Summary of Human Activity Recognition Using Smartphones, by Mayur Sonawane et al.
Human Activity Recognition using Smartphones
by Mayur Sonawane, Sahil Rajesh Dhayalkar, Siddesh Waje, Soyal Markhelkar, Akshay Wattamwar, Seema C. Shrawne
First submitted to arxiv on: 3 Apr 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary A novel approach to human activity recognition (HAR) is presented in this paper, which focuses on developing an Android application capable of recognizing daily activities and estimating calorie burn in real-time. The project involves capturing labeled triaxial acceleration readings from a smartphone’s accelerometer for various daily activities, followed by preprocessing using a median filter. Extracted features are then analyzed using machine learning algorithms with dimensionality reduction techniques to achieve high accuracy and efficient model building times. The proposed system is designed to provide accurate HAR and calorie estimation results in real-time, making it suitable for applications such as remote healthcare, activity tracking of the elderly or disabled, and calorie burn tracking. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This project creates an Android app that can recognize daily activities and calculate how many calories you’ve burned. To do this, they used a smartphone’s accelerometer to collect data on different activities, like walking or running. They then cleaned up the data using a special filter and extracted important details about each activity. Next, they tested different machine learning techniques to find the one that works best for recognizing activities and calculating calories. The result is an app that can do this in real-time, which could be useful for people who want to track their health or monitor their daily activities. |
Keywords
» Artificial intelligence » Activity recognition » Dimensionality reduction » Machine learning » Tracking
