Connectogram - A graph-based time dependent representation for sounds
dc.contributor.author | Turker, Ilker | |
dc.contributor.author | Aksu, Serkan | |
dc.date.accessioned | 2024-09-29T15:54:56Z | |
dc.date.available | 2024-09-29T15:54:56Z | |
dc.date.issued | 2022 | |
dc.department | Karabük Üniversitesi | en_US |
dc.description.abstract | The proposed method contributes the time-series classification literature with a novel time-convexity based representation, which extends the current graph conversion approaches by introducing the time dimension, also introducing a colorful graph-generator approach. The representation capability of connectograms is tested in comparison with mel-spectrograms (mels) and MFCCs for an environmental sound classification task, as input to state-of-art transfer learning models. Results indicate that connectograms cannot compete with the best-performer mel-spectrogram representations in standalone format, however they significantly improve their classification performance in case they are combined as single layers of hybrid RGB representations. A combination of [mels + mels + connectogram] outperforms either sole representations or their combinations by 2-3%, with 96.46% classification accuracy for ResNet50 classifier model.(c) 2022 Elsevier Ltd. All rights reserved. | en_US |
dc.identifier.doi | 10.1016/j.apacoust.2022.108660 | |
dc.identifier.issn | 0003-682X | |
dc.identifier.issn | 1872-910X | |
dc.identifier.scopus | 2-s2.0-85124610723 | en_US |
dc.identifier.scopusquality | Q1 | en_US |
dc.identifier.uri | https://doi.org/10.1016/j.apacoust.2022.108660 | |
dc.identifier.uri | https://hdl.handle.net/20.500.14619/4373 | |
dc.identifier.volume | 191 | en_US |
dc.identifier.wos | WOS:000783173100007 | en_US |
dc.identifier.wosquality | Q1 | en_US |
dc.indekslendigikaynak | Web of Science | en_US |
dc.indekslendigikaynak | Scopus | en_US |
dc.language.iso | en | en_US |
dc.publisher | Elsevier Sci Ltd | en_US |
dc.relation.ispartof | Applied Acoustics | en_US |
dc.relation.publicationcategory | Makale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı | en_US |
dc.rights | info:eu-repo/semantics/closedAccess | en_US |
dc.subject | Graph representation | en_US |
dc.subject | Sound classification | en_US |
dc.subject | Time-series classification | en_US |
dc.subject | Complex networks | en_US |
dc.subject | Deep learning | en_US |
dc.subject | Machine learning | en_US |
dc.title | Connectogram - A graph-based time dependent representation for sounds | en_US |
dc.type | Article | en_US |