Altınbaş University Institutional Repository
Not a member yet
5805 research outputs found
Sort by
Optimal Power Flow Based on a Metaheuristics Optimization Approach for the Iraqi Super High Voltages Network
Full text linkOptimal power flow is a tool It enables operators to run the system as efficiently as possible within specific limitations. Therefore, many tools have been developed to assist operators to make decisions for different objectives. The optimal power flow (OPF) problem is the most difficult and complex problem in power system analysis and design due to the nonlinearities and imposed constrains. OPF’s goal is to reduce generation costs and transmission losses. when the demand and generated power are balanced. In this work, the proposed approach uses genetic algorithm (GA) and camping the Hybrid Particle Swarm Optimization and Genetic algorithm (HPSO+GA) as an intelligent methods to perform optimal power flow. Cost functions that are defined and minimized in this work are the overall active losses and amount of required fuel. The viability of the suggested method is confirmed by comparing the results of the presented methodology With previous research results. Using the MATLAB platform, the best load flow technique was evaluated using data from the Iraqi 400 KV transmission network, which consists of 58 buses. Results document the viability of the proposed method in terms of less active losses and reduced fuel costs. Moreover, the proposed GA and HPSO+GA methods requires no iterations hence errors of solution divergence and initial conditions are omitted
The association between monocyte/HDL-C ratio and heart failure
Full text linkThe monocyte/HDL-cholesterol ratio (MHR) was shown to be a marker of inflammation. This study investigated the utilization of this ratio as a measure of severity for heart failure which is a condition associated with inflammation. The MHR was calculated for 323 ambulatory patients with chronic heart failure and compared to other variables associated with the severity of the condition. Additionally, the impact of MHR on the Seattle Heart Failure Model (SHFM) score was investigated. MHR correlated positively with C-reactive protein (r: 0.312, p<0.001) and neutrophil-to-lymphocyte ratio (r: 0.242, p<0.001), but not with platelet-to-lymphocyte ratio. In addition, a correlation was found between the SHFM score and MHR (r:-0.267, p<0.001). The SHFM score exhibited a significant result for proB-type natriuretic peptide (pro-BNP) (p<0.001), neutrophil (p<0.001), hematocrit (p=0.001), and serum creatinine (p=0.001) in the ordinal logistic regression analysis, but not for MHR. MHR showed a negative correlation with left ventricular ejection fraction (r:-0.151, p: 0.007), exhibited a positive association with pro-BNP (r: 0.184, p<0.001), and no correlation with New York Heart Association classes. There is a significant correlation between the MHR value and the factors associated with the severity of heart failure. The prognosis and management of this condition may be assessed by utilizing the MHR value in conjunction with existing biomarkers
An Efficient Malware Detection Method Using a Hybrid ResNet-Transformer Network and IGOA-Based Wrapper Feature Selection
Full text linkThe growing sophistication of malware and other cyber threats presents significant challenges for detection and prevention in modern cybersecurity systems. In this paper an efficient and novel malware classification model using the Hybrid Resnet-Transformer Network (HRT-Net) and Improved Grasshopper Optimization Algorithm (IGOA) is proposed. Convolutional layers in the resnet50 model effectively extract local features from malware patterns, while the Transformer focuses on long-range dependencies and complex patterns by leveraging multi-head attention. The extracted local and global features are concatenated to create a rich feature representation, enabling precise malware detection. The Improved Grasshopper Optimization Algorithm with dynamic mutation coefficient and dynamic inertia motion weights is employed to select an optimal subset of features, reducing computational complexity and enhancing classification performance. Finally, the Ensemble Learning technique is used to robustly classify malware samples. Experimental evaluations on the Malimg dataset demonstrate the high efficiency of the proposed method, achieving an impressive accuracy of 99.77%, which shows greater efficiency compared to other recent studies
Evaluating the Effectiveness of Graph Convolutional Network for Detection of Healthcare Polypharmacy Side Effects
No full textHealthcare polypharmacy is routinely used to treat numerous conditions; however, it often leads to unanticipated bad consequences owing to complicated medication interactions. This paper provides a graph convolutional network (GCN)-based model for identifying adverse effects in polypharmacy by integrating pharmaceutical data from electronic health records (EHR). The GCN framework analyzes the complicated links between drugs to forecast the possibility of harmful drug interactions. Experimental assessments reveal that the proposed GCN model surpasses existing machine learning approaches, reaching an accuracy (ACC) of 91%, an area under the receiver operating characteristic curve (AUC) of 0.88, and an F1-score of 0.83. Furthermore, the overall accuracy of the model achieved 98.47%. These findings imply that the GCN model is helpful for monitoring individuals receiving polypharmacy. Future research should concentrate on improving the model and extending datasets for therapeutic applications
