IMPACT OF CHANGING DIETARY HABITS ON HUMAN HEALTH: A DEEP LEARNING BASED ANALYSIS

Abstract

In recent decades, rapid cultural and lifestyle changes have significantly transformed human dietary habits. Traditional food practices, once based on natural, fiber rich, and minimally processed foods, are increasingly being replaced by fast foods and highly processed products. This transition has adversely affected human health, leading to metabolic imbalances and dysfunction in vital organs such as the liver, kidneys, and heart. The reduced consumption of traditional fermented foods and nutrient-rich natural products has further contributed to declining nutritional quality and increased health risks. This study explores the impact of changing dietary patterns on human physiological health by emphasizing the importance of traditional food systems, including fermented foods and naturally cultivated agricultural products grown without chemical fertilizers or pesticides. Data were collected through field surveys, laboratory test reports, and manual observations from selected populations. Prior to analysis, the dataset was preprocessed using a median filter to remove noise and improve data quality. Deep learning techniques were employed to analyze and predict health outcomes based on dietary habits. Specifically, Convolutional Neural Networks (CNN) and Artificial Neural Networks (ANN) were implemented and compared to evaluate their predictive performance. The study aims to identify the most effective model while highlighting the health benefits of traditional dietary practices. The findings suggest that reducing processed food consumption and adopting natural, nutrient rich diets can improve organ function, enhance metabolic balance, and support long-term human health.