Bilgisayar Mühendisliği Bölümü Makale Koleksiyonu
Bu koleksiyon için kalıcı URI
Güncel Gönderiler
Öğe Investigating the association between nutrient intake and food insecurity among children and adolescents in palestine using machine learning techniques(MDPI, 2024) Qasrawi, Radwan; Sgahir, Sabri; Nemer, Maysaa; Halaikah, Mousa; Badrasawi, Manal; Amro, Malak; Vicuna Polo, Stephanny; Abu Al-Halawa, Diala; Mujahed, Doa’a; Nasreddine, Lara; Elmadfa, Ibrahim; Atari, SihamFood insecurity is a public health concern that affects children worldwide, yet it represents a particular burden for low- and middle-income countries. This study aims to utilize machine learning to identify the associations between food insecurity and nutrient intake among children aged 5 to 18 years. The study's sample encompassed 1040 participants selected from a 2022 food insecurity household conducted in the West Bank, Palestine. The results indicated that food insecurity was significantly associated with dietary nutrient intake and sociodemographic factors, such as age, gender, income, and location. Indeed, 18.2% of the children were found to be food-insecure. A significant correlation was evidenced between inadequate consumption of various nutrients below the recommended dietary allowance and food insecurity. Specifically, insufficient protein, vitamin C, fiber, vitamin B12, vitamin B5, vitamin A, vitamin B1, manganese, and copper intake were found to have the highest rates of food insecurity. In addition, children residing in refugee camps experienced significantly higher rates of food insecurity. The findings emphasize the multilayered nature of food insecurity and its impact on children, emphasizing the need for personalized interventions addressing nutrient deficiencies and socioeconomic factors to improve children's health and well-being.Öğe DDoS attack detection techniques in IoT networks: a survey(Springer, 2024) Pakmehr, Amir; Aßmuth, Andreas; Taheri, Negar; Ghaffari, AliThe Internet of Things (IoT) is a rapidly emerging technology that has become more valuable and vital in our daily lives. This technology enables connection and communication between objects and devices and allows these objects to exchange information and perform intelligent operations with each other. However, due to the scale of the network, the heterogeneity of the network, the insecurity of many of these devices, and privacy protection, it faces several challenges. In the last decade, distributed DDoS attacks in IoT networks have become one of the growing challenges that require serious attention and investigation. DDoS attacks take advantage of the limited resources available on IoT devices, which disrupts the functionality of IoT-connected applications and services. This article comprehensively examines the effects of DDoS attacks in the context of the IoT, which cause significant harm to existing systems. Also, this paper investigates several solutions to identify and deal with this type of attack. Finally, this study suggests a broad line of research in the field of IoT security, dedicated to examining how to adapt to current challenges and predicting future trends. © The Author(s) 2024.Öğe Integrating machine learning models to learn potentially non-monotonic preferences for multi-criteria sorting from large-scale assignment examples(Elsevier Ltd., 2025) Li, Zhuolin; Zhang, Zhen; Pedrycz, WitoldLearning preferences from assignment examples has attracted considerable attention in the field of multi-criteria sorting (MCS). However, traditional MCS methods, designed to infer decision makers’ preferences from small-scale assignment examples, encounter limitations when confronted with large-scale data sets. Additionally, the presence of decision makers’ non-monotonic preferences for certain criteria in MCS problems necessitates accounting for potential non-monotonicity when devising preference learning methods. To address this, this paper proposes some new models to learn potentially non-monotonic preferences for MCS problems from large-scale assignment examples by leveraging machine learning models. Specifically, we first introduce the Piecewise-Linear Neural Network (PLNN) model, which leverages the threshold-based value-driven sorting procedure as the underlying sorting model and integrates a perceptron-based model to establish piecewise-linear marginal value functions to approximate real ones. On this basis, we address MCS problems with criteria interactions and extend the PLNN model to