LEVERAGING ENSEMBLE LEARNING FOR CLASSIFICATION OF OLD PEOPLE AND KIDS

Abstract

This study evaluates the effectiveness of ensemble learning methods for classifying older people and kids, with a focus on Random Forest (RF) and AdaBoost with Decision Tree (DT) Estimator. Both age groups' set of labelled images will make up the training data and the evaluation dataset. The images will be utilized for training the models to identify features that set old people and kids apart. By merging several weak learners into a strong classifier, this study hopes to improve classification accuracy and robustness by leveraging the potential of ensemble approaches. While the AdaBoost method focuses on iteratively modifying the weights of misclassified instances to enhance model performance, the Random Forest approach builds a forest of decision trees and combines their predictions to achieve accurate classification. The first phase of this investigation entailed building a large dataset including images of both kids and older individuals. "Old People" and "Kids" were two separate classes created from the information. In order to ensure the dataset's inclusivity and representativeness, a variety of sources were used to gather a wide range of images. The dataset was subsequently divided into training and validation subsets using the proper technique to make sure the model could generalize successfully to new data. Preprocessing techniques were used to standardize the images once the dataset had been prepared. This required scaling the images to a constant resolution and normalizing the pixel intensities of the images. These preprocessing procedures are essential for creating a standardized input format and improving model performance. Following training, a variety of evaluation metrics, including accuracy, precision, recall, and F1-score, will be used to evaluate the models' performance. These metrics provide insight on the models' ability differentiate between old people and kids. The evaluation's findings will then be compared to determine which algorithm is better at identifying old people and kids. Which method is better suited for this particular task can be determined with the aid of this comparison. The evaluation metrics from the previous project are compared with those from Support Vector Machines (SVM) and Convolutional Neural Networks (CNN), including accuracy, precision, recall, and F1-score. The results demonstrate the v effectiveness of ensemble learning approaches, with Random Forest performing the best overall, demonstrating superior performance across all metrics. AdaBoost with Decision Tree Estimator also performed well and was competitive with Random Forest. These results demonstrate ensemble learning's potential for accurate classification tasks and offer insightful information for further study and use in a variety of fields.