A new neural network model based on the LVQ algorithm for multi-class classification of arrhythmias

Application of artificial neural network in the diagnostic system of osteoporosis

“…The training effect has close relationship with the input data in the model of ANN. If input parameters can not be the character discrimination of output in ANN, it is difficult to establish an ideal ANN model [37].…”

A novel method of diagnosing premature ventricular contraction based on sparse auto-encoder and softmax regression

“…In recent years, many studies concerning the classification of arrhythmias have been conducted [4][5][6][7][8][9][10][11][12]. In one study, J. Wang developed a novel ECG arrhythmia classification method based on feature reduction by combing a principal component analysis (PCA) with a linear discriminant analysis (LDA).…”

Using the One-vs-One decomposition to improve the performance of class noise filters via an aggregation strategy in multi-class classification problems

“…Many real-world classification tasks, such as text classification [30], medical diagnosis [31] and intrusion detection [32], are characterized by having more than two class labels. They are known as multi-class classification problems.…”