Bioacoustic Signals Research Articles

Adaptive iterative transfer learning for effective snapping shrimp sound detection.

This study aims to detect the bioacoustics signal in the underwater soundscape, specifically those produced by snapping shrimp, using adaptive iterative transfer learning. The proposed network is initially trained with pre-classified snapping shrimp sounds and Gaussian noise, then applied to classify and remove snapping-free noise from field data. This separated ambient noise is subsequently used for transfer learning. This process was iterated to distinguish more effectively between ambient noise and snapping shrimp sounds characteristics, resulting in improved classification. Through iterative transfer learning, significant improvements in precision and recall were observed. The application to field data confirmed that the trained network could detect signals that were difficult to identify using existing threshold classification methods. Furthermore, it was found that the rate of false detection decreased, and detection probability improved with each stage. This research demonstrates that incorporating the noise characteristics of field data into the trained network via iterative transfer learning can generate more realistic training data. The proposed network can successfully detect signals that are challenging to identify using existing threshold classification methods.

Bioacoustic classification of a small dataset of mammalian vocalisations using deep learning

ABSTRACT In the last few years, automatic extraction and classification of animal vocalisations has been facilitated by machine learning (ML) and deep learning (DL) methods. Different frameworks allowed researchers to automatically extract features and perform classification tasks, aiding in call identification and species recognition. However, the success of these applications relies on the amount of available data to train these algorithms. The lack of sufficient data can also lead to overfitting and affect generalisation (i.e. poor performance on out-of-sample data). Further, acquiring large data sets is costly and annotating them is time consuming. Thus, how small can a dataset be to still provide useful information by means of ML or DL? Here, we show how convolutional neural network architectures can handle small datasets in a bioacoustic classification task of affective mammalian vocalisations. We explain how these techniques can be used (e.g. pre-training and data augmentation), and emphasise how to implement them in concordance with features of bioacoustic signals. We further discuss whether these networks can generalise the affective quality of vocalisations across different taxa.

Novel Spectral Approaches in Mathematical Bioacoustics Based on Real Time Analysis and Modern Computational Mathematical Techniques Using Digital Signal Processing and Analog Signal Processing Hardware (Review Lecture)

This review publication is an expanded version of the 2015 lecture at the III Moscow Seminar on Mathematical Bioacoustics and Analog Signal Processing in Physiology. Unlike the original 2015 version, this version includes developments by E.D. Adamovich and F.K. Orekhov, as well as a number of graphic materials of historical value. The work proposes new principles or approaches for multifactori/multimodal analysis of various bioacoustic signals based on N-dimension complex spectral analysis of different (bio) physical variables - “bioacoustic fingerprinting” and “bioacoustic footprinting”. Hadware-based technical examples of possible uses of this approache are given for the breef annotation in the text of this lecture.

Bioacoustics of Trogoderma granarium Everts (Coleoptera: Dermestidae)

Trogoderma granarium Everts (Coleoptera: Dermestidae) is one of the major destructive pests of grain products in hot and dry parts of the world. No information has been made available on the bioacoustic signals (BASs) of T. granarium. In this paper, the bioacoustic features of this insect have measured from larvae and adult males and females. No anechoic chamber was used in this study. The extracted features were compared to evaluate the ability of the acoustic method to determine larva or adult as well as their sex. Adult males and females and larvae T. granarium produced BASs with a length of 2–11, 2–52, and 2–30 ms with a maximum sound pressure level of 3, 36, and 17 dB, respectively. At least 60 % of all BASs were in the ranges of 2–12 impulses in larva and adult stages. The sum of the total BASs was different in larvae and adult stages. Adult males had the least number of BASs compared to adult females and larvae. Detection of the growth stage and determination of the sex of the adult T. granarium by acoustic method in the time domain depends on the feature extracted from BASs and number of their impulses. Furthermore, in the frequency domain, the most dominant frequency bands were in the range of 1–8 kHz. In this band, the most dominant frequency band was 3.5–4.5 and 1–1.7 kHz for adult males and larvae, respectively. The most dominant bands of 1–3 and 4–5 kHz were observed for adult females.

