Yazar "Arslan A.K." seçeneğine göre listele

Listeleniyor 1 - 5 / 5
  • Küçük Resim Yok
    Öğe
    Breast cancer classification using a constructed convolutional neural network on the basis of the histopathological images by an interactive web-based interface
    (Institute of Electrical and Electronics Engineers Inc., 2019) Arslan A.K.; Yasar S.; Colak C.
    In this study, it is aimed to develop a system that can provide clinical support to physicians in the diagnosis of breast cancer with open source access artificial intelligence based software. The proposed system was designed using an open source data set for the classification of breast cancer (benign/malignant) on the basis of the histopathological images. In this context, Keras library and convolutional neural networks from deep learning methods were used on the images obtained by staining with hematoxylin and eosin of biopsy specimens taken from breast tissues. Shiny package in the R programming language is employed to develop for the user interface. According to the experimental results obtained from the study, it was determined that the designed system gives promising predictions in the classification of breast cancer and can be used for clinical decision support in the classification of the disease. This designed system can be available at http://biostatapps.inonu.edu.tr/MKSY/ in both English and Turkish. © 2019 IEEE.
  • Küçük Resim Yok
    Öğe
    An intelligent system for the classification of postoperative pleural effusion between 4 and 30 days using medical knowledge discovery
    (Scientific Publishers of India, 2017) Guldogan E.; Arslan A.K.; Colak M.C.; Colak C.; Erdil N.
    Objective: Pleural Effusion (PE) is a considerable and a common health problem. The classification of this condition is of great importance in terms of clinical decision making. The purpose of the study is to design an intelligent system for the classification of postoperative pleural effusion between 4 and 30 days after surgery by medical knowledge discovery (MKD) methods. Materials and methods: This study included 2309 individuals diagnosed with coronary artery disease for elective coronary artery bypass grafting (CABG) operation. The results of chest x-ray were used to diagnose PE. The subjects were allocated to two groups: PE group (n=81) and non-PE group (n=2228), consecutively. In the preprocessing step, outlier analysis, data transformation and feature selection processes were performed. In the data mining step, Naïve Bayes, Bayesian network and Random Forest algorithms were utilized. Accuracy and area under receiver operating characteristics (ROC) curve (AUC) were calculated as evaluation metrics. Results: In the preprocessing step, 85 outlier observations were removed from the study. The rest of the data consisted of 2224 subjects: 2149 of these individuals were in non-PE group, and the 75 were in PE group. Random Forest yielded the best classification performance with 97.45% of accuracy and 0.990 of AUC for 0.7 of the optimal split ratio by Grid search algorithm. Conclusion: The achieved results pointed out that the best classification performance was obtained from the RF ensemble model. Therefore, the suggested intelligent system can be used as a clinical decision making tool. © 2017, Scientific Publishers of India. All rights reserved.
  • Küçük Resim Yok
    Öğe
    An Interactive Web Tool for Classification Problems Based on Machine Learning Algorithms Using Java Programming Language: Data Classification Software
    (Institute of Electrical and Electronics Engineers Inc., 2019) Percin I.; Yagin F.H.; Arslan A.K.; Colak C.
    Classification analysis is a frequently used approach in fields such as biomedical, bioinformatics, medical and engineering. In the field of health, it has become common to classify diseases based on risk factors by machine learning methods and to determine the effect sizes of these risk factors on the disease. There are many analysis tools used to guide researchers in classification analysis. While some of these tools are commercial and provide basic methods for classification analysis, some offer advanced analysis techniques and are desktop applications such as the WEKA environment.The WEKA environment includes comprehensive tools for classification analysis. However, use of the WEKA environment can be difficult and time-consuming, especially when a quick assessment is essential for users who do not have WEKA tool on their computer (doctors, etc.). Therefore; fast, comprehensive, free and easy to use analysis tool is required. The purpose of this study is to develop a user-friendly web tool (Data Classification Software; DCS) based on the classification algorithms of WEKA tool in Java programming language.The data classification software can be used on any device with an internet connection, which is independent of the any operating systems. In the developed web-based tool, data preprocessing module consists of missing value assignment, variable type conversion and normalization-standardization methods. Classification module encapsulates random forest, Naive Bayes, Bayes Network, j48, sequential minimal optimization, a rule and attribute selected classifier algorithms. This web tool can be accessed free of charge at http://biostatapps.inonu.edu.tr/DCS/. © 2019 IEEE.
  • Küçük Resim Yok
    Öğe
    Open Source Web-Based Software to Evaluate Normal Distribution: Normality Assessment Software
    (Institute of Electrical and Electronics Engineers Inc., 2019) Arslan A.K.; Tunc Z.; Colak C.
    In this study, it was aimed to develop a new user-friendly web-based software that would easily test single-variable univariate and multivariate normal distribution suitability and enable users to get more accurate results in their studies.Shiny, an open source R package, was used to develop the proposed web software. In the developed software, Shapiro-Wilk and Anderson-Darling tests were used for the uniformity of univariate distribution, and Mardia's skewness-kurtosis, Henze-Zircon and Doornik-Hansen tests were used for multivariate normal distribution. Outputs for conformity to normal distribution were supported by using graphical methods. In practice, for the data set where each variable consisting of two variables derived by simulation has a standard normal distribution and the variables contain 1000 observations, the normal distribution conformity analysis has been performed. In the derived data set, each variable is normally distributed according to the Anderson-Darling and Shapiro-Wilk tests.In addition, the derived data set showed normal distribution with three variables according to Mardia's skewness-kurtosis and Henze-Zirkler tests. However, according to the Doornik-Hansen test, the triple does not show normal distribution.The developed software is a new user-friendly web-based software that can easily perform univariate and multivariate normal distribution conformity analysis and enable users to get more accurate results in their work. In further studies, Type I and Type II error types are planned to be included in the software in order to determine the best method. © 2019 IEEE.
  • Küçük Resim Yok
    Öğe
    Prediction of melanoma from dermoscopic images using deep learning-based artificial intelligence techniques
    (Institute of Electrical and Electronics Engineers Inc., 2019) Kaplan A.; Guldogan E.; Colak C.; Arslan A.K.
    Recently, hospitals and health care institutions have increasingly been addressing clinical decision support systems (CDSS), which can offer specific patient assessments or recommendations to physicians and health care professionals. It is very useful to develop CDSS which can help physicians to make meaningful and correct decisions by using existing data or image sets. Also, CDSS increases the diagnostic accuracy of diseases, provides significant facilities in precision medicine applications, increases operating efficiency of hospitals and reduces costs. In this context, the proposed project intends to create a model using pre-Trained networks (i.e. VGG-16,) based on deep learning (DL) that can successfully predict the melanoma using dermoscopic images. The current study provides clinical support to physicians in the medical decision-making process for the diagnosis of melanoma. © 2019 IEEE.