检索结果-内蒙古大学图书馆

SSRN 2024年

作者： Nair, Anand R. Gowtham, Ramesh Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Coimbatore India

Cyber adversaries use advanced tools and techniques to develop malware, specifically ransomware, to extort wealth from organizations and individuals. Cybersecurity researchers, sovereign governments, and federal agencies around the globe are continuously developing numerous methods to prevent, protect, and recover from surging ransomware attacks. These attacks are often referenced using conventional labeling methods that use ransomware family name, trojans used, system vulnerabilities exploited, name of the victim organization, or the threat actor behind the attack. The usage of conventional labeling techniques often leads to referencing similar ransomware using conflicting aliases. Such inconsistent nomenclature prevents the researchers from obtaining a federated view of ransomware characteristics during the investigation. This also adversely affects the development of effective solutions against ransomware attacks due to the lack of unified behavioral information. The proposed method focuses on developing a novel semantic model that uniquely represents ransomware's behavioral characteristics. The semantic model addresses the shortcomings of inconsistent ransomware nomenclature and supports better ransomware traceability. This is achieved by formally representing the high-level adversarial tactics, the chain of behaviors, and the system-level atomic operations of ransomware in a semantic model. The behavioral characteristics are obtained from live Windows-based cryptoransomware samples analyzed in a sophisticated hybrid testbed. The proposed model is designed to be interoperable with other standard external knowledge bases. The semantic organization of harmonized, high-fidelity knowledge integrated from heterogeneous sources supports precise and context-aware search for information retrieval. The methodology promises potential applications such as discovering inferred relationships among ransomware behavioral characteristics as well as sharing and collaboration of

关键词： Ontology

来源：评论

学校读者我要写书评

暂无评论

A Scalable Model for Text Mining using Sentiment Analysis on PySpark

A Scalable Model for Text Mining using Sentiment Analysis on...

引用

Intelligent Technologies (CONIT), International Conference on

作者： K S Vishal Srivageesh K Srinidhi U Someswara Shashank Sankepalli Sai Samhitha Manju Venugopalan Department of Computer Science and Engineering Amrita School of Computing Bengaluru Amrita Vishwa Vidyapeetham India

ISBN: (数字)9798350349900

ISBN: (纸本)9798350349917

Sentiment analysis, an essential tool for deciphering public sentiment from vast internet data, offers valuable insights to businesses and policymakers. Its adoption is driven by the ability to interpret emotions, providing guidance for product refinement and decision-making. This tool is crucial for understanding user sentiments, empowering businesses to improve customer experiences, shape brand perception, and refine marketing strategies. Organizations benefit from sentiment analysis by leveraging customer insights for informed decision-making and product enhancement, thereby safeguarding positive relationships and brand reputation. The proposed system utilizes both formal and informal datasets and works on models like Logistic Regression, Naive bayes and SVM. Additionally, feature extraction techniques such as hashing and TF-IDF enhance data representation, contributing to the accuracy and F1-score of the employed models. The proposed system makes use of the PySpark platform to elevate the *** the three models utilized, SVM achieved the highest accuracy and F1-score for the Twitter dataset, with an accuracy of 0.76 and an F1-score of 0.76. Similarly, for the Amazon dataset, Logistic Regression exhibited the highest accuracy and F1-score, recording values of 0.89 for both metrics. For comparison and experimental evaluation, the models were executed on a merged dataset comprising both Twitter and Amazon data. In this merged dataset, Logistic Regression outperformed the other models, achieving an accuracy and F1-score of 0.83 for both metrics.

关键词： Text mining Support vector machines Sentiment analysis Logistic regression Analytical models Accuracy Social networking (online)

来源：评论

学校读者我要写书评

暂无评论

Optimized Rainfall Prediction Model Using Optune CatBoost: An Innovative Approach

Optimized Rainfall Prediction Model Using Optune CatBoost: A...

