Real time classification analysis in distributed acoustic sensing systems
| Autor: | Metin Aktas, Toygar Akgun, Hakan Maral |
|---|---|
| Rok vydání: | 2018 |
| Předmět: |
Network architecture
Artificial neural network Computer science business.industry Deep learning 02 engineering and technology Distributed acoustic sensing computer.software_genre Convolutional neural network 020210 optoelectronics & photonics 0202 electrical engineering electronic engineering information engineering Data mining Artificial intelligence Real time classification business computer Selection (genetic algorithm) |
| Zdroj: | SIU |
| DOI: | 10.1109/siu.2018.8404682 |
| Popis: | In this paper, we present a real time treat classification approach to be used in a distributed acoustic sensing system that is developed for monitoring linear assets with a maximum length of 50 kms. The Convolutional Neuaral Network (CNN) based deep learning approach is used for treat classification. The classification accuracies and execution times for neural networks with different architecture and complexity are measured. The proposed approach for classifying all the detected treats without decreasing the detection accuracy is introduced. The maximum allowable execution time for the network structure that is appropriate for the proposed approach is analyzed for the worst case scenario. Hence, the most appropriate network architecture selection can be performed based on classification accuracy and also applicability in real-time criterion. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|