develop the Piecewise-Linear Factorization Machine-based Neural Network (PLFMNN) model by incorporating the factorization machine to factorize interaction coefficients. Training these models allows us to learn potentially non-monotonic preferences of decision makers. To illustrate the proposed models, we apply them to a red wine quality classification problem. Furthermore, we assess the performance of the proposed models through computational experiments on both artificial and real-world data sets. Additionally, we conduct statistical tests to ascertain the significance of the performance differences. Experimental results reveal that the proposed models are comparable to the multilayer perceptron model and outperform other baseline models on most data sets, thus affirming their efficacy. Finally, we conduct some sensitivity analysis to assess the impact of certain parameters on the performance of the proposed models and compare them with existing studies from a theoretical perspective, further demonstrating their effectiveness. © 2024 Elsevier LtdÖğe Machine learning approach for predicting the impact of food insecurity on nutrient consumption and malnutrition in children aged 6 months to 5 years(MDPI, 2024) Qasrawi, Radwan; Sgahir, Sabri; Nemer, Maysaa; Halaikah, Mousa; Badrasawi, Manal; Amro, Malak; Polo, Stephanny Vicuna; Abu Al-Halawa, Diala; Mujahed, Doa'a; Nasreddine, Lara; Elmadfa, Ibrahim; Atari, Siham; Al-Jawaldeh, AyoubBackground: Food insecurity significantly impacts children's health, affecting their development across cognitive, physical, and socio-emotional dimensions. This study explores the impact of food insecurity among children aged 6 months to 5 years, focusing on nutrient intake and its relationship with various forms of malnutrition. Methods: Utilizing machine learning algorithms, this study analyzed data from 819 children in the West Bank to investigate sociodemographic and health factors associated with food insecurity and its effects on nutritional status. The average age of the children was 33 months, with 52% boys and 48% girls. Results: The analysis revealed that 18.1% of children faced food insecurity, with household education, family income, locality, district, and age emerging as significant determinants. Children from food-insecure environments exhibited lower average weight, height, and mid-upper arm circumference compared to their food-secure counterparts, indicating a direct correlation between food insecurity and reduced nutritional and growth metrics. Moreover, the machine learning models observed vitamin B1 as a key indicator of all forms of malnutrition, alongside vitamin K1, vitamin A, and zinc. Specific nutrients like choline in the "underweight" category and carbohydrates in the "wasting" category were identified as unique nutritional priorities. Conclusion: This study provides insights into the differential risks for growth issues among children, offering valuable information for targeted interventions and policymaking.Öğe Local core expanding-based label diffusion and local deep embedding for fast community detection algorithm in social networks(Pergamon-elsevier science ltd, 2024) Bouyer, Asgarali; Shahgholi, Pouya; Arasteh, Bahman; Tirkolaee, Erfan BabaeeCommunity detection is a key task in social network analysis, as it reveals the underlying structure and function of the network. Various global and local techniques exist for uncovering community structures in social networks wherein diffusion-based algorithms are proposed as novel methods for local community detection, particularly suited for large-scale networks. The efficacy of diffusion processes and initial detection is paramount in the successful identification of community structures within social networks. This effectiveness hinges significantly on the meticulous selection of the label diffuser core, which serves as the foundation for propagating labels through the network, and the precise labeling of boundary nodes. Addressing the constraints of current community detection algorithms, notably their time complexity and efficiency, this paper proposes a novel local community detection algorithm that combines core expansion with label diffusion, and deep embedding techniques. In the proposed method, a new centrality measure is introduced for appropriate core selection to facilitate precise label diffusion in the initial phase. Subsequently, a deep embedding technique is employed for updating labels of boundary and core nodes using the GraphSage