Level crossing control: a novel method using sound recognition

• Main Authors: Alim, Sabur Ajibola, Alang Md Rashid, Nahrul Khair, Rahman , Md Mozasser
• Format: Article
• Language: English
• Published: Chulalongkorn University 2013
• Subjects: TK7800 Electronics. Computer engineering. Computer hardware. Photoelectronic devices
• Online Access: http://irep.iium.edu.my/31232/1/Alim_2.pdf; http://irep.iium.edu.my/31232/; http://engj.org/index.php/ej/article/view/364
• Institution: Universiti Islam Antarabangsa Malaysia

The level crossing (LX) or railway crossing being an intersection between a public road and a railway line, can be controlled actively or passively. Sound recognition can be used to actively control a level crossing. A system is proposed in this study for the use of sound to control a LX. This proposed system uses Mel Frequency Cepstral Coefficient (MFCC) as feature extractor, and Recurrent Neural Network (RNN) as classifier. The proposed system has shown a great potential that could be harnessed to contribute to the reduction in the loss of lives and properties at the LX.