Topics In Demand
Notification
New

No notification found.

Human Activity Recognition (HAR) using Machine Learning!
Human Activity Recognition (HAR) using Machine Learning!

March 31, 2023

255

0

Prediction of Human Actions with AI & ML

The development of technology on a day-to-day basis has made us rely on smartphones to do daily activities. From food delivery to entertainment, everything has become handy with smartphones. Human Activities such as walking or running can be easily detected using smart devices. Recognition of human actions in videos and low-quality images has been challenging, to overcome this issue Human Activity using machine learning technology is being explored.

 

Today advanced Machine learning algorithm models are developed to make wearable medical devices that track and monitor health variables. Some of the popular medical devices are fitness smartwatches, pulse oxy meters, Glucometere, ECG monitors, etc.

 

What is Human Activity Recognition (HAR)?

Human Activity Recognition is a method of identifying human body movements through sensors with the help of AI and predicting possible activities based on previous data. All these data insights and activities are based on time series classification tasks. Human activities that can be identified includes sitting, standing, walking, talking, and many other daily activities. Advanced IoT, cloud, and edge computing have paved the way to embed smartphone sensors that track human activities. It also provides a deep understanding of human behavior.

 

HAR using Smartphones

Most smartphones have two sensors; An accelerator and a gyroscope. The Accelerator collects the horizontal movement data, and the gyroscope collects rotational motion data.

 

HAR helps in tracking the sports activities of athletes and provides accurate performance analysis. Smart medical devices track pulse rate, blood pressure, and blood sugar levels, thereby keeping the regular health history data of patients. The raw data collected from smart medical devices is extensively used for medical and nutrition research.

 

HAR using Deep Learning

Deep learning is an advanced-level technology it classifies various human activities. In deep learning models, human activity recognition dataset collected from sensors is the input and predicts the most probable human action. In vision-based human activity recognition system, this tool is very useful in predicting risk movements and avoiding major accidents in traffic.

 

Popular Deep learning models are the Convolutional Neural Network(CNN) and Recurring Neural Network(RNN) models. These Neural network models are developed based on time series classification and performance of human activity recognition. 

 

CNN models are efficient at handling challenging low-vision image datasets. The RNN model was developed to recognize and analyze the sequence of observation within the allocated time or pattern of words in a sentence. Long Short-Time Memory( LSTM) is a specific RNN model proven to resolve challenging sequence prediction problems.

 

Overall Review 

 

Human Activity Recognition using smartphones has already proven to be helpful in health and fitness tracking. This technique helped people to keep regular and accurate monitoring of health and fitness, which does not require regular visits to hospitals. Further, in case of physically challenged, obese, and elderly people can now have a health check-up at their homes.

 

Human Activity Recognition using Deep learning is a very advanced tool that efficiently handles 2D and 3D datasets. This is one of the most researched technologies at present.

 

The number of projects involving human activity recognition is growing year with  advancements in Artificial Intelligence and Machine learning. Data analysis and predictions are in each and every aspect of technical innovations, and now it's time for Human Activity Recognition which uses AI and ML to a huge extent. 




 

Learning Advanced Artificial Intelligence and Machine Learning shapes and secures your overall technological career.


That the contents of third-party articles/blogs published here on the website, and the interpretation of all information in the article/blogs such as data, maps, numbers, opinions etc. displayed in the article/blogs and views or the opinions expressed within the content are solely of the author's; and do not reflect the opinions and beliefs of NASSCOM or its affiliates in any manner. NASSCOM does not take any liability w.r.t. content in any manner and will not be liable in any manner whatsoever for any kind of liability arising out of any act, error or omission. The contents of third-party article/blogs published, are provided solely as convenience; and the presence of these articles/blogs should not, under any circumstances, be considered as an endorsement of the contents by NASSCOM in any manner; and if you chose to access these articles/blogs , you do so at your own risk.


© Copyright nasscom. All Rights Reserved.