Volume 3, Issue 7
Download Complete Issue
The current issue of the journal has five research papers on important topics in modern science and technology. These studies, though different in focus, all aim to improve our understanding and abilities in their fields. They offer insights that could shape future practices and policies. The papers cover the debate between electric vehicles (EVs) and internal combustion engine (ICE) vehicles, cybersecurity, software-defined networking (SDN), medical imaging, and multilingual text recognition. Each paper makes a significant contribution to its field. Together, they show the diverse challenges and opportunities in modern science and technology, highlighting the importance of interdisciplinary research and collaboration.
Front Cover
Publication Month: July 2024, Page(s): i – iÂ
Editorial
Publication Month: July 2024, Page(s): iii – iv
Editorial Board
Publication Month: July 2024, Page(s): ii – ii
Table of Contents
Publication Month: July 2024, Page(s): v – v
Reviewing the Value of Electric Vehicles in Achieving Sustainability
Prashobh Karunakaran, Mohammad Shahril Osman
J. Engg. Res. & Sci. 3(7), 1-10 (2024);
This paper aims to narrow the gap of the narratives blasted out in the media (including social media) about electric cars versus the conventional way humans have been transported over the last 100 years. The ICE industry is closely connected to the O & G because 64 % of the output of the O & G industry is utilized for the transportation industry, which ranges from motorcycles, cars, trucks, ships to airplanes. Therefore, these two large industries have a motive to curtail the expansion of the electric vehicles industry. This paper explains why the change from ICE to BEV is needed for the sustainability of human civilization because climate change has been proven to be linked to human activities. Without tailpipe emissions, electric vehicles can immediately clean up pollution in the largest cities of earth where 56 % of humanity lives. The batteries of electric vehicles can also become a citizen sponsored backup battery for the electric power grids, thereby saving even more pollution from the environment. Such a backup for the power grid is necessary for its ability to smoothen the sudden and unexpected spikes in electric consumption or tripping of generators in the power grid.
A Thorough Examination of the Importance of Machine Learning and Deep Learning Methodologies in the Realm of Cybersecurity: An Exhaustive Analysis
Ramsha Khalid, Muhammad Naqi Raza
J. Engg. Res. & Sci. 3(7), 11-22 (2024);
In today’s digital age, individuals extensively engage with virtual environments hosting a plethora of public and private services alongside social platforms. As a consequence, safeguarding these environments from potential cyber threats such as data breaches and system disruptions becomes paramount. Cybersecurity encompasses a suite of technical, organizational, and managerial measures aimed at thwarting unauthorized access or misuse of electronic information and communication systems. Its objectives include ensuring operational continuity, safeguarding the confidentiality and integrity of sensitive data, and shielding consumers from various forms of cyber intrusions. This paper delves into the realm of cybersecurity practices devised to fortify computer systems against diverse threats including hacking and data breaches. It examines the pivotal role of artificial intelligence within this domain, offering insights into the utilization of machine learning and deep learning techniques. Moreover, it synthesizes key findings from relevant literature exploring the efficacy and impact of these advanced methodologies in cybersecurity. Findings underscore the substantial contributions of machine learning and deep learning techniques in fortifying computer systems against unauthorized access and mitigating the risks posed by malicious software. These methodologies facilitate proactive measures by predicting and comprehending the behavioral patterns and traffic associated with potential cyber threats.