Fourier Transform Driven Bioacoustics for Frequency-Based Pest Deterrence in Sustainable Agriculture

The focus of this research is on using bioacoustics for frequency-based pest deterrence in sustainable agriculture, with the Fourier transform as the driving force. The critical need for new and improved methods of pest control in agricultural settings is addressed. This study, which makes use of cutting-edge technology, investigates how the Fourier Transform might be used as a useful instrument in the fight against pests. This research makes use of a cutting-edge algorithm for pest control; it's based on Fourier Transform bioacoustic analysis. By using the "Insect Bioacoustic Signals (IBS) Dataset," this study reveals the algorithm's effectiveness in recognising and managing pests, as indicated by a remarkable classification accuracy of 93%. This study makes important contributions to the growing body of sustainable agriculture knowledge and has far-reaching consequences for the agricultural sector. A revolutionary new method of pest control is presented, with the potential to increase agricultural output and sustainability while decreasing crop losses. Specialised tools and libraries such as the Fast Fourier Transform (FFT) method from the NumPy toolkit for spectral analysis, Scikit-learn for machine learning approaches, and Librosa for audio signal processing, were used in this work to produce these encouraging outcomes. In conclusion, this research highlights the promise of bioacoustics based on the Fourier Transform to usher in a new era of environmentally responsible farming by effectively discouraging pests.

Underdetermined Blind Source Separation of Bioacoustic Signals

Bioacoustic signals have been used as a modality in environmental monitoring and biodiversity research. These signals also carry species or individual information, thus allowing the recognition of species and individuals based on vocals. Nevertheless, vocal communication in a crowded social environment is a challenging problem for automated bioacoustic recogniser systems due to interference problems in concurrent signals from multiple individuals. The bioacoustics sources are separated from the mixtures of multiple individual signals using a technique known as Blind source separation (BSS) to address the abovementioned issue. In this work, we explored the BSS of an underdetermined mixture based on a two-stage sparse component analysis (SCA) approach that consisted of (1) mixing matrix estimation and (2) source estimation. The key point of our procedure was to investigate the algorithm’s robustness to noise and the effect of increasing the number of sources. Using the two-stage SCA technique, the performances of the estimated mixing matrix and the estimated source were evaluated and discussed at various signal-to-noise ratios (SNRs). The use of different sources is also validated. Given its robustness, the SCA algorithm presented a stable and reliable performance in a noisy environment with small error changes when the noise level was increased.

Open Set Bioacoustic Signal Classification based on Class Anchor Clustering with Closed Set Unknown Bioacoustic Signals.

Recently, deep learning-driven studies have been introduced for bioacoustic signal classification. Most of them, however, have the limitation that the input of the classifier needs to match with a trained label which is known as closed set recognition (CSR). To this end, the classifier trained by CSR would not cover a real stream task since the input of the classifier has so many variations. To combat real-world tasks, open set recognition (OSR) has been developed. In OSR, randomly collected inputs are fed to the classifier and the classifier predicts target classes and Unknown class. However, this OSR has been spotlighted in the studies of computer vision and speech domains while the domain of bioacoustic signal is less developed. Especially, to our best knowledge, OSR for animal sound classification has not been studied. This paper proposes a novel method for open set bioacoustic signal classification based on Class Anchored Clustering (CAC) loss with closed set unknown bioacoustic signals. To use the closed set unknown signals for training, a total of n +1 classes are used by adding one additional Unknown class to n target classes, and n +1 cross-entropy loss is added to the CAC loss. To evaluate the proposed method, we build an animal sound dataset that includes 101 species of sounds and compare its performance with baseline methods. In the experiments, our proposed method shows higher performance than other baseline methods in the area under the receiver operating curve for detecting target class and unknown class, the classification accuracy of open set signals, and classification accuracy for target classes. As a result, the closed set class samples are well classified while the open set unknown class can be also recognized with high accuracy at the same time.

