ARO-THE SCIENTIFIC JOURNAL OF KOYA UNIVERSITY
Not a member yet
373 research outputs found
Sort by
Artificial Intelligence-based Digital Pathology Assessment of CD44s Expression in Breast Cancer: Association with Clinicopathological Features and Survival Outcomes
Full text linkBreast cancer (BC) exhibits considerable molecular and clinical heterogeneity, complicating prognostic evaluation. The cluster of differentiation 44 standard (CD44s) isoform has been proposed as a prognostic marker in various cancers; however, its role in BC remains unclear. This study evaluated CD44s expression in BC tissues and its association with clinicopathological features and survival outcomes using an artificial intelligence (AI)-based digital pathology scoring method. A retrospective analysis of 98 BC tissue samples is conducted, with CD44s cell membrane protein expression assessed through both manual and AI based immunohistochemical (IHC) scoring. Statistical analyses included Pearson’s chi-square test, Kaplan-Meier (log-rank), and Cox regression. CD44s expression was observed in 65.31% of patients. No significant associations are found between CD44s expression and clinicopathological characteristics, including age, tumor size, lymph node metastasis, histological grade, lymphovascular invasion (LVI), or hormone receptor status (all p > 0.05). Survival analysis reveals no significant association between CD44s expression and overall survival (OS, p = 0.1345) or progression-free survival (p = 0.0669). While CD44s expression is prevalent in BC samples, it is not an independent prognostic factor; LVI is the only significant predictor of OS (p = 0.036). Finally, the moderate agreement between AI and manual scoring (Cohen’s Kappa = 0.4337, p < 0.0001) supports the potential of AI-assisted methods for biomarker quantification, warranting further validation in larger cohorts
Synthesis and Analysis of the Density States and Optical Characteristics of Se100-X TeX Semiconductors
Full text linkThe widespread commercial importance of selenium makes it an interesting element. It serves as an effective host matrix for chalcogenide alloys. However, pure selenium has a short lifetime and poor sensitivity. Therefore, specific chemical elements, such as tritium, have been used to overcome this problem. Se-Te alloys are preferred over selenium for their numerous advantages, such as increased electrical sensitivity, thermal stability, and applications in xerography. In this manuscript, the effects of partially substituting tellurium for selenium are studied for amorphous Se100-x Tex chalcogenide alloys prepared by melt quenching and spraying procedures to produce bulk and thin films, respectively, with varying tellurium concentrations (x = 10, 20, 30, and 40). X-ray diffraction of samples with different concentrations revealed that all samples had an amorphous (glassy) structure. Continuous electrical conductivity is also studied to determine the conduction mechanisms, effective energies, and densities of localized and extended states. The results of electrical conductivity measurements confirm the existence of two conduction modes (extended-state conduction at high temperatures and localized state conduction at intermediate and low temperatures in the tails of the conduction and valence bands). It is also found that the density of states, local and extended state coefficients, and activation energies are significantly affected by the partial substitution of selenium with tellurium. The optical properties of the Se₁₀₀₋ₓTeₓ films are studied using ultraviolet-visible spectroscopy, and it is found that the overall absorption increases while the energy gap decreases with increasing tellurium concentration
Scalable and Efficient Multi-Class Brain Tumor Classification with a Compact Hybrid Deep Learning Model for Real-Time Applications
Full text linkMedical diagnostics require brain tumor classification to operate in real-time so the task demands accurate results with efficient processing abilities. A new hybrid deep learning solution merges convolutional neural networks (CNNs) with support vector machines (SVMs) to improve classification results as this paper describes. A total of four tumor categories including glioma, meningioma, and pituitary tumors together with no tumor appearance contribute to the magnetic resonance imaging (MRI) dataset are used for analysis. We applied and organized three pre-trained deep learning models: Alex-Net, DarkNet-19, and ResNet-50 for comparison. A newly engineered compact CNN model linked with an SVM classifier brought decreased model dimensions while keeping excellent accuracy rates. A proposed compact CNN model delivers 97.50% accuracy through its smaller 2.38 MB size and additional SVM integration results in 97.45% accuracy using 1.43 MB. A Graphical User Interface (GUI) system comprising automated tumor classification capabilities is created to improve real-time systems that visualize MRI scans and illustrate predicted labels in addition to displaying confidence scores. A GUI enables smooth access to the trained model while being suitable for medical practice mobile healthcare environments and edge computing needs. The proposed system shows that lightweight architectures work excellently in real-time system applications especially when used for edge computing and mobile healthcare frameworks. The proposed solution demonstrates superiority over established models through its ability to scale efficiently
