SIT782 Capstone Project: Mobile Application for Activity Detection

This project focuses on developing a mobile application to detect specific activities in daily living using data from a wrist-worn accelerometer. The application configures the accelerometer, captures limb movement signals, captures the type of activity performed (ground truth), displays data, and sends it to a server for analysis. The report details the project's aim, proposal, accelerometer scope, mobile app scope, data analysis server scope, and proposed technologies. It discusses activity recognition with smartphone sensors, including accelerometers, compasses, and gyroscopes, along with core techniques like data collection, preprocessing, feature computation, and classification. The project addresses challenges such as subject sensitivity, energy constraints, activity complexity, data scarcity, and location sensitivity, and explores applications in elder care, localization, biometric signatures, manufacturing assistance, and daily life monitoring. The implementation section covers project preparation, activity recognition requests, and handling, concluding with potential research directions. The mobile app is designed to use sensors and algorithms to identify activities like walking and running, providing health-related data to the user. Desklib offers this document as a valuable resource, providing similar solved assignments and past papers for students.

project management - mobile application

Table of Contents
1 Introduction.......................................................................................................................................2
2 Project Aim........................................................................................................................................3
3 Project Proposal.................................................................................................................................3
4 Accelerometer Scope.........................................................................................................................3
5 Mobile App Scope..............................................................................................................................4
6 Data Analysis Server Scope..............................................................................................................5
7 Proposed Technologies......................................................................................................................5
Activity Recognition with smartphone sensors.......................................................................................6
Activity Recognition..............................................................................................................................6
Mobile Sensors.......................................................................................................................................6
Accelerometer....................................................................................................................................6
Compass.............................................................................................................................................7
Gyroscope...........................................................................................................................................7
Core Techniques....................................................................................................................................8
Data Collection...................................................................................................................................8
Preprocessing.....................................................................................................................................9
Feature Computation......................................................................................................................10
Feature Classification......................................................................................................................10
Challenges............................................................................................................................................12
Subject Sensitivity............................................................................................................................12
Energy and resource constrains.....................................................................................................13
Activity Complexity.........................................................................................................................13
Data Scarcity....................................................................................................................................13
Location Sensitivity.........................................................................................................................14
Applications.........................................................................................................................................14
Elder and Youth care......................................................................................................................14
Localization......................................................................................................................................15
Personal Biometric Signature.........................................................................................................15
Industry manufacture assisting......................................................................................................15
Daily life monitor.............................................................................................................................15
Possible research directions................................................................................................................16
1

8 Implementation................................................................................................................................16
Project Preparation.................................................................................................................................16
Request Activity Recognition..................................................................................................................18
Activity Recognition Handling...............................................................................................................19
9 Results..............................................................................................................................................21
10 Conclusion....................................................................................................................................21
11 References....................................................................................................................................22
2

1 Introduction
Activity recognition is a process identifying the position and activity of the device using an
application. Application can be computer based or chip based. Mobile based applications also
can be used to operate small hardware devices to sense the signals of the activity and thus
identify the activity of the device. The device location like in a vehicle, on a bicycle, on foot,
moving and etc. These applications are called as activity tracking app. This app automatically
records any activity the device does like walking, cycling and running and etc. Activity
recognition is used in some of the famous web based social networking sites like Facebook.
Some of the vendors are offering devices like wearable bands. One app in mobile can be used to
monitor the daily moves, energy spent and other parameters.
2 Project Aim
The aim of the project is to design a mobile app in suitable technology that does activity
detection with the help of a hardware device used for sensing the motion. The hardware device
will be placed around the wrist. The signals will be passed to the mobile app. Mobile app will be
having the control on the sensing hardware device like switching on, operating, configuring and
switching off. With the help of a server, the mobile app will identify the activity and does
logging.
3 Project Proposal
Suitable hardware device will be selected for sensing the movement.
Mobile app will be developed
Database design, server design will be done
Suitable algorithms will be used for engineering tasks.
Suitable logging method will be used to log the activity
3

