Nowadays many companies and institutions are interested in learning what do people think and want. Many studies are conducted to answer these questions. That's why, emotions of people are significant in terms of instructional design. However, processing and analysis of many people's ideas and emotions is a challenging task. That is where the 'sentiment analysis' through machine learning techniques steps in. Recently a fast digitalization process is witnessed. Anadolu university, that serves 1 million distant students, is trying to find its place in this digital era. A learning management system (LMS) that distant students of the Open Education Faculty (Açıköğretim Fakültesi) is developed at the Anadolu University. Interaction with students is the clear advantage of LMS's when compared to the hard copy materials. Book, audio book (mp3), video and interactive tests are examples of these materials. 6059 feedbacks for those online materials was scaled using the triple Likert method and using machine learning techniques sentiment analysis was performed in this study. 0.775 correctness ratio was achieved via the Logistic regression algorithm. The research concludes that machine learning techniques can be used to better understand learners and how they feel.

Özet: Bu çalışmanın amacı, Matrix Laboratory (MATLAB) programı ile görüntü işleme ve analizi yönteminin sağlık alanında kullanılabilirliğini değerlendirmektir. Gelişen teknoloji ile birlikte modern cihazların sağlık alanında kullanımı artmıştır. Buna paralel olarak son zamanlarda tıpta görüntü işleme tekniklerinin kullanımı da yaygınlaşmaya başlamıştır. Bu teknikler hekimlere zaman, maliyet, tedavi ve teşhis konusunda büyük kolaylık sağlamaktadır. Özellikle pediatrik olgularda doğumsal ya da travmatik katarakt cerrahisi öncesi göz içi merceği ölçümü için görüntü işleme teknikleri hekimlere yol gösterici olabilir. Ayrıca mental retardasyonda (zekâ geriliği durumu) ya da Alzheimer hastalarında katarakt cerrahisi öncesi optik biyometri zor olabilir. Bu tür hastalarda başka nedenlerle çekilen Manyetik Rezonans (MR) görüntülerinden göz içi mercek gücü ölçümü için MATLAB programı kullanılabilir. Görüntü işleme genel olarak resimsel bilgilerin analizine yönelik bir yöntem olarak tanımlanabilir. Bu çalışmada, MATLAB programının görüntü işleme sürecinin sağlık alanında kullanılabilirliğini değerlendirmek amacıyla Eskişehir Osmangazi Üniversitesi Tıp Fakültesi Göz Hastalıkları Anabilim Dalı'na 08/03/2015-08/05/2016 tarihleri arasında başvuran hastalardan rutin göz muayenesi pratiğinde Orbita MR endikasyonu olan hastalar çalışmaya dâhil edilmiştir. Bu hastalar üzerinde Göz Hastalıkları Anabilim Dalı'nda optik biyometri çalışılmıştır. Eskişehir Osmangazi Üniversitesi Tıp Fakültesi Radyoloji Anabilim Dalı'nda ileri görüntüleme işlemlerinin yapıldığı Advantage Workstation'da (AW) aynı hastalar üzerinde bulbus oküli çap değerlendirmesi yapılmıştır. GE 750w 3T MR cihazı kullanılarak elde edilen MR görüntüleri üzerinde Codonics Clarity Viewer programı, MATLAB programı ve Lenstar cihazı kullanılarak Ön Kamara Derinliği (ÖKD), Lens Kalınlığı (LK) ve Aksiyel Uzunluk (AU) hesaplamaları yapılmıştır. Üç farklı teknikle hesaplanan bu ölçümler istatistiksel yöntemler ile karşılaştırılmıştır. Karşılaştırmalar sonucunda; MATLAB bulguları ile Lenstar bulguları arasında anlamlı bir fark bulunmamıştır (AU için p=0.342, ÖKD için p=0.091, LK için p=0.766). Ayrıca, MATLAB'e ait medyan (Q1-Q3) bulgularının Codonics Clarity Viewer bulgularına kıyasla Lenstar bulgularına daha yakın olduğu görülmüştür.

In today's economic conditions, interest in second hand products has increased. Especially secondhand car or vehicles have a wide customer base. In the sector which has a workshop market, it is very important to make fast sales, to make the right pricing and to calculate the ideal prices of the cars in order to exchange at the right price. With linear regression analysis secondhand in such cases first determination of variables with effect on price, then it is possible to calculate the price by establising estimating model. In this study, the model was established by determining 23 of 78 variables affecting the price such as price, brands and model years of 5041 secondhand cars. The Determination Rate (R 2) of these 23 variables was found to be 89.1%. Then, by using this regression model, second hand prices of the cars were estimated via machine learning algorithm. The data set is divided into two as training and test data (70-30% and 80-20%). As a result of the study, it was determined the affinities between the real values and the estimated values. The proximity rate (±%) calculated in result of study shows affinity intensity of the estimation results to the true results. Via the prediction model established as a result of machine learning, the predictive accuracy rate was found to be 81.15% according to the 10% proximity of the correct results (upper limit; 110%, lower limit; 90%). According to the results, it is thought that machine learning technique could be secondhand to estimate second hand car prices. However, it is possible to reach a better estimation rate with a data set with more units and different variables.

Nowadays, many firms and companies are curious about what people think and want and they are working in this direction. For this reason, it is tried to learn the ideas and emotions of people in various ways. However, as it is impossible to process and analyze a large number of emotions and thoughts with human hands, emotion analysis gain more importance. The emotions and thoughts of the people are analyzed and acted according to these requests through the emotion analysis which is quite functional in social networks. The aim of this study is to realize the learning with the data sets obtained from the interpretations made to the social platforms of the determined brands and to transfer the subject of the emotion analysis to the researchers in the best way. The range of accuracy rates reached is wide because of the disadvantages such as not paying attention to the rules of writing on social media or other digital platforms. In our study, a accuracy rate of 70% was achieved. This demonstrates the usefulness of machine learning in interpretation classification and emotion analysis.

Background: Liberal fasting regimens, which support clear fluid intake up to 1 h before surgery in children scheduled for elective surgery, are taking their place in guidelines.However, because of the lack of publications that investigate the gastric emptying time in preoperative obese children, the practice of 1-hour clear fluid fasting in obese children remained at the level of recommendation with weak evidence. Aims:The primary aim was to investigate whether there is a difference in gastric emptying times between obese and non-obese children after preoperative intake of 3 mL/kg clear liquid containing 5% dextrose by using ultrasound.Methods: A total of 70 children were included in the study in two groups, 35 obese and 35 non-obese, aged 6-14 years, who were scheduled for elective surgery. The baseline antral cross-sectional area measurements of the children in the groups were made using ultrasound. 3 mL/kg 5% dextrose was consumed. Ultrasound was repeated immediately after fluid intake and every 5 min until the antral cross-sectional area was at the baseline level.Results: The difference in median (IQR [range]) gastric emptying times (minutes) of non-obese {35 [30.0-45.0 (20-60)]} and obese children {35 [30.0-40.0 (25-60)]} were not statistically significant (median of differences 0.0, 95% CI -5.0 to 5.0; p = .563).The antral cross-sectional area and weight-adjusted gastric volumes returned to the baseline level within 60 min after the intake of clear liquid with 3 mL/kg 5% dextrose in all children in both groups.Conclusions: Obese and non-obese children have similar gastric emptying times, and these groups can be offered clear fluids containing 3 mL/kg 5% dextrose 1 h before the surgery.