“…The percentages shown in the figure include some of the work that used multiple classifications algorithms for performance comparison; the percentage is based on the total instance that each method was used and not on the number of publications. As shown in the figure, 37% of the publications use linear discriminant analysis (LDA), 23% use support vector machine (SVM), 15% use artificial neural network (ANN), and the rest use k-nearest neighbor (KNN) [9,31,37], decision tree (DT) [9], deep neural network (DNN) [59,60], extreme learning machine (ELM) [28,55], Gaussian process regression (GPR) [65], hidden Markov model (HMM) [9], random forest (RF) [33,66], and tree bagging (TB) [67].…”