Complex wavelet algorithm for computeraided diagnosis of Alzheimer's disease

Abstract

Electroencephalography signals are used for computer-aided diagnosis of Alzheimer's disease. Therefore, extracting critical features that belong to Alzheimer's signals are useful and tedious for neural network classification due to the high-frequency non-stationary components. For this purpose, time-frequency analysis and the multi-resolution capability of wavelets represent an attractive choice. However, fluctuations of the transformed coefficients and the absence of phase information make the process less accurate in certain scenarios. Because of this, complex wavelet transform has been selected to handle Alzheimer's signals. Moreover, the importance of calculating an optimal threshold value has been highlighted, usually by means of Shannon entropy as a helpful threshold identifier of the complex wavelet transform used to produce significant results. The effectiveness of Tsallis entropy instead of Shannon entropy in handling Alzheimer's signals is evaluated, the former giving place to better features for neural network classification. As a result, accuracy has been improved from 90 to 95% using Tsallis entropy. Hence, this new proposal boosts the opportunity to reduce mortality rates by detecting the disease accurately.