Developing a Predictive Web Application for HBMI Using Machine Learning Techniques

In worldwide, we are familiar with a common term known as BMI(Body Mass Index) which is used as indicator of our health condition. But, to know the actual health condition of a human, the most common BMI calculator which only measures the height and weight of a person is not sufficient enough. Considering this type of problem we developed a system which can suggest a person’s actual health condition measuring different body parts considering height, weight, gender, waist circumference, neck circumference, hip circumference, wrist circumference. In this system, We used a flexible machine-learning method for predicting numerical values known as random forest regression. In order to decrease over-fitting problems and increase accuracy, it integrates the predictions of several decision trees. By comparing the model’s predictions with actual body fat measurements, we evaluate its accuracy and get reliable results.The results reveal a competitive performance of our model, demonstrating its potential as a practical tool for assessing body composition and promoting health and wellness. Through this work, we contribute to the advancement of technology-driven solutions in healthcare, facilitating personalized health monitoring and intervention. Our findings underscore the importance of accurate body fat assessment in promoting overall well-being and disease prevention.