Integrated Approaches to Computer System Validation Within GxP-Compliant Pharmaceutical Quality Management Systems
Authors:-Aditi Akundi, Dr. Pavithra G, Dr. Swapnil SN

Abstract-:The pharmaceutical industry is heavily regulated due to the direct impact of its products on human health and safety. To ensure compliance and maintain data integrity, regulatory authorities such as the U.S. Food and Drug Administration (FDA), European Medicines Agency (EMA), and others require that computerized systems used in Good Practice (GxP) environments undergo rigorous validation. Computer System Validation (CSV) plays a pivotal role in ensuring that such systems consistently perform according to their intended use and comply with applicable regulations. This paper provides an in-depth conceptual overview of CSV within the framework of pharmaceutical Quality Management Systems (QMS). It explores its regulatory basis, the validation lifecycle, risk-based approaches, common challenges, and industry best practices, while highlighting the significance of CSV in maintaining quality, compliance, and patient safety.

DOI: 10.61137/ijsret.vol.11.issue2.458

Published by: Kajal Tripathi

Artificial Intelligence in Energy Management: A Comprehensive Literature Review on Methods, Applications, and Challenges
Authors:-Jayendra Jadhav, Aashirwad Mehare, Aditya Wandhekar, Sanyukta Pawar, Pranjal Chavan, Vedant Nigade

Abstract-:The mounting pressure for efficient and sustainable energy solutions has driven the adoption of Artificial Intelligence (AI) in contemporary energy systems. This literature review consolidates evidence from more than 20 recent studies on AI-based approaches for renewable energy and smart grid management. It discusses AI methods like machine learning, deep learning, reinforcement learning, and optimization techniques applied in energy forecasting, load management, fault detection, and demand response. The review emphasizes AI’s application in improving energy efficiency, lowering costs, and facilitating decentralized energy systems. It also touches on the most important hardware devices involved, e.g., photovoltaic panels, smart meters, IoT devices, and battery storage systems. Although it has the potential to transform, the use of AI in energy systems is confronted with various challenges such as high infrastructure expenditure, data needs, system integration problems, and regulatory issues. This paper concludes by establishing research gaps and outlining future directions for the complete utilization of AI to achieve a sustainable and intelligent energy ecosystem.

DOI: 10.61137/ijsret.vol.11.issue2.457

Published by: Kajal Tripathi

Fake News Detection Using Natural Language Processing
Authors:-Professor Kirti Randhe, Nameet Vyavahare, Rajkumar Vishwakarma, Sai Kudale

Abstract-:In the digital age, the rapid dispersal of information through social media and online platforms has increased the spread of fake and exaggerated news, posing serious challenges and threats to public trust, societal stability, democratic processes and national security and peace. This research explores the application of Natural Language Processing (NLP) techniques for the automatic detection of fake news, aiming to enhance the reliability of information consumed by the public. By leveraging and applying machine learning and deep learning models in conjunction with NLP methods such as text preprocessing, tokenization, feature extraction, and sentiment analysis, this study investigates effective strategies for distinguishing between factual, genuine and misleading content. Various algorithms, including Support Vector Machines, Random Forest, Naïve Bayes and deep learning approaches like LSTM and BERT, are evaluated using benchmark datasets. The results demonstrate the potential of NLP-driven solutions to accurately classify news articles, highlighting their significance in combating misinformation. This paper contributes to the growing field of automated fake news detection and offers insights into building more trustworthy digital information ecosystems.

DOI: 10.61137/ijsret.vol.11.issue2.456

Published by: Kajal Tripathi

J.A.R.V.I.S: AI ASSISTANT
Authors:-Bhuneshwar Singh Chauhan, Swati Kumari, D Sai Divya Reddy, Dhananjay Sahu, Professor Neha Soni

Abstract-:This paper examines the rapidly evolving field of modern technology, with a particular focus on virtual assistants developed through Python. It shows how it changes these assistants are having on human-computer interactions by using advanced technologies such as Natural Language Processing (NLP) and Artificial Intelligence (AI). The literature review consolidates key research findings on the functions, capabilities, and design strategies of virtual assistants. In the system architecture section, a clear structure is presented for desktop virtual assistants, detailing key components like the user interface, speech recognition modules, dialogue management, and more. The methodology section outlines a structured approach to designing and building such systems. The conclusion emphasizes the significant advancements in virtual assistant technology while also addressing ongoing challenges such as ensuring system stability and safeguarding data security. Ultimately, the paper underscores the importance of continued innovation in this field to fully unlock the potential of virtual assistants in various industries.

DOI: 10.61137/ijsret.vol.11.issue2.455

Published by: Kajal Tripathi

CFD Analysis on Car Rear Spoiler
Authors:-Turlapati Siva Krishna, M. Hari Sai, K. Naresh

Abstract-:The stability of a car refers to its ability to maintain its trajectory and resist external disturbances, such as wind, road irregularities, or sudden maneuvers. Several key factors affect a car’s stability, including its center of gravity, weight distribution, suspension system, tire characteristics, and aerodynamics. A spoiler is an aerodynamic device attached to a vehicle, typically on the rear deck lid or trunk, designed to improve its stability and reduce drag at high speeds. By altering airflow around the vehicle, a spoiler can enhance its overall performance and handling. There are various types of spoilers, including rear spoilers, front spoilers, and side skirts, each serving a specific purpose. The benefits of spoilers include improved stability, reduced drag, and enhanced performance, making them a popular choice for racing cars, high-performance vehicles, and aftermarket accessories.

