Bilgisayar ve Bilişim Fakültesi Koleksiyonu
Permanent URI for this collectionhttps://hdl.handle.net/20.500.13091/10834
Browse
Browsing Bilgisayar ve Bilişim Fakültesi Koleksiyonu by Publisher "Elsevier Ltd"
Now showing 1 - 5 of 5
- Results Per Page
- Sort Options
Article Citation - WoS: 10Citation - Scopus: 11A Binary Sparrow Search Algorithm for Feature Selection on Classification of X-Ray Security Images(Elsevier Ltd, 2024) Babalik, A.; Babadag, A.In today's world, especially in public places, strict security measures are being implemented. Among these measures, the most common is the inspection of the contents of people's belongings, such as purses, knapsacks, and suitcases, through X-ray imaging to detect prohibited items. However, this process is typically performed manually by security personnel. It is an exhausting task that demands continuous attention and concentration, making it prone to errors. Additionally, the detection and classification of overlapping and occluded objects can be challenging. Therefore, automating this process can be highly beneficial for reducing errors and improving the overall efficiency. In this study, a framework consisting of three fundamental phases for the classification of prohibited objects was proposed. In the first phase, a deep neural network was trained using X-ray images to extract features. In the subsequent phase, features that best represent the object were selected. Feature selection helps eliminate redundant features, leading to the efficient use of memory, reduced computational costs, and improved classification accuracy owing to a decrease in the number of features. In the final phase, classification was performed using the selected features. In the first stage, a convolutional neural network model was utilized for feature extraction. In the second stage, the Sparrow Search Algorithm was binarized and proposed as the binISSA for feature selection. Feature selection was implemented using the proposed binISSA. In the final stage, classification was performed using the K-Nearest Neighbors (KNN) and Support Vector Machine (SVM) algorithms. The performances of the convolutional neural network and the proposed framework were compared. In addition, the performance of the proposed framework was compared with that of other state-of-the-art meta-heuristic algorithms. The proposed method increased the classification accuracy of the network from 0.9702 to 0.9763 using both the KNN and SVM (linear kernel) classifiers. The total number of features extracted using the deep neural network was 512. With the application of the proposed binISSA, average number of features were reduced to 25.33 using the KNN classifier and 32.70 using the SVM classifier. The results indicate a notable reduction in the extracted features from the convolutional neural network and an improvement in the classification accuracy. © 2024 Elsevier B.V.Article Citation - WoS: 145Citation - Scopus: 162Pso-Based Image Encryption Scheme Using Modular Integrated Logistic Exponential Map(Elsevier Ltd, 2024) Kocak, O.; Erkan, U.; Toktas, A.; Gao, S.Image encryption (IE) has been essential for internet-based storing and transferring in recent years. Effective chaotic systems play a crucial role in IE schemes which widely depend on chaotic maps and keys. However, the existing chaotic maps suffer from low performance and narrow chaotic ranges, and they utilize casual key generation approaches rather than optimum keys. In this study, an IE scheme based on key optimization using particle swarm optimization (PSO) algorithm and a novel modular integrated logistic exponential (MILE) map is presented. The chaotic performance of the MILE map is validated across a comparison with the existing maps thorough measurements such as LE, SE, 0–1 Test, and PE with means values of 12.0000, 2.1866, 0.9981, and 0.9998, respectively. The key is optimized on a small part of the image to be encrypted instead of the whole image that is employed by the existing works. That is why the IE scheme is faster than those works. Afterward, the PSO-based IE scheme is undergone reliable crypto-analyses and attacks. It is also verified through a comparison with the existing IE schemes. The proposed IE scheme is the best owing to having exceptional mean values of key sensitivity 99.6117, variance 893.12, χ2 222.4057, information entropy 7.9994, NPCR 99.6090, and UACI 33.4662. Thanks to