Volume 13 | Issue 5 |

 Abstract

Heart disease is a leading cause of death globally, underscoring the critical importance of early diagnosis and timely intervention. This project presents a Machine Learning-Based Heart Disease Prediction System aimed at identifying individuals at risk by analyzing various medical parameters. The system utilizes supervised learning algorithms, including Logistic Regression, Support Vector Machine (SVM), Random Forest, and K-Nearest Neighbors (KNN), to classify and predict the likelihood of heart disease in patients. Key attributes used for prediction include age, blood pressure, cholesterol level, resting heart rate, fasting blood sugar, and other clinically relevant features. The model is trained and tested on a publicly available heart disease dataset to ensure its generalizability and accuracy. Comparative analysis of the algorithms is conducted to evaluate performance in terms of accuracy, precision, recall, and F1-score. Among the models, Random Forest demonstrated the highest prediction accuracy, followed closely by SVM, highlighting their robustness in handling complex, non-linear relationships in medical data. This system serves as a decision support tool, providing healthcare professionals with a reliable, fast, and accessible method for preliminary screening and risk assessment. By identifying high-risk individuals at an early stage, the model enables proactive healthcare interventions and potentially reduces the risk of severe cardiovascular complications. Furthermore, the system can be integrated into digital health platforms or hospital information systems to enhance clinical workflow and ensure better patient outcomes. Overall, this project contributes to the growing field of AI in healthcare by offering an efficient and scalable solution for heart disease prediction.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Heart Disease Prediction, Machine Learning, Classification Algorithms, Logistic Regression, Decision Tree, Random Forest, Support Vector Machine, K-Nearest Neighbors, Data Mining, Healthcare Analytics, Predictive Modeling, Clinical Decision Support.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Abstract The entrepreneurial engagement of rural women in India has experienced substantial growth, primarily driven by financial inclusion initiatives, economic necessity, and the digital transformation. Women-led businesses across sectors such as agriculture, textiles, handicrafts, food processing, and services have become instrumental in fostering rural economic development, opportunities, creating employment and empowering women. This paper explores the emerging trends in rural women's entrepreneurship, the key factors influencing their entrepreneurial choices, and the challenges they encounter, societal constraints including financial limitations, and restricted market access. Government programs like Stand-Up India, MUDRA Yojana, and NRLM have been pivotal in providing the financial and infrastructural support necessary for their ventures, while Self-Help Groups (SHGs) and NGOs contribute significantly to business networking and skill development. Despite these advancements, rural women continue to face barriers such as limited access to credit, entrenched gender norms, and digital illiteracy that hinder their entrepreneurial growth. This study underscores the potential of the digital economy, green businesses, and sustainable enterprises offering expanded opportunities for women entrepreneurs. Based on these findings, the paper proposes policy recommendations aimed at improving financial access programs, strengthening market linkages and enhancing skill-building. Future research should focus on, exploring technology-driven entrepreneurship, evaluating the impact of government schemes and examining the socio-cultural factors that influence the entrepreneurial decisions of rural women. A multi-stakeholder approach community-based support systems, and the private sector involving collaboration among government, is essential for creating a sustainable entrepreneurial ecosystem for rural women.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Keywords: Rural Women, Digital Economy, Entrepreneurship, Financial Inclusion, Government Policies, Self-Employment.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Dandruff is a prevalent scalp disorder characterized by excessive flaking, itching, and inflammation, often caused by the overgrowth of Malassezia fungi. Conventional anti-dandruff treatments, though effective, can lead to side effects such as dryness, irritation, and microbial resistance with prolonged use. This study focuses on developing a natural, herbal alternative using garlic (Allium sativum) extract, renowned for its potent antifungal, antimicrobial, and anti-inflammatory properties. The objective was to formulate and evaluate an anti-dandruff gel containing garlic extract, aloe vera, and other excipients to enhance efficacy, stability, and cosmetic acceptability. Three gel formulations (F1, F2, and F3) were prepared with varying concentrations of garlic extract and evaluated for physicochemical properties such as pH, spreadability, texture, washability, and stability. Antifungal efficacy was assessed through microbial inhibition studies. The optimized formulation (F3) exhibited the best performance with a pH of 5.5, excellent spreadability, smooth consistency, and the highest zone of inhibition (21 mm) against Malassezia furfur. It was also non-irritant and easy to wash off, enhancing user compliance. The results demonstrate that garlic extract, when incorporated into a topical gel, offers an effective and safe herbal remedy for dandruff. This formulation serves as a promising alternative to chemical-based treatments, providing both therapeutic and cosmetic benefits. Further clinical evaluation is recommended to support large-scale commercialization.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Garlic extract, Anti-dandruff gel, Malassezia furfur, Herbal formulation, Allicin, Antifungal activity, Natural remedy, Scalp health, Carbopol 934, Aloe vera.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

