Todor Ganchev

Automated acoustic detection of Vanellus chilensis lampronotus

Automated acoustic recognition of Southern Lapwing in real-world soundscapes.Recognizer of Vanellus chilensis vocalizations and their start and end timestamps.Log-likelihood ratio estimator with temporal post-processing of the output scores.Computer-assisted analysis of daily and hourly acoustic activity patterns.Non-intrusive monitoring of presence/absence and activity patterns. Traditional human-observer-based biological surveys are expensive. Therefore most biodiversity studies are implemented only periodically, for short periods, and predominantly during daytime and under favorable weather conditions. Automated data acquisition and analysis can overcome these shortcomings and facilitate continuous monitoring. Here we report on the development of an automated acoustic recognizer for Southern Lapwing Vanellus chilensis lampronotus vocalizations, a first for this species. The recognizer is a species-specific information retrieval agent, which searches throughout long audio recordings in order to detect and timestamp call events of the target species. The recognizer relies on a log-likelihood ratio estimator, based on a Gaussian Mixture Model-Universal Background Model (GMM-UBM), complemented with purposely-developed temporal post-processing that incorporates domain knowledge about the structure of V. chilensis vocalizations. Validation experiments with real-field recordings of complex soundscapes indicate that the recognizer is sensitive enough to register V. chilensis call events with sound levels down to -30dB and recognition accuracy of up to 85.6%, at zero false positive rates. The recognizer is considered a valuable tool for computer-assisted analysis of hourly and daily acoustic activity of V. chilensis over extended periods of time, as it offers an indispensable support to long-term monitoring studies and conservation efforts in the Pantanal region.1INAU Project 3.14 Monitoring Bioindicators and Migratory Birds in the Pantanal. Applied Acoustomics - a Tool for Bio-sustainability Assessment, INAU Lab. 3 - Biodiversity and Ecological Processes (INAU: www.inau.org.br; 2011-2014) - Program CsF (www.cienciasemfronteiras.gov.br/web/csf).1

Audio parameterization with robust frame selection for improved bird identification

Audio parameterization method with robust frame selection.Automated acoustic recognition of 40 bird species.HMM-based bird identification. A major challenge in the automated acoustic recognition of bird species is the audio segmentation, which aims to select portions of audio that contain meaningful sound events and eliminates segments that contain predominantly background noise or sound events of other origin. Here we report on the development of an audio parameterization method with integrated robust frame selection that makes use of morphological filtering applied on the spectrogram seen as an image. The morphological filtering allows to exclude from further processing certain audio events, which otherwise could cause misclassification errors. The Mel Frequency Cepstral Coefficients (MFCCs) computed for the selected audio frames offer a good representation of the spectral information for dominant vocalizations because the morphological filtering eliminates short bursts of noise and suppresses weak competing signals. Experimental validation of the proposed method on the identification of 40 bird species from Brazil demonstrated superior accuracy and faster operation than three traditional and recent approaches. This is expressed as reduction of the relative error rate by 3.4% and the overall operational time by 7.5% when compared to the second best result. The improved frame selection robustness, precision, and operational speed facilitate applications like multi-species identification of real-field recordings.

Automated Sound Recognition Provides Insights into the Behavioral Ecology of a Tropical Bird

Computer-assisted species recognition facilitates the analysis of relevant biological information in continuous audio recordings. In the present study, we assess the suitability of this approach for determining distinct life-cycle phases of the Southern Lapwing Vanellus chilensis lampronotus based on adult vocal activity. For this purpose we use passive 14-min and 30-min soundscape recordings (n = 33 201) collected in 24/7 mode between November 2012 and October 2013 in Brazil’s Pantanal wetlands. Time-stamped detections of V. chilensis call events (n = 62 292) were obtained with a species-specific sound recognizer. We demonstrate that the breeding season fell in a three-month period from mid-May to early August 2013, between the end of the flood cycle and the height of the dry season. Several phases of the lapwing’s life history were identified with presumed error margins of a few days: pre-breeding, territory establishment and egg-laying, incubation, hatching, parental defense of chicks, and post-breeding. Diurnal time budgets confirm high acoustic activity levels during midday hours in June and July, indicative of adults defending young. By August, activity patterns had reverted to nonbreeding mode, with peaks around dawn and dusk and low call frequency during midday heat. We assess the current technological limitations of the V. chilensis recognizer through a comprehensive performance assessment and scrutinize the usefulness of automated acoustic recognizers in studies on the distribution pattern, ecology, life history, and conservation status of sound-producing animal species.

