Epilepsy is a common neurological disorder, but its diagnosis remains difficult when screening EEGs lack interictal epileptiform discharges (IEDs). Intermittent photic stimulation (IPS) can reveal abnormal responses associated with epilepsy; however, its clinical interpretation is often subjective, inconsistent, and sometimes inconclusive. This thesis explores the automatic classification of EEG responses to IPS using machine learning to improve diagnostic accuracy and reliability. Two datasets are analysed: the Temple University Hospital (TUH) Epilepsy Corpus and clinical recordings from Erasmus MC. A structured pipeline is developed, comprising preprocessing, feature extraction across temporal, spectral, wavelet, and connectivity domains, and classification with interpretable models such as XGBoost and ensemble approaches. To ensure robust generalization, leave-one-subject-out cross-validation is employed. This work demonstrates that IPS EEG segments contain informative features capable of distinguishing epileptic from nonepileptic patients, even in the absence of IEDs, thereby aiding early diagnosis and reducing the risk of misdiagnosis. Furthermore, the use of explainability tools highlights candidate electrophysiological markers, providing valuable insights and suggesting new hypotheses for future investigation.

Gallium Nitride High Electron Mobility Transistors (GaN HEMTs) are promising devices for next-generation power electronic systems due to their high efficiency, high power density, and broad applicability in areas including electric vehicles, renewable energy, and communication. Existing studies on Prognostic and Health Management (PHM) of GaN HEMTs focus on the statistical behaviors of multiple devices under specific circumstances, which means individual device variability is neglected in these approaches. This work addresses the gap in individual health status by applying deep learning to achieve the Remaining Useful Lifetime (RUL) prediction of individual p-type GaN HEMT devices under diverse working conditions. In the proposed method, a Temporal Convolutional Network (TCN) integrated with attention mechanisms is developed to extract informative features and emphasize critical features within the measurements. To handle the varying lifetimes of p-GAN HEMT devices tested under different temperatures and stress voltages, we propose a prediction pipeline, which estimates the relative RUL in percentage and then converts it into absolute RUL in seconds. The Leave-One-Group-Out (LOGO) Cross-Validation (CV) is applied to ensure the generalization of the proposed method by testing the model on data collected from the unseen environment.

With the growing developments in Artificial Intelligence (AI), deep learning models have become an attractive solution for industrial applications such as machine health monitoring and predictive maintenance. To enable real-time analysis and reduce reliance on cloud infrastructure, it is often more practical to process sensor data directly on edge devices. However, while deep learning models offer improved performance, their high memory and computational demands often exceed the limited resources of edge devices. Moreover, compression requires a lot of hyperparameter tuning, which is unique for each model, layer, and application. To address these limitations, this work utilizes dynamic Bayesian compression, which reduces model size and computational costs. By introducing learnable gate variables that control the quantization precision and the rank of decomposed factors, the model can adaptively determine the most efficient configuration for each layer during training. This results in a more flexible, end-to-end trainable compression scheme that maintains performance while significantly improving deployability on edge devices.

With the rapid development of industrial systems, the demand for stability, reliability, and robustness has become increasingly critical. Fault detection has emerged as a key research area, aiming to prevent unexpected failures and performance degradation. Recent advances in feature extraction techniques and machine learning have enabled the development of intelligent, autonomous fault detection systems.

This thesis proposes two Transformer-based models for motor fault detection. The first is a supervised classification model that incorporates discrete wavelet transform (DWT) to decompose time-series signals into multi-scale components, which are then processed by Transformer-based architectures to extract features for classification. Two structural variants are explored: one using masked attention over concatenated coefficients, and another employing upsampling and linear attention for efficient fusion. The second approach is an unsupervised forecasting-based model, where only normal samples are used for training. At inference time, samples are classified based on whether their forecasting error exceeds a threshold determined via ROC curve analysis on a validation set.

Experiments conducted on the JKU and CWRU datasets demonstrate the effectiveness of both approaches. The classification-based method achieves high accuracy in distinguishing between fault types, while the forecasting-based method shows strong robustness to previously unseen fault categories without retraining. The findings indicate that the models are capable of capturing informative temporal patterns for fault detection, showing promise for further exploration in real-world settings.

