Manuscripts

Recent Papers

Research Paper

Autonomous AI Agents for Real-Time Financial Transaction Monitoring and Anomaly Resolution Using Multi-Agent Reinforcement Learning and Explainable Causal Inference

Real-time financial fraud detection systems face significant challenges from adversaries' continually evolving attack strategies. Traditional static classifiers fail to adapt to these changes and often lack interpretability, leading to false positives and missed anomalies. This paper proposes a novel framework combining Multi-Agent Reinforcement Learning (MARL) with Explainable Causal Inference for transaction anomaly detection and resolution. A defender agent learns to identify and intercept fraud in an adversarial environment where an attacker agent simulates fraudulent behaviors. The agents interact within a stochastic game setting and are trained using a centralized critic and decentralized policies. A causal inference module constructs a directed acyclic graph over transaction features to enhance interpretability and applies do-calculus and counterfactual reasoning to explain flagged transactions. We implement a scalable, real-time deployment architecture and evaluate the system using simulated and real transaction data. Results demonstrate that our MARL-based agent outperforms static classifiers in adaptability and recall, while the causal module reduces false positives and provides transparent justifications for fraud decisions. This combination of adaptability and explainability makes the system highly suitable for practical deployment in financial institutions..

Published by: Akash Vijayrao Chaudhari, Pallavi Ashokrao Charate

Author: Akash Vijayrao Chaudhari

Paper ID: V11I2-1252

Paper Status: published

Published: April 18, 2025

Full Details
Research Paper

Utilization of Sugercane Bagasse Ash in Concert (SBA)

Sugarcane bagasse ash (SCBA) is an agro-industrial byproduct generated from sugarcane bagasse combustion in sugar mills. Due to its pozzolanic properties, SCBA can partially replace cement in concrete, enhancing sustainability and reducing environmental impact. This study explores the potential benefits of incorporating SCBA in concrete mixtures, focusing on its effects on mechanical properties, durability, and workability. Experimental results indicate that SCBA improves compressive strength, reduces permeability, and enhances resistance to chemical attacks when used in optimal proportions. Utilizing SCBA in concrete production minimizes industrial waste and contributes to cost-effective and eco-friendly construction practices.

Published by: Druv Ratndeep Aru, Karan Raju Ingle, Ganesh Gautam Gaikwad, Sujal Sunil Kamble, Chaitali Bagul

Author: Druv Ratndeep Aru

Paper ID: V11I2-1253

Paper Status: published

Published: April 18, 2025

Full Details
Research Paper

ARIA: An Intelligent Voice-Enabled Virtual Assistant for Desktop Automation and Conversation

To increase desktop productivity through natural language interaction, this research paper, Aria, introduces a Virtual Virtual Personal Assistant (VPA), built in Python. Application controls (memo blocks, calculators, etc.), webbrows, language typing, email, weather invocations, and natural conversations with DialOgpt conversation models are just some of the many tasks that ARIA can do. To interpret, create, and automate tasks on the user's computer, the assistant uses a variety of Python libraries, such as Speech_Recognition, Pyttsx3, Pyautogui, and Trans. Easy-to adjust modular architecture allows users to improve their skills according to their special needs. Integration of language-based automation into smartphones and intelligent devices has been passed considerably thanks to the efforts of established virtual assistants, providing Google Assistant, Siri, Siri, Alexa, Alexa and Cortana. The system and its capabilities rely primarily on a cloud-based ecosystem. Similarly, several open source initiatives, such as desktop-based Jarvis Clones and Mycroft AI, aim to introduce AI assistants to HR computers, but often only limited offline capabilities, are born on a specific platform and require conversational skills. Aria overcomes these limitations by providing a fully adjustable and conscious desktop assistant through privacy. Data security and user control are guaranteed by offline and online operations, support for customer-specific commands, and independence from local task cloud storage. These are open-source libraries, allowing developers and researchers to change or extend functionality at will. Aria is a convenient and clever way to improve interactions between humans and computers in everyday arithmetic environments. Thanks to the integration of conversation AI, you can respond directly to commands and have contextual conversations.

