Frontline professionals such as social workers and civil servants play a crucial role in countering violent extremism.Because of their direct contac twith society,first liners are tasked with detecting individuals that may threaten national security and the democratic rule of law. Preliminary screening takes place during the pre-crime phase. However, without clear evidence or concrete indicators of unlawful action or physical violence, it is challenging to determine when someone poses a threat. There are no set patterns that can be used to identify cognitive radicalization processes that will result in violent extremism. Furthermore, prevention targets ideas and ideologies with no clear framework for assessing terrorism-risk. This article examines how civil servants responsible for public order, security and safety deal with their mandate to engage in early detection, and discusses the side effects that accompany this practice. Based on openinterviews with fifteen local security professionals in the Netherlands, we focus here on the risk assessments made by these professionals. To understand their performance, we used the following two research questions: First, what criteria do local security professionals use to determine whether or not someone forms a potential risk? Second, how do local security professionals substantiate their assessments of the radicalization processes that will develop into violent extremism? We conclude that such initial risk weightings rely strongly on ‘gut feelings’ or intuition. We conclude that this subjectivitymayleadto prejudiceand/oradministrativearbitrariness in relationtopreliminary risk assessment of particular youth.
With the proliferation of misinformation on the web, automatic misinformation detection methods are becoming an increasingly important subject of study. Large language models have produced the best results among content-based methods, which rely on the text of the article rather than the metadata or network features. However, finetuning such a model requires significant training data, which has led to the automatic creation of large-scale misinformation detection datasets. In these datasets, articles are not labelled directly. Rather, each news site is labelled for reliability by an established fact-checking organisation and every article is subsequently assigned the corresponding label based on the reliability score of the news source in question. A recent paper has explored the biases present in one such dataset, NELA-GT-2018, and shown that the models are at least partly learning the stylistic and other features of different news sources rather than the features of unreliable news. We confirm a part of their findings. Apart from studying the characteristics and potential biases of the datasets, we also find it important to examine in what way the model architecture influences the results. We therefore explore which text features or combinations of features are learned by models based on contextual word embeddings as opposed to basic bag-of-words models. To elucidate this, we perform extensive error analysis aided by the SHAP post-hoc explanation technique on a debiased portion of the dataset. We validate the explanation technique on our inherently interpretable baseline model.
Within our research on robotic gas detection, we have focused on making a prototype based on Boston Dynamics SPOT, because it takes a lot of difficulties out of prototyping. For instance, it has its own obstacle avoidance algorithm, good drivers are available for ROS2, and SPOT is meant for outdoor navigation. Being a legged robot means that it can easily traverse curbs, shrubberies, unstable soil and even stairs. For this document, we are going to use the insights that we used when looking for a solution for SPOT.
MULTIFILE
Mondkapjes, of mondmaskers, zijn door de SARS-COV-2 pandemie niet meer uit het straatbeeld weg te denken. De kwaliteit en comfort van de pasvorm van medische en niet-medische mondmaskers wordt bepaald door hoe goed het mondmasker overeenkomt met de afmetingen van het gezicht van de drager. Echter is er geen goed overzicht van de antropometrie van het gelaat van de Nederlandse bevolking waardoor de pasvorm van mondmaskers nu vaak niet optimaal is. Er is dus vraag naar een laagdrempelige en veilige manier om gezichtskenmerken in kaart te brengen en betere ontwerprichtlijnen voor mondkapjes. Driedimensionaal (3D) scannen doormiddel van Light Detection and Ranging (LiDaR) technologie in combinatie met slimme algoritmes lijkt wellicht een manier om gezichtskenmerken snel en laagdrempelig vast te leggen bij grote groepen mensen. Daarnaast geeft het 3D scannen van gezichten de mogelijkheid om niet enkel de afmetingen van gezichten te meten, maar ook 3D pasvisualisaties uit te voeren. Hoewel 3D scannen geen nieuwe technologie is, is de LiDaR technologie pas sinds 2020 geïntegreerd in de Ipad en Iphone waardoor het toegankelijk gemaakt is voor consumenten. Doormiddel van een research through design benadering zal onderzocht worden of deze technologie gebruikt kan worden om betrouwbare en valide opnames te maken van gezichten en of er op basis hiervan ontwerprichtlijnen ontwikkeld kunnen worden. In dit KIEM GoCi-project zal daarnaast ingezet worden om een kennisbasis en netwerk op te bouwen voor een vervolg aanvraag over de inzet van 3D technologieën in de mode-industrie.
The utilization of drones in various industries, such as agriculture, infrastructure inspection, and surveillance, has significantly increased in recent years. However, navigating low-altitude environments poses a challenge due to potential collisions with “unseen” obstacles like power lines and poles, leading to safety concerns and equipment damage. Traditional obstacle avoidance systems often struggle with detecting thin and transparent obstacles, making them ill-suited for scenarios involving power lines, which are essential yet difficult to perceive visually. Together with partners that are active in logistics and safety and security domains, this project proposal aims at conducting feasibility study on advanced obstacle detection and avoidance system for low-flying drones. To that end, the main research question is, “How can AI-enabled, robust and module invisible obstacle avoidance technology can be developed for low-flying drones? During this feasibility study, cutting-edge sensor technologies, such as LiDAR, radar, camera and advanced machine learning algorithms will be investigated to what extent they can be used be to accurately detect “Not easily seen” obstacles in real-time. The successful conclusion of this project will lead to a bigger project that aims to contribute to the advancement of drone safety and operational capabilities in low-altitude environments, opening new possibilities for applications in industries where low-flying drones and obstacle avoidance are critical.
Agricultural/horticultural products account for 9% of Dutch gross domestic product. Yearly expansion of production involves major challenges concerning labour costs and plant health control. For growers, one of the most urgent problems is pest detection, as pests cause up to 10% harvest loss, while the use of chemicals is increasingly prohibited. For consumers, food safety is increasingly important. A potential solution for both challenges is frequent and automated pest monitoring. Although technological developments such as propeller-based drones and robotic arms are in full swing, these are not suitable for vertical horticulture (e.g. tomatoes, cucumbers). A better solution for less labour intensive pest detection in vertical crop horticulture, is a bio-inspired FW-MAV: Flapping Wings Micro Aerial Vehicle. Within this project we will develop tiny FW-MAVs inspired by insect agility, with high manoeuvrability for close plant inspection, even through leaves without damage. This project focusses on technical design, testing and prototyping of FW-MAV and on autonomous flight through vertically growing crops in greenhouses. The three biggest technical challenges for FW-MAV development are: 1) size, lower flight speed and hovering; 2) Flight time; and 3) Energy efficiency. The greenhouse environment and pest detection functionality pose additional challenges such as autonomous flight, high manoeuvrability, vertical take-off/landing, payload of sensors and other equipment. All of this is a multidisciplinary challenge requiring cross-domain collaboration between several partners, such as growers, biologists, entomologists and engineers with expertise in robotics, mechanics, aerodynamics, electronics, etc. In this project a co-creation based collaboration is established with all stakeholders involved, integrating technical and biological aspects.
