Browse Items (7684 total)
Sort by:
-
Whale Optimization and AutoML for Precise Phishing Detection
Online fraud and social engineering tactics frequently use phishing websites as platforms. Phishers often modify the source code of the web pages they exploit in their attacks to create the illusion that alterations were made to authentic websites. A solitary response is insufficient to mitigate phishing due to the many methods employed in its execution. This study examines machine learning algorithms and evaluates their efficacy when trained on datasets including attributes that differentiate secure websites from phishing sites. Automated algorithms facilitate real-time fraud protection by swiftly detecting suspicious URLs, domain names, and website content. This study aims to identify the optimal method for detecting a prevalent category of cyberattacks. This would enhance the security and privacy of all internet users by facilitating the identification and blocking of malicious websites. Nonetheless, there is an urgent desire for automated models that provide rapid and precise detection. This research introduces a regression-based assessment method for phishing detection to address this demand. Our approach employs a whale optimization algorithm for feature selection. An AutoML framework subsequently utilizes the selected feature subsets as input. The model showed good accuracy in its predictions with very small errors on the test data, shown by an RMSE of 0.1079, an MSE of 0.0116, and an R2 value of 0.9534. These results demonstrate the reliability of our feature selection and modeling methods. 2025 River Publishers -
Decentralized Data Integrity: Integrating MySQL with Blockchain for Resilient Healthcare Systems
A transformational solution to the problems created by healthcare data management is presented by the integration of MySQL and blockchain technology, centered around security, scalability, and efficiency. This paper presents MBHA MySQL-Blockchain Healthcare Architecture combining thestructured data storage, querying capabilities of MySQL with the decentralized, tamper-proof framework of blockchain. The system shows impressive performance metrics with an average API response time of 1.54 seconds for user registration and 841 milliseconds for login. The database queries and data retrieval or insertion took less than 1 millisecond, and JWT tokens were generated for authentication in less than 50 milliseconds. Conclusion Results indicate an efficient real-time system to accomplish tasks with integrity in terms of data but also with safety in operations. This architectural model, discussed above, is issues regarding data security and access with a need to provide care-collaboration needs. Scalability would then be optimized while keeping down computational overhead; in fact, work toward readiness for adoption is mainly towards being more regulatory compliant. 2025 River Publishers -
Emotion Recognition Through Facial Expressions: A Machine Learning Perspective in Mobile Multimedia
Facial expression-based emotion detection is very attractive because of the possibilities in security systems, mental health monitoring, and human-computer interaction. Even with the progress in accuracy in real-world settings, issues such as the lack of balanced datasets and the inability to differentiate between faint or superimposed emotions continue to plague it. This study aims to bridge these constraints by developing a CNN-based model that would be able to recognize face emotions reliably and be utilized in real-time situations, such as webcam integration. The Affect Net dataset, which is a comprehensive collection of over a million facial photos labeled with the seven major emotions of anger, disgust, fear, happiness, neutrality, sadness, and surprise, was used to train the proposed model. Other pre-processing data techniques used include grayscale conversion, normalization, scaling, and data supplementation to increase the robustness of the model. Using metrics like accuracy and loss trends for evaluation, the model demonstrated efficiency stability at around the 30th training phase. When the model is compared to existing models, this proposed model can attain the competitive level of accuracy up to approximately 60%. It also has the potential to run in real applications through its webcam integration. While the model can differentiate between various clear-cut emotions, it becomes ineffective at identifying subtle emotions, which include Fear and Neutral majorly because of unbalanced data and the subtleness of these expressions. 2025 River Publishers. -
An Efficient Detection of Suspicious Objects from Dynamic Video Surveillance by Fusion-based Multiview Deep Learning Techniques
