Real-time system identification of an unmanned quadcopter system using fully tuned radial basis function neural networks
In this paper, we present the performance analysis of a fully tuned neural network trained with the extended minimal resource allocating network (EMRAN) algorithm for real-time identification of a quadcopter. Radial basis function network (RBF) based on system identification can be utilised as...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Inder Science
2021
|
| Subjects: | |
| Online Access: | http://eprints.uthm.edu.my/6616/1/J13840_86bfec0ace2c4bbe3417b0d967ad1cc3.pdf http://eprints.uthm.edu.my/6616/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| id |
my.uthm.eprints.6616 |
|---|---|
| record_format |
eprints |
| spelling |
my.uthm.eprints.66162022-03-10T03:23:14Z http://eprints.uthm.edu.my/6616/ Real-time system identification of an unmanned quadcopter system using fully tuned radial basis function neural networks Pairan, Mohammad Fahmi Shamsudin, Syariful Syafiq Yaakub, Mohd Fauzi Mohd Anwar, Mohd Shazlan TL Motor vehicles. Aeronautics. Astronautics In this paper, we present the performance analysis of a fully tuned neural network trained with the extended minimal resource allocating network (EMRAN) algorithm for real-time identification of a quadcopter. Radial basis function network (RBF) based on system identification can be utilised as an alternative technique for quadcopter modelling. To prevent the neurons and network parameters selection dilemma during trial and error approach, RBF with EMRAN training algorithm is proposed. This automatic tuning algorithm will implement the network growing and pruning method to add or eliminate neurons in the RBF. The EMRAN’s performance is compared with the minimal resource allocating network (MRAN) training for 1000 input-output pair untrained attitude data. The findings show that the EMRAN method generates a faster mean training time of roughly 4.16 ms for neuron size of up to 88 units compared to MRAN at 5.89 ms with a slight reduction in prediction accuracy. Inder Science 2021 Article PeerReviewed text en http://eprints.uthm.edu.my/6616/1/J13840_86bfec0ace2c4bbe3417b0d967ad1cc3.pdf Pairan, Mohammad Fahmi and Shamsudin, Syariful Syafiq and Yaakub, Mohd Fauzi and Mohd Anwar, Mohd Shazlan (2021) Real-time system identification of an unmanned quadcopter system using fully tuned radial basis function neural networks. Int. J. Modelling, Identification and Control, 37 (2). pp. 128-139. |
| institution |
Universiti Tun Hussein Onn Malaysia |
| building |
UTHM Library |
| collection |
Institutional Repository |
| continent |
Asia |
| country |
Malaysia |
| content_provider |
Universiti Tun Hussein Onn Malaysia |
| content_source |
UTHM Institutional Repository |
| url_provider |
http://eprints.uthm.edu.my/ |
| language |
English |
| topic |
TL Motor vehicles. Aeronautics. Astronautics |
| spellingShingle |
TL Motor vehicles. Aeronautics. Astronautics Pairan, Mohammad Fahmi Shamsudin, Syariful Syafiq Yaakub, Mohd Fauzi Mohd Anwar, Mohd Shazlan Real-time system identification of an unmanned quadcopter system using fully tuned radial basis function neural networks |
| description |
In this paper, we present the performance analysis of a fully tuned neural network
trained with the extended minimal resource allocating network (EMRAN) algorithm for real-time
identification of a quadcopter. Radial basis function network (RBF) based on system
identification can be utilised as an alternative technique for quadcopter modelling. To prevent the
neurons and network parameters selection dilemma during trial and error approach, RBF with
EMRAN training algorithm is proposed. This automatic tuning algorithm will implement the
network growing and pruning method to add or eliminate neurons in the RBF. The EMRAN’s
performance is compared with the minimal resource allocating network (MRAN) training for
1000 input-output pair untrained attitude data. The findings show that the EMRAN method
generates a faster mean training time of roughly 4.16 ms for neuron size of up to 88 units
compared to MRAN at 5.89 ms with a slight reduction in prediction accuracy. |
| format |
Article |
| author |
Pairan, Mohammad Fahmi Shamsudin, Syariful Syafiq Yaakub, Mohd Fauzi Mohd Anwar, Mohd Shazlan |
| author_facet |
Pairan, Mohammad Fahmi Shamsudin, Syariful Syafiq Yaakub, Mohd Fauzi Mohd Anwar, Mohd Shazlan |
| author_sort |
Pairan, Mohammad Fahmi |
| title |
Real-time system identification of an unmanned
quadcopter system using fully tuned radial basis
function neural networks |
| title_short |
Real-time system identification of an unmanned
quadcopter system using fully tuned radial basis
function neural networks |
| title_full |
Real-time system identification of an unmanned
quadcopter system using fully tuned radial basis
function neural networks |
| title_fullStr |
Real-time system identification of an unmanned
quadcopter system using fully tuned radial basis
function neural networks |
| title_full_unstemmed |
Real-time system identification of an unmanned
quadcopter system using fully tuned radial basis
function neural networks |
| title_sort |
real-time system identification of an unmanned
quadcopter system using fully tuned radial basis
function neural networks |
| publisher |
Inder Science |
| publishDate |
2021 |
| url |
http://eprints.uthm.edu.my/6616/1/J13840_86bfec0ace2c4bbe3417b0d967ad1cc3.pdf http://eprints.uthm.edu.my/6616/ |
| _version_ |
1738581513495117824 |
| score |
13.211869 |