Volume 14 | Issue 5 |

 Abstract

Organ transplantation remains one of the most significant medical procedures for restoring the quality of life of patients suffering from organ failure and severe vision impairment. Despite advancements in transplantation medicine, the success of organ transplantation is often limited by the availability of compatible donors and the complexity of donor-recipient matching. Traditional methods primarily rely on manual assessment and basic compatibility analysis, which may not always provide optimal transplantation outcomes. This research proposes a data-driven prediction system for organ transplant viability and recovery using Machine Learning techniques. The proposed system utilizes donor and recipient medical information, including demographic details, physiological characteristics, medical history, and transplantation parameters, to predict compatibility and estimate transplantation success. Advanced predictive analytics techniques are employed to identify suitable donor-recipient pairs and reduce the likelihood of transplant rejection. The system integrates machine learning algorithms capable of analyzing large volumes of healthcare data to generate accurate predictions regarding transplant viability. The developed framework assists healthcare professionals in making informed decisions while improving efficiency and reducing manual effort. Experimental analysis demonstrates that predictive modeling can significantly improve donor matching accuracy and contribute to enhanced patient recovery outcomes. The proposed approach represents an important step toward intelligent healthcare systems by combining artificial intelligence with transplantation medicine. The results indicate that machine learning-based prediction systems can play a critical role in improving transplantation success rates, minimizing complications, and supporting evidence-based medical decision-making.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Machine Learning, Organ Transplantation, Healthcare Analytics, Artificial Intelligence, Predictive Modeling, Donor Matching, Medical Data Analysis, Recovery Prediction.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

: The increasing integration of artificial intelligence (AI) in healthcare has significantly advanced disease prediction, diagnosis, and personalized treatment planning. However, the development of high-performance machine learning models is critically dependent on access to large-scale, high-quality medical datasets, which are often restricted due to stringent privacy regulations such as the Health Insurance Portability and Accountability Act (HIPAA) and the General Data Protection Regulation (GDPR). These constraints lead to fragmented data silos across institutions, limiting the generalization capability of conventional centralized learning approaches. Federated Learning (FL) has emerged as a transformative paradigm that enables collaborative model training across multiple decentralized entities without requiring the exchange of raw data, thereby preserving data privacy and ownership [1]. This paper presents a comprehensive federated learning framework for privacy-preserving medical predictions, designed to address key challenges in secure collaborative healthcare analytics. The proposed system integrates advanced privacy-enhancing technologies, including secure aggregation protocols [2], differential privacy mechanisms [3], and homomorphic encryption techniques [4], to ensure that sensitive patient information remains protected throughout the training process. Additionally, the framework incorporates communication-efficient optimization strategies and adaptive federated averaging algorithms to mitigate issues related to data heterogeneity and network constraints [5]. Extensive experimental evaluations conducted on distributed healthcare datasets demonstrate that federated models achieve comparable predictive performance to traditional centralized approaches, with accuracy levels exceeding 95% in disease classification tasks, while ensuring zero raw data exposure. Furthermore, the framework maintains strict compliance with regulatory standards and significantly reduces the risk of data breaches and re-identification attacks [6]. The results highlight the feasibility, scalability, and robustness of federated learning in real-world healthcare environments, establishing it as a viable solution for next-generation privacy-preserving medical AI systems.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Federated learning, healthcare AI, privacy preservation, secure aggregation, differential privacy, homomorphic encryption, distributed machine learning, medical data security.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

The rapid advancement of Artificial Intelligence (AI) is fundamentally transforming the landscape of Human Resource Management (HRM). This paper explores the multifaceted impact of AI on HR functions, including recruitment, performance management, employee development, and decision-making. Drawing on a wide body of literature, the paper examines how AI-driven tools and techniques are being integrated into HR practices, the opportunities and challenges that arise from this integration, and the implications for the future of work. The study finds that while AI offers significant potential to enhance HR efficiency, objectivity, and strategic value, its adoption also raises critical concerns related to ethics, data privacy, and the irreplaceable value of human judgment. The paper concludes with a forward-looking agenda for HR professionals and organizations navigating this transformative era.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Keywords: Artificial Intelligence, Human Resource Management, Recruitment, Performance Management, Machine Learning, HR Technology, Digital Transformation.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