The integration of Doubly Fed Induction Generator (DFIG)-based wind turbines in hybrid power networks has gained significant attention due to the increasing penetration of renewable energy sources. However, the intermittent nature of wind energy poses challenges in maintaining system frequency stability. This review examines the role of DFIG wind turbines in frequency control within hybrid power networks, particularly in coordination with conventional generation and other renewable sources. Various frequency regulation strategies, including inertial response emulation, droop control, and advanced control techniques such as fuzzy logic and artificial intelligence-based controllers, are discussed. The impact of energy storage systems, demand-side management, and optimized control algorithms in enhancing frequency stability is also analyzed. Furthermore, the review highlights recent advancements, challenges, and future prospects in integrating DFIG-based wind turbines for effective frequency control in hybrid grids. The findings suggest that adaptive control strategies, optimization-based techniques, and hybrid energy storage integration can significantly improve frequency regulation performance.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Doubly fed induction generators (DFIGs), frequency regulation, inertia control and maximum power point tracking.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

professional nurse is no more only in the role of carrying out doctor's order. Today's nurse is expected to make independent decisions in the day-to-day health care activities. This decision-making ability comes from having relevant knowledge, appropriate attitude and expert skills about health care measures, which together may be referred to as health care competency. Also, precision in decision making about a health-related activity depends on elaborate health assessment, analysis of the health parameters and identifying specific health problem related activity depends on elaborate health assessment, analysis of the health parameters and identifying specific health problem and needs.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

EFFECTIVENESS OF VIDEO ASSISTED TEACHING VERSUS DEMONSTRATION ON KNOWLEDGE AND SKILLS REGARDING ELECTROCARDIOGRAM AMONG STUDENTS STUDENTS OF SELECTED GOVERNMENT NURSING COLLEGE OF NURSING, HYDERABAD, TELANGANA STATE.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Spirits are human attributes. When people are born, he is raised with him with just one weapon. Given the current scenario and the severity of Covid 19, people are ready to challenge themselves in this critical situation. This paper presents suggestions for performing an analysis of patients affected by Covid. Machine learning models can help you identify severity and decision-making. Understanding the pandemic will help you implement the right measures at the right time. Implementing these measures before the outbr eak will help maintain the country's health and e conomy. Here we observe and analyze the behavior of the data. This contributes to achievingbett er results for decision-making. The model proposed in this paper is extremely important in interactive applications that include pandemic updates. It displays various lo cal areas as defined by the government and also provides a platform for the poor.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

