Mannes Poel | University of Twente (original) (raw)
Uploads
Papers by Mannes Poel
Advances in Computer-Human Interaction, Mar 25, 2018
Memoranda informatica, 1991
Journal on Multimodal User Interfaces, Oct 21, 2016
Springer eBooks, Aug 10, 2016
This paper covers part of a study which concerns the feasibility of real-time word spotting with ... more This paper covers part of a study which concerns the feasibility of real-time word spotting with partially recurrent neural networks (PRNN’s). PRNN’s have already proven appropriate for other examples of pure sequence recognition [1, 2]. However choices concerning architectural and learning aspects are still hard to make. One of the questions still to be answered, is how these aspects influence the term of memory of a PRNN. This paper tries to obtain some directives regarding architectures and learning algorithms.
Proceedings of the 14th ACM international conference on Multimodal interaction
A lot of data sets, gathered for instance during user experiments, are contaminated with noise. S... more A lot of data sets, gathered for instance during user experiments, are contaminated with noise. Some noise in the measured features is not much of a problem, it even increases the performance of many Machine Learning (ML) techniques. But for noise in the labels (mislabeled data) the situation is quite different, label noise deteriorates the performance of all ML techniques. The research question addressed in this paper is to what extent can one detect mislabeled data using a committee of supervised Machine Learning models. The committee under consideration consists of a Bayesian model, Random Forest, Logistic classifier, a Neural Network and a Support Vector Machine. This committee is applied to a given data set in several iterations of 5-fold Cross validation. If a data sample is misclassified by all committee members in all iterations (consensus) then it is tagged as mislabeled. This approach was tested on the Iris plant data set, which is artificially contaminated with mislabeled...
Information Systems and Neuroscience, 2019
Sensors, 2019
Full-body motion capture typically requires sensors/markers to be placed on each rigid body segme... more Full-body motion capture typically requires sensors/markers to be placed on each rigid body segment, which results in long setup times and is obtrusive. The number of sensors/markers can be reduced using deep learning or offline methods. However, this requires large training datasets and/or sufficient computational resources. Therefore, we investigate the following research question: “What is the performance of a shallow approach, compared to a deep learning one, for estimating time coherent full-body poses using only five inertial sensors?”. We propose to incorporate past/future inertial sensor information into a stacked input vector, which is fed to a shallow neural network for estimating full-body poses. Shallow and deep learning approaches are compared using the same input vector configurations. Additionally, the inclusion of acceleration input is evaluated. The results show that a shallow learning approach can estimate full-body poses with a similar accuracy (~6 cm) to that of ...
International Journal of Accounting Information Systems, 2016
ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Sensors
Pattern recognition in EMG-based control systems suffer from increase in error rate over time, wh... more Pattern recognition in EMG-based control systems suffer from increase in error rate over time, which could lead to unwanted behavior. This so-called concept drift in myoelectric control systems could be caused by fatigue, sensor replacement and varying skin conditions. To circumvent concept drift, adaptation strategies could be used to retrain a pattern recognition system, which could lead to comparable error rates over multiple days. In this study, we investigated the error rate development over one week and compared three adaptation strategies to reduce the error rate increase. The three adaptation strategies were based on entropy, on backward prediction and a combination of backward prediction and entropy. Ten able-bodied subjects were measured on four measurement days while performing gait-related activities. During the measurement electromyography and kinematics were recorded. The three adaptation strategies were implemented and compared against the baseline error rate and agai...
ArXiv, 2021
Deep Reinforcement Learning has shown its ability in solving complicated problems directly from h... more Deep Reinforcement Learning has shown its ability in solving complicated problems directly from high-dimensional observations. However, in end-to-end settings, Reinforcement Learning algorithms are not sample-efficient and requires long training times and quantities of data. In this work, we proposed a framework for sample-efficient Reinforcement Learning that take advantage of state and action representations to transform a high-dimensional problem into a low-dimensional one. Moreover, we seek to find the optimal policy mapping latent states to latent actions. Because now the policy is learned on abstract representations, we enforce, using auxiliary loss functions, the lifting of such policy to the original problem domain. Results show that the novel framework can efficiently learn low-dimensional and interpretable state and action representations and the optimal latent policy.
ArXiv, 2020
We present a map-less path planning algorithm based on Deep Reinforcement Learning (DRL) for mobi... more We present a map-less path planning algorithm based on Deep Reinforcement Learning (DRL) for mobile robots navigating in unknown environment that only relies on 40-dimensional raw laser data and odometry information. The planner is trained using a reward function shaped based on the online knowledge of the map of the training environment, obtained using grid-based Rao-Blackwellized particle filter, in an attempt to enhance the obstacle awareness of the agent. The agent is trained in a complex simulated environment and evaluated in two unseen ones. We show that the policy trained using the introduced reward function not only outperforms standard reward functions in terms of convergence speed, by a reduction of 36.9\% of the iteration steps, and reduction of the collision samples, but it also drastically improves the behaviour of the agent in unseen environments, respectively by 23\% in a simpler workspace and by 45\% in a more clustered one. Furthermore, the policy trained in the sim...
Advances in Computer-Human Interaction, Mar 25, 2018
Memoranda informatica, 1991
Journal on Multimodal User Interfaces, Oct 21, 2016
Springer eBooks, Aug 10, 2016
This paper covers part of a study which concerns the feasibility of real-time word spotting with ... more This paper covers part of a study which concerns the feasibility of real-time word spotting with partially recurrent neural networks (PRNN’s). PRNN’s have already proven appropriate for other examples of pure sequence recognition [1, 2]. However choices concerning architectural and learning aspects are still hard to make. One of the questions still to be answered, is how these aspects influence the term of memory of a PRNN. This paper tries to obtain some directives regarding architectures and learning algorithms.
