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.
DOCUMENT
While the Municipality of Amsterdam wants to expand the electric vehicle public charging infrastructure to reach carbon-neutral objectives, the Distribution System Operator cannot allow new charging stations where low-voltage transformers are reaching their maximum capacity. To solve this situation, a smart charging project called Flexpower is being tested in some districts. Charging power is limited during peak times to avoid grid congestion and, therefore, enable the expansion of charging infrastructure while deferring grid investments. This work simulates the implementation of the Flexpower strategy with high penetration of electric vehicles, considering dynamic and local power limits, to assess the impact on both the satisfaction of electric vehicle users and the business model of the Charging Point Operator. A stochastic approach, based on Gaussian Mixture Models, has been used to model different profiles of electric vehicle users using data from the Amsterdam public electric vehicle charging infrastructure. Several key performance indicators have been defined to assess the impact of such charging limitations on the different stakeholders. The results show that, while Amsterdam’s existing public charging infrastructure can host just twice the current electric vehicle demand, the application of Flexpower will enable the growth in charging stations without requiring grid upgrades. Even with 7 times more charging sessions, Flexpower could provide a power peak reduction of 57% while supplying 98% of the total energy required by electric vehicle users.
DOCUMENT
Report in English on the results of the international Master Class by Stadslab on intercultural park design. The case described is a design for for a park in Eastern Ukrainian city of Melitopol. A redevelopment strategy is proposed for its historic Gorky Park (1936). The book also contains essays by intercultural cities expert Phil Wood and introductions by Marc Glaudemans, Beatriz Ramo and Olexandr Butsenko.
DOCUMENT
Instead of using a passive AC power grid for low power applications, this paper describes a smart plug for DC networks that is capable of providing the correct power to a device (up to 100W) and that allows for communication between different plugs and monitoring of energy consumption across the DC network using the Ethernet protocol in conjunction with a signal modulator to adapt the signals to the DC network. The ability to monitor consumption on a device-per-device basis allows for closer monitoring of in-house energy use and provides an easily scalable platform to monitor consumption at a macro level. In order to make this paper attractive for the consumer market and easily integrable with existing consumer devices, a generally compatible solution is needed. To meet these demands and to take advantage of the trend of charging consumer devices through USB, we opted for the recently adapted USB Power Delivery standard. This standard allows devices to communicate with the plug and demand a specific voltage and current needed for the device to operate. The purpose of this paper is to give the reader insight in the development of a proof of concept of the smart DC/DC power plug. 10.1109/DUE.2014.6827761
DOCUMENT
This study presents an automated method for detecting and measuring the apex head thickness of tomato plants, a critical phenotypic trait associated with plant health, fruit development, and yield forecasting. Due to the apex's sensitivity to physical contact, non-invasive monitoring is essential. This paper addresses the demand for automated, contactless systems among Dutch growers. Our approach integrates deep learning models (YOLO and Faster RCNN) with RGB-D camera imaging to enable accurate, scalable, and non-invasive measurement in greenhouse environments. A dataset of 600 RGB-D images captured in a controlled greenhouse, was fully preprocessed, annotated, and augmented for optimal training. Experimental results show that YOLOv8n achieved superior performance with a precision of 91.2 %, recall of 86.7 %, and an Intersection over Union (IoU) score of 89.4 %. Other models, such as YOLOv9t, YOLOv10n, YOLOv11n, and Faster RCNN, demonstrated lower precision scores of 83.6 %, 74.6 %, 75.4 %, and 78 %, respectively. Their IoU scores were also lower, indicating less reliable detection. This research establishes a robust, real-time method for precision agriculture through automated apex head thickness measurement.
DOCUMENT
Public lighting’s primary purpose is nighttime visibility for security and safety. How to meet so many requirements of so many stakeholders? The key to developing a good plan is to relate lighting to functions of public spaces, because street lighting is more than a technical requirement, a security need, or a design element. It can be thought of and utilized in terms of how the type, placement, and wattage affect how a street is perceived and used. With present-day used street lighting systems however, flexibility is expensive, as is maintenance and energy consumption. A new solution is to use LED lighting with a Direct Current power system. Advantages are a decrease in: energy conversions; material use; amount of switch- boxes; components; labour costs and environmental comfort. The overall implementation of LED and DC will result in better control and efficient maintenance due to integrated bidirectional communication. A challenge is the relatively high investment for these new solutions. Another challenge; DC is not a standard yet in rules and regulations. In the paper the transition to direct current public lighting system will be described with all the pros and cons. A new concept of public ownership, to overcome financial challenges will be discussed. M Hulsebosch1, P Willigenburg2 ,J Woudstra2 and B Groenewald3 1CityTec b.v., Alblasserdam, The Netherlands 2The Hague University of Applied Sciences, The Hague, The Netherlands 3Cape Peninsula University of Technology, Cape Town, South Africa 10.1109/ICUE.2014.6904186
DOCUMENT
In recent years, drones have increasingly supported First Responders (FRs) in monitoring incidents and providing additional information. However, analysing drone footage is time-intensive and cognitively demanding. In this research, we investigate the use of AI models for the detection of humans in drone footage to aid FRs in tasks such as locating victims. Detecting small-scale objects, particularly humans from high altitudes, poses a challenge for AI systems. We present first steps of introducing and evaluating a series of YOLOv8 Convolutional Neural Networks (CNNs) for human detection from drone images. The models are fine-tuned on a created drone image dataset of the Dutch Fire Services and were able to achieve a 53.1% F1-Score, identifying 439 out of 825 humans in the test dataset. These preliminary findings, validated by an incident commander, highlight the promising utility of these models. Ongoing efforts aim to further refine the models and explore additional technologies.
