Search

Commissioned by Jaarbeurs I created a model for predicting the number of leads specific content would generate in an online content marketing setting. I will describe how I addressed this problem and what methodology I used (Chapter 1). I will give an extensive overview of the data model I created and how I used imputation, feature engineering and feature selection to get the most out of the data (Chapter 2). In chapter 3, I will elaborate on the theoretical background of linear regression, logistic regression and survival analysis. In chapter 4 the experiment setup and results of the models just using content data are discussed. A classification model is constructed to predict if a user would download certain content. This model is extended with features which describe a match between the user and the content (chapter 5). Survival analysis is used to make predictions depending on time. The newsletter data is added using time-dependent covariates (chapter 6). In chapter 7, the results are discussed and a conclusion is drawn.

Item does not contain fulltext, BACKGROUND: Mucopolysaccharidosis III (MPS III), known as Sanfilippo disease, is a lysosomal storage disorder mainly characterized by progressive neurodegeneration with cognitive decline and relatively attenuated somatic signs and symptoms. Although short stature is invariably present in patients with the other mucopolysaccharidoses, it has not been sufficiently addressed in MPS III. The aim of this study was to investigate growth data of a large Dutch MPS III cohort in order to construct growth charts for MPS III patients. METHODS: Height, weight, head circumference (HC), and body mass index (BMI) data from 118 MPS III patients were used to construct reference curves, using the lambda, mu, sigma (LMS) method. Genotype-group comparisons for height standard deviation scores (SDS) were performed by Kruskal-Wallis analysis for different age groups. RESULTS: Birth weight and length were within normal ranges for gestational age and showed a significantly stunted growth from age 6 years onward. Mean final heights were 169.7 cm (-2.0 SDS) and 165.4 cm (-0.84 SDS) for adult male and female, patients, respectively. Phenotypic severity, as assessed by genotyping, correlated with growth pattern and final height. In addition, mean BMI and HC SDS were significantly higher when compared with Dutch standards for both boys and girls. CONCLUSIONS: Growth in MPS III is stunted mainly in patients with the severe phenotype. We provide disease-specific growth references that can be used for clinical management of MPS III patients and may be of value for future treatment studies.

Contains fulltext : 96665.pdf (publisher's version ) (Closed access), The clinical phenotype of congenital disorders of glycosylation is heterogeneous, mostly including a severe neurological involvement and multisystem disease. We identified a novel patient with a galactosyltransferase deficiency with mild hepatopathy and coagulation anomalies, but normal psychomotor development. The tissue-specific expression of the defective B4GALT1 gene correlated with the clinical phenotype.

Contains fulltext : 86980.pdf (publisher's version ) (Closed access)

11th International Workshop on Telework, Fredericton ,Canada, 28 augustus 2006, Contains fulltext : 46819.pdf (publisher's version ) (Open Access)

De gehalten aan zink en cadmium in de landbouwbodems rond zinkfabriek bij Budel liggen beduidend te hoog. Dit was aanleiding om onderzoek te doen naar de gehalten in bodem en daarmee te hoge gehaltes in de gewassen gras en maïs