Exemplar deep and hand-modeled features based automated and accurate cerebral hemorrhage classification method.

BACKGROUND: Cerebral hemorrhage (CH) is a commonly seen disease, and an accurate diagnosis of the type of CH is a very crucial step in treatment. Therefore, CH requires a prompt and accurate diagnosis. To simplify this process, an accurate CH classification model is presented using a machine learning technique. MATERIAL AND METHOD: A computed tomography (CT) image dataset was collected retrospectively in this research. This dataset contains 9818 images with five categories. An exemplar fused feature generator is presented to classify these features. This generator uses pre-trained AlexNet, local binary pattern (LBP), and local phase quantization (LPQ). The neighborhood component analysis (NCA) method selects the top features, and the chosen feature vector is classified on the support vector machine. RESULTS: Six validation methods are utilized to calculate the performance of the presented exemplar fused features and NCA-based CH classification model. This model attained 97.47%, 96.05%, 95.21%, 93.62%, 91.28% and 96.34% accuracies using five hold-out validations and ten-fold cross-validation respectively. CONCLUSIONS: The calculated results clearly demonstrate the success and robustness of the introduced exemplar fused feature generation and NCA-based model. Furthermore, this model can be used in emergency services to overcome a prompt diagnosis of CH.

Application of substitution box of present cipher for automated detection of snoring sounds.

BACKGROUND AND PURPOSE: Snoring is one of the sleep disorders, and snoring sounds have been used to diagnose many sleep-related diseases. However, the snoring sound classification is done manually which is time-consuming and prone to human errors. An automated snoring sound classification model is proposed to overcome these problems. MATERIAL AND METHOD: This work proposes an automated snoring sound classification method using three new methods. These methods are maximum absolute pooling (MAP), the nonlinear present pattern, and two-layered neighborhood component analysis, and iterative neighborhood component analysis (NCAINCA) selector. Using these methods, a new snoring sound classification (SSC) model is presented. The MAP decomposition model is applied to snoring sounds to extract both low and high-level features. The presented model aims to attain high performance for SSC problem. The developed present pattern (Present-Pat) uses substitution box (SBox) and statistical feature generator. By deploying these feature generators, both textural and statistical features are generated. NCAINCA chooses the most informative/valuable features, and these selected features are fed to k-nearest neighbor (kNN) classifier with leave-one-out cross-validation (LOOCV). The Present-Pat based SSC system is developed using Munich-Passau Snore Sound Corpus (MPSSC) dataset comprising of four categories. RESULTS: Our model reached an accuracy and unweighted average recall (UAR) of 97.10 % and 97.60 %, respectively, using LOOCV. Moreover, a nocturnal sound dataset is used to show the universal success of the presented model. Our model attained an accuracy of 98.14 % using the used nocturnal sound dataset. CONCLUSIONS: Our developed classification model is ready to be tested with more data and can be used by sleep specialists to diagnose the sleep disorders based on snoring sounds.

An automated snoring sound classification method based on local dual octal pattern and iterative hybrid feature selector.

In this research, a novel snoring sound classification (SSC) method is presented by proposing a new feature generation function to yield a high classification rate. The proposed feature extractor is named as Local Dual Octal Pattern (LDOP). A novel LDOP based SSC method is presented to solve the low success rate problems for Munich-Passau Snore Sound Corpus (MPSSC) dataset. Multilevel discrete wavelet transform (DWT) decomposition and the LDOP based feature generation, informative features selection with ReliefF and iterative neighborhood component analysis (RFINCA), and classification using k nearest neighbors (kNN) are fundamental phases of the proposed SSC method. Seven leveled DWT transform, and LDOP are used together to generate low, medium, and high levels features. This feature generation network extracts 4096 features in total. RFINCA selects 95 the most discriminative and informative ones of these 4096 features. In the classification phase, kNN with leave one out cross-validation (LOOCV) is used. 95.53% classification accuracy and 94.65% unweighted average recall (UAR) have been achieved using this method. The proposed LDOP based SSC method reaches 22% better result than the best of the other state-of-the-art machine learning and deep learning-based methods. These results clearly denote the success of the proposed SSC method.

A novel local senary pattern based epilepsy diagnosis system using EEG signals.

Epilepsy is a critical and widely seen neurological disorder for people and electroencephalogram (EEG) signals are used to diagnose epilepsy. To accurately diagnose epilepsy, distinctive features of the EEG signals should be extracted. Therefore, a novel texture descriptor is presented for distinctive feature extraction in this study and an EEG recognition method is proposed. The proposed method consists of four main phases. These are feature extraction, feature concatenation, feature reduction and classification. Firstly, the EEG signal is divided into 1 × 25 size of overlapping blocks and these blocks are converted to 2 dimensional blocks with size of 5 × 5. Because, the proposed novel local senary pattern (LSP) uses 5 × 5 size of blocks for feature extraction. 1536 Features are extracted using the proposed LSP. The proposed LSP is used ternary function to extract features and as we know that the main problem of the ternary function is to find optimal threshold value. Therefore, we used 10 threshold values by using standard deviation function and 1536 × 10 = 15,360 features are extracted from an EEG signal. In the feature combining phase, these features are concatenated. In order to reduce these features, a neighborhood component analysis based feature reduction method is used. In the classification phase support vector machine, k nearest neighborhood, quadratic discriminant analysis and linear discriminant analysis are utilized as the classifiers. To test success of the proposed method, the widely used EEG signals dataset which is Bonn University EEG database is used and 7 cases are defined for testing using this database and the proposed method achieved 93.0% classification accuracy for 5 classes case. The obtained results and comparisons clearly indicated success of the proposed LSP based method.