4 Accelerometer Scope
The accelerometer scope is given below (Deitel & Deitel, 2015) (Thompson, 2010)
 Accelerometer will be a wrist own
 It senses the limp movement and sends the signal data to the mobile app
 It sends data in real time
5 Mobile App Scope
 Mobile App collects the continuous signals from the accelerometer
 Mobile App will be installed in a mobile device
 Mobile device will be connected with the accelerometer
 Mobile app can configure the accelerometer that does the data generation based on the
limp movement.
 It captures the signal
 Mobile app algorithm will be doing the following
o Take the mobile activity as an input
o Extract the features of the activity
o Apply feature selection techniques
o Uses ANN model
o Uses machine learning algorithms for training and testing the ANN model
o Identify the activity
4

Mobile App may make use of the CMMotionActivity class
The uses of CMMotionActivity class is given below (Yoon, Park & Chang, 2015).
6 Data Analysis Server Scope
Server collects the data sent by the mobile app
Server runs HTTP/FTP application to receive the data from the mobile app
Opens log file, fill the log file and stores the log file
5

7 Proposed Technologies
Python is used in Mobile App development
MATLAB is used for demonstrating ANN modelling, training and testing
Activity Recognition with smartphone sensors
Activity Recognition
Activity Recognition is used to identify the actions and goals of more than one agents from a
series of the agent’s action and environmental conditions. Computer can takes an input as raw
data and recognizes the motion activity of user.
Mobile Sensors
Mobile Sensors are mainly classified into 3 types. They are
 Video sensors
 Environment sensors
 Wearable sensors
6

In this mobile sensor we can see some sensor which is used in mobile phones.
Accelerometer
It is one of the important mobile sensors in Activity Recognition. At moment of time, an
accelerometer can measure acceleration along 3 spatial axes (Thompson, 2010) (McDonald &
Stigborg, 2018).
𝐴𝑐𝑐𝑖 = < 𝑥𝑖, 𝑦𝑖, 𝑧𝑖 >, 𝑖 = 1, 2, 3…
−2.0 ≤ 𝑥𝑖, 𝑦𝑖, 𝑧𝑖 ≤ 2.0
Compass
Compass begins from 0 which is indicates north. The actual reading is, in clockwise the angle
between north and current heading direction (Tran, 2016) (Kling & Ellis, 2010).
0 ≤ 𝐶𝑜𝑚𝑝𝑖 ≤ 360, 𝑖 = 1, 2, 3 …
7

Gyroscope
It measure the rotation in rad/s. It works along 3 axes i.e. x, y and z (Zhang, Zhang & Wang,
2017) (Jackson Kimball, 2018).
Core Techniques
The core techniques are given below
Data Collection
Data Preprocessing
Feature Consumption
Classification
Data Collection
Data Collections have some Sensors (Vogt, 2010). They are given below
Single type sensor
 Single accelerometer
 Multiple accelerometer
8

Multi-modality
 Different combinations
Locations
 Single location
 Multiple location
The below picture will give some details about data collection.
9

Preprocessing
The Preprocessing is also known as DE-noising.DE-noising have Signal filter and Average.
Feature Computation
The Feature computation is Time-Domain features and Frequency Domain features. Time-
Domain features are Mean, Standard Deviation, Variance, Max, Min, Signal-Magnitude Area
and Correlation. Frequency Domain Features are Energy. Time between peaks and Entropy i.e.
normalized information entropy of discrete FFT component
Feature Classification
Feature Classification are mainly two types. They are
 Base-level Classification
 Meta-level Classification
10

Base-level Classification
The Base-level Classification are given below.
 Decision Table
 Support Vector Machine (SVM)
 K-Nearest Neighbor (KNN)
 Decision Tree
 Hidden Markov Model (HMM)
 Naive Bayes, Gaussian Mixture Model, Artificial Neural Networks etc.
The other classifiers are given below.
 Gaussian Mixed Model
 Navie Bayes
 Fuzzy Inference
 Artificial Neural Network
 Rule-based Classifier.
11