Electrical - Electronic Engineering / Elektrik - Elektronik Mühendisliği

Permanent URI for this collectionhttps://hdl.handle.net/11147/11

Browse

Filters

2021 - 20232

Settings

Access Right: Closed AccessSubject: search.filters.subject.Deep neural networks

Search Results

Now showing 1 - 2 of 2
  • Article
    Citation - WoS: 5
    Citation - Scopus: 7
    Adaptive Resizer-Based Transfer Learning Framework for the Diagnosis of Breast Cancer Using Histopathology Images
    (Springer, 2023) Düzyel, Okan; Çatal, Mehmet Sergen; Kayan, Ceyhun Efe; Sevinç, Arda; Gümüş, Abdurrahman
    Breast cancer is a major global health concern, and early and accurate diagnosis is crucial for effective treatment. Recent advancements in computer-assisted prediction models have facilitated diagnosis and prognosis using high-resolution histopathology images, which provide detailed information on cancerous tissue. However, these high-resolution images often require resizing, leading to potential data loss. In this study, we demonstrate the effect of a learnable adaptive resizer for breast cancer classification using the BreakHis dataset. Our approach incorporates the adaptive resizer with various convolutional neural network models, including VGG16, VGG19, MobileNetV2, InceptionResnetV2, DenseNet121, DenseNet201, and EfficientNetB0. Despite producing visually less appealing images, the learnable resizer effectively improves classification performance. DenseNet201, when jointly trained with the adaptive resizer, achieves the highest accuracy of 98.96% for input images of 448x448 resolution. Our experimental results demonstrate that the adaptive resizer performs better at a magnification factor of 40x compared to higher magnifications. While its effectiveness becomes less pronounced as image resolution increases to 100x, 200x, and 400x, the adaptive resizer still outperforms bilinear interpolation. In conclusion, this study highlights the potential of adaptive resizers in enhancing performance for medical image classification. By outperforming traditional image resizing methods, our work contributes to the advancement of deep neural networks in the field of breast cancer diagnostics.
  • Article
    Citation - WoS: 2
    Citation - Scopus: 2
    Deep Learning Based Adaptive Bit Allocation for Heterogeneous Interference Channels
    (Elsevier, 2021) Aycan, Esra; Özbek, Berna; Le Ruyet, Didier
    This paper proposes an adaptive bit allocation scheme by using a fully connected (FC) deep neural network (DNN) considering imperfect channel state information (CSI) for heterogeneous networks. Achieving an accurate CSI has a crucial role on the system performance of the heterogeneous networks. Different quantization techniques have been employed to reduce the feedback overhead. However, the system performance cannot increase linearly with the number of bits increasing exponentially. Since optimizing the total number of bits is too complex for the entire network, an initial step is performed to distribute the bits to each cell in the conventional method. Then, the distributed bits are further allocated to each channel optimally. In order to enable direct allocation for the entire network, a FC-DNN based method is presented in this study. The optimized number of bits can be directly obtained for a different number of bits and scenarios by the proposed approach. The simulations are performed by using various scenarios with different allocation schemes. The performance results show that the DNN based method achieves a closer performance to the conventional approach. (C) 2021 Elsevier B.V. All rights reserved.