One of the most common and severe neurological disorders worldwide is epilepsy, affecting nearly 50 million people. Electroencephalogram (EEG) signals remain the primary tool for monitoring abnormal brain activity and detecting seizures. This paper presents a systematic review of machine learning (ML) and deep learning (DL) approaches for EEG-based epileptic seizure detection published between 2022 and 2025. The review covers traditional ML methods such as Support Vector Machines (SVM) and Random Forests, as well as advanced DL architectures including CNN, LSTM, CNN-LSTM, CNN-GRU, Transformers, Attention Mechanisms, and Graph Neural Networks (GNNs). PRISMA-based methodology was used for literature selection and analysis. Comparative evaluations of different approaches, datasets, advantages, limitations, and performance metrics are discussed. The study also identifies major research gaps such as poor cross-patient generalization, interpretability challenges, class imbalance, and lack of real-time deployment validation. Future research directions including federated learning, wearable EEG systems, multimodal fusion, and foundation models are highlighted.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

EEG, Epilepsy, Seizure Detection, Machine Learning, Deep Learning, CNN, LSTM, Transformer, Graph Neural Networks

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Abstract- Self-medication is a common practice in rural areas where access to healthcare is limited. It involves using medicines without consulting a doctor, often based on personal experience or advice. While it may help in treating minor illnesses, improper use can lead to serious health risks. This study assessed self-medication practices among 1,379 participants using a structured questionnaire. The results showed that 65.1% of individuals practiced self-medication. Common conditions included fever, headache, cold, cough, and body pain, and commonly used drugs were analgesics, antipyretics, antibiotics, and cold and cough preparations. The main reasons for self-medication were saving time and money, minor illness, and limited healthcare access. Many participants relied on family, friends, pharmacists, or the internet for information. Unsafe practices were observed, as 32.7% did not complete the full course of medication and many experienced side effects. Overall, awareness about proper drug use was limited. The study concludes that although self-medication is convenient, it can be harmful if not used responsibly, highlighting the need for better awareness and safer use of medicines.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Index Terms: Self-Medication, Rural Population, Antibiotic Misuse, Awareness, Drug safety, Public Health

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

The onion peel hair oil are hair care components implemented to the hair for the treatment of alopecia.The present study is about the formulation and evaluation of hair oil using various plant material. This hair oil was prepared for the hair growth. The formulated oil contains different herbal plant which are traditionally utilized for hair growth plants used are onion peel, coconut oil, curry leaves, neem, hibiscus, amla, fenugreek seed. The prepared onion peel hair oil evaluated different parameters such as pH, density, viscosity, organoleptic properties, acid value, saponification value, phytochemical screening. The primary irritation test is carried out. Henceforth the onion peel hair oil considered to treat alopecia and increasing hair growth, reduce hair loss and reduce the dandruff.The global shift toward natural and sustainable personal care products has increased interest in herbal formulations for hair management. This study aimed to formulate and evaluate a polyherbal hair oil incorporating plant-based ingredients with established pharmacological benefits. Key botanicals, including Emblica officinalis, Eclipta Alba, Azadirachta indica, and Hibiscus rosa-sinensis, were selected due to their reported properties such as hair growth promotion, antimicrobial activity, and scalp nourishment. The formulation was prepared using a suitable oil base, followed by standardized extraction and blending techniques.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Alopecia, onion peel, Hair growth, Dandruff, Herbal plant, Neem, Phytochemical screening, pH, Viscosity.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

