The human brain comprises a complex network of neurons, which supports cognitive actions, body balance, and performing innumerable actions. Electroencephalography (EEG) is a method of recording the electrical activities of the brain, which can be used for several applications, such as prediction of alertness, drowsiness, attention-seeking, motor imaginary movements, emotion, and diagnose the effects of drugs. Advanced Artificial Intelligence (AAI) methods such as Machine Learning (ML) and Deep Learning algorithms (DL) play a vital role in the classification EEG signals. This study presents a systematic review of the prominent research articles which comprehend the identification of mental alertness and the impact of sports in mental alertness. This significant survey infers that, physical activities will intensify the concentration level. The feature extraction, feature selection and classification algorithms in specific to mental alertness were reported and compared. From the cluster of features like relative power, absolute power, power spectral density, spectral power signal entropy, the predominant features viz. relative power and power spectral density were selected using filter, wrapper, LASSO based algorithms with p values of 0.075 and 0.06 respectively. Support Vector Machine (SVM), Artificial Neural Network (ANN), K-Nearest Neighbor (KNN), Decision Tree (DT), and Logistic Regression (LR) techniques were used to classify the mental alertness. SVM and ANN were the widely used accurate classifiers for mental alertness, with an accuracy of 87.6% and 96.6%, respectively.