Multileveled ternary pattern and iterative ReliefF based bird sound classification

Birds may need to be identified for purposes such as environmental monitoring, follow-up, and species detection in the ecological area. Automatic sound classifiers have been used to perform species detection. Many methods have been presented in the literature to classify bird sounds with high accuracy. Nowadays, deep learning models have been used to classify data with high classification accuracy. However, these networks have high computational complexity. To obtain a highly accurate and lightweight classification model, a new multileveled and handcrafted features based machine learning model is presented. The presented automated bird sound classification model uses the multileveled ternary pattern (TP) feature generation, feature selection, and classification phases. The multileveled feature generation network can reach high classification accuracies since they generate high-level, low-level, and mid-level features. To construct levels, discrete wavelet transform (DWT) is employed to use the effectiveness of the DWT in bird sound classification. An improved version of the ReliefF, which is iterative ReliefF (IRF), is considered as feature selector. IRF selects the most informative features automatically, and these features are operated on linear discriminant (LD), k nearest neighbor (kNN), bagged tree (BT), and support vector machine (SVM) classifiers to calculate results of variable classifiers. The proposed multilevel TP and IRF based bird sound classification method reached 96.67% accuracy by using SVM on the 18 classes bird sound dataset.