With limited hardware capabilities the deployment of multi-object tracking in near real-time remains a challenging task. To address this, a combination of YOLOv10 and DeepSORT for object tracking and detection is proposed which can run on CPU-only devices. This paper carefully selects the key parameters such as the resolution and removes irrelevant objects from an image. This work achieved 86
This paper aims to outline the development of adaptation strategies and HMI guidelines for a COntroller adaptive Digital Assistant (CODA) to support Air Traffic Controllers in their operational duties by dynamically managing their workload. The strategies and guidelines were constructed using relevant literature and interviews with operational experts. The interim results include areas of specific interest based on operational knowledge, fourteen adaptation strategies and fifteen HMI guidelines. These results will serve as input for subsequent mock-ups that consider technical factors as well, and ensure an effective and usable support to controllers. These interim results provide valuable insights for developing supportive tools in the highly regulated, safety-critical domain of ATC, contributing to the advancement of operational safety and efficiency.
In this paper we analyse the world and network connections of biohacking within a medium-sized city, focusing on the interactions between the stakeholders and the potential risks and benefits. Through the design of a network model and simulation experiments with it, we get insight into the dynamics of biohacking activities and the impact of potential protective measures in a medium-sized city. One the findings from the simulation scenario was the identification of the risks associated with unregulated biohacking practices, in particular those conducted by DIY biohacking enthusiasts. The conducted simulations showed how with the implementation of structured protective measures, such as the public forum and task forces, the risk levels can be reduced. The simulations also showed that the benefits from biohacking such as enhanced physical and cognitive abilities can outweigh the risks of complications over time, providing that protective measures have been provided and are effective.
This paper addresses computational analysis of defence against Advanced Persistent Threats (APTs). The analysis is done by a behavioural network model for simulating the relevant processes, including (1) the APT attack chain itself and adaptivity of it by learning both by the hackers and by the organisation, (2) the understanding of the process by the organisation, and (3) management of the organisational response. Several variations of simulation experiments and a What-If analysis have been applied, leading to risk assessment.
Context-aware assistance systems are becoming essential for aiding decision-making and task management for the workers. However, integrating these systems with various other entities such that they interact seamlessly, poses a challenge. This paper proposes a solution that leverages advanced interaction protocols and context-aware robotic assistance to ensure smooth and effective collaboration in the factory environment supported by three pillars: 1) an ontology-based Digital Twin (DT) representing the semantic dimension and providing object-specific information, 2) an egocentric perception system using HoloLens2 to observe the worker with individually tailored dataset for context recognition, and 3) a robotic assistant guided by an intention-recognition module that responds to emerging worker needs, based on behavioral and environmental observations. In a manual assembly scenario, our framework provides useful contextual information as well as automated and adaptive robotic assistance. We present the results from a user experiment which was conducted to compare the stress level of participants with and without the use of the assistance system in a manual assembly scenario. Physiological sensors from the Empatica E4 wrist-watch were used to collect physiological data on which the stress levels were detected using a deep learning model. Additionally, the user ratings on the System Usability Scale (SUS) were used to assess the usability and acceptance of robotic-assistance technology.
