Issue 1 (June)

This paper explores the burgeoning field of Explainable AI (XAI) within the context of predictive healthcare analytics. With the increasing reliance on machine learning algorithms to make diagnostic and treatment recommendations, the need for XAI becomes paramount. We discuss the significance of transparency and interpretability in AI systems for healthcare, emphasizing the importance of understanding the rationale behind AI predictions. The paper delves into various XAI models that have been developed to enhance the explainability of predictive healthcare analytics, such as SHAP (SHapley Additive exPlanations), LIME (Local Interpretable Model-agnostic Explanations), and decision trees. We assess the strengths and limitations of these models and their implications for trust, decision-making, and clinical practice. Furthermore, we examine the challenges and opportunities in integrating XAI into existing healthcare workflows and the potential impact on patient outcomes. Ultimately, the paper underscores the necessity of XAI in promoting responsible and ethical use of AI in healthcare to ensure the delivery of high-quality and equitable patient care.

The rapid growth of the Internet of Things (IoT) has led to an exponential increase in the volume and velocity of data being processed. Real-time data processing is crucial for the success of IoT applications, as it allows for timely decision-making and efficient resource utilization. However, traditional cloud-based processing frameworks struggle to meet the stringent latency requirements of real-time IoT applications. This paper presents a comprehensive review of fog computing frameworks designed for real-time IoT data processing. Fog computing, which distributes computing resources closer to the edge of the network, offers a promising solution to the latency problem. We explore the key components and architectures of fog computing frameworks, emphasizing their ability to process data with low latency, high scalability, and enhanced security. Additionally, we discuss the challenges faced by these frameworks in adapting to diverse IoT applications and propose potential solutions to address them. This review aims to provide insights into the current state of fog computing for real-time IoT data processing, identify research gaps, and guide future developments in this field.

The rapid advancement in technology has led to the development of numerous wearable health monitoring devices. However, the effectiveness and user acceptance of these devices are contingent upon their human-centered design. This paper explores the principles and methodologies behind the human-centered design of wearable health monitoring devices. It emphasizes the importance of understanding the users' needs, preferences, and behaviors to create devices that are both intuitive and functional. The paper discusses the integration of user-centered design processes with technological innovations, such as machine learning and sensor technology, to enhance the performance and user satisfaction of these devices. Furthermore, it highlights the challenges faced in ensuring the usability, portability, and reliability of wearable health monitors. The study concludes by proposing a framework for designing future generations of health monitoring devices that prioritize user experience and health outcomes.

The paper delves into the evolving landscape of human-robot interaction (HRI) within collaborative manufacturing environments. With the advent of advanced robotics and automation technologies, the integration of robots into the manufacturing process has become increasingly prevalent. This study examines the challenges and opportunities that arise from the coexistence of humans and robots in these settings. A comprehensive analysis is conducted to understand the technical, social, and psychological aspects of HRI, focusing on how humans can effectively collaborate with robots to enhance productivity and efficiency. The paper discusses existing collaborative robots (cobots) and their capabilities, the design principles for creating safe and ergonomic workspaces, and the implications of human-robot teamwork on the overall manufacturing landscape. Additionally, the article highlights the importance of human-robot communication, training, and adaptability in fostering successful collaborations. The findings suggest that while there are significant benefits to be gained from HRI, there are also critical considerations for ensuring the well-being of workers and the seamless integration of robotics into the manufacturing ecosystem.

The increasing deployment of smart city technologies has led to a surge in data generation, particularly from real-time video analytics. This paper focuses on the integration of intelligent edge computing in the context of real-time video analytics, aiming to enhance the efficiency and responsiveness of smart city applications. The abstract discusses the challenges posed by centralized data processing and proposes an intelligent edge computing framework that leverages distributed computing resources at the network edge. By processing video data closer to where it is generated, the framework reduces latency, improves bandwidth efficiency, and enhances privacy and security. The paper further explores the use of advanced machine learning algorithms to enable real-time video analysis for tasks such as traffic management, public safety, and environmental monitoring. It concludes with a discussion on the potential benefits and future directions for integrating intelligent edge computing into the fabric of smart cities.