Abstract
This paper presents a method to predict a fish motion by Neural Network (N.N.) with on-line learning. We assume the motion trajectory of a fish swimming in a pool be approximated by circles with time varying radius and center position. We try to improve prediction accuracy of a fish motion by using N.N. whose inputs are radii and angular velocities in previous three control-times and outputs are radius and angular velocity in the following control period. Using radius and angular velocity obtained by circular approximation, we confirmed that the proposed N.N. prediction system can maintain good prediction performances under the proposed on-line learning process.
| Original language | English |
|---|---|
| Title of host publication | 2006 SICE-ICASE International Joint Conference |
| Pages | 5120-5125 |
| Number of pages | 6 |
| DOIs | |
| Publication status | Published - 2006 |
| Externally published | Yes |
| Event | 2006 SICE-ICASE International Joint Conference - Busan, Korea, Republic of Duration: Oct 18 2006 → Oct 21 2006 |
Other
| Other | 2006 SICE-ICASE International Joint Conference |
|---|---|
| Country | Korea, Republic of |
| City | Busan |
| Period | 10/18/06 → 10/21/06 |
Fingerprint
Keywords
- Back propagation
- Gazing-GA
- Neural network
- Prediction
ASJC Scopus subject areas
- Computer Science Applications
- Control and Systems Engineering
- Electrical and Electronic Engineering
Cite this
On-line prediction of escaping fish from catching net by neural network and circular approximation. / Yoshida, Toshiaki; Suzuki, Hidekazu; Minami, Mamoru; Mae, Yasushi.
2006 SICE-ICASE International Joint Conference. 2006. p. 5120-5125 4108687.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - On-line prediction of escaping fish from catching net by neural network and circular approximation
AU - Yoshida, Toshiaki
AU - Suzuki, Hidekazu
AU - Minami, Mamoru
AU - Mae, Yasushi
PY - 2006
Y1 - 2006
N2 - This paper presents a method to predict a fish motion by Neural Network (N.N.) with on-line learning. We assume the motion trajectory of a fish swimming in a pool be approximated by circles with time varying radius and center position. We try to improve prediction accuracy of a fish motion by using N.N. whose inputs are radii and angular velocities in previous three control-times and outputs are radius and angular velocity in the following control period. Using radius and angular velocity obtained by circular approximation, we confirmed that the proposed N.N. prediction system can maintain good prediction performances under the proposed on-line learning process.
AB - This paper presents a method to predict a fish motion by Neural Network (N.N.) with on-line learning. We assume the motion trajectory of a fish swimming in a pool be approximated by circles with time varying radius and center position. We try to improve prediction accuracy of a fish motion by using N.N. whose inputs are radii and angular velocities in previous three control-times and outputs are radius and angular velocity in the following control period. Using radius and angular velocity obtained by circular approximation, we confirmed that the proposed N.N. prediction system can maintain good prediction performances under the proposed on-line learning process.
KW - Back propagation
KW - Gazing-GA
KW - Neural network
KW - Prediction
UR - http://www.scopus.com/inward/record.url?scp=34250712382&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=34250712382&partnerID=8YFLogxK
U2 - 10.1109/SICE.2006.315377
DO - 10.1109/SICE.2006.315377
M3 - Conference contribution
SN - 8995003855
SN - 9788995003855
SP - 5120
EP - 5125
BT - 2006 SICE-ICASE International Joint Conference
ER -