Joos Vandewalle
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Joos Vandewalle has a total of 12 co-authors. Here are the top co-authors by number of shared publications:
- Johan A. K. Suykens
ESAT-STADIUS, KU Leuven
7 shared publications - Samuel Xavier-De-Souza
UFRN
4 shared publications - Daniel Hillier
Faculty of Information Technology, Péter Pázmány Catholic University; 1083, Budapest, Práter u. 50/a. phone: +36-1-886-47-03; fax: +36-1-886-4700
2 shared publications - Michiel Van Dyck
Cognitive Automation and Technology, Johnson & Johnson, Beerse, Belgium
2 shared publications - Amaury Lendasse
The University of Iowa
1 shared publication - Bart De Moor
Limburg Clinical Research Center/Mobile Health Unit, Faculty of Biomedical and Life Sciences, Hasselt University, Agoralaan, 3590 Diepenbeek, Belgium
1 shared publication
Latest Publications
- Open Access
- 27 April 2023
- Published by PubPub
Open Science @ KU Leuven
The KU Leuven Open Science Task Force is currently preparing a new visual representation of the open science strategy. The visual will include six components: scholarly communications, RDM, rewards & incentives, integrity & reproducibility, public engagement, and OER.
- 27 April 2023
- Published by PubPub
Open AccessOpen Science @ KU Leuven
The KU Leuven Open Science Task Force is currently preparing a new visual representation of the open science strategy. The visual will include six components: scholarly communications, RDM, rewards & incentives, integrity & reproducibility, public engagement, and OER.
- 1 January 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Circuits and Systems Magazine
- Vol. 22 (4) , 49-57
Simple Derivation of Kirchhoff’s Laws and Analogous Laws From Symmetries
Kirchhoff’s laws are undoubtedly the best known laws of electricity. Hence, they have been taught and used widely. So, it may come as a surprise to still write a paper about it. However, for reasons of clarity and wide applicability, it is useful to derive Kirchhoff’s laws with minimal assumptions and using only elementary arguments. This brings some deeper reflections on the role and value of these laws.
- 1 January 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Circuits and Systems Magazine
- Vol. 22 (4) , 49-57
Simple Derivation of Kirchhoff’s Laws and Analogous Laws From Symmetries
Kirchhoff’s laws are undoubtedly the best known laws of electricity. Hence, they have been taught and used widely. So, it may come as a surprise to still write a paper about it. However, for reasons of clarity and wide applicability, it is useful to derive Kirchhoff’s laws with minimal assumptions and using only elementary arguments. This brings some deeper reflections on the role and value of these laws.
- 21 November 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Circuits and Systems Magazine
- Vol. 18 (4) , 32-39
The Role of CAS Concepts and Methods in EE Education and Professional Activities: Societal Challenges and Lessons Learned from Alfred Fettweis
Evolutions in technology and society and in particular the grand challenges of engineering require a proactive strategy and actions for CAS research and education. Indeed, these have a direct impact on the outcome of CAS education in terms of our EE graduates and on the outcome of CAS research and professional activities in terms of designs of devices, systems, services and deeper findings. Our students should have a growth mindset with skills and insights that support an evolving professional horizon of at least 40 years. The paper builds on the contributions and insights of Alfred Fettweis and other new insights in order to produce interesting avenues for dealing with the challenges in the areas of interest within the scope of the circuits and systems society. In particular the role of mathematics in EE education and research are highlighted.
- 21 November 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Circuits and Systems Magazine
- Vol. 18 (4) , 32-39
The Role of CAS Concepts and Methods in EE Education and Professional Activities: Societal Challenges and Lessons Learned from Alfred Fettweis
Evolutions in technology and society and in particular the grand challenges of engineering require a proactive strategy and actions for CAS research and education. Indeed, these have a direct impact on the outcome of CAS education in terms of our EE graduates and on the outcome of CAS research and professional activities in terms of designs of devices, systems, services and deeper findings. Our students should have a growth mindset with skills and insights that support an evolving professional horizon of at least 40 years. The paper builds on the contributions and insights of Alfred Fettweis and other new insights in order to produce interesting avenues for dealing with the challenges in the areas of interest within the scope of the circuits and systems society. In particular the role of mathematics in EE education and research are highlighted.
