Browsing by Author "Kilinc M."

Now showing 1 - 8 of 8
  • No Thumbnail Available
    Item
    A whole genome screen for linkage in Turkish multiple sclerosis
    (Elsevier, 2003) Eraksoy M.; Kurtuncu M.; Akman-Demir G.; Kilinc M.; Gedizlioglu M.; Mirza M.; Anlar Ö.; Kutlu C.; Demirkiran M.; Idrisoglu H.A.; Compston A.; Sawcer S.; Tombul T.; Asker Ö.; Balkan S.; Seçkin D.; Aydin H.; Akman-Demir G.; Kiyat A.; Yapici Z.; Epçeliden T.; Çe P.; Goldenberg E.; Gültiken B.; Güvenç A.; Işik N.; Seleker T.; Idiman E.; Özakbaş S.; Irkeç C.; Nazlier B.; Forta H.; Seleker F.; Güner K.; Karabudak R.; Kilinç M.; Komsuoǧlu S.; Efendi H.; Mert M.; Mirza M.; Erdoǧan F.; Müngen B.; Bulut S.; Özer F.; Yayla V.; Petek-Balci B.; Saǧduyu A.; Sarica Y.; Demirkiran M.; Selçuki D.; Mavioǧlu H.; Siva A.; Altintaş A.; Saip S.; Sütlaş N.; Kuşçu Yandim D.; Tireli H.; Özalp K.; Türkoǧlu R.; Örken C.; Özmanoǧlu M.; Velioǧlu S.; Özdemir G.; Gücüyener D.; Özkan S.; Tunali G.; Turan F.; Utku U.; Turgut N.; Ümit S.; Us Ö.; Ince Günal D.; Ütkür Y.; Aluçlu U.; Yavaşoǧlu Ö.; Yücemen N.; Yücesan C.; Zadikoǧlu A.; Zorlu Y.
    Factors exerting recessive effects on susceptibility to complex traits are expected to be over-represented in communities having a higher frequency of consanguineous marriage. Multiple sclerosis, a typical complex trait, is relatively common in Turkey where cultural factors also determine a high rate of consanguineous marriage. Previous genetic studies of multiple sclerosis in Turkey have been confined to the search for associations with candidate genes. In order to exploit the special genetic features of the Turkish population, we performed a whole genome screen for linkage in 43 Turkish multiplex families employing 392 microsatellite markers. Two genomic regions where maximum lod score (MLS) values were suggestive of linkage were identified (chromosomes 13q and 18q23) along with a further 14 regions of potential linkage. Parametric analysis of these data using a recessive model, appropriate for populations with a high frequency of consanguinity, increased the LOD scores in four regions. © 2003 Elsevier B.V. All rights reserved.
  • No Thumbnail Available
    Item
    Thermal, Chemical and Mechanical Properties of Regenerated Bacterial Cellulose Coated Cotton Fabric
    (Taylor and Francis Ltd., 2022) Kilinc M.; Ay E.; Kut D.
    Bacterial cellulose is a raw material that is used in many industrial areas such as textile due to its properties and an alternative to plant cellulose whose usage is increasing day by day. In this research, dissolved bacterial cellulose was used as a coating material. After the coating process, samples were immersed in three different coagulation baths to provide regeneration of the coated material. TGA, FTIR, SEM-EDX, air permeability, tensile test, thermal comfort (alambeta), and water vapor transmission (permetest) analyses were carried out to compare the mechanical, chemical, and thermal properties between raw fabric and treated fabrics. Because of chemical analysis, it was observed that the structures are similar to each other. In terms of thermal stability, it has been determined that the samples that have been coated are more durable than the raw fabric. The tensile test revealed that there was a decrease between 15.05% and 41,62% in the strength of coated materials. According to the results of air permeability, alambeta, and permetest, a decrease in air permeability values, an increase in relative water vapor permeability, and thermal conductivity values were observed with the increase of the remaining coating material in the fabric. © 2021 Taylor & Francis.
  • No Thumbnail Available
    Item
    CFTest: Web Based Business Intelligence Application That Measures Crowdfunding Success
    (Institute of Electrical and Electronics Engineers Inc., 2022) Kilinc M.; Aydin C.; Tarhan C.
    Crowdfunding (CF), which is implemented and offered to users all over the world as digital entrepreneurship, is a new generation funding type that removes geographical barriers. However, when all CF platforms are considered, the successful project rate on the platforms has entered a decreasing trend as the projects do not comply with a certain standard. To solve this problem, a web-based business intelligence application has been developed to provide decision support to users about their projects by collecting all data from crowdfunding platforms in Turkey using data scraping techniques. The application offered to users under the name of CFTest, uses machine learning methods to deploy projects in the CF ecosystem to a certain standard, predict success, modeling alternative scenarios and visualize summaries, and make a system recommendation to users. Among the models established in this context, the highest performance was achieved with the random forest algorithm, with an accuracy score of 87.52% and an F1 score of 92.16%. Models and plugins transferred to the web environment with the Flask framework are designed in such a way that the user can query. This study presents a model proposal with the application developed by the solution of the problem by considering the decreasing trend in the success rate of crowdfunding platforms. © 2022 IEEE.
  • No Thumbnail Available
    Item
    Feature selection for Turkish Crowdfunding projects with using filtering and wrapping methods
    (Elsevier B.V., 2023) Kilinc M.; Aydin C.
