Conference proceeding
Feature Engineering and Interpretation of Active Sonar Data Using Geometric Wavelets and Support Vector Machines
OCEANS 2021: San Diego – Porto, pp.1-5
09/20/2021
DOI: 10.23919/OCEANS44145.2021.9705879
Abstract
This paper presents initial findings in exploring the learned weights of support vector machines trained and tested on experimental active sonar field data in both unfiltered and geometrically filtered cases. A two-dimensional Gabor wavelet is used as the filter, applied through convolution, to three different contacts or targets. After training the support vector machine, the learned weights are extracted and multiplied by the input vectors, then summed pixel-by-pixel to gain insight on the classifiers choices. Two domains, ping versus time and ping versus frequency, are considered. The largest increase in classification accuracy seen is 9.17% when training and testing on the ping versus time case due to the smoothing features ping to ping.
Details
- Title: Subtitle
- Feature Engineering and Interpretation of Active Sonar Data Using Geometric Wavelets and Support Vector Machines
- Creators
- Betnice Kubicek - University of Iowa,Electrical and Computer Engineering,Iowa City,IA,United StatesAnanya Sen Gupta - University of Iowa,Electrical and Computer Engineering,Iowa City,IA,United StatesIvars Kirsteins - Naval Undersea Warfare Center,Newport,RI,United States
- Resource Type
- Conference proceeding
- Publication Details
- OCEANS 2021: San Diego – Porto, pp.1-5
- DOI
- 10.23919/OCEANS44145.2021.9705879
- Publisher
- MTS
- Grant note
- Office of Naval Research (10.13039/100000006)
- Language
- English
- Date published
- 09/20/2021
- Academic Unit
- Electrical and Computer Engineering
- Record Identifier
- 9984217410802771
Metrics
7 Record Views