Portal of UHD Academic Journals
Not a member yet
496 research outputs found
Sort by
Enhanced Kidney Stone Detection and Classification Using SVM and LBP Features
Full text linkNephrolithiasis is a scientific term that refers to kidney stones and means the formation of crystal concretions in the kidney. It is considered a widespread situation that affects millions of people worldwide. Those stones can cause serious discomfort to infected people, especially when they traverse the urinary system, although, the big stones may need a surgical intervention. Various systems are already in use to address kidney stones, including ultrasound imaging for detection, extracorporeal shock wave lithotripsy (ESWL) for non-invasive stone fragmentation, and ureteroscopy for surgical removal, showcasing the advances in medical technology for managing this condition. This study presents an approach for detecting stones in the affected kidney. A public dataset has been employed in this work, containing (2370) images of healthy and affected kidneys. The dataset was utilized to train the proposed approach for the aim of stone detection. To achieve high detection accuracy, we implemented two key phases before classification. The preprocessing phase enhances image quality by reducing noise using a median filter and improving contrast through contrast stretching and tone enhancement. The segmentation phase follows, accurately identifying the kidney’s edges and regions of interest for effective feature extraction. The Local Binary Pattern (LBP) technique, combined with the support vector machine (SVM) algorithm serves as the primary components of the proposed model. The feature extraction comes into action through the LBP technique as a preparation step for the SVM classifier to complete the stone detection process. The approach introduced in this paper has the potential to enhance detection accuracy and efficiency. Furthermore, it could be used as an early detection tool to identify potential cases, thereby helping to prevent complications and adverse outcomes. This method aims to improve on the traditional manual process employed by radiologists, which could be described as time and effort consumption rather than the exposure of the interpretations. The obtained results were compared with the most relevant approaches in the field of kidney stone detection, demonstrating the model’s effectiveness in achieving the desired goal with a diagnostic accuracy of 96.37% for kidney stones
Utilizing Machine Learning Techniques for Cancer Prediction and Classification based on Gene Expression Data
Full text linkCancer classification through genetic evaluation has become a hot topic among researchers. It holds the promise of delivering systematic, precise, and scientifically backed diagnoses for different types of cancer. Lately, several studies have delved into cancer classification by leveraging data mining techniques, machine learning algorithms, and statistical methods to thoroughly analyze high-dimensional datasets. Detecting cancer early by examining gene expression data is vital for providing effective patient care. Each sample in the Gene dataset usually includes a range of features, each representing a specific gene. In this paper, we propose a unique approach that utilizes DistilBERT, a distilled version of the Bidirectional Encoder Representations from Transformers, for cancer classification and prediction. In addition, our model integrates a self-attention mechanism in the transformer layers to enhance the model’s focus on key features and employs an embedding layer for dimensionality reduction, improving the processing of gene statistics, preventing overfitting, and boosting generalization. We utilized datasets from important resources: The gene expression omnibus, which provided microarray records of lung and ovarian cancers, and the cancer genome atlas (TCGA), which offered RNA-Seq facts encompassing multiple most cancer types (breast invasive carcinoma, kidney renal clear cell carcinoma, colon adenocarcinoma, lung adenocarcinoma, and prostate adenocarcinoma). Our approach established excessive accuracy across all datasets, showcasing big upgrades in overall model performance compared to present strategies within the subject. The results underscore the ability to leverage transformer-primarily based architectures for strong cancer-type prediction and classification. Our approach achieved and improved exceptional accuracy compared to previous studies, with DS1: 97.56% for lung cancer, DS2: 100% for ovarian cancer, and DS3: 99.504% for the TCGA dataset
Enhancing Clinical Decision Support: A Deep Learning Approach for Automated Diagnosis of Eye Diseases from Fundus Images
