Basic and Clinical Neuroscience Journal
مجله علوم اعصاب پایه و بالینی
BCN
Medical Sciences
http://bcn.iums.ac.ir
137
journal137
2008-126X
2228-7442
10.32598/bcn
en
jalali
1390
1
1
gregorian
2011
4
1
2
3
online
1
fulltext
en
A Gray-Box Neural Network Model of Parkinson’s Disease Using Gait Signal
Computational Neuroscience
Computational Neuroscience
Original
Original
<font color="#211d1e" size="2"><font color="#211d1e" size="2"><p style="DIRECTION: ltr" align="left">In this study, we focused on the gait of Parkinson’s disease (PD) and presented a gray box model for it. We tried to present a model for basal ganglia structure </p></font></font><font color="#211d1e" size="2" face="Times New Roman,Times New Roman"><font color="#211d1e" size="2" face="Times New Roman,Times New Roman"><font color="#211d1e" size="2" face="Times New Roman,Times New Roman">in order to generate stride time interval signal in model output for healthy and PD states. Because of feedback role of dopamine neurotransmitter in basal </font></font></font><font color="#211d1e" size="2"><font color="#211d1e" size="2">ganglia, this part is modelled by “Elman Network”, which is a neural network </font></font><font color="#211d1e" size="2" face="Times New Roman,Times New Roman"><font color="#211d1e" size="2" face="Times New Roman,Times New Roman"><font color="#211d1e" size="2" face="Times New Roman,Times New Roman">structure based on a feedback relation between each layer. Remaining parts of the </font></font></font><font color="#211d1e" size="2"><font color="#211d1e" size="2">basal ganglia are modelled with feed-forward neural networks. We first trained </font></font><font color="#211d1e" size="2" face="Times New Roman,Times New Roman"><font color="#211d1e" size="2" face="Times New Roman,Times New Roman"><font color="#211d1e" size="2" face="Times New Roman,Times New Roman">the model with a healthy person and a PD patient separately. Then, in order to </font></font></font><font color="#211d1e" size="2"><font color="#211d1e" size="2">extend the model generality, we tried to generate the behaviour of all subjects of our database in the model. Hence, we extracted some features of stride signal including mean, variance, fractal dimension and five coefficients from spectral domain. With adding 10% tolerance to above mentioned neural network weights </font></font><font color="#211d1e" size="2" face="Times New Roman,Times New Roman"><font color="#211d1e" size="2" face="Times New Roman,Times New Roman"><font color="#211d1e" size="2" face="Times New Roman,Times New Roman">and using genetic algorithm, we found proper parameters to model every person in the used database. The following points may be regarded as clues for the acceptability of our model in simulating the stride signal: the high power of the network for simulating normal and patient states, high ability of the model in producing the behaviour of different persons in normal and patient cases, and the similarities between the model and physiological structure of basal ganglia.</font></font></font><p> </p><p> </p>
Basal Ganglia,Artificial Neural Network,Genetic Algorithm, Simulation
33
42
http://bcn.iums.ac.ir/browse.php?a_code=A-10-1-59&slc_lang=en&sid=1
Yashar
Sarbaz
137003194753284600959
137003194753284600959
No
Shahriar
Gharibzadeh
daliri@iust.ac.ir
137003194753284600960
137003194753284600960
Yes
Farzad
Towhidkhah
137003194753284600961
137003194753284600961
No
Masood
Banaie
137003194753284600962
137003194753284600962
No
Ayyoob
Jafari
137003194753284600963
137003194753284600963
No