embedding method. Finally, a rapid merging step is executed to amalgamate initially proximate communities into finalized community structures in large-scale social networks. We evaluate our algorithm on 14 real-world and 4 synthetic networks and show that it outperforms existing methods in terms of NMI, F-measure, ARI, and modularity. According to numerical results, the proposed method shows approximately 1.04 %, 1.03 %, and 1.12 % improvement in F-measure, NMI, and ARI measures respectively, compared to the second-best method, LBLD, in the networks with ground-truth. In addition, our method is able to accurately identify communities in large-scale networks such as Orkut, YouTube, and LiveJournal, where it ranks among the top-performing methods. Our approach exhibits the best performance in terms of ARI compared to other algorithms under comparison.Öğe Matrix-based network data envelopment analysis: A common set of weights approach(Elsevier Ltd, 2024) Peykani, Pejman; Seyed Esmaeili, Fatemeh Sadat; Pishvaee, Mir Saman; Rostamy Malkhalifeh, Mohsen; Hosseinzadeh Lotfi, FarhadPerformance measurement of decision-making units (DMUs) with network structure is one of the main challenges in data envelopment analysis (DEA) field. The main purpose of this paper is to propose a novel network data envelopment analysis (NDEA) approach based on matrix of efficiency, common set of weights (CSW), multi-objective programming (MOP), and goal programming (GP) technique for performance measurement of peer DMUs in two-stage network structure. The advantages of the proposed NDEA approach can be summarized as follows: comparing all DMUs and sub-DMUs on the same base, considering all internal structures and relations and capability to extending this for all network structures, linearity of the proposed models, unique efficiency decomposing without any need to consider multiplicative, additive or leader-follower relations between overall and stages efficiency. To illustrate the usefulness and applicability of the proposed approach we applied it to a real application of non-life insurance companies in Taiwan. © 2024 Elsevier LtdÖğe Decisioning-based approach for optimising control engineering tools using digital twin capabilities and other cyber-physical metaverse manufacturing system components(IEEE, 2024) Mourad, Nahia; Alsattar, Hassan A.; Qahtan, Sarah; Zaidan, Aws Alaa; Deveci, Muhammet; Sangaiah, Arun Kumar; Pedrycz, WitoldThe optimisation of control engineering tools based on digital twin capabilities and other cyber-physical metaverse manufacturing system (CPMMS) components are crucial for the successful performance. This study proposes a model for optimising control engineering tools using digital twin capabilities and other CPMMS components to solve the open issues. The main contributions and novelty aspects of the methodological process are outlined as follows: Formulated and developed is a decision matrix based on a utility procedure for 10 control engineering tools with digital twin capabilities and other three CPMMS components (Programmable-Logic-Controller and Human-Machine-Interface, Internet of Things connectivity and cybersecurity features). This matrix accounts for the uncertainty associated with tool assessment and transformation evaluation issue; formulated and develop an integrating fuzzy weighted with zero-inconsistency-interval-valued spherical fuzzy rough sets (IvSFRS-FWZIC) and combined compromise solution (CoCoSo) methods. The IvSFRS-FWZIC method is utilised to assign importance degrees to the digital twin capabilities and other CPMMS components. The applicability and robustness of the proposed approach are validated and evaluated through conducting sensitivity, correlation, and comparative analyses. The proposed approach can assist managers in analysing and selecting the most suitable tool for developing CPMMS.