Signal-dependent wavelets for electromyogram classification.

In the study, an efficient method to perform supervised classification of surface electromyogram (EMG) signals is proposed. The method is based on the choice of a relevant representation space and its optimisation with respect to a training set. As EMG signals are the summation of compact-support waveforms (the motor unit action potentials), a natural tool for their representation is the discrete dyadic wavelet transform. The feature space was thus built from the marginals of a discrete wavelet decomposition. The mother wavelet was designed to minimise the probability of classification error estimated on the learning set (supervised classification). As a representative example, the method was applied to simulate surface EMG signals generated by motor units with different degrees of short-term synchronisation. The proposed approach was able to distinguish surface EMG signals with degrees of synchronisation that differed by 10%, with a misclassification rate of 8%. The performance of a spectral-based classification (error rate approximately 33%) and of the classification with Daubechies wavelet (21%) was significantly poorer than with the proposed wavelet optimisation. The method can be used for a number of different application fields of surface EMG classification, as the feature space is adapted to the characteristics of the signal that discriminate between classes.

Duality of gonadotropins in gnathostomes.

The glycoprotein hormone alpha subunit and two beta subunits were cloned from the ventral lobe of the pituitary gland of an elasmobranch fish, Scyliorhinus canicula. The mature alpha subunit was 96 amino acids long and showed 64-76 amino acid residues in common with alpha subunit sequences of representatives of sarcopterygians (tetrapods and dipnoi) and actinopterigyans (chondrostei and teleostei). The Scyliorhinus beta 1 subunit was 115 amino acid long and had characteristics specific to FSH beta subunits and, in particular, the two potential N-linked glycosylation sites in conserved positions. The beta 2 sequence was 112 amino acids long. The Scyliorhinus beta 2 subunit had only one potential N-linked glycosylation site at the same position as that in LH. None of the two beta subunits from Scyliorhinus displayed the two amino acid insertions shared by TSH beta subunit sequences between the fifth and the sixth cysteines as compared to actinopterygian and sarcopterygian gonadotropins. These data indicate that Scyliorhinus beta 1 and beta 2 subunits are orthologous to FSH and LH beta subunits, respectively. It is concluded that the two FSH and LH lineages were already individualized at the emergence of chondrichthyans.