Matches in SemOpenAlex for { <https://semopenalex.org/work/W4366979730> ?p ?o ?g. }
Showing items 1 to 60 of
60
with 100 items per page.
- W4366979730 abstract "Acoustic signals in complex real-world environments are randomized by processes such as multipath reflections, surface scattering, and volume scattering by turbulence and vegetation. Traditional machine learning classification algorithms require large datasets with substantial variation to mitigate the challenge posed by randomized signals. In this paper, a Bayesian classifier is introduced that incorporates the underlying physics of the scattered signal into a realistic likelihood distribution for the random signal variations. Performance of the Bayesian classifier is compared to machine learning classification algorithms based on two convolutional neural networks (CNN), one for images and one for sound. Given the varying architectures of the three classification algorithms each approach requires a different feature set. The image-based CNN uses a spectrogram as the input, the soundbased CNN uses the normalized waveform, and the Bayesian classifier is developed on features given by the power in the one-third octave bands. For the comparison, we employ the acoustic seismic classification identification data set (ACIDS) and the environmental sound classification data set (ESC-50). To account for the small size of the considered data sets, we use transfer learning for the machine learning classification algorithms. For the ACIDS and ESC-50 data sets, we show that the Bayesian classifier method outperforms the image-based CNN and the sound-based CNN when measured by accuracy on a test set of data. Unlike the physics-based Bayesian classifier, the machine learning algorithms do not take advantage of the underlying physics of the acoustic signal, which impacts the classification accuracy of traditional machine learning approaches." @default.
- W4366979730 created "2023-04-27" @default.
- W4366979730 creator A5045779683 @default.
- W4366979730 creator A5066313662 @default.
- W4366979730 creator A5088096640 @default.
- W4366979730 date "2023-06-14" @default.
- W4366979730 modified "2023-09-25" @default.
- W4366979730 title "Comparing a Bayesian classifier for acoustic signals to machine-learning classifiers" @default.
- W4366979730 doi "https://doi.org/10.1117/12.2663959" @default.
- W4366979730 hasPublicationYear "2023" @default.
- W4366979730 type Work @default.
- W4366979730 citedByCount "0" @default.
- W4366979730 crossrefType "proceedings-article" @default.
- W4366979730 hasAuthorship W4366979730A5045779683 @default.
- W4366979730 hasAuthorship W4366979730A5066313662 @default.
- W4366979730 hasAuthorship W4366979730A5088096640 @default.
- W4366979730 hasConcept C107673813 @default.
- W4366979730 hasConcept C115961682 @default.
- W4366979730 hasConcept C119857082 @default.
- W4366979730 hasConcept C12267149 @default.
- W4366979730 hasConcept C139532973 @default.
- W4366979730 hasConcept C153180895 @default.
- W4366979730 hasConcept C154945302 @default.
- W4366979730 hasConcept C169258074 @default.
- W4366979730 hasConcept C41008148 @default.
- W4366979730 hasConcept C45273575 @default.
- W4366979730 hasConcept C52001869 @default.
- W4366979730 hasConcept C75294576 @default.
- W4366979730 hasConcept C81363708 @default.
- W4366979730 hasConcept C95623464 @default.
- W4366979730 hasConceptScore W4366979730C107673813 @default.
- W4366979730 hasConceptScore W4366979730C115961682 @default.
- W4366979730 hasConceptScore W4366979730C119857082 @default.
- W4366979730 hasConceptScore W4366979730C12267149 @default.
- W4366979730 hasConceptScore W4366979730C139532973 @default.
- W4366979730 hasConceptScore W4366979730C153180895 @default.
- W4366979730 hasConceptScore W4366979730C154945302 @default.
- W4366979730 hasConceptScore W4366979730C169258074 @default.
- W4366979730 hasConceptScore W4366979730C41008148 @default.
- W4366979730 hasConceptScore W4366979730C45273575 @default.
- W4366979730 hasConceptScore W4366979730C52001869 @default.
- W4366979730 hasConceptScore W4366979730C75294576 @default.
- W4366979730 hasConceptScore W4366979730C81363708 @default.
- W4366979730 hasConceptScore W4366979730C95623464 @default.
- W4366979730 hasLocation W43669797301 @default.
- W4366979730 hasOpenAccess W4366979730 @default.
- W4366979730 hasPrimaryLocation W43669797301 @default.
- W4366979730 hasRelatedWork W2041636156 @default.
- W4366979730 hasRelatedWork W2508925980 @default.
- W4366979730 hasRelatedWork W2539163683 @default.
- W4366979730 hasRelatedWork W2964383635 @default.
- W4366979730 hasRelatedWork W2979979539 @default.
- W4366979730 hasRelatedWork W2999842097 @default.
- W4366979730 hasRelatedWork W3127425528 @default.
- W4366979730 hasRelatedWork W3168994312 @default.
- W4366979730 hasRelatedWork W3193301557 @default.
- W4366979730 hasRelatedWork W4311106074 @default.
- W4366979730 isParatext "false" @default.
- W4366979730 isRetracted "false" @default.
- W4366979730 workType "article" @default.