Öğe Soft-Sensing of burn-through point based on weighted kernel just-in-time learning and fuzzy broad-learning system in sintering process(IEEE, 2024) Hu, Jie; Wu, Min; Cao, Weihua; Pedrycz, WitoldBurn-through point (BTP) is an essential thermal state parameter in a sintering process, which is a direct reflection of the stability of this process. However, it cannot be measured online. Soft-sensing technology offers a reliable method for estimating unmeasurable variables in industrial processes. Here, a soft-sensing model for BTP based on weighted kernel just-in-time learning (WKJITL) and fuzzy broad-learning system (FBLS) is built. First, an abnormal production data detection and correction strategy is employed to process the production data, and the mechanism analysis and mutual information analysis are utilized to specify the detectable process variables that are directly related to BTP. Then, the WKJITL method is proposed to obtain historical production data similar to the query data of BTP for local learning modeling, and the FBLS is utilized as an efficient modeling method for the soft-sensing prediction of BTP. Finally, the results of simulation experiments based on actual sintering production data reveal that the developed soft-sensing model of BTP exhibits better prediction accuracy and efficiency compared with some advanced modeling methods. Furthermore, the proposed method is of general nature and can also be easily applied to other industrial processes.Öğe Indirect effect of elevated pressure via the modulations of crystals intrinsic parameters on radiation shielding efficacy: A comparative study between two α-quartz homeotypes SiO2 and GeO2(Elsevier Ltd., 2025) Afaneh, F.; Al Omari, S.; ALMisned, Ghada; Tekin, Hüseyin Ozan; Khattari, Z.Y.This study investigates the indirect effects of elevated pressure on the radiation shielding competence of two α-quartz homeotypes, SiO2 and GeO2, by examining the modulations of their crystal intrinsic tetrahedral parameters. The study focuses on structural modifications and their correlations with radiation attenuation properties. The results show that both homeotypes exhibit energy-dependent mass attenuation coefficients (MAC) and linear attenuation coefficients (LAC). SiO2 demonstrates higher transparency to incident radiation compared to GeO2, with a relative difference in MAC values of 91% at 0.015 MeV, decreasing to 28% at 15 MeV. However, within the energy range of 0.4 < E < 4 MeV, SiO2 exhibits higher MAC values than GeO2, with the MAC of SiO2 surpassing GeO2 by 17% at 0.4 MeV. The pressure dependence of LAC values indicates that both SiO2 and GeO2 become more effective in attenuating radiation under higher pressure conditions. For instance, at 0.015 MeV, the LAC of GeO2 increased from 274.826 cm−1 at 0.001 GPa to 308.073 cm−1 at 5.57 GPa. GeO2 generally exhibits higher LAC values than SiO2 across the energy and pressure ranges studied. It can be concluded that the structural modifications induced by elevated pressure significantly enhance the radiation shielding capabilities of α-quartz homeotypes, particularly GeO2, making them promising candidates for advanced shielding materials in various high-radiation environments. © 2024 Elsevier LtdÖğe First principles investigations of linear and nonlinear optical, radiation shielding and thermoelectric properties of the non-centrosymmetric Ba-based chalcogenides Ba2In2X5 (X=S, Te)(Elsevier Ltd., 2025) İrfan, Muhammad; İbrahim, Fatma A.; Hamdy, Mohamed S.; Issa, Shams A.M.; Zakaly, Hesham M.H.We explore the structural, elastic, optoelectronic, Radiation Shielding, and thermoelectric properties of Ba2In2X5 (X = S, Te) using first-principles computations and semi-classical Boltzmann Transport equations. These materials are classified as semiconductors exhibiting band gaps of 2.0 eV and 3.0 eV for both investigated NLO compounds that have more significant direct band gaps of superior optical birefringence and second-order NLO coefficients. The bonding properties have been investigated by analyzing the electron charge density (ECD) contour of the (1 0 1) crystallographic plane. It is clear from the reflectivity spectra that both compounds have a high degree of reflectivity, which could make them useful as UV and visible light shields. From 0 to 14.0 eV, the approximated reflectivity values, R (ω), are displayed against the incident photon energy. Therefore, the reflectivity is around 30 % before E ≈ 12.0 eV and 40 % reflection at ∼13.0 eV. Phase matching is possible for both compounds detected, as shown by the birefringence computations. Furthermore, the radiation shielding properties of Ba2In2S5 and Ba2In2Te5 have been evaluated using Phy-X software, demonstrating their potential effectiveness in medical and nuclear energy applications. The thermoelectric properties display N-type nature at low temperatures when the Seebeck coefficient changes from N to P-type at higher temperature ranges. These compounds have remarkable optical and thermal properties, rendering them highly attractive materials for thermoelectric and optoelectronic devices. © 2024 Elsevier LtdÖğe First-ever