Asian Journal of Research in Computer Science

Exam Assessor Tool: An Automated System for Efficient Answer Sheet Evaluation

2024-04-15T10:54:09+00:00

With Education 4.0 and four quadrant approach number of innovations have gone into academics for efficient, experiential, and outcome-based education however assessment schemes are still very much dependent on manual assessment methods which are time-consuming and cumbersome. The grading system can sometimes be irrational, with diversified schemes for the same course and can also be biased. Covid 19 pandemic caused a global economic avalanche like we’ve never experienced in our lifetime. Many countries have implemented control measures such as blockades and curfews. The education system in this chaos saw a silver lining with academics shifting to online mode, with paradigm shift in teaching, assessment techniques too need to evolve. Work done is an effort to ease the process of assessment, a machine learning assisted model is developed that automates subjective answer evaluation in the education sector. Our project involved several crucial steps, including grayscale conversion, Natural Language Processing (NLP) for data cleansing, data splitting, and training an artificial neural network (ANN) to predict scores based on extracted features. ANN-based system grades subjective responses without human intervention, reducing the workload of teachers and professors. Model constructed an ANN architecture with three layers using Rectified Linear Activation Unit (ReLU) and Sigmoid activation functions. Trained model was incorporated into a user-friendly web application using the Streamlit library. Model design gives a major boost in grading efficiency and accuracy while providing valuable feedback to students. Research surveys were conducted, and a dataset was constructed for training and testing the model. study yielded an accuracy of 83.14% after employing techniques such as text cleaning, preprocessing, and feature extraction.

Enhancing Security Using GPS-GSM Motorcycle Tracking System

2024-04-15T13:18:50+00:00

Motorcycles are progressively becoming a well-known mode of transportation in Ghana, especially in the northern region. Their affordability and easy movement on our rough roads make them a choice many users prefer. Nonetheless, the increase in the number of these motorcycles brought some concerns connected with safety and security. To resolve these issues, the improvement of the security framework is fundamental. Real-time monitoring is part of the Internet of Things (IoT), which permits distance monitoring. Different tracking technologies such as RFID, Internet tracking, cellphone triangulation, GPS, and other technologies. This research work expects to plan a far-reaching motorcycle security and global positioning framework utilizing an Arduino microcontroller Uno r3, Neo-6mGPS, and GSM SIM800L modules. The GPS module obtains the location area while the GSM module works with interaction between the Arduino Uno and the client's cell phone, showing the area on Google Maps. The framework comprises a locking component and a global positioning framework. The motorcycle's ignition system is controlled by a locking mechanism that enhances protection against theft. Besides, the scarcity of these security systems and the existing motorcycle tracking systems are very costly to purchase and maintain. There is restricting openness for the overwhelming majority of bike users. This prompt is a high pace of bike theft, making recovery challenging. One of the project's goals are to decrease power utilization in the global positioning framework, upgrade GPS following precision, and use SMS as the essential means of communication. This research work adopted the Agile Methodology of designing applications. While this research work presents various benefits, it additionally has limits. These incorporate the expenses of equipment parts. Restricted accessibility of Arduino components in the Ghanaian market and time. Regardless of these restrictions, the exploration attempts to create powerful and open bike security in the Ghanaian market.

Fire Prediction Analysis Based on Ensemble Machine Learning Algorithms

2024-04-17T13:38:32+00:00

A fire accident is the most tragic incident in human life. Particularly environmental hazards such as forest fires lead loss of wildlife, economy, wealth, human lives and pollution. our research purpose of predict the occurrence of fire incidents using ensemble machine learning models. The goal is to develop an accurate and reliable model that can forecast the occurrence of forest fires based on various environmental factors. The best performance is obtained by the ensemble machine learning model for this work. Comparative study of individual model and ensemble model. If you check all models Decision tree predicts 75.4%, the Random Forest tree predicts 83.2%, the Support Vector Machine predicts 71.8%, and the K nearest neighbour predicts 82.1%. Ensemble models with two combinations of decision tree and random forest tree predicts accuracy is 80.8%. Support vector machine and KNN predicts the accuracy rate is 73.4%. The individual model predicts more accuracy compared to ensemble learning model.

