Yazar "Turk, Fuat" seçeneğine göre listele

Listeleniyor 1 - 8 / 8
  • [ X ]
    Öğe
    A Research: Investigation of Financial Applications with Blockchain Technology
    (2024) Mohammed, Mohammed Ali; Turk, Fuat
    Cryptocurrencies have revolutionized the financial landscape by providing decentralized and anonymous payment systems, making them an intriguing subject for investors and researchers. This article delves into applying machine learning techniques for predicting cryptocurrency prices, mainly focusing on Bitcoin, Ethereum, and Binance Coin. Employing a range of machine learning models, including XGBoost, Linear Regression, and Gaussian Processes, the study aims to evaluate their predictive performance comprehensively. The results are promising; our models outperform existing studies, achieving impressively low RMSE values of 0.0040 for Bitcoin, 0.028 for Ethereum, and 0.027 for Binance Coin. These findings contribute valuable insights into the volatility and dynamics of cryptocurrency pric- es and underscore the potential of machine learning in shaping financial decision-making. Future directions include integrating advanced deep learning models, additional data sourc- es, and ensemble methods to enhance prediction accuracy and robustness.
  • [ X ]
    Öğe
    Comparison of Multi Layer Perceptron and Jordan Elman Neural Networks for Diagnosis of Hypertension
    (Tsi Press, 2015) Turk, Fuat; Barisci, Necaattin; Ciftci, Aydin; Ekmekci, Yakup
    In this study, from 150 individuals over the age of 30 taken no drugs, sex, age, height, weight, HDL, LDL, Triglyceride, smoking and uric acid were measured. 65 of them are normal but 85 consist of the patients. This data was transferred to the computer by processing methods of quantitative analysis. Data obtained of each patient was applied Artificial Neural Network (ANN) models. The results obtained will be classified as either normal or the patient. Using Multi Layer Perceptron (MLP) neural network, 80.4% of patient individuals and 81.8% of normal individuals were classified correctly. Using Jordan Elman neural network, 85.3% of the patient individuals and 87.8% of normal individuals were classified correctly.
  • [ X ]
    Öğe
    Comparison of Principal Component Analysis and Radial Basis Function Network for Diagnosis of Hypertension
    (Turgut Ozal Univ, 2012) Turk, Fuat; Barisci, Necaattin; Ciftci, Aydin; Ekmekci, Yakup
    In this study, from 150 individuals over the age of 30 taken no drugs, sex, age, height, weight, HDL, LDL, Triglyceride, smoking and uric acid were measured. 65 of them are normal but 85 consist of the patients. Data obtained of each patient was applied Artificial Neural Network (ANN) models. The results obtained will be classified as either normal or the patient. Using Principal Component Analysis (PCA), 89% of patient individuals and 88% of normal individuals were classified correctly. Using Radial Basis Function Networks (RBFN), 89% of the patient individuals and 84% of normal individuals were classified correctly.
  • [ X ]
    Öğe
    Investigation of machine learning algorithms on heart disease through dominant feature detection and feature selection
    (Springer London Ltd, 2024) Turk, Fuat
    Heart diseases are an essential research topic in healthcare institutions around the world. Therefore, using machine learning and optimization algorithms attracts attention as an important method in detecting heart diseases. Additionally, the factors that affect heart disease are a matter of current debate. In this study, an effective DFD method is proposed using optimization techniques for classifying heart diseases and examining the factors affecting the disease. Initially, the study employs classical machine learning and ensemble algorithms for classification. Subsequently, feature selection is performed using BEO, BSPO, GA, and GFO methods, and the importance levels of features are determined utilizing the DFD approach. The results indicate that the ensemble model achieved an accuracy of 86.34% without optimization methods, whereas the proposed DFD method, when applied in conjunction with ensemble models, increased the accuracy to 99.08%. Therefore, it is observed that ensemble models yield the highest results when used in conjunction with optimization algorithms. The outcomes identified using the DFD method, which are clinically significant, are believed to hold great importance in reducing the number of heart patients and enhancing treatment.