fusion of high entropy alloy (HEA) with glass: Enhancing of critical properties of zinc-tellurite glass through TiZrNbHfTaOx incorporation(Elsevier Ltd, 2024) Güler, Ömer; Kılıç, Gökhan; Kavaz, E; İlik, Erkan; Güler, Seval Hale; ALMisned, Ghada; Tekin, Hüseyin OzanMany oxide additives have historically been used to enhance the radiation shielding properties of glasses, yet the potential of high-entropy oxides (HEOs), which have gained popularity in material science for their unique properties, has not been explored in this context. This study is the first to investigate the radiation shielding capabilities of Zinc-Tellurite glass infused with High Entropy Oxide (HEO), specifically utilizing the novel attributes of a synthesized TiZrNbHfTa. In this study, the nuclear shielding properties of newly fabricated Zinc-Tellurite glasses doped with TiZrNbHfTaOx with a composition (25ZnO·75TeO2)100-x. (TiZrNbHfTaOx)x (x = 0, 1, 2, 3, 4 mol%) were studied. Through the synthesis of a TiZrNbHfTa HEA and its integration into glass structure, we have developed a series of novel materials with enhanced protective properties against both gamma-ray and neutron radiation. Experimental results demonstrate that the HEO-infused glass, particularly the HEC1-4 composition, significantly surpasses traditional shielding materials in neutron attenuation, evidenced by its superior effective neutron removal cross-section. Additionally, the HEC1-4 glass demonstrates improved gamma-ray shielding capabilities, with increased mass attenuation coefficients and decreased half-value layers, indicating a higher capacity for photon interaction and absorption. It can be concluded that the incorporation of High Entropy Alloys into glass matrices not only opens a new frontier in radiation shielding materials but also provides a versatile and effective solution with considerable potential for enhancing safety measures in radiation-prone environments. © 2024 Elsevier Ltd and Techna Group S.r.l.Öğe Frequency domain channel-wise attack to CNN classifiers in motor imagery brain-computer interfaces(IEEE-INST electronics electrical engineers, 2024) Huang, Xiuyu; Choi, Kup-Sze; Liang, Shuang; Zhang, Yuanpeng; Zhang, Yingkui; Poon, Simon; Pedrycz, WitoldObjective: Convolutional neural network (CNN), a classical structure in deep learning, has been commonly deployed in the motor imagery brain-computer interface (MIBCI). Many methods have been proposed to evaluate the vulnerability of such CNN models, primarily by attacking them using direct temporal perturbations. In this work, we propose a novel attacking approach based on perturbations in the frequency domain instead. Methods: For a given natural MI trial in the frequency domain, the proposed approach, called frequency domain channel-wise attack (FDCA), generates perturbations at each channel one after another to fool the CNN classifiers. The advances of this strategy are two-fold. First, instead of focusing on the temporal domain, perturbations are generated in the frequency domain where discriminative patterns can be extracted for motor imagery (MI) classification tasks. Second, the perturbing optimization is performed based on differential evolution algorithm in a black-box scenario where detailed model knowledge is not required. Results: Experimental results demonstrate the effectiveness of the proposed FDCA which achieves a significantly higher success rate than the baselines and existing methods in attacking three major CNN classifiers on four public MI benchmarks. Conclusion: Perturbations generated in the frequency domain yield highly competitive results in attacking MIBCI deployed by CNN models even in a black-box setting, where the model information is well-protected. Significance: To our best knowledge, existing MIBCI attack approaches are all gradient-based methods and require details about the victim model, e.g., the parameters and objective function. We provide a more flexible strategy that does not require model details but still produces an effective attack outcome.