HUMAN ACTIVITIES RECOGNIZATIONUSING MACHINE LEARNING AND DATA ANALYTICS
Keywords:
k-nearest neighbor (KNN), SGD, Random Forest, Naïve BayesAbstract
In recent years, smartphones have emerged as indispensable tools for recognizing
human activities, garnering significant attention in research circles. This paper
provides a detailed overview of various research endeavors in human activity
recognition. Artificial Intelligence (AI) models have been meticulously developed to
discern human activities using data sourced from the UCI online repository,
characterized by its multivariate nature. We employed a spectrum of machine
classification techniques including Random Forest, kNN, Neural Network, Logistic
Regression, Stochastic Gradient Descent, and Naïve Bayes to scrutinize human
activity patterns. Additionally, we employed feature selection techniques to reduce the
dataset's dimensionality. Precision and Recall metrics were computed, and Confusion
Matrices were constructed for each model. Experimental findings underscore that
Neural Network and logistic regression models exhibit superior accuracy in human
activity recognition compared to other classifiers like k-nearest neighbor (KNN),
SGD, Random Forest, and Naïve Bayes, albeit at the expense of increased
computational time and memory resources.
Downloads
Published
Issue
Section
License

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.













