Indoor Positioning Using Artificial Neural Network with Field Programmable Gate Array Implementation
Indoor positioning required fast and accurate result. This paper applied the artificial neural network (ANN) as a system for calculating the target in indoor environment. To speed up the calculation time, ANN then is run into field programmable gate array (FPGA). Since the original sigmoid function...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
American Scientific Publisher
2018
|
| Subjects: | |
| Online Access: | http://umpir.ump.edu.my/id/eprint/19956/1/49.%20Indoor%20Positioning%20Using%20Artificial%20Neural%20Network%20with%20Field%20Programmable%20Gate%20Array%20Implementation1.pdf http://umpir.ump.edu.my/id/eprint/19956/ https://doi.org/10.1166/asl.2018.12985 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Universiti Malaysia Pahang |
| Language: | English |
| Summary: | Indoor positioning required fast and accurate result. This paper applied the artificial neural network (ANN) as a system for calculating the target in indoor environment. To speed up the calculation time, ANN then is run into field programmable gate array (FPGA). Since the original sigmoid function in ANN is not feasible to be applied into FPGA, two-steps sigmoid function calculation proposed by previous researcher then is used as a replacement. A new design of the FPGA is proposed to suite the requirement for implementing the previous researcher method. The results showing that FPGA can calculate 20 times faster with the maximum error 0.04 meters, slightly higher than the software implementation. |
|---|