Öğe From Fuzzy Rule-Based Models to Granular Models(Institute of Electrical and Electronics Engineers Inc., 2025) Cui, Ye; Hanyu, E.; Pedrycz, Witold; Li, ZhiwuFuzzy rule-based models constructed in the presence of numeric data are nonlinear numeric models producing for any input some numeric output. There are no ideal models so the obtained numeric output could create a false illusion of achieved accuracy. A desirable approach is to augment the results with some measure of confidence (credibility) by admitting a granular rather than numeric format of the produced output values of the model. Our focus of this study is on fuzzy Takagi–Sugeno rule-based models whose conclusions are constant. The ultimate objective is to extend such models to the generalized granular structure with the conclusions formed as information granules. We study information granules described by intervals and fuzzy sets as well as probabilistic Gaussian information granules. The original design of the granular model is realized by involving the principle of justifiable granularity. Using this principle, we also show how to determine the equivalence between information granules. The construction of probabilistic information granules of the model is completed with the aid of optimized Gaussian process models. The granular models built in this way constitute a substantial and application-oriented departure from the numeric fuzzy models by offering a comprehensive insight into the quality of the produced results. The experimental studies based on synthetic and publicly available data demonstrate the design process and discuss the quality of the obtained results. © 2024 IEEE.Öğe High-Density Lead Germanate Glasses with Enhanced Gamma and Neutron Shielding Performance: Impact of PbO Concentration on Attenuation Properties(Prof.Dr. İskender AKKURT, 2025) Alkarrani, Hessa; Şen Baykal, Duygu; ALMisned, Ghada; Tekin, Hüseyin OzanLead germanate glasses, improved with lead oxide (PbO), have emerged as effective materials for radiation shielding due to their increased density and structural robustness. The goal of this study is to find out how well lead germanate glasses with PbO concentrations between 20 and 55 mol% can block gamma rays and neutrons. The Phy-X/PSD software was used to obtain important numbers like the mass attenuation coefficient (MAC), the linear attenuation coefficient (LAC), the half-value layer (HVL), the mean free path (MFP), and the fast neutron removal cross section (FNRCS). The results show that the 55PbGe sample, which has the most PbO, has better gamma-ray attenuation and a low energy absorption buildup factor (EABF). This makes it a good choice option for locations requiring compact but efficient radiation shielding. The 50PbGe sample, on the other hand, demonstrates effective neutron shielding capabilities, suggesting it may be suitable for applications requiring protection against both gamma and neutron exposure. Higher PbO content is linked to better radiation blocking, which supports the idea that lead germanate glasses could be used instead of traditional lead-based shielding materials. © IJCESEN.Öğe Identifying causes of aviation safety events using wW2V-tCNN with data augmentation(Taylor and Francis Ltd., 2025) Xiong, Sheng Hua; Wei, Xi Hang; Chen, Zhen Song; Zhang, Hao; Pedrycz, Witold; Skibniewski, Mirosław J.Identifying the causes of these safety events is crucial for safety agencies to create recommendations and for airlines to enhance procedures and mitigate hazards. This paper proposes a model to identify the causes of civil aviation safety events using a weighted Word2Vec-based Text-CNN (wW2V-tCNN) algorithm and data augmentation techniques. A corpus is built by matching narrative texts from investigation reports with cause labels from the Aviation Safety Network database. This corpus is transformed into Text-CNN inputs using a weighted sentence vector method based on word embeddings, considering word frequency and part-of-speech weighting. Additionally, a novel document balancing method is introduced for data augmentation. The proposed identification model achieves Macro-F1 and Macro-accuracy scores of 0.9803 and 0.9699, outperforming traditional methods and showing significant improvement over models like Doc2vec and SBERT. This model provides an accurate tool for safety agencies and airlines to analyze and effectively mitigate civil aviation safety events. © 2025 Informa UK Limited, trading as Taylor & Francis Group.