Diabetes is a metabolic disease that occurs due to high blood sugar levels in the body. If it is not treated, diabetes-related health problems may occur in many vital organs of the body. With the latest techniques in machine learning technologies, some of the applications can be used to diagnose diabetes at an early stage. In this study, the data set from the laboratories of Medical City Hospital Endocrinology and Diabetes Specialization Center Al Kindy Training Hospital was used. The dataset consists of 3 different classes: normal, pre-diabetes and diabetes. The obtained diabetes dataset was classified using Long Short-Term Memory (LSTM), Convolutional Neural Network (CNN) and Gated Recurrent Unit (GRU) deep learning methods. The classification performance of each algorithm was evaluated with accuracy, precision, sensitivity and F score performance parameters. Among the deep learning methods, 96.5% classification accuracy was obtained with the LSTM algorithm, 94% with the CNN algorithm and 93% with the GRU algorithm. In this study, the Permutation Feature Importance (PFI) method was also used to determine the effect of features in the data set on classification performance. With this method, study reveals that the HbA1c feature is an important parameter in the used deep learning methods. Both the results obtained with the LSTM algorithm and the determination of the most important feature affecting the classification success reveal the originality of the study. It shows that the obtained results will provide healthcare professionals with a prognostic tool for effective decision-making that can assist in the early detection of the disease.

Classification of skin diseases is a important isssue for early diagnosis and treatment. The process of determining the disease by the specialist physician also delays the treatment process to be applied to the patient. Computer-aided diagnosis systems play an important role in early diagnosis and initiation of treatment by minimizing such processes. In this study, high-performance classification of skin lesions was performed by using Deep Learning models. Dataset was ISIC data set, dataset were expanded by using data augmentation techniques. In the images in this dataset, there are images of Actinic Keratosis, Dermatofibroma, Pigmented Benign Keratosis, Seborrheic Keratosis, Vascular Lesion skin diseases. The data set was classified by Deep Learning models by using the supervised learning method.. SequeezeNet, AlexNet, GoogleNet, Vgg-19, ResNet101, DenseNet201, ResNet-50, ResNet-18, Vgg-16 DL models were used for classification. To evaluate of classification success of Deep Learning models, confusion matrix and F1-score, precision, sensitivity and accuracy metrics obtained from the matrix were used. According to the F1-score, the most successful model is Vgg16 with 97.41%, while the highest accuracy rate obtained by ResNet18 with 98.06%. High success rate shows that such systems can be used for diagnosis and treatment processes.

Determination and investigation of incidents affecting Power Quality (PQ) is very important for consumers. In this study, estimation of PQ events is obtained to determine the disturbances of PQ by using Empirical Wavelet Transform (EWT) and Discrete Wavelet Transform (DWT) methods and with this estimated parameters. PQ disturbances were examined with Support Vector Machine (SVM), Artificial Neural Network (ANN) and Adaptive Neuro-Fuzzy Inference System (ANFIS) classification methods. Voltage signals (sag, swell, interruption, transient and normal) used in the classification of PQ disturbances were recorded from grid with the aid of a microcontroller based on device designed with a sampling frequency of 6.4 kHz. Classification consequences using Machine Learning Methods show that DWT outperforms over EWT for feature extraction processing and the classification accuracy is tabled. Classification by ANN and ANFIS through the use of conjecture parameters in PQ disturbances based on DWT Method has been recommended.

EEG signals contain a lot of information about brain functions.Wave forms of EEG signs are similar to other forms of brain signs.In this study, firstly power spectrum was obtained by applying Auto-Regressive Burg (AR-Burg) method to the EEG signals. The data obtained from the analysis of AR-Burg was classified with Support Vector Machines (SVM). Classification achievements were investigated for some kernel functions used in SVM. Regularization parameter and kernel parameter that increase the success of classification were calculated with a novel approach Particle Swarm Optimization (PSO) technique. Such that global best results for classification were searched by investigating optimum values. As a result of this study a new algorithmic approach presented for the diagnosis of epilepsy patients.

The amount of electric energy produced by photovoltaic panels depends on air temperature, humidity rate, wind velocity, photovoltaic module temperature, and particularly solar radiation. Being aware of the behaviour patterns of the panels to be used in project and planning works regarding photovoltaic applications will set forth a realistic expense form; therefore, erroneous investments will be avoided, and the country budget will benefit from added value. The power ratings obtained from the photovoltaic panels and the environmental factors were measured and recorded for a year by the measurement stations established in three diverse regions (Adiyaman-Malatya-Sanliurfa). In the developed artificial neural network models, the estimation accuracy was 99.94%. Furthermore, by taking the data of the General Directorate of Meteorology as a reference, models of artificial neural networks were developed using the data from Adiyaman province for training; by using Malatya and Sanliurfa as test data, 99.57% estimation accuracy was achieved. With the artificial neural network models developed as a result of the study, the energy efficiency for the photovoltaic energy systems desired to be established by using meteorological parameters such as temperature, humidity, wind, and solar radiation of various regions anywhere in the world can be estimated with high accuracy.