skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Explore Research Products in the PAR
It may take a few hours for recently added research products to appear in PAR search results.


Title: Fusing shallow and deep learning for bioacoustic bird species classification
Automated classification of organisms to species based on their vocalizations would contribute tremendously to abilities to monitor biodiversity, with a wide range of applications in the field of ecology. In particular, automated classification of migrating birds' flight calls could yield new biological insights and conservation applications for birds that vocalize during migration. In this paper we explore state-of-the-art classification techniques for large-vocabulary bird species classification from flight calls. In particular, we contrast a “shallow learning” approach based on unsupervised dictionary learning with a deep convolutional neural network combined with data augmentation. We show that the two models perform comparably on a dataset of 5428 flight calls spanning 43 different species, with both significantly outperforming an MFCC baseline. Finally, we show that by combining the models using a simple late-fusion approach we can further improve the results, obtaining a state-of-the-art classification accuracy of 0.96.  more » « less
Award ID(s):
1633259
PAR ID:
10042567
Author(s) / Creator(s):
; ; ;
Date Published:
Journal Name:
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Page Range / eLocation ID:
141 to 145
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; ; (, Computational Intelligence and Neuroscience)
    Doulamis, Anastasios D. (Ed.)
    Hyperspectral imaging is an area of active research with many applications in remote sensing, mineral exploration, and environmental monitoring. Deep learning and, in particular, convolution-based approaches are the current state-of-the-art classification models. However, in the presence of noisy hyperspectral datasets, these deep convolutional neural networks underperform. In this paper, we proposed a feature augmentation approach to increase noise resistance in imbalanced hyperspectral classification. Our method calculates context-based features, and it uses a deep convolutional neuronet (DCN). We tested our proposed approach on the Pavia datasets and compared three models, DCN, PCA + DCN, and our context-based DCN, using the original datasets and the datasets plus noise. Our experimental results show that DCN and PCA + DCN perform well on the original datasets but not on the noisy datasets. Our robust context-based DCN was able to outperform others in the presence of noise and was able to maintain a comparable classification accuracy on clean hyperspectral images. 
    more » « less
  2. ; ; (, Journal of Applied Ecology)
    Insects play vital ecological roles; many provide essential ecosystem services while others are economically devastating pests and disease vectors. Concerns over insect population declines and expansion have generated a pressing need to effectively monitor insects across broad spatial and temporal scales. A promising approach is bioacoustics, which uses sound to study ecological communities. Despite recent increases in machine learning technologies, the status of emerging automated bioacoustics methods for monitoring insects is not well known, limiting potential applications. To address this gap, we systematically review the effectiveness of automated bioacoustics models over the past four decades, analysing 176 studies that met our inclusion criteria. We describe their strengths and limitations compared to traditional methods and propose productive avenues forward. We found automated bioacoustics models for 302 insect species distributed across nine Orders. Studies used intentional calls (e.g. grasshopper stridulation), by‐products of flight (e.g. bee wingbeats) and indirectly produced sounds (e.g. grain movement) for identification. Pests were the most common study focus, driven largely by weevils and borers moving in dried food and wood. All disease vector studies focused on mosquitoes. A quarter of the studies compared multiple insect families. Our review illustrates that machine learning, and deep learning in particular, are becoming the gold standard for bioacoustics automated modelling approaches. We identified models that could classify hundreds of insect species with over 90% accuracy. Bioacoustics models can be useful for reducing lethal sampling, monitoring phenological patterns within and across days and working in locations or conditions where traditional methods are less effective (e.g. shady, shrubby or remote areas). However, it is important to note that not all insect taxa emit easily detectable sounds, and that sound pollution may impede effective recordings in some environmental contexts. Synthesis and applications: Automated bioacoustics methods can be a useful tool for monitoring insects and addressing pressing ecological and societal questions. Successful applications include assessing insect biodiversity, distribution and behaviour, as well as evaluating the effectiveness of restoration and pest control efforts. We recommend collaborations among ecologists and machine learning experts to increase model use by researchers and practitioners. 
    more » « less
  3. (, Proceedings of the IEEE International Conference on Acoustics , Speech, and Signal Processing (ICASSP))
    This article addresses the automatic detection of vocal, nocturnally migrating birds from a network of acoustic sensors. Thus far, owing to the lack of annotated continuous recordings, existing methods had been benchmarked in a binary classification setting (presence vs. absence). Instead, with the aim of comparing them in event detection, we release BirdVox-full-night, a dataset of 62 hours of audio comprising 35402 flight calls of nocturnally migrating birds, as recorded from 6 sensors. We find a large performance gap between energybased detection functions and data-driven machine listening. The best model is a deep convolutional neural network trained with data augmentation. We correlate recall with the density of flight calls over time and frequency and identify the main causes of false alarm 
    more » « less
  4. ; ; (, IEEE International Conference on Communications)
    Radio Frequency (RF) device fingerprinting has been recognized as a potential technology for enabling automated wireless device identification and classification. However, it faces a key challenge due to the domain shift that could arise from variations in the channel conditions and environmental settings, potentially degrading the accuracy of RF-based device classification when testing and training data is collected in different domains. This paper introduces a novel solution that leverages contrastive learning to mitigate this domain shift problem. Contrastive learning, a state-of-the-art self-supervised learning approach from deep learning, learns a distance metric such that positive pairs are closer (i.e. more similar) in the learned metric space than negative pairs. When applied to RF fingerprinting, our model treats RF signals from the same transmission as positive pairs and those from different transmissions as negative pairs. Through experiments on wireless and wired RF datasets collected over several days, we demonstrate that our contrastive learning approach captures domain-invariant features, diminishing the effects of domain-specific variations. Our results show large and consistent improvements in accuracy (10.8% to 27.8%) over baseline models, thus underscoring the effectiveness of contrastive learning in improving device classification under domain shift. 
    more » « less
  5. ; ; ; ; (, npj Computational Materials)
    Abstract In current in situ X-ray diffraction (XRD) techniques, data generation surpasses human analytical capabilities, potentially leading to the loss of insights. Automated techniques require human intervention, and lack the performance and adaptability required for material exploration. Given the critical need for high-throughput automated XRD pattern analysis, we present a generalized deep learning model to classify a diverse set of materials’ crystal systems and space groups. In our approach, we generate training data with a holistic representation of patterns that emerge from varying experimental conditions and crystal properties. We also employ an expedited learning technique to refine our model’s expertise to experimental conditions. In addition, we optimize model architecture to elicit classification based on Bragg’s Law and use evaluation data to interpret our model’s decision-making. We evaluate our models using experimental data, materials unseen in training, and altered cubic crystals, where we observe state-of-the-art performance and even greater advances in space group classification. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email