Real-time detections of suspicious objects are needed to identify for finding criminal activities and are used in immediate alert systems for public safety applications. Video surveillance systems use live, closed-circuit televisions (live CCTVs) for dynamic video capturing of objects. Finding criminal activities over the dynamic video data is an emerging surveillance problem. The deep learning techniques are tedious for detecting suspicious movable objects and criminal activities. YOLO (You Only Look Once) gives more prominent movable video object detection accuracy than conventional deep models, like Convolutional Neural Network (CNN), 3D CNN, and Convolutional LSTM. State-of-the-art YOLO models, YOLOv8n, YOLOv8s, and YOLOv8l, are emphasized for extracting and detecting object motion detection from the dynamic video. YOLO models use single-view deep learning to classify or detect objects. These models limit the accuracy of the detection of complex and dynamic objects of dynamic video data. This paper presents the Fusion-based Multiview deep learning techniques to overcome this issue. The experimental study demonstrates that the proposed methodology efficiently detects suspicious data objects more than the single-view deep models. 2025 River Publishers. -
The Impact of Helicobacter Pylori Infection on Renal and Hepatic Function Parameters in Saudi Arabia, A Case-Control Study
Helicobacter pylori (H. pylori) is a common gastric pathogen that is linked to peptic ulcers, gastric cancer and systemic disorders. There is emerging evidence of an association between infection with H. pylori and chronic kidney disease and non-alcoholic hepatic steatosis, and possible renal and hepatic involvement. This study was conducted to assess the relationship between H. pylori and kidney and liver function changes in Saudi Arabian people. Blood samples were collected from 82 participants divided into two groups, namely H. pylori-infected and non-infected. Biochemical analyses were done to determine kidney (creatinine, urea, sodium and potassium) and liver function (ALT, AST, ALP, total protein and albumin). A total of 82 participants were included in the study, of whom 42 (51.2%) tested positive for Helicobacter pylori infection, while 40 (48.8%) were non-infected and served as the control group. Liver enzyme levels (ALP (64.00), AST (21.40), ALT (21.26) and GGT (20.78)) were normal and did not differ significantly between groups (p > 0.05). Regression analysis showed a significant relationship between H. pylori infection and high creatinine (OR = 6.38, p = 0.018). Borderline correlations were found for GGT (OR = 1.179, p = 0.092), uric acid (OR = 2.661, p = 0.061), and the electrolytes and lipid profiles showed no significant variation. H. pylori infection was significantly related to elevated creatinine levels, and may be affecting renal function. Most liver and electrolyte parameters were not affected. Further studies with larger cohorts are required in order to confirm these findings. Oriental Scientific Publishing Company 2026. -
Gene Expression Data-Based Interpretable Machine Learning Framework for Classifying Brain Cancer Subtypes
Early detection, therapeutic stratification, and precision medicine all rely on the precise classification of brain cancer subtypes. To categorize brain tumor subtypes, we examine the application of ensemble machine learning modelsRandom Forest, XGBoost, and LightGBMusing high-dimensional gene expression data from the GSE50161 dataset (CuMiDa). The top 1000 genes were selected using variance thresholding, and models were then trained and evaluated on a stratified split of the dataset. Despite the availability of models achieving similar accuracies (~9596%) in existing works, our framework integrates SHAP-based interpretability to identify biologically significant genes, such as CDK4, EGFR, and TP53, offering dual benefits of high predictive power and explainability. The use of SHAP (SHapley Additive exPlanations) values to assess model predictions and identify physiologically important gene features revealed that key gene probes, including as CDK4, EGFR, and TP53, were significant across different tumor subtypes. This study demonstrates how SHAP and interpretable ensemble learning may be used to diagnose brain tumors with excellent classification accuracy and physiologically meaningful gene identification. Published by Oriental Scientific Publishing Company 2025. -
Optimized Hybrid Prognostics Using Hynetreg Model for Infertility Prediction
This paper develops an optimized hybrid approach to predict infertility with the HyNetReg Model. The HyNetReg Model combines deep feature extraction by using neural networks with logistic regression with regularization. It uses both hormonal and demographic information of 100 participants to clarify intricate interlinkages between demographic factors and salient hormonal levels, such as Luteinizing Hormone, Follicle Stimulating Hormone, Anti-Mlerian Hormone, and Prolactin, and the ability of these same factors to affect fertility outcomes. It applies heavy data pre-processing including normalization, missing values imputation, and class imbalance handling through oversampling techniques. A multi-layer neural network is utilized to extract features