Short-term precipitation forecasting, or nowcasting, plays a vital role in mitigating the impacts of extreme weather by supporting timely decisions in urban planning, flood management, and transportation systems. In this thesis, we cast precipitation nowcasting as a video prediction problem, where the goal is to generate future radar images given a sequence of past observations. To address this, we propose BlockGPT, a generative transformer model that predicts entire frames autoregressively, capturing spatial dependencies within each frame using bidirectional attention, while maintaining temporal causality across frames. BlockGPT is evaluated on two real-world radar datasets: KNMI (Netherlands) and SEVIR (United States), across two forecasting tasks involving different temporal resolutions. The model is benchmarked against existing state-of-the-art approaches-NowcastingGPT and Diffcast-which represent token-based and diffusion-based paradigms, respectively. Our results show that BlockGPT offers competitive performance and strong capabilities in detecting and localizing significant rainfall events, while also enabling faster inference. These properties make it a promising candidate for real-time, threshold-aware weather forecasting systems.

The current Electronic Design Automation (EDA) tools focus on a component-level design perspective, based on modifying its physical dimensions and electrical parameters. Although this approach works, this forces a design space that often becomes unmanageable, leading to an excessive brute-force solution that results in an unnecessary overuse of resources. This thesis proposes an approach for the detection of fundamental subcircuit structures, also known as functional structures or primitives, contributing to the compartmentalization of the design space and thus to the Analog Design Automation Flow. The classification and detection of these structures is not trivial, and it has become a major challenge for future development. Some previous proposed approaches have demonstrated an overall good detection ratio, yet with non realistic limitations in such a diverse field as analog design, including its complexity in time or high number of primitive variations, among others. This thesis proposes a new approach for the identification of components functionality using Graph Neural Networks (GNN). The proposed scheme uses a node classification problem approach together with a compound graph, enabling the functionality detection of each transistor in the circuit. This detection is based on a sub-graph isomorphism subsystem, which annotates the information during the creation of the dataset. This differs from other previous approaches, such as graph classification or linking prediction, being one of the firsts in its kind. This system has reached an accuracy of > 97% in component classification, even with unbalanced data, being easily expansible, robust and scalable. Future work will focus on the incorporation of more complex data within the proposed flow using NXP data, and the study of a topology identification approach, so that 100% can be reached.

Surgical workflow analysis is crucial in optimising procedural efficiency, resource utilisation, and patient safety in catheterisation laboratories. Traditional manual work- flow analysis methods are labour-intensive and prone to inconsistencies, prompting the need for automated solutions that leverage machine learning and computer vision. This thesis presents an explainable two-stage model for surgical workflow analysis using ceiling-mounted cameras. The proposed approach integrates a YOLOv8 object detection model with a Gaussian Mixture Model - Hidden Markov Model (GMM-HMM) framework. The first stage detects key objects that serve as input to the second stage. The GMM-HMM component then infers surgical workflow phases by modelling spatial and temporal dynamics, enabling real-time phase classification. The model is validated on two datasets from different hospitals, achieving a classification accuracy of 95.2% for the RdGG dataset and 95.4% for the HH Tampere dataset, ensuring its generalisability across diverse clinical environments. Experimental results demonstrate that the model achieves high accuracy in detecting workflow phases, with an emphasis on explain- ability and robustness. The combination of YOLOv8’s efficient object detection with GMM-HMM’s structured temporal inference ensures that phase transitions are identified with minimal error. The model’s real-time feasibility and generalisation across hospitals highlight its potential for clinical implementation. This research advances automated surgical workflow analysis by addressing the dual challenges of interpretability and adaptability. Future work includes enhancing the model’s robustness to occlusions, integrating additional modalities such as audio data, and exploring its application in other surgical environments.

This project addresses the challenge of monitoring large, dynamic classrooms by proposing a privacyoriented multimodal data acquisition system tailored for MMLA. Traditional learning analytics rely on unimodal data and fail to capture complex classroom interactions. In contrast, MMLA leverages multiple data sources to better understand learning behaviors. Current systems lack adaptability, userfriendliness, and privacy considerations, impeding their integration into classrooms. The proposed system comprises static and dynamic nodes, with dynamic nodes worn by individuals and static nodes strategically placed in classrooms. Data features, selected on MMLA relevance, are transmitted wirelessly to the static node for storage and analysis. Privacy is prioritized by avoiding sensitive data collection and adhering to GDPR guidelines. The design ensures adaptability, supporting additional sensors and seamless integration into various educational settings. This foundational system enables future research while addressing ethical and technical challenges in large-scale classrooms.

