We propose a fast and accurate method for visual drone detection based on YOLOv5 architecture providing state-of-the-art performance. The proposed method aims to drone detection in combat and real-world environments for military use based on visual detection in the visible and infrared spectrum. The method provides precision/recall of 99.1/98.5% and 99.0/95.3% for RGB and infrared videos from the AntiUAV dataset.
The aim of the article is to build up qualitative evidence that CBRN training, which requires quick and prompt reactions from first responders, should involve simulation. The authors rely on a case study, the European Sensor System for CBRN Applications EU-SENSE project, which has to provide an adaptable and multipurpose hazard detection solution for enhancing situational awareness. A dedicated training mode on how to use the device by CBRN practitioners assumes that life-threatening substances are present in a real-life operation. Therefore, in order to provide lifelike experiences in a controlled environment, a simulation-based activities can be proposed. The analysis of CBRN training requirements and sample hypothetical scenarios, which complement the case study, proves that CBRN mission-specific training requires the design of a range of simulationbased activities that help learners acquire safe behavioural competences and at the same time examine their performance. They will be also conducive to developing decision-making and communication skills and improving situational awareness. In a contaminated environment, these skills are necessary for survival. This study contributes to the growing body of research on CBRN training concerning newly developed devices, which enhance the work of CBRN practitioners.
An Intelligence Platform for Chemical, Biological, Radiological, Nuclear and explosives (CBRNe) Events and Asymmetric Threats has been developed as a pilot prototype to meet the needs of organizations, specialist, experts, professionals from the intelligence, law-enforcement, military, chemical, biological, radiological/nuclear and health domains. The main goal was to provide a tool able to collect open source information in an asymmetric threats environment, with a focus on CBRNe events and terrorism, and with a pilot focus on COVID-19 related information, and to generate outcomes that can help analysis of trends, threats and intelligence sources, with application across security, academia and health fields. The developed IT solution is a flexible and innovative instrument offering support to CBRNe risk and Asymmetric threat knowledge management by monitoring a wide range of information sources, using normalized terminologies, based on tuned ontology and able to enhance interaction and communication between different international entities (semantic interoperability). The experimentation aimed to provide a lite tool that can be adopted at different levels, including where less skills and economic resources are available (local units of complex organizations, public administrations in developing Countries, SMEs, ONGs, media). The activities have been carried out by the Observatory on Security and CBRNe Defence OSDIFE - Italy, in cooperation with the University of Rome âTor Vergataâ - Department of Electronic Engineering - Italy, the State University of the Republic of San Marino - Center for Security Studies, the Flinders University - Australia and Expert AI - Italy.
The COVID-19 outbreak hit all countries and all mankind with unexpected initial force. This forced decision-makers at all levels, both among the rulers and managers of the private sector, to make decisions that had been atypical so far. As a last resort, in order to minimize the number of cases and ultimately the number of victims, the rulers were forced to introduce further lockdowns. Unfortunately, such activities have severely limited economic activity, contributing to the economic slowdown. Thus, the rulers are forced to make difficult decisions on how much to protect health and how much to protect the economy. In this paper, using the method of systems dynamics and epidemic development models, we present how to predict its course and how to support decision-makers in assessing the current and future situation. The paper describes how to use well known epidemic spread model called SIR (Susceptible-Infected-Recovered) together with System Dynamics methodology and simulation tool JOptisim. The methodology that was choosen, allows modelers to easily extend basic SIR model by new variables depending on modeler needs. In presented example the cost of hospitalization was the variable which was added to the basic model. Using the proprietary JOptisim tool, which has implemented RADU5 numerical procedure, allows authors to validate developed model and achieve accurate simulation results. The paper consists of three sections. The first one is the general introduction to possibilities of predicting epidemic spread and the second one describes briefly the System Dynamics methodology. In the last section it is explained how to choose equations for some of the variables of the model using nonlinear regression methods implemented in R language when real data is available.
We propose a fast and accurate method for visual drone detection based on YOLOv5 architecture providing state-of-the-art performance. The proposed method aims to drone detection in combat and real-world environments for military use based on visual detection in the visible and infrared spectrum. The method provides precision/recall of 99.1/98.5% and 99.0/95.3% for RGB and infrared videos from the AntiUAV dataset.