引用

Electrical Power engineering, Communication and computing Technology(ODICON), Odisha International Conference on

作者： Tina Babu Rekha R Nair Pavithra K Department of Computer Science and Engineering Alliance School of Advanced Computing Alliance University Bengaluru India

ISBN: (数字)9798350354379

ISBN: (纸本)9798350354386

Rainfall forecasting is important for several uses, such as agriculture, water supply, and flooding emergencies. This is because rainfall, which is a type of precipitation, is not easily predictable owing to several factors that include atmospheric, oceanic, and geographical factors. Therefore, a new Optune CatBoost prediction model has been developed here that can be used to predict rainfall. Some of the research techniques used include; data preprocessing, outlier analysis, normalization, SMOTE, feature engineering, and correlation analysis. This Optune CatBoost prediction gives a maximum accuracy of 96% a precision of 97% F1 score of 96.7%, and recall of 95.5%. The discrimination between rainfall and non-RA events is evaluated to be strong with the area under the ROC curve equalling 0.96. The study implies that the developed model could be used to enhance rainfall prediction, which in turn aids in decision-making on appropriate resource utilization in weather-sensitive areas.

关键词： Rain Accuracy Atmospheric modeling Decision making Weather forecasting Predictive models Agriculture Real-time systems Resource management Water resources

来源：评论

学校读者我要写书评

暂无评论

Strategic Mobility Insights: Optimizing Parking and Operational Efficiency through Density Analysis

Strategic Mobility Insights: Optimizing Parking and Operatio...

引用

Intelligent Systems for Cybersecurity (ISCS), International Conference on

作者： Payila Rama Praharsh Meka Venkata Sai Tarun Vanacharla Venkata Satya Priya A Anirudh Reddy Lalithamani N Department of Computer Science and Engineering Amrita School of Computing Coimbatore Amrita Vishwa Vidyapeetham India

ISBN: (数字)9798350375237

ISBN: (纸本)9798350375244

This research introduces a comprehensive approach to optimize parking and operational efficiency by employing density analysis based on entrance and exit camera footage in public spaces, such as malls or educational institutions. The study focuses on vehicle tracking to estimate crowd density within these locations, utilizing image processing techniques to count the number of vehicles entering and exiting the public space. The computed crowd density serves as a pivotal metric for proactive alert systems that trigger interventions when congestion levels are critical, redirecting incoming traffic to alternative parking areas. In addition to real-time density management, the research explores trends in crowd density variations across different days, offering insights for strategic resource planning and operational adjustments. The implemented alert system demonstrates its effectiveness in managing high-density situations, providing a dynamic solution for optimizing parking resources and overall crowd-related resources. This research contributes to the evolution of intelligent urban management systems by presenting a robust methodology that integrates both parking management and crowd density trends, setting the stage for future innovations in resource optimization.

关键词： Space vehicles Measurement Technological innovation Image processing Market research Real-time systems Planning

来源：评论

学校读者我要写书评

暂无评论

Airfoil Self Noise Prediction Using Machine Learning and Explainable AI

Airfoil Self Noise Prediction Using Machine Learning and Exp...

引用

IEEE Recent Advances in Intelligent Computational Systems (RAICS)

作者： Honey Pandey Prateek Pandey Deepa Gupta Department Of Computer Science And Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Bengaluru India

ISBN: (数字)9798350381689

ISBN: (纸本)9798350381696

A major environmental challenge in the aerospace sector is presented by aircraft noise, particularly airfoil noise. Traditional methods for predicting airfoil noise involve complex and computationally intensive numerical simulations. This research explores the use of machine learning to enhance the efficiency and accuracy of airfoil noise prediction. By utilizing extensive datasets from wind tunnel experiments, encompassing a variety of airfoil geometries and flow conditions, supervised learning algorithms are employed to construct a predictive model. Diverse regression models, including random forests, support vector regression, CatBoost, XgBoost, Gradient Boosting and decision trees, are trained on the NACA 0012 airfoil dataset to uncover correlations between airfoil characteristics and noise emissions. Initial findings underscore the potential of machine learning, with Gradient Boosting regression achieving a noteworthy R2 score of 0.96625 and RMSE as 1.2622. This study not only equips engineers with a valuable tool for optimizing airfoil shapes to reduce noise but also establishes the groundwork for real-time noise prediction systems in aircraft operations.

