A5019986708- Time Series Analysis and Forecasting
- Stock Market Forecasting Methods
- Complex Systems and Time Series Analysis
- Obstructive Sleep Apnea Research
- Data Visualization and Analytics
- Sleep and Work-Related Fatigue
- EEG and Brain-Computer Interfaces
- COVID-19 epidemiological studies
- Species Distribution and Climate Change
- Cryospheric studies and observations
- Anomaly Detection Techniques and Applications
- Air Quality Monitoring and Forecasting
- Greenhouse Technology and Climate Control
- Infection Control and Ventilation
- Image and Video Quality Assessment
Ghent University
2021-2023
Visual analytics is arguably the most important step in getting acquainted with your data. This especially case for time series, as this data type hard to describe and cannot be fully understood when using example summary statistics. To realize effective series visualization, four requirements have met; a tool should (1) interactive, (2) scalable millions of points, (3) integrable conventional science environments, (4) highly configurable. We observe that open source Python visualization...
Time series processing and feature extraction are crucial time-intensive steps in conventional machine learning pipelines. Existing packages limited their applicability, as they cannot cope with irregularly-sampled or asynchronous data make strong assumptions about the format. Moreover, these do not focus on execution speed memory efficiency, resulting considerable overhead. We present tsflex, a Python toolkit for time extraction, that focuses performance flexibility, enabling broad...
A healthy and safe indoor environment is an important part of containing the coronavirus disease 2019 (COVID-19) pandemic. Therefore, this work presents a real-time Internet things (IoT) software architecture to automatically calculate visualize COVID-19 aerosol transmission risk estimation. This estimation based on climate sensor data, such as carbon dioxide (CO2) temperature, which fed into Streaming MASSIF, semantic stream processing platform, perform computations. The results are...
Monitoring climate change, and its impacts on ecological, agricultural, other societal systems, is often based temperature data derived from official weather stations. Yet, these do not capture most microclimates, influenced by soil, vegetation topography, operating at spatial scales relevant to the majority of organisms Earth. Detecting attributing change with confidence certainty will only be possible a better quantification changes in forests, croplands, mountains, shrublands, remote...
Over the last few years, research in automatic sleep scoring has mainly focused on developing increasingly complex deep learning architectures. However, recently these approaches achieved only marginal improvements, often at expense of requiring more data and expensive training procedures. Despite all efforts their satisfactory performance, staging solutions are not widely adopted a clinical context yet. We argue that most for limited real-world applicability as they hard to train, deploy,...
Visual analytics is arguably the most important step in getting acquainted with your data. This especially case for time series, as this data type hard to describe and cannot be fully understood when using example summary statistics. To realize effective series visualization, four requirements have met; a tool should (1) interactive, (2) scalable millions of points, (3) integrable conventional science environments, (4) highly configurable. We observe that open source Python visualization...
Time series processing and feature extraction are crucial time-intensive steps in conventional machine learning pipelines. Existing packages limited their applicability, as they cannot cope with irregularly-sampled or asynchronous data make strong assumptions about the format. Moreover, these do not focus on execution speed memory efficiency, resulting considerable overhead. We present $\texttt{tsflex}$, a Python toolkit for time extraction, that focuses performance flexibility, enabling...