Tegmina-size variation in a Neotropical cricket with implications on spectral song properties

This study evaluates the relationship between shape and size of tegmen, harp, mirror, and spectral range of calling song frequency of a Neotropical cricket subpopulation (Lerneca inalata beripocone. In addition, we compare intraspecific morphological divergence and calling song properties between individuals from different sites of the Pantanal of Poconé, Mato Grosso, Brazil. Regression analysis showed that the dominant and maximum calling song frequencies were negatively correlated with tegmen size, i.e. frequencies are either lower or higher depending on the corresponding size variation in resonance structures of the forewings. Canonical variable analysis demonstrated marked intraspecific differences in morphometric characters between localities of a L. inalata subpopulation c. 35 km apart (SESC-Pantanal Advanced Research Base and Pouso Alegre Farm, Mato Grosso, Brazil). Lerneca inalata beripocone at SESC had larger forewings than conspecifics from Pouso Alegre Farm. These morphological variations of wing properties related to reproductive behaviours were interpreted as fitness parameters, likely shaped by restricted gene flow during temporal habitat isolation episodes. Such isolation patterns occur in the Pantanal wetlands for several months during the annual hydrological cycle.

Overall Design of the SLADE Data Acquisition System

We present the overall design of a data acquisition system developed for the needs of the SLADE (Stress Level and Emotional State Assessment Database) database. The database consists of synchronized EEG, ECG, skin temperature (ST), and galvanic skin response (GSR) recordings, used in stress level assessment and recognition of emotional states. SLADE will facilitate the development of automated tools and services for stress-level assessment and monitoring.

Automated Stress Level Monitoring in Mobile Setup

We present the design of a mobile system for real-time stress-level assessment. The system combines wearable sensors, wireless data acquisition, and Cloud computing in order to collect and analyze physiological signals, such as, Galvanic Skin Response (GSR) and skin temperature. We report on the implementation of a specific use case, which incorporates functionality for real-time data logging and analysis. Experimental results demonstrate excellent recognition accuracy of affective arousal and decent accuracy for binary detection of valence. In addition, we also evaluate the feasibility for detection of high arousal/negative valence (HANV) events, which in specific setups can be connected to stress.

Evaluation of Cepstral Coefficients as Features in EEG-Based Recognition of Emotional States

The study of physiological signals and the evaluation of their features are of great importance for the automated emotion detection, as these are directly connected with the successful modelling and classification of the states of interest. In the presented work, we present an evaluation of the appropriateness of LFCC and the logarithmic energy of signals as features for automated recognition of negative emotional states in terms of recognition accuracy. In particular, three sets of features are compared – features computed after frame-level segmentation of the signal; features computed after averaging of frame level descriptors; and features extracted from an entire EEG recording. The performance of the extracted features is evaluated using C4.5 classifier for 10, 15, 20, 30, 45, and 60 filters.

FPGA Implementation of the Locally Recurrent Probabilistic Neural Network

The Locally Recurrent Probabilistic Neural Network (LRPNN) consists of an input layer, three hidden layers and an output layer. The first two hidden layers are derived from the original PNN, while the third layer referred as recurrent layer is capable to model correlations within temporal sequences of observations. In the present study, we investigate the feasibility of FPGA-based implementation of the locally recurrent layer of LRPNN. An important consideration due to the specifics of this architecture is the use of modules with very high precision in the hardware design. Although expensive in terms of available resources in the FPGA chip, this is necessary, in order to compensate for the added error of quantization due to the multiple feedbacks from neurons in the neural network. The weights for the recurrent layer of the LRPNN are automatically computed from the available training data and translated into the hardware design. The experimental evaluation was carried out on the DEAP database, where two classes of emotional states were considered. The design makes use of a computed short-term energy from a 32-channel electroencephalographic (EEG) signal as an input. Results of an extensive experimental validation show that there is approximately one percent difference between the accuracy achieved with CPU-based software and FPGA-based hardware implementation of the LRPNN.

Spatio-temporal EEG signal descriptors for recognition of negative emotional states

In the following paper we present a study on novel signal descriptors for the purposes of automated recognition of negative emotional states from EEG signals - namely, the decorrelated values of the energy of the spatio-temporal distribution of EEG activity. Using the extracted features person-specific SVM models are created. The experimental setups are based on data taken from the DEAP database. The classification accuracy of the proposed features is evaluated using two experimental setups: valence detection and like/dislike detection. Recognition accuracy of 77.5% and 78.0%, respectfully, was achieved.