WoS İndeksli Yayınlar Koleksiyonu / WoS Indexed Publications Collection

Permanent URI for this collectionhttps://hdl.handle.net/11147/7150

Browse

Filters

2016 - 201922020 - 202522

Settings

Department: search.filters.department.İzmir Institute of TechnologyPublisher: search.filters.publisher.IEEE

Search Results

Now showing 1 - 10 of 24
  • Conference Object
    Speckle Intensity Correlation Distribution Analysis Based on Coincidence Detection for Scattering Medium Characterization
    (IEEE, 2025) Yoldas, Cansu; Kisa, Alperen; Atac, Enes; Karatay, Anil; Dinleyici, Mehmet Salih
    Characterizing a scattering medium is essential for understanding and controlling light propagation, enabling accurate imaging, correlation analysis, and material diagnostics in scientific applications. In this study, the scattering medium has been characterized by examining the spatial distribution of the second-order temporal correlation function of varying speckle patterns obtained under faint-light conditions using a charge-coupled device (CCD) camera. In the proposed method, the exposure time has been utilized as a self-coincidence circuit of the CCD. The spatial statistics of second-order temporal autocorrelation values have been analyzed through power spectral density and radial spatial autocorrelation function. The scattering degree of the medium has been determined using our proposed autocorrelation-based metric. The results from three different media have shown that the method is effective and holds potential for applications such as characterization through speckle imaging.
  • Conference Object
    Citation - WoS: 13
    Automatic HTML Code Generation from Mock-Up Images Using Machine Learning Techniques
    (IEEE, 2019) Asiroglu, Batuhan; Mate, Busra Rumeysa; Yildiz, Eyyup; Nalcakan, Yagiz; Sezen, Alper; Dagtekin, Mustafa; Ensari, Tolga
    The design cycle for a web site starts with creating mock-ups for individual web pages either by hand or using graphic design and specialized mock-up creation tools. The mock-up is then converted into structured HTML or similar markup code by software engineers. This process is usually repeated many more times until the desired template is created. In this study, our aim is to automate the code generation process from hand-drawn mock-ups. Hand drawn mock-ups are processed using computer vision techniques and subsequently some deep learning methods are used to implement the proposed system. Our system achieves 96% method accuracy and 73% validation accuracy.
  • Conference Object
    Outage and Intercept Performance in THz LEO-Ground Communication With Satellite Selection
    (IEEE, 2025) Bakirci, Emre Berker; Ahrazoglu, Evla Safahan; Altunbas, Ibrahim; Erdogan, Eylem
    Satellite communication and THz communication systems are some of the methods that aim to meet the demand of increasing data rates. With an importance growing alongside increasing data amounts, data security is on its way to a position that cannot be neglected when building systems. In this study, it has been shown that secure data transmission can be made possible through the use of THz frequencies in a link between LEO satellites and a ground station. Proposed scenarios data transmission performance have been analyzed. It has been shown that selection transmission have improved both data transmission and security performances.
  • Conference Object
    Performance Evaluation of Filter-Based Gene Selection Methods in Cancer Classification
    (IEEE, 2025) Gokalp, Osman
    With the advances in microarray technology, gene expression levels can be measured efficiently, and this data can be used to solve important problems such as cancer classification. However, microarray data suffers from the high-dimensionality problem and requires dimensionality reduction techniques such as feature selection. This study addresses the cancer classification problem using microarray datasets and comparatively evaluates the performance of different filter-based gene (feature) selection methods. To this end, 11 microarray datasets have been evaluated using 6 different filter methods, and experimental results are presented. According to the findings, the gene selection methods used can improve classification performance by 5% to 30%. Using 5-fold cross-validation, the highest accuracy rates were achieved with 32 genes selected by the gain ratio filter for the Breast and Colon datasets, and with 8 genes selected by the information gain filter for the CNS dataset.
  • Conference Object
    User Selection for Secure Massive Mimo Based Mobile Edge Computing With Delay-Sensitive Applications
