Acoustic classification of frogs has gotten a lot of attention recently due to its potential applicability in ecological investigations. Numerous studies have been presented for identifying frog species, although the majority of recorded species are thought to be monotypic. The purpose of this study is to demonstrate a method for classifying various frog species using an audio recording. To be more exact, continuous frog recordings are cut into audio snippets first (10 seconds). Then, for each ten-second recording, several time-frequency representations are constructed. Following that, rather than using manually created features, Machine Learning methods are employed to classify the frog species. Data reduction techniques; Principal Component Analysis (PCA) and Independent Component Analysis (ICA) are used to extract the most important features before classification. Finally, to validate our classification accuracy, cross validation and prediction accuracy are used. Experimental results show that PCA extracted features that achieved better classification accuracy both with cross validation and prediction accuracy.
翻译:最近,青蛙的声学分类因其在生态调查中的潜在适用性而引起许多关注,已经为确定青蛙物种提出了许多研究,尽管大多数记录物种被认为是单一的。这项研究的目的是展示一种使用录音对各种青蛙物种进行分类的方法。更确切地说,先将连续青蛙记录切入音频片段(10秒),然后为每10秒记录制作若干时间频率表示。随后,采用机器学习方法而不是使用人工制作的特征来对青蛙物种进行分类。数据减少技术;主要成分分析(PCA)和独立成分分析(ICA)用于在分类前提取最重要的特征。最后,用于验证我们的分类准确性、交叉验证和预测准确性。实验结果显示,五氯苯甲醚提取的特征在交叉验证和预测准确性两方面都实现了更好的分类准确性。