DOI: 10.61137/ijsret.vol.11.issue2.454

Published by: Kajal Tripathi

Application of Carbon Nanomaterials in Energy Production and Storage
Authors:-Aryan Kuhar

Abstract-:In this modern world the demand for more sustainable energy production and storage solutions has elevated the interest in nanotechnology, in which carbon-based nanomaterials are particularly interesting in improving energy production systems. This review paper explores the application of carbon nanomaterials, including nanomaterials like carbon nanotubes (CNTs), graphene, fullerene etc., in many energy production methods. Their unique properties such as large surface area, high electrical conductivity and high mechanical strength, make these carbon nanomaterials optimal candidates for improving energy storage and generation processes. In energy devices such as lithium-ion batteries, solar cells and fuel cells, these carbon nanomaterials have demonstrated improvement in better charge transport, energy density, catalytic performance and charge/discharge efficiency. These nanomaterials are also developed so there are more cost-effective alternatives to current technology.

DOI: 10.61137/ijsret.vol.11.issue2.453

Published by: Kajal Tripathi

A Supervised Learning Framework for Predicting GSC Antibody Seropositivity in Guillain–Barré Syndrome Using Multivariate Clinical and Demographic Indicators
Authors:-Ms. Sangeetha Raj S, Ayushi Negi, Ekta Kumari, Christina S

Abstract-:This paper proposes a robust supervised learning framework for predicting ganglioside complex (GSC) antibody seropositivity in patients with Guillain–Barré Syndrome (GBS) using multivariate clinical and demographic features. Drawing from a comprehensive dataset encompassing 129 GBS patients, we employed advanced machine learning methods support vector machines, random forests, decision trees, and k-nearest neighbours to predict seropositivity for six key anti-ganglioside antibodies (GM1, GM2, GD1a, GD1b, GT1b, GQ1b). Rigorous feature selection, cross-validation, and class imbalance handling were implemented to ensure robustness. Results show that routine clinical data can deliver accurate antibody seropositivity predictions, supporting GBS management where serological assays are delayed or unavailable.

DOI: 10.61137/ijsret.vol.11.issue2.452

Published by: Kajal Tripathi

Smart Vehicle Accident Detection and Anti-Theft System
Authors:-Shaikh Mubashshir, Mohammad Zafir, Hrutuja Ingole, Professor A. P. Jaware

Abstract-:The rapid advancement of technology has transformed transportation but has also escalated challenges like road accidents and vehicle theft. This paper presents a smart system integrating accident detection and anti-theft mechanisms using piezoelectric sensors, GPS, GSM, and fingerprint verification technologies. The accident detection module employs a piezoelectric sensor to identify crashes or rollovers, instantly transmitting the vehicle’s location to emergency contacts via GSM and GPS modules. The anti-theft system uses fingerprint authentication to ensure only authorized users can operate the vehicle, with real-time tracking and remote immobilization capabilities. This dual-purpose system enhances road safety by reducing emergency response times and strengthens vehicle security against theft. Designed for scalability, the system leverages Arduino as the central microcontroller, offering a cost effective and reliable solution for modern vehicles. This paper details the system’s design, implementation, and potential impact on automotive safety and security.

DOI: 10.61137/ijsret.vol.11.issue2.451

Published by: Kajal Tripathi

A Smart Reverse Vending Machine for Plastic Bottles
Authors:-Assistant Professor V. Srinivas Rao, Narla Sai Kiran, Rajarapu Pavan Jagadeesh, Sanagapalli Madhav, Sarikonda Mahendra Sai, Sariki Appalanaidu

Abstract-:The exponential rise in plastic waste, particularly from single-use PET bottles, presents a critical challenge to environmental sustainability. Conventional recycling approaches are often hindered by inconvenient manual processes, limiting public engagement. To counter this, the proposed Smart Reverse Vending Machine (RVM) offers an automated, user-friendly solution for the collection and preliminary sorting of plastic bottles. The system employs an Arduino Uno microcontroller, an IR sensor, and a load cell with HX711 amplifier to detect, validate, and weigh deposited bottles. In exchange, users receive immediate incentives such as coins, fostering responsible waste disposal habits. Designed with affordability and scalability in mind, this compact system is ideal for installation in high-traffic areas like malls, transport hubs, and educational campuses. The initiative aims to enhance recycling participation through real-time rewards and minimal operational complexity. Potential future enhancements include IoT connectivity, AI-based recognition, and digital rewards, positioning the system as a smart and sustainable waste management solution.

DOI: 10.61137/ijsret.vol.11.issue2.450

Published by: Kajal Tripathi

Sign Language to Voice Translator
Authors:-B. Sai Praneetha, Dyanesh R, M. Praniksha, Sanjai R J, Professor Dr. Ajay Kumar Singh

Abstract-:One area of assistive technology that is gaining popularity is its capacity to facilitate communication between people with hearing impairments and the general public. This research introduces a real-time sign language detection system that uses a single webcam to recognize the alphabet in American Sign Language (ASL) and interpret numerical gestures. Based on hand landmarks recorded by MediaPipe, the system recognizes ASL alphabets with high accuracy and recognizes digits from 1 to 10 using deep learning, computer vision, and language processing algorithms. The suggested solution combines OpenCV and MediaPipe for landmark tracking, pyttsx3 for speech feedback, and a user-friendly graphical user interface created using Tkinter. TensorFlow is used to train the alphabet identification model, while landmark distance computations and geometric logic is used to distinguish numerical movements. Because this hybrid approach guarantees real-time speed and usability, the solution is feasible for applications that are focused on accessibility, education, and assistive technology.

DOI: 10.61137/ijsret.vol.11.issue2.449

Published by: Kajal Tripathi