Prediction of Coronary Artery Disease Using Machine Learning Techniques with Iris Analysis.

Coronary Artery Disease (CAD) occurs when the coronary vessels become hardened and narrowed, limiting blood flow to the heart muscles. It is the most common type of heart disease and has the highest mortality rate. Early diagnosis of CAD can prevent the disease from progressing and can make treatment easier. Optimal treatment, in addition to the early detection of CAD, can improve the prognosis for these patients. This study proposes a new method for non-invasive diagnosis of CAD using iris images. In this study, iridology, a method of analyzing the iris to diagnose health conditions, was combined with image processing techniques to detect the disease in a total of 198 volunteers, 94 with CAD and 104 without. The iris was transformed into a rectangular format using the integral differential operator and the rubber sheet methods, and the heart region was cropped according to the iris map. Features were extracted using wavelet transform, first-order statistical analysis, a Gray-Level Co-Occurrence Matrix (GLCM), and a Gray Level Run Length Matrix (GLRLM). The model's performance was evaluated based on accuracy, sensitivity, specificity, precision, score, mean, and Area Under the Curve (AUC) metrics. The proposed model has a 93% accuracy rate for predicting CAD using the Support Vector Machine (SVM) classifier. With the proposed method, coronary artery disease can be preliminarily diagnosed by iris analysis without needing electrocardiography, echocardiography, and effort tests. Additionally, the proposed method can be easily used to support telediagnosis applications for coronary artery disease in integrated telemedicine systems.

Exposure assessment of radio frequency electromagnetic field levels in hospitals of Samsun Province, Turkey.

With the increase in the use of different types of electronic systems used inside and outside the hospital, the electromagnetic medium in the hospital has changed significantly. The increase in the number and type of EMF sources in sensitive mediums such as hospitals has led researchers to measure EMFs to assess the potential risk to patients and staff. For this reason, this study aims to determine the radio frequency electromagnetic field (RF-EMF) levels to which patients and staff are exposed voluntarily or unintentionally in the hospital environment and to control their compliance with the limits defined in the standards. In order to achieve these goals, three different types of RF-EMF measurements were carried out as, short-term, long-term, and band selective in 21 state hospitals in the Samsun Province, Turkey. Total RF-EMF in the band between 100 kHz and 3 GHz is measured using PMM-8053, while band selective is conducted using SRM-3006 in the frequency range from 27 MHz up to 3 GHz. The recorded RF-EMF values were statistically analyzed, and the main RF-EMF sources in the medium were determined. The highest average RF-EMF exposure level obtained for short-term measurements was 2.52 V/m. For long-term measurements, the highest average RF-EMF was 3.11 V/m and the highest mean RF-EMF was 2.29 V/m. Within our measurements, the limit of 3 V/m set by the Information and Communication Technologies Authority (ICTA) was exceeded in the hospital, although the highest RF-EMF was below the limit level set by the International Commission on Non-Ionizing Radiation Protection (ICNIRP). Long-term measurement results showed that the RF-EMF level at midday was higher than at night; the highest RF-EMF was measured in the afternoon and during evening hours. The mean RF-EMF levels are 1.01 V/m, 1.15 V/m, 1.12 V/m, and 0.84 V/m, for morning, afternoon, evening, and night respectively. The RF-EMF level measured during the afternoon hours maybe about 37% higher than the RF-EMF levels measured at night. The main sources of total RF-EMF in the environment determined from the band-selective RF-EMF results were base stations located outside the hospital and their contribution to total RF-EMF was 92.6%. Systems that make the most contribution to the RF-EMF in the environment are base stations using the LTE 800, GSM 900, GSM 1800, LTE 1800, and UMTS 2100 frequency bands. Among these, the UMTS 2100 frequency band gave the highest contribution with 40.42%. With the use of these main RF-EMF sources, an empirical model that helps in computing the total E of the medium with 99.8% accuracy was proposed.

Comprehensive radiofrequency electromagnetic field measurements and assessments: a city center example.

In this study, radiofrequency electromagnetic field (RF-EMF) measurements were carried out between 2016 and 2018 in one the largest provinces of Turkey; measurement results are compared with the limit values determined by International Commission on Non-Ionizing Radiation Protection (ICNIRP) and Turkey's Information and Communication Technologies Authority (ICTA). In the first stage of a three-phase evaluation, short-term RF-EMF measurements were conducted in 500 locations over a 2-year period. In the second stage, short-term RF-EMF measurement results were analyzed to determine selected locations for long-term RF-EMF measurements to be carried out, including variation of RF-EMF during the day. In the last stage, band selective measurements were taken and the main sources of RF-EMF in the environment were determined. Overall, RF-EMF values do not exceed the limits determined by ICNIRP and ICTA, and they are below levels that threaten public health. In the short-term RF-EMF measurements, RF-EMF levels doubled after fourth generation (4G) systems were introduced. In the long-term RF-EMF measurements, RF-EMF values in the day are 35.4% more than at night. The total measured RF-EMF within the city center is 99.3% base station sourced. Among the six main RF-EMF sources, the devices operating in UMTS2100 band have the most contribution to total RF-EMF of medium with 31.2%. Additionally, we found short-term average electric field strength data are best described by the "exponential distribution," while long-term RF-EMF measurement data is best described by the "Burr distribution."

