Context-based recommender system to provide cognitive support to online chat counsellors in the Helpline of 113 Suicide Prevention

STUDY OBJECTIVE: Suicide crisis chat counsellors work in an environment which de- mands high emotional and cognitive awareness. A shared opinion among counsellors is that as the chat conversation turns more difficult it takes longer and more effort to come up with a response. Supportive technology might resolve this ”writer’s block” by giving...

Understanding the relationship between user emotion and latent musical features

With the advent of Internet and resulting data boom, Recommender Systems have come to rescue by filtering the information available on the internet by providing us with relevant information. These systems come handy when one wants to listen to songs, watch movies or even buy products on the Internet. Primarily, these recommender systems used...

Camera Positioning and Vision-based Fall Detection

Elderly care residences often have falling incidents, sometimes with dire consequences. This project aims to implement a method for detecting when people fall, an issue that has seen much research and practical implementations already. In contrast to other work, this project aims to create a non-intrusive, non-wearable solution through the use...

Comparing Spreadsheets: A New Strategy for Analysis, Detection and Aggregation of Spreadsheet Differences

Comparing spreadsheet files is a new, unexplored research domain in computer science. Methods for regular file comparison are not straightforwardly applicable to spreadsheet files, because they are fundamentally different. Spreadsheets are binary files, the structure of spreadsheets is two-dimensional, they contain both data and calculations,...

Axiomatic Thinking in Neural IR: An axiomatic approach to diagnosing deep IR models

After surpassing human performance in the fields of Computer Vision, Speech Recognition and NLP, deep learning has been gaining scientific ground in IR. In spite of the sheer amount of publications that have proposed so-called neural IR approaches over the past decade, the field has not achieved the kind of progress seen in related fields. Over...

Faster Onboarding of Developers in Existing Codebases

When a new software developer joins bunq, a Dutch bank, (s)he will need some time to get familiar with the existing codebase. Preferably, the time necessary for the familiarisation is as short as possible. The faster the developer is up to speed, the faster (s)he can contribute to new features and help solving bugs. This research develops a...

Reservoir Characterization using a Geometric Approach

Quantifying the anthropogenic impacts such as reservoir characterization is a big challenge in the field of water management. In this work, a computer graphics based geometric approach is presented which can predict the underlying topology of large-scale reservoirs. The proposed algorithm uses freely available, satellite based landscape data of...

Leveraging Social Information To Improve Recommendation Novelty

In today’s digital world, users are often confronted with an abundance of information. Whether the user is looking to compare online prices for products, searching for new movies to watch or music to listen, the available information at hand exceeds the amount of information which the user wants to consider before making a choice. For this,...

Recognizing and Handling Negations in Machine Learning

In several machine learning problems, a relatively small subproblem is present in which combinations of (negating) objects or structures result in a negation or otherwise other classification compared to when these (negating) objects are not present. To be more specific, a variant of the XOR problem is present in a small amount of objects in...

Rituals of Leaving: Predictive Modelling of Leaving Behaviour in Conversation

In this thesis, leaving behaviour in a small group setting is studied. In the past, group conversations have mostly been studied in a static setting. Inclusion of a temporal dimension would be of use in numerous applications. In order to account for temporal elements, we must understand how group conversations evolve. Leaving and joining a...

Popularity-based Detection of Domain Generation Algorithms: Or: How to detect botnets?

In order to stay undetected and keep their operations alive, cyber criminals are continuously evolving their methods to stay ahead of current best defense practices. Over the past decade, botnets have developed from using statically hardcoded IP addresses and domain names to randomly-generated ones, so-called domain generation algorithms (DGA)....

Continuous Mutation Testing in Modern Software Development

Modern software is being built in a continuously integrated fashion, in order to overcome the challenges that come with developing large software systems from many contributors. The cornerstone of continuous integration is the testing step, since it is supposed to protect the system from changes that might disrupt correct behavior. Mutation...

Limits on Modeling Compensation in Multimodal DNNs for Audio Visual Speech Recognition

Speech is a natural way of communicating that does not require us to develop any new skills in order to be able to interact with electronic devices. With the evolution of technology, speech has become one of the primary means of communication. Speech recognition is a form of multimedia content analysis, where the information carried in a speech...

An Automated Language Translation System for Classical Music Titles

Muziekweb is the biggest source of music that has been released in the Netherlands. At this moment, all of their data is currently in Dutch. However, Muziekweb wishes their classical music titles to be translated to other languages as well. Since over 250.000 classical music titles exist, it is too much work to be done manually. Therefore,...