the MILE map, the PSO-based IE scheme demonstrates excellent numerical and visual encryption results. © 2023 Elsevier LtdArticle Citation - WoS: 3Citation - Scopus: 1The Role of Magma Recharge and Mixing in Producing Compositional Modality in Post-Collisional Volcanic Rocks, Konya Volcanic Field, Central Anatolia (türkiye)(Elsevier Ltd, 2024) Asan, K.; Gündüz, M.; Korkmaz, G.G.; Kurt, H.The Neogene Erenlerdağ-Alacadağ (ErAVC) and Sulutas (SVC) volcanic complexes in the Konya Volcanic Field, Türkiye have distinctly different unimodal and bimodal compositional variations, respectively. They occurred in graben-like extensional basins behind the retreating Cyprus subduction zone between the African and Eurasian plates. We here investigate their compositional modality by using new and published whole-rock major and trace element and Sr-Nd-Pb isotope data. Both complexes are characterized by basaltic to rhyodacitic high-K calc-alkaline rocks with the geochemical signatures of orogenic volcanism, except for minor alkaline rocks in the SVC. Mass-balance models suggest that major element variations can be largely explained by the fractional crystallization of amphibole, plagioclase, and Fe-Ti oxides. However, Sr-Nd-Pb isotopes show correlations with SiO2 indicating that open-system processes played a role in their differentiation. Modeling of AFC (Assimilation and Fractional Crystallization) involving a recharge situation shows that low degrees of crustal assimilation (rate of assimilation/rate of fractional crystallization, r < 0.2 and crust/magma ratio, ρ: 15–16 %) of lower and upper crust-like rocks was involved in the differentiation of the ErAVC and SVC, respectively. However, the modeling suggests that magma recharge (β: rate of magma recharge/rate of assimilation) was more efficient in the ErAVC (β: 3.45, % ∼52.5 rate of recharge) relative to that of the SVC (β: 2.15, % ∼36.55 rate of recharge). We conclude that for the ErAVC and SVC, different parental magmas derived from the subduction-modified mantle source followed distinct differentiation paths in the crust, and their compositional modality was mainly controlled by the magma recharge and mixing process. © 2024 Elsevier LtdEditorial Citation - WoS: 1Citation - Scopus: 1Virtual Special Issue on Recent Advances in Discrete Swarm Intelligence Algorithms for Solving Engineering Problems(Elsevier Ltd, 2022) Kıran, Mustafa Servet; Gao, Xiao-Zhi; Vasudevan, Muneeswaran; Gündüz, Mesut[No abstract available]Article Citation - WoS: 8Citation - Scopus: 10X-Ray Image Analysis for Explosive Circuit Detection Using Deep Learning Algorithms(Elsevier Ltd, 2024) Seyfi, G.; Yilmaz, M.; Esme, E.; Kiran, M.S.X-ray imaging technologies find applications across various domains, including medical imaging in health institutions or security in military facilities and public institutions. X-ray images acquired from diverse sources necessitate analysis by either trained human experts or automated systems. In cases where concealed electronic cards potentially pose threats, such as in laptops harboring explosive triggering circuits, conventional analysis methods are challenging to detect, even when scrutinized by skilled. The present investigation is centered on the utilization of deep learning algorithms for the analysis of X-ray images of laptop computers, with the aim of identifying concealed hazardous components. To construct the dataset, some control cards such as Arduino, Raspberry Pi and Bluetooth circuits were hidden inside the 60 distinct laptop computers and were subjected to X-ray imaging, yielding a total of 5094 X-ray images. The primary objective of this study is to distinguish laptops based on the presence or absence of concealed electronic cards. To this end, a suite of deep learning models, including EfficientNet, DenseNet, DarkNet19, DarkNet53, Inception, MobileNet, ResNet18, ResNet50, ResNet101, ShuffleNet and Xception were subjected to training, testing, and comparative evaluation. The performance of these models was assessed utilizing a range of metrics, encompassing accuracy, sensitivity, specificity, precision, f-measure, and g-mean. Among the various models examined, the ShuffleNet model emerged as the top-performing one, yielding superior results in terms of accuracy (0.8355), sensitivity (0.8199), specificity (0.8530), precision (0.8490), f-measure (0.8322), and g-mean (0.8352). © 2023 Elsevier B.V.