Full text linkBackground and Objective: One of the most crucial sensory organs that helps the human brain receive information about the outside world is the eye. Due to its structural features, the back surface of the eye (retina) provides valuable insights about various disorders. It is essential to protect the eyes from diseases that could lead to vision impairment. If diseases affecting the retina are not identified and treated promptly, vision loss cannot be reversed. Therefore, effective automatic detection systems are necessary, as manual diagnosis is not only time-consuming, expensive, and labor-intensive but also requires a high level of expertise. To address this issue, many deep learning (DL)-based solutions have been proposed for screening retinal conditions. This study aimed to develop an effective system for the automated classification of four major eye conditions to support clinical decision-making. Methods: In this research, various convolutional neural network (CNN) architectures were applied to the dataset, and their performance was recorded. The CNN models are the common transfer learning pre-trained models on the ImageNet dataset. Finally, we developed a hybrid DL model combining DenseNet169 and MobileNetV1 to extract deep features from fundus images and perform multiclass classification into four categories: diabetic retinopathy, cataract, glaucoma, and normal fundus. Results: This hybrid approach yielded impressive results, attaining 92.99%, 93.02%, 92.85%, 92.90%, and 98.77% for accuracy, precision, recall, F1-score, and area under the curve (AUC) on a publicly available Kaggle dataset, i.e., eye disease classification. These results indicate that the hybrid approach enhances classification accuracy compared to other individual pre-trained CNN models. Conclusion: In summary, this study evaluated a substantial number of pre-trained models and developed a framework based on the top two optimal-performing models. Given that retinal image detection and diagnosis are critical for patient eye therapy and rehabilitation, our study offers an innovative framework that can function as a diagnostic aid for eye-related diseases
Address Bar Spoofing in Contemporary Web Browsers: A Taxonomy, Exploitation Study, and Mitigation Guidelines
Full text linkThe browser address bar is the cornerstone of user trust and web security. Despite advancements, address bar spoofing remains a persistent threat, enabling attackers to make malicious URLs appear legitimate. This paper presents an extensive investigation into address bar spoofing vulnerabilities across modern desktop and mobile browsers. We introduce a comprehensive taxonomy classifying over 15 distinct spoofing techniques, many of which are novel. Across systematic testing, over 70 vulnerabilities were identified and responsibly disclosed, resulting in patches across more than 15 browsers. These findings are enumerated in this paper for verification. This research analyzes the root causes of these vulnerabilities, highlighting common pitfalls in URL parsing, display logic, and UI state management. Based on our findings, we propose a robust mitigation framework and best practices for browser developers, alongside actionable advice for users. Our findings underscore the ongoing challenge of maintaining address bar integrity and the critical need for continuous vigilance in browser security. A public repository documents these findings to aid further research
Exploring the Association Between Screen Time Exposure and Autism Spectrum Disorder in Preschool-Aged Children in Sulaymaniyah
Full text linkIntroduction: Autism Spectrum Disorder (ASD) is a neurodevelopmental condition characterized by social communication deficits and repetitive behaviors. Recent research suggests that excessive screen time may influence ASD-related developmental patterns. This study examines the correlation between screen exposure and ASD symptoms in preschool-aged children in Sulaymaniyah, Iraq. Methods: A cross-sectional study was conducted on children aged 2-6 years, including both formally diagnosed ASD cases and those exhibiting ASD-related symptoms. Data collection involved structured face-to-face questionnaires adapted from previous research, covering screen time duration, content type, parent-child interactions, and ASD symptom prevalence. Statistical analyses, including Kendall’s tau-b correlation and logistic regression, were performed using IBM SPSS Statistics 22. Results: The study found that children in Sulaymaniyah engage in excessive screen exposure, averaging over four hours per day—far exceeding international recommendations. Logistic regression analysis identified screen time as a significant predictor of ASD-related symptoms (p = 0.011, Exp(B) = 6.364). Additionally, socioeconomic factors, including household income and parental education level, showed associations with screen time habits. Conclusion: Findings suggest a strong correlation between prolonged screen exposure and ASD-related behaviors in young children. Socioeconomic determinants further influence screen time regulation. These results underscore the need for parental guidance and structured screen time policies to mitigate potential neurodevelopmental impacts. Future research should explore causal relationships and intervention strategies for screen exposure management in early childhood
