International Journal for Global Academic & Scientific Research
Not a member yet
64 research outputs found
Sort by
Contrasting Synthetic and Real Art: Pioneering AI Learning Advancements
Full text linkThis paper presents a comparative study between models trained on real-world and synthetic datasets in the domain of artificial intelligence and machine learning. By meticulously evaluating model performance, generalization capabilities, and robustness across diverse scenarios, the investigation of the efficacy and feasibility of synthetic data in machine learning applications. Through empirical analysis, the address fundamental questions regarding predictive accuracy, resilience to adversarial inputs, and biases inherent in synthetic data. Our findings provide valuable insights for practitioners and researchers navigating the dynamic landscape of AI methodologies, offering guidance for informed decision-making and future advancements in the field
A Systematic Literature Review of During and Post-treatment Sleep Disturbances in Breast Cancer Patients
Full text linkBreast cancer patients in India suffered with various post treatment symptoms even after many years of treatment completion. Sleep problems are most dominant issue among all the issues among fatigue, stress, mood swings etc. There is growing need to assess the sleep quality of the patients prior, during and after the treatment. Although oncologists have been working widely for the better treatment facilities resulting the higher survival rates, it is critical to keep track of good quality of sleep and maintaining it during the treatment. Out of 2180 Scopus indexed research papers 32 were selected after rigorous selection criteria. Supportive Care in Cancer published higher number of publications whereas Journal of Pain and Symptom Management received the highest number of citations. This article explores the evidences of sleep problems in breast cancer patients, an overview of significant studies as evidences of treatment induced symptoms, related factors, solution for burdensome symptoms, and how machine learning techniques can be incorporated into sleep quality prediction in breast cancer patients
Enhancing News Article Summarization with Machine Learning
Full text linkThe exponential growth of online news content has created a pressing need for automated summarization tools to help process and condense information effectively. This paper presents a machine learning-based approach to summarizing news articles, focusing on techniques that produce concise and coherent summaries. The methodology includes text preprocessing steps such as tokenization, stop-word removal, and stemming, followed by feature extraction and model training using machine learning frameworks. Libraries such as NLTK and TensorFlow are employed to facilitate text processing and the implementation of the summarization model. The proposed approach is evaluated against baseline models, showcasing its ability to generate high-quality summaries efficiently. The research highlights the advantages of machine learning in automating news summarization, saving time and effort for readers and editors. Challenges such as handling nuanced language and context are discussed, and the paper outlines future research directions to address these limitations and further enhance summarization performance. This study contributes to the growing field of automated news summarization by providing a practical, scalable, and effective solution. It underscores the potential of machine learning to revolutionize how news content is consumed and processed, offering valuable insights for advancing this domain
Study of Retrial Queueing System with Differentiated Vacation, Failure and Repair
Full text linkThis paper presents study of a M/M/1 retrial system incorporating differentiated vacation, failure and repair. Customer arrives according to Poisson process with rate λ. In regular state, if server is busy in serving customers, incoming customers who cannot be served immediately enter an orbit (Pool or virtual queue) of infinite capacity. When server becomes free during regular state, customers waiting in orbit reattempt for service according to classical retrial policy with rate nχ, where n shows orbit or pool size otherwise customer will have to wait for the server to be free. Customers get served with rate μ during regular busy state. Server join complete vacation if server is idle in free regular state, where no service will be provided to customer. If customer arrives during this state, then server transition to the working vacation (WV) state where despite not serving customers completely, now get served with some slow rate ω, (ω˂μ). If no customer remains during WV, server may return to complete vacation. During WV completion instant, if customers are still present in the system, then server resumes regular busy state for serving customers otherwise continue working vacation. Additionally, the server is subject to random breakdowns during its regular busy state. In such cases, it is sent for immediate repair and, upon completion, resumes service in the regular state. By using Probability generating function (PGF) approach, steady state analysis of model, analytical expression of distinct metrics of the system have been derived. The model’s analytical results were further supported by numerical simulations and visualizations implemented using Python, an open-source scientific computing language. The analysis provides insights into how system parameters affect the operational efficiency and quality of service
Ethical Algorithms for Machine Learning Based Ai Powered Robotics: Ethical Perspective for Covid-19 Like Health Emergencies
Full text linkThe coronavirus, a dangerous member of the virus family, infected millions globally. Many peoples were gone infected with it. The of infected peoples were increasing very fast day by day. Now a day’s total cases were about 110M, recoveries about 60M and deaths about 3M. For this, we use AI means artificial intelligence in health care. We can ethical trained robots through machine learning in the situation of covid pandemic. We made robots that help staff in their personal care touch. They go to patient and met the live to doctors by the help of a tab that can we insert in them. They make patients happy by play songs, talk and motivate them. We can insert camera on their head with that they scan the patients that they are happy, sad or depressed. They also help doctors to make the vaccines of this deadliest virus. Robots can be very useful for doctors. The pandemic has disrupted machine learning, analytics, and data for large companies around the world. Now is a good time to look at what that means for leaders who depends on these tools, and what these leaders are doing to regroup and recruit