Factorization Algorithm for Semi-primes and the Cryptanalysis of Rivest-Shamir-Adleman (RSA) Cryptography

2024-04-18T10:18:58+00:00

This paper introduces a new factoring algorithm called Anorld’s Factorization Algorithm that utilizes semi-prime numbers and their implications for the cryptanalysis of the Rivest-Shamir-Adleman (RSA) cryptosystem. While using the concepts of number theory and algorithmic design, we advance a novel approach that notably enhances the efficiency of factoring large semi-prime numbers compared to other algorithms that have been developed earlier. In our approach, we propose a three-step algorithm that factorizes relatively large semi-primes in polynomial time. We have introduced factorization up to 12-digit semi-prime using Wolfram|Alpha, a mathematical software suitable for exploring polynomials. Additionally, we have discussed the implications of the new algorithm for the security of RSA-based cryptosystems. In conclusion, our research work emphasizes the important role of factoring algorithms in the cryptanalysis of RSA cryptosystems and proposes a novel approach that bolsters the efficiency and effectiveness of semi-prime factorization, thereby informing the development of more powerful cryptographic protocols.

Cost-Efficient Deployment Strategies: A Comparative Analysis of Feature Flagging Services and Blue/Green Deployments

2024-04-18T10:26:54+00:00

Aims: This study provides a detailed comparison of two leading feature flagging services, LaunchDarkly and ConfigCat, and also examines the cost-efficiency and operational implications of using Blue/Green deployment strategies. It seeks to aid stakeholders in understanding the trade-offs and benefits of each approach to make informed decisions based on project-specific needs, budget constraints, and developmental objectives.

Study Design: The study employs a comparative analysis framework, focusing on features, usability, scalability, architectural design, and the financial impacts of adopting feature flagging services versus Blue/Green deployment strategies.

Place and Duration of Study: The analysis was conducted over a period of two years, encompassing a broad range of software development environments and project scenarios to ensure comprehensive coverage and relevance.

Methodology: The methodology employed in this paper includes a detailed examination of LaunchDarkly and ConfigCat's service offerings, an evaluation of Blue/Green deployment strategies, and an analysis of cost-efficiency of each approach. The study synthesizes information from product documentation, user feedback, and performance metrics, alongside interviews with industry experts and case studies from diverse software development projects.

Results: The results highlight the nuanced differences between feature flagging services in terms of scalability, ease of use, and the suitability for various project sizes. LaunchDarkly emerges as optimized for large-scale, complex projects due to its extensive feature set and scalability, while ConfigCat is favored for its simplicity and ease of use in smaller projects. The analysis also uncovers the cost benefits of feature flagging over Blue/Green deployments, emphasizing the savings on infrastructure and operational expenses while offering dynamic feature management capabilities.

Conclusion: The study concludes that the choice between feature flagging services like LaunchDarkly and ConfigCat, and the utilization of Blue/Green deployment strategies, should be guided by specific project requirements, financial constraints, and desired operational efficiency. Feature flagging services provide a cost-effective, flexible solution for dynamic feature management, whereas Blue/Green deployments offer a straightforward, though potentially more resource-intensive, approach to minimizing deployment risks. This comparative analysis aims to assist stakeholders in selecting the most appropriate deployment strategy to meet their development goals efficiently.

