JSI Activity Recognizer
Jožef Stefan Institute
Name of the competing system: JSI Activity Recognizer
Name and email of the responsible person: Simon Kozina ( simon.kozina(at)ijs.si)
Date and place: 10.07.2013, Valencia, Spain
Data sources
For each datasource the following table is fulfilled:
Name | 3-axis acceleration for chest and thigh accelerometers |
Description of the information measured | sensor acceleration provided by 2 accelerometers placed on the chest and the right thigh |
Units | Acceleration (m/s2) |
Example values | 9.2 m/s2 |
Frequency of generated data in operation | Acceleration is generated every 20ms (approximately). It is not a constant rate, therefore the timestamp should be used to estimate the exact difference between two consecutive samples. |
DataSets
After, for instance, 30 minutes operation the competitor generates the following data sets:
An array of arrays that include:
[time, accelerationValueChest_x, accelerationValueChest_y, accelerationValueChest_z, accelerationValueThigh_x, accelerationValueThigh_y, accelerationValueThigh_z]
every 20ms (approximately).
An array of arrays that include: [time, accelerationValueChest_x, accelerationValueChest_y, accelerationValueChest_z, accelerationValueThigh_x, accelerationValueThigh_y, accelerationValueThigh_z]every 20ms (approximately).
Files:
- A file containing this sample in .txt format.
Devices used during benchmark
Device name | Type | Position in LLab (x,y,z) in meters | Position in user | Input | Output | Communication means to your system |
Accelerometer1 | Accelerometer | - | Chest | Person moves | Acceleration X,Y,Z[-1.5G,1.5G] | Bluetooth |
| Accelerometer2 | Accelerometer | - | Right thigh | Person moves | Acceleration X,Y,Z[-1.5G,1.5G] | Bluetooth |