Machine Learning Classification for Human Activity Recognition

Team

1. Dheemanth Rajakumar
2. Andy Malinsky
3. Greg Moore

Problem Description:

The objective of this project is to develop a machine learning system that can predict human activities using data collected from smartphone sensors. The activities to be classified include walking, walking upstairs, walking downstairs, sitting, standing, and lying. This problem has practical applications in areas such as health monitoring, fitness tracking, and human-computer interaction.

Dataset:

The UCI Machine Learning Repository provides a labeled dataset for this task. The dataset includes sensor signals collected from the accelerometer and gyroscope of a smartphone carried by participants while performing the activities.

---

# Algorithms to Investigate:

Algorithm Type	Algorithm
Classification Algorithms
	1. Decision Trees
	2. Random Forest
	3. Support Vector Machines (SVM)
	4. Neural Networks (e.g., Convolutional Neural Networks, Recurrent Neural Networks)
Clustering Algorithms
	5. K-means Clustering
	6. DBSCAN (Density-Based Spatial Clustering of Applications with Noise)

---