Psychiatric disorders are highly prevalent among adolescents, yet current diagnostic processes largely depend on time-intensive interviews and subjective assessments. Objective, scalable, and non-invasive tools are urgently needed to support early detection and monitoring. Speech acoustics represent a promising biomarker, as subtle variations in pitch, rhythm, and fluency may reflect underlying psychiatric symptoms.

This thesis investigates whether acoustic features of adolescent speech can be used to classify psychiatric symptoms through machine learning. The longitudinal iBerry study, which followed a large cohort of adolescents in the Rotterdam area, was used. Speech samples from semi-structured interviews were combined with self-reported questionnaires, including the Youth Self-Report (YSR) and the PQ-16 psychosis screener. Acoustic features were extracted using different established open-source toolkits and reduced via minimum redundancy maximum relevance (mRMR) selection. Three machine learning models—Random Forest, XGBoost, and Support Vector Machines—were trained using cross-validation, class weighting, and oversampling techniques to address class imbalance. Model performance was evaluated using F1-score, weighted accuracy, precision-recall curves and receiver operating characteristic (ROC) analyses. Fairness checks were performed to assess the influence of age and sex.

Results showed that predictive performance across most symptom domains was modest, with weighted accuracies generally only slightly above 50\% and F1-scores often low due to imbalanced data. Broader constructs, such as internalising and total problem scores, were somewhat better captured than narrow symptom subscales. These findings indicate that speech acoustics alone may be insufficient for reliable clinical classification, though they may still contribute as one element within a multimodal assessment strategy.

Beyond technical performance, this study highlights important methodological, ethical, and clinical considerations. Class imbalance, developmental changes in adolescent voices, and reliance on self-reported outcomes constrain model performance. At the same time, issues of bias, transparency, and privacy raise challenges for clinical implementation. Future research should focus on assembling larger and more diverse datasets, incorporating longitudinal monitoring, and integrating multimodal data sources such as linguistic or physiological measures. By addressing these challenges, speech-based models may eventually provide valuable tools to support scalable and objective psychiatric assessment.

Introduction and Research Goal: Epilepsy is a common neurological disorder that severely impacts patients’ quality of life. Current diagnostic standards rely on the presence of seizures or interictal epileptiform discharges (IEDs) in the electroencephalogram (EEG). However, some patients who are ultimately diagnosed with epilepsy do not present with seizures or IEDs on their initial EEG, which delays their diagnosis and appropriate medical treatment. Previous studies by Thangavel et al. 2022 and Mirwani 2024 suggest the potential of machine learning methods applied to IED-free EEGs for classifying epilepsy. The aim of this study is to evaluate whether adding clinical characteristics and visual EEG interpretation to existing machine learning models based on quantitative EEG improves the performance of these models for the identification of epilepsy in IED-free EEGs. Additionally, the study explores model interpretability to promote clinical application.
Methods: We focus on subjects who presented at the emergency room following a first clinical seizure and were not diagnosed with epilepsy based on their initial EEG. Ten quantitative EEG feature sets based various mathematical transforms were readily available from previous research by Mirwani 2024. EXtreme Gradient Boosting (XGBoost) models were trained using Leave-One-Subject-Out Cross-Validation (LOSO CV) on these feature sets as benchmark models. Model performance was assessed using the Area Under the Curve (AUC). Clinical and EEG report features were added individually to each quantitative EEG feature set to evaluate their added value to model performance. The best performing clinical and report features for each quantitative EEG feature set were determined using a two-fold grid search, and significance was tested via Welch’s t-test. Ensembles were created from the best performing models of each quantitative EEG feature set including their best performing clinical and report features. SHapley Additive exPlanations (SHAP) and XGBoost feature importance were used for model interpretation, while Bayesian statistics were applied to gain insight into clinical implementation.
Results: The best performing clinical and report features varied across EEG feature sets and did not consistently yield significant performance gains. Only the addition of EEG background to graph metrics of phase lock values showed a significant increase in model performance. SHAP analysis identified residual focal sharp activity as the primary contributor to this improvement. Combining individual models into ensembles substantially improved performance, achieving AUCs up to 0.870. To align model performance interpretation to the guidelines of the ILAE, sensitivity at P(posterior) ≥ 0.6 was proposed as a key evaluation metric. The best XGBoost model with clinical and report features achieved 0.48 sensitivity at P(posterior) = 0.6, while the best ensemble attained 0.81.
Conclusion: Incorporating clinical and report features into XGBoost models based on quantitative EEG data does not consistently improve the detection of epilepsy based on IED-free EEGs. The variability of the best performing clinical and report features across quantitative EEG feature sets suggests that their impact is dependent on the quantitative EEG feature sets. Combining individual models into ensembles significantly enhances performance, achieving a sensitivity of 0.81 at P(posterior) ≥ 0.6. However, external validation is required to confirm these findings. Future models should assess model performance according to the sensitivity at P(posterior) ≥ 0.6 to comply with ILAE guidelines.

