Classification of Complicated Urban Forest Acoustic Scenes with Deep Learning Models

Abstract

The use of passive acoustic monitoring (PAM) can compensate for the shortcomings of traditional survey methods on spatial and temporal scales and achieve all-weather and wide-scale assessment and prediction of environmental dynamics. Assessing the impact of human activities on biodiversity by analyzing the characteristics of acoustic scenes in the environment is a frontier hotspot in urban forestry. However, with the accumulation of monitoring data, the selection and parameter setting of the deep learning model greatly affect the content and efficiency of sound scene classification. This study compared and evaluated the performance of different deep learning models for acoustic scene classification based on the recorded sound data from Guangzhou urban forest. There are seven categories of acoustic scenes for classification: human sound, insect sound, bird sound, bird–human sound, insect–human sound, bird–insect sound, and silence. A dataset containing seven acoustic scenes was constructed, with 1000 samples for each scene. The requirements of the deep learning models on the training data volume and training epochs in the acoustic scene classification were evaluated through several sets of comparison experiments, and it was found that the models were able to achieve satisfactory accuracy when the training sample data volume for a single category was 600 and the training epochs were 100. To evaluate the generalization performance of different models to new data, a small test dataset was constructed, and multiple trained models were used to make predictions on the test dataset. All experimental results showed that the DenseNet_BC_34 model performs best among the comparison models, with an overall accuracy of 93.81% for the seven acoustic scenes on the validation dataset. This study provides practical experience for the application of deep learning techniques in urban sound monitoring and provides new perspectives and technical support for further exploring the relationship between human activities and biodiversity.

YOLOv8-RMDA: Lightweight YOLOv8 Network for Early Detection of Small Target Diseases in Tea

“…The enhancement and application of deep learning networks have practical importance for detection tasks in various intricate practical environments [32]. This study introduces enhancements based on YOLOv8 to effectively detect small targets of early tea diseases in complex scenarios.…”

Soundscape Characterization Using Autoencoders and Unsupervised Learning

“…For instance, Dufourq et al [ 13 ] employed transfer learning to adapt existing Convolutional Neural Networks (CNNs) for bioacoustic classification. Furthermore, architectures such as ResNet, EfficientNet, MobileNet, and DesNet have been deployed to accurately identify acoustic scenes involving humans, birds, insects, and silence [ 14 ], and the MobileNetV2 architecture has been successfully employed for classifying biophonies, geophonies, anthropophonies, and silence [ 1 ]. These advancements underscore the growing contribution of machine learning to advance our understanding of acoustic environments.…”

Forest Sound Classification Dataset: FSC22

“…Several investigations have been carried out with different techniques in the context of a forest monitoring system to protect forest reserves. For example, prior studies have experimented with different sound classification approaches for the recognition of various species and possible forest threats such as illegal logging, poaching, and wildfire [ 1 , 2 , 3 , 4 , 5 ]. In such systems, environmental sounds are captured, processed using a modelling algorithm, and classified into different sound classes.…”