Journal of Innovations in Data Science and Big Data Management

Predicting Blood Donations with Regression Algorithms

Thu, 13 Feb 2025 00:00:00 +0000

Blood transfusion is a critical procedure that saves countless lives by replacing lost blood during major surgeries, injuries, and treatments for various illnesses and blood disorders. However, maintaining an adequate blood supply remains a significant challenge for healthcare providers. This study focuses on predicting the likelihood of a donor returning to donate blood in the future, utilizing data collected. Our approach includes rigorous data pre-processing, such as feature engineering, normalization, and stratified data splitting. The study further explores logistic regression resulting in a marginally improved AUC score of 0.7890. The findings demonstrate the potential of machine learning models to predict donor behaviour, offering insights that can enhance blood donation campaigns and resource allocation. The study emphasizes the importance of accurate predictions in blood donation forecasting, particularly during periods of fluctuating demand, such as holiday seasons. Even minor improvements in model accuracy can significantly impact the effectiveness of donor recruitment strategies.

Predicting Pneumonia with Precision: A Deep Learning Approach

M. Nikesh, D. Rohini, M. Bharathi, Syeda Hifsa Naaz — Sat, 08 Mar 2025 00:00:00 +0000

Pneumonia is an infection that affects the lungs, causing inflammation in the air sacs, which then fill with fluid or pus. Common symptoms include coughing, difficulty breathing, fever, and chest pain. The condition can be triggered by bacteria, viruses, or fungi and can vary in severity from mild to life-threatening. Those at higher risk include infants, young children, older adults over 65, and individuals with weakened immune systems. Prompt diagnosis and treatment are crucial to prevent complications. This research explores how Machine Learning (ML) and Deep Learning (DL) can improve pneumonia detection. Using a dataset from Kaggle, we compare different models, including Random Forest and Deep Learning architectures like VGG-16, Inception V3, and various CNN structures. By evaluating models with different configurations, we aim to find the most reliable and accurate approach for detecting pneumonia effectively.

Game Engines and Beyond Tools

Suraj R. Nalawade, Praveen R. Barapatre, Tapase H. O., Bhade Darshan — Thu, 13 Mar 2025 00:00:00 +0000

Game engines have really revolutionized the making of interactive digital content because it offers robust frameworks which transcend traditional gaming applications. Fundamentally, a game engine is an integrated tool suite that provides rendering, physics simulation, scripting, and asset management; all these allow developers to create immersive experiences in a much more efficient way. Yet their reach stretches into simulation, education, architecture, and virtual production. This study shall explore the evolution of game engine technology, highlighting the fact that these are complete ecosystems in which creativity and innovation are happening. Emerging trends of procedural generation, cross-platform compatibility, and metaverseready frameworks are pointed at technological pillars underpinning game engines such as real-time rendering, AI, and physics-based interactions. The use of game engines for applications beyond games further provides possibilities as a transformative tool to solve problems and virtual storytelling. This research is based on technical innovation and interdisciplinary applications that give an overall understanding of how game engines can be maximized to place them at a strategic point for the future of digital media and beyond.

AI-Based Heart Disease Prediction System

Wed, 19 Mar 2025 00:00:00 +0000

Heart disease is a leading cause of death globally, requiring early and accurate detection for effective management. This study proposes an AI-based heart disease prediction system using machine learning algorithms to analyse patient data. Key features influencing heart disease are identified to enhance model accuracy and interpretability. The system, trained on publicly available datasets, achieves high prediction accuracy, demonstrating its potential as a reliable, cost-effective diagnostic tool. Integrating AI into clinical workflows can improve personalized care and patient outcomes. Future work focuses on real-time data integration and advanced AI techniques for further improvement.

Machine Learning Model to Detect Mood Swings in Women during Menstrual Time – Review

A. Avinash, Sayantan Kar, M. Uma Devi, P. Lakshmi Satya, T. N. V. Durga — Mon, 14 Apr 2025 00:00:00 +0000

Machine learning is transforming mood detection by leveraging vast datasets to identify intricate patterns and correlations. One significant application of this technology is predicting mood variations during the menstrual cycle, providing valuable insights into the biological and psychological factors that influence emotional states. By integrating physiological data, behavioural indicators, and self-reported mood assessments, machine learning models can analyse hormonal fluctuations, sleep patterns, physical activity, and stress levels to develop personalized mood predictions. This data-driven approach enhances the understanding of how hormonal changes impact emotional well-being, enabling more precise mental health strategies. Unlike traditional methods, which rely solely on subjective reporting, machine learning offers objective and continuous monitoring, leading to early intervention and personalized recommendations. These insights can be particularly beneficial for individuals experiencing mood disorders such as Premenstrual Dysphoric Disorder (PMDD) or heightened emotional sensitivity during specific menstrual phases. By utilizing predictive analytics, machine learning contributes to adaptive mental health support, improving emotional resilience and well-being. This innovative integration of artificial intelligence in health monitoring fosters the development of personalized therapeutic strategies, helping individuals manage their moods more effectively throughout the menstrual cycle. Ultimately, machine learning-driven mood detection has the potential to revolutionize mental health care by offering proactive, data-driven solutions tailored to individual needs.