检索结果-内蒙古大学图书馆

2024 International Conference on Distributed Systems, computer Networks and cybersecurity, ICDSCNC 2024

作者： Malathi, V. Shammi, L. Unni, Manu Vasudevan Babulal Nadaf, Akabarsaheb Devi, S. Rukmani Thangam, E. Dr. N.G.P Arts and Science College Department of Computer Science with Cyber Security Coimbatore India East Point College of Engineering and Technology Deptartment of Computer Science Bengaluru India St. Claret College Autonomous Department of Management Bangalore India Abhijit Kadam Institute of Management Ame Social Sciences Solapur India Saveetha College of Liberal Arts and Sciences Simats Deemed to Be University Department of Computer Science Chennai India Ramco Institute of Technology Department of Eee Rajapalayam India

ISBN: (纸本)9798350375442

Examining the cyber security risks faced by companies and e-commerce platforms is the focus of this research. People in the corporate world and those in academia are curious about the technology applications of e-commerce. There are now possibilities that were before unimaginable for both businesses and consumers. On the other hand, there were certain issues with its arrival, chief among them being cyber security. Among the many forms of cybercrime, this study focuses on social engineering, denial-of-service attacks, malware, and data breaches. This proposed approach consists of three phases, which are feature extraction, model training, and data preprocessing. Addressing missing values, normalizing features, and eliminating noise are all part of preprocessing, which aims to clean and organize raw data. When dealing with multivariate data, principal component analysis (PCA) is a common tool for feature extraction. Throughout the training process, we employed an AdaBoost-CNN. With an average accuracy of 90.65%, this innovative technique surpasses CNN and AdaBoost © 2024 IEEE.

关键词： cyber attacks

来源：评论

学校读者我要写书评

暂无评论

Plant Disease Detection using Image Processing with Machine Learning

Plant Disease Detection using Image Processing with Machine ...

引用

Electronics and Sustainable Communication Systems (ICESC), 2020 International Conference on

作者： Ajmeera Kiran S.K. Lokesh Naik M Silpa Raj Srinivas Kumar Palvadi Department of Computer Science and Engineering MLR Institute of Technology Hyderabad Department of Computer Science and Engineering MLR Institute of Technology Dundigal Hyderabad Department of Computer Science and Engineering (Cyber Security) CVR College of Engineering Department of Computer Science & Information Technology Koneru Lakshmaiah Education Foundation

Crop diseases pose a severe challenge to food security, yet in many parts of the world it is still challenging to promptly diagnose them owing to a lack of necessary infrastructure. Image processing may be the most effective method to anticipate this issue and provide findings that are remarkably precise. Support vector machines and deep CNN were used in this research by improving training effectiveness and accuracy. In this study, Plant Disease Dataset is used which involves images of healthy and diseased plants collected by under some controlled conditions, SVM (support vector machine which used for feature extraction of images) and CNN (it will classify the dataset images into diseased plant or healthy plant) and further it’ll be recommending the fertilizers according to the plant diseases.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Development of a Sociocyberphysical Systems cyber Threats Classifier 7

Development of a Sociocyberphysical Systems Cyber Threats Cl...

引用

7th International Symposium on Multidisciplinary Studies and Innovative Technologies, ISMSIT 2023

作者： Yevseiev, Serhii Murr, Pierre Milevskyi, Stanislav Korol, Olha Melnyk, Marharyta National Technical University 'Kharkiv Polytechnic Institute' Cybersecurity Department Kharkiv Ukraine International University of Science and Technology in Kuwait Computer Engineering Department Kuwait Kuwait National Technical University 'Kharkiv Polytechnic Institute' Cybersecurity Department Kharkiv Ukraine Set University Department of Cyber Security and Information Protection Kyiv Ukraine

ISBN: (纸本)9798350342154

The emergence of transformations of cyber-physical systems based on integration with elements of smart technologies and Internet of things predetermined the formation of socio-cyber-physical systems, which, on the one hand, expands the range of services based on the use of the advantages of social networks, on the other hand, forms the integration of targeted attacks with threats based on social engineering methods. The proposed universal classifier of cyber threats allows to take into account the possibilities of integration, as well as signs of synergy and hybridity of modern target threats. This approach increases the level of objectivity of the possible impact on the infrastructure elements of socio-cyber-physical systems by modern mechanisms of cyber-physical threats with their possible integration with threats based on social engineering methods, increases the level of security based on the timely formation of preventive measures for building multi-contour security systems, and carrying out measures to increase the level of knowledge of employees, companies, organizations, etc. © 2023 IEEE.

