Hüseyin Polat

Combining Neural Network and Genetic Algorithm for Prediction of Lung Sounds

Recognition of lung sounds is an important goal in pulmonary medicine. In this work, we present a study for neural networks–genetic algorithm approach intended to aid in lung sound classification. Lung sound was captured from the chest wall of The subjects with different pulmonary diseases and also from the healthy subjects. Sound intervals with duration of 15–20 s were sampled from subjects. From each interval, full breath cycles were selected. Of each selected breath cycle, a 256-point Fourier Power Spectrum Density (PSD) was calculated. Total of 129 data values calculated by the spectral analysis are selected by genetic algorithm and applied to neural network. Multilayer perceptron (MLP) neural network employing backpropagation training algorithm was used to predict the presence or absence of adventitious sounds (wheeze and crackle). We used genetic algorithms to search for optimal structure and training parameters of neural network for a better predicting of lung sounds. This application resulted in designing of optimum network structure and, hence reducing the processing load and time.

A Simple Computer-Based Measurement and Analysis System of Pulmonary Auscultation Sounds

Listening to various lung sounds has proven to be an important diagnostic tool for detecting and monitoring certain types of lung diseases. In this study a computer-based system has been designed for easy measurement and analysis of lung sound using the software package DasyLAB. The designed system presents the following features: it is able to digitally record the lung sounds which are captured with an electronic stethoscope plugged to a sound card on a portable computer, display the lung sound waveform for auscultation sites, record the lung sound into the ASCII format, acoustically reproduce the lung sound, edit and print the sound waveforms, display its time-expanded waveform, compute the Fast Fourier Transform (FFT), and display the power spectrum and spectrogram.

Software Development for the Analysis of Heartbeat Sounds with LabVIEW in Diagnosis of Cardiovascular Disease

In this paper, a time-frequency spectral analysis software (Heart Sound Analyzer) for the computer-aided analysis of cardiac sounds has been developed with LabVIEW. Software modules reveal important information for cardiovascular disorders, it can also assist to general physicians to come up with more accurate and reliable diagnosis at early stages. Heart sound analyzer (HSA) software can overcome the deficiency of expert doctors and help them in rural as well as urban clinics and hospitals. HSA has two main blocks: data acquisition and pre-processing, time–frequency spectral analyses. The heart sounds are first acquired using a modified stethoscope which has an electret microphone in it. Then, the signals are analysed using the time–frequency/scale spectral analysis techniques such as STFT, Wigner–Ville distribution and wavelet transforms. HSA modules have been tested with real heart sounds from 35 volunteers and proved to be quite efficient and robust while dealing with a large variety of pathological conditions.

Resident activity recognition in smart homes by using artificial neural networks

Recognition and detection of human activity is one of the challenges in smart home technologies. In this paper, three algorithms of artificial neural networks, namely Quick Propagation (QP), Levenberg Marquardt (LM) and Batch Back Propagation (BBP), have been used for human activity recognition and compared according to performance on Massachusetts Institute of Technology (MIT) smart home dataset. The achieved results demonstrated that Levenberg Marquardt algorithm has better human activity recognition performance (by 92.81% accuracy) than Quick Propagation and Batch Back Propagation algorithms.

Diagnosis of Chronic Kidney Disease Based on Support Vector Machine by Feature Selection Methods

As Chronic Kidney Disease progresses slowly, early detection and effective treatment are the only cure to reduce the mortality rate. Machine learning techniques are gaining significance in medical diagnosis because of their classification ability with high accuracy rates. The accuracy of classification algorithms depend on the use of correct feature selection algorithms to reduce the dimension of datasets. In this study, Support Vector Machine classification algorithm was used to diagnose Chronic Kidney Disease. To diagnose the Chronic Kidney Disease, two essential types of feature selection methods namely, wrapper and filter approaches were chosen to reduce the dimension of Chronic Kidney Disease dataset. In wrapper approach, classifier subset evaluator with greedy stepwise search engine and wrapper subset evaluator with the Best First search engine were used. In filter approach, correlation feature selection subset evaluator with greedy stepwise search engine and filtered subset evaluator with the Best First search engine were used. The results showed that the Support Vector Machine classifier by using filtered subset evaluator with the Best First search engine feature selection method has higher accuracy rate (98.5%) in the diagnosis of Chronic Kidney Disease compared to other selected methods.

