[SOLVED] AReM

AReM
AReM (Activity Recognition system based on Multisensor data fusion)
Bending
Sensors placement Bending1
3
RBF

arem_train.csv 36747 arem_test.csv ,5012 :
Bending2
X

avg_rss12 var_rss12 avg_rss13 var_rss13 avg_rss23
var_rss23

float
y activity
string

:bending1, bending2, walking, standing, sitting, lying, cycling.
X y

Feature Scaling;
Batch Training
:
: accuracy = # #
bending1, bending2, walking, standing, sitting, lying, cycling walking
: sum( ( y_pre == y_true ) & ( y_true == walking ) ) sum( y_true == walking )
Reference
[1] UCI AReM Data Set
https://archive.ics.uci.edu/ml/datasets/Activity+Recognition+system+based+on+Multisensor+data+fusion +%28AReM%29#
[2] F. Palumbo, C. Gallicchio, R. Pucci and A. Micheli, Human activity recognition using multisensor data fusion based on Reservoir Computing, Journal of Ambient Intelligence and Smart Environments, 2016, 8 (2), pp. 87-107.