关键词： cyber Physical System

来源：评论

学校读者我要写书评

暂无评论

A 5G framework and its analysis of interference cancellation in multi-tier heterogeneous networks

A 5G framework and its analysis of interference cancellation...

引用

2021 IEEE International Conference on Electrical, computer, Communications and Mechatronics engineering, ICECCME 2021

作者： Gachhadar, Anand Maharjan, Ram Krishna Shrestha, Surendra Adhikari, Nanda Bikram Qamar, Faizan Institute of Engineering Tribhuvan University Department of Electronics and Computer Engineering Center of Cyber Security Malaysia

ISBN: (纸本)9781665412629

In order to attain the maximum data rate and better spectral efficiency for the 5G wireless communication network, the operators increase user density of cellular network to reduce the transmitter-receiver distance. Due to densification and wireless networks being interference-limited systems, it motivates a use of interference mitigation techniques. In this work, we present a statistical framework to evaluate and measure the performance of multi-tier heterogeneous networks using successive interference cancellation (SIC) capabilities in an heterogeneous environment where the access points and users are randomly distributed. We analyse the performance of users based on success probability, ergodic capacity, throughput gain, outage probability and coverage probability. The interference cancellation technique regenerates the interfering signals and then cancel them to improve the SIR ratio of the received signal. Hence statistical model includes performance based on varying maximum instantaneous SIR and load. © 2021 IEEE.

关键词： Heterogeneous networks

来源：评论

学校读者我要写书评

暂无评论

Bioinformatics-Driven Discovery of Signaling Pathways and Genes Influencing Cervical Cancer

引用

SN computer Science 2024年第8期5卷 989页

作者： Ali, Anooja Mohan, Jinu Nadaf, Tousif Ahamed Allabksha Ravishankar, H. Deepa, K.R. School of CSE REVA University Karnataka Bangalore India Department of Artificial Intelligence and Cyber Security Ilahia College of Engineering and Technology Kerala Ernakulam India Wipro Arabia Ltd. Dhahran Saudi Arabia School of Computing and Information Technology REVA University Karnataka Bangalore India School of Electrical and Electronics Engineering REVA University Karnataka Bangalore India

Cervical cancer is a threat to women worldwide, with poor early prognosis. Cervical cancer is strongly linked to human papillomavirus (HPV), particularly high-risk HPV16 and HPV18, a prevalent gynecological malignancy. It ranks fourth among women's malignant diseases in terms of morbidity and mortality and there has been a rise in the incidence of cervical cancer among young females in recent decades. The Gene Expression Omnibus database (GEO) was used to screen and download three gene expression profiles (GSE63514, GSE6791, and GSE9750). The study used GEO2R and Venn diagrams to identify differentially expressed genes (DEGs) across three gene expression datasets. GO and KEGG Pathway Enrichment Analysis (PEA) were then performed on the DEGs to understand their biological functions and signaling pathways. Gene set enrichment analysis (GSEA) is also applied to analyze expression profiles. Additionally, a protein–protein interaction (PPI) network is constructed using the DEGs, which underwent a functionality-based enrichment investigation to identify hub genes. The proposed approach has clinical relevance in uncovering potential therapeutic targets and improving our understanding of the prognosis and treatment of the disease. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： Cervical cancer Differentially expressed genes Expression profile Gene ontology Human papillomavirus

来源：评论

学校读者我要写书评

暂无评论

A Novel Methodology Design to Predict Hate Speech on Social Media Using Machine Learning Principles

A Novel Methodology Design to Predict Hate Speech on Social ...

