6.Conference Paper (07)

Permanent URI for this collectionhttps://dspace.psgrkcw.com/handle/123456789/5388

Browse

Now showing 1 - 7 of 7

AUTHOR-CENTRIC PATTERN DETECTION IN SCOPUS CITATION NETWORK VIA COMMUNITY STRUCTURES (Conference Paper)
(Springer Science and Business Media Deutschland GmbH, 2025-01-24) Kiruthika R; Radha N
Analyzing citation networks provides effective utilization of research such as identifying domain-specific research influencers, encouraging the growth of collaboration within various scientific domains: Discover the essential trending topics to promote scholarly development. Performing Citation network analysis and bibliometric analysis on Scopus as a complex interconnected network dataset provides an in-depth knowledge about network analysis, structures, and Community detection based on their citation patterns. Citation network analysis involves studying the relationships, interconnections, and patterns among scientific publications through references. The importance of community detection in the Scopus network is to find hidden intellectual connections, interdisciplinary relationships, and research trends. The research objectives of this work focus on using Python-based methodologies to analyze the citation patterns among authors in the Scopus citation network. The key findings are to analyze the citation patterns of top authors, top 10 solo contributing authors, and authorship patterns from the Scopus network. The main contribution of this study is to understand evolving research trends and the importance of community detection in academic fields. This study employs the Louvain approach, which identifies eight communities from the Scopus citation network. The goal is to discover communities within the academic Scopus data through bibliometric and network analysis, with the aim of enhancing research publication in different fields.
ANALYZING THE CITATION NETWORKS USING COMMUNITY DETECTION APPROACHES : A REVIEW (Conference Paper)
(Springer Science and Business Media Deutschland GmbH, 2025-01-28) Kiruthika R; Radha N
Community detection (CD) in a citation network is necessary for detecting the relationships and patterns between scientific articles which results to discover the knowledge and a better understanding of significant research works. Citation network analysis is a field of research in which it demonstrates how the academic articles and their citations are interrelated, most influenced and illustrating the trends of research. CD is an important element for studying citation networks and it provides a way to understand the relationships between different elements of the network. The primary goal of CD in citation networks is to identify groups of closely related publications that have common topics or subjects. This may lead to a better understanding of the topic. The goal of this study is to find the communities based on their citation patterns of linked sources in citation networks to understand the implicit structure and connections between the academic papers using different CD algorithms.
A FRAMEWORK FOR DETECTING AND EVICTING MALICIOUS NODES IN VEHICULAR NETWORKS SESSION HIJACKING ATTACK (Conference Paper)
(American Institute of Physics, 2025-02-05) Jeevitha R.; Sudha Bhuvaneswari N
Vehicular Ad-hoc Networks (VANET) concentrate on safety driving, driving effectiveness and infotainment in road networks. They have a lot of promise because they can make driving safer by exchanging information from sensors and increasing road awareness. Every vehicle in the vehicular network is considered a node. Users can receive a variety of services divided into categories of security and convenience. Security, privacy, and message transfer are the important issues in vehicular networks. Important parameters for VANET authentication are authentication speed and privacy protection. Vehicles connect wirelessly with one another to share data and information. This information exchange is subject to a variety of threats. Before VANETs can be deployed on a broad basis, a few significant issues must be resolved. Security and privacy issues are unquestionably the most pressing issues that must be addressed. The issue of malicious nodes and their impact on the network is one of several difficulties that must be tackled with VANETs. This paper focuses on the framework for detection and eviction of misbehaving nodes in Session Hijacking Attack.
A ROBUST PROTOCOL DESIGN TO PERFORM DATA COMMUNICATION OVER WIRELESS SENSOR NETWORKS WITH ENHANCED PRIVACY PRESERVING PRINCIPLES (Conference Paper)
(Institute of Electrical and Electronics Engineers Inc., 2025-02-20) Sathyavani, Bandela; Kumar Yadav, Rakesh; John Shiny J; Revathi R; Bulakh, Ashish Kumar; Jain, Shilpa
The growth of wireless sensor networks has transformed all automation and industrial systems. Nonetheless, guaranteeing safe and privacy-preserving connectivity in sensor networks continues to be a difficult task. Current authentication and routing techniques frequently jeopardize privacy, entail significant design intricacy, also vulnerable to malware assaults. To mitigate these restrictions, we present an innovative secure protocol, the Asymmetric Cryptography-based Modified Cuckoo Search Optimization Protocol (MCuSO) for wireless sensor networks. Our proposed technique impacts asymmetric credentials with belief supervision for the privacy preservation of WSN data. This method attains an equilibrium in the middle of security and efficiency. Through comprehensive simulations utilizing the MATLAB platform, we illustrate that MCuSO attains an average network throughput of 94% and a network residual energy of 89%, in comparison to leading other algorithms. Moreover, the protocol efficiently reduces malware attacks. These findings underscore MCuSO as a viable outcome of resource limited WSN devices, providing an advantageous equilibrium of information security, data integrity and data efficacy.
