Utilizing Artificial Neural Network to Model Sound for Virtual Landmine Detection Training


Sound is the only information a soldier can get from a landmine detector to judge the landmine location and type. Therefore, it is imperative that a Virtual Landmine Detection Training System can replicate the sound in a realistic manner. To study the characteristics of different landmine targets and to devise a mathematical model for sound estimation and generation, several different sound datasets for various targets have been collected. Each dataset contains about 500 instances, each representing a different radius and height of the detector head from the target. In this paper, a Multilayer Perceptrons (MLP) Artificial Neural Network (ANN) utilizing supervised back propagation is implemented to represent the sound model. Neural networks including a particle swarm optimization (PSO) based neural network and a genetic algorithm (GA) based neural network are applied to the datasets in order to obtain a good mathematical model for sound generation. The Mean Squared Error (MSE) resulted from the different methods is compared with each other, and it is shown that PSO based neural network has the least MSE.

  • Abstract
  • Keywords
  • 1. Introduction
  • 2. System Overview
  • 3. Sound Modeling
  • 4. Sound Data Collection
  • 5. Sound Amplitude Data Preprocessing
  • 6. Utilizing Artifical Neural Network (ANN) for Sound Data Analysis
  • 7. Results and Discussion
  • 8. Conclusion
  • Acknowlegement
  • References

Related Content

Customize your page view by dragging and repositioning the boxes below.

Related Journal Articles
Related eBook Content
Topic Collections

Sorry! You do not have access to this content. For assistance or to subscribe, please contact us:

  • TELEPHONE: 1-800-843-2763 (Toll-free in the USA)
  • EMAIL: asmedigitalcollection@asme.org
Sign In