Mathematics, Discrete Mathematics and Combinatorics, Logic
11
Scopus Publications
Scopus Publications
Detection of Fraudulant Transaction Over Credit Card Using Ensemble Learning Ekant Ratanlal Tekam, Afrin Sheikh, Satish D. Kale, Anant Kaulage, Yuvraj S. Suryavanshi, A. S. Sasipriya 2026 IEEE 3rd International Conference on Emerging Trends in Engineering and Medical Sciences Icetems 2025, 2026 The tremendous use of credit card payment that affect to increase in credit card frauds and posing serious risks to financial institutions and customers. Traditional fraud detection methods often struggle with the highly imbalanced nature of transaction data, where fraudulent cases are rare. This paper proposed ensemble learning-based approach to enhance the fraud detection performance over the credit card transactions. The model combines multiple machine learning classifiers such as Random Forest, AdaBoost, K-Nearest Neighbors, and a Deep Neural Network. A publicly available credit card transaction dataset was used, and class imbalance was addressed using SMOTE. The proposed model obtained the accuracy score of 99.94% without SMOTE and improved recall of 87.75 % with SMOTE shows the effectiveness in identifying fraudulent transactions while minimizing false positives. The final outcome of proposed ensemble model shows that when balancing the fraudulent transactions dataset significantly improve the fraud detection performance in real-world financial systems.
Energy of Fuzzy, Intuitionistic Fuzzy, and Neutrosophic Graphs in Decision Making-A Literature Review Sasipriya Sasipriya, ,, Hemant Kumar International Journal of Neutrosophic Science, 2025 This review of the literature delves into the complex interplay between energy measures and decision-making processes in the domains of fuzzy graphs, intuitionistic fuzzy graphs, and neutrosophic graphs. In graph theory, energy is a key quantity that is used to measure structural properties and evaluate decision model dynamics. The research methodically examines the theoretical underpinnings, computational techniques, and practical applications of energy measures in contexts involving decision-making, considering the special features brought forth by fuzzy, intuitionistic fuzzy, and neutrosophic graph models. This review attempts to provide a thorough understanding for researchers and practitioners looking to use energy measures for efficient decision support in the setting of uncertainty contained within these specific graph topologies by synthesizing prior research.
Leveraging Statistical Techniques for Risk Analysis in Mega Transportation Projects: A Systematic Review of Alternative Assessments 16th International Conference on Advances in Computing Control and Telecommunication Technologies Act 2025, 2025
Harmonious Labelling of Some Graphs and Social Network Analysis Through Graph Theory and Artificial Intelligence A. Anto Cathrin Aanisha, R. Manoharan, A. S. Sasipriya, Shraddha Gendlal Vaidya, S. Vijayalekshmi 2025 3rd Dmiher International Conference on Artificial Intelligence in Healthcare Education and Industry Idicaihei 2025, 2025 This work discusses harmonious labeling of different graphs such as H<inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">n</inf> graph, Lilly graph, Triangular book graph, Bull graph, square of path graph. This work further discusses the application of graph theory to model social networks and how Artificial Intelligence contributes to the improvement of users' safety and experience. The resulting labeling suggested establishes that all graphs in question are harmonious and contributes useful information for network modeling and AI integration. Graph theory has many applications.
Contra Harmonic Mean Labeling of Some Graphs and Python-Based Continuous-Time Neural Networks for Solving the Travelling Salesman Problem in Artificial Intelligence A.Anto Cathrin Aanisha, R. Manoharan, A. S. Sasipriya, S. Vijayalekshmi, Ekant Ratanlal Tekam 2025 3rd Dmiher International Conference on Artificial Intelligence in Healthcare Education and Industry Idicaihei 2025, 2025 In this paper, we prove Contra Harmonic Mean Labeling for some star related graphs such as <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\mathrm{K}_{1, \mathrm{n}}, S(\mathrm{K}_{1, \mathrm{n}}), \mathrm{B}_{\mathrm{n}, \mathrm{n}}, \mathrm{S}(\mathrm{B}_{\mathrm{n}, \mathrm{n}}), \mathrm{K}_{\mathrm{1, n}} \odot \mathrm{K}_{\mathrm{1}}, \mathrm{C}_{\mathrm{n}} \oplus \mathrm{K}_{\mathrm{1, n}}, \mathrm{P}_{\mathrm{n}} \oplus \mathrm{K}_{\mathrm{1, n}}$</tex>. Furthermore, we demonstrate how a Continuous-Time Neural Network (CTNN) can be applied to solve the Travelling Salesman Problem (TSP) by dynamically updating neuron states over time. A Python implementation is provided to demonstrate how the network generates an efficient tour based on city distances. Throughout this paper, we refer to Contra Harmonic Mean labeling as CHM labeling and the corresponding graph as a CHM graph. The study integrates discrete mathematics and artificial intelligence through bridging CHM labeling of graphs and continuous-time neural networks for optimization problem solving such as the TSP. The two-pronged contribution demonstrates both theoretical advancement and computational implementation.
Automating Web Penetration Testing and Vulnerability Scanning 16th International Conference on Advances in Computing Control and Telecommunication Technologies Act 2025, 2025
Recognizing the Stages of Depression and Optimizing through Guided Imagery 16th International Conference on Advances in Computing Control and Telecommunication Technologies Act 2025, 2025
Personalized Stock Market Prediction using Dynamic Risk Profiling 16th International Conference on Advances in Computing Control and Telecommunication Technologies Act 2025, 2025
Software-Defined Networking (SDN): A Comprehensive Survey Trishul Dhale, Pradnyawant M. Gote, Utkarsha Pacharney, Praveen Kumar, Ujwalla H. Gawande, Sasipriya A. S 2025 3rd Dmiher International Conference on Artificial Intelligence in Healthcare Education and Industry Idicaihei 2025, 2025 Software-Defined Networking (SDN) is that very new technology that separates the control and data planes to change the entire network structure. Its centralization of programming of the network causes the automation to lead to a better detection of the network. The contemporary survey thoroughly examined the SDN technology and its architecture. It begins with presenting the controller, APIs, and interfaces as the architectural components along with their brief description. After that, it positions SDN next to legacy networks and talks about various features like configuration, scaling, and fault management, to name a few. Furthermore, the authors present several SDN applications from multiple sectors including data centers, WAN, enterprise networks, security systems, and even 5G/IoT infrastructure. Among the various issues that the survey brings to light, the most pressing ones are the need to scale, secure, standardize and integrate with the legacy systems, coupled with the recent trends like intent-based networking, edge computing and the shift towards zero-touch networks.
Single-Valued Neutrosophic Graphs for Energy Analysis of Various Power Plants A.S. Sasipriya 2024 IEEE 2nd International Conference on Emerging Trends in Engineering and Medical Sciences Icetems 2024, 2024 The paper presents an innovative approach to energy analysis in power plants using single-valued neutrosophic graphs (SVNG). It begins by establishing the relevance of graph theory in modeling complex systems and introduces the concept of graph energy within the neutrosophic set framework, which is particularly useful for handling indeterminate and inconsistent information. The study applies this methodology to evaluate and compare four types of power plants by considering its interdependency factors such as location, water availability, cost, and fuel type, the research models the degree of truth, indeterminacy, and falsity for each power plant using SVNG. MATLAB is used to analyze the energy of these graphs, to find the most suitable option based on the energy score function. This research offers a novel decision-making tool for the energy sector, demonstrating the effectiveness of neutrosophic graphs in managing the uncertainties inherent in power plant selection and energy analysis.