    (IEEE, 2025) Yilmaz, Saadet Simay; Ozbek, Berna
    Mobile edge computing (MEC) has been a promising technology that leverages cloud computing capabilities at the network edge to address compute-intensive and delay-sensitive applications of mobile users with limited resources. Employing massive multiple-input multiple-output (mMIMO) and nonorthogonal multiple access (NOMA) in the MEC system facilitates simultaneous task offloading for multiple users, resulting in increased spectral efficiency and decreased offloading delay. Despite the great potential of the mMIMO-NOMA-based MEC system, offloading computation tasks to MEC servers can introduce inherent security concerns and vulnerabilities. We address a notable gap in the existing literature by investigating the effect of user selection to minimize the delay in MEC while enhancing the security of this framework. Specifically, this paper presents a user selection strategy for an uplink mMIMO-NOMA-based secure MEC system in the presence of a malicious eavesdropper (Eve) to minimize offloading and computing delays, subject to the transmit power, computing resource, and secrecy rate constraints with remote computing. We propose a two-step secure user selection algorithm and solve the optimization problem with the active-set algorithm. The simulation results demonstrate the effectiveness of the proposed user selection strategy on secure MEC with a malicious Eve by minimizing the task execution delay compared to the benchmark schemes.
  • Conference Object
    Df-Segdiff: Adiffusion Segmentation Model Using a New Distributed Parallel Computing Algorithm
    (IEEE, 2024) Mi, Hancang; Gan, Hong-Seng; Wang, Xiaoyi; Shimizu, Akinobu; Ramlee, Muhammad Hanif; Unlu, Mehmet Zubeyir
    Brain tumours are among the most life-threatening diseases, and automatic segmentation of brain tumours from medical images is crucial for clinicians to identify and quantify tumour regions with high precision. While traditional segmentation models have laid the groundwork, diffusion models have since been developed to better manage complex medical data. However, diffusion models often face challenges related to insufficient parallel computing power and inefficient GPU utilization. To address these issues, we propose the DF-SegDiff model, which includes diffusion segmentation, parallel data processing, a distributed training model, a dynamic balancing parameter and model fusion. This approach significantly reduces training time while achieving an average Dice score of 0.87, with several samples reaching Dice values close to 0.94. By combining BRATS2020 with the Medical Segmentation Decathlon dataset, we also integrated a comprehensive dataset containing 800 training samples and 53 test samples. Evaluation of the model using Dice, IoU, and other relevant metrics demonstrates that our method outperforms current state-of-the-art techniques.
  • Conference Object
    Citation - WoS: 3
    Citation - Scopus: 5
    Predicting Software Functional Size Using Natural Language Processing: an Exploratory Case Study
    (IEEE, 2024) Unlu, Huseyin; Tenekeci, Samet; Ciftci, Can; Oral, Ibrahim Baran; Atalay, Tunahan; Hacaloglu, Tuna; Demirors, Onur
    Software Size Measurement (SSM) plays an essential role in software project management as it enables the acquisition of software size, which is the primary input for development effort and schedule estimation. However, many small and medium-sized companies cannot perform objective SSM and Software Effort Estimation (SEE) due to the lack of resources and an expert workforce. This results in inadequate estimates and projects exceeding the planned time and budget. Therefore, organizations need to perform objective SSM and SEE using minimal resources without an expert workforce. In this research, we conducted an exploratory case study to predict the functional size of software project requirements using state-of-the-art large language models (LLMs). For this aim, we fine-tuned BERT and BERT_SE with a set of user stories and their respective functional size in COSMIC Function Points (CFP). We gathered the user stories included in different project requirement documents. In total size prediction, we achieved 72.8% accuracy with BERT and 74.4% accuracy with BERT_SE. In data movement-based size prediction, we achieved 87.5% average accuracy with BERT and 88.1% average accuracy with BERT_SE. Although we use relatively small datasets in model training, these results are promising and hold significant value as they demonstrate the practical utility of language models in SSM.