Automated diagnosis of epilepsy for differentiating epileptic EEGs without Interictal Epileptic Discharges (IEDs) from normal EEGs remains a critical challenge in clinical settings.
Current state-of-the-art methods use algorithms that can effectively detect epilepsy seizures which improves the current treatment methods for people suffer from epilepsy. Electroencephalograms (EEGs) analyzed by neurologists which are not able to meet the criteria are further looked into to obtain an efficient classification. This thesis presents an automated epilepsy diagnosis approach using a multi-algorithmic feature extraction pipeline. The final models include the development of a robust multi-processing feature extraction pipeline, the application of advanced machine learning / deep learning algorithms, and the validation of the proposed methods on comprehensive EEG datasets. The results, achieved using an XGBoost classifier with leave-one-subject-out (LOSO) cross-validation, demonstrate comparable performance to state-of-the-art epilepsy detectors. The study emphasizes the detection of epilepsy without IEDs, optimizing models through nested cross-validation, and evaluates their performance on the Temple University Hospital (TUH) and Erasmus Medical Center (EMC) Rotterdam datasets.

This report presents the design process of a project aimed at the automatic recognition of 3D structures formed by magnetic spheres in a turbulent water-filled cylinder. This field of research holds promise for future technologies, as macroscopic self-assembly might be the key to three-dimensional storage on chips. With the macroscopic setup, the microscopic self-assembly process is imitated. To automatically recognise a 3D structure, this report is divided into three subgroups that research the optimal test setup, develop an image processing program and create a deep learning model. A labelled result of the 3D formation will be outputted, all while limiting the data size, computation time and inaccuracies. The subgroup responsible for the setup and the underlying physics produces images of the magnetic spheres forming a structure in the test setup. The Image Processing subgroup extracts the properties of the spheres from the image. Finally, the subteam for deep learning, in combination with data management, gives the extracted properties as input to a neural network model, which determines the structure of the spheres. Each submodule has demonstrated successful functionality on its own. However, due to time constraints, a fully integrated system with high accuracy has not been achieved yet. Future work will involve expanding the dataset to enhance the robustness of the recognition algorithms.

Intense precipitation can have extensive economic outcomes, from disrupting outdoor activities to causing severe infrastructural damage, such as landslides, and endangering public safety. The urgency to mitigate these impacts underscores the need for improved early warning systems. Enhanced short-term weather prediction, or nowcasting, is critical for addressing these severe weather events effectively. Traditional meteorological forecasting methods, while foundational, are often constrained by simplistic physical assumptions and fail to capture the complex, nonlinear patterns of intense weather events. These methods also struggle with high computational demands and lack the resolution needed to detect crucial microscale atmospheric phenomena for accurate short-term forecasts.
To address these challenges, this research introduces a novel deep learning approach utilizing a streamlined architecture that combines a Vector Quantized Variational Autoencoder (VQVAE) and an Autoregressive (AR) Transformer. This model aims to predict weather conditions up to 180 minutes ahead, using data analyzed at 30-minute intervals. The proposed model displays comparable performance with the state-of-theart conventional methods and other deep learning nowcasting models in predicting precipitations and sometimes extreme events. This study seeks to enhance forecasting accuracy and efficiency, providing valuable contributions to the field of meteorological nowcasting.

