Hardware Implementation Of Artificial Neural Network On FPGA For Sulfate-Reducing Bacteria
The study presents a preliminary design of a classification system to detect the presence of sulfate-reducing bacteria (SRB). The thesis focuses on the development of artificial neural network (ANN) model 10 recognize the presence of SRB in a sample based on the sensors responses. Two sensors are...
| Main Author: | |
|---|---|
| Format: | Thesis |
| Language: | English |
| Published: |
2014
|
| Subjects: | |
| Online Access: | http://eprints.usm.my/61074/1/24%20Pages%20from%2000001779827.pdf |
| _version_ | 1825908404272496640 |
|---|---|
| author | Tan, Earn Tzeh |
| author_facet | Tan, Earn Tzeh |
| author_sort | Tan, Earn Tzeh |
| collection | USM |
| description | The study presents a preliminary design of a classification system to detect the
presence of sulfate-reducing bacteria (SRB). The thesis focuses on the development
of artificial neural network (ANN) model 10 recognize the presence of SRB in a
sample based on the sensors responses. Two sensors are implemented in this study,
TGS 825 and SI-IT 75. The sensors responses from preliminary experimental works
show that presence of SRI) in a sample give a significant effect on the concentration
level of hydrogen sulphide (1-I2S) and temperature. The statements are proved by the
two-sample T-test analysis, where the null hypotheses are rejected. The data
collected data from the experiments form the training dataset of ANN. The ANN is
trained with back propagation algorithm in Matlab and the classification results show
that the ANN model promises a good performance with 100% prediction accuracy to
classify a sample into two groups, either with SRB or without SRB. |
| first_indexed | 2024-09-25T03:57:54Z |
| format | Thesis |
| id | usm.eprints-61074 |
| institution | Universiti Sains Malaysia |
| language | English |
| last_indexed | 2024-09-25T03:57:54Z |
| publishDate | 2014 |
| record_format | dspace |
| spelling | usm.eprints-610742024-09-09T04:11:48Z http://eprints.usm.my/61074/ Hardware Implementation Of Artificial Neural Network On FPGA For Sulfate-Reducing Bacteria Tan, Earn Tzeh TK1-9971 Electrical engineering. Electronics. Nuclear engineering The study presents a preliminary design of a classification system to detect the presence of sulfate-reducing bacteria (SRB). The thesis focuses on the development of artificial neural network (ANN) model 10 recognize the presence of SRB in a sample based on the sensors responses. Two sensors are implemented in this study, TGS 825 and SI-IT 75. The sensors responses from preliminary experimental works show that presence of SRI) in a sample give a significant effect on the concentration level of hydrogen sulphide (1-I2S) and temperature. The statements are proved by the two-sample T-test analysis, where the null hypotheses are rejected. The data collected data from the experiments form the training dataset of ANN. The ANN is trained with back propagation algorithm in Matlab and the classification results show that the ANN model promises a good performance with 100% prediction accuracy to classify a sample into two groups, either with SRB or without SRB. 2014-03 Thesis NonPeerReviewed application/pdf en http://eprints.usm.my/61074/1/24%20Pages%20from%2000001779827.pdf Tan, Earn Tzeh (2014) Hardware Implementation Of Artificial Neural Network On FPGA For Sulfate-Reducing Bacteria. Masters thesis, Perpustakaan Hamzah Sendut. |
| spellingShingle | TK1-9971 Electrical engineering. Electronics. Nuclear engineering Tan, Earn Tzeh Hardware Implementation Of Artificial Neural Network On FPGA For Sulfate-Reducing Bacteria |
| title | Hardware Implementation Of Artificial Neural Network On FPGA For Sulfate-Reducing Bacteria |
| title_full | Hardware Implementation Of Artificial Neural Network On FPGA For Sulfate-Reducing Bacteria |
| title_fullStr | Hardware Implementation Of Artificial Neural Network On FPGA For Sulfate-Reducing Bacteria |
| title_full_unstemmed | Hardware Implementation Of Artificial Neural Network On FPGA For Sulfate-Reducing Bacteria |
| title_short | Hardware Implementation Of Artificial Neural Network On FPGA For Sulfate-Reducing Bacteria |
| title_sort | hardware implementation of artificial neural network on fpga for sulfate reducing bacteria |
| topic | TK1-9971 Electrical engineering. Electronics. Nuclear engineering |
| url | http://eprints.usm.my/61074/1/24%20Pages%20from%2000001779827.pdf |
| work_keys_str_mv | AT tanearntzeh hardwareimplementationofartificialneuralnetworkonfpgaforsulfatereducingbacteria |