  • Conference Object
    Citation - WoS: 1
    Citation - Scopus: 1
    Towards the Construction of a Software Benchmarking Dataset Via Systematic Literature Review
    (IEEE, 2024) Yurum, Ozan Rasit; Unlu, Huseyin; Demirors, Onur
    Effort estimation is a fundamental task during the planning of software projects. Prediction models usually rely on two essential factors: software size and effort data. Measuring the size of the software can be done at various stages of the project with desired accuracy. Nevertheless, the industry faces challenges when it comes to collecting reliable actual effort data. Consequently, organizations encounter difficulties in establishing effort prediction models. Benchmarking datasets are available, but, in most cases, they have huge variances that make them less useful for effort prediction. In this study, we aimed to answer whether creating a software benchmarking dataset is possible by gathering the data from the literature. To the best of our knowledge, a comprehensive dataset that gathers the functional size and effort data of the studies from the literature is unavailable. For this purpose, we performed a systematic literature review to find studies that include projects measured with the COSMIC Functional Size Measurement (FSM) method and the related effort. As a result, we formed a dataset including 337 records from 18 studies that shared the corresponding size and effort data. Although we performed a limited search, we created a larger dataset than many datasets in the literature. In light of our review, we obtained that most studies did not share their dataset, and many lacked case details such as implementation environment and the scope of software development life cycle activities included in the effort data. We also compared the dataset with the ISBSG repository and found that our dataset has less variation in productivity. Our review showed the applicability of creating a software benchmarking dataset is possible by gathering the data from the literature. In conclusion, this study addresses gaps in the literature through a cost-free and easily extendable dataset.
  • Conference Object
    Outage and Ser Analyses for Dual-Hop Inter-Satellite Thz Communication
    (IEEE, 2024) Ahrazoglu, Evla Safahan; Erdogan, Eylem; Altunbas, Ibrahim
    Inter-satellite links have crucial significance in offering global connectivity and low latency in satellite mega-constellations. In such architectures, system capacity and data-rate can be enhanced by utilizing terahertz (THz) frequencies. Considering the importance of inter-satellite links in mega-constellations and the mounting interest in THz communications, in this study, an inter-satellite THz communication system is examined. In this setup, a low earth orbit (LEO) satellite is deployed to assist transmission between two LEO satellites by using variable-gain amplify-and-forward relaying protocol. The system's performance is analyzed in terms of both outage probability and symbol error rate, and asymptotic outage characteristic is explored. All theoretical findings are verified by Monte-Carlo simulations.
  • Conference Object
    Citation - WoS: 1
    Citation - Scopus: 1
    Robust and Energy-Efficient Hardware Architectures for Dizy Stream Cipher
    (IEEE, 2024) Schmid, Martin; Arul, Tolga; Kavun, Elif Bilge; Regazzoni, Francesco; Kara, Orhun
    In the era of ubiquitous computing, efficient and secure implementations of cryptographic hardware are crucial. This paper extends the hardware implementations of a Small Internal State Stream (SISS) cipher, namely DIZY. Previous work shows that DIZY's hardware performance, in terms of area cost and power consumption, is among the best when compared to notable stream ciphers, especially for frame-based encryptions requiring frequent initialization. In this study, we initially optimize the existing hardware implementation and then evaluate the energy efficiency of DIZY. We implement different unrolled versions of DIZY and analyze their energy consumption. Furthermore, we address physical security by integrating masking techniques into the DIZY S-box to protect the implementation against side-channel attacks. We thoroughly investigate the associated overhead and apply optimizations to reduce it, ensuring robust security without compromising efficiency. Our results present a secure, energy-efficient, and lightweight cryptographic hardware design for the stream cipher DIZY, making it suitable for various applications, including Internet of Things (IoT) and embedded systems.