- document
-
Wan, K.P. (author)Over the last few years machine learning has become popular among businesses. The insights and predictions given by the classifiers can help people make better decisions. The field of machine learning research is also highly active. Researchers frequently come up with clever tweaks or improvements that increase the accuracy of certain...master thesis 2016
- document
-
Bosch, B.C. (author)This thesis deals with improving an existing method that simulates the destruction of objects inside a game environment. The existing method combines physical- and geometry-based methods. The improved method uses a physically based method to calculated internal energy after an impact and uses the energy as a weight function to fracture the...master thesis 2016
- document
-
Ghiëtte, V.D.H. (author)This thesis focuses on the classification of behavioural aspects of scanners based on unroutable traffic collected from two /16 subnets. Firstly the study determines that the use of a smaller dataset achieves similar results and allows for the same correctness compared to larger ones. Secondly different scanning tools are analysed, and methods...master thesis 2016
- document
-
Schutter, A.S.C. (author)The role of military operators is changing towards supervision of multiple unmanned vehicles. This places new demands on the operators that require supportive systems. This study focused on the design of a system to support the user to allocate high-level tasks to unmanned vehicles for military operations and that respects the objectives and...master thesis 2016
- document
-
Dong, T. (author)Online social networks have been attracted considerable attentions and provided new channels for users to share and disseminate content, products, ideas and etc on the websites. With the advent of Internet, the user activities in online social networks can be easily tracked, which provide us with a extremely large scale of online data to study...master thesis 2016
- document
- Yu, Q. (author) master thesis 2016
- document
-
Swastanto, B.A. (author)Long-term time series forecasting has found many utilities in various domains. Nevertheless, it remains difficult to perform by many existing methods. One of the most well-known forecasting techniques, the ARIMA, does not suffice the long-term forecasting task due to the mean convergence problem. Therefore, this research empirically assesses the...master thesis 2016
- document
-
Kariotis, S. (author)Motivation: Reversible epigenetic modifications that happen on the DNA’s histones, namely histone modifications, play an important role in gene regulation by controlling the accessibility of different functional genomic regions. Such modifications have been measured and primarily studied on genes or their promoters, but a currently interesting...master thesis 2016
- document
-
Khan, M.S. (author)Human-robot collaborative act is obvious nowadays in a modern intervention room. It is very important to ensure the safety of the patient along with other personnel in the operation theater and prevent damages to the equipment during an intervention. Due to the complex environment and multiple unknown dynamic objects in the room, vision-based...master thesis 2016
- document
-
Albeda, J. (author)Affect-adaptive systems are dependent on their ability to automatically recognize a user’s affective state. This study aims to contribute to the creation of an affect-adaptive system that can recognize negative moods of elderly in care homes from a video feed, and improve it by adapting the lighting in the room. An affective database of videos...master thesis 2016
- document
-
Cuomo, A. (author)Motivation: Genome-wide association studies (GWAS) aim to uncover the genetic basis of traits and common diseases. Due to the large number of common variants, most studies use a single-locus approach. However, those fail to explain most of the heritability, especially for complex diseases. Epistatic interactions, where two or more loci have a...master thesis 2016
- document
-
Taal, F. (author)Designing realistic 3D content in a virtual urban environment is a hot topic and a challenge, specifically when including semantics to improve the realism of vegetation, buildings and roads. Road networks typically lack plausible signaling objects, unless they were inserted manually which is inefficient and time-consuming. This thesis presents a...master thesis 2016
- document
-
Cao, Y. (author)In neuroscience research, fMRI image analysis is a major approach to identify the relationships between brain region and behavior. fMRI provides delayed real time brain activity signals non-invasively. Spatial preprocessing and statistical analysis needs to be performed to find the brain region that is responsive to certain tasks or stimulations...master thesis 2016
- document
-
Peperkamp, J.B. (author)When performing a piece of music, there are certain ways in which performers turn the score into their own musical interpretation of it. The difference between what is written and what is played can be substantial, and can vary between performers and even individual performances. In this thesis we examine what information can be gained from...master thesis 2016
- document
- Corsini, F. (author) master thesis 2016
- document
-
Meijer, D.W.J. (author)In this work, we have shown that AdaBoost is prone to overfitting when the training set contains mislabeled objects. We proposed that this is in part because the error estimate used to weight base classifiers and (indirectly) objects is biased in this scenario. We have shown that an unbiased estimator can prevent the overfitting, but such an...master thesis 2016
- document
-
Li, B. (author)In a business network, a company may be encouraged to utilise a new technique when either its cooperators or its competitors have made their adoption. Nevertheless, its willingness can be reduced as more of its competitors start applying the new technique. Inspired by the this scenario, in this thesis we proposed a viral spreading model in...master thesis 2016
- document
-
Zhou, X. (author)Network science studies a complex system as a network to capture the connectivity patterns and topological features. Different network topologies have been observed to shape dynamic spread- ing processes on the network in various ways, while the exact relationship is complicated and not yet fully understood. Epidemic models are often applied to...master thesis 2016
- document
-
Viering, T.J. (author)In many settings in practice it is expensive to obtain labeled data while unlabeled data is abundant. This is problematic if one wants to train accurate (supervised) predictive models. The main idea behind active learning is that models can perform better with less labeled data, if the model may choose the data from which it learns. Active...master thesis 2016
- document
- Makrodimitris, S. (author) master thesis 2016