for the reduction of complex, non-linear interaction among the input variables. Then, regularized logistic regression is applied for classification on the same features. Performance evaluation metrics, including accuracy, precision, recall, F1-score, and ROC curve analysis, demonstrate the superiority of the HyNetReg Model over traditional logistic regression. The ROC curve was specifically utilized to assess the models discrimination ability between infertile and fertile cases by plotting the true positive rate (sensitivity) against the false positive rate (1-specificity). A higher Area Under the Curve indicated that the model effectively distinguished infertility risks based on hormonal and demographic features. The results indicate that the model can recover very slight interdependencies of hormones and influences of demographics, making it suitable for modeling multi-factorial determinants of infertility and holding significant implications for clinical decision-making. 2025 Oriental Scientific Publishing Company. All rights reserved. -
Automated Brain Tumor Segmentation in MRI Using AI for Improved Neurodiagnostics
Early and accurate classification of brain tumors plays a pivotal role in clinical decision-making and treatment planning. Manual methods are time-intensive and prone to variability, creating a need for robust automated solutions. This study aims to classify brain tumors from MRI scans using artificial intelligence techniques, specifically Logistic Regression (LR) and Support Vector Machines (SVM) with Radial Basis Function (RBF) kernels. The dataset, sourced from The Cancer Imaging Archive (TCIA), includes four classes: Meningioma, Glioma, Hypothalamic tumor, and No tumor. Preprocessing involved dimensionality reduction using Principal Component Analysis (PCA) to retain dominant features. Models were trained on an 80:20 train-test split, with LR achieving 99.83% training and 78.91% testing accuracy, while SVM performed better with 93.85% training and 81.88% testing accuracy. Error analysis revealed 104 misclassified samples, primarily due to structural similarity among tumor types. The findings suggest that SVM offers superior classification performance, and the study recommends further enhancement through deep learning models like Convolutional Neural Networks (CNNs) for improved diagnostic accuracy. 2025 Oriental Scientific Publishing Company. All rights reserved. -
Polycystic Ovary Syndrome Diagnosis: The Promise of Artificial Intelligence for Improved Clinical Accuracy
PCOS is an endocrine illness that affects 610% of women worldwide. It can cause a variety of symptoms, including irregular menstruation periods, ovarian cysts, and hyperandrogenism. Its lack of defined biomarkers, overlapping symptoms, and heterogeneity make diagnosis difficult. By studying hormone profiles, identifying patterns difficult to see with conventional approaches, and offering great precision and accuracy, AI and ML techniques are transforming diagnostic difficulties. Hybrid models in the list include SWISS-AdaBoost and ensemble learning techniques that have accuracies up to 98% enabling early diagnosis along with appropriate treatment strategies. Early detection by technologies such as AI will prevent significant health complications that are PCOS-related, such as infertility, type II diabetes, or cardiovascular diseases. This study depicts the transformative role of the application of AI in diagnosing cases of PCOS and highlights the possibility of facilitating clinical decision-making, reducing potential diagnostic delays, and enhancing improvements in patient outcomes. Future research should hence be directed towards the establishment of AI within healthcare with consideration of validation, reliability, and ethical considerations to maximize its use in clinical practice. 2025 Oriental Scientific Publishing Company. All rights reserved. -
Novel Approach for Osteoporosis Classification Using X-ray Images
This research delves into the technical advancements of image segmentation and classification models, specifically the refined Pix2Pix and Vision Transformer (ViT) architectures, for the crucial task of osteoporosis detection using X-ray images. The improved Pix2Pix model demonstrates noteworthy strides in image segmentation, achieving a specificity of 97.24% and excelling in the reduction of false positives. Simultaneously, the modified ViT models, especially the MViT-B/16 variant, exhibit superior accuracy at 96.01% in classifying osteoporosis cases, showcasing their proficiency in identifying critical medical conditions. These models are poised to revolutionize osteoporosis diagnosis, providing clinicians with accurate tools for early detection and intervention. The synergies between the Pix2Pix and ViT models open avenues for nuanced approaches in automated diagnostic systems, with the potential to significantly improve clinical results and contribute to the broader landscape of medical image analysis. As osteoporosis remains a prevalent and often undiagnosed condition, the technical insights from this study hold substantial importance in advancing the field, emphasizing the critical role of accurate diagnostic tools in improving patient care and health outcomes. 2025 Oriental Scientific Publishing Company. All rights reserved. -