引用

2024 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems, ICSES 2024

作者： Anitha, G. Karthik, G. Chadge, Rajkumar Dinesh, M. Subha, T.D. Al Sherideh, Alaa Saveetha University Department of Ece Tamil Nadu Chennai India Karpagam College of Engineering Department of It Coimbatore India Yeshwantrao Chavan College of Engineering Department of Mechanical Engineering Nagpur India Department of Vlsi Microelectronics Chennai India R.M.K. Engineering College Department of Ece Kavaraipettai Chennai India College of Information Technology Zarqa University Department of Cyber Security zarqa Jordan University of Business and Technology Jeddah21448 Saudi Arabia

ISBN: (纸本)9798331543617

Hate speech detection on social media platforms has become increasingly critical in maintaining a safe and inclusive online environment. This study proposes a novel methodology combining Bidirectional Encoder Representations from Transformers (BERT) with Convolutional Neural Networks (CNN) to improve the accuracy and robustness of hate speech detection models. The BERT-CNN hybrid model leverages BERT's contextual understanding of language and CNN's ability to capture local patterns in text data. The methodology involves comprehensive data collection from Twitter, including both labeled and unlabeled datasets, followed by rigorous data preprocessing, including text cleaning, tokenization, and feature extraction using Transformer-based embeddings. The proposed model was evaluated against nine existing models, including LR, SVM, RF, NB, DT, CNN, LSTM, BiLSTM, and BERT. The results demonstrate that the BERT-CNN hybrid model outperforms all other models, achieving an accuracy of 92.34 %, indicating its effectiveness in both precision and recall metrics. This study's findings highlight the potential of hybrid models in advancing hate speech detection technology on social media platforms. © 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

Predictive Models of Cholesterol Levels through Protein Expression Patterns

Predictive Models of Cholesterol Levels through Protein Expr...

引用

2024 IEEE International Conference on Intelligent Systems and Advanced Applications, ICISAA 2024

作者： Maram, Balajee Vasavi, Gotte Rani, V Vasudha Ramesh, B. Reddy, M Narendra Nadh Pappu, Sasibhushana Rao SR University School of Computer Science and Artificial Intelligence Telangana Warangal506371 India Malla Reddy University Department of Cyber Security School of Engineering Telangana Hyderabad India GMR Institute of Technology Department of IT Vizianagaram Dist AP Rajam India Aditya Institute of Technology and Management Dept. Of CSE Tekkali India KKR&KSR Institute Of Technology And Sciences Guntur India GITAM School Of Technology Department of CSE Visakhapatnam Campus India

ISBN: (纸本)9798331539948

This review article is designed to analyze pattern variations in protein expression in order to develop algorithms for predicting cholesterol levels. Considering the critical role cholesterol plays in health assessments, the current study evaluates the literature comprehensively so as to track the current state of research in this area. The background establishes the importance of cholesterol while pointing out the limitations of traditional techniques of prediction. The literature review covers the latest methodologies, including mass spectrometry and machine learning algorithms. Two categories the studies are divided into: proteomic approaches and computational models. It specifically states that special attention has been given to omics data integration in further work to improve the accuracy of predictive models. The critical analysis study highlighted some challenges in existing methodologies and gave indicative future directions that help develop the improvement and optimization methodologies of prediction models based on protein expression patterns. This could make a big difference in cholesterol prediction and provide more realistic and personalized health assessments. © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Optimizing Diabetes Prediction Accuracy: A Comprehensive Approach with Advanced Preprocessing and Diverse Machine Learning Classifiers 3

Optimizing Diabetes Prediction Accuracy: A Comprehensive App...

引用

3rd International Conference on Advancement in Electrical and Electronic engineering, ICAEEE 2024

作者： Talukder, Md Simul Hasan Nur, Abdullah Hafez Zaman, Snigdha Noor, Moshiur Rahman Khan, Mohammad Aman Ullah Amir, Fatima Bangladesh Atomic Energy Regulatory Authority Nuclear Safety Security and Safeguards Divison Dhaka Bangladesh International Islamic University Chittagong Department of Electronic and Telecommunication Engineering Chittagong Bangladesh International Islamic University Chittagong Department of Computer Science and Engineering Chittagong Bangladesh Eastern University Department of Electrical and Electronic Engineering Dhaka Bangladesh BRAC University Department of Computer Science and Engineering Dhaka Bangladesh Shanto Mariam University of Creative Technology Department of Computer Science and Engineering Dhaka Bangladesh

