HarborZeng / HumanActivityRecognition

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

1 Data Collection Procedure 

We used four Samsung Galaxy S2 smartphones in our experiments for data collection. Using these smartphones, we collected data for six different physical activities. They are walking, running, sitting, standing, walking upstairs and downstairs. We asked four participants to perform these six activities for a few minutes. As these are repetitive activities, so the amount of time for each activity was kept between 3-5 minutes per participant which gave us enough examples for our evaluations. The activities were carried out indoor in one of our university buildings. For walking, and running, the department's corridor was used. For sitting activity, participants’ offices were used when they were using their computers. For standing activity, coffee area was used where some participants stood for few minutes while involved in a conversation with others. For walking upstairs and downstairs, 5-floor stairs were used. It is important to mention that these stairs had short walks at each floor for switching between stairs (2-3 steps) but there were only four such switches in the whole walking upstairs and downstairs activities. We could not find one single continuous stair from first till 5th floor. Each of these participants was provided with four smartphones on four body positions: right jeans pocket, belt, arm, and wrist. The data was recorded for all four positions at the same time for each activity. All the four participants were male, between the age of 25 and 30. They signed a consent form before taking part in the activities

2 Datafile Formats 
Arm.xlsx (Sensor data on arm position for all four participants)
Belt.xlsx (Sensor data on Belt position for all four participants)
Wrist.xlsx (Sensor data on Wrist position for all four participants)
Pocket.xlsx (Sensor data on Pocket position for all four participants)

3 Raw Data Columns within these files: 

Timestamp 
Ax (Accelerometer X-axis) 
Ay (Accelerometer Y-axis)
Az (Accelerometer Z-axis)
Gx (Gyroscope X-axis)
Gy (Gyroscope Y-axis)
Gz (Gyroscope Z-axis)
Mx (Magnetometer X-axis)
My (Magnetometer Y-axis)
Mz (Magnetometer Z-axis)
Activity Label 

4 Data Labelling 
All data samples in these files are properly labelled with our six acitivities. 

Citation: This dataset can only be used with citing the following paper. 
Shoaib, Muhammad,  "Human Activity Recognition Using Hetrogenious Sensors" “Appears in the Adjunct Proceedings of UbiComp  2013.

About


Languages

Language:Python 100.0%