HARGRURNN: Human activity recognition using inertial body sensor gated recurrent units recurrent neural network

Abstract

Internet of Things (IoT), wearable devices, and smartphones are more ubiquitous and available at a reasonable cost. Fitbit, Microsoft Band, Apple Watch, MI band, and Smartphone apps namely Strava and Runkeeper are some of the commercial products which are already available in the market. These products are embedded with the sensors that facilitate them to regularly sense and capture the environmental, physiological, functional data for applications in healthcare, wellbeing, and sports. These sensing devices have mediocre computing capabilities for data processing and transfer. The size of devices is so compact that can be worn on the body put in the pocket or locate in the house. This large scale recorded a wealth of physiological data require an efficient and meaningful interpretation as well as the proper and proficient method of analysis and the classification of data.

Human Activity Recognition is classified into two features say Shallow and Deep features. Shallow features are extracted conventionally with the help of a simple machine learning approach. The large-scale time series situ data which require high computation power, processing capabilities, activities, and real-time classification, Deep Learning (DL) is the promising technique to deal with these activities.

Weexercise the triaxial Accelerometers and triaxial Gyroscope to capture the data for HAR. The data set measured by the inertial sensor is then divided into the segments of 4 to 10s. The performance will be shown on the parameters of precision (%), Recall (%) and Accuracy (%).Parameter optimization and extraction of the segments are the two areas where we can carry forward our research.

Subject Classification:

• Primary 93A30
• Secondary 49K15

Keywords:

• HAR
• Shallow and deep features
• Smartphone
• Feature extraction
• Neural Network