Yazar "Varcin, Fatih" seçeneğine göre listele

Listeleniyor 1 - 6 / 6
  • Küçük Resim
    Öğe
    Alternate Low-Rank Matrix Approximation in Latent Semantic Analysis
    (Hindawi Ltd, 2019) Horasan, Fahrettin; Erbay, Hasan; Varcin, Fatih; Deniz, Emre
    The latent semantic analysis (LSA) is a mathematical/statistical way of discovering hidden concepts between terms and documents or within a document collection (i.e., a large corpus of text). Each document of the corpus and terms are expressed as a vector with elements corresponding to these concepts to form a term-document matrix. Then, the LSA uses a low-rank approximation to the term-document matrix in order to remove irrelevant information, to extract more important relations, and to reduce the computational time. The irrelevant information is called as noise and does not have a noteworthy effect on the meaning of the document collection. This is an essential step in the LSA. The singular value decomposition (SVD) has been the main tool obtaining the low-rank approximation in the LSA. Since the document collection is dynamic (i.e., the term-document matrix is subject to repeated updates), we need to renew the approximation. This can be done via recomputing the SVD or updating the SVD. However, the computational time of recomputing or updating the SVD of the term-document matrix is very high when adding new terms and/or documents to preexisting document collection. Therefore, this issue opened the door of using other matrix decompositions for the LSA as ULV- and URV-based decompositions. This study shows that the truncated ULV decomposition (TULVD) is a good alternative to the SVD in the LSA modeling.
  • Küçük Resim
    Öğe
    Block classical Gram-Schmidt-based block updating in low-rank matrix approximation
    (Scientific Technical Research Council Turkey-Tubitak, 2018) Erbay, Hasan; Varcin, Fatih; Horasan, Fahrettin; Bicer, Cenker
    Low-rank matrix approximations have recently gained broad popularity in scientific computing areas. They are used to extract correlations and remove noise from matrix-structured data with limited loss of information. Truncated singular value decomposition (SVD) is the main tool for computing low-rank approximation. However, in applications such as latent semantic indexing where document collections are dynamic over time, i.e. the term document matrix is subject to repeated updates, SVD becomes prohibitive due to the high computational expense. Alternative decompositions have been proposed for these applications such as low-rank ULV/URV decompositions and truncated ULV decomposition. Herein, we propose a BLAS-3 compatible block updating truncated ULV decomposition algorithm based on the block classical Gram-Schmidt process. The simulation results presented show that the block update algorithm is promising.
  • Küçük Resim
    Öğe
    Crop pest classification with a genetic algorithm-based weighted ensemble of deep convolutional neural networks
    (ELSEVIER SCI LTD, 2020) Ayan, Enes; Erbay, Hasan; Varcin, Fatih
    Insects are among the important causes of significant losses in crops such as rice, wheat, corn, soybeans, sugarcane, chickpeas, potatoes. Identification of insect species in the early period is crucial so that the necessary precautions can be taken to keep losses at a low level. However, accurate identification of various types of crop insects is a challenging task for the farmers due to the similarities among insect species and also their lack of knowledge. To address this problem, computerized methods, especially based on Convolutional Neural Networks (CNNs), can be employed. CNNs have been used successfully in many image classification problems due to their ability to learn data-dependent features automatically from the data. Throughout the study, seven different pre-trained CNN models (VGG-16, VGG-19, ResNet-50, Inception-V3, Xception, MobileNet, SqueezeNet) were modified and re-trained using appropriate transfer learning and finetuning strategies on publicly available D0 dataset with 40 classes. Later, the top three best performing CNN models, Inception-V3, Xception, and MobileNet, were ensembled via sum of maximum probabilities strategy to increase the classification performance, the model was named SMPEnsemble. After that, these models were ensembled using weighted voting. The weights were determined by the genetic algorithm that takes the success rate and predictive stability of three CNN models into account, the model was named GAEnsemble. GAEnsemble achieved the highest classification accuracy of 98.81% for D0 dataset. For the sake of robustness ensembled model, without changing the initial best performing CNN models on D0, the process was repeated by using two more datasets such that SMALL dataset with 10 classes and IP102 dataset with 102 classes. The accuracy values for GAEnsemble are 95.15% for SMALL dataset and 67.13% for IP102. In terms of performance metrics, GAEnsemble is competitive compared to the literature for each of these three datasets.
