Binary Switch Floor Dataset
----------------------------
(c) 2012, Jaakko Suutala

Please cite the related papers [1] and [2] when using the dataset.

Datasets
---------
Each dataset file contains feature vectors as rows and each column gives the 
values of that particular feature, first column being order number of sequence 
(NOT TO BE USED AS FEATURE!) and last column being a true class label (i.e., person id). 
If you want to classify single foosteps ingnore the first column. You can combine these to accelerometer
measurements in another datasets, which were collected simultaneously.


Induvidual datasets are:

9dataset_floor.txt: 28 spatial, statistical, and time-related features from footstep profiles, 9 subjects and 
20 walking seq. / subject

4dataset_floor.txt: 28 spatial, statistical, and time-related features from footstep profiles, 4 subjects and 
ca. 80 walking seq. / subject. 3 different footwear and walking speed collected from each subject

9dataset_floor_all.txt: combined dataset of two presented above. Totally 2586 footsteps profiles and 418 walking sequences 
from 9 subjects  

Individual features are listed in [1].

References
----------
[1] Suutala J. (2012) Learning Discriminative Models from Structured 
Multi-sensor Data for Human Context Recognition, Doctoral Thesis, University of Oulu.
[2] Suutala J, Fujinami K & Röning J (2008) Gaussian Process person identifier based on simple floor sensors.
Proc. 3rd European Conference on Smart Sensing and Context (EuroSSC08), Zürich, Switzerland, 55-68.