This work introduces the design, architecture, implementation, and testing of a low-cost and machine-learning-enabled device to be worn on the wrist. The suggested wearable device has been developed for use during emergency incidents of large passenger ship evacuations, and enables the real-time monitoring of the passengers’ physiological state, and stress detection. Based on a properly preprocessed PPG signal, the device provides essential biometric data (pulse rate and oxygen saturation level) and an efficient unimodal machine learning pipeline. The stress detecting machine learning pipeline is based on ultra-short-term pulse rate variability, and has been successfully integrated into the microcontroller of the developed embedded device. As a result, the presented smart wristband is able to provide real-time stress detection. The stress detection system has been trained with the use of the publicly available WESAD dataset, and its performance has been tested through a two-stage process. Initially, evaluation of the lightweight machine learning pipeline on a previously unseen subset of the WESAD dataset was performed, reaching an accuracy score equal to 91%. Subsequently, external validation was conducted, through a dedicated laboratory study of 15 volunteers subjected to well-acknowledged cognitive stressors while wearing the smart wristband, which yielded an accuracy score equal to 76%.

Visual sensing of the environment is crucial for flying an unmanned aerial vehicle (UAV) and is a centerpiece of many related applications. The ability to run computer vision and machine learning algorithms onboard an unmanned aerial system (UAS) is becoming more of a necessity in an effort to alleviate the communication burden of high-resolution video streaming, to provide flying aids, such as obstacle avoidance and automated landing, and to create autonomous machines. Thus, there is a growing interest on the part of many researchers in developing and validating solutions that are suitable for deployment on a UAV system by following the general trend of edge processing and airborne computing, which transforms UAVs from moving sensors into intelligent nodes that are capable of local processing. In this paper, we present, in a rigorous way, the design and implementation of a $12.85$ kg UAV system equipped with the necessary computational power and sensors to serve as a testbed for image processing and machine learning applications, explain the rationale behind our decisions, highlight selected implementation details, and showcase the usefulness of our system by providing an example of how a sample computer vision application can be deployed on our platform.

A mass casualty incident may result in tens or hundreds of victims. Triage, being the procedure of classifying victims according to their medical emergency, and the unique identification of victims are equally crucial procedures for effectively managing the crisis with respect to personnel (emergency medical services and non-medical civil protection practitioners) and assets (ambulances, medical equipment, hospital beds, etc.). The solution developed in this work aims at reducing the time needed for triage and identification procedures, and at the same time enhancing the situation awareness of crisis managers. Our system consists of (a) electronic wearable triage tags, aiming at replacing the legacy paper tags, supporting enhanced actuating and connectivity functionalities, visually presenting the status of the medical emergency of the victims and uniquely identifying them, (b) a mobile application, connected in real time with a cloud-based data aggregation node, enabling the emergency personnel to control the wearable device and to record the personal and medical emergency information of the victims, (c) an interoperability layer, supporting different connectivity options and capable of secure and reliable distribution of the collected data to multiple systems, such as Command and Control (C2s) systems of civil protection agencies, and (d) a web application, graphically presenting the victims’ medical emergencies and their personal information in aggregated and in-detail views, intended to be utilized by crisis managers in tactical and strategic levels of command. The efficiency of our system has been demonstrated in multiple civil protection full-scale exercises across Europe.

Countries worldwide, including European ones, face a transboundary crisis of increased frequency and severity. Especially at the EU-level the effective coordinated response becomes crucially important while the increased challenges faced by the civil protection agencies and their personnel require the development of innovative but also integrated and interoperable technologies. Both challenges require standardised procedures and methodological/technological frameworks. In this chapter, the activities of 2 interlinked EU-funded projects (H2020 IN-PREP and H2020 STRATEGY) provide solutions spanning from the collaborative response planning and training to the (pre-)standardisation of significant items related to the crisis management domain. Significant lessons learnt during the preparation and execution of trials in these projects are being discussed while the collaboration with the DRIVER+ project and the reuse and extension of its results in the context of the projects, demonstrate the importance of inter-project collaboration and development of interoperable solutions through open and standardised methods and tools.