Dans le cadre de la reconnaissance de formes, la définition d'un espace de représentation est nécessaire. Nous proposons ici de l'adapter à l'objectif de classification en utilisant la décomposition en paquets d'ondelettes. Notre algorithme s'appuie sur une représentation fréquentielle des signaux (marginales des coefficients des paquets d'ondelettes) qui dépend de la base de décomposition choisie. Nous proposons donc de sélectionner la décomposition fréquentielle la plus pertinente en optimisant la base de décomposition sur une population d'apprentissage. Pour cela, nous avons défini un critère de contraste entre les classes. Il est additif, ce qui nous a permis d'utiliser un algorithme rapide de recherche de meilleure base. Les fonctions ...
Abstract—This paper describes the development and testing of a wavelet-like filter, named the SNAP, ...
The main issue to build applicable Brain-Computer Interfaces is the capability to classify the elect...
The wavelet packet transform (WPT) [1] is an extension of the discrete wavelet transform (DWT). The ...
<p>The full algorithm can be divided into two parts. The Wavelet-Level Selection and the Band-Featur...
Background: Recently, successful applications of the discrete wavelet transform hav...
Selection of relevant features is an open problem in Brain-computer interfacing (BCI) research. Some...
This paper introduces a method to classify EEG signals using features extracted by an integration of...
In the context of signal classification, this paper assembles and compares criteria to easily judge ...
We present a method of selecting optimal input features from wavelet coefficients of electroencephal...
The potential of brain-computer interfaces (BCI) in serving a useful purpose, e.g., supporting commu...
Exoskeleton or brain computer interface design is an complicated and challenging effort as it involv...
Brain Computer Interfaces (BCI) require the use of statistical learning methods for signal recogniti...
Hybrid wavelet { large margin classiers have recently proven to solve dicult signal classication pro...
Exoskeleton or brain computer interface design is an complicated and challenging effort as it involv...
Combined wavelet - large margin classifiers succeed in solving difficult signal classification probl...
Abstract—This paper describes the development and testing of a wavelet-like filter, named the SNAP, ...
The main issue to build applicable Brain-Computer Interfaces is the capability to classify the elect...
The wavelet packet transform (WPT) [1] is an extension of the discrete wavelet transform (DWT). The ...
<p>The full algorithm can be divided into two parts. The Wavelet-Level Selection and the Band-Featur...
Background: Recently, successful applications of the discrete wavelet transform hav...
Selection of relevant features is an open problem in Brain-computer interfacing (BCI) research. Some...
This paper introduces a method to classify EEG signals using features extracted by an integration of...
In the context of signal classification, this paper assembles and compares criteria to easily judge ...
We present a method of selecting optimal input features from wavelet coefficients of electroencephal...
The potential of brain-computer interfaces (BCI) in serving a useful purpose, e.g., supporting commu...
Exoskeleton or brain computer interface design is an complicated and challenging effort as it involv...
Brain Computer Interfaces (BCI) require the use of statistical learning methods for signal recogniti...
Hybrid wavelet { large margin classiers have recently proven to solve dicult signal classication pro...
Exoskeleton or brain computer interface design is an complicated and challenging effort as it involv...
Combined wavelet - large margin classifiers succeed in solving difficult signal classification probl...
Abstract—This paper describes the development and testing of a wavelet-like filter, named the SNAP, ...
The main issue to build applicable Brain-Computer Interfaces is the capability to classify the elect...
The wavelet packet transform (WPT) [1] is an extension of the discrete wavelet transform (DWT). The ...