Ensemble Learning Based Prediction for Cyber Harassment Observations on Tweets

2024-04-18T10:34:20+00:00

Now a days social media plays crucial role in allowing individuals to express their views. Based on their views find the information of different keywords/statements like sadness, happiness, teasing, harassment and abuse. Online abuse, a novel form of pestering, have become increasingly predominant in online groups in modern civilization. Detecting harassment is indeed a significant challenge. Several studies provide information on cyber harassment, but none of them offer a solid remedy. Several studies provide information on cyber harassment, but none of them offer a solid remedy. Due to this reason, multiple models can be practiced to recognize and block harassment-related communications. We have utilized ensemble machine learning models to predict accurate results. The twitter dataset used for our research. We observe two models getting accuracy for RF+DT is 92% and SVM+LR is 93%. It is similar accuracy in individual models. So, there is no difference between Ensemble or individual model accuracy rate.

Enhancing English Learning for Special Needs Students through Technology

2024-04-20T07:03:30+00:00

In the realm of educational instruction, teachers encounter a diverse array of students, each with unique learning styles and potential challenges. Among these learners are those with distinct needs, requiring tailored approaches to facilitate their academic progress. These students often encounter hurdles across various educational facets, necessitating personalized strategies to enhance their learning experiences and self-expression. Thus, the focus of this study is to investigate whether the integration of technological tools such as laptops and tablets, coupled with multimedia elements, can serve as effective motivators and engagement enhancers for students with specific learning requirements.

This qualitative study adopts an observational approach, examining the impact of technology integration on students with special needs across six primary schools in municipalities of Gjilan and Prizren, Kosovo. The primary objective is to gauge the efficacy of technology-assisted instruction, particularly in the context of English language learning. Through a four-week observation period, conducted twice weekly, the study aims to discern the differential outcomes between traditional instructional methods and those supplemented by technology applications.

The study results revealed that in technology-driven English language lessons, special needs students were more motivated to get involved in the lesson, worked together, and participated actively in the classroom activities.

Detection and Classification of Human Gender into Binary (Male and Female) Using Convolutional Neural Network (CNN) Model

2024-04-22T12:04:33+00:00

This paper focuses on detecting the human gender using Convolutional Neural Network (CNN). Using CNN, a deep learning technique used as a feature extractor that takes input photos and gives values to various characteristics of the image and differentiates between them, the goal is to create and develop a real-time gender detection model. The model focuses on classifying human gender only into two different categories; male and female. The major reason why this work was carried out is to solve the problem of imposture. A CNN model was developed to extract facial features such as eyebrows, cheek bone, lip, nose shape and expressions to classify them into male and female gender, and also use demographic classification analysis to study and detect the facial expression. We implemented both machine learning algorithms and image processing techniques, and the Kaggle dataset showed encouraging results.

Cybersecurity Considerations for Smart Bangladesh: Challenges and Solutions

2024-04-26T13:03:48+00:00

Cybersecurity stands as a cornerstone for safeguarding the integrity, security, and prosperity of a nation in the digital era. It involves a multifaceted approach to protect interconnected digital systems, critical infrastructure, and sensitive data. In the context of a smart nation, where interconnected devices, sensors, and systems are integrated to enhance efficiency and quality of life, cybersecurity becomes even more crucial. As Bangladesh progresses towards its vision of becoming a Smart Nation, characterized by extensive integration of digital technologies into various sectors, cybersecurity emerges as a critical concern. The rapid digitization of infrastructure and services, driven by initiatives such as smart cities, e-governance, and digital healthcare, introduces new vulnerabilities and threats that must be addressed to safeguard against cyber-attacks and protect sensitive data. This paper explores the cybersecurity landscape of Bangladesh in the context of its Smart Nation aspirations, identifying key challenges and proposing solutions to mitigate risks. The cybersecurity challenges facing Smart Bangladesh initiatives are multifaceted and include inadequate cybersecurity policies, limited awareness and education, insufficient investment in cybersecurity infrastructure, and the proliferation of Internet of Things (IoT) devices with inherent vulnerabilities. These challenges expose smart systems to a range of threats, including malware and ransomware attacks, data breaches, insider threats, Distributed Denial of Service (DDoS) attacks, and IoT vulnerabilities. To address these challenges, stakeholders must adopt a proactive and multi-layered approach to cybersecurity. Recommendations include the development of comprehensive cybersecurity policies, enhanced public awareness and education campaigns, investment in cybersecurity infrastructure, implementation of secure-by-design principles in smart infrastructure development, and fostering public-private partnerships to share threat intelligence and resources. By prioritizing cybersecurity considerations and implementing robust cybersecurity measures, Bangladesh can build a resilient and secure digital ecosystem that supports its Smart Nation goals. However, addressing cybersecurity challenges requires coordinated efforts from government agencies, private sector organizations, academia, and civil society to create a cyber-resilient environment conducive to sustainable development and innovation. The author found this area of utmost interest and decided to delve deep into the aspects related to cybersecurity, in order to develop a well-designed journey towards a digitally transformed Bangladesh.

