Background: Rapid advancements in large language models (LLMs) have significantly enhanced Retrieval-Augmented Generation (RAG) techniques, leading to more accurate and context-aware information retrieval systems. Methods: This article presents the creation of a RAG-based chatbot tailored for university course catalogs, aimed at answering queries related to course details and other essential academic information, and investigates its performance by testing it on several locally deployed large language models. By leveraging multiple LLM architectures, we evaluate performance of the models under test in terms of context length, embedding size, computational efficiency, and relevance of responses. Results: The experimental analysis obtained by this research, which builds on recent comparative studies, reveals that while larger models achieve higher relevance scores, they incur greater response times than smaller, more efficient models. Conclusions: The findings underscore the importance of balancing accuracy and efficiency for real-time educational applications. Overall, this work contributes to the field by offering insights into optimal RAG configurations and practical guidelines for deploying AI-powered educational assistants.

The sensors used in the Internet of Medical Things (IoMT) network run on batteries and need to be replaced, replenished or should use energy harvesting for continuous power needs. Additionally, there are mechanisms for better utilization of battery power for network longevity. IoMT networks pose a unique challenge with respect to sensor power replenishment as the sensors could be embedded inside the subject. A possible solution could be to reduce the amount of sensor data transmission and recreate the signal at the receiving end. This article builds upon previous physiological monitoring studies by applying new decision tree-based regression models to calculate the accuracy of reproducing data from two sets of physiological signals transmitted over cellular networks. These regression analyses are then executed over three different iteration varieties to assess the effect that the number of decision trees has on the efficiency of the regression model in question. The results indicate much lower errors as compared to other approaches indicating significant saving on the battery power and improvement in network longevity.

Internet of Things (IoT) holds great promises for industrial, commercial, and consumer applications. While wireless techniques have matured with time and have gained the users’ confidence in relaying data containing qualitative as well as quantitative information, cynicism still exists on trusting them for applications involving control. The wireless protocols and techniques used for industrial control have proved their robustness. In this work we have attempted to test some aspects of feasibility on the use of wireless control involving such protocols for IoT healthcare sensor networks (IoT-HSNs). We conceptualized and simulated a 24-channel IoT-HSN model that includes biosensors as well as bioactuators. Currently, no protocol supporting control in such networks has been standardized. We tried to fit in the widely used WirelessHART (Highway Addressable Remote Transducer) industrial protocol for sensing as well as control in the model to test if it would work for a healthcare sensor network. We probed the performance of the model with respect to network parameters such as channels, bandwidth, Quality of Service (QoS) requirements, payload, transmission delays, and allowable errors. For the parameters considered, the results obtained from the model were encouraging, suggesting that WirelessHART fits the IoT-HSN control requirements according to this initial probe. The findings could provide useful insights for researchers working in the field of control in IoT-HSNs and for designers and manufacturers of IoT-HSN equipment.

Healthcare, lifestyle, and medical applications of Internet of Things (IoT) involve the use of wearable technology that employs sensors of various kinds to sense human physiological parameters such as steps walked, body temperature, blood pressure, heart rate and other cardiac parameters. Such sensors and associated actuators can be worn as gadgets, embedded in clothing, worn as patches in contact with the body and could even be implanted inside the body. These sensors are electronic, and any electronic activity during their sensing, processing and wireless transmission is associated with the generation of heat. This dissipated heat can cause discomfort to the subject and has the potential of damaging healthy living tissue and cells. In the proposed work, the author does a performance check on the intrinsic safety aspects of an IoT healthcare network with respect to the functioning of the wireless sensors involved and routing of sensor data samples. The author also suggests an optimized thermal and energy aware framework to address the issue of temperature rise due to processing and data transmission from sensors through signal processing approaches that help in reducing thermal hazards and simultaneously enhancing the network lifetime through energy conservation.