- 15 August 2015
- Published by Springer Nature
- p. 1-24
Discovering Cluster Dynamics Using Kernel Spectral Methods
- 15 August 2015
- Published by Springer Nature
- p. 1-24
Discovering Cluster Dynamics Using Kernel Spectral Methods
- 1 May 2012
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 71, 2925-2928
Shortcuts in circuits and systems education with a case study of the Thévenin/Helmholtz and Norton/Mayer equivalents
Basic Circuits and Systems CAS education is crucial in the first phase of any electrical engineering curriculum, but increasingly under threat. This situation is in many ways similar to that of mathematics education in engineering. Creative shortcuts for teaching mathematics have recently been advocated in the “streetfighting mathematics approach”. Similar innovative, alternative ways can make the basic CAS education more effective. This special session aims to provide a forum where colleagues across the globe come together to share best practices, such as jewels or pedagogical shortcuts, and where they propose modern circuits, signals, and systems curricula for various target student audiences and discuss other related issues. Here we survey the contributions and discuss a case study, namely, the Thévenin/Helmholtz and Norton/Mayer equivalents.
- 1 May 2012
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 71, 2925-2928
Shortcuts in circuits and systems education with a case study of the Thévenin/Helmholtz and Norton/Mayer equivalents
Basic Circuits and Systems CAS education is crucial in the first phase of any electrical engineering curriculum, but increasingly under threat. This situation is in many ways similar to that of mathematics education in engineering. Creative shortcuts for teaching mathematics have recently been advocated in the “streetfighting mathematics approach”. Similar innovative, alternative ways can make the basic CAS education more effective. This special session aims to provide a forum where colleagues across the globe come together to share best practices, such as jewels or pedagogical shortcuts, and where they propose modern circuits, signals, and systems curricula for various target student audiences and discuss other related issues. Here we survey the contributions and discuss a case study, namely, the Thévenin/Helmholtz and Norton/Mayer equivalents.
- Open Access
- 1 April 2007
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 4 (15206149) , IV-1269-IV-1272
State-of-the-Art and Evolution in Public Data Sets and Competitions for System Identification, Time Series Prediction and Pattern Recognition
It is the aim of reproducible research to provide mechanisms for objective comparison of methods, algorithms, software and procedures in various research topics. In this paper, we discuss the role of data sets, benchmarks and competitions in the fields of system identification, time series prediction, classification, and pattern recognition in view of creating an environment of reproducible research. Important elements are the data sets, their origin, and the comparison measures that will be used to rank the performance of the methods. The issues are discussed, a comparison is made and recommendations are given.
- 1 April 2007
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 4 (15206149) , IV-1269-IV-1272
Open AccessState-of-the-Art and Evolution in Public Data Sets and Competitions for System Identification, Time Series Prediction and Pattern Recognition
It is the aim of reproducible research to provide mechanisms for objective comparison of methods, algorithms, software and procedures in various research topics. In this paper, we discuss the role of data sets, benchmarks and competitions in the fields of system identification, time series prediction, classification, and pattern recognition in view of creating an environment of reproducible research. Important elements are the data sets, their origin, and the comparison measures that will be used to rank the performance of the methods. The issues are discussed, a comparison is made and recommendations are given.
- 1 August 2006
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1
Fast and roust face tracking applieed to wheelchair driving
In this demonstration we will present an application of a fast and robust face tracking algorithm implemented with a CNN Universal Machine chip. The application is the driving of a wheelchair according to predefined movements of the user's head. A 3D model of a wheelchair is used in order to demonstrate the driving mechanism.
- 1 August 2006
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1
Fast and roust face tracking applieed to wheelchair driving
In this demonstration we will present an application of a fast and robust face tracking algorithm implemented with a CNN Universal Machine chip. The application is the driving of a wheelchair according to predefined movements of the user's head. A 3D model of a wheelchair is used in order to demonstrate the driving mechanism.