Comprehensive Analysis of Software-Defined Networking: Evaluating Performance Across Diverse Topologies and Investigating Topology Discovery Protocols
Nikolaos V. Oikonomou, Dimitrios V. Oikonomou, Eleftherios Stergiou, Dimitrios LiarokapisÂ
J. Engg. Res. & Sci. 3(7), 23-43 (2024);
Software-defined networking (SDN) represents an innovative approach to network architecture that enhances control, simplifies complexity, and improves operational efficiencies. This study evaluates the performance metrics of SDN frameworks using the Mininet simulator on virtual machines hosted on a Windows platform. The research objectives include assessing system performance across various predefined network topologies, investigating the impact of switch quantities on network performance, measuring CPU consumption, evaluating RAM demands under different network loads, and analyzing latency in packet transmission. Methods involved creating and testing different network topologies, including basic, hybrid, and custom, with the Mininet simulator. Performance metrics such as CPU and RAM usage, latency, and bandwidth were measured and analyzed. The study also examined the performance and extendibility of the OpenFlow Data Path (OFDP) protocol using the POX controller. Results indicate that balanced tree topologies consume the most CPU and RAM, while linear topologies are more efficient. Random topologies offer adaptability but face connection reliability issues. The POX controller and OFDP protocol effectively manage SDN network scalability. This research aims to analyze performance in a manner consistent with numerous previous studies, underscoring the importance of performance metrics and the scale of the network in determining the efficiency and reliability of SDN implementations. By benchmarking various topologies and protocols, the research offers a valuable reference for both academia and industry, promoting the development of more efficient SDN solutions. Understanding these performance metrics helps network administrators make informed decisions about implementing SDN frameworks to improve network performance and reliability.
Keratoconus Disease Prediction by Utilizing Feature-Based Recurrent Neural Network
Saja Hassan Musa, Qaderiya Jaafar Mohammed Alhaidar, Mohammad Mahdi Borhan Elmi Â
J. Engg. Res. & Sci. 3(7), 44-52 (2024);
Keratoconus is a noninflammatory disorder marked by gradual corneal thinning, distortion, and scarring. Vision is significantly distorted in advanced case, so an accurate diagnosis in early stages has a great importance and avoid complications after the refractive surgery. In this project, a novel approach for detecting Keratoconus from clinical images was presented. In this regard, 900 images of Cornea were used and seven morphological features consist of area, majoraxislength, minoraxislength, convexarea, perimeter, eccentricity and extent are defined. For reducing the high dimensionality datasets without deteriorate the information significantly, principal component analysis (PCA) as a powerful tool was used and the contribution of different PCs are determined. In this regard, Box plot, Covariance matrix, Pair plot, Scree Plot and Pareto plot were used for realizing the relation between different features. Improved recurrent neural network (RNN) with Grey Wolf optimization method was used for classification. Based on the obtained results, the average prediction error of the visual characteristics of a patient with keratoconus six and twelve months after the Kraring ring implantation using RNN are 9.82% and 9.29%, respectively. The average error of estimating characteristics of predicting the visual characteristics of a patient with keratoconus six and twelve months after myoring ring implantation are 11.46% and 7.47% respectively.
A Flourished Approach for Recognizing Text in Digital and Natural Frames
Mithun Dutta, Dhonita Tripura, Jugal Krishna DasÂ
J. Engg. Res. & Sci. 3(7), 53-58 (2024);
Acquiring tenable text detection and recognition outcomes for natural scene images as well as for digital frames is very challenging emulating task. This research approaches a method of text identification for the English language which has advanced significantly, there are particular difficulties when applying these methods to languages such as Bengali because of variations in script, morphology. Text identification and recognition is accomplished on multifarious distinct steps. Firstly, a photo is taken with the help of a device and then, Connected Component Analysis (CCA) and Conditional Random Field (CRF) model are introduced for localization of text components. Secondly, a merged model (region-based Convolutional Neural Network (Mask-R-CNN) and Feature Pyramid Network (FPN)) are used to detect and classify text from images into computerized form. Further, we introduce a combined method of Convolutional Recurrent Neural Network (CRNN), Connectionist Temporal Classification (CTC) with K-Nearest Neighbors (KNN) Algorithm for extracting text from images/ frames. As the goal of this research is to detect and recognize the text using a machine learning-based model a new Fast Iterative Nearest Neighbor (Fast INN) algorithm is now proposed based on patterns and shapes of text components. Our research focuses on a bilingual issue (Bengali and English) as well as it producing satisfactory image experimental outcome with better accuracy and it gives around 98% accuracy for our proposed text recognition methods which is better than the previous studies.