Toward Real-Time Maritime Surveillance: Deep Learning and Feature Fusion for Ship Detection
No full textVolume editors : Shaposhnikov S., Saint Petersburg Electrotechnical University �LETI�, Prof. Popov str. 5, Saint Petersburg
Conference name : 28th IEEE International Conference on Soft Computing and Measurements, SCM 2025
Conference city : St. Petersburg
Conference date : 28 March 2025 - 30 March 2025
Conference code : 210220Ship detection in maritime environments presents significant challenges due to factors like dramatic scale variations, complex backgrounds, and flexible viewpoints in drone-captured images, traditional object detection methods struggle with these conditions, requiring advanced deep learning techniques for effective identification and in this paper, we propose a deep learning-based ship detection system designed to overcome these challenges and the system integrates Gray-Level Co-occurrence Matrix (GLCM) and Histogram of Oriented Gradients (HOG) for feature extraction, enhancing the model's ability to differentiate ships from cluttered backgrounds, a deep neural network with Dropout layers is employed to improve generalization and reduce overfitting. The model Is trained on synthetic datasets and evaluated using key performance metrics like precision, recall, F1-score, accuracy, and ROC-AUC curves, results demonstrate high detection accuracy, effectively minimizing false positives and false negatives, additionally, threshold optimization enhances detection performance across diverse maritime conditions, to further improve efficiency, future research may incorporate Vision Transformers (ViTs) to enhance contextual understanding and reinforcement learning for adaptive detection in dynamic environments and the proposed system contributes to real-time ship monitoring and maritime security, offering a scalable solution for autonomous surveillance and vessel tracking
Comparative Study on Sentiment Analysis Using Advance Deep Learning Models
No full textSentiment Analysis (SA) involves collecting opinions regarding a particular subject and classifying them based on emotional content; it refers to opinion mining, which examines product reviews and online feedback. Capturing relationships of long sequences, contextual meaning, and effectively achieving Cross-Lingual Sentiment Classification can be considered key challenges of the SA. This paper performs a comparative analysis of traditional sequence models, such as Gated Recurrent Unit (GRU) and Bidirectional GRU (Bi-GRU), and state-of-the-art transformer-based models, including Bidirectional Encoder Representations from Transformers (BERT) and XLM-RoBERTa (XLM-R). The traditional sequence models are enhanced with pre-trained Word2Vec embeddings. Firstly, all the models are trained and evaluated using the English IMDB dataset. Then, the XLM-R is assessed on the Spanish IMDB dataset without further fine-tuning. The results indicate that both BERT and XLM-R surpass GRU and Bi-GRU in sentiment classification accuracy. XLM-R obtained the best results, with an accuracy of 93.21%, slightly outperforming BERT, which achieved an accuracy of 93.11% in English. XLM-R was also utilized for zero-shot cross-lingual sentiment classification, achieving a sentiment accuracy of 93.12% in Spanish, close to its performance in English
MEMF-Net: A Mega-Ensemble of Multi-Feature CNNs for Classification of Breast Histopathological Images
Full text linkPathological anatomical images play a pivotal role in diagnosing diseases, notably breast cancer, which affects women globally. These images, obtained through biopsies or post-mortem examinations, are preserved to maintain their structural integrity. Software tools, like computer-aided diagnosis, aid doctors in early detection and treatment planning, contributing to reduced mortality rates. In this context, convolutional neural networks (CNNs) have emerged as valuable tools for diagnosing benign and malignant breast cancers. This paper introduces a Mega Ensemble Net method, leveraging multi-scale combination features on the breast histopathology dataset. Three fine-tuned deep learning models, namely ResNet-18, ResNet-34, and ResNet-50, are integrated into this method. Techniques such as patch extraction for data augmentation, dataset amalgamation, and transfer learning bolster the method’s capabilities. Fusing extracted patches with primary images enhances the method’s robustness and adaptability, offering diverse perspectives and intricate details for nuanced class distinctions. BACH and BreaKHis datasets have been used to evaluate the Mega Net. During four-fold cross-validation on the test folds, the Mega-Net demonstrates 99% test-set accuracy in the full image and 98% test-set accuracy in patches within the multi-classification BACH dataset and 99% test-set accuracy within the binary classification BreaKHis dataset. Moreover, the MEMF-Net achieved a multi-classification test accuracy of 98.95% across an optimal selected MEMF model in validation testing images
Prognostic Value of the Hemoglobin, Albumin, Lymphocyte, Platelet Score in Metastatic Mesothelioma: A Retrospective Study