- 1 August 2006
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 21650144,p. 1-6
Fast an Robust Face Tracking for CNN chips: application to wheelchair driving
An algorithm for fast and robust face tracking with the CNN universal machine is proposed in this paper. It is applied to a driving mechanism for a wheelchair with an on-chip implementation. A novel object tracking CNN visual algorithm is introduced and employed in the tracking of multiple face features. The speed and robustness of this method are achieved due to the parallelism in the visual algorithm, and the tracking of multiple face features. The tracking algorithm is designed to achieve a high frame rate and exploit the specific properties of face features. The face tracking method proposed here was implemented on a Bi-I stand-alone cellular vision system and applied to a wheelchair driving mechanism. The template operations were trained and/or fine-tuned in order to generate chip-specific robust templates. In order to improve performance in environments with varying illumination, an adaptive image capture procedure was also introduced. Our simulations with a 3D model wheelchair showed that the final algorithm is capable of performing tracking with a frame rate of 92 frames/sec, which is supposedly enough for real-time driving in most of the real life situations
- 1 August 2006
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 21650144,p. 1-6
Fast an Robust Face Tracking for CNN chips: application to wheelchair driving
An algorithm for fast and robust face tracking with the CNN universal machine is proposed in this paper. It is applied to a driving mechanism for a wheelchair with an on-chip implementation. A novel object tracking CNN visual algorithm is introduced and employed in the tracking of multiple face features. The speed and robustness of this method are achieved due to the parallelism in the visual algorithm, and the tracking of multiple face features. The tracking algorithm is designed to achieve a high frame rate and exploit the specific properties of face features. The face tracking method proposed here was implemented on a Bi-I stand-alone cellular vision system and applied to a wheelchair driving mechanism. The template operations were trained and/or fine-tuned in order to generate chip-specific robust templates. In order to improve performance in environments with varying illumination, an adaptive image capture procedure was also introduced. Our simulations with a 3D model wheelchair showed that the final algorithm is capable of performing tracking with a frame rate of 92 frames/sec, which is supposedly enough for real-time driving in most of the real life situations
- 1 August 2006
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1
CNNOPT: Learning dynamics and CNN chip-specific robustness
A software tool with the aim of learning new CNN templates and incorporating the ability to tune templates to individual chip instances is presented. During demonstration, the training process of the grayscale constrained trigger-wave template [1] will be shown. The audience can test the tool by proposing their own operation to be learned/tuned.
- 1 August 2006
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1
CNNOPT: Learning dynamics and CNN chip-specific robustness
A software tool with the aim of learning new CNN templates and incorporating the ability to tune templates to individual chip instances is presented. During demonstration, the training process of the grayscale constrained trigger-wave template [1] will be shown. The audience can test the tool by proposing their own operation to be learned/tuned.
- 1 August 2006
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 21650144,p. 1-6
CNNOPT: Learning dynamics and CNN chip-specific robustness
A method is presented that unifies previous approaches with the aim of learning new templates with the ability to tune cellular nonlinear network (CNN) templates to individual chip instances in a global optimization framework. The proposed method is built on earlier approaches extending them in three main aspects. First, hardware parameters of the CNN chip are included in the optimization that opens the way to run templates so far believed to be very unstable on chip. Second, a novel global optimization algorithm is used that improves learning speed significantly. Third, the whole method is presented as a new Matlab toolbox so that the only task of the CNN algorithm designer is to formulate the operation to be learned as a training set of the optimization process. Training set design is the most crucial issue of this approach, thus basic rules for the design of training sets are presented. Examples are given in order to illustrate the design issues. We believe that the proposed method can be a valuable tool to find new CNN templates and robustly implement them on chip
- 1 August 2006
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 21650144,p. 1-6
CNNOPT: Learning dynamics and CNN chip-specific robustness
A method is presented that unifies previous approaches with the aim of learning new templates with the ability to tune cellular nonlinear network (CNN) templates to individual chip instances in a global optimization framework. The proposed method is built on earlier approaches extending them in three main aspects. First, hardware parameters of the CNN chip are included in the optimization that opens the way to run templates so far believed to be very unstable on chip. Second, a novel global optimization algorithm is used that improves learning speed significantly. Third, the whole method is presented as a new Matlab toolbox so that the only task of the CNN algorithm designer is to formulate the operation to be learned as a training set of the optimization process. Training set design is the most crucial issue of this approach, thus basic rules for the design of training sets are presented. Examples are given in order to illustrate the design issues. We believe that the proposed method can be a valuable tool to find new CNN templates and robustly implement them on chip