Publications
Reliable assessment of uncertainty for appliance recognition in NILM using conformal prediction Ghent University
A primary task of Non-intrusive Load Monitoring (NILM) is the identification of appliances that are switched on or off. However, state-of-the-art machine learning methods such as deep learning do not express uncertainty of their predictions. Especially in cases where appliances are confused, it is desirable that an NILM system can suggest multiple possible predictions to the end-user, including its confidence and credibility of any given ...
Wideband complex vector fitting for modeling time delay variations in passive photonic filters Ghent University
This paper presents a novel wideband baseband macromodeling framework tailored for the representation of linear and passive photonic filters. The proposed framework is able to efficiently estimate the baseband scattering representations of such filters as a function of the delay in the waveguides that control their center frequency. Notably, the macromodel allows for frequency and time-domain simulations at arbitrary optical carrier frequencies, ...
A robust multi-objective Bayesian optimization framework considering input uncertainty Ghent University
Bayesian optimization is a popular tool for optimizing time-consuming objective functions with a limited number of function evaluations. In real-life applications like engineering design, the designer often wants to take multiple objectives as well as input uncertainty into account to find a set of robust solutions. While this is an active topic in single-objective Bayesian optimization, it is less investigated in the multi-objective case. We ...
Open-set patient activity recognition with radar sensors and deep learning Ghent University
Open-set recognition (OSR) has achieved significant importance in recent years. For a robust recognition system, we need to identify the right class from a myriad of knowns and unknowns. In this work, we build and compare OSR systems for patient activity recognition (PAR) using compact radar sensors in a hospital setting. Radar sensors are an important part of a privacy-preserving monitoring system. Specifically, the proposed approach is based ...
{PF}²ES : parallel feasible pareto frontier entropy search for multi-objective Bayesian optimization Ghent University
Cost-aware active learning for feasible region identification Ghent University
Design space exploration for engineering design involves identifying feasible designs that satisfy design specifications, often represented by feasibility constraints. To determine whether a design is feasible, an expensive simulation is required. Therefore, it is crucial to find and model the feasible region with as few simulations as possible. Model-based Active learning (AL) is a data-efficient, iterative sampling framework that can be used ...
Graph neural networks for fault diagnosis of geographically nearby photovoltaic systems Ghent University
Faults in photovoltaic (PV) systems significantly reduce their efficiency and can pose safety risks. Nevertheless, most residential PV systems are not actively monitored, because existing methods often require expensive sensors, which are only cost-effective for large PV systems. Therefore, we propose a graph neural network (GNN) to monitor a group of nearby PV systems without relying on dedicated sensors. Instead, the GNN compares 24 h of ...