No full textIntroduction: Malignant mesothelioma is a rare but aggressive cancer with limited treatment options and poor prognosis. Hemoglobin, Albumin, Lymphocyte, Platelet (HALP) score, reflecting inflammation and nutritional status, is a potential prognostic marker in various cancers. Our study aimed to investigate the prognostic value of the HALP score in mesothelioma. Methods: This retrospective study included 68 metastatic mesothelioma patients diagnosed between 2015 and 2023. Clinical and laboratory data were collected, and HALP scores were calculated at the time of metastasis. Patients were divided into HALP-low and HALP-high groups based on the median HALP score. Overall survival (OS) and progression-free survival (PFS) were analyzed using the Kaplan-Meier method, and prognostic factors were assessed using univariate and multivariate analyses. Results: The median HALP score was 24.85. The median OS for the entire cohort was 11.59 months. Patients with low HALP scores had significantly worse OS (7.81 months) compared to those with high HALP scores (16.36 months) (p = 0.01). Similarly, median PFS was significantly shorter in the HALP-low group (7.29 months) compared to the HALP-high group (12.12 months) (p = 0.02). In multivariate analysis, low HALP score (p = 0.02) and de novo metastatic disease (p = 0.01) remained independent prognostic factors for OS. Conclusion: This study demonstrates that the HALP score is an independent prognostic biomarker in metastatic mesothelioma. Low HALP scores are associated with worse OS and PFS. Given its simplicity and cost-effectiveness, the HALP score may be a valuable tool for risk stratification and treatment decision-making in clinical practice
Opinions of nurse managers on impact of domestic violence on work life: a qualitative study
Full text linkBackground: Domestic violence is a pervasive issue that affects women regardless of language, religion, race, geography, culture or social structure. Objective: This study aimed to explore the perspectives of nurse managers on how domestic violence impacts employees’ work lives. Method: This research was conducted in design by using the qualitative research method. The necessary permissions from institutions and ethical committee approval have been obtained. The sample of the research was determined by maximum diversity method, one of the purposeful sampling methods. The sample of the research consists of 52 female nurse managers who work in different managerial positions, different experience and training, from three different hospital groups (a university hospital, a ministry of health hospital, and two private hospitals) in Turkey. The data collection process was terminated when data saturation was reached. The data were collected using a semi-structured interview form. Interviews were conducted face-to-face with nurse managers in hospitals. The interviews lasted for 63 min on average. The collected data were analyzed by content analysis method, and theme, sub-themes and codes were created. Results: This study was presenting results related to the theme of “reflections of domestic violence on work life.” The results under this theme were explored through three subthemes: “how it is noticed that the employee is subjected to violence,” “how domestic violence is reflected on work life,” and “how the nurse manager approaches the employee who is subjected to domestic violence”. Conclusion: In interviews conducted with nurse managers, it was observed that employees often hesitated to disclose that they were subjected to domestic violence; some only revealed their situation when they felt compelled to do so or when it was noticed by the nurse manager. The effects of domestic violence on work life were stated to have included absenteeism, physical inability to work, reduced team cohesion, performance decline, and difficulty adhering to work schedules. Nurse managers adopted several strategies to support employees affected by domestic violence, including managing other employees’ attitudes, adjusting work arrangements, removing her from the environment, providing support (legal, psychological, sociological, and temporary accommodation), and ensuring security measures. The findings show that the necessity of developing institutional policies and protocols on domestic violence within healthcare settings, establishing early note and intervention mechanisms, and implementing structured training programs for nurse managers and healthcare professionals on this issue. Moreover, it is of great importance to integrate domestic violence prevention strategies into national health, family, and social policies. Clinical trial number: Not applicable
The histological examination of vena saphena magna as a graft in coronary artery bypass surgery
No full textCoronary artery bypass surgery (CABG) is one of the most frequently performed surgical procedures worldwide, owing to the increasing incidence of coronary artery disease, which remains a leading cause of death globally. Following CABG, the development of occlusion in vein grafts is one of the significant indicators of poor prognosis, resulting in an increased risk of recurrent ischemic events and repeat revascularization. In the early and late postoperative periods, the use of healthy grafts with intact endothelium is critical to reduce mortality and morbidity rates. In this study, the histopathological findings of the vena saphena magna grafts in 12 patients who underwent CABG were evaluated to identify any preoperative degenerative changes in the grafts. The findings of the study showed that preoperative morphological degeneration was minimal in most grafts. However, in one sample, intimal fibrosis narrowed the lumen, while another sample exhibited mild medial sclerosis. In contrast, all other samples showed minimal or no degeneration. Consequently, assessing the histopathological condition of vessels before the operation is crucial to avoid using unsuitable grafts and to direct the surgeon to use different grafts if necessary. This study highlights the importance of examining the histology of vena saphena magna grafts to ensure their suitability as a bypass conduit in CABG surgery