https://isjr.co.in/index.php/ITML <p> International Transactions in Machine Learning</p> <p><strong>Scope:</strong></p> <p><strong>International Transactions in Machine Learning</strong> is a peer-reviewed, interdisciplinary journal dedicated to advancing the field of machine learning through the dissemination of high-quality research and innovation. The journal welcomes contributions from researchers, scientists, engineers, and practitioners in academia, industry, and beyond.</p> <p><strong>Aims and Objectives:</strong> The primary objectives of International Transactions in Machine Learning are as follows:</p> <ol> <li> <p><strong>Advancement of Machine Learning</strong>: The journal aims to foster the development and dissemination of cutting-edge research and developments in the field of machine learning. It provides a platform for scholars and practitioners to share their knowledge, insights, and innovations, contributing to the growth of machine learning as a scientific discipline.</p> </li> <li> <p><strong>Interdisciplinary Collaboration</strong>: International Transactions in Machine Learning encourages interdisciplinary collaboration by bringing together researchers from various domains, including computer science, statistics, data science, and artificial intelligence. This interdisciplinary approach enables the exploration of diverse applications and methodologies within the machine learning domain.</p> </li> <li> <p><strong>Dissemination of Knowledge</strong>: The journal is committed to the dissemination of knowledge in the form of research papers, reviews, case studies, and technical notes. It serves as a central repository for high-quality research output, ensuring that the latest findings and trends in machine learning are readily accessible to the global research community.</p> </li> <li> <p><strong>Innovation and Practical Applications</strong>: International Transactions in Machine Learning seeks to promote innovation in machine learning techniques and their practical applications. It encourages researchers to address real-world challenges, explore novel algorithms, and apply machine learning to domains such as healthcare, finance, robotics, and more.</p> </li> </ol> <p><strong>Scope of Topics:</strong> The journal covers a broad spectrum of topics within the field of machine learning, including but not limited to:</p> <ul> <li>Supervised, unsupervised, and reinforcement learning algorithms</li> <li>Deep learning, neural networks, and convolutional neural networks</li> <li>Natural language processing and text analysis</li> <li>Computer vision and image recognition</li> <li>Data mining, feature engineering, and dimensionality reduction</li> <li>Machine learning for healthcare, finance, and cybersecurity</li> <li>Explainable AI and interpretability in machine learning</li> <li>Ethical considerations and bias in machine learning</li> <li>Machine learning tools, frameworks, and libraries</li> <li>Optimization techniques and hyperparameter tuning</li> <li>Transfer learning and domain adaptation</li> <li>Machine learning in edge computing and IoT applications</li> </ul> <p><strong>Types of Contributions:</strong> The journal welcomes the following types of contributions:</p> <ol> <li> <p><strong>Research Papers</strong>: Original research articles that present novel findings and contributions to the field of machine learning.</p> </li> <li> <p><strong>Reviews</strong>: Comprehensive reviews of current research trends, methodologies, and applications within the machine learning domain.</p> </li> <li> <p><strong>Case Studies</strong>: In-depth analyses of practical applications of machine learning in real-world scenarios.</p> </li> <li> <p><strong>Technical Notes</strong>: Short articles that provide insights into specific machine learning techniques, challenges, or tools.</p> </li> </ol> <p><strong>Audience:</strong> International Transactions in Machine Learning is intended for researchers, academics, professionals, and practitioners who are engaged in or interested in the field of machine learning. It is an invaluable resource for those seeking to stay informed about the latest developments and best practices in this dynamic and rapidly evolving field.</p> <p><strong>Publication Frequency:</strong> The journal is published quarterly to ensure the timely dissemination of research findings and maintain a steady flow of valuable contributions to the field of machine learning.</p> <p><strong>Peer Review:</strong> All contributions to International Transactions in Machine Learning undergo a rigorous peer review process to ensure the publication of high-quality and scientifically sound research.