Abstarct: Fatigue is an important and natural response to many physical activities, long-term mental stress, sleep deprivation and also a non-specific symptom of physical or mental disorder. Undoubtedly, all people experienced fatigue feeling after a severe mental activity or a lot thinking. This feeling is just like when the human body gets tired after long-term exercise. In general, fatigue topics are divided into "physical fatigue" and "mental fatigue" categories. Fatigue affects many aspects of a person's life. This vague and unpleasant symptom undermines his life by negatively affecting a person's ability to carry out daily activities. The past researches have shown that electroencephalogram signals (EEGs) are more accurate and high-performance among the various techniques of the fatigue testing. The purpose of this study is to analyze the symptoms of mental fatigue that appears in people's brain signals. In order to evaluate the signals, first was used a filter to pre-processing the data then, to extract the features, empirical mode decomposition (EMD) method was applied to decompose the signal into its frequency components. These frequency components are called intrinsic mode functions (IMFs) which are obtained by applying EMD on EEG signals and used as input vector in a classifier. Also, to improve the results, a combination of two EMD and STFT techniques was presented as a proposed method. The artificial neural network (ANN) and support vector machine (SVM) classifiers were used for the classification of the obtained features. Then, the Short Time Fourier transform, wavelet energy in EEG signal bands and the combination of these methods were compared with the proposed method. The results of the proposed method, using the two Classifier of ANN and SVM, are respectively 91.3% and 90%, respectively, and also three parameters Accuracy (ACC), sensitivity (Sn) and Specificity (Sp) were used to evaluate the results.