Explainable automated anuran sound classification using improved one-dimensional local binary pattern and Tunable Q Wavelet Transform techniques

被引:11
作者
Akbal, Erhan [1 ]
Barua, Prabal Datta [2 ,3 ,4 ,5 ,6 ,7 ,8 ,9 ,10 ]
Dogan, Sengul [1 ]
Tuncer, Turker [1 ]
Acharya, U. Rajendra [11 ]
机构
[1] Firat Univ, Coll Technol, Dept Digital Forens Engn, TR-23119 Elazig, Turkiye
[2] Cogninet Australia, Sydney, NSW 2010, Australia
[3] Univ Southern Queensland, Sch Business Informat Syst, Darling Hts, Qld, Australia
[4] Univ Technol Sydney, Fac Engn & Informat Technol, Sydney, NSW 2007, Australia
[5] Australian Int Inst Higher Educ, Sydney, NSW 2000, Australia
[6] Univ New England, Sch Sci & Technol, Armidale, NSW, Australia
[7] Taylors Univ, Sch Biosci, Subang Jaya, Malaysia
[8] SRM Inst Sci & Technol, Sch Comp, Chennai, India
[9] Kumamoto Univ, Sch Sci & Technol, Kumamoto, Japan
[10] Univ Sydney, Sydney Sch Educ & Social Work, Camperdown, NSW, Australia
[11] Univ Southern Queensland, Sch Math Phys & Comp, Springfield, Australia
关键词
Anuran sound classification; Bioacoustics; Machine learning; Improved local binary pattern; Feature engineering; ACOUSTIC IDENTIFICATION; RECOGNITION; FEATURES;
D O I
10.1016/j.eswa.2023.120089
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Classification of animal species using animal sounds is a critical issue for bioacoustics work. Especially the determination of anurans (frogs or toads) species can be used as an indicator of climate change. However, counting and classifying anurans in their natural habitat is challenging. Therefore, computer-assisted intelligent systems must be used to determine anuran types correctly. This work collected a new anuran sound dataset and proposed a hand-modeled sound classification system. The collected dataset contains 1536 anuran sounds belonging to 26 anuran species. Furthermore, an improved one-dimensional local binary pattern (1D-LBP) and Tunable Q Wavelet Transform (TQWT) based feature extraction method has been proposed to generate features at both frequency and space domains. Our proposed hand-modeled anuran sound classification architecture comprises of feature extractor (TQWT + improved 1D-LBP), iterative neighborhood component analysis (INCA) selector and k nearest neighbor (kNN) classifier. Our proposed 1D-LBP and TQWT-based anuran sound classi-fication model has obtained a classification accuracy of 99.35% in classifying 26 anuran species. Moreover, we discussed explainable results. In the future, we plan to validate this work by increasing more species in each group.
引用
收藏
页数:15
相关论文
共 66 条
[1]  
Alabi M, 2021, Arxiv, DOI arXiv:2112.05148
[2]   Automatic anuran identification using noise removal and audio activity detection [J].
Alonso, Jesus B. ;
Cabrera, Josue ;
Shyamnani, Rohit ;
Travieso, Carlos M. ;
Bolanos, Federico ;
Garcia, Adrian ;
Villegas, Alexander ;
Wainwright, Mark .
EXPERT SYSTEMS WITH APPLICATIONS, 2017, 72 :83-92
[3]   Advance in the bat acoustic identification systems based on the audible spectrum using nonlinear dynamics characterization [J].
Alonso, Jesus B. ;
Henriquez, Aaron ;
Henriquez, Patricia ;
Rodriguez-Herrera, Bernal ;
Bolanos, Federico ;
Alpizar, Priscilla ;
Travieso, Carlos M. ;
Cabrera, Josue .
EXPERT SYSTEMS WITH APPLICATIONS, 2015, 42 (24) :9528-9538
[4]  
AmphibiaWeb, 2020, US, V10
[5]  
[Anonymous], 2020, US, V1
[6]   An accurate valvular heart disorders detection model based on a new dual symmetric tree pattern using stethoscope sounds [J].
Barua, Prabal Datta ;
Karasu, Mehdi ;
Kobat, Mehmet Ali ;
Balik, Yunus ;
Kivrak, Tarik ;
Baygin, Mehmet ;
Dogan, Sengul ;
Demir, Fahrettin Burak ;
Tuncer, Turker ;
Tan, Ru-San ;
Acharya, U. Rajendra .
COMPUTERS IN BIOLOGY AND MEDICINE, 2022, 146
[7]   Novel automated PD detection system using aspirin pattern with EEG signals [J].
Barua, Prabal Datta ;
Dogan, Sengul ;
Tuncer, Turker ;
Baygin, Mehmet ;
Acharya, U. Rajendra .
COMPUTERS IN BIOLOGY AND MEDICINE, 2021, 137
[8]   Automatic recognition of anuran species based on syllable identification [J].
Bedoya, Carol ;
Isaza, Claudia ;
Daza, Juan M. ;
Lopez, Jose D. .
ECOLOGICAL INFORMATICS, 2014, 24 :200-209
[9]  
Cai JH, 2007, PROCEEDINGS OF THE 2007 INTERNATIONAL CONFERENCE ON INTELLIGENT SENSORS, SENSOR NETWORKS AND INFORMATION PROCESSING, P293
[10]   Effect of multiple stressors and population decline of frogs [J].
Carrasco, Guilherme Henrique ;
de Souza, Marcelino Benvindo ;
de Souza Santos, Lia Raquel .
ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH, 2021, 28 (42) :59519-59527