As the ictal signal recorded by EEG is mainly the most commonly used method for its non-invasive, different methods are studied to classify them into different types wither on time or frequency domain. However, it is not easy to get focal and informative data especially with deep stimulated problem, which is happened to be the challenging part for seizure data processing. Thus, we raised our model on Hilbert transform with intrinsic mode function (IMF) of empirical mode decomposition (EMD), which over advantage Fourier Transform and Wavelet Transform with its possibility in non-linear and non-stationary signal. With the request for inference from limited clinical data, the Bayes inference is applied with Hamilton Markov Chain on the energy-quantities based on the IMFs. Due to the computation power, the leapfrog is iterated and tempered in 50 steps separately only. However, because of the focus on HFOs (> 70Hz) which are focal and commonly used in drug efficiency test. Their explicit expression can be studied both on time series or event-related phase analysis on frequency domain according to our previous work as well. This paper utilize this model on EEG epilepsy data classifying the HFOs into ictal and interictal.(HMC and HIS are utilised).
Qin He (2021). Ictal classification with HMC (https://www.mathworks.com/matlabcentral/fileexchange/73956-ictal-classification-with-hmc), MATLAB Central File Exchange. Retrieved .
Find the treasures in MATLAB Central and discover how the community can help you!Start Hunting!