Surgery Versus Flexible Endoscopic Rubber Band Ligation for Grade 2 and 3 Internal Hemorrhoids
Full text linkSurgery has traditionally been the primary treatment for symptomatic internal hemorrhoids. However, office-based interventions such as rubber band ligation (RBL) are increasingly used for Grades 1–3 hemorrhoids. Flexible endoscopic RBL offers a minimally invasive alternative, whereas surgery remains standard for Grade 4. To compare the effectiveness of flexible endoscopic RBL versus surgical hemorrhoidectomy in managing symptomatic Grades 1–3 internal hemorrhoids, focusing on bleeding control, pain, recovery time, and recurrence. A comparative study of 55 patients treated with flexible endoscopic RBL (using Olympus kits) and 55 matched patients undergoing conventional excisional hemorrhoidectomy (open technique). Patients choose their treatment after counseling. Outcomes were assessed over 1 year, with follow-up at 1 week, 3, 6, and 12 months. Pain was measured using a Visual Analog Scale (≥4 defined significant pain). Statistical analysis used a statistical package for the social sciences v26 (t-tests for continuous variables, Chi-square for categorical; P < 0.05 significant). Both groups showed comparable efficacy: Bleeding control (95% vs. 93%), mucosal prolapse resolution (96% vs. 97%), and 1-year recurrence (30% vs. 29%). RBL had superior post-procedural outcomes: Lower pain (10% vs. 90%), fewer work absences (5% vs. 95%), and no bed-boundness (0% vs. 100%; all P < 0.05). Flexible endoscopic RBL is as effective as surgery for Grades 1–3 hemorrhoids but significantly reduces pain, recovery time, and work absenteeism. RBL should be considered a first-line option for eligible patients
Molecular Identification and Antibiotic Resistance Profile of Some Pseudomonas aeruginosa Clinical Isolates
Full text linkPseudomonas aeruginosa is a Gram-negative, opportunistic bacterium being increasingly recognized as the causative agent of hospital-acquired infection, especially in immunocompromised patients. The bacterium is well known for its environmental persistence and multidrug resistance (MDR). This study aimed to characterize the antibacterial persistence profiles and genetic diversity of P. aeruginosa isolates from clinical settings in Sulaymaniyah city, Iraq. Twenty-eight suspected P. aeruginosa isolates were collected from hospitals and private laboratories from October 2024 to January 2025. The collected bacteria were identified with standard microbiological procedures, the VITEK 2 system, and confirmation through 16S RNA sequencing. Ten antibiotics were tested following the guidelines of the Clinical and Laboratory Standards Institute for antibiotic susceptibility testing. 12 out of 28 collected isolates were confirmed as P. aeruginosa. The antimicrobial susceptibility testing indicated that resistance to Imipenem, Ceftazidime, and Cefepime was seen in 66.7% of the isolates (MDR isolates), while Ceftolozane/Tazobactam had the lowest resistance rate (41.7%). It is observed that 66.7% of isolates subjected to MDR show resistance to three or more antibiotic classes. There is a high prevalence of P. aeruginosa in clinical isolates that are resistant to antibiotics. These results underscore the urgent need for improved antimicrobial stewardship programs and the development of alternative treatment options to address this rising public health concern. Through media genomics and molecular methods, reliable identification has been enhanced, which signifies the importance of both studies
Awareness of Infection Control and Barriers among the Healthcare Workers in Sulaymaniyah City, Iraq