Role of AI In Water Pollution
Full text linkA major cause of threat to human life and ecosystems is water pollution. The development of innovative solutions with the latest technologies can solve the problem of water pollution around the world. This research paper guides how water pollution management can be done by AI using the combination of AI algorithms with machine learning and data analytics. This shows how we can detect, monitor, and remediate water pollution in real time through intelligent systems. We look at how large amounts of water body data are collected by the sensors powered by AI. The identification of pollutant patterns and prediction of pollution events can be analyzed by advanced machine learning models and deep learning models. This paper guides people on how AI can help in understanding and being more involved in water management. The use of interactive visualization tools makes it easier for people to understand and act on pollution data. AI with the help of different sensors and monitoring systems be a guide in the reduction of water pollution. With the help of AI, we can also make sure that water is safe and clean for future generations. AI plays a huge role in the conservation of water from different water pollutants. Not only because it can help make pollution control more accurate, but it can also help create a more sustainable future
YOLOv4: Balancing Velocity with Vision for High-Performance Object Detection
Full text linkObject detection remains one of the most challenging and impactful problems in computer vision, where the trade-off between speed and accuracy often limits practical deployment. While a vast number of architectural and training features have been proposed to enhance Convolutional Neural Network (CNN) performance, their effectiveness varies depending on datasets, tasks, and model architectures. Certain strategies, such as batch normalization and residual connections, have proven broadly beneficial, while others remain context-specific. In this work, we present YOLOv4: Balancing Velocity with Vision for High-Performance Object Detection, which systematically integrates and validates both universal and novel techniques to achieve state-of-the-art results. Key contributions include the incorporation of Weighted Residual Connections (WRC), Cross Stage Partial connections (CSP), Cross mini-Batch Normalization (CmBN), Self-Adversarial Training (SAT), Mish activation, Mosaic data augmentation, DropBlock regularization, and Complete IoU (CIoU) loss. These innovations are strategically combined to maximize robustness, generalization, and inference efficiency. Extensive experiments on the MS COCO dataset demonstrate that YOLOv4 achieves 43.5% AP (65.7% AP50) at a real-time speed of ~65 FPS on Tesla V100, outperforming existing object detection frameworks in both velocity and precision. Beyond benchmark performance, YOLOv4 provides a practical and scalable solution for real-time computer vision applications, spanning autonomous driving, surveillance, robotics, and edge computing. This work not only advances the state of the art but also establishes a reproducible and accessible framework, enabling researchers and practitioners to balance speed and accuracy effectively in real-world detection tasks
A comparative study on analyzing the impact of NEP 2020 on Achieving Sustainable Development Goals
Full text linkThis research constitutes a thorough examination of the ramifications of the National Education Policy (NEP) 2020 on the higher education system in India. The NEP aims to instigate transformative changes that align higher education with the demands of the 21st century and sustainable development. The study delves into the diverse impacts of the NEP on various facets of higher education, encompassing curriculum, governance, research, technology integration, and vocational education. Through a scrutiny of the policy\u27s implications, this research furnishes valuable insights into the manner in which the NEP reshapes higher education to foster multidisciplinary learning, research and innovation, adaptable curricula, and comprehensive development. The study sheds light on both the potential advantages and challenges stemming from the NEP\u27s implementation, thereby contributing to a deeper comprehension of its role in the metamorphosis of India\u27s higher education landscape
The Influence of Global Trade Policies on Business Development in Emerging Markets
Full text linkThis study explores the complex relationship between global trade policies and business development in emerging markets. As globalization transforms economic environments, comprehending the ramifications of trade policy is becoming increasingly vital for enterprises in developing countries. This study examines the impact of trade agreements, tariffs, and regulatory frameworks on market accessibility, competitiveness, and growth prospects for enterprises in emerging markets. The research analyses case studies from many areas, emphasizing the dual role of trade policy as both a driver of growth and a barrier for local businesses. This study utilizes a qualitative technique, using case studies and interviews with industry experts, legislators, and corporate executives. The findings highlight the imperative for politicians and business leaders to cooperate in establishing favourable conditions that promote sustainable company growth in emerging nations
OptiMediaAI :Transforming Customer Support with AI-Driven Video Innovation
Full text linkIn a customer-first era, effective care is paramount in driving satisfaction and loyalty. OptiMediaAI, an AI-powered video care platform, revolutionizes customer experiences with state-of-the-art technology including AI, machine learning, video communications, and emotion analysis. Personalized, empathetic, and effective contact through NLP, emotion analysis, and gesture analysis enables deeper relationships and reduced attrition of customers. The solution integrates face recognition, speech-to-text, and LSTM-powered chatbots for inclusivity, correct communications, and real-time responsiveness. Meeting both apparent and unobvious customer needs, OptiMediaAI maximizes fulfillment and enables operational perfection. As a 24x7 AI service agent, it transforms customer care into a real-time and efficient experience, driving business and supporting economic growth. OptiMediaAI is an AI-powered customer care breakthrough innovation