Veritas AI: The ChatGPT Polygraph

2024-04-27T08:29:01+00:00

Aims: The objective of Veritas AI is to revolutionize the domain of lie detection through the deployment of a cutting-edge algorithm within the realms of computational linguistics and artificial intelligence.

Study Design: Veritas AI is conceptualized as a groundbreaking framework that integrates advanced syntactic and semantic analysis, leveraging generative pre-trained transformers to identify linguistic cues indicative of deception.

Place and Duration of Study: The research underpinning Veritas AI’s algorithm was meticulously executed at the Abacus CSE Lab over a period from December 2022 to March 2024, ensuring a robust empirical foundation for the system’s validation and optimization.

Methodology: Employing a deep learning neural network at its core, Veritas AI is trained on a diverse dataset comprising both truthful and deceptive dialogues. This training is complemented by multimodal biometric interrogation techniques and sophisticated natural language processing algorithms.

Results: The empirical results underscore Veritas AI’s unparalleled accuracy in discerning truth, marked by its ability to provide real-time adaptive feedback and maintain robust performance across various communication scenarios.

Conclusion: In conclusion, Veritas AI stands as a testament to the symbiotic potential of human ingenuity and machine learning. Its precision-engineered algorithm, underpinned by empirical validation, heralds a transformative leap in the field of automated veracity assessment, setting a new benchmark for truth analysis in the digital age.

Design and Implementation of an Iot-Based Safety and Energy Efficient System

2024-04-27T13:06:30+00:00

The paper provides a safe and power-efficient Internet of Things (IoT)-based solution. With the growing concerns about environmental sustainability and the demand for improved safety measures in today’s society, it has become critical to focus on building systems that decrease energy consumption and assure the safety of humans and the environment. The proposed system employs cutting-edge technologies and novel approaches that will result in optimal energy usage with minimal or no human involvement thereby assuring the safety of people. The proposed system leverages on existing IoT technologies and is comprised of smart sensors, energy-efficient gadgets, and a centralized control unit. Therefore, it is able to demonstrate cutting edge power control strategies including power gating and dynamic central power regulation which control the usage of gadgets to operate at optimal power levels vis-a-vis the real-time demand to achieve energy efficiency. The system is also able to collect data on occupancy, lighting, temperature, and power consumption trends which can assist in making data-driven choices that improve the usage of energy. The proposed system provides large energy savings without sacrificing user comfort by dynamically altering lighting, and cooling systems based on occupants and ambient factors. Multiple simulations and real-world trials in homes and institutions’ buildings were used to assess the efficacy of the suggested system. The findings revealed substantial reductions in energy consumption without jeopardizing safety.