ISBN: (纸本)9798350388282

Diabetes is a prevalent chronic health disease affecting millions of people over the world. Early detection and effective management contribute in preventing its complications. This study investigates the use of machine learning algorithms to predict the risk of acquiring diabetes based on multiple clinical parameters (Indian PIMA Dataset). In the study, advanced data preprocessing techniques like missing data handling, outlier rejection, robust scaling and SOMTE oversampling are consolidated with eight traditional machine learning. Effectiveness of those eight models such as Gradient Boosting (GB), XGBoost (EGB), Random Forest (RF), Light GBM (LGBM), Cat Boost (CB), Ada Boost (AB), Decision Tree (DT) and K-Nearest Neighbor (KNN) are analyzed and compared. The prediction outcomes of each model are contrasted using accuracy, roc score and F1 score. After evaluating the model's performances, GB has provided the highest accuracy of 90.25%, ROC score of 96.38% and F1 score of 86.48%. © 2024 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Privacy preserving techniques for decision trees

引用

International Journal of Information and computer security 2021年第3-4期16卷 255-271页

作者： Liu, Xiaoqian Li, Qianmu Li, Tao Wu, Ming Department of Computer Information and Cyber Security Jiangsu Police Institute Nanjing China School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China School of Computer Science Nanjing University of Posts and Telecommunications Nanjing China

As a representative classification model, decision tree has been extensively applied in data mining. It generates a series of if-then rules based on the homogeneity of class distribution. In a society where data spreads everywhere for knowledge discovery, the privacy of the data respondents is likely to be leaked and abused. Based on this concern, we propose an overview of the rapidly evolving research results focusing on privacy preserving decision tree induction. The research results are summarised according to the characteristics of related privacy preservation techniques, which include data perturbation, cryptography, and data anonymisation. In addition, we demonstrate the comparison between the merits and demerits of these methods considering the specific property of decision tree induction. At last, we conclude the future trend of privacy preserving techniques. Copyright © 2021 Inderscience Enterprises Ltd.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Enhancing Smart City and IoT Solutions with Deep Residual Bi-LSTM Model

Enhancing Smart City and IoT Solutions with Deep Residual Bi...

引用

2023 International Conference on Self Sustainable Artificial Intelligence Systems, ICSSAS 2023

作者： Madumidha, S. Chander Rao, S. Poorna Yadav, Sameer Hashmi, Syed Ghyasuddin Ahmad, Jorair Syed, Ziauddin Sri Krishna College of Technology Department of Information Technology Tamilnadu India Geethanjali College of Engineering and Technology Eee Department Telangana Hyderabad India University of Allahabad Department of Commerce and Business Administration Uttar Pradesh Prayagraj India College of Computer Science & Information Technology Jazan University Department of Information Technology & Security Jazan Saudi Arabia Information Technology & Security College of Computer Science and Information Technology Jazan University Jazan Saudi Arabia College of Computer Science and Information Technology Jazan University Department of Computer Science Jazan Saudi Arabia

ISBN: (纸本)9798350300857

There is a limitless supply of useful information and services made available by IoT devices connected to the internet. The Internet of Things (IoT) refers to the vast network of interconnected devices seen in a smart city. The scattered and dynamic natures of entities such as sensing, actuating devices, humans, and computing resources make it challenging to design applications in such large-scale IoT systems, despite the promise nature of the new breed of data and resources. In this research study, the proposed approach takes a coordinated look at the process of creating Internet of Things apps for use in Smart Cities. The proposed approach demonstrates the need for a distributed coordination model capable of monitoring such a vast number of independently operating parts while constructing Smart City IoT applications. Preprocessing, feature selection, and model performance evaluation are all used in the suggested method. Normalization and standardization are used during preprocessing. It uses entropy HOA for feature selection. The model's effectiveness is measured with Deep Residual Bi-LSTM. When compared to BiLSTM and Residual LSTM, two existing approaches, the suggested methodology performs admirably. © 2023 IEEE.

关键词： Standardization

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：