Convolutional Neural Networks for 1-D Many-Channel Data

Abstract

Deep convolutional neural networks (CNNs) represent the state of the art in image recognition. The same properties that led to their success in that domain allow them to be applied to superficially very different problems with minimal modification. In this work, we have modified a simple CNN, originally written to classify digits in the MNIST database (28 28 pixels, 1 channel), for use on 1-D acoustic data taken from experiments focused on crack detection (8,000 data points, 72 channels). Though the models predictive ability is limited to fitting the trend, its partial success suggests that the application of convolutional networks to novel domains deserves further attention.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jun 01, 2018
Accession Number
AD1052801

Entities

People

  • Eliseo Iglesias
  • John S. Hyatt
  • Michael D Lee

Organizations

  • United States Army Research Laboratory

Tags

Communities of Interest

  • Sensors

DTIC Thesaurus Topics

  • Acoustic Measurement
  • Acoustic Signals
  • Actuators
  • Algorithms
  • Artificial Intelligence Software
  • Artificial Neural Networks
  • Convolutional Neural Networks
  • Crack Propagation
  • Data Science
  • Data Set
  • Data Sets
  • Databases
  • Deep Learning
  • Detection
  • Digital Data
  • Frequency
  • Image Recognition
  • Images
  • Information Science
  • Learning
  • Machine Learning
  • Measurement
  • Metal Plates
  • Military Research
  • Neural Networks
  • Probability
  • Recognition
  • Standards
  • Training
  • Two Dimensional

Fields of Study

  • Computer science

Readers

  • Calculus or Mathematical Analysis
  • Neural Network Machine Learning.

Technology Areas

  • AI & ML
  • AI & ML - Neural Networks