  • [ X ]
    Öğe
    Investigation of the effect of hectoliter and thousand grain weight on variety identification in wheat using deep learning method
    (Pergamon-Elsevier Science Ltd, 2023) Luy, Murat; Turk, Fuat; Argun, Mustafa Samil; Polat, Turgay
    Accurate identification of wheat varieties in the seed and flour industry is extremely important. The success rate of correctly identifying wheat varieties using artificial intelligence methods compared to traditional methods is quite high. Whether hectoliter weight (HLW) and thousand grain weight (TGW) represent the variety in iden-tification studies is a subject to debate. The reason of this debate is these parameters are heavily affected by environmental factors such as soil nutrient levels, amount of rainfall, and number of sunny days. In other words, it is assumed that these parameters are not specific to the variety. In this study, the feature map obtained using the GLCM method was compared with the feature map obtained by adding the HLW and TGW parameters. As a result of the comparison, the accuracy rate was calculated as 78% in the first feature map. However, when standard features were added to the HLW and TGW parameters, the accuracy rate was calculated as 82%. The results show that the HLW and TGW parameters contribute to the identification of the wheat variety when used correctly with artificial intelligence.
  • Küçük Resim
    Öğe
    Kidney and Renal Tumor Segmentation Using a Hybrid V-Net-Based Model
    (MDPI, 2020) Turk, Fuat; Luy, Murat; Barisci, Necaattin
    Kidney tumors represent a type of cancer that people of advanced age are more likely to develop. For this reason, it is important to exercise caution and provide diagnostic tests in the later stages of life. Medical imaging and deep learning methods are becoming increasingly attractive in this sense. Developing deep learning models to help physicians identify tumors with successful segmentation is of great importance. However, not many successful systems exist for soft tissue organs, such as the kidneys and the prostate, of which segmentation is relatively difficult. In such cases where segmentation is difficult, V-Net-based models are mostly used. This paper proposes a new hybrid model using the superior features of existing V-Net models. The model represents a more successful system with improvements in the encoder and decoder phases not previously applied. We believe that this new hybrid V-Net model could help the majority of physicians, particularly those focused on kidney and kidney tumor segmentation. The proposed model showed better performance in segmentation than existing imaging models and can be easily integrated into all systems due to its flexible structure and applicability. The hybrid V-Net model exhibited average Dice coefficients of 97.7% and 86.5% for kidney and tumor segmentation, respectively, and, therefore, could be used as a reliable method for soft tissue organ segmentation.
  • [ X ]
    Öğe
    Kidney Tumor Segmentation Using Two-Stage Bottleneck Block Architecture
    (Tech Science Press, 2022) Turk, Fuat; Luy, Murat; Barisci, Necaattin; Yalcinkaya, Fikret
    Cases of kidney cancer have shown a rapid increase in recent years. Advanced technology has allowed bettering the existing treatment methods. Research on the subject is still continuing. Medical segmentation is also of increasing importance. In particular, deep learning-based studies are of great importance for accurate segmentation. Tumor detection is a relatively difficult procedure for soft tissue organs such as kidneys and the prostate. Kidney tumors, specifically, are a type of cancer with a higher incidence in older people. As age progresses, the importance of having diagnostic tests increases. In some cases, patients with kidney tumors may not show any serious symptoms until the last stage. Therefore, early diagnosis of the tumor is important. This study aimed to develop support systems that could help physicians in the segmentation of kidney tumors. In the study, improvements were made on the encoder and decoder phases of the V-Net model. With the double-stage bottleneck block structure, the architecture was transformed into a unique one, which achieved an 86.9% kidney tumor Dice similarity coefficient. The results show that the model gives applicable and accurate results for kidney tumor segmentation.
  • [ X ]
    Öğe
    RNGU-NET: a novel efficient approach in Segmenting Tuberculosis using chest X-Ray images
    (Peerj Inc, 2024) Turk, Fuat
    Tuberculosis affects various tissues, including the lungs, kidneys, and brain. According to the medical report published by the World Health Organization (WHO) in 2020, approximately ten million people have been infected with tuberculosis. U-NET, a preferred method for detecting tuberculosis-like cases, is a convolutional neural network developed for segmentation in biomedical image processing. The proposed RNGU-NET architecture is a new segmentation technique combining the ResNet, Non-Local Block, and Gate Attention Block architectures. In the RNGU-NET design, the encoder phase is strengthened with ResNet, and the decoder phase incorporates the Gate Attention Block. The key innovation lies in the proposed Local Non-Local Block architecture, overcoming the bottleneck issue in U-Net models. In this study, the effectiveness of the proposed model in tuberculosis segmentation is compared to the U-NET, U-NET+ResNet, and RNGU-NET algorithms using the Shenzhen dataset. According to the results, the RNGU-NET architecture achieves the highest accuracy rate of 98.56%, Dice coefficient of 97.21%, and Jaccard index of 96.87% in tuberculosis segmentation. Conversely, the U-NET model exhibits the lowest accuracy and Jaccard index scores, while U-NET+ResNet has the poorest Dice coefficient. These findings underscore the success of the proposed RNGU-NET method in tuberculosis segmentation.