Proceedings of the 14th ACM international conference on Multimodal interaction
A lot of data sets, gathered for instance during user experiments, are contaminated with noise. S... more A lot of data sets, gathered for instance during user experiments, are contaminated with noise. Some noise in the measured features is not much of a problem, it even increases the performance of many Machine Learning (ML) techniques. But for noise in the labels (mislabeled data) the situation is quite different, label noise deteriorates the performance of all ML techniques. The research question addressed in this paper is to what extent can one detect mislabeled data using a committee of supervised Machine Learning models. The committee under consideration consists of a Bayesian model, Random Forest, Logistic classifier, a Neural Network and a Support Vector Machine. This committee is applied to a given data set in several iterations of 5-fold Cross validation. If a data sample is misclassified by all committee members in all iterations (consensus) then it is tagged as mislabeled. This approach was tested on the Iris plant data set, which is artificially contaminated with mislabeled...
Information Systems and Neuroscience, 2019
Sensors, 2019
Full-body motion capture typically requires sensors/markers to be placed on each rigid body segme... more Full-body motion capture typically requires sensors/markers to be placed on each rigid body segment, which results in long setup times and is obtrusive. The number of sensors/markers can be reduced using deep learning or offline methods. However, this requires large training datasets and/or sufficient computational resources. Therefore, we investigate the following research question: “What is the performance of a shallow approach, compared to a deep learning one, for estimating time coherent full-body poses using only five inertial sensors?”. We propose to incorporate past/future inertial sensor information into a stacked input vector, which is fed to a shallow neural network for estimating full-body poses. Shallow and deep learning approaches are compared using the same input vector configurations. Additionally, the inclusion of acceleration input is evaluated. The results show that a shallow learning approach can estimate full-body poses with a similar accuracy (~6 cm) to that of ...
International Journal of Accounting Information Systems, 2016
ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Sensors
Pattern recognition in EMG-based control systems suffer from increase in error rate over time, wh... more Pattern recognition in EMG-based control systems suffer from increase in error rate over time, which could lead to unwanted behavior. This so-called concept drift in myoelectric control systems could be caused by fatigue, sensor replacement and varying skin conditions. To circumvent concept drift, adaptation strategies could be used to retrain a pattern recognition system, which could lead to comparable error rates over multiple days. In this study, we investigated the error rate development over one week and compared three adaptation strategies to reduce the error rate increase. The three adaptation strategies were based on entropy, on backward prediction and a combination of backward prediction and entropy. Ten able-bodied subjects were measured on four measurement days while performing gait-related activities. During the measurement electromyography and kinematics were recorded. The three adaptation strategies were implemented and compared against the baseline error rate and agai...
ArXiv, 2021
Deep Reinforcement Learning has shown its ability in solving complicated problems directly from h... more Deep Reinforcement Learning has shown its ability in solving complicated problems directly from high-dimensional observations. However, in end-to-end settings, Reinforcement Learning algorithms are not sample-efficient and requires long training times and quantities of data. In this work, we proposed a framework for sample-efficient Reinforcement Learning that take advantage of state and action representations to transform a high-dimensional problem into a low-dimensional one. Moreover, we seek to find the optimal policy mapping latent states to latent actions. Because now the policy is learned on abstract representations, we enforce, using auxiliary loss functions, the lifting of such policy to the original problem domain. Results show that the novel framework can efficiently learn low-dimensional and interpretable state and action representations and the optimal latent policy.
ArXiv, 2020
We present a map-less path planning algorithm based on Deep Reinforcement Learning (DRL) for mobi... more We present a map-less path planning algorithm based on Deep Reinforcement Learning (DRL) for mobile robots navigating in unknown environment that only relies on 40-dimensional raw laser data and odometry information. The planner is trained using a reward function shaped based on the online knowledge of the map of the training environment, obtained using grid-based Rao-Blackwellized particle filter, in an attempt to enhance the obstacle awareness of the agent. The agent is trained in a complex simulated environment and evaluated in two unseen ones. We show that the policy trained using the introduced reward function not only outperforms standard reward functions in terms of convergence speed, by a reduction of 36.9\% of the iteration steps, and reduction of the collision samples, but it also drastically improves the behaviour of the agent in unseen environments, respectively by 23\% in a simpler workspace and by 45\% in a more clustered one. Furthermore, the policy trained in the sim...
Journal on Multimodal User Interfaces, 2010
The multimodal, multi-paradigm brain-computer interfacing (BCI) game Bacteria Hunt was used to ev... more The multimodal, multi-paradigm brain-computer interfacing (BCI) game Bacteria Hunt was used to evaluate two aspects of BCI interaction in a gaming context. One goal was to examine the effect of feedback on the ability of the user to manipulate his mental state of relaxation. This was done by having one condition in which the subject played the game with real feedback, and another with sham feedback. The feedback did not seem to affect the game experience (such as sense of control and tension) or the objective indicators of relaxation, alpha activity and heart rate. The results are discussed with regard to clinical neurofeedback studies. The second goal was to look into possible interactions between the two BCI paradigms used in the game: steady-state visually-evoked potentials (SSVEP) as an indicator of concentration, and alpha activity as a measure of relaxation. SSVEP stimulation activates the cortex and can thus block the alpha rhythm. Despite this effect, subjects were able to keep their alpha power up, in compliance with the instructed relaxation task. In addition to the main goals, a new SSVEP detection algorithm was developed and evaluated.