Biomedical subjects

J del R Millán

Publications and source records attributed to J del R Millán.

3 recordsLinked to original sources

PubMed2002

Classification of EEG mental patterns by using two scalp electrodes and Mahalanobis distance-based classifiers.

OBJECTIVES: In this paper, we explored the use of quadratic classifiers based on Mahalanobis distance to detect mental EEG patterns from a reduced set of scalp recording electrodes. METHODS: Electrodes are placed in scalp centro-parietal zones (C3, P3, C4 and P4 positions of the international 10-20 system). A Mahalanobis distance classifier based on the use of full covariance matrix was used. RESULTS: The quadratic classifier was able to detect EEG activity related to imagination of movement with an affordable accuracy (97% correct classification, on average) by using only C3 and C4 electrodes. CONCLUSIONS: Such a result is interesting for the use of Mahalanobis-based classifiers in the brain computer interface area.

Biomedical Engineering↗

PubMed2001

Recognition of imagined hand movements with low resolution surface Laplacian and linear classifiers.

EEG-based Brain Computer Interfaces (BCIs) require on-line detection of mental states from spontaneous EEG signals. In this framework, it was suggested that EEG patterns can be better detected with EEG data transformed with Surface Laplacian computation (SL) than with the unprocessed raw potentials. However, accurate SL estimates require the use of many EEG electrodes, when local estimation methods are used. Since BCI devices have to use a limited number of electrodes for practical reasons, we investigated the performances of spline methods for SL estimates using a limited number of electrodes (low resolution SL). Recognition of mental activity was attempted on both raw and SL-transformed EEG data from five healthy people performing two mental tasks, namely imagined right and left hand movements. Linear classifiers were used including Signal Space Projection (SSP) and Fisher's linear discriminant. Results showed an acceptable average correlation between the waveforms obtained with the low resolution SL and these obtained with the SL computed from 26 electrodes (full resolution SL). More importantly, satisfactorily recognition scores for mental EEG-patterns were obtained with the low-resolution surface Laplacian transformation of the recorded potentials when compared with those obtained by using full resolution SL (82%). These results demonstrated also the utility of linear classifiers for the detection of mental patterns in the BCI field.

Biomedical Engineering↗

PubMed1998

Learning reaching strategies through reinforcement for a sensor-based manipulator.

This paper presents a neural controller that learns goal-oriented obstacle-avoiding reaction strategies for a multilink robot arm. It acquires these strategies on-line from local sensory data. The controller consists of two neural modules: an actor-critic module and a module for differential inverse kinematics (DIV). The input codification for the controller exploits the inherent symmetry of the robot arm kinematics. The actor-critic module generates actions with regard to the Shortest Path Vector (SPV) to the closest goal in the configuration space. However, the computation of the SPV is cumbersome for manipulators with more than two links. The DIV module aims to overcome the SPV calculation. This module provides a goal vector by means of the inversion of a neural network that has been trained previously to approximate the manipulator forward kinematics. Results for a two-link robot arm show that the combination of both modules speeds up the learning process.

Journal Article↗