The Vaital Deula is one of the most famous Tantric temples in Odisha. It is dedicated to Goddess Chamunda and follows the unique Khakhara order of Kalinga architecture. The temple is known for its semi-cylindrical shape, complex sculptures, and strong connection to Tantric religions. The current study looks into the study of art, architectural parts and sacred landscape setting of the Vaitala temple. To understand the sacred geography of the Vaitala temple the present study use QGIS tools for georeferencing, spatial mapping, GPS-based documentation, buffer analysis, and Digital Elevation Model (DEM) maps are prepared and interpreted to understand the relationship of the temple with the landscape. The study shows the connection of Vaital Deula to the larger sacred urban network of Bhubaneswar, which includes nearby temples and water bodies used for rituals.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Vaital Deula, Bhubaneswar, GIS, Khakhara Architecture, Sacred Geography

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

The rapid growth of online payment systems and digital transactions has increased the risk of cyber fraud and unauthorized financial activities. Traditional fraud detection methods are often unable to identify complex and evolving fraud patterns efficiently. This project, "Fraud Detection in Online Payments Using Artificial Intelligence," aims to develop an intelligent system capable of detecting fraudulent transactions using Artificial Intelligence (AI) and Machine Learning techniques. The proposed system analyzes transaction data such as payment amount, transaction frequency, user behavior, location, and device information to identify suspicious activities in real time. Machine Learning algorithms are trained on historical transaction datasets to recognize patterns associated with genuine and fraudulent transactions. The system can automatically classify transactions and generate alerts whenever unusual behavior is detected. The project focuses on improving transaction security, reducing financial losses, and minimizing false fraud alerts. By using AI-based predictive analysis, the system becomes more adaptive and accurate compared to traditional rule-based methods. The proposed model can be implemented in banking systems, e-commerce platforms, digital wallets, and online payment gateways to enhance cybersecurity and protect users from financial fraud. This project demonstrates how Artificial Intelligence can play an important role in securing digital payment systems and ensuring safer online financial transactions.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

AI, Fraud Detection, Online Payments, Machine Learning, Cyber Security, Digital Transactions

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

YAKRITDALYUDARA , NAFLD , STATUS OF AGNI , AMA , UDARROGA ,

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Polycystic ovary syndrome (PCOS) is a multifactorial endocrine disorder characterized by hormonal imbalance, chronic inflammation, and metabolic irregularities. Conventional treatments often present limitations, including side effects and poor patient compliance. In this study, a novel herbal transdermal patch technology was developed as a non-invasive approach to support hormonal regulation and symptom management in PCOS. The formulations incorporated standardized herbal extracts of Ashwagandha (Withania somnifera), Fenugreek (Trigonella foenum-graecum), Cinnamon (Cinnamomum verum), and Spearmint (Mentha spicata) plants known for their phytochemicals with adaptogenic, insulin-modulating, anti-androgenic, and anti-inflammatory actions. Their chemical constituents, including withanolides, trigonelline, cinnamaldehyde, and rosmarinic acid, play a crucial role in restoring hormonal balance, particularly by regulating cortisol levels, improving insulin sensitivity, and reducing excess androgens associated with PCOS.Two types of transdermal patches were formulated: a pre-period patch, designed to mitigate premenstrual discomfort and early hormonal fluctuations, and a continuous-period patch, intended for sustained support throughout the menstrual cycle. The patches were prepared using suitable polymers and evaluated for drug-polymer compatibility, physicochemical properties, and stability. Compatibility studies confirmed the absence of major interactions between the herbal extracts and excipients, ensuring effective transdermal permeation. Preliminary observations indicated favorable mechanical strength, uniform drug distribution, and potential for controlled release.Overall, the developed herbal transdermal patches demonstrate promise as an innovative and effective delivery system for PCOS management by providing targeted hormone- balancing support through natural phytochemicals. Further in vitro and in vivo studies are recommended to validate therapeutic efficacy and long-term safety.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Polycystic Ovary Syndrome (PCOS), Herbal transdermal patches, Ashwagandha, Fenugreek, Cinnamon, Spearmint, Curcumin, Hormonal balance.

  License

Creative Commons Attribution 4.0 and The Open Definition