An intelligent optical fibre pH sensor based on sol-gel advanced material and artificial neural network / Mohd Nasir Taib, Faiz Bukhari Mohd Suah and Musa Ahmad
The application of artificial neural network (ANN) in signal processing of optical fibre pH sensor is presented. The pH sensor is developed based on the use of bromophenol blue indicator immobilized in a sol-gel thin film as a sensing material. A three layer feed-forward network was used and the net...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Institute of Research, Development and Commercialisation (IRDC),
2005.
|
| Subjects: | |
| Online Access: | Get fulltext View Fulltext in UiTM IR |
| LEADER | 01594 am a22001933u 4500 | ||
|---|---|---|---|
| 001 | 12802 | ||
| 042 | |a dc | ||
| 100 | 1 | 0 | |a Taib, Mohd Nasir |e author |
| 700 | 1 | 0 | |a Mohd Suah, Faiz Bukhari |e author |
| 700 | 1 | 0 | |a Ahmad, Musa |e author |
| 245 | 0 | 0 | |a An intelligent optical fibre pH sensor based on sol-gel advanced material and artificial neural network / Mohd Nasir Taib, Faiz Bukhari Mohd Suah and Musa Ahmad |
| 260 | |b Institute of Research, Development and Commercialisation (IRDC), |c 2005. | ||
| 856 | |z Get fulltext |u https://ir.uitm.edu.my/id/eprint/12802/1/AJ_MOHD%20NASIR%20TAIB%20SRJ%2005%201.pdf | ||
| 856 | |z View Fulltext in UiTM IR |u https://ir.uitm.edu.my/id/eprint/12802/ | ||
| 520 | |a The application of artificial neural network (ANN) in signal processing of optical fibre pH sensor is presented. The pH sensor is developed based on the use of bromophenol blue indicator immobilized in a sol-gel thin film as a sensing material. A three layer feed-forward network was used and the network training was performed using the back-propagation algorithm. Spectra generated from the pH sensor at several selected wavelengths are used as the input for the ANN. The bromophenol blue indicator, which has a limited dynamic range of 3.00-5.50 pH units, was found to show higher pH dynamic range of 2.00-12.00 and low calibration error after training with ANN. The trained ANN was successfully employed to predict several spectra from unknown buffer solution with an average error of 0.06 pH units. | ||
| 546 | |a en | ||
| 650 | 0 | 4 | |a Neural networks (Computer science) |
| 650 | 0 | 4 | |a Optical fibers |
| 655 | 7 | |a Article | |