检索结果-内蒙古大学图书馆

International Conference on Communication Systems and Network Technologies (CSNT)

作者： Vipin Kumar Vivek Kumar Abhay Pratap Singh Bhadauria Jay Dixit Amit Kumar Department of Computer Science Gurukula Kangri (Deemed to be University) Haridwar India Department of Computer Engineering & Applications GLA University Mathura Department of Computer Engineering & Applications GLA University Mathura UP

ISBN: (数字)9798331531935

ISBN: (纸本)9798331531942

Edge computing has transformed technology by enabling seamless connections between IoT devices, but it also introduces significant security challenges. EC is crucial for providing minimal latency processing and reducing the load on centralized servers, ensuring timely and scalable intrusion detection for IoT environments. The findings underscore the potential of combining edge computing, IoT, and deep learning to address evolving security challenges in distributed systems. To mitigate these risks, efficient models for detecting malicious activities are crucial. This study investigates the application of edge computing, Internet of Things (IoT), and deep learning to improve the performance of Intrusion Detection Systems (IDS). By leveraging the UNSW-NB15 dataset, the research assesses the capability of deep learning models to identify and mitigate cyber threats effectively. The results demonstrate better performance, showing their suitability for real-time security applications. These findings highlight the potential of intelligent intrusion detection systems powered by robust datasets and deep learning for addressing evolving security threats in edge computing environments.

关键词： Deep learning Image edge detection Computational modeling Intrusion detection Real-time systems Internet of Things Security Servers Long short term memory Edge computing

来源：评论

学校读者我要写书评

暂无评论

Hybrid Optimization Algorithms for Accurate Prediction and Classification of Cardiovascular Diseases

Hybrid Optimization Algorithms for Accurate Prediction and C...

引用

3rd IEEE International Conference on Automation and Computation, AUTOCOM 2025

作者： Kumar, Gaurav Varshney, Neeraj Gla University Department of Computer Engineering & Applications Mathura India

ISBN: (纸本)9798331542375

A collection of precise prediction models is necessary to lessen the burden of cardiovascular disease (CVD), which continues to be a leading cause of death worldwide. This work presents a unique hybrid optimization approach for improving the categorization and prediction of cardiac disease. Support Vector Machine (SVM), Salp Swarm Optimized Neural Network (SSO-NN), Particle Swarm Optimization (PSO), Ant Colony Optimization (ACO), Bayesian Optimization of SVM (BO-SVM), and by combining PSO and gradient descent (PSOGD) are some of the advanced machine learning algorithms that have been implemented with improved accuracy. Training, testing, and validation are done using the Cleveland and Framingham datasets. Imputation for missing data and feature scaling using MinMaxScaler are important preprocessing processes. In order to evaluate performance parameters like as sensitivity, specificity, and accuracy. As a consequence, the hybrid PSOGD algorithm achieved impressive results, with accuracies with the dataset of Cleveland having 99.56% and other dataset Framingham having 98.80%. The model's robustness was shown by the sensitivity and specificity results. The measures like Mean Absolute Error (MAE), Mean Squared Error (MSE), and Root Mean Squared Error (RMSE) over epochs, the performance analysis is further testified to for model validation. It suggests that hybrid optimization algorithms that improve CVD prediction models be praised as essential for management planning and early identification. By exposing scalable alternatives for heart disease prediction, our study offers crucial help in the area where AI and health intersect. © 2025 IEEE.

关键词： Particle swarm optimization (PSO)

来源：评论

学校读者我要写书评

暂无评论

Cybersecurity Threat Detection in Smart Cities using Box Plot Sampling Isolation Forest 1

Cybersecurity Threat Detection in Smart Cities using Box Plo...

