Search

Background and Objective: Brain-Computer Interfaces (BCI) are used to provide environmental interaction among individuals, especially people with disabilities. Spelling systems, one of the BCI applications, are based on the principle of detecting P300 waves from EEG signals. The aim of speller systems is to identify the P300 waves and determine the letter on a screen opposite the person. The purpose of the operating speller systems is to minimize the processing cost of the system with smaller data sizes to be obtained by compressing EEG data before the pre-processing step. In this study, a hybrid model was presented. With Pairwise and variance-based signal compression Algorithm, first of all, data is compressed and then preprocessing, and classification is performed. The proposed hybrid model is intended to be stored in offline systems and to increase the speed of operation in online systems., Methods: In this paper, we proposed a new hybrid model with the compression algorithm called Pairwise and Variance Based Signal Compression Algorithm (PVBSC) for P300-based speller systems. The proposed method wasevaluated on Wadsworth BCI speller dataset. As the focus is the compression algorithm, the channel selection has been applied to increase the working speed. Channel selection was made by detecting eight channels most commonly used in the literature., Results: As the first step in the compression algorithm was segmentation, the study was repeated with 16, 32 and 64 channel lengths to see the effect of the window length. Then, to find the target character from EEG signals, we have used two different classifiers including an ensemble of LS-SVMs and ensemble of LDAs. In this study, as the best classification accuracy, 1.437 compression ratio and 94.166% accuracy rate by Ensemble of LDAs was achieved with PVBSC with 32 window lengths., Conclusions: The obtained results have shown that the proposed compression method could be confidently used in the compressing the P300 wave-containing EEG signals and reduce the data size significantly., (Copyright © 2019 Elsevier B.V. All rights reserved.)

Background and Objective: Infant cry signal carries several levels of information about the reason for crying (hunger, pain, sleepiness and discomfort) or the pathological status (asphyxia, deaf, jaundice, premature condition and autism, etc.) of an infant and therefore suited for early diagnosis. In this work, combination of wavelet packet based features and Improved Binary Dragonfly Optimization based feature selection method was proposed to classify the different types of infant cry signals., Methods: Cry signals from 2 different databases were utilized. First database contains 507 cry samples of normal (N), 340 cry samples of asphyxia (A), 879 cry samples of deaf (D), 350 cry samples of hungry (H) and 192 cry samples of pain (P). Second database contains 513 cry samples of jaundice (J), 531 samples of premature (Prem) and 45 samples of normal (N). Wavelet packet transform based energy and non-linear entropies (496 features), Linear Predictive Coding (LPC) based cepstral features (56 features), Mel-frequency Cepstral Coefficients (MFCCs) were extracted (16 features). The combined feature set consists of 568 features. To overcome the curse of dimensionality issue, improved binary dragonfly optimization algorithm (IBDFO) was proposed to select the most salient attributes or features. Finally, Extreme Learning Machine (ELM) kernel classifier was used to classify the different types of infant cry signals using all the features and highly informative features as well., Results: Several experiments of two-class and multi-class classification of cry signals were conducted. In binary or two-class experiments, maximum accuracy of 90.18% for H Vs P, 100% for A Vs N, 100% for D Vs N and 97.61% J Vs Prem was achieved using the features selected (only 204 features out of 568) by IBDFO. For the classification of multiple cry signals (multi-class problem), the selected features could differentiate between three classes (N, A & D) with the accuracy of 100% and seven classes with the accuracy of 97.62%., Conclusion: The experimental results indicated that the proposed combination of feature extraction and selection method offers suitable classification accuracy and may be employed to detect the subtle changes in the cry signals., (Copyright © 2017 Elsevier B.V. All rights reserved.)

Elderly people are commonly affected by Parkinson's disease (PD) which is one of the most common neurodegenerative disorders due to the loss of dopamine-producing brain cells. People with PD's (PWP) may have difficulty in walking, talking or completing other simple tasks. Variety of medications is available to treat PD. Recently, researchers have found that voice signals recorded from the PWP is becoming a useful tool to differentiate them from healthy controls. Several dysphonia features, feature reduction/selection techniques and classification algorithms were proposed by researchers in the literature to detect PD. In this paper, hybrid intelligent system is proposed which includes feature pre-processing using Model-based clustering (Gaussian mixture model), feature reduction/selection using principal component analysis (PCA), linear discriminant analysis (LDA), sequential forward selection (SFS) and sequential backward selection (SBS), and classification using three supervised classifiers such as least-square support vector machine (LS-SVM), probabilistic neural network (PNN) and general regression neural network (GRNN). PD dataset was used from University of California-Irvine (UCI) machine learning database. The strength of the proposed method has been evaluated through several performance measures. The experimental results show that the combination of feature pre-processing, feature reduction/selection methods and classification gives a maximum classification accuracy of 100% for the Parkinson's dataset., (Copyright © 2014 Elsevier Ireland Ltd. All rights reserved.)

The optic nerve disease is an important disease that appears commonly in public. In this paper, we propose a hybrid diagnostic system based on discretization (quantization) method and classification algorithms including C4.5 decision tree classifier, artificial neural network (ANN), and least square support vector machine (LSSVM) to diagnose the optic nerve disease from Visual Evoked Potential (VEP) signals with discrete values. The aim of this paper is to investigate the effect of Discretization method on the classification of optic nerve disease. Since the VEP signals are non-linearly-separable, low classification accuracy can be obtained by classifier algorithms. In order to overcome this problem, we have used the Discretization method as data pre-processing. The proposed method consists of two phases: (i) quantization of VEP signals using Discretization method, and (ii) diagnosis of discretized VEP signals using classification algorithms including C4.5 decision tree classifier, ANN, and LSSVM. The classification accuracies obtained by these hybrid methods (combination of C4.5 decision tree classifier-quantization method, combination of ANN-quantization method, and combination of LSSVM-quantization method) with and without quantization strategy are 84.6-96.92%, 94.20-96.76%, and 73.44-100%, respectively. As can be seen from these results, the best model used to classify the optic nerve disease from VEP signals is obtained for the combination of LSSVM classifier and quantization strategy. The obtained results denote that the proposed method can make an effective interpretation and point out the ability of design of a new intelligent assistance diagnosis system.

This paper presents a hybrid approach based on feature selection, fuzzy weighted pre-processing and artificial immune recognition system (AIRS) to medical decision support systems. We have used the heart disease and hepatitis disease datasets taken from UCI machine learning database as medical dataset. Artificial immune recognition system has shown an effective performance on several problems such as machine learning benchmark problems and medical classification problems like breast cancer, diabetes, and liver disorders classification. The proposed approach consists of three stages. In the first stage, the dimensions of heart disease and hepatitis disease datasets are reduced to 9 from 13 and 19 in the feature selection (FS) sub-program by means of C4.5 decision tree algorithm (CBA program), respectively. In the second stage, heart disease and hepatitis disease datasets are normalized in the range of [0,1] and are weighted via fuzzy weighted pre-processing. In the third stage, weighted input values obtained from fuzzy weighted pre-processing are classified using AIRS classifier system. The obtained classification accuracies of our system are 92.59% and 81.82% using 50-50% training-test split for heart disease and hepatitis disease datasets, respectively. With these results, the proposed method can be used in medical decision support systems.