Robust Forest Sound Classification Using Pareto-Mordukhovich Optimized MFCC in Environmental Monitoring
As a complex ecosystem composed of flora and fauna, the forest has always been vulnerable to threats. Previous researchers utilized environmental audio collections, such as the ESC-50 and UrbanSound8k datasets, as proximate representatives of sounds potentially present in forests. This study focuses...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10856116/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832540517724848128 |
|---|---|
| author | Ahmad Qurthobi Robertas Damasevicius Vytautas Barzdaitis Rytis Maskeliunas |
| author_facet | Ahmad Qurthobi Robertas Damasevicius Vytautas Barzdaitis Rytis Maskeliunas |
| author_sort | Ahmad Qurthobi |
| collection | DOAJ |
| description | As a complex ecosystem composed of flora and fauna, the forest has always been vulnerable to threats. Previous researchers utilized environmental audio collections, such as the ESC-50 and UrbanSound8k datasets, as proximate representatives of sounds potentially present in forests. This study focuses on the application of deep learning models for forest sound classification as an effort to establish an early threats detection system. The research evaluates the performance of several pre-trained deep learning models, including MobileNet, GoogleNet, and ResNet, on the limited FSC22 dataset, which consists of 2,025 forest sound recordings classified into 27 categories. To improve classification capabilities, the study introduces a hybrid model that combines neural network (CNN) with a Bidirectional Long-Short-Term Memory (BiLSTM) layer, designed to capture both spatial and temporal features of the sound data. The research also employs Pareto-Mordukhovich-optimized Mel Frequency Cepstral Coefficients (MFCC) for feature extraction, improving the representation of audio signals. Data augmentation and dimensionality reduction techniques were also explored to assess their impact on model performance. The results indicate that the proposed hybrid CNN-BiLSTM model significantly improved classification loss and accuracy scores compared to the standalone pre-trained models. GoogleNet, with an added BiLSTM layer and augmented data, achieved an average reduced loss score of 0.7209 and average accuracy of 0.7852, demonstrating its potential to classify forest sounds. Improvements in loss score and classification performance highlight the potential of hybrid models in environmental sound analysis, particularly in scenarios with limited data availability. |
| format | Article |
| id | doaj-art-329c4ca1b37b46faba4e2a1c1308a663 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-329c4ca1b37b46faba4e2a1c1308a6632025-02-05T00:01:02ZengIEEEIEEE Access2169-35362025-01-0113209232094410.1109/ACCESS.2025.353579610856116Robust Forest Sound Classification Using Pareto-Mordukhovich Optimized MFCC in Environmental MonitoringAhmad Qurthobi0https://orcid.org/0000-0003-3882-2897Robertas Damasevicius1https://orcid.org/0000-0001-9990-1084Vytautas Barzdaitis2Rytis Maskeliunas3https://orcid.org/0000-0002-2809-2213Faculty of Informatics, Kaunas University of Technology, Kaunas, LithuaniaDepartment of Applied Informatics, Center of Excellence Forest 4.0, Vytautas Magnus University, Kaunas, LithuaniaDepartment of Applied Informatics, Center of Excellence Forest 4.0, Vytautas Magnus University, Kaunas, LithuaniaFaculty of Informatics, Kaunas University of Technology, Kaunas, LithuaniaAs a complex ecosystem composed of flora and fauna, the forest has always been vulnerable to threats. Previous researchers utilized environmental audio collections, such as the ESC-50 and UrbanSound8k datasets, as proximate representatives of sounds potentially present in forests. This study focuses on the application of deep learning models for forest sound classification as an effort to establish an early threats detection system. The research evaluates the performance of several pre-trained deep learning models, including MobileNet, GoogleNet, and ResNet, on the limited FSC22 dataset, which consists of 2,025 forest sound recordings classified into 27 categories. To improve classification capabilities, the study introduces a hybrid model that combines neural network (CNN) with a Bidirectional Long-Short-Term Memory (BiLSTM) layer, designed to capture both spatial and temporal features of the sound data. The research also employs Pareto-Mordukhovich-optimized Mel Frequency Cepstral Coefficients (MFCC) for feature extraction, improving the representation of audio signals. Data augmentation and dimensionality reduction techniques were also explored to assess their impact on model performance. The results indicate that the proposed hybrid CNN-BiLSTM model significantly improved classification loss and accuracy scores compared to the standalone pre-trained models. GoogleNet, with an added BiLSTM layer and augmented data, achieved an average reduced loss score of 0.7209 and average accuracy of 0.7852, demonstrating its potential to classify forest sounds. Improvements in loss score and classification performance highlight the potential of hybrid models in environmental sound analysis, particularly in scenarios with limited data availability.https://ieeexplore.ieee.org/document/10856116/Forest soundsclassificationMordukhovich subdifferentialPareto optimization |
| spellingShingle | Ahmad Qurthobi Robertas Damasevicius Vytautas Barzdaitis Rytis Maskeliunas Robust Forest Sound Classification Using Pareto-Mordukhovich Optimized MFCC in Environmental Monitoring IEEE Access Forest sounds classification Mordukhovich subdifferential Pareto optimization |
| title | Robust Forest Sound Classification Using Pareto-Mordukhovich Optimized MFCC in Environmental Monitoring |
| title_full | Robust Forest Sound Classification Using Pareto-Mordukhovich Optimized MFCC in Environmental Monitoring |
| title_fullStr | Robust Forest Sound Classification Using Pareto-Mordukhovich Optimized MFCC in Environmental Monitoring |
| title_full_unstemmed | Robust Forest Sound Classification Using Pareto-Mordukhovich Optimized MFCC in Environmental Monitoring |
| title_short | Robust Forest Sound Classification Using Pareto-Mordukhovich Optimized MFCC in Environmental Monitoring |
| title_sort | robust forest sound classification using pareto mordukhovich optimized mfcc in environmental monitoring |
| topic | Forest sounds classification Mordukhovich subdifferential Pareto optimization |
| url | https://ieeexplore.ieee.org/document/10856116/ |
| work_keys_str_mv | AT ahmadqurthobi robustforestsoundclassificationusingparetomordukhovichoptimizedmfccinenvironmentalmonitoring AT robertasdamasevicius robustforestsoundclassificationusingparetomordukhovichoptimizedmfccinenvironmentalmonitoring AT vytautasbarzdaitis robustforestsoundclassificationusingparetomordukhovichoptimizedmfccinenvironmentalmonitoring AT rytismaskeliunas robustforestsoundclassificationusingparetomordukhovichoptimizedmfccinenvironmentalmonitoring |