International Journal of Engineering Research and Sustainable Technologies (IJERST)

Editorial Message

Dr.V.Ramesh Babu — Tue, 25 Jun 2024 00:00:00 +0000

Message from Editorial Desk	25^th June 2024
Message from Editorial Desk

Dear Readers, Researchers, and Contributors,

We are pleased to present the latest issue of the International Journal of Engineering Research and Sustainable Technologies (IJERST), Volume 2, No. 2, 2024. This edition showcases cutting-edge research and innovative contributions in the field of engineering and sustainable technologies from scholars across the globe. We continue our mission of fostering knowledge-sharing and interdisciplinary dialogue to advance sustainable solutions for engineering challenges in a rapidly evolving world.

Our journal's commitment to high standards of quality and academic integrity remains steadfast. In this regard, I am excited to inform you that we are making significant progress toward obtaining DOI (Digital Object Identifier) numbers for all our published articles. The DOI integration will not only enhance the visibility of the research work published in IJERST but also provide greater accessibility, reliability, and citation indexing for our contributors.

In addition to these developments, we are actively pursuing inclusion in UGC-CARE (Consortium for Academic and Research Ethics), ensuring our journal's alignment with the standards required for quality research publications. We understand the importance of this recognition for our contributors and readers and are dedicated to achieving this milestone in the near future.

Our team is also planning several initiatives aimed at enhancing the scope and reach of the journal, including webinars, special issues on trending topics, and collaborations with leading academic institutions. These activities are part of our ongoing effort to ensure that IJERST continues to serve as a valuable resource for researchers, engineers, and professionals working towards sustainable development.

We sincerely thank all the authors, reviewers, and editorial board members for their contributions and dedication. Together, we are building a platform that not only highlights innovative research but also supports the global engineering community in its pursuit of sustainability.

Thank you for your continued support, and we look forward to your valuable submissions and feedback for future issues.

Warm regards,

On behalf of Editorial Team

Dr.V.RameshBabu

Managing Editor

Dean-University Journal , Dr.M.G.R. Educational and Research Institute

Chennai,Tamilnadu,India

dean-univ.journals@drmgrdu.ac.in / ijerst@drmgrjournals.org

ENHANCING CYBERSECURITY THREAT DETECTION: A COMPARATIVE STUDY OF DEEP LEARNING AND MACHINE LEARNING

Cinthiya Joy Godly — Tue, 25 Jun 2024 00:00:00 +0000

The goal of this Paper is to improve cybersecurity threat detection by thoroughly examining deep learning and machine learning
models. The study attempts to solve the difficulty of precisely categorizing and forecasting hostile actions in network traffic
by focusing on a dataset that encompasses a variety of cyber threats. Preprocessing the data, using Principal Component
Analysis (PCA) to apply dimensionality reduction, and putting a variety of machine learning algorithms into practice—
including Logistic Regression, K-Nearest Neighbours, Gaussian Naive Bayes, Support Vector Machines, Decision Trees, and
Random Forest—are all part of the methodology. Important conclusions highlight how ensemble models— Random Forest in
particular—work well to achieve notable precision and accuracy. Principal Component Analysis's effect on model performance
is also examined, providing information about the significance of features and the interpretability of the model. In addition to
highlighting the promise of ensemble methods for reliable threat detection, the research provides insightful information about
the efficacy of different machine learning algorithms in cybersecurity. The study’s insights have practical consequences for
cybersecurity practitioners and lay the groundwork for future cybersecurity analytics research projects.

BIOSYNTHESIZED GOLD NANOPARTICLES FROM RED SEAWEED AMPHIROA FRAGILISSIMA THROUGH ANTIOXIDANT AND ANTICANCER ACTIVITY AGAINST OSTEOSARCOMA CANCER CELLS

Vijaya Bhaskara Reddy Mutha — Tue, 25 Jun 2024 00:00:00 +0000

AUTOMATED PRICING PREDICTIONS FOR PRE-OWNED VEHICLES USING RANDOM FOREST

Jayashri Kethini Umapathi — Tue, 25 Jun 2024 00:00:00 +0000

The pricing of new vehicles in the automotive industry is determined by manufacturers, augmented by additional costs imposed by the government in the form of taxes. Consequently, customers purchasing a new car can be assured that their investment is justified. However, due to escalating prices of new vehicles and the financial constraints faced by many consumers, the market for used cars is experiencing significant global growth. This underscores the pressing necessity for an effective used car price prediction system that can accurately assess the vehicle's value based on various factors, including mileage, year of manufacture, fuel consumption, transmission type, road tax, fuel type, and engine size. We have developed a highly effective model designed to serve the needs of sellers, buyers, and manufacturers within the used car market. Upon completion, this model will deliver relatively precise price predictions based on the information provided by users. The Random Forest algorithm was employed in this research to maximize accuracy, enabling the prediction of an actual vehicle price rather than merely a price range. To evaluate the performance of each regression model, the R-squared metric was calculated.

FACE RECOGNITION USING CNN

D.Gayathry, R. Latha — Tue, 25 Jun 2024 00:00:00 +0000

The use of face recognition is growing at an astounding rate these days. Currently, researchers are developing many methods
for how a facial recognition system functions. People often find themselves alone in their families in situations such as normal
disasters, kidnappings, accidents, missing persons cases, and many more situations. To reach the family of those refugees and
ensure their safety and support, it is imperative to identify their relatives. Every day, police departments enroll missing cases.
Some of these enlisted cases are resolved, but not all of them are resolved by employing the labor-intensive manual approach.
This study aims to address the time delay caused by current police examination procedures by leveraging the latest innovations.
Therefore, we implement a framework that makes use of the CNN (Convolutional Neural Network) technique and the VGG16
architecture. We begin with our input dataset, which consists of 84 photos taken from 21 different households. The final dataset,
obtained by applying the enhancement method, consists of 1512 photos, of which 80% are utilized for training and 20% are for
testing. This framework offers a quick and easy method for locating a refugee's personal and helps validate an individual's
identity by using their picture and family information with related models that are more accurate.

REAL TIME ACCIDENT DETECTION AND REPORTING SYSTEM USING CNN ALGORITHM

P.Dineshkumar, Barathwaj K, Ganesh Kumar H, Charan MJ, T.Kirubadevi — Tue, 25 Jun 2024 00:00:00 +0000

In order to identify patterns for decision-making, deep learning, a branch of artificial intelligence, imitates how the human brain processes data. Within machine learning, it utilizes networks that discern and categorize patterns from unstructured or untagged data. Referred to as deep neural learning, Convolutional Neural Networks (ConvNets or CNNs) shine in image recognition tasks, adept at identifying faces, objects, and traffic signs. Their prowess extends to robotics, enhancing vision for self-driving cars. Despite widespread awareness of driving regulations, a substantial number globally fall victim to vehicle crash injuries due to drivers' negligence, despite their knowledge. This paper contributes to road accident detection through the Mask R- CNN method, aiming to improve safety measures.