Biomedical subjects

R Strungaru

Publications and source records attributed to R Strungaru.

3 recordsLinked to original sources

PubMed1998

The use of Matlab for colour fuzzy representation of multichannel EEG short time spectra.

During the last years, a lot of EEG research efforts was directed to intelligent methods for automatic analysis of data from multichannel EEG recordings. However, all the applications reported were focused on specific single tasks like detection of one specific "event" in the EEG signal: spikes, sleep spindles, epileptic seizures, K complexes, alpha or other rhythms or even artefacts. The aim of this paper is to present a complex system being able to perform a representation of the dynamic changes in frequency components of each EEG channel. This representation uses colours as a powerful means to show the only one frequency range chosen from the shortest epoch of signal able to be processed with the conventional "Short Time Fast Fourier Transform" (S.T.F.F.T.) method.

Artificial Intelligence↗

PubMed1998

Analysing the spectral properties of EEG ictal events with time-frequency transform.

Analysis of EEG events, as e.g. the epileptic seizures, is a challenge for a lot of research that has been carried out during the last five years. New methods are required to better analyse the epileptic transients occurring during seizures. This paper discusses a model for features extraction from EEG signal to determine a specific signature of the seizure (inter-ictal) and to detect it using an artificial neural network, or just to provide a better representation of the frequency changes to the clinician.

Electroencephalography↗

PubMed1998

Myoelectric signal classification using neural networks.

A feed-forward neural network is used for diagnosis of spastic paralysis. It is a two-layer perceptron and it is able to classify two kinds of myoelectric signal recorded in surface electromyography: the normal EMG and the EMG in the case of spastic paralysis. The myoelectric signal was recorded with a surface electrode pair and sampled at 10 kHz. The EMG activity is stochastic and the instantaneous amplitude distribution for a fixed level of contraction is Gaussian. The signal variance is considered a measure of muscle force. We can describe any kind of this process by the AR model. For a precisely modeling of EMG there are necessary many AR model parameters. In the classification problem we have it is not necessary to use a high order AR model. We find a 4-th order AR model is good enough for this study. The Hopfield algorithm is used to calculate the parameters of the autoregressive model.

Electrodes↗