In this paper, we address the problem of identifying brain haemorrhage which is considered as a tedious task for radiologists, especially in the early stages of the haemorrhage. The problem is solved using a deep learning approach where a convolutional neural network (CNN), the well-known AlexNet neural network, and also a modified novel version of AlexNet with support vector machine (AlexNet-SVM) classifier are trained to classify the brain computer tomography (CT) images into haemorrhage or nonhaemorrhage images. The aim of employing the deep learning model is to address the primary question in medical image analysis and classification: can a sufficient fine-tuning of a pretrained model (transfer learning) eliminate the need of building a CNN from scratch? Moreover, this study also aims to investigate the advantages of using SVM as a classifier instead of a three-layer neural network. We apply the same classification task to three deep networks; one is created from scratch, another is a pretrained model that was fine-tuned to the brain CT haemorrhage classification task, and our modified novel AlexNet model which uses the SVM classifier. The three networks were trained using the same number of brain CT images available. The experiments show that the transfer of knowledge from natural images to medical images classification is possible. In addition, our results proved that the proposed modified pretrained model “AlexNet-SVM” can outperform a convolutional neural network created from scratch and the original AlexNet in identifying the brain haemorrhage.

The influence of data resampling on ensemble methods, and repeated cross-validation (RCV)-based ensemble feature selection (FS) is proposed. To evaluate the proposed method, support vector machine and its extension and recursive feature elimination were used as the underlying classification and FS techniques, respectively. Experimental evaluation was performed using four microarray datasets. The results show that especially for extremely small signature sizes, increasing ensemble size increases both classification performance and the robustness of gene selection (stability) for both RCV and bootstrap (BS). However, for ensembles of the same size, RCV outperforms BS in terms of performance and especially stability. When compared to the top results obtained by two other studies in which BS is utilised, RCV performs similar or better in terms of area under the receiver operator curve and better in terms of stability.

The features obtained in this study can potentially contribute to the neuroelectrical understanding and clinical diagnosis of ADHD.

Universal environmental contamination is a real situation that deteriorates our world step by step. The dairy factory out flowing is the second greatest source of contamination in water streams. The environmental impact of these factories can be very high, especially due to the discharge of wastewater with high content of organic matter and nutrients. These problems can be analyzed only after performing factual study of various physicochemical characteristics. In the presented study, physicochemical parameters like, temperature, pH, COD, TDS, TS and SS were taken into account. Another purpose of this study is to ascertain university student's awareness and consciousness against general and dairy products related environments. These levels were evaluated by the survey method. The data obtained from the questionnaire were analyzed using SPSS 20.0. Results showed that the public and company owners/ employees in particular should be informed about the seasonal and cheese variety dependent patterns in environmental pollution.

Objective: In our study the factors related to anesthesia and peroperative variables associated with postoperative mortality among patients aged ≥65 years who had undergone orthopedic surgery were assessed. Methods: Reports on patients aged ≥65 years who had undergone orthopedic surgery between 2015 and 2017 were investigated retrospectively. Results: A total of 135 patients were included in the study. The operations comprised implantations of total hip prosthesis in 26%, total knee prosthesis in 18%, fixation of lower extremity fractures in 24, and upper extremity fractures in 14%, and amputation surgery in 17% of the patients. The postoperative mortality rates were highest (76.9%) among patients who underwent amputation surgery (p<0.05). It was found that anesthesia type, whether regional or general, was not related to mortality. Mortality was found to be associated with increasing age, ≥3 ASA score, emergency surgery, ≥3 accompanying diseases, prolonged preoperative hospital stay and low preoperative hemoglobin (Hb) values (p<0.05). Patients developing postoperative complications, those who were monitored in intensive care unit (ICU) and required mechanical ventilator (MV), and patients with prolonged ICU and hospital stay had higher mortality rates (p<0.05). 9% of all patients were determined dead. Conclusion: Among geriatric orthopedic surgery patients, apart from gender and anesthesia method, increasing age, high ASA scores, emergency surgery, the number of accompanying diseases, duration of preoperative hospital stays, low preoperative Hb values, postoperative complications requiring ICU-MV and prolonged ICU and hospital stays were all factors that affected postoperative mortality. We believe that detailed preoperative assessment and perioperative clinical management are essential if postoperative prognosis after geriatric orthopedic surgery is to be improved.