srinivas, Kale Naga Venkata Lakineni, Prasanna Kumar Department of Electronics and Communication Engineering BMS Institute of Technology and Management Karnataka Bangalore India Pune India Department of Computer Science and Engineering Alliance University Karnataka Bangalore India Department of Computer Science and Engineering Aditya Institute of Technology and Management Tekkali India Department of Computer Science and Engineering Aditya College of Engineering Surampalem India Department of CSE GITAM School of Technology GITAM University Visakhapatnam India

ISBN: (纸本)9798350305258

Smartphones have completely altered the mobile communication scene. Wi-Fi, global positioning system navigation, high-resolution cameras, and touchscreens with high-speed internet access are just some of the cutting-edge capabilities that these devices offer, allowing users to stay in constant contact with the present. Since many of these features are embedded deeply in the mobile operating system, they are typically inaccessible to the average user. However, Google released Android, a revolutionary operating system. Because of its open system architecture, this platform encourages third-party development and a debugging environment that users may change to create their own unique apps. In this research project, we examine the development of an Emergency Based Remote Collateral Tracking System app on the Android mobile platform from Google. There are three main forms of emergencies: those involving the heart, those involving personal safety, and those involving the roads. Users who own and operate motor vehicles are the primary focus of this app. Our program can keep tabs on the driver's pulse by connecting to a heart rate monitor. Our application has a backup function in case of anomalies. First, it sends SMS messages containing the user's location data after using GPS to do so. © 2023 IEEE.

关键词： Android application development Emergency alert system GPS tracking Location monitoring app Location sharing Real-time location tracking

来源：评论

学校读者我要写书评

暂无评论

Hybrid Optimization Algorithm for Handwritten Document Enhancement

引用

computers, Materials & Continua 2024年第3期78卷 3763-3786页

作者： Shu-Chuan Chu Xiaomeng Yang Li Zhang Václav Snášel Jeng-Shyang Pan College of Computer Science and Engineering Shandong University of Science and TechnologyQingdao266590China School of Information and Control Engineering Qingdao University of TechnologyQingdao266520China Faculty of Electrical Engineering and Computer Science VŠB-TU OstravaOstrava70080Czech Republic Department of Information Management Chaoyang University of TechnologyTaichung41349Taiwan

The Gannet Optimization Algorithm (GOA) and the Whale Optimization Algorithm (WOA) demonstrate strong performance;however, there remains room for improvement in convergence and practical applications. This study introduces a hybrid optimization algorithm, named the adaptive inertia weight whale optimization algorithm and gannet optimization algorithm (AIWGOA), which addresses challenges in enhancing handwritten documents. The hybrid strategy integrates the strengths of both algorithms, significantly enhancing their capabilities, whereas the adaptive parameter strategy mitigates the need for manual parameter setting. By amalgamating the hybrid strategy and parameter-adaptive approach, the Gannet Optimization Algorithm was refined to yield the AIWGOA. Through a performance analysis of the CEC2013 benchmark, the AIWGOA demonstrates notable advantages across various metrics. Subsequently, an evaluation index was employed to assess the enhanced handwritten documents and images, affirming the superior practical application of the AIWGOA compared with other algorithms.

关键词： Metaheuristic algorithm gannet optimization algorithm hybrid algorithm handwritten document enhancement

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：