A novel ternary and signum kernelled linear hexadecimal pattern and hybrid feature selection based environmental sound classification method

Abstract

Environmental sound classification (ESC) is one of the fundamental study areas for digital forensics and machine learning. A novel textural feature extractor which is ternary and signum kernelled linear hexadecimal pattern (TSK-LHP) is presented as feature extractor. Multileveled feature extraction method is used and levels are created by discrete wavelet transform (DWT). TSK-LHP generates features from each level. The most distinctive ones are selected by using hybrid feature selector. This hybrid feature selector uses neighborhood component analysis (NCA) and principle component analysis (PCA) together. Therefore, it is called as NPCA. A novel ESC dataset was collected for testing and there are 1211 sounds with 25 classes in this dataset. The proposed method is tested by using four shallow classifiers which are decision tree (DT), linear discriminant (LD), support vector machine (SVM), k nearest neighbor (kNN) and bagged tree (BT). Our proposed method achieved 99.83%, 100.0%, 99.17%, 93.64% and 98.35% classification accuracies by using these classifiers respectively.