A secure lightweight fuzzy embedder based user authentication scheme for internet of medical things applications

The Internet of Medical Things (IoMT) is a network of medical devices, hardware infrastructure, and software that allows healthcare information technology to be communicated over the web. The IoMT sensors communicate medical data to server for the quick diagnosis. As, it handles private and confidential information of a user, security is the primary objective. The existing IoT authentication schemes either using two-factor(Username, password) or multi-factor (username, password, biometric) to authenticate a user. Typically the structural characteristics-based biometric trait like Face, Iris, Palm print or finger print is used as a additional factor. There are chances that these biometrics can be fabricated. Thus, these structural biometrics based authentication schemes are fail to provide privacy, security, authenticity, and integrity. The biodynamic-based bioacoustics signals are gained attention in the era of human-computer interactions to authenticate a user as it is a unique feature to each user. So, we use a frequency domain based bio-acoustics as a biometric input. Thus, this work propose a Secure Lightweight Bioacoustics based User Authentication Scheme using fuzzy embedder for the Internet of Medical Things applications. Also, the IoT sensors tends to join and leave the network dynamically, the proposed scheme adopts chinese remainder technique for generate a group secret key to protect the network from the attacks of former sensor nodes. The proposed scheme’s security is validated using the formal verification tool AVISPA(Automated Validation of Internet Security Protocols and Applications). The system’s performance is measured by comparing the proposed scheme to existing systems in terms of security features, computation and communication costs. It demonstrates that the proposed system outperforms existing systems.

Bayesian detection and tracking of odontocetes in 3-D from their echolocation clicks.

Localization and tracking of marine animals can reveal key insights into their behaviors underwater that would otherwise remain unexplored. A promising nonintrusive approach to obtaining location information of marine animals is to process their bioacoustic signals, which are passively recorded using multiple hydrophones. In this paper, a data processing chain that automatically detects and tracks multiple odontocetes (toothed whales) in three dimensions (3-D) from their echolocation clicks recorded with volumetric hydrophone arrays is proposed. First, the time-difference-of-arrival (TDOA) measurements are extracted with a generalized cross-correlation that whitens the received acoustic signals based on the instrument noise statistics. Subsequently, odontocetes are tracked in the TDOA domain using a graph-based multi-target tracking (MTT) method to reject false TDOA measurements and close gaps of missed detections. The resulting TDOA estimates are then used by another graph-based MTT stage that estimates odontocete tracks in 3-D. The tracking capability of the proposed data processing chain is demonstrated on real acoustic data provided by two volumetric hydrophone arrays that recorded echolocation clicks from Cuvier's beaked whales (Ziphius cavirostris). Simulation results show that the presented MTT method using 3-D can outperform an existing approach that relies on manual annotation.

Automatic acoustic recognition of pollinating bee species can be highly improved by Deep Learning models accompanied by pre-training and strong data augmentation.

Bees capable of performing floral sonication (or buzz-pollination) are among the most effective pollinators of blueberries. However, the quality of pollination provided varies greatly among species visiting the flowers. Consequently, the correct identification of flower visitors becomes indispensable to distinguishing the most efficient pollinators of blueberry. However, taxonomic identification normally depends on microscopic characteristics and the active participation of experts in the decision-making process. Moreover, the many species of bees (20,507 worldwide) and other insects are a challenge for a decreasing number of insect taxonomists. To overcome the limitations of traditional taxonomy, automatic classification systems of insects based on Machine-Learning (ML) have been raised for detecting and distinguishing a wide variety of bioacoustic signals, including bee buzzing sounds. Despite that, classical ML algorithms fed by spectrogram-type data only reached marginal performance for bee ID recognition. On the other hand, emerging systems from Deep Learning (DL), especially Convolutional Neural Networks (CNNs), have provided a substantial boost to classification performance in other audio domains, but have yet to be tested for acoustic bee species recognition tasks. Therefore, we aimed to automatically identify blueberry pollinating bee species based on characteristics of their buzzing sounds using DL algorithms. We designed CNN models combined with Log Mel-Spectrogram representations and strong data augmentation and compared their performance at recognizing blueberry pollinating bee species with the current state-of-the-art models for automatic recognition of bee species. We found that CNN models performed better at assigning bee buzzing sounds to their respective taxa than expected by chance. However, CNN models were highly dependent on acoustic data pre-training and data augmentation to outperform classical ML classifiers in recognizing bee buzzing sounds. Under these conditions, the CNN models could lead to automating the taxonomic recognition of flower-visiting bees of blueberry crops. However, there is still room to improve the performance of CNN models by focusing on recording samples for poorly represented bee species. Automatic acoustic recognition associated with the degree of efficiency of a bee species to pollinate a particular crop would result in a comprehensive and powerful tool for recognizing those that best pollinate and increase fruit yields.

