Roberto Benocci, Andrea Potenza, Giovanni Zambon, Andrea Afify, H. Eduardo Roman
{"title":"Data Augmentation to Improve the Soundscape Ranking Index Prediction","authors":"Roberto Benocci, Andrea Potenza, Giovanni Zambon, Andrea Afify, H. Eduardo Roman","doi":"10.37394/232015.2023.19.85","DOIUrl":null,"url":null,"abstract":"Predicting the sound quality of an environment represents an important task especially in urban parks where the coexistence of sources of anthropic and biophonic nature produces complex sound patterns. To this end, an index has been defined by us, denoted as soundscape ranking index (SRI), which assigns a positive weight to natural sounds (biophony) and a negative one to anthropogenic sounds. A numerical strategy to optimize the weight values has been implemented by training two machine learning algorithms, the random forest (RF) and the perceptron (PPN), over an augmented data-set. Due to the availability of a relatively small fraction of labelled recorded sounds, we employed Monte Carlo simulations to mimic the distribution of the original data-set while keeping the original balance among the classes. The results show an increase in the classification performance. We discuss the issues that special care needs to be addressed when the augmented data are based on a too small original data-set.","PeriodicalId":53713,"journal":{"name":"WSEAS Transactions on Environment and Development","volume":"1 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2023-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"WSEAS Transactions on Environment and Development","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.37394/232015.2023.19.85","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"Social Sciences","Score":null,"Total":0}
引用次数: 0
Abstract
Predicting the sound quality of an environment represents an important task especially in urban parks where the coexistence of sources of anthropic and biophonic nature produces complex sound patterns. To this end, an index has been defined by us, denoted as soundscape ranking index (SRI), which assigns a positive weight to natural sounds (biophony) and a negative one to anthropogenic sounds. A numerical strategy to optimize the weight values has been implemented by training two machine learning algorithms, the random forest (RF) and the perceptron (PPN), over an augmented data-set. Due to the availability of a relatively small fraction of labelled recorded sounds, we employed Monte Carlo simulations to mimic the distribution of the original data-set while keeping the original balance among the classes. The results show an increase in the classification performance. We discuss the issues that special care needs to be addressed when the augmented data are based on a too small original data-set.
期刊介绍:
WSEAS Transactions on Environment and Development publishes original research papers relating to the studying of environmental sciences. We aim to bring important work to a wide international audience and therefore only publish papers of exceptional scientific value that advance our understanding of these particular areas. The research presented must transcend the limits of case studies, while both experimental and theoretical studies are accepted. It is a multi-disciplinary journal and therefore its content mirrors the diverse interests and approaches of scholars involved with sustainable development, climate change, natural hazards, renewable energy systems and related areas. We also welcome scholarly contributions from officials with government agencies, international agencies, and non-governmental organizations.