Yazar "Acar, Erdi" seçeneğine göre listele
Listeleniyor 1 - 10 / 10
Sayfa Başına Sonuç
Sıralama seçenekleri
Öğe A quantum algorithm for solving weapon target assignment problem(Pergamon-Elsevier Science Ltd, 2023) Acar, Erdi; Hatipoglu, Saim; Yilmaz, IhsanQuantum computers, known to have the potential for exponential speedup in solving some problems due to their superposition property, are expected to facilitate the solution of NP-hard optimisation problems. This study proposes a quantum algorithm to solve the weapon target assignment problem (WTAP), one of the NP-hard optimisation problems. The proposed quantum algorithm is a gate-based approach, and scenario examples are executed on Qiskit quantum computing platform and IBM Lima quantum computer with Falcon r4T processor type. The results manifest that the proposed quantum algorithm has low space and time complexity, demonstrating its memory and computational resources efficiency.Öğe COVID-19 detection on IBM quantum computer with classical-quantum transfer learning(TUBITAK, 2021) Acar, Erdi; Yılmaz, İhsanDiagnose the infected patient as soon as possible in the coronavirus 2019 (COVID-19) outbreak which is declared as a pandemic by the world health organization (WHO) is extremely important. Experts recommend CT imaging as a diagnostic tool because of the weak points of the nucleic acid amplification test (NAAT). In this study, the detection of COVID-19 from CT images, which give the most accurate response in a short time, was investigated in the classical computer and firstly in quantum computers. Using the quantum transfer learning method, we experimentally perform COVID-19 detection in different quantum real processors (IBMQx2, IBMQ-London and IBMQ-Rome) of IBM, as well as in different simulators (Pennylane, Qiskit-Aer and Cirq). By using a small number of data sets such as 126 COVID-19 and 100 normal CT images, we obtained a positive or negative classification of COVID-19 with 90% success in classical computers, while we achieved a high success rate of 94%–100% in quantum computers. Also, according to the results obtained, machine learning process in classical computers requiring more processors and time than quantum computers can be realized in a very short time with a very small quantum processor such as 4 qubits in quantum computers. If the size of the data set is small; due to the superior properties of quantum, it is seen that according to the classification of COVID-19 and normal, in terms of machine learning, quantum computers seem to outperform traditional computers.Öğe Hibrit kuantum-klasik makine öğrenmesi ile KOVID-19 tespiti(Çanakkale Onsekiz Mart Üniversitesi, 2021) Acar, Erdi; Yılmaz, İhsanDünya Sağlık Örgütü'nün pandemi olarak ilan ettiği KOVID-19 pandemisinde enfekte olan hastanın en kısa sürede teşhis edilmesi son derece önemlidir. Uzmanlar, RT-PCR testinin zayıf noktaları nedeniyle RT-PCR yanında BT görüntülemeyi önermektedir. Bu tez çalışmasında, gerçek kuantum bilgisayarlar kullanılarak kuantum makine öğrenmesinin küçük boyutlu veri seti üzerindeki etkisi araştırılmıştır. Hibrit kuantum-klasik transfer öğrenme yöntemi kullanılarak IBM Q tarafından kullanıma sunulan farklı kuantum bilgisayarlar (IBMQx2, IBMQ-London ve IBMQ-Rome) ve simülatörler (Pennylane, Qiskit ve Cirq) üzerinde test edilmiştir. Ayrıca klasik bilgisayarlarda daha fazla işlem gücü ve zaman gerektiren klasik makine öğrenmesi işlemi, kuantum bilgisayarlarda 4 kübitlik varyasyonel kuantum devresi ile gerçekleştirilmiştir. Sonuçlar aynı veri setini kullanan diğer çalışmalarla karşılaştırıldı. Karşılaştırma sonucunda, kuantumun üstün özelliklerinden dolayı veri kümesinin boyutu küçük olduğunda hibrit kuantum-klasik modelin daha iyi performans gösterdiği görülmüştür.Öğe High-dimensional Grover multi-target search algorithm on Cirq(Springer Heidelberg, 2022) Acar, Erdi; Gunduz, Sabri; Akpinar, Guven; Yilmaz, IhsanHigh-dimensional computing, compared to traditional qubit computing, has the advantage of operating in a larger scale and storing more information. Considering its advantages, it is of great importance to adapt existing quantum algorithms to high dimension for quantum computing. Yet, the challenges pertaining to high-dimensional quantum computing have limited the studies in this field. In this study, the Grover Search Algorithm for two, three and four targets in high dimension is implemented on Cirq. We concluded that computing in high dimension provides an advantage in terms of capacity and number of qudits used.