Professional Documents
Culture Documents
Goals
To develop technologies for independent daily life
assistance of elderly or sick persons.
Design a complex assistive system that can learn and
adapt due to the uses of artificial neural networks (ANN).
Design and test of several Matlab ANN models in order
to find the best performing architecture.
Finding necessary preprocessing of raw data aiming to
have a better recognition rate.
Optimization of the number of sensors and their
placement in order to obtain the best trade-off
between recognition rate and the complexity of the
recognition system.
100
200
300
400
500
600
700
800
900
1000
100
200
300
400
500
600
700
800
900
1000
100
200
300
400
500
600
700
800
900
1000
100
200
300
400
500
600
700
800
900
1000
100
200
300
400
500
600
700
800
900
1000
N
e
u
r
a
ln
e
tw
o
r
k
o
u
tp
u
ts
2
1
0
-1
2
1
0
-1
2
1
0
-1
2
1
0
-1
Samples
Activity recognition
activities to be recognized
1. Standing,
2. Sitting
3. Supine
12. Squats
4. Prone
14 .Falls
7. Walking
8. Running
9. Bending forward
Transitions
95.44%
96.28%
98.06%
98.07%
97.81%
96.28%
Conclusions
The use of ANN was found to be very effective even for
architectures with one hidden layer with 20 neurons.
Even using a single 3-axis acceleration tag combined with
proper signal preprocessing e.g., mean, standard deviation,
etc. very high recognition rates can be obtained.
As expected the recognition rate for the static activities was
better than for dynamic activities.
We also implemented and tested a real time recognition
system using Raspberry Pi mini-computer.
Further research will be made regarding the best performing,
hardware implementation friendly, ANN.