Full text linkBackground: Healthcare workers (HCWs) are at risk of exposure to blood-borne pathogens such as human immunodeficiency virus and hepatitis B and C viruses through sharps injuries and contact with body fluids. Standard infection control practices are critical to preventing such exposures. Objectives: This study aimed to assess the awareness of infection control measures and perceived barriers among HCWs in Sulaymaniyah governorate, Iraq. Patients and Methods: A cross-sectional survey was conducted between June 2021 and May 2022 among 557 HCWs working in different hospitals in Sulaymaniyah. Data were collected using a self-administered questionnaire with 44 items covering awareness, standard precautions, and barriers to infection control. Descriptive and inferential statistics were applied to analyze the data. Results: Overall, 79% of participants demonstrated adequate awareness of infection control practices, and 82% reported compliance with standard precautions. A significant association was observed between participation in infection control training and higher awareness levels (P < 0.05). Despite this, 52% of respondents acknowledged barriers to consistently applying standard precautions within their hospital units. Conclusions: Although awareness and compliance with infection control practices among HCWs in Sulaymaniyah were generally high, notable barriers remain. Regular training and institutional support are recommended to enhance adherence to standard precautions and strengthen infection prevention in healthcare facilities
Link Prediction in Dynamic Networks Based on the Selection of Similarity Criteria and Machine Learning
Full text linkThe study’s findings showed that link prediction utilizing the similarity learning model in dynamic networks (LSDN) performed better than other learning techniques including neural network learning and decision tree learning in terms of the three criteria of accuracy, coverage, and efficiency., Compared to the random forest approach, the LSDN learning algorithm’s link prediction accuracy increased from 97% to 99%. The proposed method’s use of oversampling, which improved link prediction accuracy, was the cause of the improvement in area under the curve (AUC). To bring the ratio of the classes closer together, the suggested strategy attempted to produce more samples from the minority class. In addition, similarity criteria were chosen utilizing feature selection techniques based on correlation that had a strong link with classes. This technique decreased over-fitting and improved the suggested method’s test data generalizability. Based on the three criteria (accuracy, coverage, and efficiency), the research’s findings demonstrated that link prediction utilizing the similarity LSDN outperformed other learning techniques including neural network learning and decision tree learning. Compared to the random forest algorithm, the LSDN algorithm’s link prediction accuracy increased from 97% to 99%. The oversampling in the suggested strategy, which increased link prediction accuracy, is what caused the increase in AUC. To bring the ratio of the classes closer together, the suggested strategy attempted to produce more samples from the minority class. In addition, similarity criteria were chosen utilizing feature selection techniques based on correlation that had a strong link with classes. This technique decreased over-fitting and improved the suggested method’s test data generalizability
Infant Mortality in Iraq and Iran: A Comparative and Predictive Study
Full text linkInfant mortality is one of the most important indicators of the A country’s health status and socio-economic development. Classified as the death of an infant before his or her first birthday, the rate of infant mortality is an indicator of whether a society has sufficient healthcare, nutrition, sanitation, and maternal services. The research presents comparative predictive analysis for Iraqi and Iranian infant mortality rates (IMR) during the period 2025–2032 with the help of exponential grey mod. These findings demonstrate a high effectiveness of the proposed aforementioned application with achieved mean absolute percentage error (MAPE) values of 0.795% and 0.907% for Iraq and Iran, respectively, which correspond to accuracy rates of 99.20% and 99.09%, both as both Iraq and Iran’s MAPE values in the “Highly accurate.” Corresponding precision values also classifies the decisions in “Highly accurate” (P ≥ 99.0%). A historical comparison showed a significant difference in infant mortality when comparing Iraq (mean = 27.37) with Iran (mean = 15.57) with P = 0.000. Projections for 2025–2032 also indicate a difference between the two nations, as a country average IMR in Iraq will be 18.32, and, it accounts for 8.41 for Iran, with statistical significance (P = 0.000). It also forecasts falls in the number of births, with Iraq’s dropping from 20.13 in 2025 to 16.61 in 2032, and Iran’s from 9.63 to 7.28. These results validate that the exponential grey mod model offers a superior forecasting model that has great stability and performance for these two countries (Iraq and Iran) to supply decision makers with high-quality forecasts