IEEE 802.15.4 is one of the preferred mechanisms to provide modulation and Media Access Control (MAC) in wireless Internet of Things (IoT) networks. With the goal of preserving battery life, IEEE 802.15.4 is characterized by low power consumption that results in low Signal-to-Noise (SNR) ratios responsible of low transmission rates and high Bit Error Rates (BER). In these Low Rate Lossy Networks (LLNs), and from the application layer perspective, the Constrained Application Protocol (CoAP) provides lightweight session management and control with two modes of operation; (1) a reliable mode where retransmissions guarantee packet delivery at a cost of increased latency, power consumption and throughput and (2) an unreliable mode that provides packet loss-prone delivery of packets with lower battery use. In this paper we present a dynamic mode selection mechanism that extends battery life while minimizing latency as well as transmission rates and improving overall Quality of Service (QoS).

The application of AI (Artificial Intelligence) in emergency medicine helps significantly improve the quality of diagnostics under limitations of resources and time constraints in emergency cases. We have designed a comprehensive AI-based diagnostic and treatment plan decision-support system for emergency medicine by integrating the available LLMs (Large Language Models), like ChatGPT, Gemini, Claude, and others, and tuning them up with additional training on actual emergency cases. There is a special focus on early detection of life-threatening and time-sensitive diseases like sepsis, stroke, and heart attack, which are the major causes of death in emergency medicine. Additional training was conducted on a total of 600 cases (300 sepsis; 300 non-sepsis). The collective capability of the integrated LLMs is much stronger than each individual engine. Emergency cases can be predicted based on information from multiple sensors and streaming sources combining traditional IT (Information Technology) infrastructure with Internet of Things (IoT) schemes. Medical personnel compare and validate the AI models used in this work.

The Internet Engineering Task Force (IETF) has developed and promoted several standards intended to facilitate Internet of things communication among constrained devices in low‐power low‐rate networks (LLNs). Specifically, IETF introduces a series of protocols that deal with different layers of the stack ranging from IPv6 adaptation to routing in LLN. Among them, the constrained application protocol (CoAP) is a session protocol that is used to carry sensor and actuator traffic. Since CoAP transport relies on the user datagram protocol , and in order to provide reliability, it introduces a mode operation known as confirmable where messages are considered delivered once they have been acknowledged. One drawback of this approach, however, is the latency that results from the retransmission of packets in lossy networks. In this study, the authors present, model, compare and evaluate a forward error correction mechanism that enables CoAP to improve its reliability while reducing latency.