Non-sequential automatic classification of anuran sounds for the estimation of climate-change indicators. (1st April 2018)

• Record Type: Journal Article
• Authors: Luque, Amalia; Romero-Lemos, Javier; Carrasco, Alejandro; Barbancho, Julio
• Is Part Of: Expert systems with applications. Volume 95(2018)
• Page Start: 248
• Page End: 260
• Publication Date: 2018-04-01
• Subjects: Global warming -- Sound classification -- Machine learning -- Data mining -- Feature extraction; Expert systems (Computer science) -- Periodicals; Systèmes experts (Informatique) -- Périodiques; Electronic journals; 006.33
• DOI: 10.1016/j.eswa.2017.11.016
• Languages: English
• ISSNs: 0957-4174

Abstract

Highlights: A non-sequential method for classifying sounds is proposed. The procedure relies on featuring frame sounds using MPEG-7 parameters. Several machine learning classifiers are compared and the decision tree is selected. It has been applied to classify anuran sounds as an indicator of global warming. Abstract: Several biological research studies have shown that the number of individuals of certain species of anurans in a specific geographical region, and the evolution of this number over time, can be used as an indicator of climate change. To detect the presence of anurans, Wireless Sensor Networks (WSNs) are usually deployed with the aim of obtaining bio-acoustic information in a set covering numerous locations. However, the identification of the anuran species from a huge number of recordings usually involves an overwhelming task that has to be undertaken by expert and intelligent systems. Previous studies into this issue have proposed several classification techniques with a common approach: they all take into account the sequential characteristic of sounds by considering syllables or other kinds of vocal segments. In noisy sounds, as it is usually the case in recordings made in natural habitats, segmentation of the signal is no straightforward task and may cause low classification accuracy. To override this problem, a new non-sequential approach is proposed in this paper. It is based on considering very small pieces of sounds (frames) each of which is then classified without considering preceding or subsequent information. Up to nine frame-based classifiers are explored in this paper and their performances are compared to the most commonly used sequential classifier: the Hidden Markov Model (HMM). Additionally, for featuring the frames, many choices have been described, although the application of the Mel Frequency Cepstral Coefficients (MFCCs) has probably become the most common method. In this work, an alternative methodology is suggested: the use of a set of MPEG-7 parameters, which offers a normalized solution with a much greater semantic content. The experimental results have shown that the proposed method clearly outperforms the HMM, thereby showing the non-sequential classification of anuran sounds to be feasible. From among the algorithms tested, the decision-tree classifier has shown the best performance with an overall classification success rate of 87.30%, which is an especially striking result considering that the analyzed sounds were affected by a decidedly noisy background.