Power Spectral Analysis of Bioacoustic Signals Emitted by a Bottlenose Dolphin when Performing Assisted Therapy

To understand the origin of the benefits of Dolphin-Assisted Therapy (DAT), it is important to know the factors that intervene during it, as well as the patient’s reactions to these factors. The purpose of this work is to measure the frequencies emitted by the dolphin through the use of specialized transducers for aquatic environments, which allow us to measure the sound waves coming from the dolphin. In this way, it is sought to know the real time in which they were emitted and the spectral density of these frequencies.

Sparse Component Analysis (SCA) Based on Adaptive Time-Frequency Thresholding for Underdetermined Blind Source Separation (UBSS).

Blind source separation (BSS) recovers source signals from observations without knowing the mixing process or source signals. Underdetermined blind source separation (UBSS) occurs when there are fewer mixes than source signals. Sparse component analysis (SCA) is a general UBSS solution that benefits from sparse source signals which consists of (1) mixing matrix estimation and (2) source recovery estimation. The first stage of SCA is crucial, as it will have an impact on the recovery of the source. Single-source points (SSPs) were detected and clustered during the process of mixing matrix estimation. Adaptive time-frequency thresholding (ATFT) was introduced to increase the accuracy of the mixing matrix estimations. ATFT only used significant TF coefficients to detect the SSPs. After identifying the SSPs, hierarchical clustering approximates the mixing matrix. The second stage of SCA estimated the source recovery using least squares methods. The mixing matrix and source recovery estimations were evaluated using the error rate and mean squared error (MSE) metrics. The experimental results on four bioacoustics signals using ATFT demonstrated that the proposed technique outperformed the baseline method, Zhen's method, and three state-of-the-art methods over a wide range of signal-to-noise ratio (SNR) ranges while consuming less time.

Blockchain-enabled bioacoustics signal authentication for cloud-based electronic medical records

In this paper, we explore Blockchain technology can be used to build a reliable decentralised authentication system. High security for the bioacoustics signal authentication mechanism is guaranteed by using an optimised number of secured features from the bioacoustics signal rather than conventional biometric features for authentication, and by utilising a blockchain model to improve the robustness of multiple checks on the data. It allows for trustworthy authentication and the tracking of terminal activity. Then, light weighted cryptography (LWC) is developed to offer protection at each edge node and terminal. Finally, the belief propagation (BP) algorithm for retraining the features of the bioacoustics signal serves as the foundation for the catching method. It improves hit ratio while decreasing delay time. The experimental setup uses the bioacoustics signals for authentication instead of conventional biometric features, and the use of a blockchain model for data transparency improves the efficiency of multiple checks. When this happens, privacy and safety are both boosted.

ANIMAL-SPOT enables animal-independent signal detection and classification using deep learning

