arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.15360q-bio.QMcs.LGcs.SDeess.AS
收藏

所有阈值皆被排除:生物声学数据中叫声密度的直接估计

All Thresholds Barred: Direct Estimation of Call Density in Bioacoustic Data

Oregon State University(俄勒冈州立大学);Google Research(谷歌研究院)

Amanda K. Navine, Tom Denton, Matthew J. Weldy, Patrick J. Hart

AI总结:

本文提出直接估计生物声学数据中叫声密度的方法,通过贝叶斯推理获得正负类置信分数分布以预测位点密度,并在夏威夷鸟类数据上验证了其对分布偏移和分类器质量变化的鲁棒性。

摘要:

被动声学监测(PAM)研究会产生数千小时的音频,这些音频可用于监测特定动物种群、开展广泛的生物多样性调查、检测偷猎者等威胁等。用于物种识别的机器学习分类器正越来越多地被用于处理生物声学调查所产生的大量音频,从而加快分析速度并提高PAM作为管理工具的实用性。在常见实践中,会对分类器输出分数施加一个阈值,高于该阈值的分数被汇总为检测计数。阈值的选择会产生有偏差的发声计数,这些计数受到假阳性/假阴性率的影响,而这些比率可能在数据集的各个子集之间有所不同。在这项工作中,我们主张直接估计叫声密度:即包含目标发声的检测窗口所占的比例,而不考虑分类器分数。我们的方法针对的是一个理想的生态学估计量,并为识别由分布偏移——即数据分布的定义特征发生变化时——所引发的核心问题以及设计缓解这些问题的策略提供了更严格的基础。我们提出了一种用于估计一批数据中叫声密度的验证方案,并通过贝叶斯推理获得了正类和负类置信分数的概率分布。我们利用这些分布来预测位点级别的密度,这些密度可能受到分布偏移的影响。我们在夏威夷鸟类的真实世界研究上测试了我们提出的方法,并利用现有的完全标注数据集提供了模拟结果,证明了该方法对叫声密度变化和分类器模型质量的鲁棒性。

英文摘要:

Passive acoustic monitoring (PAM) studies generate thousands of hours of audio, which may be used to monitor specific animal populations, conduct broad biodiversity surveys, detect threats such as poachers, and more. Machine learning classifiers for species identification are increasingly being used to process the vast amount of audio generated by bioacoustic surveys, expediting analysis and increasing the utility of PAM as a management tool. In common practice, a threshold is applied to classifier output scores, and scores above the threshold are aggregated into a detection count. The choice of threshold produces biased counts of vocalizations, which are subject to false positive/negative rates that may vary across subsets of the dataset. In this work, we advocate for directly estimating call density: The proportion of detection windows containing the target vocalization, regardless of classifier score. Our approach targets a desirable ecological estimator and provides a more rigorous grounding for identifying the core problems caused by distribution shifts -- when the defining characteristics of the data distribution change -- and designing strategies to mitigate them. We propose a validation scheme for estimating call density in a body of data and obtain, through Bayesian reasoning, probability distributions of confidence scores for both the positive and negative classes. We use these distributions to predict site-level densities, which may be subject to distribution shifts. We test our proposed methods on a real-world study of Hawaiian birds and provide simulation results leveraging existing fully annotated datasets, demonstrating robustness to variations in call density and classifier model quality.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