Discrimination between Two Mental States (Rest and Motor Image) Using Wavelet Transform and Neural Networks.
ABSTRACT This paper presents a method for the processing and classification of electroencephalographic (EEG) signals linked to mental
states (rest and motor image) using the wavelet transform of these signals as input information of an LVQ neural network.
This system obtained a 70% correct qualification rate in the first recording session, a 50% rate in the second and an 80%
rate in the third, with a 75% classification success rate for the whole set of data. These results fall within the average
range obtained by other systems which require more information.
- SourceAvailable from: Jean Decety[Show abstract] [Hide abstract]
ABSTRACT: The performance of subjects walking blindly to previously inspected visual targets (located at 5, 10 or 15 m from the subjects) was studied in 2 experiments. In Expt. 1, subjects selected as good visual imagers were instructed to build up a mental representation of the target. Then they had to either actually walk or imagine themselves walking to the target. Walking time was measured in both the actual and the mental performance. It was found that subjects took almost exactly the same time in the two conditions. Accuracy of these subjects was also measured in the actual walking task. They were found to make no direction errors and to slightly overshoot target location. Subjects from another, control, group, who received no instructions about visual imagery made much larger errors. In Expt. 2, actual and mental walking times were measured in the same subjects as in Expt. 1, while they carried a 25-kg weight on their shoulders. In this condition, actual walking time was the same as in Expt. 1, although mental walking time was found to increase systematically by about 30%. These results are discussed in terms of the neural parameters encoded in the motor program for actually executing or mentally performing an action.Behavioural Brain Research 09/1989; 34(1-2):35-42. · 3.39 Impact Factor
- [Show abstract] [Hide abstract]
ABSTRACT: This monograph gives a tutorial treatment of new approaches to self-organization, adaptation, learning and memory. It is based on recent research results, both mathematical and computer simulations, and lends itself to graduate and postgraduate courses in the natural sciences. The book presents new formalisms of pattern processing: orthogonal projectors, optimal associative mappings, novelty filters, subspace methods, feature-sensitive units, and self-organization of topological maps, with all their computable algorithms. The main objective is to provide an understanding of the properties of information representations from a general point of view and of their use in pattern information processing, as well as an understanding of many functions of the brain. In the second edition two new chapters on neural computing and optical associative memories have been added.3rd 01/1989; Spring-Verlag.
- [Show abstract] [Hide abstract]
ABSTRACT: The aim of this study was to examine whether a sensation of effort would arise in subjects requested, by verbal instructions, to mentally perform motor tasks with an internal imagery strategy. Sixteen subjects had to imagine themselves, from a first person perspective, writing a sentence and drawing a Necker's cube either with their right dominant hand or with their left hand, as well as hopping around a square either on their right or left foot. The time needed to mentally execute these actions was measured. The sensation of effort following the mental performance and the difficulty of imaging the tasks were assessed by means of two analog rating scales. The results indicate that the sensation of effort increased across the trials. Furthermore, a negative correlation coefficient (mean r = -0.99) was found between the difficulty to imagining a given motor task and the subjective sensation of effort across the trials. Moreover, the sensation of effort was more pronounced when the tasks involved the non-dominant limb.Scandinavian Journal of Psychology 02/1991; 32(2):97-104. · 1.29 Impact Factor