Manuscripts

Recent Papers

Research Paper

Detecting Money Laundering through Artificial Intelligence: A Commercial and Predictive Perspective

Money laundering—the concealment and integration of illicit proceeds into the formal financial system—undermines the trust and fairness of global financial systems, presenting enormous challenges to investors, regulators, and commercial enterprises. Traditional detection methods based on rigid rule-based systems and manual auditing have proven insufficient in combating increasingly sophisticated laundering schemes. This paper demonstrates how data science, commercial domain knowledge, and machine learning—specifically, decision tree models—can be synthesized to enhance real-time detection of suspicious financial activities. Through a comprehensive workflow involving synthetic transaction data generation, exploratory data analysis, and predictive modeling, critical patterns such as transaction amount, timing, customer risk profiles, and transaction type emerge as powerful indicators of money laundering behavior. Bar diagrams and visual analytics visually support the findings, illustrating feature importance rankings and identifying high-risk transaction segments. The commercial impact of this approach includes proactive regulatory compliance, significant workload reduction for compliance analysts, and minimal customer friction through reduced false positives. This research highlights how student-level expertise combined with interpretable AI tools can effectively bridge the gap between traditional commerce education and modern financial technology compliance solutions. The decision tree model achieved 99.93% testing accuracy with a precision and recall of 99.82% each, demonstrating the viability of automated AML detection systems in real-world banking environments.

Published by: Nimit Jain, Kaashvi Soni

Author: Nimit Jain

Paper ID: V11I5-1212

Paper Status: published

Published: October 25, 2025

Full Details
Research Paper

Margins and Gateways: The Economic Struggles of Emerging Fine Artists in India’s Contemporary Art Landscape

This paper examines the key challenges faced by emerging artists in India, including limited access to markets, professional networks, and financial stability. It explores how gatekeeping in galleries, intense competition for exposure, and the scarcity of grants and patrons restrict opportunities for new talent. The instability of freelance and teaching work further compounds these difficulties. Through analysis of current conditions and available support systems, the paper highlights the need for more inclusive, transparent, and decentralized frameworks to support emerging artists and ensure a more equitable future for India’s creative community.

Published by: Kaavya Mittal

Author: Kaavya Mittal

Paper ID: V11I5-1209

Paper Status: published

Published: October 24, 2025

Full Details
Research Paper

Text Mining and Sentiment Analysis of Major Religious and Philosophical Texts- Applying Natural Language Processing to Uncover Linguistic Patterns, Thematic Elements, and Emotional Tone

This research uses natural language processing (NLP) methodologies to quantitatively analyze key religious and philosophical texts by identifying language trends, themes, and sentiment. Using a combination of text-mining techniques, topic modeling, and sentiment/emotion analysis, we evaluate how ideas, values, and emotions are conveyed within religious and philosophical traditions, including the Bible, Quran, Bhagavad Gita, and classic philosophy texts. The research analyzes publicly available text corpora and translations to quantify word counts, identify topic trends, and analyze emotional trajectories across chapters and verses. The comparative analysis reveals differences in thematic focus, emotional tone, and rhetorical style across religious and philosophical texts, and across translations of the same texts. The study's aim is to show the efficacy of computational methods as a complement to traditional textual scholarship by developing new ways to analyze form, sentiment, and meaning of primary texts. The interdisciplinary study and research also aim to contribute to emerging dialogue between the fields of digital humanities, linguistics, and religious studies to provide frameworks for large-scale, digital, and data-based analysis of sacred texts and literature.

Published by: Sohan Sai Yerragunta

Author: Sohan Sai Yerragunta

Paper ID: V11I5-1205

Paper Status: published

Published: October 24, 2025

Full Details
Research Paper

QiML Framework for Anomaly Detection in NFV-Clouds

Network Function Virtualization (NFV) transforms traditional network infrastructures by replacing hardware components with software-based Virtual Network Functions (VNFs). While NFV improves flexibility, scalability, and cost efficiency, it also introduces significant cybersecurity challenges due to vulnerabilities in virtualization layers, orchestration tools, and multi-tenant environments. Conventional intrusion detection systems and classical machine learning (ML) models such as Support Vector Machines, Random Forests, and traditional neural networks often fail to cope with evolving threats, leading to high false positives, computational overhead, and limited effectiveness against zero-day attacks. To address these limitations, this paper proposes a Quantum-Inspired Machine Learning (QiML) framework specifically designed for anomaly detection in NFV-cloud security. The framework integrates multiple modules: Quantum-inspired Feature Encoding (QiFE) for compact data representation, a Quantum-inspired Evolutionary Algorithm (QiEA) for feature selection, Quantum-inspired Neural Networks (QiNN) for accurate anomaly detection, an Adaptive Quantum-Inspired Cybersecurity Strategy for real-time mitigation, and Quantum-inspired Explainable AI (QiXAI) for interpretability. Experimental evaluations using CIC-IDS2018, UNSW-NB15, and NFV-specific synthetic datasets demonstrate the superior performance of the proposed framework. The QiEA + QiNN model achieved an accuracy of 98.20%, precision of 97.70%, recall of 97.40%, and F1-score of 97.55% on CIC-IDS2018, outperforming classical ML baselines. Furthermore, the framework reduced feature dimensionality and training time, enhancing efficiency for real-world NFV-cloud deployments. Overall, the QiML framework demonstrates strong potential for advancing secure, adaptive, and interpretable anomaly detection in NFV-cloud environments.

Published by: Mr M. Jayababu, Dr J. Kejiya Rani

Author: Mr M. Jayababu

Paper ID: V11I5-1206

Paper Status: published

Published: October 24, 2025

Full Details
Survey Report

IOT-Based Drainage Block Detection with Control-Based Drainage Unit Cleaner

This Paper presents an IoT-based drainage block detection and cleaning system designed to address frequent drainage blockages that cause waterlogging, foul odors, and health risks. The system uses sensors such as ultrasonic, flow, and gas detectors to monitor water levels and detect blockages in real time. Data is transmitted to a control room dashboard via IoT modules (ESP8266/ESP32), where alerts are generated when abnormal conditions occur. A mechanized cleaning unit, controlled remotely from the control room, removes solid waste using motorized arms or brushes, reducing manual intervention and ensuring worker safety. The proposed system provides an efficient, low-cost, and smart solution for real-time monitoring and automated drainage maintenance, contributing to safer and cleaner urban environments.

Published by: Kshama N Pendse, Shrinivas R Vaidya, Preetam R Joshi, Prof G M Patil

Author: Kshama N Pendse

Paper ID: V11I5-1203

Paper Status: published

Published: October 23, 2025

Full Details
Research Paper

Explainable Deep Learning for Satellite-Based Natural Disaster Detection and Prediction

Over Earth’s 4.54 billion-year history, natural disasters have reshaped its topography countless times. Earthquakes, storms, floods, and droughts are among the most destructive and unpredictable natural disasters. However, satellite data combined with machine learning algorithms now offer new ways to detect early warning signs of these disasters and mitigate their effects. By leveraging Geographic Information System (GIS) data, NASA’s Global Precipitation Measurement (GPM), and other satellite technologies, researchers can analyze massive geospatial datasets to identify subtle patterns imperceptible to humans. This paper explores the role of machine learning and satellite data in predicting natural disasters. It highlights the technological advancements that could significantly reduce the human and environmental toll of these events.

Published by: Hruday Shreyas Rachapudi

Author: Hruday Shreyas Rachapudi

Paper ID: V11I5-1202

Paper Status: published

Published: October 22, 2025

Full Details