Fair AI: State-of-the-art overview of the literature

Supervised segmentation of NO2 plumes from individual ships using TROPOMI satellite data

The shipping industry is one of the strongest anthropogenic emitters of NOx—a substance harmful both to human health and the environment. The rapid growth of the industry causes societal pressure on controlling the emission levels produced by ships. All the methods currently used for ship emission monitoring are costly and require proximity to a...

Fair automated assessment of noncompliance in cargo ship networks

Hybrid AI: The Way Forward in AI by Developing Four Dimensions

In recent years, AI based on deep learning has achieved tremendous success in specialized tasks such as speech recognition, machine translation, and the detection of tumors in medical images. Despite these successes there are also some clear signs of the limitations of the current state-of-the-art in AI. For example, biases in AI-enabled face...

Prediction of long-term hospitalisation and all-cause mortality in patients with chronic heart failure on Dutch claims data: a machine learning approach

Appl.AI - Research strategy trustworthy adaptive AI

TNO Appl.AI is the branding for AI activities in the TNO units. Among these activities are TNO-wide science and technology research investments to further the capabilities and propositions that TNO can offer to its customers, research partners and other stakeholders. The goal of this Research Strategy document is to guide the investment...

Improving evaluation of NO2 emission from ships using spatial association on TROPOMI satellite data

Supervised temporal link prediction in large-scale real-world networks

Link prediction is a well-studied technique for inferring the missing edges between two nodes in some static representation of a network. In modern day social networks, the timestamps associated with each link can be used to predict future links between so-far unconnected nodes. In these so-called temporal networks, we speak of temporal link...

Understanding Dynamics of Truck Co-Driving Networks

The goal of this paper is to learn the dynamics of truck co-driving behaviour. Understanding this behaviour is important because co-driving has a potential positive impact on the environment. In the so-called co-driving network, trucks are nodes while links indicate that two trucks frequently drive together. To understand the network’s dynamics,...

Verantwoord datadelen voor AI

Idealiter is data vrij toegankelijk, maar de realiteit is vaak anders. De data houdt zich vaak op bij verschillende organisaties die zelfstandig keuzes maken over wie de data mag gebruiken en waarvoor. Data heeft waarde, en mag daarom soms niet of beperkt gedeeld worden. Er kunnen kosten mee gemoeid zijn met het beschikbaar stellen van de data....

Understanding behavioral patterns in truck co-driving networks

This paper examines the co-driving behavior of truck drivers using network analysis. From a unique spatiotemporal dataset encompassing more than 10 million measurements of trucks passing 17 different highway locations in the Netherlands, we extract a so-called co-driving network. In this network, nodes are truck drivers and edges represent pairs...

Imputation methods outperform missing-indicator for data missing completely at random

Finding Dutch natives in online forums

Law enforcement agencies have a restricted area in which their powers apply, which is called their jurisdiction. These restrictions also apply to the Internet. However, on the Internet, the physical borders of the jurisdiction, typically country borders, are hard to discover. In our case, it is hard to establish whether someone involved in...

The MediaMill TRECVID 2006 semantic video search engine

In this paper we describe our TRECVID 2006 experiments. The MediaMill team participated in two tasks: concept detection and search. For concept detection we use the MediaMill Challenge as experimental platform. The MediaMill Challenge divides the generic video indexing problem into a visual-only, textual-only, early fusion, late fusion, and...