Search for: All records

This paper introduces a feature extraction technique that identifies highly informative features from sonar magnitude spectra for automated target classification. The approach involves creating feature representations through convolution of a two-dimensional Gabor wavelet and acoustic color magnitudes to capture elastic waves. This feature representation contains extracted localized features in the form of Gabor stripes, which are representative of unique targets and are invariant of target aspect angle. Further processing removes non-informative features through a threshold-based culling. This paper presents an approach that begins connecting model-based domain knowledge with machine learning techniques to allow interpretation of the extracted features while simultaneously enabling robust target classification. The relative performance of three supervised machine learning classifiers, specifically a support vector machine, random forest, and feed-forward neural network are used to quantitatively demonstrate the representations' informationally rich extracted features. Classifiers are trained and tested with acoustic color spectrograms and features extracted using the algorithm, interpreted as stripes, from two public domain field datasets. An increase in classification performance is generally seen, with the largest being a 47% increase from the random forest tree trained on the 1–31 kHz PondEx10 data, suggesting relatively small datasets can achieve high classification accuracy if model-cognizant feature extraction is utilized. 

In this work, we present peak-cognizant quantification of environmental weathering of crude oil from the from the Deepwater Horizon oil spill. The key idea is to autonomously extract peak information from raw gas chromatography-mass spectrometry (GC-MS) signals from crude oil samples, and represent the relative weathering of different peaks in a graph-based quantitative computational framework. We also present results from pre-processing the raw signals with baseline correction and signal normalization. Retention time alignment is performed by first aligning the source oil by determining the retention time drift between prominent peaks within the signals and applying the calculated drift to the weathered oil samples. Peak finding, validation, and grouping of the five weathered oil samples to a source oil sample allows compound associations to be discovered. We present preliminary results as graphical visualizations allowing for rapid and precise interpretation of weathering compounds within polycyclic aromatic hydrocarbons (PAH). Results presented were generated with oil samples showing different degrees of weathering collected from the Deepwater Horizon spill.