Mechanical and Microstructure Characteristic of Oil- based Drilling Cuttings as Mineral Powder Substitute in Hot Mix Asphalt Mixture
Full text linkBeyond the intensive worldwide oil wells drilling activities for seeking energy, the amount of oil-based drilling cuttings (OBDC) increased significantly, OBDC defined as a wasted drilling mud which is used in the drilling operation of oil wells. The OBDC falls under the category of hazardous waste that contains heavy metals and radioactive elements. In this study, OBDC was used as a substitute of mineral powder in hot mix asphalt. Various doses of OBDC (0%, 25%, 50%, 75%, and 100% by weight) were employed to replace the mineral powder. Marshall specimens were prepared to assess the physical characteristics and examine the microstructure. In results, by employing OBDC to 100%, The Marshall stability decreased from 12.1 kN to 9.22 kN, and flow value decreased from 3.96 mm to 3.3 mm compared to control specimen (0% of OBDC) due to the presence of uncoated and agglomeration of large amount of OBDC particle in bitumen constituent as examined by scanning electron microscope. Air voids increase from 3.9% to 4.26% and voids in mineral aggregates increase from 14.63% to 15.20% when mineral powder replaced by OBDC filler from 0% to 100%, respectively, due to the difference between the specific gravity of OBDC and mineral powder, in which higher percentage of OBDC leads to increase the porosity of the specimen. Utilizing 100% of OBDC instead of the mineral powder is compromised because the result falls within the standard ranges
Impact of Vitamin D Deficiency on Iron Deficiency Anemia: A Comparative Analysis in Iraqi Population
Full text linkTwo important health problems are iron deficiency anemia and vitamin D deficiency, as well as the ability to cope with acute and chronic diseases, because iron and vitamin D are the main elements of physiological functions in the human body. Recent studies have indicated that generalized IDA in both healthy and diseased populations may be associated with inadequate levels of VD. The research comprised 132 participants, 65 with IDA and 67 controls, the study was conducted in a competent cross-sectional design, between the two groups matched by age and gender. The laboratory findings included the study of blood indices. Ferritin, iron, hemoglobin, mean corpuscular volume, red cell distribution width, and VD levels were measured for each participant. Iron metabolism markers showed highly significant variations between the groups. Patients with IDA exhibited considerably lower levels of iron indicators than the healthy control group, except for total iron binding capacity (TIBC), which was increased among the patients. The normal control group showed substantially higher serum VD levels than patients with iron deficient anemia (p < 0.035). This distinction suggests a high positive link between VD levels and iron metabolism markers, except for TIBC, which exhibited a negative correlation. The results showed a significant correlation between VD levels and several iron metabolism markers in the research participants. This suggests that VD may affect how iron is metabolized and help treat IDA. To fully understand the underlying mechanisms and any therapeutic benefit, further research is needed
A Spatio-Temporal Deep Learning Approach for Efficient Deepfake Video Detection
Full text linkDeepfake videos have grown to be a big concern in the modern digital media landscape as they cause difficulties undermining the legitimacy of channels of information and communication. Humans often find it challenging to tell the difference between a fake and a genuine video due to the increasing realism of facial deepfakes. Identification of these misleading materials is the first step in preventing deepfakes from spreading through social media. This work introduces Spatio-temporal Intelligent Deepfake Detector (STIDD), a deep learning system including enhanced spatial and temporal modeling techniques. By means of a pre-trained EfficientNetV2-B0 model, the proposed framework efficiently extracts spatial characteristics from each frame, subsequently, and Bidirectional Long Short-Term Memory layers help to capture temporal relationships from video sequences. We evaluate STIDD on the FaceForensics++ (FF++) dataset encompassing all five manipulation techniques (DeepFakes, FaceSwap, Face2Face, FaceShifter, and NeuralTextures). The experimental results reveal that STIDD achieved precision, recall, and F1-scores all higher than 0.99 and a final test accuracy of 99.51% on the combined FF++ test set. The results demonstrate that the integration of sophisticated spatial extraction and strong temporal modeling allows STIDD to achieve high detection performance while maintaining computing efficiency at just 0.39 Giga Floating-Point Operations (GFLOPs) per inference.
