Yazar "Ismailoglu, Firat" seçeneğine göre listele

Listeleniyor 1 - 6 / 6
  • Küçük Resim Yok
    Öğe
    Classifying Cancer Types Based on Microarray Gene Expressions using Conformal Prediction
    (IEEE, 2021) Ismailoglu, Firat
    The key aspect in cancer treatment is to predict the subclass of the cancer accurately. To this aim, making use of the microarray gen data collected from cancerous tissues has been increasingly popular recently. In the present study, to predict the subclass of various cancer types, we employ the Conformal Prediction method, which outputs a set of classes guaranteeing to some extent that the true subclass is in the set of the predicted classes, different from the conventional machine learning classification algorithms. We tested the performance of the conformal prediction on five different microarray cancer data, ranging from leukemia to prostate cancer. The results showed that the true subclass of the cancer is in the predicted set in almost all settings; and the predicted sets includes as less as possible classes, hence are compacts.
  • Küçük Resim Yok
    Öğe
    Effects of agmatine, glutamate, arginine, and nitric oxide on executive functions in children with attention deficit hyperactivity disorder
    (Springer Wien, 2020) Sari, Seda Aybuke; Ulger, Dilara; Ersan, Serpil; Bakir, Deniz; Uzun Cicek, Ayla; Ismailoglu, Firat
    In this study, we aimed to investigate the effects of agmatine, nitric oxide (NO), arginine, and glutamate, which are the metabolites in the polyamine pathway, on the performance of executive functions (EF) in attention deficit hyperactivity disorder (ADHD). The ADHD group included 35 treatment-naive children (6-14 years old) who were ewly diagnosed with ADHD. The control group consisted of 35 healthy children with the same age and sex, having no previous psychiatric disorders. In the study groups, Stroop test (ST) and trail making test (TMT) were used to monitor EF, and blood samples were collected to measure agmatine with ultra-high-performance liquid chromatography and NO, glutamate, and arginine with enzyme-linked immunosorbent assay (ELISA). The EFs were significantly impaired in the ADHD group. The agmatine and arginine levels of the ADHD group were significantly higher than their peers. The NO and glutamate levels were also higher in the ADHD group compared to the control group, but these differences did not reach statistical significance. Children with ADHD had more difficulties during EF tasks compared to healthy children. The elevated NO and glutamate levels may be related with the impairment during EF tasks. Therefore, agmatine and arginine may increase to improve EF tasks through its inhibitory effect on the synthesis of NO and glutamate. Further studies are needed about polyamine pathway molecules to shed light on the pathophysiology of ADHD.
  • Küçük Resim Yok
    Öğe
    Enhancing Classification in Zero-Shot Learning with the Aid of Perceptron
    (Institute of Electrical and Electronics Engineers Inc., 2022) Zengin, Hilal; Ismailoglu, Firat
    Since it is costly to obtain labeled instances for each class, and new classes emerge over time, there are no instances in training set for some classes in image classification. These classes are called test classes and to classify them, Zero-Shot Learning (ZSL) was developed. However, ZSL makes use of training classes to classify the test classes, which raises the domain shift problem. To deal with the domain shift problem, a new algorithm called PPG was developed in this study, which has its roots in the perceptron algorithm. PPG is able to update the prototypes of the test classes considering the transfer matrix learned using the training classes. By integrating PPG into the state-of-the-art ZSL methods, a better classification of the test classes was achieved. © 2022 IEEE.
  • Küçük Resim Yok
    Öğe
    Heterogeneous Domain Adaptation Based on Class Decomposition Schemes
    (SPRINGER INTERNATIONAL PUBLISHING AG, 2018) Ismailoglu, Firat; Smirnov, Evgueni; Peeters, Ralf; Zhou, Shuang; Collins, Pieter; Phung, D; Tseng, VS; Webb, GI; Ho, B; Ganji, M; Rashidi, L
    This paper introduces a novel classification algorithm for heterogeneous domain adaptation. The algorithm projects both the target and source data into a common feature space of the class decomposition scheme used. The distinctive features of the algorithm are: (1) it does not impose any assumptions on the data other than sharing the same class labels; (2) it allows adaptation of multiple source domains at once; and (3) it can help improving the topology of the projected data for class separability. The algorithm provides two built-in classification rules and allows applying any other classification model.
  • Küçük Resim Yok
    Öğe
    Heterogeneous Domain Adaptation for IHC Classification of Breast Cancer Subtypes
    (IEEE Computer Soc, 2020) Ismailoglu, Firat; Cavill, Rachel; Smirnov, Evgueni; Zhou, Shuang; Collins, Pieter; Peeters, Ralf
    Increasingly, multiple parallel omics datasets are collected from biological samples. Integrating these datasets for classification is an open area of research. Additionally, whilst multiple datasets may be available for the training samples, future samples may only be measured by a single technology requiring methods which do not rely on the presence of all datasets for sample prediction. This enables us to directly compare the protein and the gene profiles. New samples with just one set of measurements (e.g., just protein) can then be mapped to this latent common space where classification is performed. Using this approach, we achieved an improvement of up to 12 percent in accuracy when classifying samples based on their protein measurements compared with baseline methods which were trained on the protein data alone. We illustrate that the additional inclusion of the gene expression or protein expression in the training process enabled the separation between the classes to become clearer.
  • Küçük Resim Yok
    Öğe
    Metric Learning for Context-Aware Recommender Systems
    (Association for Computing Machinery, 2021) Ismailoglu, Firat
    Context-Aware Recommender Systems (CARS) refer to recommender systems that can incorporate side information regarding to users, items and ratings. In the present study, we are concerned with CARS, where the side information is provided in the form of item-attribute matrix with entries indicating whether an item has an attribute. We propose to multiply this matrix with user-item rating matrix to represent the the users in the attribute space of the items. We then apply a popular metric learning method, specifically Mahalanobis Metric Learning (MMC), in the attribute space to calculate the distances between the users and their favorite items as less as possible. We recommend the n items that are closest to the users based on these calculations. We verify the effectiveness of the proposed method on two famous MovieLens datasets that differ in size showing that using metric learning increases the success of CARS up to 7% in comparison with using the traditional cosine similarity. © 2021 ACM.