EXPLORATION OF DEEP GENERATIVE MODELS FOR ADDRESSING DATA IMBALANCE IN COMPUTER VISION (Conference Paper)
(Springer Science and Business Media Deutschland GmbH, 2025-02-25) Priyadharshini A; Karpagavalli S
Computer vision tasks primarily depend on image data collection, preprocessing of the images, and the feature extraction steps to accomplish the task. When the collected images count is highly imbalanced within a category or between multiple categories involved, the anticipated tasks cannot be achieved. Data imbalance is a communal tricky problem that occurs in acquiring image data collection in specific complex real-world scenarios such as medical diagnosis, fraud detection, manufacturing defect detection, object detection, biological research etc., are inevitable. Several traditional methods for class imbalance are available but more advanced data generation models show promising results. The effectiveness of the computer vision algorithms has an inverse relationship to the quality and quantity of the dataset. In recent years, data generation models like Generative Adversarial Network, Variational Autoencoders, have gained enormous attention from researchers across domains, due to their potential for learning to generate images and their effectiveness in restoring balance in imbalanced datasets. They not only enhance the dataset volume but also contribute to the generalization and robustness of the machine learning algorithms. Moreover, data generation models play a vital role in improving classification accuracy, object detection and semantic segmentation tasks in deep learning. The survey is done with an intention to deliver a comprehensive study of data generation models, their learning representations from data, and their efficiency to address various challenges related to dataset quality, size and diversity.
STUDY ON MACHINE LEARNING AND DEEP LEARNING FOR FAKE NEWS DETECTION (FND) IN SOCIAL MEDIA (Conference Paper)
(Springer Science and Business Media Deutschland GmbH, 2025-02-25) Padmavathy L.; Radha N
Due to the risks associated with fake news, gathering fake information through social networks is difficult. As a result, it is now extremely difficult to evaluate fake news so that the producers can verify it through data processing media without misleading the public. There is a need for an automated technique for the detection because the news’s technical quality is in consideration. Studies currently in existence generally concentrate on using information extracted from the news content. This review’s objective is to use machine learning and deep learning techniques to clearly discuss FND on social media. (1) FND in social media by machine learning and (2) FND in social media by deep learning in data mining are the two main headings in this paper review. Lastly, the finest FND for effective results is deep learning. A Deep Neural Network (DNN) used by the best hyper-parameters has been introduced to categorize news and social context separately. FND dataset from BuzzFeed and PolitiFact by Kaggle repository has been used to validate the effectiveness of the proposed approach. Precision, recall, F-measure, and accuracy are some of the parameters applied to test the validity of the proposed model.
AI-ENHANCED LITERARY ANALYSIS: EXPLORING MACHINE LEARNING TECHNIQUES FOR UNDERSTANDING ENGLISH LITERARY TEXTS (Conference Paper)
(Institute of Electrical and Electronics Engineers Inc., 2025-04-02) Rajlakshmi P.V; Bharathi, V.R.Yasu; Murugavel S; Priyadharshini K; Raja, Sushmitha; Victoria, T. Irwin
Translating and analyzing literary works in English literary texts, or the other way around, is known as cross-language research in English literature. This multifaceted task involves several elements, such as literary comprehension, cultural adaption, and linguistics conversion. People from a variety of language origins may study and enjoy the depth of English literature by using cross-language examinationto make literary texts initially published in English more widely available. This study presents a novel artificial intelligence (AI) paradigm for examining contemporary English literature poetries, which aligns with the worldwide Sustainable Growth Objectives and interdisciplinary methods fusing AI and sustainability. It goes beyond conventional subjective evaluations by using feature extraction and machine-learning methods to categorize poetry. The system's accuracy and generalization will be improved by extending its application to a wider range of literary forms and approaches. Furthermore, initiatives will concentrate on equitably implementing AI tools to provide access to high-quality learning. This study sheds light on the way AI might improve poetry instruction and support environmental objectives. It paves the way for significant advancements in electronic literature poetry and academic innovation by resolving the noted drawbacks and incorporating the approach into learning environments.