Enhancing Resilience: Smart Grid Cybersecurity and Fault Diagnosis Strategies

2024-04-02T13:00:10+00:00

The increasing integration of advanced technologies within the power grid infrastructure has led to significant advancements in efficiency, reliability, and sustainability. However, this integration also introduces new vulnerabilities, particularly in the realm of cybersecurity. This paper presents an overview of smart grid cybersecurity challenges and proposes strategies for enhancing resilience through fault diagnosis techniques. Firstly, the paper examines the evolving threat landscape facing smart grids, encompassing cyber-attacks, insider threats, and natural disasters. It highlights the critical need for robust cybersecurity measures to safeguard grid operations and prevent potentially catastrophic disruptions. Next, the paper delves into various cybersecurity frameworks and standards tailored specifically for smart grids, emphasizing the importance of comprehensive risk assessment, intrusion detection systems, and secure communication protocols. Additionally, it discusses the role of machine learning and artificial intelligence in augmenting cyber defense capabilities, enabling proactive threat detection and rapid response. Furthermore, the paper explores fault diagnosis strategies aimed at maintaining grid resilience in the face of cyber incidents or physical faults. It discusses the integration of data analytics, predictive modeling, and real-time monitoring to identify and mitigate potential grid disturbances swiftly.

Leveraging AI for Enhanced Quality Assurance in Medical Device Manufacturing

2024-04-08T06:12:47+00:00

The medical device sector adheres to strict regulatory frameworks, requiring precise adherence to quality assurance (QA) processes during the production process. Conventional quality assurance (QA) approaches, although successful, sometimes require substantial time and resource allocations, resulting in possible obstacles and higher expenses. The emergence of Artificial Intelligence (AI) in recent years has completely transformed quality assurance (QA) methods in different sectors, providing unparalleled prospects for improved productivity, precision, and scalability. This research examines the possibility of using AI technologies to enhance quality assurance processes in the manufacturing of medical devices. Manufacturers may improve product quality and streamline production workflows by utilising AI techniques like machine learning, computer vision, and natural language processing to automate and optimize important QA procedures. Artificial intelligence systems can analyse large amounts of data to find abnormalities, uncover flaws, and anticipate any problems in real-time. This allows for proactive intervention and reduces the chances of non-compliance hazards. In addition, AI-powered QA systems provide adaptive learning capabilities, constantly enhancing performance through feedback and adapting to changing regulatory needs. The incorporation of artificial intelligence (AI) into current quality management systems enables smooth and efficient sharing of data and compatibility, promoting a comprehensive approach to quality control throughout the whole production process.

E-commerce Website Performance Evaluation: Technology, Strategy and Metrics

2024-04-19T13:09:12+00:00

Customers can shop conveniently online with the help of the Cooperative Store Management System, an e-commerce web application, without having to go to the store in person. This technology seeks to lessen the effort of sales staff and eliminate the possibility of manual errors by automating data entry operations. Customers can save costs dramatically and gain valuable time by using this method. In addition, clients may take advantage of increased convenience and better service quality because to the fact that these services are available from the comfort of their homes, which promotes customer retention and draws in new customers. Work has unraveled the intricacies of web development process, shedding light on the challenges faced and the inventive solutions devised. From the complexities of user interface (UI) and user experience (UX) design to the thoughtful analysis of essential qualities for our online store, every facet has been meticulously examined to ensure that the platform prioritizes user involvement, seamless navigation, and efficient communication channels. A detailed study is done to analyse the drawbacks of using marketplaces instead of self-owned sites for small scale business. This work shed light on the processes that went into the creation of a website. Additionally, it provides a thorough analysis of the architecture, Technology, and system's functionality. Facebook News Feed that uses React for dynamic contents, react.js allows for efficient updates to the news feed in real-time without having to reload the entire page. while in LinkedIn Mobile its mobile app uses AngularJS for front-end development. Very limited amount of research work done till date explores the issue of web strategy in web site evaluation, and none includes web strategy in their evaluation frameworks. Citing above problem, a strategic framework was adopted to ensure consistency and provide an efficient solution. AngularJS provides a structured framework for building dynamic and responsive user interfaces. For the use case - MERN Stack website, the Largest Contentful Paint comes as 3.8 sec, First Input Delay comes as 20 milli-sec and cumulative layout shifts come with no delay. These scores provide suggestions for improving various aspects of performance, such as optimizing images, leveraging browser caching, and minimizing render-blocking resources.