Annals of biomedical engineering
-
In this study, normal EEG series recorded from healthy volunteers and epileptic EEG series recorded from patients within and without seizure are classified by using Multilayer Neural Network (MLNN) architectures with respect to several time domain entropy measures such as Shannon Entropy (ShanEn), Log Energy Entropy (LogEn), and Sample Entropy (Sampen). In tests, the MLNN is performed with several numbers of neurons for both one hidden layer and two hidden layers. The results show that segments in seizure have significantly lower entropy values than normal EEG series. ⋯ The LogEn approach, which has not been experienced in EEG classification yet, provides the most reliable features into the EEG classification with very low absolute error as 0.01. In particular, the MLNN can be proposed to distinguish the seizure activity from the seizure-free epileptic series where the LogEn values are considered as signal features that characterize the degree of EEG complexity. The highest classification accuracy is obtained for one hidden layer architecture.
-
A new method for measuring the fixed charge density (FCD) in intervertebral disc (IVD) tissues employing a two-point electrical conductivity approach was developed. In this technique, the tissue is first confined and equilibrated in a potassium chloride (KCl) solution, and the tissue conductivity is then measured. This is then repeated with a second concentration of KCl solution. ⋯ The FCD of AF was significantly lower than that of NP tissue, similar to results in the literature for human IVD tissues. In order to verify the accuracy of the new method, the glycosaminoglycan (GAG) contents of the tissues were measured and used to estimate the tissue FCD. A strong correlation (R (2) = 0.84-0.87) was found to exist between FCD values measured and those estimated from GAG contents, indicating that the conductivity approach is a reliable technique for measuring the FCD of IVD tissues.