This report serves to finalize the bachelor graduation project on the topic of self-supervised federated learning, specifically the implementation of the algorithms in Python. The goal of the project is to implement a self-supervised learning setup in a decentralized approach using Field-Programmable Gate Arrays (FPGAs) for the processing of data. This serves as a proof of concept that decentralized machine learning on unlabeled data using FPGAs is possible. Multiple algorithms based on the literature were considered to allow for a low-profile learning setup, with simplifications done to be able to reduce the compute required. The results are promising: scaled-down models that can run on an FPGA show that self-supervised learning functions as expected from the theory. By decentralizing the computations increases in performance are possible in favorable conditions. The authors hope that the concept of self-supervised federated learning can be employed to FPGAs on a larger scale to help in the processing of the abundant yet underutilized unlabeled data present at the edges of information networks.

This thesis serves to finalise the bachelor graduation project on the topic of self-supervised federated learning, specifically the on-chip implementation of the algorithms. The goal of the project is to implement a self-supervised learning setup in a decentralised approach using Field-Programmable Gate Arrays (FPGAs) for the processing of data. In this thesis, we endeavour to illustrate the possibility of employing FPGAs to move the fairly compute-intensive self-supervised learning algorithms to the edge. We have developed a number of modules that can accelerate key algorithmic blocks that underlie the major bottlenecks of the classical application of the algorithms and showcase prospective results, which are extensively discussed afterwards to pave a clear path towards truly autonomous and efficient edge-intelligence.

Introduction: Heart failure (HF) poses a significant burden on public health. This can be largely attributed to recurrent hospitalizations in consequence of HF decompensation. Detection of early signs of impending fluid retention may facilitate timely medical intervention and thereby prevent hospitalizations. Monitoring of Cardiac Implantable Electronic Devices (CIEDs)-derived parameters has been proposed as promising solution, as the sensor inherent in CIEDs provide the ability to continuously monitor physiological signals. The aim of this study was to develop personalized machine learning (ML) models that can identify upcoming HF decompensation based on CIED-derived parameters. Methods: Two ML models, a support vector classifier (SVC) and an extreme gradient boosting (XGBoost) model, were developed for all patients. Features known to be associated to HF decompensation were extracted from daily CIED data. The output of the models is the daily classification of the patient’s HF status, either ‘stable’ or ‘unstable’. Model performance was evaluated through area under the precision-recall curve (AUPRC). First, the models were tested on a development dataset with leave-one-out cross-validation, and subsequently on an independent test set. Results: In total, for 62 patients two models were developed. The average AUPRC on the independent test set of the XGBoost models was 0.63 ± 0.28 and of the SVC models was 0.57 ± 0.26. Finally, for each patient, the model that resulted in the highest AUPRC was selected. The final models achieved an AUPRC on the independent test set of 0.61 ± 0.28. Conclusion: The findings of this study show promising results for the use of personalized CIED-derived models. However, significant variability in model performance across patients highlight the need for further research.

Introduction
Opioids are vital for pain management but are highly addictive and may lead to opioid-induced respiratory depression (OIRD), which is the primary cause of death related to both prescription and illicit opioid use. This study employed unsupervised machine learning (ML) to examine potential changes in cluster patterns post-opioid administration and their relationship with respiratory depression levels. Additionally, comprehensive data analysis was conducted based on questions that resulted from observations of cluster behaviour.

Methods
Following preprocessing, a preliminary study evaluated three different models, each trained on the baseline and post-opioid epochs, aiming to identify the most efficient distance metrics and feature space combinations. These models included principal component analysis with Euclidean distance, computed feature space with Euclidean distance, and time series with dynamic time warping. Next, the preferred approach, determined by testing different hypotheses regarding the desired cluster behaviour, underwent further refinement, and predictions were generated for post-antagonist epochs. Finally, feature influence was determined and questions were identified for the data-analysis.

Results
In total, 34 subjects were included, resulting in a total of 6630 epochs for model development. Based on the preliminary study, it was decided to opt for a fuzzy clustering approach using calculated features as input, resulting in membership values indicating the probability of an epoch belonging to a certain cluster. A change in membership values was observed post-opioid as well as a recovery to baseline values post-antagonist in the majority of subjects when clustering was obtained for each subject individually. However, it was expressed as a sudden switch followed by a prolonged plateau phase rather than a gradual transition which was expected. Conversely, when trained collectively over all subjects, the majority of subjects showed no difference, probably due to the presence of inter-subject variability. Nevertheless, SHAP value analysis identified the same feature behaviour among subjects, despite variations in orientation and positioning, hinting at the potential for adjustment using static features. Yet, no significant correlations were found between static features and feature behaviour within this study.