引用

1st International Conference on Intelligent Systems and Computational Networks, ICISCN 2025

作者： Shankari, S. Uma Mohameed, Haeedir Kulkarni, Megha Aravindh, S. Purushotham, N. Srm Institute of Science and Technology Department of Computer Science and Applications Ramapuram India The Islamic University of Al Diwaniyah College of Technical Engineering Department of Computers Techniques Engineering Al Diwaniyah Iraq Nitte Meenakshi Institute of Technology Department of Civil Engineering Bengaluru India New Prince Shri Bhavani College of Engineering and Technology Department of Mechanical Engineering Chennai India Mohan Babu University Department of Computer Science and Engineering Tirupati India

ISBN: (纸本)9798331529246

Now a days, the standard of living in urban areas is advanced by leveraging technologies such as Cyber-Physical Systems (CPS) and Internet of Things (IoT) with physical infrastructures. However, smart cities highly rely on digital ecosystems, which makes them vulnerable to various cyber threats such as Distributed Denial of Service (DDoS) which leads in violations of privacy and threats to safety of citizens. To develop an effective and efficient system for detection of cybersecurity threats, Box plot Sampling Isolation Forest (BSIF) is proposed. Initially, the data was collected from the Botnet Traffic attack in Internet of Things (BoT-IoT) dataset which contains various normal traffic and Botnet traffic data. After that, Label Encoding (LE) was used for preprocessing the data, which assigns numerical labels to each category in the dataset. Furthermore, Recursive Feature Elimination (RFE) technique was utilized for iterative extraction and selection of features based on their weights is performed by Decision Tree (DT). Finally, the proposed BSIF model is used for detection of cybersecurity threats associated with smart cities, by leveraging box plot sampling method. The proposed obtain better results with 99.74% Precision, 99.92% Accuracy, 99.87% Recall and 99.84% F1-score, compared with Smart Attacks Learning Machine Advisor (SALMA) respectively. © 2025 IEEE.

关键词： Bot (Internet)

来源：评论

学校读者我要写书评

暂无评论

Intelligent Email Spam Detection: A Machine Learning-Based Approach

Intelligent Email Spam Detection: A Machine Learning-Based A...

引用

Trends in Material Science and Inventive Materials (ICTMIM), International Conference on

作者： Vinod Jain Department of Computer Engineering and Applications GLA University Mathura India

ISBN: (数字)9798331501488

ISBN: (纸本)9798331501495

Email spam emails frequently contain dangerous material like viruses, phishing attempts, and fraudulent schemes. Email spam detection is an essential component of cybersecurity. Machine learning models are required to increase accuracy and efficiency because traditional rule-based filtering strategies are insufficient to handle developing spam techniques. This study investigates how well five popular machine learning algorithms—Random Forest, Logistic Regression, Support Vector Machine (SVM), Decision Tree, and Multinomial Naïve Bayes (MultinomialNB) to detect and categorize spam emails. Different methods are used by each of these models to examine email content and detect spam. MultinomialNB is a probabilistic classifier founded on the Bayes theorem, excels at text classification problems. By merging several decision trees, Random Forest, an ensemble learning technique, improves generalization and decreases overfitting while increasing prediction accuracy. A linear model for binary classification called logistic regression uses learned weights for several features to calculate the likelihood that an email is spam. SVM, a potent classification method, finds the best hyperplane in a high-dimensional space to distinguish between spam and non-spam emails. A rule-based approach called a Decision Tree uses a hierarchical structure of decision nodes to classify emails, making it simple to use and analyze. A dataset of tagged spam and non-spam emails is used to assess the performance of these models. To ensure a thorough evaluation of the model, the dataset is divided into training and testing sets. To compare the efficacy of the models, evaluation criteria accuracy is employed. While all models perform well, the results show that SVM offer superior accuracy and achieved 98.45% accuracy. The results emphasize how crucial it is to choose the right machine learning models depending on the properties of the dataset, available computing power, and intended performance indicato

关键词： Support vector machines Training Logistic regression Accuracy Unsolicited e-mail Computational modeling Text categorization Bayes methods Decision trees Random forests

来源：评论

学校读者我要写书评

暂无评论

DNN-STACK: a stacking technique based on deep neural network for detecting copy-move forgery

引用

Neural Computing and applications 2025年第6期37卷 4989-5004页

作者： Krishnalal, G. Jagathy Raj, V.P. Madhu, G. Arun, K.S. School of Engineering Cochin University of Science and Technology Kerala Cochin682022 India School of Management Studies Cochin University of Science and Technology Kerala Cochin682022 India Department of Computer Applications Cochin University of Science and Technology Kerala Cochin682022 India