Strain energy based frequency independent impedances of soil for interaction effect on structure
The present study proposes a strain energybased method for evaluating soilstructure interaction (SSI) effects for ground-mounted parabolic antenna systems founded on layered soils. Conventional frequency-independent impedance formulations, such as those recommended in ASCE 4-16, are primarily based on homogeneous soil assumptions and may not adequately capture the dynamic behavior of layered soil profiles. In this work, a strain energy equivalence approach is developed to estimate translational and rotational soil impedances by accounting for depth-wise variations in soil stiffness. The proposed method is validated using three-dimensional finite element modeling and in-situ microtremor measurements. The results demonstrate improved prediction of natural frequencies and modal mass participation factors compared to standard impedance-based approaches, indicating that the proposed method provides a more realistic representation of SSI effects for precision-sensitive antenna structures. 2026 Techno-Press, Ltd. -
A data-driven approach to predicting breast cancer recurrence with hybrid machine learning models
Breast cancer recurrence is one of the most significant medical concern, and accurate recurrence models can assist in early intervention and treatment planning. Breast cancer recurrent remains as one of the most critical concern for patients prognosis and treatment planning. Accuracy Predicting individual recurrence risk is crucial for the development of precise therapy, specialy for those patients with high-risk profiles. In the study proposes a hybrid machine learning approach that uses the computational modeling and the medical information to predict the recurrence of breast cancer in a patient. The dataset contains the medical and patient information like the age, tumor size, lymph node involvement, malignancy degree, location, irradiation status and recurrence class. This proposed approach begins with the process of data processing, handling the missing data values, features normalization and encoding of categorical variable into numerical format. The dataset is divided into two parts the training set and the testing set and the two selected models random forest and logistic regression models are trained independently. The predictions form both the model is stacked and a logistic regression meta-model is trained on these combined predictions. The evaluation of the model was conducted using the metrics such as accuracy, precision, recall, and F1 score. The designed hybrid model was able to achieve the accuracy of 97.66% with the precision, recall and F1 score all reaching around 98.15%. This study highlights the potential of hybrid machine learning techniques, improving the accuracy and reliability of machine learning models for breast cancer recurrence prediction. This development model can serve as a valuable tool for the medical industry to support decision making and assist in personalized treatment decisions, offering early detection of recurrence. This can enhance the treatment of a patient by supporting early detection and patients outcomes through targeted therapy. Copyright 2026 Techno-Press -
Balancing patient privacy and predictive accuracy through data anonymization in healthcare
Data anonymization in healthcare is essential for protecting sensitive patient information while enabling secure usage for research, analytics, and AI-driven clinical decision-making. In this study, the MIMIC-III - Deep Reinforcement Learning dataset was used, which contains comprehensive electronic health records (EHRs) of ICU patients. Data preprocessing was performed using Min-Max Normalization to scale numerical features and ensure consistency. Anonymization techniques such as pseudonymization, generalization, suppression, data masking, and statistical methods like k-anonymity, l-diversity, and t-closeness were applied to safeguard patient privacy. The anonymized dataset was then utilized for predictive modelling using AI techniques including Random Forest and LSTM. Results demonstrated that privacy was maintained with 0% PII leakage, while predictive accuracy remained high, achieving accuracy of 94.6%, precision of 93.8%, recall of 92.5%, and F1-score of 93.1%. This study highlights that effective data anonymization ensures compliance with HIPAA and GDPR while retaining the utility of healthcare data for advanced analytics and AI applications. 2026 Techno-Press -
Stress-Driven Changes in Ascorbic Acid Levels in Raphanus Sativus: A Comparative Study
