Asian Journal of Research in Computer Science
Not a member yet
792 research outputs found
Sort by
Proposed Methods for Preventing Overfitting in Machine Learning and Deep Learning
No full textThe article discusses various approaches and methods to combat overfitting, which is a key problem in the field of artificial intelligence. Overfitting occurs when the model over-adapts to the training dataset, losing the ability to generalize to new data. The main causes and signs of overfitting are also discussed, including excessive complexity of models and limited data. The focus is on methods such as regularization, dropout, and the use of ensemble methods that can significantly reduce the risk of overfitting. These approaches are evaluated using examples from various fields of neural network applications, providing the reader with a comprehensive understanding of the problem and its solution methods
Smart Media or Biased Media: The Impacts and Challenges of AI and Big Data on the Media Industry
No full textThis study critically analyzes the impact of artificial intelligence (AI) and big data on the media industry, focusing on the ethical challenges and biases introduced by these technologies. The research aims to uncover the extent to which AI and big data influence content personalization, creation, and marketing, and the ramifications of these influences on cultural diversity and societal norms. A mixed-methods approach was employed, combining quantitative analysis through a survey of 532 respondents and qualitative thematic analysis of 10 academic literatures. The findings reveal significant associations between automated content creation tools and societal biases, personalized recommendation systems and echo chambers, and algorithmic recommendations and cultural homogenization. Conversely, no significant association was found between big data analytics and privacy concerns. The study highlights the need for ethical guidelines, enhanced content diversity, strengthened data privacy measures, and increased algorithmic transparency to mitigate the ethical challenges and biases in AI-driven media platforms. These insights contribute to the broader understanding of AI and big data\u27s role in shaping the media industry, offering valuable implications for future research, policy-making, and industry practices
Benefit of Incorporating Technology in Special Education
No full textThe objective of this study is the application of technology in the process of learning by students with special needs. The author argued that the integration of information technology and various technological device help in enhancing learning outcome and social skills of students with disabilities., whether in the educational process or in socialization. The research methods used are of the combined type: quantitative and qualitative. Quantitative methods are part of the empirical research that involves parents, support teachers, school management, and representatives of associations of persons with disabilities. On the other hand, the qualitative method was employed to the focus group with 6 participants, with disabilities and a support teacher, where the discussion was assisted by the support teacher
Maximizing Penetration Testing Success with Effective Reconnaissance Techniques Using ChatGPT
No full textBackground/Objective: The study investigates the integration of ChatGPT, a generative pretrained transformer language model into the reconnaissance phase of penetration testing. The research aims to enhance the efficiency and depth of information gathering during critical security assessments offering potential improvements to traditional approaches.
Research Problem: The research study addresses the challenge of optimizing the reconnaissance phase in penetration testing. It seeks to provide a solution by exploring the capabilities of ChatGPT in extracting valuable data, such as various aspects of the digital footprint or infrastructure of a system or an organization. The scope of the research relies in demonstrating how ChatGPT can contribute to the planning phase of penetration testing, guiding the selection of tactics, tools, and techniques for identifying and mitigating potential risks that could be used to assist with securing Internet accessible assets of a system or an organization.
Methodology: The research adopts a case study methodology to assess the effectiveness of ChatGPT in reconnaissance. Tailored questions are formulated to extract specific information relevant to penetration testing. The study highlights the importance of prompt engineering emphasizing the need for carefully constructed questions to ensure usable results.
Results: The research showcases the ability of ChatGPT to provide diverse and insightful reconnaissance information. The extracted data includes IP address ranges, domain names, vendor technologies, SSL/TLS ciphers, and network protocols. The information gathering improves efficiency of the reconnaissance phase aiding penetration testers in planning subsequent phases of the assessment.
Discussion: The research study extends to the broader field of cybersecurity where artificial intelligence language models can play a valuable role in enhancing the success of reconnaissance in penetration testing. The research suggests that integrating ChatGPT into penetration testing can bring about positive changes in the efficiency and depth of information obtained during reconnaissance.