Öğe Improving the performance of self-organizing map using reweighted zero-attracting method(Elsevier B.V., 2024) Hameed, Alaa Ali; Jamil, Akhtar; Alazzawi, Esraa Mohammed; Marquez, Fausto Pedro Garcia; Fitriyani, Norma Latif; Gu, Yeonghyeon; Syafrudin, MuhammadIn this paper, we introduce a novel approach to enhance the accuracy and convergence behavior of Self-Organizing Maps (SOM) by incorporating a reweighted zero-attracting term into the loss function. We evaluated two SOM versions: conventional SOM and robust adaptive SOM (RASOM). The enhanced versions, reweighted zero-attracting SOM (RZA-SOM) and reweighted zero-attracting RASOM (RZA-RASOM), include an l1 norm in the error function to add a zero-attractor term, which improves weight coefficient adjustments while preserving topology. The models were assessed for convergence speed and misadjustment under sparsity assumptions of the true coefficient matrix, and their robustness was tested under conditions of increased non-zero taps. Using six different datasets, we compared the performance of RZA-SOM and RZA-RASOM against conventional SOM and RA-SOM in terms of accuracy, quantization error, and topology preservation. Experimental results consistently demonstrated that RZA-SOM and RZA-RASOM surpassed the performance of conventional SOM and RA-SOM. © 2024 The AuthorsÖğe Coupled Multimodal Emotional Feature Analysis Based on Broad-Deep Fusion Networks in Human-Robot Interaction(Institute of Electrical and Electronics Engineers Inc., 2024) Chen, Luefeng; Li, Min; Wu, Min; Pedrycz, Witold; Hirota, KaoruA coupled multimodal emotional feature analysis (CMEFA) method based on broad-deep fusion networks, which divide multimodal emotion recognition into two layers, is proposed. First, facial emotional features and gesture emotional features are extracted using the broad and deep learning fusion network (BDFN). Considering that the bi-modal emotion is not completely independent of each other, canonical correlation analysis (CCA) is used to analyze and extract the correlation between the emotion features, and a coupling network is established for emotion recognition of the extracted bi-modal features. Both simulation and application experiments are completed. According to the simulation experiments completed on the bimodal face and body gesture database (FABO), the recognition rate of the proposed method has increased by 1.15% compared to that of the support vector machine recursive feature elimination (SVMRFE) (without considering the unbalanced contribution of features). Moreover, by using the proposed method, the multimodal recognition rate is 21.22%, 2.65%, 1.61%, 1.54%, and 0.20% higher than those of the fuzzy deep neural network with sparse autoencoder (FDNNSA), ResNet-101 + GFK, C3D + MCB + DBN, the hierarchical classification fusion strategy (HCFS), and cross-channel convolutional neural network (CCCNN), respectively. In addition, preliminary application experiments are carried out on our developed emotional social robot system, where emotional robot recognizes the emotions of eight volunteers based on their facial expressions and body gestures. © 2012 IEEE.Öğe In-depth exploration of the radiation exposure to staff performing endoscopic retrograde cholangiopancreatography procedures (ERCP) through RANDO phantom and TLDs(Springer, 2024) Kesmezacar, Fahrettin Fatih; Tunçman, Duygu; Naycı, Ali Emre; Günay, Osman; Yeyin, Nami; Üzüm, Güngör; Demir, Mustafa; Akkuş, Baki; Elshami, Wiam; Almisned, Ghada; Tekin, Hüseyin OzanThis study provides a comprehensive evaluation of the occupational radiation exposure faced by healthcare professionals during Endoscopic Retrograde Cholangiopancreatography (ERCP) procedures. Utilizing an anthropomorphic RANDO phantom equipped with Thermoluminescent Dosimeters (TLDs), we replicated ERCP scenarios to measure radiation doses received by medical staff. The study meticulously assessed radiation exposure in various corresponding body regions typically occupied by medical staff during ERCP, with a focus on eyes, thyroid, hands, and reproductive corresponding organ regions. The findings revealed significant variations in radiation doses across different body parts, highlighting areas of higher exposure and underscoring the need for improved protective measures and procedural adjustments. The effective radiation doses were calculated using standard protocols, considering the varying levels of protection offered by lead aprons and thyroid shields. The results demonstrate the substantial radiation exposure experienced by healthcare staff, particularly in regions not adequately shielded. This study emphasizes the necessity for enhanced radiation safety protocols in clinical settings, advocating for advanced protective equipment, training in radiation safety, and the exploration of alternative imaging modalities. The findings have crucial implications for both patient and staff safety, ensuring the continued efficacy and safety of ERCP and similar interventional procedures. This research contributes significantly to the field of occupational health and safety in interventional radiology, providing vital data for the development of safer medical practices. © The Author(s) under exclusive licence to Japan Radiological Society 2024.