Project

Design of Fuzzy Expert Systems

Updates
0 new
0
Recommendations
0 new
0
Followers
0 new
10
Reads
1 new
71

Project log

Novruz Allahverdi
added 12 research items
Introduction: An electroencephalographic (EEG) is an electrical activity which is recorded from the scalp over the sensorimotor cortex during vigilance or sleeping conditions of subjects. It can be used to detect potential problems associated with brain disorders. The aim of this study is assessing the clinical usefulness of EEG which is recorded from slow cortical potentials (SCP) training in stroke patients using deep learning (DL) algorithms. Classifier: This study introduces a DL application on classification of the brain activities in stroke patients. Deep belief network (DBN) is an effective DL algorithm which has a greedy layer wise training using Restricted Boltzmann Machines based unsupervised weight and bias evaluation and neural network based supervised training. Database: EEGs are recorded during eight SCP neurofeedback sessions from two stroke patients with a sampling rate of 256 Hz. Brain activities are labeled successful as positivity, and success indicated to the participant as negativity, if brain activation was regulated as required by the task. Preprocessing: All EEGs are filtered with a low pass filter (10 Hz). 8000 trials (500trials for each session and each patient) with 2400 data points were segmented from 2 EEGs. Methods: Hilbert-Huang Transform is applied to the trails and various numbers of Instinct Mode Functions (IMF) are obtained. High order statistics and standard statistics are extracted from IMFs to create the dataset. Dataset is normalized to a [0, 1] range. Results: The proposed DBN-based brain activity classification has discriminated positivity and negativity tasks in stroke patients and has achieved high rates of 90.30%, 96.58%, and 91.15%, for sensitivity, selectivity, and accuracy, respectively. The results show IMF-based statistical features and the DBN classifier have a clinically significant importance for EEGs from SCP training in stroke patients.
In this study, a decision-support system is presented to aid cardiologists during the diagnosis and to create a base for a new diagnosis system which separates two classes (CAD and no-CAD patients) using an electrocardiogram (ECG). 24 hour filtered ECG signals from PhysioNet were used. 15 second short-term ECG segments were extracted from 24 hour ECG signals to increase the number of samples and to provide a convenient transformation in a short period of time. The Hilbert-Huang Transform, which is effective on non-linear and non-stationary signals, was used to extract the features from short-term ECG signals. Instinct Mode Function(IMF) was extracted by applying Empirical Mode Decomposition to short-term ECG signals. The Hilbert Transform (HT) was applied to each IMF to obtain instantaneous frequency characteristics of the signal. Dataset was created by extracting statistical features from HT applied to IMF. Deep Belief Networks (DBN) which have a common use in Deep Learning algorithms were used as the classifier. DBN classification accuracy in the diagnosis of the CAD is discussed. The extracted dataset was tested using the 10-fold cross validation method.The test characteristics (sensitivity, accuracy and specificity) that are the basic parameters of independent testing in the medical diagnostic systems were calculated using this validation method. Short-term ECG signals of CAD patients and no-CAD groups were classified by the DBN with the rates of 98.05%, 98.88% and 96.02%, for accuracy, specificity and sensitivity, respectively. The DBN model achieved higher accuracy rates than the Neural Network classifier.
ABSTRACT In this study, the application of position control on a fixed track by an autonomous robot fuzzy controller approach is realized. For this purpose, a system is designed in which the real time data exchange can be done both for hardware and software. The embedded system (Atmel 2560 Integrity) is used in the hardware section to achieve the target attainment and position control with the fuzzy controller. DC motor, servo motor, ultrasonic sensor, Bluetooth module and optical sensor are controlled using this system. In addition, the desktop software is designed using the microcontroller software as well as Visual Studio 2015 platform using c# language. The coordinates (x, y) and path information sent by Altu robot (The name of the robot designed for this study) on the designed track in real time are processed with the fuzzy controller. The obtained data is displayed with the desktop software, position information, and robot motion map of Altu robot. Applications using the fuzzy approach are also tested with the conventional control method and the results are compared. Thus, the fuzzy logic approach has proved that it can provide more precise control than the conventional approach.
Novruz Allahverdi
added 2 research items
In this study, a fuzzy control system is presented to aid physicians in the diagnosis and to identify a risk value of type 2 diabetes.
In this study, Hilbert-Huang Transform (HHT) was applied to the lung sounds from RespiratoryDatabase@TR and the statistical features were calculated from the different modulations of the HHT. The statistical features were fed into the DBN to classify the lung sounds from Chronic Obstructive Pulmonary Disease (COPD) and healthy subjects.
Novruz Allahverdi
added 2 research items
What is the AI? What are the ES, knowledge engineering? Structure of the ES. Types of ESs. Design of the ESs. Example of their design. Application of the ESs in the medicine, agroculture, endustry, education and etc.