This article compares the performance of machine learning algorithms on breast cancer data. The aim is to predict the survival status of breast cancer patients and contribute to the development of clinical decision support systems. Using a dataset obtained from the National Cancer Institute, XGBoost, Random Forest, Support Vector Machines (SVM), and Logistic Regression algorithms were compared. Data preprocessing steps were applied, correlation analysis was performed, and it was determined that the XGBoost algorithm showed the best performance with hyperparameter optimization. The metrics obtained after hyperparameter optimization of the XGBoost algorithm show an overall accuracy of 92%. Optimization has resulted in high performance for class 0 (precision 92%, recall 98%), but the recall for class 1 remains at 54%. The article discusses the effect of data imbalance on the results and offers suggestions for future studies.
31 December 2020 in International Journal of Applied Mathematics Electronics and Computers
Customer relationship management - CRM systems aim to increase customer satisfaction and loyalty to the company through actions that can be performed by monitoring and analyzing customer behaviours for companies. In these systems, the data obtained from different sources such as sales process, service, and call center are interpreted by the CRM experts as a whole, and the necessary action is taken for the customer. With the rapid progress in information technologies, the diversity of channels that are used to collect data, the size and dynamism of the data have increased. This situation has made it impossible for experts to wholly interpret big-size data from a wide variety of sources in a short period of time. In the CRM area, there is a need for technologies that automatically integrate the data obtained from several sources and can interpret it semantically. In this study, an ontology-based approach is proposed, which allows automatic semantic interpretations on the data obtained from different sources. Based on the proposed approach, a tool has been developed that can unify data from different CRM systems in a common format and make customer-centric interpretations of this data. The tool continuously monitors the systems it is integrated with, and when it detects the conditions defined by the users on the data, it can automatically perform the actions determined by the users. The tool developed was experienced by integrating a CRM system of a company and the evaluation results obtained in this process were discussed.
The non-destructive and chemical-free determination of anthocyanin content in single maize kernels is of great importance for plant-breeding programs. Previous studies have mainly relied on Near-Infrared Reflectance (NIR) spectroscopy and color-based approaches, often using conventional or randomly selected modeling techniques. In this study, an Automated Machine Learning (AutoML) framework was employed to predict anthocyanin content using spectral and digital image data obtained from individual maize kernels measured in two orientations (embryo-up and embryo-down). Forty colored maize genotypes representing diverse phenotypic characteristics were analyzed. Digital images were acquired in RGB, HSV, and LAB color spaces, together with NIR spectral data, from a total of 200 kernels. Reference anthocyanin content was determined using a colorimetric method. Ten datasets were constructed by combining different color space and spectral features and were grouped according to kernel orientation. AutoML was used to evaluate nine machine learning algorithms, while Partial Least Squares Regression (PLSR) served as a classical benchmark method, resulting in the development of 1918 predictive models. Kernel orientation had a notable effect on model performance and outlier detection. The best predictions were obtained from the RGB dataset for embryo-up kernels and from the combined RGB+HSV+LAB+NIR dataset for embryo-down kernels. Overall, AutoML outperformed conventional modeling by automatically identifying optimal algorithms for specific data structures, demonstrating its potential as an efficient screening tool for anthocyanin content at the single-kernel level.
28 March 2023 in The European Journal of Research and Development
Corn farming is of great importance for the continuity of our society. Because corn is a cheap and efficient food, especially for animal feeding. However, with the Doubled-haploid technique, the selection of the haploid seeds necessary for this job to be done efficiently creates a problem. Today, the selection of haploid seeds is usually done by trained technicians. With the development of machine learning methods, the parts expected from technicians can be made by machines. In this study, a new model architecture based on a convolutional neural network (CNN) was produced to perform the selection of haploid seeds and the hyperparameters of this model were optimized with the use of tree-structured parzen estimator algorithm. The newly produced model achieved a 94.66% validation score, higher than the VGG-19 model, which proved to be relatively efficient.
22 June 2026 in The European Journal of Research and Development
Doubled Haploid (DH) technology significantly accelerates the development of homozygous lines in maize breeding; however, its scalability is constrained by the reliable discrimination of haploid and diploid individuals. The widely used R1-nj anthocyanin marker at the seed stage is susceptible to genetic suppression and environmental variability, leading to high misclassification rates. This limitation has driven a shift toward seedling root morphology as a more robust phenotypic marker, yet it introduces major challenges, including complex image noise and severe class imbalance. In this study, we systematically evaluate the limitations of standard computer vision pipelines and baseline deep learning models for root-based classification. Automated background removal methods (HSV, Rembg) are shown to misinterpret fine root hairs as noise, resulting in significant morphological data loss. Additionally, experiments conducted under a realistic class imbalance (1:5.4) demonstrate that widely used CNN architectures (ResNet50, VGG16, EfficientNetB0, DenseNet121) exhibit strong majority class bias, with haploid recall dropping to 0.00% and 27.7%. These findings reveal a critical limitation in existing approaches and highlight the need for domain-informed datasets and imbalance-aware learning strategies for robust and scalable AI-based maize breeding systems.