Electrical - Electronic Engineering / Elektrik - Elektronik Mühendisliği

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

Browse

Filters

2014 - 201922020 - 20233

Settings

Access Right: Closed AccessPublisher: search.filters.publisher.Springer

Search Results

Now showing 1 - 5 of 5
  • 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
    Time-Efficient Evaluation of Adaptation Algorithms for Dash With Svc: Dataset, Throughput Generation and Stream Simulator
    (Springer, 2021) Çalı, Mehmet; Özbek, Nükhet
    Bitrate adaptation algorithms have received considerable attention recently. In order to evaluate these algorithms objectively, multiple DASH datasets have been proposed. However, only few of them are compatible to SVC-based adaptation algorithms. Apart from the dataset, to fully implement and evaluate an adaptation algorithm, many time-consuming steps are required such as MPD parser design, adaptation logic design and network environment setup. In this paper, a dash simulator which assesses the performance of SVC-based adaptation algorithms without the requirement of any additional implementation steps is proposed. Also, an SVC dataset that includes both CBR and VBR encoded videos is designed. Demonstration is performed as evaluation of an SVC-based adaptation algorithm under several throughput scenarios using the designed dataset. Results show that the proposed system considerably reduces time requirement compared to real-time assessment. Dataset, throughput generation tool and simulator are all publicly available so that the researchers can test their implementation and compare with the results presented in this paper.
  • Conference Object
    Citation - Scopus: 8
    Localization of a Passive Molecular Transmitter With a Sensor Network
    (Springer, 2020) Güleç, Fatih; Atakan, Barış
    Macroscale molecular communication (MC), which has a potential for practical applications, is a promising area for communication engineering. In a practical scenario such as monitoring air pollutants released from an unknown source, it is essential to estimate the location of the molecular transmitter (TX). This paper presents a novel Sensor Network-based Localization Algorithm (SNCLA) for passive transmission by using a novel experimental platform which mainly comprises a clustered sensor network (SN) with 24 sensor nodes and evaporating ethanol molecules as the passive TX. With the usage of the SN concept, novel methods can be developed for the problems in macroscale MC by utilizing the wide literature of sensor networks. In SNCLA, Gaussian plume model is employed to derive the location estimator. The parameters such as transmitted mass, wind velocity, detection time and actual concentration are calculated or estimated from the measured signals via the SN to be employed as the input for the location estimator. The numerical results show that the performance of SNCLA is better for stronger winds in the medium. Our findings show that evaporated molecules do not propagate homogeneously through the SN due to the presence of the wind. In addition, the estimation error of SNCLA decreases for higher detection threshold values. © 2020, ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering.
  • Book
    Citation - Scopus: 17
    Feedback Strategies for Wireless Communication
    (Springer, 2014) Özbek, Berna; Le Ruyet, Didier
    This book explores the different strategies regarding limited feedback information. The book analyzes the impact of quantization and the delay of CSI on the performance. The author shows the effect of the reduced feedback information and gives an overview about the feedback strategies in the standards. This volume presents theoretical analysis as well as practical algorithms for the required feedback information at the base stations to perform adaptive resource algorithms efficiently and mitigate interference coming from other cells. © 2014 Springer Science+Business Media New York. All rights are reserved.
  • Book
    Citation - Scopus: 37
    Molecular Communications and Nanonetworks: From Nature To Practical Systems
    (Springer, 2014) Atakan, Barış
    This book will introduce the concept of molecular communications and nanonetworks. The publication addresses why nanoscale communication is needed for the sophisticated nano and biotechnology applications. The text introduces the frontier applications of the molecular communication and nanonetworks. The book examines the molecular communication types called active, passive, and gap junction molecular communications. The author presents the molecular transmitter, receiver, encoding and decoding mechanisms used in these systems. Discussing the molecular communication system model and looking at the unique characteristics of practical molecular communication systems and these chemical reactions and their effects on the communication performance. Finally, the book examines the point-to-point, broadcast, and multiple-access molecular channel and shows two promising application examples of the nanonetworks. The first application example is the body area nanonetworks used in nanomedicine. the second nanonetwork application example, i.e., NanoSensor Networks (NSNs) with Molecular Communication. © Springer Science+Business Media New York 2014.