In recent years, detecting image forgery has become an important topic because of the availability of efficient and sophisticated image-editing software. Copy-move forgery, which involves copying a section of an image and pasting it to a different location inside the same image, is one of the most popular tampering techniques that alter the identity of a given image. This paper presents DNN-STACK, a deep neural network-based stacking scheme to identify copy-move forgery by effectively combining the predictions yielded by different base-level models. To extract hierarchical representations from the given images and generate base-level predictions, the proposed approach uses five distinct but complementary deep learning-based base-level models. After that, a consensus prediction is generated using the proposed DNN-STACK model, which can infer the nonlinear relationship between the base-level predictions. Experimental evaluation on three publicly available datasets, such as MICC-F600, MICC-F2000, and FAU, reveals the fact that the proposed DNN-STACK model outperforms the existing forgery detection techniques, significantly improving detection accuracy across varying image resolutions and attack types, including rotation, scaling, noise, and compression levels. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Hybrid Optimization Algorithms for Accurate Prediction and Classification of Cardiovascular Diseases

Hybrid Optimization Algorithms for Accurate Prediction and C...

引用

Automation and Computation (AUTOCOM), International Conference on

作者： Gaurav Kumar Neeraj Varshney Department of Computer Engineering & Applications GLA University Mathura India

ISBN: (数字)9798331542375

ISBN: (纸本)9798331542382

关键词： Heart Support vector machines Training Accuracy Sensitivity Computational modeling Predictive models Classification algorithms Optimization Testing

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Technique for computer Vision-Based Pose Estimation for Augmented Reality 3rd

Deep Learning Technique for Computer Vision-Based Pose Estim...

引用

3rd International Conference on Intelligent Computing Techniques for Smart Energy Systems, ICTSES 2023

作者： Palanimeera, J. Ponmozhi, K. Jyothi, Kanagaraj Dargar, Shashi Kant Birla, Shilpi Department of Computer Applications Sathyabama Institute of Science and Technology Chennai India Department of Computer Applications Kalasalingam Academy of Research and Education Krishnan Kovil Tamil Nadu Virudhunagar India Department of Biotechnology Kalasalingam Academy of Research and Education Krishnan Kovil Tamil Nadu Virudhunagar India Department of Electronics and Communication Engineering Kalasalingam Academy of Research and Education Krishnan Kovil Tamil Nadu Virudhunagar India Department of Electronics and Communication Engineering Manipal University Jaipur Rajasthan Jaipur India

ISBN: (纸本)9789819784288

Pose estimation approaches of open pose were suggested. Pose estimation in real-time is a difficult research subject with many computer vision applications. Pose estimation applications are Human Activity Estimation, Motion Transfer and Augmented Reality, Training Robots, Motion Tracking for Consoles, and Human Fall Detection. This paper describes the Augmented Reality (AR) of pose estimation. AR is an enhanced version of the real physical world that is achieved through the use of digital visual elements, sound, or other sensory stimuli delivered via technology. One interesting use for obtaining the Open-Pose discovered important locations in each pose is in the field of augmented reality. A technique for 3D model overlays on an image using pose key point information that is presented in this study. To extract crucial information from the data, the fully convolutional networks deep learning technique is used. The technique used in this work comprises the real-time intersection of the picture plane with the intended 3D model and accurate model orientation based on the key point data. The performance will greatly depend on the Graphics Processing Unit specifications. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Harnessing Deep Learning and Time Series Models for Accurate Global Solar Radiation Prediction

引用

Procedia computer Science 2025年 259卷 98-107页

作者： K. Meena A. Vadivel Tanvir Habib Sardar Arnav Kotiyal Guru Prasad M S Utsav Kumar Department of Computer Science and Engineering School of Engineering Dayananda Sagar University Bengaluru - 562112 India Department of Computer Applications Graphic Era (Deemed to be University) Dehradun India

For applications such as weather forecasting, power grid management, and solar energy integration, accurate solar radiation prediction is essential. Using real-time data from the EU Science Hub’s Climate Monitoring Satellite Application Facility (CM SAF), this research examines the efficacy of several time series models for hourly solar radiation prediction. The data are subjected to stationarity testing using the Augmented Dickey-Fuller (ADF) test prior to the models being applied. This study uses well-known time series models, including Vector Auto-regression (VAR), Linear Regression, and Autoregressive Integrated Moving Average (ARIMA). The performance of the proposed model is evaluated using Mean Square Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), R-squared, and Mean Absolute Percentage Error (MAPE). It is found that Vector Auto-regression (VAR) is encouraging for predicting solar radiation on hourly basis with least amount of overall error. This analysis has used residual error inspection, error distribution analysis and sample accuracy evaluation using MAPE. This paper highlights the importance of VAR on using time series model for predicting solar radiation.