Conclusion
In this study, a fuzzy clustering model was implemented, incorporating SHAP value analysis to enhance the interpretability of the clustering results. Although the model successfully identified changes in respiratory flow patterns associated with OIRD and subsequent recovery after naloxone administration, it requires further refinement.

The thesis explores an innovative technique for enhancing the precision of short-term weather forecasts, particularly in predicting extreme weather phenomena, which present a notable challenge for existing models such as PySTEPS due to their volatile behavior. Leveraging precipitation and meteorological data sourced from the Royal Netherlands Meteorological Institute (KNMI), the research innovates through the development of a physics-informed neural network. Central to this approach is the implementation of a Physics-Informed Discriminator GAN (PID-GAN), a method that embeds physical principles directly into the adversarial training regime. The architecture is marked by the integration of a Vector Quantization Generative Adversarial Network (VQ-GAN) and a Transformer as the generator, complemented by a temporal discriminator as the discriminator component. Results from this study indicate a notable advancement over traditional numerical weather prediction and cutting-edge deep learning models, underscoring the PID-GAN model's superiority in delivering accurate precipitation nowcasting metrics.

Extreme precipitation, like floods and landslides, poses major risks to safety and the economy, underscoring the need for sophisticated weather forecasting to predict these events accurately, enhancing readiness and resilience. Nowcasting, which uses real-time atmospheric data to predict short-term weather, is key in addressing this challenge. Traditional nowcasting systems, reliant on extrapolation from rainfall radar observations and constrained by simplistic physical assumptions, often struggle to detect complex, nonlinear weather patterns. This gap has opened the door for deep learning models, which have shown significant promise in improving the accuracy and reliability of short-term weather predictions, making them a focal point of recent research and the basis of this thesis's approach.

This thesis introduces a deep generative model designed for the nowcasting of extreme precipitation events up to 3 hours ahead, utilizing a Vector-Quantized Variational Autoencoder (VQ-VAE) to compress radar data into a low-dimensional latent representation, and an Autoregressive Transformer for predicting future radar images. Additionally, a binary classifier works in conjunction with the Autoregressive Transformer to identify extreme versus non-extreme weather events, using these classifications to inform an Extreme Value Loss (EVL) function. This loss function aims to improve the accuracy of predicting extreme weather events by addressing the data imbalance between normal and extreme precipitation occurrences. The proposed model displays comparable performance with the state-of-the-art conventional methods and other deep learning nowcasting models in predicting extreme events.

To address the challenges of manual egg sorting on poultry farms, such as labor intensity and
inconsistent quality standards, Moba is developing a machine for automated egg candling
using computer vision. As part of the prototype phase, this project evaluates various methods
to process the egg images for this sorting task.
This project presents an algorithm that segments the individual eggs within the camera’s
field of view, classifies them into five categories, and tracks them across multiple images
to perform the outlet control prediction. To enhance computational efficiency, an anomaly
detector is introduced, directing classification resources exclusively to eggs with a high like-
lihood of defects.
For segmentation, the number of channels in the YOLOv8n model was significantly re-
duced, resulting in YOLOv8xn. With a 97.2% AP95, this model outperformed a classical
algorithm using domain-specific information, as well as more complex deep learning meth-
ods, such as YOLOv8n and the prompt-based FastSAM and MobileSAM models.
Various low-complexity deep learning models were evaluated and compared to classical
feature extraction combined with ensemble machine learning methods for the classification
task. Balancing accuracy and runtime, MobileNetV3 proved to be the optimal choice, achiev-
ing 95.6% accuracy on the final test set.
For anomaly detection, both classical methods and the autoencoder reconstruction loss
were evaluated. Modeling the edge count of non-defective eggs with an exponential distribu-
tion to set a threshold reduced the computational load for classification by 83%. Furthermore,
using the anomaly detector the batch size can be reduced from 32 to 8 images.
To send the eggs to the correct outlet, the predictions for each egg were combined using
thresholds on count-per-class and normalized cumulative class predictions, both without and
with anomaly detection enabled. This resulted in overall accuracies of 97.3%, 98.4%, and
98.0%, respectively.