Abiotic stresses such as extreme temperatures and salinity are known to significantly influence the nutritional quality of vegetables during cultivation and postharvest handling. However comparative study on how different abiotic stresses alter ascorbic acid stability in root vegetables like red radish is understudied. Thus, the present study was conducted to evaluate the effect of various abiotic stresses (heat, cold and salinity) on ascorbic acid (AA) levels and antioxidant activity in red radish (Raphanus sativus L.). DCPIP titration and DNPH UV-Vis spectrophotometric techniques were used to analyse the ascorbic acid content, and the DPPH radical scavenging assay was used to measure antioxidant capacity. The findings showed that as stress duration and intensity increased, the total AA content decreased significantly (p < 0.05). At high temperature (90 C), heat treatment resulted in a progressive decrease from 27.7 mg/100g to 20.8 mg/100g. Under cold stress, AA content increased slightly initially and then dropped by 22% on day 8. A two-phase response to salt stress was seen mild salt concentration leading to a moderately increased AA content, while severe salt concentration caused a 55% reduction after 72 hours. With an IC50 value of 8.27mg/mL, the antioxidant activity increased as extract concentration increased from 3.8% to 62.1% inhibition. According to these findings, red radish exhibits a short-term adaptive defence in mild stress situations but a significant decrease in AA in severe stress situations. These findings are consistent with previous reports in other related vegetables such as tomato, broccoli and spinach, where moderate abiotic stress increases antioxidant defences before degradation occurs. These results suggest the need for efficient postharvest management and stress-aware storage techniques to preserve the functional and health-promoting qualities of red radish. 2026 The Author(s). -
Feature Engineering for Epileptic Seizure Classification Using SeqBoostNet
Epileptic seizure, a severe neurological condition, profoundly impacts patients social lives, necessitating precise diagnosis for classification and prediction. This study addresses the need for reliable automated seizure detection in epilepsy by employing Artificial Intelligence (AI) driven analysis of Electroencephalography (EEG) signals. Key innovations include combining spectral and temporal features using Uniform Manifold Approximation and Projection (UMAP) with Fast Fourier Transformation (FFT), and the introduction of the Sequential Boosting Network (SeqBoostNet), a robust stacking model integrating machine learning and deep learning for effective seizure classification. Validated on benchmark datasets such as the BONN dataset from the UCI repository and the BEED from the Bangalore EEG Epilepsy Dataset, this approach achieved high accuracy, distinguishing Focal and Generalized seizure onsets with 95.91% accuracy and overall average accuracies of 96.71% on BEED and 97.11% on BONN. Existing models frequently struggle with the variability of seizure events. However, these findings underscore the models strength in distinguishing between seizure onset types, even with the inherent fluctuations in seizure patterns. This research not only advances automated seizure detection but also underscores the value of integrating AI with EEG analysis to improve neurological diagnostics, offering the potential for significant enhancements in diagnostic accuracy and patient outcomes. 2025 University of Bahrain. All rights reserved. -
ODD SUN-FREE TRIANGULATED GRAPHS ARE S-PERFECT
For a graph G with the vertex set V (G) and the edge set E(G) and a star subgraph S of G, let ?S(G) be the maximum number of vertices in G such that no two of them are in the same star subgraph S and ?S(G) be the minimum number of star sub-graph S that cover the vertices of G. A graph G is called S-perfect if for every induced subgraph H of G, ?S(H) = ?S(H). Motivated by perfect graphs discovered by Berge, Ravindra in-troduced S-perfect graphs. In this paper we prove that a trian-gulated graph is S-perfect if and only if G is odd sun-free. This result leads to a conjecture which if proved is a structural char-acterization of S-perfect graphs in terms of forbidden subgraphs. 2025, Diogenes Co. Ltd.. All rights reserved. -
VERTEX COLOURING OF FINITE NETWORKS WITH RESPECT TO AVERAGE DISTANCE
For a finite network, represented as a graph G = (V, E) with average distance (G), the average distance colouring of G is a function c from V to the set of non-negative integers, such that for any v ? V, |c(v) ? c(u)| ? 1 for all u ? V such that d(u, v) ? ??. In this paper, we find the average distance colouring number of some special types of networks and present a greedy algorithm to colour any graph with average distance colouring constraint. 2025, Diogenes Co. Ltd.. All rights reserved. -
Loving lifes impermanence: How existential gratitude sparks transformation in cancer survivors; [????????? ??? ???????????? ??? ????: ??? ? ????????? ??????????? ???? ?? ?????????????? ???????? ?? ??????????? ????????]