AN EMPIRICAL STUDY: THE IMPACT OF THE NUMBER OF USERS ON ELECTRIC FIELD STRENGTH OF WIRELESS COMMUNICATIONS.

As a result of the drastic increase in the number of mobile device users, there is considerable public debate about possible health hazards especially due to base stations and Wi-Fi access points. For this reason, in this study the effects of the number of users in a base station and wireless fidelity (Wi-Fi) access point on electric field strength (E) levels were investigated using real-time measurements. Two-stage E measurements were performed on Ondokuz Mayis University's (OMU) Kurupelit Campus with a PMM-8053 and SRM-3006 electromagnetic field (EMF) meter. In the first stage, 24-h measurements were performed with PMM-8053 at the location where the maximum E was measured and from which the busiest times of the day were then determined. The relationship among band selective E values was assessed using the number of users per minute provided by three cellular system operators for the location. Upper and lower bounds of E according to the number of users were calculated, and then an empirical model that helps calculate the E of medium with 86% accuracy was proposed. In the second stage, the effect of the number of users in a Wi-Fi access point on E level was investigated. For this purpose, the measurement environment was set as including one Wi-Fi access point with needed measurement devices. The number of users was increased as per user per minute. The number of users was validated with the data obtained from OMU IT Department. Using the measurement result, a model with a 96% accuracy between the E value in the environment and the number of users accessing the Wi-Fi system is proposed. With the use of these models, E level in the medium can be determined without using any EMF meters, thus precautions can be taken to stay within regulatory limits.

MEASUREMENT AND EVALUATION OF ELECTRIC FIELD STRENGTH LEVELS IN PRIMARY AND SECONDARY SCHOOLS IN A PILOT REGION.

In this study, in order to evaluate the exposed radiofrequency electromagnetic field (RF-EMF) levels, and to control their compliance with the limits determined by International Commission on Non-Ionizing Radiation Protection (ICNIRP), extensive short-term/band-selective and long-term RF-EMF measurements were conducted at 92 primary and secondary schools in the Ilkadim district of Samsun/Turkey. The measurements were performed once each in May, June, October and December in 2016, using the PMM-8053 EMF meter. It was seen from the measurement results that the maximum average electric field strength (Eavg) was recorded, 2.34 V/m, in October, when students were at school. It was concluded from the measurement results that the measured Eavg levels recorded at 92 schools were below the limits determined by ICNIRP. According to the band-selective measurement results performed using a Narda SRM-3006 EMF meter, the five main electric field strength (E) sources that had the most contribution in total E were LTE800, GSM900, GSM1800, UMTS2100 and WLAN services. With the use of these main E sources, an empirical model was then proposed that helps to determine the total E with 99.6% accuracy. It was also concluded from the long-term broadband measurement result that the number of active users affected the total E in the medium directly, and that the measured E levels were significantly higher in daytime than those of recorded in night-time. In the final stage of the study, all measurement results were transferred on scaled color maps. The use of these maps helped to determine and maintain control on the levels of RF-EMF exposure at schools using, or intending to install, such systems, and also to take measures for future precautions.

LONG-TERM ELECTROMAGNETIC FIELD MEASUREMENT AND ASSESSMENT FOR A SHOPPING MALL.

As a result of the dense deployment of wireless devices and base stations, measuring and evaluating the electromagnetic (EM) exposure levels they emit have become important to human health especially if they exceed the limits defined in the standards. Base stations, Wi-Fi equipment and other electronic devices are used heavily, especially in densely crowded places like shopping centers. In this study, electric field strength (E) measurements were conducted at one of the largest shopping malls in Turkey. Broadband E measurements were performed using PMM 8053 EM field strength meter for 24 h a day for the duration of one week while frequency selective measurements were carried out with SRM-3006 EM field strength meter. It is concluded from the measurements that the mean measured total E in the band between 100 kHz and 3 GHz is 0.59 V/m while the maximum E is 7.88 V/m, which are both below the limit determined by International Commission on Non-Ionizing Radiation Protection. Evolutions show that E can increase by up to 55% during the daytime. Analyses demonstrate that 71.3% of total E is caused by UMTS2100, 16.3% is produced by GSM900, 6.2% by LTE, 3.5% by Wi-Fi, and 2.7% is generated by devices that use the remaining frequency bands. Based on the detailed statistical analysis of long-term E measurement results, it can be concluded that the measured E levels are not in normal distribution and that they are statistically different with respect to days. Furthermore, distribution of E can be best modeled with the non-parametric approach.