Intergrading: Creating a Balanced Landscape, Integrating Food Production and Biodiversity in Agricultural Areas

The Netherlands has created a large nitrogen pollution problem in its soils, which is harming biodiversity. By intensifying and industrialized farming, by importing animal feed for dairy production and fertilizer for crop farming, too much nitrogen has accumulated in the soil. Consequently, ecological processes are disturbed due to...

Modifying a path into the shortest path

The inverse shortest path problem (ISPP) is a problem based on graph theory, that is to design link weights in a graph to satisfy that given paths are the shortest between the corresponding node pairs. It can be used in networks of complex systems to solve practical problems such as re-routing in transportation systems and reallocating resources...

HomeTree - Gamified tool to increase creative session engagement for participants with diverse backgrounds

A creative session is a lot more than a session of generating ideas. It’s part of a much larger goal of delivering innovation in a company. It is necessary to get everyone on board and motivated. And when the motivation levels reached, then beautiful things can happen. In order to achieve a certain motivation level, It’s imperative that people...

Implementing Circular Economy in the Built Environment: Comparative Study between China and the Netherlands

Circular economy is gaining global momentum as a new economic system to achieve sustainable development. The built environment plays an important role during the transition to a circular economy. China and the Netherlands share a common basis on enhancing resource efficiency by circular economy, which provides opportunities for mutual learning....

Suction Grasp Pose Planning Using Self-supervision and Transfer Learning

Planning grasp poses for a robot on unknown objects in cluttered environments is still an open problem. Recent research suggests that deep learning technique is a promising approach to plan grasp poses on unknown objects in cluttered environments. In this field, three types of data are used for training: (a) human labeled data; (b) synthetic...

From Non-place to H[ai]yper-place: Shanghai metro station design

Globalization and urbanization produce large amount of space, which cannot be defined as relational, or historical, or concerned with identity. This kind of non-places creates neither singular identity nor relations; only solitude and similitude, especially for those metropolises, like Shanghai. Shanghai is described as the place where eastern...

Learning state representations for robotic control: Information disentangling and multi-modal learning

Representation learning is a central topic in the field of deep learning. It aims at extracting useful state representations directly from raw data. In deep learning, state representations are usually used for classification or inferences. For example, image embedding that provides similarity metrics can be used for face recognition. Recent...

Personalized Microblog Search on Twitter

This thesis describes our approach to microblog search personalization. The approach uti-lizes implicit information about the user’s interests to personalize original search results. We first present how do we model users’ preferences on Twitter. Subsequently, we investi-gate different ways to represent search results so that they can be...