    Crowdfunding (CF) platforms host an increasing number of projects, where financial support from backers plays a vital role in project realization. Unfortunately, CF projects have experienced a downward trend in success rates. To address this issue, it is crucial to identify the factors that influence success by analyzing project characteristics. In our study, we collected project data from Turkey's Fongogo CF platform, performed feature selection, and rigorously tested the results. We employed various methods such as Pearson correlation, mutual information statistics, chi-square, Fisher's score from filtering methods, and recursive feature elimination from wrapper methods to understand feature relationships. We proposed a cross-validated recursive feature elimination method for feature selection. The identified success factors were classified using diverse machine learning algorithms, with the Gradient Boosting algorithm achieving the highest result of 84.28%. The results obtained with wrapper methods highlight the potential of utilizing features in decision support processes to enhance CF success. © 2023 Elsevier B.V.
  • No Thumbnail Available
    Item
    MetaPortal: Business Intelligence and Machine Learning Approach for VR Data
    (Institute of Electrical and Electronics Engineers Inc., 2023) Kilinc M.; Geris A.; Teke O.; Cukurbasi B.
    Virtual reality (VR) is a technology that offers near real-world experiences in various fields. With the widespread use of virtual environments designed to provide VR experiences, the amount of data collected from these environments has increased rapidly. However, as the volume of data grows, there is a need to develop analysis processes and advance the data-driven development model. In this study, an application called MetaPortal was developed, utilizing personal characteristics, activity, location, and interaction data of users in the immersive learning environment of Manisa Celal Bayar University (MetaCBU). By employing business intelligence techniques and machine learning algorithms, the application can analyze the vast amount of VR data and classify users in MetaCBU based on their characteristics, activities, and interactions. This paper proposes a combination of business intelligence and machine learning approaches for VR data analysis and provides detailed information about the MetaPortal application developed in this context. © 2023 IEEE.
  • No Thumbnail Available
    Item
    Factors Influencing the Learner's Cognitive Engagement in a Language MOOC: Feature Selection Approach
    (Institute of Electrical and Electronics Engineers Inc., 2023) Kilinc M.; Teke O.; Ozan O.; Ozarslan Y.
    This study aims to predict the cognitive engagement rate in a Language MOOC (Massive Open Online Course) based on the features extracted from learners' engagement behaviors within the content and activities. The features were extracted from the data of the Language MOOC 'Türkçe Öǧreniyorum (I learn Turkish)' which aims to provide self-paced learning materials for those interested in developing their skills in Turkish as a foreign language. After the data preprocessing processes were carried out with the data set obtained for cognitive engagement classification, feature selection processes were performed using filtering and wrapper methods. Afterward, the machine learning model trained using the Logistic Regression (LR) algorithm performed the classification with 94% accuracy. The model evaluation metrics also support the classification result obtained. Based on the extracted features and the classification results obtained, the model will be able to capture learners' interaction behaviors with the content and activities in a Language MOOC and detect changes in learner behavior over time. Prediction accuracy is essential to offer dynamic content and activities in a Language MOOC for adjusting the individual needs of each learner, providing personalized learning experiences that are tailored to their skills, knowledge, and preferences. © 2023 IEEE.
  • No Thumbnail Available
    Item
    Balancing performance and comfort in virtual reality: A study of FPS, latency, and batch values
    (John Wiley and Sons Ltd, 2024) Geris A.; Cukurbasi B.; Kilinc M.; Teke O.
    This manuscript investigates the relationships among various performance metrics in a virtual reality (VR), namely frames per second (FPS), latency, batches, and the number of triangles (tris) and vertices (verts). The study aims to uncover correlations and directional associations between these metrics, shedding light on their impact on VR performance. The findings reveal a significant correlation between FPS and latency, albeit in opposite directions. Higher FPS values are associated with reduced latency, indicating that a smoother visual experience is accompanied by shorter delays in the VR. Conversely, lower FPS values are linked to increased latency, suggesting a potential degradation in overall system responsiveness. Additionally, a strong correlation is observed between latency and batches processed. This finding implies that latency has a direct impact on the system's ability to efficiently process and render objects within VR. Furthermore, a positive correlation is identified between the number of batches and the values of tris and verts. This relationship suggests that higher batch counts are associated with larger quantities of triangles and vertices, reflecting a more complex scene rendering process. Consequently, the performance of VR may be influenced by the density and intricacy of the virtual environments, as indicated by these metrics. © 2024 The Author(s). Software: Practice and Experience published by John Wiley & Sons Ltd.
  • No Thumbnail Available
    Item
    Automated Categorization of Turkish E-commerce Product Reviews Using BERTurk
    (Institute of Electrical and Electronics Engineers Inc., 2024) Altintas V.; Kilinc M.
    Thanks to rapid technological developments, users can now easily access and distribute information. While users have the opportunity to share content and information as they wish, they can also use the information shared to improve themselves in line with their own interests. Especially when buying a product, they make their final decision about the product by examining the content of the comments made about the product. Automatically classifying the comments made about the product by the system and displaying them in the relevant category is one of the issues that has been studied recently. In this study, comments on e-commerce sites were automatically categorized. The dataset was created by collecting comments in Turkish about phones, computers and headphones produced by the same company on Amazon.com.tr, one of the world's largest e-commerce platforms, with the help of a Python script. User comments were automatically sorted into categories by machine learning algorithms such as Naive Bayes, Linear Support Vector Classifier and Random Forest algorithms and pre-trained and fine-tuned Bert Multilingual and BERTurk models based on transfomer architecture. The results obtained were compared with the help of the F1-score metric. When the results of different machine learning algorithms and BERT models were compared, it was seen that the BERTurk model gave more accurate results than other models. © 2024 IEEE.