Akademik YayınlarUlusal/Uluslararası makale ve bildiriler..

Plants are our source of oxygen and nutrients on earth. Therefore, conservation of biodiversity is vital for the survival of other species. With the developing technology, plant species can be examined more closely. Image processing, which is a subject of computer science, has an important role in this field. In this study, an image processing–based method has been developed to automatically separate the petiole region of the plant leaves. To determine the boundary line of the petiole region, the cumulative pixel distributions of the input images in binary format according to the X- and Y-axis are analyzed. Accordingly, optimum thresholds and petiole boundary points are determined. The proposed method was tested on 795 leaf images from 90 different plant species that grow both as trees and shrubs in the Czech Republic. According to the results obtained in experimental studies, it is thought that the proposed method will make an important contribution especially in studies such as automatic classification of plants and leaves and determination of plant species in botanical science.

Background and Objective: Traditional machine learning methods assume that both training and test data come from the same distribution. In this way, it becomes possible to achieve high successes when modelling on the same domain. Unfortunately, in real-world problems, direct transfer between domains is adversely affected due to differences in the data collection process and the internal dynamics of the data. In order to cope with such drawbacks, researchers use a method called “domain adaptation”, which enables the successful transfer of information learned in one domain to other domains. In this study, a model that can be used in the classification of white blood cells (WBC) and is not affected by domain differences was proposed. Methods: Only one data set was used as source domain, and an adaptation process was created that made possible the learned knowledge to be used effectively in other domains (multi-target domain adaptation). While constructing the model, we employed data augmentation, data generation and fine-tuning processes, respectively. Results: The proposed model has been able to extract “domain-invariant” features and achieved high success rates in the tests performed on nine different data sets. Multi-target domain adaption accuracy was measured as %98.09. Conclusions: At the end of the study, it has been observed that the proposed model ignores the domain differences and it can adapt in a successful way to target domains. In this way, it becomes possible to classify unlabeled samples rapidly by using only a few number of labeled ones.

Blood and its components have an important place in human life and are the best indicator tool in determining many pathological conditions. In particular, the classification of white blood cells is of great importance for the diagnosis of hematological diseases. In this study, 350 microscopic blood smear images were tested with 6 different machine learning algorithms for the classification of white blood cells and their performances were compared. 35 different geometric and statistical (texture) features have been extracted from blood images for training and test parameters of machine learning algorithms. According to the results, the Multinomial Logistic Regression (MLR) algorithm performed better than the other methods with an average 95% test success. The MLR can be used for automatic classification of white blood cells. It can be used especially as a source for diagnosis of diseases for hematologists and internal medicine specialists.

Cardiotocography provides information about the fetal heart rate during pregnancy and childbirth, monitoring the uterine contractions and the physiological status of the fetus to identify hypoxia. Accurate information from these records can be used to estimate the pathological condition of the fetus. Thus, it allows early intervention by reporting any irreversible negative condition in the fetus. In this study, due to the importance of this subject, Naive Bayes machine learning algorithm can be used to diagnose the model developed. The result was 97.18% classification and 95.68% test success with Naive Bayes machine learning algorithm. The obtained data were presented in detail in the following sections.

Peripheral blood smear is microscopically examining technique for blood samples from patients by painting special dyes in clinic laboratories. Blood diseases can be diagnosed by examining morphology, numbers and percentages of leukocyte, erythrocyte and thrombocyte cells in blood samples. However, this method is a considerably time-consuming process and requires an evaluation performed by a hematology specialist. It is not often provided a definitive assessment due to the expert's clinical experience and judgment during review. Although there are considerable studies about the segmentation of blood smear images in the literature, there is no method to segment all blood cells. In this study, a new segmentation algorithm is proposed, which automatically extracts leukocyte, erythrocyte and thrombocyte cells from peripheral blood smear images. Purpose of this study here is to make highly accurate and complete blood count. The algorithm treats each image as a universal set and represents each object in the image as a subset as a result of the applied operations. In the developed method, leukocytes and thrombocytes achieve better success than other studies. However, it has been observed that the average success rate of stacked erythrocytes decreases. Statistical tests of the developed method were performed using 200 blood smear images in experimental studies. According to the obtained results, it is seen that high accuracy (leukocyte 99.86%, thrombocyte 98.4%, erythrocyte 93.4%) and precision (leukocyte 94.77%, thrombocyte 90.14%, erythrocyte 95.88%) were achieved in all three blood cells.

With the development of technology, security has entered our lives as an indispensable element. Nowadays, people are now using some methods that increase safety in every system. Biometrics technologies used in the identification of the physical properties of the body (facial, fingerprint and fingerprint) have become a common security detection approach today. Different methods are used for biometric applications. In this study, an application was developed by using PCA (Principal Component Analysis) method in the literature using face recognition algorithm. In this application, a workplace with hundreds of employees is followed by face recognition of the arrival and departure of the staff. After the follow-up, the persons who are late to the job or who are early to the desired time are reported to the management mail.

There have been many studies in various fields such as engineering, medicine, military applications, geographical applications, space studies with image processing methods. In this study, by applying image processing techniques of digitized leaf images, leaf type was determined according to morphological characteristics. The average of each leaf area is taken in itself. Mean area-based leaf type detection was developed in the C # application environment. In the study, 90 leaf types were determined and a total of 795 leaf images were studied.After the application, 85% recognition was done in 25 leaf types. Recognition of 100% in 65 leaf types was performed. The other findings obtained are presented in the conclusions.

Gel Electrophoresis (GE) is one of the most used methods which separate nucleic acid and protein molecules according to electric charge, amount of them, molecule weights and other physical features. GE is used in many fields such as genetic, molecular biology and biochemistry. In this paper, Canny edge detection algorithm based on artificial neural network is used to separate and detect DNA bands automatically. Thus, GE analysis of gel electrophoresis period is realized and many properties of DNA bounds like intensity are extracted from digital images automatically.

In this study, the solution to the problem of automating the course timetabling used at the universities through the student affairs automation tool has been established by applying one of the heuristic optimization approaches, namely, the genetic algorithm method. The scheduling problem involves the optimal placing of tasks in time slots in accordance with designated constraints. Solving this problem through analytical methods at universities is becoming impossible due to the magnitude of the solution space and the wide range of constraints. Therefore, the genetic algorithm method, which is known to yield very good results for such problems, is used as a new approach, along with the investigation of parameters with the best results. The performance of the algorithm is measured using real data from the university. In order to enable the practical use of the algorithm, the genetic algorithm method is implemented within the student affairs automatization tool.

In this study, solution of course scheduling problems in student affairs automation used in the universities was carried out using Genetic Algorithm method which is one of Heuristic Optimization approaches.Scheduling problem is the process of placing the works to be done in time intervals at optimum level withinthe constraints. The solution of this problem at universities becomes impossible with analytic methods sincesolution space is too wide and there are many constraints. Therefore, giving the best solutions for this type of problems, Genetic Algorithm method was used with a new approach by examining the parameters giving thebest results.The performance of the Algorithm was measured by conducting applications over the actual data from theuniversity (504 instructors, 4163 course, 203 classrooms and 10525 students). Algorithm was developed using ASP.NET, C# programming language and SQL Server Database. Interfaceand reporting pages of student affairs automation were also added to the program for practical use of the Algorithm.