Bart Dhoedt

Bart Dhoedt

Auto-generated profile, based on publicly available information

Bart Dhoedt

IDLab, Department of Information Technology Ghent University–IMEC Ghent Belgium

Research Focus & Metrics

Academic Career Length

29Years (1998-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 October 2021 in Neural Networks
Verified
Journal Article
Closed access
OCOzan Catal
Ozan Catal
TVTim Verbelen
Tim Verbelen
TMToon Van de Maele
Toon Van de Maele
BDBart Dhoedt
Bart Dhoedt
Adam SafronAdam Safron
Adam Safron

1 September 2017
Verified
Conference Paper
Open access
SBSteven Bohez
Steven Bohez
TVTim Verbelen
Tim Verbelen
ECElias De Coninck
Elias De Coninck
BVBert Vankeirsbilck
Bert Vankeirsbilck
PSPieter Simoens
Pieter Simoens
BDBart Dhoedt
Bart Dhoedt
Deep reinforcement learning is becoming increasingly popular for robot control algorithms, with the aim for a robot to self-learn useful feature representations from unstructured sensory input leading to the optimal actuation policy. In addition to sensors mounted on the robot, sensors might also be deployed in the environment, although these might need to be accessed via an unreliable wireless connection. In this paper, we demonstrate deep neural network architectures that are able to fuse information generated by multiple sensors and are robust to sensor failures at runtime. We evaluate our method on a search and pick task for a robot both in simulation and the real world.

6 June 2022 in Journal of Educational Computing Research
Verified
Journal Article
Closed access
CPCharlotte Van Petegem
Charlotte Van Petegem
LDLouise Deconinck
Louise Deconinck
DMDieter Mourisse
Dieter Mourisse
RMRien Maertens
Rien Maertens
NSNiko Strijbol
Niko Strijbol
BMBart Mesuere
Bart Mesuere
We present a privacy-friendly early-detection framework to identify students at risk of failing in introductory programming courses at university. The framework was validated for two different courses with annual editions taken by higher education students ( N = 2 080) and was found to be highly accurate and robust against variation in course structures, teaching and learning styles, programming exercises and classification algorithms. By using interpretable machine learning techniques, the framework also provides insight into what aspects of practising programming skills promote or inhibit learning or have no or minor effect on the learning process. Findings showed that the framework was capable of predicting students’ future success already early on in the semester.

1 January 2011
Verified
Conference Paper
Open access
PDF file
JBJens Buysse
Jens Buysse
CCCicek Cavdar
Cicek Cavdar
MLMarc De Leenheer
Marc De Leenheer
BDBart Dhoedt
Bart Dhoedt
CDChris Develder
Chris Develder
Exploiting anycast routing significantly reduces optical network and server energy usage. In this work we present a case study showing that intelligently selecting destinations and routes thereto, while switching off unused (network) elements, cuts power consumption by around 20% and saves network resources by 29%.

3 August 2023 in Experimental Dermatology
Verified
Journal Article
Closed access
PMPieter Van Molle
Pieter Van Molle
SMSofie Mylle
Sofie Mylle
TVTim Verbelen
Tim Verbelen
CBCedric De Boom
Cedric De Boom
BVBert Vankeirsbilck
Bert Vankeirsbilck
LBLieve Brochez
Lieve Brochez

22 May 1998
Verified
Conference Paper
Closed access
PDF file
RBRonny Bockstaele
Ronny Bockstaele
AHAn Van Hove
An Van Hove
TCT Coosemans
T Coosemans
CSC Sys
C Sys
Ingrid MoermanIngrid Moerman
Ingrid Moerman
LTL Van Der Torren
L Van Der Torren
Parallel optical data links using high efficiency Microcavity LEDs and small diameter POF ribbons are proposed. MCLED performance, coupling efficiencies, alignment tolerances, POF end facet termination techniques and first link experiments are studied.