关键词： Machine learning algorithms Accuracy Atmospheric modeling Wind tunnels Wind speed Noise Boosting Prediction algorithms Aircraft Automotive components

来源：评论

学校读者我要写书评

暂无评论

Identifying the Influences Behind the LinkedIn Posts using Topic Modeling and Sentiment Analysis

Identifying the Influences Behind the LinkedIn Posts using T...

引用

Trends in Quantum computing and Emerging Business Technologies (TQCEBT), International Conference on

作者： R. Nagaraj C.R Rohith Adithya Sakalabathula Sri Chakra Teja Deepika T Department of Computer Science and Engineering Amrita School of Computing Coimbatore Amrita Vishwa Vidyapeetham India

ISBN: (数字)9798350384277

ISBN: (纸本)9798350384284

The proliferation of social networking in the modern world has made it a ubiquitous presence in people’s lives. On a daily basis, individuals post and share their opinions, rating products, and engage in business-related activities. Social media platforms play a crucial role in the business field, facilitating the establishment of relationships with prospects and clients. As such, LinkedIn has emerged as the ideal online platform for building trust by sharing success stories, business promotions, and recommendations through posts. This professional website serves as a means of connecting the world’s professionals with the general public. At the same time, many people post opinions and professional content regularly, and only a select few post become influenced by reaching larger community. The factors responsible for this influence remain unknown, prompting us to propose a solution based on topic modeling and sentiment analysis. Our project aims to identify the influences behind LinkedIn posts by examining the role of media content in posts, and by utilizing natural language processing techniques to analyze the underlying aspects of posts which then examined using topic modeling and sentiment analysis to identify subtopics and aspects present in the posts.

关键词： Analytical models Sentiment analysis Quantum computing Social networking (online) Computational modeling Buildings Media

来源：评论

学校读者我要写书评

暂无评论

Cryptographically Secured Data Transmission Over a Network with NetCAT

Cryptographically Secured Data Transmission Over a Network w...

引用

Electronics, computing, Communication and Control Technology (ICECCC), International Conference on

作者： Subhiksha Suresh Rao Sahil Mishra S Akhilesh Kavitha C.R. Department of Computer Science and Engineering Amrita School of Computing Bengaluru Amrita Vishwa Vidyapeetham India

ISBN: (数字)9798350371802

ISBN: (纸本)9798350371819

This study focuses on cryptically secure data trans-mission on a network with NetCAT and emphasizes the improvement of the Advanced Encryption Standard (AES) algorithm to improve data security. It specifically addresses file encryption using the modified AES and uses the flexibility of NetCAT utility for safe transfer. In particular, the deliberate transformation of intercepted data into incomprehensible gibberish emphasizes the robustness of modified AES against potential surveillance and unauthorized access. This document presents an improved and practical approach to improving data protection during trans-mission, especially in the context of encrypted data transmission through a network with NetCAT. Through the discussion of this specific topic, it contributes significantly to the evolving field of cryptography and emphasizes the need for accurate specifications and a clear focus on the treatment of data security challenges.

关键词： Resistance Surveillance Data protection Solids Robustness Encryption Data communication

来源：评论

学校读者我要写书评

暂无评论

Analyzing GNN Models for Community Detection Using Graph Embeddings: A Comparative Study

Analyzing GNN Models for Community Detection Using Graph Emb...

