Scriptiebank overzicht

Metacognition, the ability to think about one's thinking processes, is vital for
professional performance, academic achievement, and mental health. However, its
ambiguous nature and subjective measurement techniques across various fields have
posed significant challenges to research. Cognitive neuroscience offers a unique
solution by providing objective measurements that link metacognition to brain activity,
thereby establishing a ground truth. Recently, the convergence of explainable artificial
intelligence (XAI) and perceptual decision-making, a subsection of metacognition
within cognitive neuroscience, has led to the development of the WaveFusion
framework. This innovative framework holds the potential to contribute to the
unification of the fragmented metacognition research fields.
The aim of this thesis was to enhance the WaveFusion framework, an explainable
deep learning model, to classify metacognitive sensitivity and confidence using EEG
data. The objectives were (1) to achieve a classification accuracy of 95% for
metacognitive sensitivity, (2) to improve the accuracy for metacognitive confidence to
97.5%, and (3) to identify key ambiguities and limitations in metacognition research.
This study utilized an EEG dataset with event-related potentials (ERP) responselocked for type 1 decisions. Data preprocessing addressed dataset imbalances
through augmentation and balanced batch sampling. EEG samples were transformed
into spectrograms and processed using the deep learning architecture comprising a
Lightweight Convolutional Neural Network (LWCNN), a Squeeze and Excitation
Network (SEN), and a classification network. The model was pre-trained using Subject
Aware Contrastive loss (SAC) and trained with binary cross-entropy loss. SEN
facilitated the models explainability by visualizing the created attention weights
through topoplots, providing insights into brain areas used for classification.
The WaveFusion model achieved high classification accuracy, reaching 99.7% for
metacognitive confidence and 99.1% for metacognitive sensitivity. These
improvements were due to a larger selection of electrodes, response-locked ERP
data, and increased dataset size. The WaveFusion model not only demonstrates high
classification accuracy but also offers enhanced explainability. This allows the
framework to contribute to three major ambiguities: (1) the relationship between
metacognition and executive functions, (2) its connection to consciousness, and (3)
the domain generality of metacognition. By leveraging the WaveFusion framework, we
can overcome limitations in cognitive neuroscience research through (1) utilizing
transfer learning to compare relationships, (2) employing automatic classification to
investigate ecological validity, and (3) expanding the framework for multimodality to
integrate insights across various fields.
Future research should focus on increasing data variability, addressing outlier
performances, and improving interpretability through advanced visualization
techniques to enhance the WaveFusion model’s robustness and applicability across
cognitive neuroscience domains.

In deze studie wordt met behulp van convolutionele neurale netwerken (CNN’s) een geautomatiseerd scoresysteem ontwikkeld dat radiologen ondersteunt in het opsporen en opvolgen van erosieve artrose.

Solar power forecasting is essential for optimizing energy use in residential households.
Machine learning models are promising for this power forecasting because they can
capture its non-linear characteristics. Nonetheless, these models require a significant
amount of data that is unavailable for new installations. To overcome the limited
data availability, this thesis proposes a transfer learning model using Long ShortTerm Memory (LSTM) networks trained on synthetic photovoltaic (PV) generation
provided by the Photovoltaic Geographical Information System. Using the metadata
about a PV installation, this synthetic data simulates the past production of the
new PV installation. The model utilizes Numerical Weather Predictions (NWP)
and autoregressive covariates. This proposed model is compared to benchmarks,
including models trained only on sites’ actual PV power, physical models, and TL
models with no weather covariates.
The research investigates the effect of physics-informed variables on the accuracy
of transfer learning. Furthermore, it examines the usage of reanalysis data to train
with synthetic PV data due to the low accessibility of historical Numerical Weather
Prediction output. Walk-forward validation is employed for forecasting the actual
PV power to simulate real-life conditions and the impact of increasing target data.
The results demonstrate that models trained with historical Numerical Weather
Prediction data achieve higher zero-shot forecasting accuracy. Contrary to expectations, including physics-informed variables did not enhance performance; in fact,
it showed a slight decrease. Additionally, models trained on reanalysis data catch
up with those trained on historical NWP data once limited target data becomes
available.
Discussion highlights include the impact of Storm Darcy in February 2021, which
caused instability in machine learning models and the suitability of other ML models.
The proposed LSTM-based transfer learning model can provide accurate forecasts
even with no or limited actual PV power data, proving its potential for practical
applications in solar power forecasting for residential households.

Deze scriptie bevat onderzoek naar meer efficiënte en routinematige screening en kwantificatie-methoden voor Pyrrolizidine-alkaloïden in commerciële thee preparaten.

Een enorm voorgetraind taalmodel (GPT2) wordt gebruikt om elektro-encefalografie te classificeren. Zo wordt nagegaan of er een verband is tussen taal en elektrische hersengolven, in de hoop inzicht te krijgen in algemene hersengolf patronen.

Een data-efficiënte controle-eenheid is ontworpen met behulp van reinforcement learning en gebruik makend van transfer learning om zo een optimale controle te realiseren op het laagspanningsnetwerk. Als flexibiliteitsbronnen worden batterijen en zonnepanelen gebruikt.

Hoe zorg je ervoor dat zelflerende algorithems ook echt slimmer worden en efficienter functioneren. Deze master-thesis beschrijft een theoretisch en praktisch onderzoek hoe je dit zou kunnen doen en waar je op moet letten zodat algorithmes kunnen leren van eerdere ervaringen.

Een brein-computer interface (BCI) is een input-output systeem dat ervoor zorgt dat de gebruiker
een bepaald computersysteem kan aansturen via zijn hersenen. Dit systeem is echter heel
persoonsgebonden, waardoor de gebruiker een lange kalibratietijd moet doorgaan van 20 tot 30
minuten. Daar dit veel concentratie en tijd van de gebruiker vergt, is dit niet gewenst. In deze thesis wordt een methode voorgesteld om deze langdurige kalibratietijd te verminderen met behoud van een hoge accuraatheid.

Bachelorproef“Een verkennende studie van de nodige voorwaarden voor het bereiken van een kwaliteitsvolle therapeutische rijervaring of rijproces door alle belanghebbenden, zijnde: cliënt, ouders, coach en paard.”De wisselwerking tussen coach, cliënt, paard en ouders in Equine Assisted Interventions binnen, Festina Lente Foundation, IerlandVan jongs af aan zit ik tussen de pony’s en paarden. Ik ben er net niet op geboren. Toen ik in het zesde middelbaar zat besloot ik om op Hogeschool een sociale richting te volgen. Het werd Orthopedagogie.