Glucuronidase Gene: A Strong Evidence of a Novel Interaction of Glucuronidase-labeled Gluconacetobacter diazotrophicus with Spinach, Spinacia oleracea L. Seedlings
Full text linkGluconacetobacter diazotrophicus lives inside plant tissue cells in the form of colonies and excretes about half of the fixed nitrogen, which offers potential power that improves plant growth. The aim of this study is to find the interaction of glucuronidase (GUS)-labeled G. diazotrophicus with spinach seedlings and the detection of GUS genes using X-gluc dye (5-bromo-4-chloro-3-indolyl-β-D- glucuronic acid). The GUS protocol is used to detect GUS-labeled G. diazotrophicus in spinach seedling tissues by chemical detection using X-gluc dye. The results show that the spinach seedlings are successfully infected with GUS-labeled G. diazotrophicus , with the survival of the seedlings throughout their growth period and an improvement in the growth of pollinated seedlings. The outcomes of the microscopic inspection of the root slices reveal the presence of bacterial cells at the root tips and their concentration in the area of the cell walls of the peripheral cells. Furthermore, the findings of microscopic examinations of longitudinal sections for cotyledons show the presence of a number of bacteria within epidermal cell walls. This indicates that the determinants of the interaction between these bacteria and spinach seedlings are suitable for the expression of the gene responsible for the formation of the nitrogenase enzyme
Web Page Ranking Based on Text Content and Link Information Using Data Mining Techniques
Full text linkThanks to the rapid expansion of the Internet, anyone can now access a vast array of information online. However, as the volume of web content continues to grow exponentially, search engines face challenges in delivering relevant results. Early search engines primarily relied on the words or phrases found within web pages to index and rank them. While this approach had its merits, it often resulted in irrelevant or inaccurate results. To address this issue, more advanced search engines began incorporating the hyperlink structures of web pages to help determine their relevance. While this method improved retrieval accuracy to some extent, it still had limitations, as it did not consider the actual content of web pages. The objective of the work is to enhance Web Information Retrieval methods by leveraging three key components: text content analysis, link analysis, and log file analysis. By integrating insights from these multiple data sources, the goal is to achieve a more accurate and effective ranking of relevant web pages in the retrieved document set, ultimately enhancing the user experience and delivering more precise search results the proposed system was tested with both multi-word and single-word queries, and the results were evaluated using metrics such as relative recall, precision, and F-measure. When compared to Google’s PageRank algorithm, the proposed system demonstrated superior performance, achieving an 81% mean average precision, 56% average relative recall, and a 66% F-measure
Electrocardiogram Heartbeat Classification using Convolutional Neural Network-k Nearest Neighbor
Full text linkElectrocardiogram (ECG) analysis is widely used by cardiologists and medical practitioners for monitoring cardiac health. A high-performance automatic ECG classification system is challenging because there is difficulty in detecting and categorizing different waveforms in the signal, especially in manual analysis of ECG signals, which means, a better classification system is needed in terms of performance and accuracy. Hence, in this paper, the authors propose an accurate ECG classification and monitoring system called convolutional neural network-k nearest neighbor (CNN-kNN). The proposed method utilizes 1D-CNN and kNN. Unlike the existing techniques, the examined technique does not need training during classifying the ECG signals. The CNN-kNN is evaluated against the PhysioNet’s MIT-BIH and PTB diagnostics datasets. The CNN is fed using the ECG beat raw signal directly. In addition, the learned features are extracted from the 1D-CNN model and its dimensions are reduced using two fully connected layers and then fed to the k-NN classifier. The CNN-kNN model achieved average accuracies of 98% and 97.4% on arrhythmia and myocardial infarction classifications, respectively. These results are evidence of the great ability of the proposed model compared to the mentioned models in this article
The Recovery of Historical Buildings in Post-war Aleppo
Full text linkThroughout history, wars and armed conflicts have severely impacted cultural heritage, erased collective memories, and left entire populations seemingly non-existent. However, recognizing the significance of cultural heritage is the primary impetus for its subsequent reconstruction. Since the Syrian war outbreak in 2011, Aleppo, one of the world’s oldest continuously inhabited urban centers, has suffered significant damage to its historic sites such as shrines, khans, and other architectural treasures due to bombings and clashes. In 2017, a study by the Directorate of Antiquities and Museums in Aleppo revealed that over 70% of the city’s historic center was destroyed. As a result, the cultural heritage of Aleppo and its social and symbolic values have been threatened. This represents a huge loss not only to Syria but also to the international community. This paper explores the significant role that collective memories play in shaping a city’s identity in the aftermath of war. The research aims to analyze the best approach for intervention during the reconstruction phase, whether it be preservation, restoration, enhancement, or eventual reconstruction by reviewing some international experiences. Furthermore, it explains the current situation of the old city of Aleppo and presents some cultural buildings that have been severely damaged or destroyed during the conflict. The study will compare the essential values of each case study and finally conclude with suggestions about the suitable intervention of different case studies that represent the values mentioned before