引用

International Conference on computing and Networking Technology (ICCNT)

作者： V V Devesh Kumar S Sreesankar Krishnpriya Dinesan Pranav B Nair L R Deepthi Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Amritapuri India

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

Graphs are effective models for illustrating complex connections in various contexts, including social networks, citation networks, and biological systems. In this study, the performance of Graph Neural Networks(GNN) for two main tasks is being explored: Node classification and Community detection. Community detection on complex networks is an emerging area that helps to understand the underlying structures and functions of interconnected systems across various domains. The structural and semantic information are captured using the various GNN models. This paper uses four GNN models for node classification: GCN, GAT, GraphSAGE, and Deep Graph Infomax. The embeddings of these models are clustered to detect the communities by using spectral clustering, k-means clustering, and the Louvain algorithm. The GNN model’s performance was assessed in terms of computational complexity, accuracy of clustering, and modularity. The results demonstrate that GNN models, particularly GCN, yield competitive performance in community detection tasks on citation networks. The effectiveness of each model varies across different datasets and community detection algorithms.

关键词： Analytical models Social networking (online) Computational modeling Image edge detection Semantics Complex networks Interconnected systems Graph neural networks Detection algorithms Context modeling

来源：评论

学校读者我要写书评

暂无评论

Evaluation of RPL and SDN-WISE in UAV assisted WSN data collection

Evaluation of RPL and SDN-WISE in UAV assisted WSN data coll...

引用

2nd International Conference on computer Vision and Internet of Things (ICCVIoT 2024)

作者： Deepankumar S Rengaraj R Boggarapu Mithil Raj Kumar Gupta Nalinadevi K Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Coimbatore India

ISBN: (数字)9781837242535

This paper evaluates the performance of the Routing Protocol for Low-Power and Lossy Networks (RPL) and the Software-Defined WIreless SEnsor network (SDN-WISE) approach in a IPv6 over Low-Power Wireless Personal Area Net-works (6LoWPAN) network scenario. In this network scenario a mobile sink acting as an Unmanned Aerial Vehicle (UAV) is used for data collection in Wireless Sensor Networks (WSNs). A novel methodology is presented for generating efficient paths for the mobile UAV sink. It involves leveraging the K means clustering algorithm for finding the centroids which can cover the sensors within the transmission range. The Ant Colony Optimization technique is then used for traversing the centroids to solve the Travelling Salesmen problem (TSP). Key performance metrics such as average end-to-end delay, packet delivery ratio and energy consumption are analysed under varying conditions and sensor node densities. The study provides valuable insights into optimising UAV-assisted WSNs for enhanced performance and longevity in real-world applications.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Credit Scoring for Loan Applicants Using Machine Learning Models

Credit Scoring for Loan Applicants Using Machine Learning Mo...

引用

Intelligent Technologies (CONIT), International Conference on

作者： Kaivaram Sivarama Krishna Bommala Deepak Kumar Morumpalli Deekshith Reddy Ch Saketh Manju Venugopalan Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Bengaluru India

ISBN: (数字)9798350349900

ISBN: (纸本)9798350349917

This study presents a comprehensive framework for credit scoring in loan application processes. The research presents a framework that uses data analysis and machine learning techniques to evaluate creditworthiness, in loan applications. By incorporating cutting-edge algorithms like Naive Bayes, SVM, Decision Tree, Multi Layer Perceptron (MLP), and Gradient Booster (GB) the goal is to revolutionize the decision-making process for loan approvals by using analytics. The model utilizes a dataset that includes payment statements enabling a thorough and randomized credit scoring system for each individual applying for a loan. By leveraging machine learning algorithms, the system examines past payment behaviors to extract patterns and information. These findings are then used to generate a credit score that is further classified as good, bad, or moderate. This approach provides an assessment of an applicant’s reliability. To improve the model’s accuracy, feature selection techniques and Synthetic Minority Oversampling Techniques (SMOTE) are utilized to compare models’ effectiveness, in predicting creditworthiness. The integration of data and machine learning not only enhances the efficiency of loan approval processes but also facilitates more informed financial decisions based on data analysis. On all the machine learning models which were performed, SVM performed best among the five models with an F-measure value of 0.86 incorporating feature selection and SMOTE.

关键词： Support vector machines Machine learning algorithms Data analysis Decision making Machine learning Predictive models Feature extraction

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：