eprintid: 14280 rev_number: 15 eprint_status: archive userid: 2 dir: disk0/00/01/42/80 datestamp: 2024-09-19 23:30:12 lastmod: 2024-09-19 23:30:13 status_changed: 2024-09-19 23:30:12 type: article metadata_visibility: show creators_name: Shaikh, Asadullah creators_name: Baowaly, Mrinal Kanti creators_name: Sarkar, Bisnu Chandra creators_name: Walid, Md. Abul Ala creators_name: Ahamad, Md. Martuza creators_name: Singh, Bikash Chandra creators_name: Silva Alvarado, Eduardo René creators_name: Ashraf, Imran creators_name: Samad, Md. Abdus creators_id: creators_id: creators_id: creators_id: creators_id: creators_id: creators_id: eduardo.silva@funiber.org creators_id: creators_id: title: Deep transfer learning-based bird species classification using mel spectrogram images ispublished: pub subjects: uneat_eng divisions: uneatlantico_produccion_cientifica divisions: uninimx_produccion_cientifica divisions: uniromana_produccion_cientifica full_text_status: public abstract: The classification of bird species is of significant importance in the field of ornithology, as it plays an important role in assessing and monitoring environmental dynamics, including habitat modifications, migratory behaviors, levels of pollution, and disease occurrences. Traditional methods of bird classification, such as visual identification, were time-intensive and required a high level of expertise. However, audio-based bird species classification is a promising approach that can be used to automate bird species identification. This study aims to establish an audio-based bird species classification system for 264 Eastern African bird species employing modified deep transfer learning. In particular, the pre-trained EfficientNet technique was utilized for the investigation. The study adapts the fine-tune model to learn the pertinent patterns from mel spectrogram images specific to this bird species classification task. The fine-tuned EfficientNet model combined with a type of Recurrent Neural Networks (RNNs) namely Gated Recurrent Unit (GRU) and Long short-term memory (LSTM). RNNs are employed to capture the temporal dependencies in audio signals, thereby enhancing bird species classification accuracy. The dataset utilized in this work contains nearly 17,000 bird sound recordings across a diverse range of species. The experiment was conducted with several combinations of EfficientNet and RNNs, and EfficientNet-B7 with GRU surpasses other experimental models with an accuracy of 84.03% and a macro-average precision score of 0.8342. date: 2024-08 publication: PLOS ONE volume: 19 number: 8 pagerange: e0305708 id_number: doi:10.1371/journal.pone.0305708 refereed: TRUE issn: 1932-6203 official_url: http://doi.org/10.1371/journal.pone.0305708 access: open language: en citation: Artículo Materias > Ingeniería Universidad Europea del Atlántico > Investigación > Producción Científica Universidad Internacional Iberoamericana México > Investigación > Artículos y libros Universidad de La Romana > Investigación > Producción Científica Abierto Inglés The classification of bird species is of significant importance in the field of ornithology, as it plays an important role in assessing and monitoring environmental dynamics, including habitat modifications, migratory behaviors, levels of pollution, and disease occurrences. Traditional methods of bird classification, such as visual identification, were time-intensive and required a high level of expertise. However, audio-based bird species classification is a promising approach that can be used to automate bird species identification. This study aims to establish an audio-based bird species classification system for 264 Eastern African bird species employing modified deep transfer learning. In particular, the pre-trained EfficientNet technique was utilized for the investigation. The study adapts the fine-tune model to learn the pertinent patterns from mel spectrogram images specific to this bird species classification task. The fine-tuned EfficientNet model combined with a type of Recurrent Neural Networks (RNNs) namely Gated Recurrent Unit (GRU) and Long short-term memory (LSTM). RNNs are employed to capture the temporal dependencies in audio signals, thereby enhancing bird species classification accuracy. The dataset utilized in this work contains nearly 17,000 bird sound recordings across a diverse range of species. The experiment was conducted with several combinations of EfficientNet and RNNs, and EfficientNet-B7 with GRU surpasses other experimental models with an accuracy of 84.03% and a macro-average precision score of 0.8342. metadata Shaikh, Asadullah; Baowaly, Mrinal Kanti; Sarkar, Bisnu Chandra; Walid, Md. Abul Ala; Ahamad, Md. Martuza; Singh, Bikash Chandra; Silva Alvarado, Eduardo René; Ashraf, Imran y Samad, Md. Abdus mail SIN ESPECIFICAR, SIN ESPECIFICAR, SIN ESPECIFICAR, SIN ESPECIFICAR, SIN ESPECIFICAR, SIN ESPECIFICAR, eduardo.silva@funiber.org, SIN ESPECIFICAR, SIN ESPECIFICAR (2024) Deep transfer learning-based bird species classification using mel spectrogram images. PLOS ONE, 19 (8). e0305708. ISSN 1932-6203 document_url: http://repositorio.unini.edu.mx/id/eprint/14280/1/journal.pone.0305708.pdf