Öğe High-dimensional Grover multi-target search algorithm on Cirq (vol 137, 244, 2022)(Springer Heidelberg, 2022) Acar, Erdi; Gunduz, Sabri; Akpinar, Guven; Yilmaz, Ihsan[Anstract Not Available]Öğe Improving effectiveness of different deep learning-based models for detecting COVID-19 from computed tomography (CT) images(Springer Science and Business Media Deutschland GmbH, 2021) Acar, Erdi; Şahin, Engin; Yılmaz, İhsanCOVID-19 has caused a pandemic crisis that threatens the world in many areas, especially in public health. For the diagnosis of COVID-19, computed tomography has a prognostic role in the early diagnosis of COVID-19 as it provides both rapid and accurate results. This is crucial to assist clinicians in making decisions for rapid isolation and appropriate patient treatment. Therefore, many researchers have shown that the accuracy of COVID-19 patient detection from chest CT images using various deep learning systems is extremely optimistic. Deep learning networks such as convolutional neural networks (CNNs) require substantial training data. One of the biggest problems for researchers is accessing a significant amount of training data. In this work, we combine methods such as segmentation, data augmentation and generative adversarial network (GAN) to increase the effectiveness of deep learning models. We propose a method that generates synthetic chest CT images using the GAN method from a limited number of CT images. We test the performance of experiments (with and without GAN) on internal and external dataset. When the CNN is trained on real images and synthetic images, a slight increase in accuracy and other results are observed in the internal dataset, but between 3 % and 9 % in the external dataset. It is promising according to the performance results that the proposed method will accelerate the detection of COVID-19 and lead to more robust systems.Öğe Kuantum Bilişim Teknolojileri Kullanılarak Kuantum Ağ Simülasyon Yazılımı Geliştirilmesi(2021) Yılmaz, İhsan; Boy, Murat; Acar, Erdi; Ceylan, Osman Semi; Yaşar, Ahmet BuğraBu proje kapsamında ilk olarak kuantum ağlar alanında günümüzde var olan deneysel çalışmalardan biri olan Tokyo Kuantum Ağı mevcut kuantum ağ simülatörlerinde test edilmiştir. SQUANCH, QuNetSim ve SimulaQron ağ simülatörlerinde gerçekleştirilen test sonuçlarına göre Tokyo Kuantum Ağ simülasyonu performans olarak en iyi SQUANCH ağ simülatöründe gerçekleştirilebileceği sonucuna varılmıştır. İkinci olarak da kuantum iletişim için güvenli bir kuantum ağ topolojisi önerilmeye çalışılmıştır. Bu çalışma aynı zamanda SQUANCH ağ simülatöründe de test edilmiştir. Elde edilen sonuçlar önerilen ağ topolojisinin güvenli bir kuantum iletişim için kullanılabileceğini göstermektedir. Üçüncü olarak da mevcut simülatörlerden üstün bir kuantum ağ simülatörü geliştirilmeye çalışılmıştır. Geliştirilen simülatör hem gürültünün hem de saldırganın dinamik olarak simülasyonun içinde olması bağlamında diğer simülatörlere göre üstündür. Bunula birlikte geliştirilen simülatör diğerlerinden faklı olarak her platformda çalışabilme özelliğine sahiptir. Yapılan test sonuçları genel olarak değerlendirildiğinde geliştirilen simülatörün üstün özellikleri açıkça ortaya çıktığı görülmektedir.Öğe Machinability of different Cu-Gr composites in milling: Performance parameters prediction via machine learning models(Pergamon-Elsevier Science Ltd, 2025) Sap, Serhat; Acar, Erdi; Degirmenci, Uenal; Usca, uesame Ali; Memis, Samet; Sener, RamazanThe machinability of copper-graphite (Cu-Gr) composites has gained significant attention due to their unique thermal, electrical, and mechanical properties. This study experimentally investigates the machinability performances (such as surface roughness, flank wear, cutting temperature, and energy consumption) of Cu-Gr hybrid composite materials during milling. It predicts these parameters with machine learning models. The study aims to contribute to sustainable and optimized manufacturing processes by analyzing the effects of different cutting parameters and cooling/lubrication conditions on this performance. Furthermore, advanced artificial intelligence-based models predict machining outcomes, providing a robust framework for process enhancement and industrial implementation. Although there are comprehensive studies on the machining performances of metal matrix composites in the literature, there is limited information on Cu-Gr composites' mechanical and thermal behaviors in milling processes. To address this deficiency, a