Designing better frog call recognition models

Evaluating and optimising performance of multi-species call recognisers for ecoacoustic restoration monitoring

Monitoring the effect of ecosystem restoration can be difficult and time-consuming. Autonomous sensors, such as acoustic recorders, can aid monitoring across long time scales. This project successfully developed, tested and implemented call recognisers for eight species of frog in the Murray-Darling Basin. Recognisers for all but one species performed well and substantially better than many species recognisers reported in the literature. We achieved this through a comprehensive development phase, which carefully considered and refined the representativeness of training data, as well as the construction (amplitude cut-off) and the similarity thresholds (score cut-offs) of each call template used. Recogniser performance was high for almost all species examined. Recognisers for Crinia signifera, Limnodynastes fletcherii, Limnodynastes dumerilii, Litoria peronii and Crinia parinsignifera all performed well, with most templates having receiver operating characteristics values (the proportion of true positive and true negatives) over 0.7, and some much higher. Recognisers for L. peronii, L. fletcherii and L. dumerilii performed particularly well in the training data set, which allowed for responses to environmental watering events, a restoration activity, to be clearly observed. While slightly more involved than building recognisers using commercial packages, the workflows ensure that a high-quality recogniser can be built and the performance fine-tuned using multiple parameters. Using the same framework, recognisers can be improved on in future iterations. We believe that multi-species recognisers are a highly effective and precise way to detect the effects of ecosystem restoration.

Implementation of Artificial Intelligence for Classification of Frogs in Bioacoustics

This research presents the implementation of artificial intelligence (AI) for classification of frogs in symmetry of the bioacoustics spectral by using the feedforward neural network approach (FNNA) and support vector machine (SVM). Recently, the symmetry concept has been applied in physics, and in mathematics to help make mathematical models tractable to achieve the best learning performance. Owing to the symmetry of the bioacoustics spectral, feature extraction can be achieved by integrating the techniques of Mel-scale frequency cepstral coefficient (MFCC) and mentioned machine learning algorithms, such as SVM, neural network, and so on. At the beginning, the raw data information for our experiment is taken from a website which collects many kinds of frog sounds. This in fact saves us collecting the raw data by using a digital signal processing technique. The generally proposed system detects bioacoustic features by using the microphone sensor to record the sounds of different frogs. The data acquisition system uses an embedded controller and a dynamic signal module for making high-accuracy measurements. With regard to bioacoustic features, they are filtered through the MFCC algorithm. As the filtering process is finished, all values from ceptrum signals are collected to form the datasets. For classification and identification of frogs, we adopt the multi-layer FNNA algorithm in machine learning and the results are compared with those obtained by the SVM method at the same time. Additionally, two optimizer functions in neural network include: scaled conjugate gradient (SCG) and gradient descent adaptive learning rate (GDA). Both optimization methods are used to evaluate the classification results from the feature datasets in model training. Also, calculation results from the general central processing unit (CPU) and Nvidia graphics processing unit (GPU) processors are evaluated and discussed. The effectiveness of the experimental system on the filtered feature datasets is classified by using the FNNA and the SVM scheme. The expected experimental results of the identification with respect to different symmetry bioacoustic features of fifteen frogs are obtained and finally distinguished.

Designing better frog call recognition models

Advances in bioacoustic technology, such as the use of automatic recording devices, allow wildlife monitoring at large spatial scales. However, such technology can produce enormous amounts of audio data that must be processed and analyzed. One potential solution to this problem is the use of automated sound recognition tools, but we lack a general framework for developing and validating these tools. Recognizers are computer models of an animal sound assembled from "training data" (i.e., actual samples of vocalizations). The settings of variables used to create recognizers can impact performance, and the use of different settings can result in large differences in error rates that can be exploited for different monitoring objectives. We used Song Scope (Wildlife Acoustics Inc.) to build recognizers and vocalizations of the wood frog (Lithobates sylvaticus) to test how different settings and amounts of training data influence recognizer performance. Performance was evaluated using precision (the probability of a recognizer match being a true match) and sensitivity (the proportion of vocalizations detected) based on a receiver operating characteristic (ROC) curve-determined score threshold. Evaluations were conducted using recordings not used to build the recognizer. Wood frog recognizer performance was sensitive to setting changes in four out of nine variables, and small improvements were achieved by using additional training data from different sites and from the same recording, but not from different recordings from the same site. Overall, the effect of changes to variable settings was much greater than the effect of increasing training data. Additionally, by testing the performance of the recognizer on vocalizations not used to build the recognizer, we discovered that Type I error rates appear idiosyncratic and do not recommend extrapolation from training to new data, whereas Type II errors showed more consistency and extrapolation can be justified. Optimizing variable settings on independent recordings led to a better match between recognizer performance and monitoring objectives. We provide general recommendations for application of this methodology with other species and make some suggestions for improvements.