COVID 19, Machine learning, decision making

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Abstract The accurate segmentation of brain tumors from magnetic resonance imaging (MRI) remains a critical task in neuro-oncology, directly impacting diagnosis, treatment planning, and patient monitoring. Traditional manual delineation is often time-consuming, subjective, and prone to variability among radiologists. While conventional convolutional neural networks (CNNs) have improved segmentation automation, their limitations in capturing long-range dependencies compromise their effectiveness in complex cases. In this paper, we present a Swin UNet-based architecture that integrates the attention mechanisms of Swin Transformers with the localization strengths of U-Net to achieve high-fidelity segmentation across diverse tumor types and MRI modalities. The Swin UNet model introduces a hybrid learning framework capable of encoding both local and global features using hierarchical shifted windows and skip connections. This dual-path design enables precise reconstruction of tumor boundaries even when they exhibit irregular shapes, heterogeneous intensities, or overlapping structures. The model was trained and validated on the BraTS2024 dataset, demonstrating robust performance with a Dice Similarity Coefficient of 89.5% and an IoU of 83.2%. These results outperform many conventional deep learning methods and confirm the model's effectiveness in practical clinical scenarios. Our work emphasizes the real-world utility of transformer-based segmentation by focusing on performance, generalizability, and deployment potential. Beyond algorithmic accuracy, this study explores implementation strategies for clinical integration, including user interface development and platform optimization for inference speed. The results indicate that Swin UNet can serve as a vital decision-support tool in radiology, helping physicians make faster, more consistent, and accurate decisions in diagnosing brain tumors.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Brain Tumor Segmentation, Swin UNet, Swin Transformer, U-Net, MRI, Deep Learning, Medical Image Analysis, Attention Mechanism, Dice Similarity Coefficient, Intersection over Union (IoU), BraTS2024, Clinical Decision Support, Neuro-oncology, Image Segmentation, Transformer-based Models.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

The present investigation was conducted with an aim to study the effect of Postpartum depression on general health of women. The sample for the present study was selected by random sampling method. A total of 80 postpartum mothers out of which 40 were from a government hospital and 40 were from a private hospital. The 40 subjects from government hospital were equally divided according to their type of delivery - into 20 subjects who had a normal delivery and 20 subjects who had a caesarean delivery. The same was repeated with the other group also. The tools used to measure the postpartum depression and general health among women were Edinburgh Postpartum Depression Scale (EPDS) questionnaire, developed by Cox J, Holden J and Sagovsky R (1987 and updated in 2013) and General Health Questionnaire - 28(GHQ-28) developed by Annabel McDermott, OT, Annie Rochette, PhD OT and Gabriel Plumier (2015). The collected data obtained was subjected to statistical analysis using Mean, Standard deviation, 't'-test and Karl Pearson's coefficient of correlation. Postpartum depression was found to be similar among women who had Normal and Caesarean delivery. But there was found to be a significant difference in General health between women who had normal and caesarean delivery in private hospital. It was also found that women from private hospital who had normal delivery had better General health than women who had caesarean delivery. The present investigation also revealed that Postpartum depression was found to be similar among women who had delivery in Private and Government hospital. There was also found to be a significant difference in General health between women who had caesarean delivery in private and government hospitals. It was also found that women who delivered in government hospital had better general health than the women who delivered in private hospital. There was a significant relationship between postpartum depression and general health among women who had normal delivery in private hospital.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Keywords: postpartum, postpartum depression, general health, Government Hospital, Private Hospital, Normal delivery, caesarean delivery

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Ekaksarisanjnakaranam Mugdhabodhakarasya Camatkaritvam

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Ekaksarisanjnakaranam Mugdhabodhakarasya Camatkaritvam

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Ensuring secure and scalable access control has become a crucial challenge in the age of distributed computing architectures. In order to overcome these issues, this paper offers a thorough analysis and implementation of an authorisation framework based on OAuth 2.0 that permits token-based access without requiring the exchange of user credentials. Modern web and mobile applications benefit greatly from OAuth 2.0, an industry-standard protocol that enables delegated access, granular permission control, and seamless cross-platform authentication. Through a review of recent protocols, such as identity-based, SMS-based, and federated authentication models, we examine the core ideas of OAuth 2.0 and contrast its security and performance characteristics with those of conventional authentication methods. Additionally, we present a real-world implementation with Spring Security that highlights the entire authorisation flow, system architecture, and response behaviours. Our results demonstrate that OAuth 2.0 is a strong option for safe API interactions in multi-domain systems because it effectively enhances security, usability, and scalability for resource access in distributed environments.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

OAuth 2.0, Access Control, Token-Based Authentication, Authorization Framework, Spring Security, Secure API Access, Identity and Access Management (IAM)

  License

Creative Commons Attribution 4.0 and The Open Definition