Conclusion: The results of the study determine that incorporating ChatGPT in the reconnaissance phase significantly benefits penetration testers by offering valuable insights and streamlining subsequent assessment planning. The results affirm ChatGPT as a pivotal tool in maximizing success in penetration testing, contributing to ongoing advancements in cybersecurity practices
Detection and Classification of Human Gender into Binary (Male and Female) Using Convolutional Neural Network (CNN) Model
No full textThis 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
EEG Innovations in Neurological Disorder Diagnostics: A Five-Year Review
No full textThe study provides a description of electroencephalography (EEG) advancements and their application in diagnosing and assessing various neurological diseases over the previous five years. The paper covers how EEG is used to examine epilepsy, sleep disorders, movement disorders, cognitive function, and brain damage. In epilepsy, EEG remains critical for seizure diagnosis, categorization, and localization of epileptogenic zones. Recent enhancements include the integration of machine learning techniques with high-density EEG equipment. In terms of sleep disorders, aberrant patterns suggestive of illnesses such as sleep apnea or narcolepsy may be diagnosed by a sleep architecture study utilizing EEGs, which can also be used to track therapy response. Cortical involvement occurs in Parkinson’s disease and Huntington’s disease, as well as other areas of the brain stem or basal ganglia. It helps researchers learn more about the cortical damage produced by these disorders, which contributes greatly to understanding their pathophysiology. Aside from that, cognitive evaluation based on EEG has evolved via the creation of quantifiable biomarkers for early identification and monitoring of deterioration in Alzheimer’s disease, among others. Traumatic injuries can damage brain functioning, hence knowledge regarding severity predicted outcomes can be acquired by Traumatic Brain Injury evaluation utilizing EEG
Enhancing English Learning for Special Needs Students through Technology
No full textIn 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
Revisiting Blockchain Technologies and Smart Contracts Security: A Pragmatic Exploration of Vulnerabilities, Threats, and Challenges
No full textAim: This study aims to offer a comprehensive examination of the security vulnerabilities associated with blockchain technology, with the aim of identifying critical challenges and formulating strategic solutions to bolster system integrity and enhance user trust.
Methods: The study employs a combination of literature review and case study analysis to explore specific vulnerabilities such as re-entrance attacks, transaction malleability, and the risks associated with third-party integrations. Various recommendations are offered to address the outlined vulnerabilities in blockchains and smart contacts.
Conclusion: Securing blockchain platforms against emerging threats requires a multidisciplinary approach that encompasses technological innovation, stringent regulatory oversight, and comprehensive user education. It advocates for ongoing research and collaborative efforts to develop robust security measures that ensure the sustainable integration of blockchain technology into global digital infrastructures, thereby maximizing its transformative potential while minimizing associated risks. Enhancing the understanding of blockchain\u27s security needs and continuously adapting to emerging threats are crucial for the technology’s future resilience and widespread adoption
Enhancing Agricultural Practices Through IoT-Based Smart Farming Technologies: A Case Study on Banana Crop Yield Optimization
No full textAims: Smart farming and precision agriculture have emerged as transformative paradigms in modern agricultural practices, leveraging technological innovations to enhance productivity, sustainability, and efficiency in food production. This paper provides a comprehensive review of the concepts and technologies related to smart farming. The work proposed implements a sensor assisted IoT based model to enhance the overall yield of banana crop, by monitoring the current conditions existing at the site and predicting the alterations to achieve optimal conditions for conducive and healthy growth, further early identification and prediction of infection causing pathogens to have also been embedded in the model. Model designed has been tested on the farm field of banana crop located in the premises of Amity University Lucknow Campus equipped with moisture and humidity sensors (DHT11), NPK soil nutrient sensor, PIR motion sensor (HC-SR501), pH Sensor (pH -450), rain drop sensor along with camera installed drone for infection identification. Data from sensors and drone camera were monitored at regular intervals for future predictions about health and productivity estimate of the crop
Impact of Generative AI in Academic Integrity and Learning Outcomes: A Case Study in the Upper East Region
No full textWith the increasing use of Generative Artificial Intelligence (AI) tools like ChatGPT and Bard, universities face challenges in maintaining academic integrity. This research investigates the impact of these tools on learning outcomes (factual knowledge, comprehension, critical thinking) in selected universities of Ghana\u27s Upper East Region during the 2023-2024 academic year. The study specifically analyzes changes in student comprehension and academic integrity concerns when using Generative AI for content generation, research assistance, and summarizing complex topics. A mixed-methods approach was employed, combining qualitative data from interviews and open-ended questions with quantitative analysis of survey data and academic records. The research focuses on three institutions: C. K. Tedam University of Technology and Applied Sciences, Bolgatanga Technical University, and Regentropfen University College. A purposive sampling technique recruited 150 participants (50 from each university) who had used Generative AI tools. Key findings show that 72% of students reported improved understanding of course material through Generative AI use, yet 75% cited academic integrity as a primary concern. Quantitative analysis revealed a weak to moderate positive correlation (r = 0.45) between AI tool usage and improved grades, with variations depending on the specific AI tasks performed. Qualitative data highlighted concerns about overreliance on AI and its impact on critical thinking skills.
This research contributes to the ongoing debate on AI\u27s role in education by providing valuable insights for educators and policymakers worldwide. The findings suggest that while AI tools can enhance comprehension, ethical considerations and potential drawbacks related to critical thinking require careful attention. The study concludes with recommendations for integrating AI literacy programs, developing ethical guidelines, and implementing advanced plagiarism detection systems to harness the benefits of Generative AI while mitigating risks to academic integrity. Although specific to the Upper East Region of Ghana, these insights may be applicable to other educational systems with similar characteristics