Minimize experimentation overhead through dataset selection, ensemble feature attention, and feature selection with reduced subset sizes

In large-scale ML, data size becomes a critical variable, especially in the context of large companies, where models already exist and are hard to change and fine-tune. Time to market and model quality are essential metrics, thus looking for ways to select, prune and augment the input data while treating the model as a black box can speed up the...

Tracing the Map: Exploring experimental cartographic alternatives and their potential contribution to the improvement of architectural surveying

Reducing waiting times at out-of-hours general practitioner departments: A data-driven simulation modelling and optimization study

The pressure on healthcare systems is increasing all over the world. With an ageing world population, the costs for healthcare and the shortages in medical staff are continually increasing. In the Netherlands, out-of-hours general practitioner departments, or ‘huisartsenposten’, suffer from this increasing pressure in their telephone triage...

Development of the Ford Concreate, a data immersion toolkit: Building data for better insights

This report describes the development of the Ford Concreate, a data immersion toolkit designed for the Innovation Management for Smart Vehicle Concepts team (design team) of Ford’s Research and Innovation Centre Aachen. The collaborative data physicalisation toolkit consists of three elements: an instruction process, the physicalisation tool and...

The analysis of three-dimensional embeddings in Virtual Reality

Dimensionality reduction algorithms transform high-dimensional datasets with many attributes per observation into lower-dimensional representations (called embeddings) such that the structure of the dataset is maintained as well as possible. In this research, the use of Virtual Reality (VR) to analyse these embeddings has been evaluated and...

Design with Data

In the emerging field of data science many exciting things are happening. Through the Internet of Things, health trackers and more we are collecting all kinds of data, that allow us to learn more about the world around us than we could have ever imagined. But how do we deal with this as designers? Why would we design with data, and how can we?...

Making IMPaCt: a blockchain based solution for consumer centred privacy control

The increase of data collection and analytics over the past few years the control over personal data has become an important issue. Control over data is the execution of privacy and the ability to protect the individual identity. Solutions to give consumers more control have failed in the past due to security and privacy concerns. On top of that...

The future of air cargo: Design of a solution to use sensor-based data to improve efficiency, transparency and communication for KLM Cargo’s employees and customers

Assignment - This report describes the design of solutions that enable KLM Cargo to add more value for its employees and customers using data generated by new technological opportunities. The scope for this report is on pharmaceutical shipments passing through KLM Cargo’s Schiphol hub, from acceptance to delivery, and focuses on addressing the...

The Value of Data for Philips Hospital to Home Solutions: A strategic design approach for creating shared value through integrated Chronic Care data solutions

This project analyzed the topic of what is the value of data for Hospital to Home (H2H) telehealth solutions focusing on chronic care in the Netherlands in order to deliver strategic design advice on what are interesting opportunities to explore in this field. The project focused on an analysis of the strategic situation of the company that...

Het modelgebaseerd corrigeren van meetdata (Model-based correction of data)

Tijdens het varen zijn er verschillende data gemeten. In deze data zitten fouten. Vanwege de fouten zijn er aannames opgesteld. De aannames worden getoetst. De data wordt gecorrigeerd, gebruikmakend van gewogen gemiddelden en kubische splines

Modeling the Cost Reduction of Master Data Management

Much research has been done on the advantages of Master Data Management (MDM) and the problems that poor MDM may cause. Much is also known about the importance of data quality. However little is known about quantifying and structuring the costs related to MDM. In this thesis the question ”How can the possible reduction of costs for organizations...

Vergelijking en implementatie van digitale signaalbewerkingstechnieken bij communicatie via leds