DETONATION CLASSIFICATION FROM ACOUSTIC SIGNATURE WITH THE RESTRICTED BOLTZMANN MACHINE

作者：Bengio Yoshua^*; Chapados Nicolas; Delalleau Olivier; Larochelle Hugo; Saint Mleux Xavier; Hudon Christian; Louradour Jerome

来源：Computational Intelligence, 2012, 28(2): 261-288.

DOI：10.1111/j.1467-8640.2012.00419.x

• discriminative restricted Boltzmann machine
• support vector machine
• detonation classification

We compare the recently proposed Discriminative Restricted Boltzmann Machine (DRBM) to the classical Support Vector Machine (SVM) on a challenging classification task consisting in identifying weapon classes from audio signals. The three weapon classes considered in this work (mortar, rocket, and rocket-propelled grenade), are difficult to reliably classify with standard techniques because they tend to have similar acoustic signatures. In addition, specificities of the data available in this study make it challenging to rigorously compare classifiers, and we address methodological issues arising from this situation. Experiments show good classification accuracy that could make these techniques suitable for fielding on autonomous devices. DRBMs appear to yield better accuracy than SVMs, and are less sensitive to the choice of signal preprocessing and model hyperparameters. This last property is especially appealing in such a task where the lack of data makes model validation difficult.

• 出版日期2012-5