Bioacoustic research spans a wide range of biological questions and applications, relying on identification of target species or smaller acoustic units, such as distinct call types. However, manually identifying the signal of interest is time-intensive, error-prone, and becomes unfeasible with large data volumes. Therefore, machine-driven algorithms are increasingly applied to various bioacoustic signal identification challenges. Nevertheless, biologists still have major difficulties trying to transfer existing animal- and/or scenario-related machine learning approaches to their specific animal datasets and scientific questions. This study presents an animal-independent, open-source deep learning framework, along with a detailed user guide. Three signal identification tasks, commonly encountered in bioacoustics research, were investigated: (1) target signal vs. background noise detection, (2) species classification, and (3) call type categorization. ANIMAL-SPOT successfully segmented human-annotated target signals in data volumes representing 10 distinct animal species and 1 additional genus, resulting in a mean test accuracy of 97.9%, together with an average area under the ROC curve (AUC) of 95.9%, when predicting on unseen recordings. Moreover, an average segmentation accuracy and F1-score of 95.4% was achieved on the publicly available BirdVox-Full-Night data corpus. In addition, multi-class species and call type classification resulted in 96.6% and 92.7% accuracy on unseen test data, as well as 95.2% and 88.4% regarding previous animal-specific machine-based detection excerpts. Furthermore, an Unweighted Average Recall (UAR) of 89.3% outperformed the multi-species classification baseline system of the ComParE 2021 Primate Sub-Challenge. Besides animal independence, ANIMAL-SPOT does not rely on expert knowledge or special computing resources, thereby making deep-learning-based bioacoustic signal identification accessible to a broad audience.

Discriminative Singular Spectrum Classifier with applications on bioacoustic signal recognition

Automatic analysis of bioacoustic signals is a fundamental tool to evaluate the vitality of our planet. Frogs and bees, for instance, may act like biological sensors providing information about environmental changes. This task is fundamental for ecological monitoring and includes many challenges, such as nonuniform signal length processing, degraded target signal due to environmental noise, and the scarcity of labeled samples for training machine learning systems. To tackle these challenges, we present a bioacoustic signal classifier equipped with a discriminative mechanism to extract useful features for analysis and classification efficiently. The proposed classifier does not require a large amount of training data and handles nonuniform signal length natively. Unlike current bioacoustic recognition methods, which are task-oriented, the proposed model relies on transforming the input signals into vector subspaces generated by applying Singular Spectrum Analysis (SSA). Then, a subspace is designed to expose discriminative features. The proposed model shares end-to-end capabilities, which are desirable in modern machine learning systems. This formulation provides a segmentation-free and noise-tolerant approach to represent and classify bioacoustic signals and a highly compact signal descriptor inherited from SSA. The validity of the proposed method is verified using three challenging bioacoustic datasets containing anuran, bee, and mosquito species. Experimental results on three bioacoustic datasets have shown the competitive performance of the proposed method compared to commonly employed methods for bioacoustics signal classification in terms of accuracy. The code developed for this research can be found in the following repository: http://github.com/bernardo-gatto/DSSC.

First record of Teleogryllus (Brachyteleogryllus) marini Otte & Alexander, 1983 (Orthoptera: Gryllidae) in korea and discussion of its continued misidentification using DNA barcoding

• Teleogryllus (Brachyteleogryllus) marini is newly recorded from Korea. • A key to Korean Teleogryllus species is provided. • T. (B.) marini is transferred to the subgenus Brachyteleogryllus . • Asian T. (B.) marini has been misidentified as T. (B.) commodus with DNA barcoding. DNA barcoding is useful for identifying species that are difficult to distinguish via morphological analysis. However, if the public DNA barcode database includes misidentified DNA samples, subsequent molecular studies could generate incorrect results. Here, we report a misidentified DNA barcode for the North Coastal Black Field Cricket Teleogryllus ( Brachyteleogryllus ) marini . T. (B.) marini is routinely misidentified using DNA barcoding; it has been reported as Teleogryllus (Brachyteleogryllus) commodus since its misidentification in various studies of Asian samples. Here, we report the first occurrence of T. (B.) marini in Korea, along with its morphological diagnosis, bioacoustic signals, and DNA barcoding findings. T. (B.) marini is transferred to the subgenus Brachyteleogryllus from the subgenus Teleogryllus , based on the male genitalia morphology and phylogenetic analysis. Genetic distance analyses have shown that cytochrome c oxidase I barcoding is useful for species identification of the genus Teleogryllus, but detailed morphological investigations are essential for DNA barcoding before any molecular study.

Multichannel Acoustic Spectroscopy of the Human Body for Inviolable Biometric Authentication.