</p> <p>International Transactions in Machine Learning is dedicated to promoting the exchange of knowledge, facilitating collaboration, and contributing to the growth of the machine learning community worldwide. It invites researchers and practitioners to contribute to its mission by submitting their original work and actively engaging with the vibrant discourse on machine learning and its applications.</p> en-US International Transactions in Machine Learning https://isjr.co.in/index.php/ITML/article/view/229 <p>The adoption of Internet of Things (IoT) in healthcare has revolutionized remote patient monitoring, providing continuous and real-time health data to healthcare providers. This paper presents the design and implementation of an IoT-based remote patient monitoring system. The system includes wearable sensors, data transmission modules, and a cloud-based platform for data storage and analysis. We discuss the technical challenges in sensor integration, data security, and real-time analytics. A pilot study involving patients with chronic illnesses demonstrates the system's effectiveness in early detection of health anomalies, thereby improving patient outcomes and reducing hospital readmissions.</p> <p>&nbsp;</p> <p>&nbsp;</p> Prof. Raj Sanani Copyright (c) 2024 2024-07-01 2024-07-01 6 6 https://isjr.co.in/index.php/ITML/article/view/230 <p>The concept of smart hospitals leverages IoT technologies to improve operational efficiency, patient care, and resource management in healthcare facilities. This paper reviews the current state of smart hospital technologies, including IoT-enabled medical devices, real-time location systems (RTLS), and automated medication management systems. We analyze the impact of these technologies on healthcare delivery, patient safety, and operational costs. The paper also addresses the challenges of IoT integration in hospitals, such as interoperability, data privacy, and cybersecurity. Case studies of successful smart hospital implementations provide insights into best practices and future trends in IoT-driven healthcare innovation.</p> <p>&nbsp;</p> Prof Madhu Makan Copyright (c) 2024 2024-07-01 2024-07-01 6 6 https://isjr.co.in/index.php/ITML/article/view/231 <p>LoRaWAN has emerged as a leading technology for low-power, wide-area networks (LPWANs), enabling robust communication for Internet of Things (IoT) devices. However, as the adoption of LoRaWAN grows, challenges related to scalability and security become increasingly critical. This paper provides a comprehensive analysis of the latest techniques and protocols aimed at enhancing the scalability and security of LoRaWAN networks. We examine the limitations of current LoRaWAN implementations, including network congestion and vulnerabilities to various attacks. The paper reviews recent advancements in adaptive data rate algorithms, multi-gateway deployments, and enhanced security mechanisms such as end-to-end encryption and secure key management. Through simulations and real-world experiments, we evaluate the effectiveness of these techniques in improving network performance and resilience. Our findings highlight the potential of these innovations to support the growing demands of IoT applications while ensuring secure and reliable communication.</p> <p>&nbsp;</p> Prof. Chi young Copyright (c) 2024 2024-06-07 2024-06-07 6 6 https://isjr.co.in/index.php/ITML/article/view/232 <p>The widespread deployment of LoRaWAN in IoT applications is driven by its capability to support long-range communication with minimal power consumption. However, optimizing energy efficiency remains a critical concern, especially for battery-operated devices in remote or inaccessible locations. This paper investigates the optimization of energy efficiency in LoRaWAN networks through the implementation of adaptive data transmission and sleep scheduling algorithms. We explore the impact of various transmission parameters, such as spreading factor, transmission power, and duty cycle, on energy consumption. Additionally, we present novel sleep scheduling algorithms designed to minimize power usage while maintaining reliable data transmission. Our study involves both theoretical analysis and practical experiments using a testbed of LoRaWAN-enabled devices. The results demonstrate significant improvements in battery life and overall energy efficiency, validating the proposed methods. These findings offer valuable insights for the design and deployment of energy-efficient IoT solutions leveraging LoRaWAN technology.</p> <p>&nbsp;</p> <p>&nbsp;</p> Prof. Kingsl Sultani Copyright (c) 2024 2024-06-15 2024-06-15 6 6