关键词： Solar Radiation Prediction Time Series Models Autoregressive Integrated Moving Average (ARIMA) Vector Autoregressive (VAR) Regression Error Metrics performance analysis

来源：评论

学校读者我要写书评

暂无评论

Enhanced Monitoring and Security Measures with Video Analysis

Enhanced Monitoring and Security Measures with Video Analysi...

引用

2025 International Conference on Multi-Agent Systems for Collaborative Intelligence, ICMSCI 2025

作者： Jyothi, V. Esther Rakesh, G. Aruna, Vipparla Gorintla, Shobana Ayyappa, Yalanati Naidu, U. Ganesh Velagapudi Ramakrishna Siddhartha Engineering College Deemed to be University Department of Computer Applications A.P. Vijayawada India Department of Computer Science and Engineering Pothavarapadu A.P India Vel Tech Rangarajan Dr.Sagunthala R&d Institute of Science and Technology Department of Computer Science and Engineering Tamilnadu Avadi India B V Raju Institute of Technology Telangana Narsapur India

ISBN: (纸本)9798331509828

In modern surveillance, activities have increasingly become dependent on the continuous observation offered by CCTV systems. Still, with massive amounts of video data generated in a minute, sifting through this information manually to pick up any anomalies would be extremely burdensome and nearly impossible without significant human labor and vigilant watchfulness. CNN and CLIP models changed everything with regards to the working of surveillance systems. It makes use of CNN's capability for video frame processing and analysis to detect and classify these activities in the frames as either normal or suspicious. At the same time, it improves this by adding the CLIP model's capability of understanding textual descriptions and visual content together for better nuance detection in suspicious activities. This methodology transforms video surveillance by breaking video streams into frames and analyzing the behavior and interactions of persons in those frames. The synergy of CNN and CLIP models not only ensures real-time, efficient, and accurate surveillance but also minimizes dependency on extensive manual labor for monitoring. This paper aims to provide a contribution toward developing better security infrastructures in public spaces, transportation hubs, and private facilities. The introduction of this anomaly-detection mechanism can hugely improve the capability of implemented surveillance systems with a proactive response based on real-time detection and response capabilities against suspicious activities. © 2025 IEEE.

关键词： Video analysis

来源：评论

学校读者我要写书评

暂无评论

Biometric Authentication with Blockchain: A Secure and User-Friendly Approach 3rd

Biometric Authentication with Blockchain: A Secure and User-...

引用

3rd International Conference on Intelligent Systems and Sustainable Computing, ICISSC 2023

作者： Subburaj, T. Raju, K. Srujan Suthendran, K. Kumar, Kovuri Praveen Rekha, Ch. Sultana, Saba Deeraj, C. Department of Master of Computer Applications Rajarajeswari College of Engineering Bengaluru India Department of CSE CMR Technical Campus Telangana Hyderabad India Department of Information Technology Kalasalingam Academy of Research and Education Tamilnadu Krishnankoli India

ISBN: (纸本)9789819783540

"Biometric Authentication with Blockchain: A Secure and User-Friendly Approach" proposes a novel system, a Blockchain-based Distributed biometric Authentication System (BDAS), to address vulnerabilities in existing biometric authentication methods. The primary concerns tackled include the leakage of biometric information, irregularity in authentication modules, and non-transparency in information management. BDAS, leveraging blockchain technology, establishes a decentralized and distributed authentication system, ensuring reliable and secure authentication while minimizing performance overhead. The authors present a detailed exploration of biometric authentication, emphasizing the immutability of biometric data and the challenges associated with centralized management. They introduce BDAS as a solution that utilizes blockchain to enhance security, reliability, and transparency in biometric authentication. The paper includes an insightful evaluation of BDAS, comparing its performance with conventional authentication systems. The proposed system exhibits increased reliability in scenarios involving disabled clients, outperforming traditional systems. The authors conclude by highlighting BDAS's contributions to securing biometric information and propose future enhancements, such as optimizing template segmentation processes and considering the number of nodes for improved reliability. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Information leakage

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：