Dimensionality Reduction-Based Discriminatory Classification of Human Activity Recognition Using Machine Learning

Majority of work in activity recognition using different machine learning and deep learning has shown very challenging results to monitor daily activities. Different datasets available on Web have been used to improve the results, still model fitness need to be verified in terms of different characteristics of matrix and error analysis. Dimensionality reduction (DR) of datasets improves the results of models due to pruning of dataset features. In this paper, we have introduced seven different machine learning models to improve the results. Proposed framework has used principle components analysis (PCA) and linear discriminant analysis (LDA) for dimensionality reduction of UCI-ML dataset. Results show that LDA is better than PCA. Kernel–SVM accuracy has increased from 95.39 to 96.23%. Naïve Bayes has shown 96.78% accuracy with dimensionality reduction. Simple dataset has shown low accuracy while dimensionality reduction has improved the performances of models. We have also introduced different challenges associated with machine learning models, fitness value, and future challenges. At the end of this work, we have done comparative study and error analysis of models.