Finding a best parking place using exponential smoothing and cloud system in a metropolitan area

Finding a vacant place to park cars in the rush hour is time-consuming and even may be frustrating for the drivers. In some studies, vehicles are equipped with communicative tools called On Board Units (OBUs), which come along with roadside devices known as Roadside Units (RSUs), which allow the drivers to communicate each other and trace a vacant parking place easily. Previous systems work with connection of sensors all over the road and parking space and may result in spending much time to find a parking place, occupancy of the empty parking place until the car gets to the desired location, requirement for an additional hardware, wired network communication, and security issues. In this paper, we propose an exponential smoothing and multi-objective decision-making by using cloud-based methods to find the best parking place, taking into consideration of the park-cost for the driver. The proposed system uses the cellular base stations to eliminate the cost of the RSUs and the sensors. The results of our simulations via NS-2 network simulator confirm the efficiency of the proposed model.

Examination of the Effects of Degeneration on Vertebral Artery by Using Neural Network in Cases With Cervical Spondylosis

The scope of this study is to diagnose vertebral arterial inefficiency by using Doppler measurements from both right and left vertebral arterials. Total of 96 patients’ Doppler measurements, consisting of 42 of healthy, 30 of spondylosis, and 24 of clinically proven vertebrobasillary insufficiency (VBI), were examined. Patients’ age and sex information as well as RPSN, RPSVN, LPSN, LPSVN, and TOTALVOL medical parameters obtained from vertebral arterials were classified by neural networks, and the performance of said classification reached up to 93.75% in healthy, 83.33% in spondylosis, and 97.22% in VBI cases. The area under ROC curve, which is a direct indication of repeating success ratio, is calculated as 92.3%, and the correlation coefficient of the classification groups is 0.9234. It is also demonstrated that those medical parameters of age and systolic velocity, which were applied into the neural networks, were more effective in developing vertebral deficiency.

The effects of DoS attacks on ODL and POX SDN controllers

The use of Software Defined Network (SDN) in recently networking architecture has brought tremendous advantage in computer networking technology. Administrative issues such as routing, security and load balancing can be centralized and automated in SDN controllers. Controllers have been an integral part of the SDN architecture enabling intelligent networking. However, because all the packets are transmitted to the controller, any flooded packet from an attacker who gets access to SDN network may lead to Denial of Service (DoS) attack. In this paper, the effect of DoS attack on bandwidth of two communicating hosts in SDN network for Opendaylight (ODL) and POX controllers was investigate. We observed that the bandwidth was reduced as attack increases and the response time was also too high. We also find out that, even after a flow table has been installed in switch, it was impossible for it to be reinstalled again if a flow timeout has been reached due to a controller handling too many packet-in events and error notification from the switches.

Energy consuption monitoring with smart lamp socket for smart grid via M2M platform

Main problem of energy is limited energy resources, because the energy consumption rapidly increases. Furthermore, efficiently use of energy is a way to reduce the problem. In this study, a smart lamp socket unit was developed to report the consumption values of the energy and to measure energy consumption in the lighting area where the consumption of electric energy is generally high. The smart lamp socket is able to communicate via wireless network connection and internet protocol. A machine to machine (M2M) platform has been developed for easily accessible user interaction, energy consumption tracking, management and reporting thanks to the smart lamp socket. Using the M2M platform, many smart lamp socket unit can be communicated at the same time. Thus any costumer can directly manage to save energy according to reported consumption data and observed the energy consumption in the lighting fields.