MULTIFILE
Adverse Outcome Pathways (AOPs) are conceptual frameworks that tie an initial perturbation (molecular initiat- ing event) to a phenotypic toxicological manifestation (adverse outcome), through a series of steps (key events). They provide therefore a standardized way to map and organize toxicological mechanistic information. As such, AOPs inform on key events underlying toxicity, thus supporting the development of New Approach Methodologies (NAMs), which aim to reduce the use of animal testing for toxicology purposes. However, the establishment of a novel AOP relies on the gathering of multiple streams of evidence and infor- mation, from available literature to knowledge databases. Often, this information is in the form of free text, also called unstructured text, which is not immediately digestible by a computer. This information is thus both tedious and increasingly time-consuming to process manually with the growing volume of data available. The advance- ment of machine learning provides alternative solutions to this challenge. To extract and organize information from relevant sources, it seems valuable to employ deep learning Natural Language Processing techniques. We review here some of the recent progress in the NLP field, and show how these techniques have already demonstrated value in the biomedical and toxicology areas. We also propose an approach to efficiently and reliably extract and combine relevant toxicological information from text. This data can be used to map underlying mechanisms that lead to toxicological effects and start building quantitative models, in particular AOPs, ultimately allowing animal-free human-based hazard and risk assessment.
DOCUMENT
The Johan Cruijff ArenA (JC ArenA) is a big events location in Amsterdam, where national and international football matches, concerts and music festivals take place for up to 68,000 visitors. The JC ArenA is already one of the most sustainable, multi-functional stadia in the world and is realizing even more inspiring smart energy solutions for the venue, it’s visitors and neighbourhood. The JC ArenA presents a complex testbed for innovative energy services, with a consumption of electricity comparable to a district of 2700 households. Thanks to the 1 MWp solar installation on the roof of the venue, the JC ArenA already produces around 8% of the electricity it needs, the rest is by certified regional wind energy.Within the Seev4-City project the JC ArenA has invested in a 3 MW/2.8 MWh battery energy storage system, 14 EV charging stations and one V2G charging unit. The plan was to construct the 2.8 MWh battery with 148 2nd life electric car batteries, but at the moment of realisation there were not enough 2nd life EV batteries available, so 40% is 2nd life. The JC ArenA experienced compatibility issues installing a mix of new and second-life batteries. Balancing the second-life batteries with the new batteries proved far more difficult than expected because an older battery is acting different compared to new batteries.The EV-based battery energy storage system is unique in that it combines for the first time several applications and services in parallel. Main use is for grid services like Frequency Containment Reserve, along with peak shaving, back-up services, V2G support and optimization of PV integration. By integrating the solar panels, the energy storage system and the (bi-directional) EV chargers electric vehicles can power events and be charged with clean energy through the JC ArenA’s Energy Services. These and other experiences and results can serve as a development model for other stadiums worldwide and for use of 2nd life EV batteries.The results of the Seev4-City project are also given in three Key Performance Indicators (KPI): reduction of CO2-emission, increase of energy autonomy and reduction in peak demand. The results for the JC ArenA are summarised in the table below. The year 2017 is taken as reference, as most data is available for this year. The CO2 reductions are far above target thanks to the use of the battery energy storage system for FCR services, as this saves on the use of fossil energy by fossil power plants. Some smaller savings are by replacement of ICEby EV. Energy autonomy is increased by better spreading of the PV generated, over 6 instead of 4 of the 10 transformers of the JC ArenA, so less PV is going to the public grid. A peak reduction of 0.3 MW (10%) is possible by optimal use of the battery energy storage system during the main events with the highest electricity demand.
DOCUMENT
We need mental and physical reference points. We need physical reference points such as signposts to show us which way to go, for example to the airport or the hospital, and we need reference points to show us where we are. Why? If you don’t know where you are, it’s quite a difficult job to find your way, thus landmarks and “lieux de memoire” play an important role in our lives.
LINK