full factorial experimental plan was applied on six different Cu-Gr composites and the effects of different cutting speeds, feed rates and cooling/ lubrication environments (Dry, MQL, cryogenic LN2) on flank wear, surface roughness, cutting temperature and energy consumption were analyzed. The materials used in the study were prepared by mixing graphite and hard phases (Al2O3 and Cr3C2) in specific proportions, and these composites were compared in terms of machinability. Afterward, the output parameters of the experimental results are predicted by employing the well-known machine learning models and the experimental results. The results manifested that Gradient-Boosted Decision Tree Regression performs better than the other ten machine learning models in predicting machinability parameters. Finally, this study highlights potential areas for future research and provides a practical guide for optimizing CuGr composites in manufacturing processes and achieving sustainability goals. It has engineering value in efficiency, cost reduction, and developing environmentally friendly applications, especially for the automotive, aerospace, and energy sectors.Öğe Prediction of newly synthesized heparin mimic's effects as heparanase inhibitor in cancer treatments via variational quantum neural networks(Elsevier Sci Ltd, 2025) Kocabay, Samet; Acar, Erdi; Memis, Samet; Taskin, Irmak Icen; Sever, Meryem Ruveyda; Sener, RamazanCancer remains a leading global cause of death, primarily driven by the uncontrolled proliferation of abnormal cells. Malignant tumors, such as carcinomas, originate from unchecked epithelial cell growth and produce growth factors like FGF and VEGF, which promote angiogenesis and tumor progression through heparanasemediated degradation of heparan-sulfate proteoglycans. Chitosan and its derivatives have shown promise in inhibiting tumor growth and metastasis. This study aims to investigate newly synthesized sulfated chitosan oligomers as heparin mimics to inhibit heparanase, evaluating their cytotoxic effects on SH-SY5Y, HCT116, A549, and MDA-MB-231 cancer cell lines. Moreover, it seeks to leverage a variational quantum neural network (VQNN) to predict and validate cytotoxicity outcomes, integrating quantum computing methods into evaluating novel anticancer compounds. The VQNN algorithm was applied to analyze the anticancer effects of sulfated chitosan oligomers. Cytotoxicity data from wet lab experiments validated the model's predictive performance. The VQNN model demonstrated strong predictive capabilities in evaluating anticancer compounds. Specifically, it achieved a mean absolute error (MAE) of 6.5844, indicating a similar trend to the experimental results. Additionally, the model obtained an R2 value of 0.6020, reflecting a moderate level of correlation between predicted and observed outcomes. The results underscore the potential of integrating quantum-based machine learning models into cancer research. The VQNN effectively predicted experimental outcomes, showcasing its utility in assessing novel anticancer compounds. This approach could speed up drug discovery by streamlining the identification and optimization of therapeutic candidates. Furthermore, the findings support the ongoing development of quantum computing techniques for tackling complex biological challenges, contributing to innovative cancer treatment strategies that target tumor growth and angiogenesis.Öğe Unlocking the high dimensional’ potential: Comparative analysis of qubits and qutrits in variational quantum neural networks(Elsevier B.V., 2025) Acar, Erdi; Yılmaz, İhsanQuantum machine learning is a promising research area with great potential. In particular, Variational quantum neural networks (VQNN) have shown high performance in many applications. However, while qubits, which are 2-level quantum systems, are the standard building blocks of quantum computing, the development of qudits, i.e. d-level quantum systems, has opened up new opportunities in VQNNs thanks to many properties such as robustness to noise and more quantum information processing with fewer quantum resources. In this study, we present a comparative analysis of qubits and qutrits (3-level quantum systems) systems performance in VQNNs while also exploring the effect of encoding strategies and entanglement on classifier performance. Our findings contribute to a better understanding the benefits and limitations of using qutrits in VQNN and pave the way for future developments in this field. © 2025 Elsevier B.V.
