Smartphone-Based Human Activity Recognition and Prediction - IT Assignment Help

Assignment Task

Introduction:
Human-centered computing is an emerging, interdisciplinary field that focuses on the analysis of human behavior using computational artifacts [1]. Gathering context information about someone based on the activities he/she is engaged by using sensors mounted on smartphones attached to an individual that keeps track of and recordshuman body motion is a typical example of human-centered computing. This branch of human-centered computing is particularly known as Human Activity Recognition (HAR). The Samsung dataset used in this analysis is a human activity recognition database built from the recordings of thirty (30) subjects/volunteers within an age bracket of 19-48 years performing activities of daily living (ADL) while carrying a waistmounted smartphone (Samsung Galaxy S II) with embedded inertial sensors [2]. The activities they engaged in are walking, walking upstairs, walking downstairs, sitting,standing, and laying. Each of the thirty volunteers performed all the above mentione six activities. The main goal of this analysis is to build a function that predicts what activity a subject is performing based on the quantitative measurements from the Samsung phone dataset.

Finally, the complete set of variables that were recorded in the Samsung data set were estimated from the following properties of the above mentioned signals of interest:

•  Mean value denoted as ‘mean()’
•  Standard deviation denoted as ‘std()’
•  Median absolute deviation denoted as mad()
•  Largest value in array denoted as max()
•  Smallest value in array denoted as min()
•  Signal magnitude area denoted as ‘sma()’
•  Energy measure which is the sum of the squares divided by the number of values denoted as ‘energy()’
•  Interquartile range denoted as ‘iqr()’
•  Signal entropy denoted as ‘entropy()’
•  Autorregresion coefficients with Burg order equal to 4 denoted as ‘arCoeff()’
•  Correlation coefficient between two signals denoted as ‘correlation()’
•  Index of the frequency component with largest magnitude denoted as ‘maxInds()’
•  Weighted average of the frequency components to obtain a mean frequency denoted as ‘meanFreq()’
•  skewness of the frequency domain signal denoted as ‘skewness()’
•  kurtosis of the frequency domain signal denoted as ‘kurtosis()’
•  Energy of a frequency interval within the 64 bins of the FFT of each window denoted as ‘bandsEnergy()’
• Angle between two vectors denoted as ‘angle()’

This IT Assignment has been solved by our IT Experts at My Uni Paper. Our Assignment Writing Experts are efficient to provide a fresh solution to this question. We are serving more than 10000+Students in Australia, UK & US by helping them to score HD in their academics. Our Experts are well trained to follow all marking rubrics & referencing style.
    
Be it a used or new solution, the quality of the work submitted by our assignment Experts remains unhampered. You may continue to expect the same or even better quality with the used and new assignment solution files respectively. There’s one thing to be noticed that you could choose one between the two and acquire an HD either way. You could choose new assignment solution file to get yourself an exclusive, plagiarism (with free Turnitin file), expert quality assignment or order an old solution file that was considered worthy of the highest distinction.