Specific features of the human body, such as fingerprint, iris, and face, are extensively used in biometric authentication. Conversely, the internal structure and material features of the body have not been explored extensively in biometrics. Bioacoustics technology is suitable for extracting information about the internal structure and biological and material characteristics of the human body. Herein, we report a biometric authentication method that enables multichannel bioacoustic signal acquisition with a systematic approach to study the effects of selectively distilled frequency features, increasing the number of sensing channels with respect to multiple fingers. The accuracy of identity recognition according to the number of sensing channels and the number of selectively chosen frequency features was evaluated using exhaustive combination searches and forward-feature selection. The technique was applied to test the accuracy of machine learning classification using 5,232 datasets from 54 subjects. By optimizing the scanning frequency and sensing channels, our method achieved an accuracy of 99.62%, which is comparable to existing biometric methods. Overall, the proposed biometric method not only provides an unbreakable, inviolable biometric but also can be applied anywhere in the body and can substantially broaden the use of biometrics by enabling continuous identity recognition on various body parts for biometric identity authentication.

Bioacoustic signal analysis through complex network features

The paper proposes a graph-theoretical approach to auscultation, bringing out the potential of graph features in classifying the bioacoustics signals. The complex network analysis of the bioacoustics signals - vesicular (VE) and bronchial (BR) breath sound - of 48 healthy persons are carried out for understanding the airflow dynamics during respiration. The VE and BR are classified by the machine learning techniques extracting the graph features – the number of edges (E), graph density (D), transitivity (T), degree centrality (Dcg) and eigenvector centrality (Ecg). The higher value of E, D, and T in BR indicates the temporally correlated airflow through the wider tracheobronchial tract resulting in sustained high-intense low-frequencies. The frequency spread and high-frequencies in VE, arising due to the less correlated airflow through the narrow segmental bronchi and lobar, appears as a lower value for E, D, and T. The lower values of Dcg and Ecg justify the inferences from the spectral and other graph parameters. The study proposes a methodology in remote auscultation that can be employed in the current scenario of COVID-19.

Development of deep neural networks for marine mammal call detection using an open-source, user friendly tool

As the collection of large acoustic datasets used to monitor marine mammals increases, so too does the need for expedited and reliable detection of accurately classified bioacoustic signals. Deep learning methods of detection and classification are increasingly proposed as a means of addressing this processing need. These image recognition and classification methods include the use of a neural networks that independently determine important features of bioacoustic signals from spectrograms. Recent marine mammal call detection studies report consistent performance even when used with datasets that were not included in the network training. We present here the use of DeepSqueak, a novel open-source tool originally developed to detect and classify ultrasonic vocalizations from rodents in a low-noise, laboratory setting. We have trained networks in DeepSqueak to detect marine mammal vocalizations in comparatively noisy, natural acoustic environments. DeepSqueak utilizes a regional convolutional neural network architecture within an intuitive graphical user interface that provides automated detection results independent of acoustician expertise. Using passive acoustic data from two hydrophones on the Ocean Observatories Initiative’s Coastal Endurance Array, we developed networks for humpback whales, delphinids, and fin whales. We report performance and limitations for use of this detection method for each species.

PAMGuard: Open-source detection, classification, and Localization software

The PAMGuard open-source software project was established in 2006 to provide a toolbox and app for the detection, classification, and localization (DCL) of bioacoustic signals. Releases typically attract between 1500 and 3500 downloads. Primarily developed for marine mammals, users can configure PAMGuard to work with a wide variety of hardware configurations (single hydrophones, to complex 3D arrays) and DCL algorithms, depending on the species of interest. A Java code base and integrated multi-threading allow multiple DCL algorithms to be run in parallel enabling rapid analysis of large acoustic datasets. A comprehensive data management system and a suite of interactive displays then allow users to visualize and annotate resulting data at temporal scales from milliseconds to years. This combination of advanced analysis algorithms and powerful data visualization in both real-time, or reviewing data post-hoc, means PAMGuard provides both automatic and a proven and reliable human-in-the-loop approach to analysis. Developers can use the program’s infrastructure to rapidly develop and deploy new algorithms; recently, an international collaboration has improved support for terrestrial species and developed a new module to import acoustic deep learning models, enabling users to take advantage of PAMGuard’s data management and visualization capabilities alongside the latest automated acoustic classifiers.