No abstract

No abstract

No abstract

Chest X-Ray is a radiological examination that is commonly used in clinical practice and is easy to access. Deep convolutional neural networks (DCNN) are used to make the computer-aided diagnosis (CAD) of diseases on chest radiography. Deep convolutional neural networks help the radiologist to diagnose better. In this study, the ChestX-Ray14 data set was examined to assess performance modern deep learning networks in diagnosing chest diseases. X-Ray image quality was improved by applying a three-step process including crop, histogram equalization and contrast-limited adaptive histogram equalization to the data sets. For training and validation purposes, images in the dataset were applied to the model with and without preprocessing. It was determined that the processed datasets provided more accurate results than the original images. AlexNet, ResNet50, and GoogLeNet deep learning architectures were used to determine the presence of chest disease. The performances of these models, which generally classify normal and abnormal results from chest radiographs, were analyzed using preprocessed ChestX-Ray14 datasets and comparative evaluations were made. The most accurate was the ResNet architecture, where we used the preprocessed datasets to detect abnormalities, with 91.46% accuracy and 0.9584 area under curve (AUC) results.

The development of modern electronic systems and increasing number of application areas (computers, office equipment, rectifiers, converters, speed control devices, uninterruptible power supplies, switched power supplies) has led to harmonic generation and reduced energy efficiency. The majority of loads are inductive in nature and the draw of reactive power has increased in networks and transmission lines resulting in problems with power quality. In addition to efficient power flow in transmission systems, there is also a need to compensate for the reactive power flow in order the meet the requirements of the load and system. As an alternative to traditional solutions, FACTS (Flexible Alternating Current Transmission Systems) has been developed in order to operate electrical systems efficiently and improve stability and power quality. Technological applications such as SVC, STATCOM, SSSC and active harmonic filter are becoming widespread in order to improve power quality. In this study, applications within the scope of FACTS systems are explained and analysis of a fixed capacitor-thyristor controlled reactor (FC-TCR) to improve power factor is discussed. A circuit model of the FC-TCR is developed as a simulation and used to investigate how power factor may be kept within desired limits by adjusting the firing angle of the thyristors under different load conditions. A comparative evaluation has been carried out to determine the effect of FC-TCR by presenting results before and after the load compensation process is applied. From the simulation it is observed that reactive power compensation can be achieved even for varying linear loads.