Published by: Aniket Supe, Amey Waikar, Aditya Tripathi, Dr. Shudhodhan Bokefode

Author: Aniket Supe

Paper ID: V11I2-1227

Paper Status: published

Published: April 17, 2025

Full Details
Research Paper

The Israel-Palestine Conflict: A Legal and Geopolitical Overview

The Israel-Palestine conflict is one of the most intractable and controversial geopolitical disputes in modern history. Rooted in colonial legacies, competing nationalist movements, and overlapping religious claims, it continues to generate widespread humanitarian, legal, and political implications across the globe. This paper seeks to provide a brief but comprehensive overview of the conflict by addressing its historical evolution, major flashpoints, key legal controversies, and contemporary developments—including the 2023–24 Israel-Gaza war, the South Africa v. Israel genocide case before the ICJ, and the regional reverberations involving Iran, Hezbollah, and major global powers.

Published by: Siddharth Dua

Author: Siddharth Dua

Paper ID: V11I2-1248

Paper Status: published

Published: April 17, 2025

Full Details
Review Paper

A Review On Alzheimer’s Disease

Alzheimer's disease (AD) is a progressive neurodegenerative disorder marked by a gradual decline in cognitive function, which affects memory, thinking, and reasoning abilities. As the disease advances, individuals experience worsening impairments in daily activities and exhibit behavioral changes. This condition is the most common cause of dementia, with a significant impact on quality of life for both patients and caregivers. Alzheimer's disease (AD) is the most common form of both pre-senile and senile dementia, affecting about 5% of men and 6% of women over the age of 60 worldwide, according to the World Health Organization (WHO). The disease typically begins with subtle memory failure, which progressively worsens and can become debilitating. Current treatments offer minimal impact, including acetylcholinesterase inhibitors (rivastigmine, galantamine, donepezil) and the NMDA receptor antagonist memantine. While these drugs can slow disease progression and relieve symptoms, they do not cure or prevent the disease's onset. Although the neuropathological features of AD are known, the exact mechanisms behind the disease remain unclear, which contributes to the lack of effective treatments. However, recent advances in understanding AD's pathophysiology have led to new therapeutic targets that may directly address the underlying disease process. This article discusses these recent developments in AD research and how they could potentially improve disease management and reduce care costs. It highlights the importance of advancing knowledge in this area for better treatment outcomes..

Published by: Munshi Shaikh Rahat, Maniyar Hassan, Surwase Mohini, Bagwan Wasim, Kasture Pranav, Sustarphod Vijay, Budge Ganesh, Chandel Adityasingh

Author: Munshi Shaikh Rahat

Paper ID: V11I2-1200

Paper Status: published

Published: April 16, 2025

Full Details
Research Paper

SynapseEd-Systematic LLM Neural Application for Personalized Educational Development

Education is evolving, yet traditional learning models struggle to adapt to individual student needs. Synapseed is an AI-driven, innovative learning system that personalizes education through Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), and multi-agent AI frameworks. It dynamically tailors learning paths, providing real-time AI-driven content, interactive explanations, and coding assistance across various programming languages. The system integrates vector databases, conversational memory models, and CrewAl-powered multi-agent systems to enhance knowledge retrieval from PDFs, YouTube transcripts, and structured academic resources. Additionally, Code Synapse offers multi-language coding support with syntax-aware responses. The platform is scalable and suitable for K-12, higher education, and professional training. A key innovation of SynapseEd is its efficient memory utilization and computational optimization. Unlike traditional LLM-based educational models that require high-end GPUs and large-scale infrastructure, SynapseEd achieves similar functionality on a non-GPU system with just 8GB of RAM. Leveraging quantization (4-bit QLoRA) and lightweight fine-tuning techniques demonstrates that LL.M-powered educational platforms can be built within limited hardware constraints, making AI-driven learning more accessible and deployable across diverse environments.

Published by: Vinmay Vidyadhar Tondle, Priyanka Dhulchand Kapade, Rushikesh Jitendra Bobale, Dr. Geetanjali Vivek Kale

Author: Vinmay Vidyadhar Tondle

Paper ID: V11I2-1198

Paper Status: published

Published: April 16, 2025

Full Details
Request a Call
If someone in your research area is available then we will connect you both or our counsellor will get in touch with you.

    [honeypot honeypot-378]

    X
    Journal's Support Form
    For any query, please fill up the short form below. Try to explain your query in detail so that our counsellor can guide you. All fields are mandatory.

      X
       Enquiry Form
      Contact Board Member

        Member Name

        [honeypot honeypot-527]

        X
        Contact Editorial Board

          X

            [honeypot honeypot-310]

            X