  • [ X ]
    Öğe
    Determination of the severity level of yellow rust disease in wheat by using convolutional neural networks
    (Springer, 2021) Hayit, Tolga; Erbay, Hasan; Varcin, Fatih; Hayit, Fatma; Akci, Nilufer
    Yellow rust disease caused by Puccinia striiformis f. sp. tritici, a pathogen in wheat, results in significant losses in wheat production worldwide due to its high destructive property. On the other side, yellow rust can be taken under control by growing resistant cultivars, by the application of fungicides, and by the use of appropriate cultural practices. Thus, it is crucial to detect the disease at an early stage. The current study offers to use computerized models in determining the infection type of yellow rust disease in wheat. Herein, a deep convolutional neural networks-based model, named Yellow-Rust-Xception, was proposed. The model inputs the wheat leaf image and classifies it as no disease, resistant, moderately resistant, moderately susceptible, or susceptible according to the rust severity, i.e. percentage. The convolutional neural networks, a state-of-art approach, have layered structures those inspired by the human brain and able to learn discriminative features from data automatically; thus networks performance match and even surpass humans in task-specific applications, a newly developed dataset containing yellow rust-infected wheat leaf images, was used to train, validate, and test Yellow-Rust-Xception, in result, the test accuracy was 91%. Thus, Yellow-Rust-Xception can be used in determining wheat yellow rust and its severity level.
  • [ X ]
    Öğe
    End-To-End Computerized Diagnosis of Spondylolisthesis Using Only Lumbar X-rays
    (Springer, 2021) Varcin, Fatih; Erbay, Hasan; Cetin, Eyup; Cetin, Ihsan; Kultur, Turgut
    Lumbar spondylolisthesis (LS) is the anterior shift of one of the lower vertebrae about the subjacent vertebrae. There are several symptoms to define LS, and these symptoms are not detected in the early stages of LS. This leads to disease progress further without being identified. Thus, advanced treatment mechanisms are required to implement for diagnosing LS, which is crucial in terms of early diagnosis, rehabilitation, and treatment planning. Herein, a transfer learning-based CNN model is developed that uses only lumbar X-rays. The model was trained with 1922 images, and 187 images were used for validation. Later, the model was tested with 598 images. During training, the model extracts the region of interests (ROIs) via Yolov3, and then the ROIs are split into training and validation sets. Later, the ROIs are fed into the fine-tuned MobileNet CNN to accomplish the training. However, during testing, the images enter the model, and then they are classified as spondylolisthesis or normal. The end-to-end transfer learning-based CNN model reached the test accuracy of 99%, whereas the test sensitivity was 98% and the test specificity 99%. The performance results are encouraging and state that the model can be used in outpatient clinics where any experts are not present.
  • Küçük Resim
    Öğe
    Latent Semantic Analysis via Truncated ULV Decomposition
    (Ieee, 2016) Varcin, Fatih; Erbay, Hasan; Horasan, Fahrettin
    Latent semantic analysis (LSA) usually uses the singular value decomposition (SVD) of the term-document matrix for discovering the latent relationships within the document collection. With the SVD, by disregarding the smaller singular values of the term-document matrix a vector space cleaned from noises that distort the meaning is obtained. The latent semantic structure of the terms and documents is obtained by examining the relationship of representative vectors in the vector space. However, the computational time of re-computing or updating the SVD of the term-document is high when adding new terms and/or documents to pre-existing document collection. Thus, the need a method not only has low computational complexity but also creates the correct semantic structure when updating the latent semantic structure is arisen. This study shows that the truncated ULV decomposition is a good alternative to the SVD in LSA modelling about cost and producing the correct semantic structure.