Manuscripts

Recent Papers

Research Paper

Artificial Intelligence and Risk Management in Digital Banking Services: Opportunities, Challenges, and Future Perspectives

The rapid growth of digital banking has transformed the financial services sector by enhancing accessibility, efficiency, and customer experience. Simultaneously, the increasing dependence on digital platforms has exposed banks to various risks, including cyber threats, operational failures, fraud, data breaches, and regulatory compliance issues. Artificial Intelligence (AI) has emerged as a significant technological solution for identifying, assessing, and mitigating these risks. This paper examines the role of AI in risk management within digital banking services. The study explores AI-based applications such as fraud detection, predictive analytics, credit risk assessment, anti-money laundering systems, and cybersecurity monitoring. The paper also highlights challenges associated with AI adoption, including algorithmic bias, privacy concerns, regulatory issues, and technological dependence. Based on a review of contemporary literature and industry practices, the study concludes that AI significantly enhances the effectiveness of risk management while requiring appropriate governance frameworks to ensure ethical and secure implementation.

Published by: Mohd Sarim Syed

Author: Mohd Sarim Syed

Paper ID: V12I3-1219

Paper Status: published

Published: June 17, 2026

Full Details
Research Paper

Experimental investigation on Utilization of Recycled PET Fiber in Concrete

This paper presents an experimental investigation on the utilization of recycled Polyethylene Terephthalate (PET) bottle fibers in M35 grade concrete. The increasing generation of plastic waste has become a serious environmental issue due to its non-biodegradable nature and improper disposal methods. The use of recycled PET fibers in concrete offers an effective solution for waste management while enhancing the mechanical properties of concrete. In this study, waste PET bottles were collected, cleaned, and cut into fibers of suitable dimensions before being incorporated into concrete at varying percentages of 0%, 1%, 2%, and 3% by weight of cement. Concrete specimens were prepared and tested to evaluate compressive strength, split tensile strength, and flexural strength after standard curing periods. The experimental results indicated that the inclusion of PET fibers improved the overall performance of concrete by enhancing crack resistance, tensile strength, and flexural behavior. The fibers acted as crack-bridging elements, reducing the propagation of microcracks and improving the ductility of concrete. Among the different mixes, the optimum PET fiber content exhibited the best mechanical performance. The utilization of PET fibers also contributes to sustainable construction practices by reducing plastic waste accumulation and promoting the recycling of non-biodegradable materials. The findings of this study demonstrate that recycled PET fiber reinforced concrete can be considered a viable and eco-friendly construction material. Therefore, the incorporation of PET fibers in concrete not only improves structural performance but also supports environmental sustainability and effective plastic waste management in the construction industry.

Published by: Sanjay Balte, Kanthali Sudhir Bhausaheb, Mule Akash Suresh, Mundhe Prakash Vasant, Rashinkar Vishal Nanasaheb, Rathod Jagdish Nandalal

Author: Sanjay Balte

Paper ID: V12I3-1218

Paper Status: published

Published: June 16, 2026

Full Details
Research Paper

Gesture to Voice: A Real-Time Arabic Sign Language Recognition System for Spoken Saudi Arabic Output

Communication barriers between deaf individuals and the general public remain a persistent challenge in Arabic-speaking communities. This paper presents Gesture to Voice, a real-time Arabic Sign Language (ArSL) recognition system that translates hand gestures into spoken Saudi Arabian audio output. MediaPipe extracts 21 hand landmarks per hand (126 features total), and a Long Short-Term Memory (LSTM) neural network processes temporal sequences of 30 consecutive frames to classify gestures. A two-stage prediction stabilization mechanism combining confidence thresholding and majority voting ensures reliable output. The system achieves a best validation accuracy of 84.26% and reliable real-time performance across three gesture classes. Unlike prior work producing text-only output, Gesture to Voice uniquely delivers spoken SaudiArabianc responses, addressing a critical gap in localized assistive technology.

Published by: Alanoud Saud M. Alnawmasi, Badriya Abaker Mohajir, Jood Mtaleq F. Alenazi, Jumanah S. Almarzooq, Manar Majed N. Alhur, Nouf Fraih A. Alshammari

Author: Alanoud Saud M. Alnawmasi

Paper ID: V12I3-1214

Paper Status: published

Published: June 13, 2026

Full Details
Research Paper

Vehicle Breakdown Assistance Management System

Vehicle breakdown situations often create inconvenience, delays, and safety concerns for drivers. In many traditional cases, assistance is arranged manually through phone calls or local contacts, which may consume time and create communication gaps. This paper presents a Vehicle Breakdown Assistance Management System (VBAMS) developed using the Python Django framework and MySQL database, based directly on the implemented project model. The system provides a centralized platform where customers can submit assistance requests, administrators can manage bookings and drivers, and assigned drivers can update service progress. The project follows Django’s Model-View-Template (MVT) architecture and includes secure authentication, role-based access, driver management, booking records, and request tracking. The developed system improves operational efficiency, organizes service data, and reduces manual coordination. Future scope of the project includes GPS tracking, artificial intelligence based dispatching, mobile application support, and automated notifications.

Published by: Sonia, Er Bablu Jaipal

Author: Sonia

Paper ID: V12I3-1215

Paper Status: published

Published: June 13, 2026

Full Details
Research Paper

Deep Learning Based Non-Invasive Screening of Autism Spectrum Disorder Using Transfer Learning

Autism Spectrum Disorder (ASD) is a complex neurodevelopmental condition characterized by persistent challenges in social communication. Early intervention is paramount; however, traditional diagnostic pathways often take years due to a lack of specialized clinicians. This research proposes an automated screening tool using facial image analysis. By employing the VGG16 architecture via Transfer Learning, we extract high-level spatial features from facial landmarks to identify markers associated with ASD. Our findings indicate that computational models can provide a significant preliminary screening layer, reducing the burden on clinical resources.

Published by: Nisha Sharma, Bablu Jaipal

Author: Nisha Sharma

Paper ID: V12I3-1213

Paper Status: published

Published: June 10, 2026

Full Details
Research Paper

Lane Detection System using Python OpenCV

Lane detection is an important perception module in advanced driver-assistance and autonomous driving because it helps a vehicle interpret road geometry and remain centered within the lane. This paper presents a compact lane detection pipeline developed in Python with OpenCV using classical image-processing techniques. The method processes each video frame in sequence and applies grayscale conversion, Gaussian smoothing, Canny edge detection, a region-of-interest mask, and Probabilistic Hough Transform line extraction. The detected segments are separated into left- and right-lane candidates using slope-based rules, averaged to reduce noise, and drawn on the original frame to create an annotated road view. The system was tested on real driving video captured from a front-facing camera under normal daylight conditions. The results indicate that the approach performs well on straight roads and moderate curves when lane markings are visible, but its robustness decreases under shadows, glare, faded paint, and partial occlusion. Because the pipeline is lightweight, deterministic, and capable of near real-time execution on standard hardware, it is a useful baseline for educational and prototype intelligent transportation systems. The paper also discusses the problem context, design objectives, implementation steps, results, limitations, and future extensions such as adaptive thresholding, temporal tracking, and learning-based lane recognition.

Published by: Yash Bhardwaj

Author: Yash Bhardwaj

Paper ID: V12I3-1211

Paper Status: published

Published: June 9, 2026

Full Details