Cancer survivorship is often accompanied by existential distress as individuals confront mortality and search for meaning in their experiences. This study examines existential gratitude, which is a heightened appreciation of life shaped by suffering and impermanence, as a mediator between spirituality and post-traumatic growth (PTG) among Indian cancer survivors. Grounded in Terror Management Theory (TMT), this research explores how spirituality, rather than directly fostering PTG, requires existential gratitude as a transformative mechanism. A sample of 118 Indian cancer survivors, at least six months post-active treatment, participated in the study. Spearmans rho correlations revealed significant positive associations between existential gratitude, spirituality, and PTG. Mediation analysis demonstrated that existential gratitude fully mediated the relationship between spirituality and PTG (? = .16, p = .003), with spirituality showing no direct effect on PTG (? = .08, p = .414) when existential gratitude was introduced. These findings challenge traditional views of spirituality as an inherent driver of growth, highlighting instead that PTG arises when existential gratitude transforms mortality awareness into an appreciation of lifes fragility. 2025, Layah Liz Jacob, Anuradha Sathiyaseela. -
Trauma, Ontological Exile, and the Trans Self: Reading Transgender Autobiographical Narratives from the Global South
Scholarly understanding of exile usually foregrounds the forced displacement of human beings from one geographical location to another due to war, violence, or fear of persecution. However, exile is also a psychological state of being caused by external factors that need not necessarily be limited to the physicality of dislodgement from a sense of home. This paper explores exile as an ontological condition informed by experiences of trauma, selfhood, and marginalisation from the vantage point of transgender lived experiences from India. The philosophical engagement of these ideas is exemplified by the autobiographical work of a transgender woman, A. Revathi, titled The Truth About Me: A Hijra Life Story. The paper facilitates dialogues between narrativising trauma, psychological exile, and the trans self-using interdisciplinary frameworks of Paul Ilie, Maurice Merleau-Ponty, Edward W. Said, Judith Butler, Cathy Caruth, Sara Ahmed, and Shoshana Felman to examine the interconnection between thoughts on trauma, testimony, inner exile, lived experiences, queer phenomenology, and gender performativity. The study observes that the reclamation of transgender selfhood emerges through the act of self-narration. It also reimagines exile and trauma as philosophical processes of self-awareness and becoming. 2025, University of Western Macedonia. All rights reserved. -
Development of carbonaceous anode battery materials from cornstalk and their electrochemical characterization using cyclic voltammetry
This paper presents a study on the development of carbonaceous battery anode material derived from biomass sources, particularly cornstalk for energy storage applications. The carbonization process was optimized, followed by activation and doping with transition metal oxides like nickel and cobalt to enhance the electrochemical performance of the anode material. Cyclic voltammetry and chronopotentiometry studies were employed to characterize the electrochemical properties, specifically the charge storage behavior of the synthesized materials. Fourier transform infrared spectroscopy spectrum, BrunauerEmmettTeller analysis, and scanning electron microscopy were employed to study the impact of doping, surface area, pore size distribution, and surface morphology. The results indicate that doping with metal oxides significantly improves the conductivity and charge storage capacity of the carbon-based materials, making them promising candidates for sustainable battery applications. The Author(s) 2025.