Öğe Synthesis and characterization of Nb 5+and Sm 3+-doped 13-93 bioactive glass particles with improved photon transmission properties for advanced biomedical and dental applications(Elsevier, 2024) Deliormanlı, Aylin M.; ALMisned, Ghada; Tekin, Hüseyin OzanBioactive glasses are renowned for their applications in dentistry, serving as restorative materials, dental adhesives, intracanal medicaments, and agents for enamel remineralization. Niobium pentoxide (Nb 2 O 5 ) is employed in dental adhesive resins and orthodontic adhesives, offering radio -pacifying properties essential for dental materials. Samarium oxide (Sm 2 O 3 ) emerges as a potential additive in aesthetic restorative dental ceramics and resins, enhancing the natural fluorescence of teeth. In this study Nb 2 O 5 and Sm 2 O 3 -doped (1, 3, and 5 wt%) 13 -93 bioactive glass particles were synthesized via the sol-gel method, tailored for dental implementations. We conducted a comprehensive analysis of the physical, structural, and optical properties of the resultant glass powders. Additionally, their in vitro bioactivity and ionizing radiation shielding characteristics were rigorously evaluated. The results indicate that Sm 3 + ions preserve the amorphous nature of the silicate glasses, while Nb 5 + incorporation leads to the crystallization of the T-Nb 2 O 5 phase. Bioactivity assays across three physiological fluids -simulated body fluid, alpha-minimum essential medium, and phosphate -buffered saline, demonstrated the ability of doped glasses to facilitate hydroxyapatite layer formation, with the most pronounced bioactivity observed in phosphate -buffered saline immersed samples. Furthermore, radiation shielding simulations reveal that the addition of Nb 2 O 5 and Sm 2 O 3 enhances the ionizing radiation attenuation capabilities of the glasses, a property that holds significant promise for protecting against radiation in dental radiology. It can be concluded that the dual functionality of Nb 5 + and Sm 3 + -doped bioactive glasses, which may revolutionize restorative dental practices and offer improved protection in radiological applications.Öğe Exploring the gamma-ray shielding performance of boron-rich high entropy alloys(Elsevier Ltd., 2025) Alan, Hatice Yılmaz; Güler, Ömer; Yılmaz, Ayberk; Susam, Lidya Amon; Kavaz, Esra; Kılıç, Gökhan; İlik, Erkan; Oktik, Şener; Akkuş, Baki; ALMisned, Ghada; Tekin, Hüseyin OzanHigh entropy alloys (HEAs) are innovative materials combining multiple principal elements, known for their exceptional properties and wide-ranging applications. This study assesses the gamma-ray shielding capacity of twelve boron-based HEAs through advanced computational methods. Key parameters in terms of understanding the material's ability to reduce radiation intensity, specifically half-value layer (HVL) and tenth-value layer (TVL); its capacity to absorb or scatter photons, including mass attenuation coefficient (MAC) and linear attenuation coefficient (LAC); and other related factors such as equivalent atomic number (Zeq), effective atomic number (Zeff), effective electron density (Neff), mean free path (MFP), and fast neutron removal cross-section (FNRCS) were calculated for photon energies between 0.015 and 15 MeV using the computational method Phy-X/PSD (Photon Shielding and Dosimetry). Additionally, the interaction of alpha particles and protons with these alloys was assessed by calculating energy deposition KERMA (Kinetic Energy Released per Unit Mass) and mass stopping power (MSP) using PAGEX (interaction of protons, alpha, gamma rays, electrons, and X-rays with matter) software, while SRIM (Stopping and Range of Ions in Matter) was employed to estimate particle penetration depths. Electron interactions were evaluated using ESTAR (Stopping Power and Range Tables for Electrons) for stopping power and penetration depth. Among the alloys, Sample 10, S10, (Zr10.8%-Hf21.3%-Nb11.0%-Ta21.6%-W22.0%-B13.1%) exhibited efficient shielding properties due to its high density and interaction characteristics. It can be concluded that boron-based HEAs with optimized compositions and high densities demonstrate significant potential for advanced radiation protection applications. © 2025 Elsevier Ltd