Many endogenous and external components may affect the physiological, mental and behavioral states in humans. Monitoring tools are required to evaluate biomarkers, identify biological events, and predict their outcomes. Being one of the valuable indicators, brain biomarkers derived from temporal or spectral electroencephalography (EEG) signals processing, allow for the classification of mental disorders and mental tasks. An EEG signal has a non-stationary nature and individual frequency feature, hence it can be concluded that each subject has peculiar timing and data to extract unique features. In order to classify data, which are collected by performing four mental task (reciting the alphabet backwards, imagination of rotation of a cube, imagination of right hand movements (open/close) and performing mathematical operations), discriminative features were extracted using four competitive time-frequency techniques; Wavelet Packet Decomposition (WPD), Morlet Wavelet Transform (MWT), Short Time Fourier Transform (STFT) and Wavelet Filter Bank (WFB), respectively. The extracted features using both time and frequency domain information were then reduced using a principal component analysis for subset reduction. Finally, the reduced subsets were fed into a multi-layer perceptron neural network (MP-NN) trained with back propagation (BP) algorithm to generate a predictive model. This study mainly focuses on comparing the relative performance of time-frequency feature extraction methods that are used to classify mental tasks. The real-time (RT) conducted experimental results underlined that the WPD feature extraction method outperforms with 92% classification accuracy compared to three other aforementioned methods for four different mental tasks.