Improving Misfire Fault Diagnosis with Cascading Architectures via Acoustic Vehicle Characterization DOI Creative Commons
Adam M. Terwilliger,

Joshua Siegel

Sensors, Journal Year: 2022, Volume and Issue: 22(20), P. 7736 - 7736

Published: Oct. 12, 2022

In a world dependent on road-based transportation, it is essential to understand automobiles. We propose an acoustic road vehicle characterization system as integrated approach for using sound captured by mobile devices enhance transparency and understanding of vehicles their condition non-expert users. develop implement novel deep learning cascading architectures, which we define conditional, multi-level networks that process raw audio extract highly granular insights understanding. To showcase the viability build multi-task convolutional neural network predicts cascades attributes misfire fault detection. train test these models synthesized dataset reflecting more than 40 hours augmented audio. Through fuel type, engine configuration, cylinder count aspiration type attributes, our CNN achieves 87.0% set accuracy detection demonstrates margins 8.0% 1.7% over naïve parallel baselines. explore experimental studies focused features, data augmentation, reliability. Finally, conclude with discussion broader implications, future directions, application areas this work.

Language: Английский

Computational bioacoustics with deep learning: a review and roadmap DOI Creative Commons
Dan Stowell

PeerJ, Journal Year: 2022, Volume and Issue: 10, P. e13152 - e13152

Published: March 21, 2022

Animal vocalisations and natural soundscapes are fascinating objects of study, contain valuable evidence about animal behaviours, populations ecosystems. They studied in bioacoustics ecoacoustics, with signal processing analysis an important component. Computational has accelerated recent decades due to the growth affordable digital sound recording devices, huge progress informatics such as big data, machine learning. Methods inherited from wider field deep learning, including speech image processing. However, tasks, demands data characteristics often different those addressed or music analysis. There remain unsolved problems, tasks for which is surely present many acoustic signals, but not yet realised. In this paper I perform a review state art learning computational bioacoustics, aiming clarify key concepts identify analyse knowledge gaps. Based on this, offer subjective principled roadmap learning: topics that community should aim address, order make most future developments AI informatics, use audio answering zoological ecological questions.

Language: Английский

Citations

197
Sounding the Call for a Global Library of Underwater Biological Sounds DOI Creative Commons
Miles Parsons, Tzu‐Hao Lin, T. Aran Mooney

et al.

Frontiers in Ecology and Evolution, Journal Year: 2022, Volume and Issue: 10

Published: Feb. 8, 2022

Aquatic environments encompass the world’s most extensive habitats, rich with sounds produced by a diversity of animals. Passive acoustic monitoring (PAM) is an increasingly accessible remote sensing technology that uses hydrophones to listen underwater world and represents unprecedented, non-invasive method monitor environments. This information can assist in delineation biologically important areas via detection sound-producing species or characterization ecosystem type condition, inferred from properties local soundscape. At time when worldwide biodiversity significant decline soundscapes are being altered as result anthropogenic impacts, there need document, quantify, understand biotic sound sources–potentially before they disappear. A step toward these goals development web-based, open-access platform provides: (1) reference library known unknown biological sources (by integrating expanding existing libraries around world); (2) data repository portal for annotated unannotated audio recordings single soundscapes; (3) training artificial intelligence algorithms signal classification; (4) citizen science-based application public users. Although individually, resources often met on regional taxa-specific scales, many not sustained and, collectively, enduring global database integrated has been realized. We discuss benefits such program provide, previous calls data-sharing libraries, challenges be overcome bring together bio- ecoacousticians, bioinformaticians, propagation experts, web engineers, processing specialists (e.g., intelligence) necessary support funding build sustainable scalable could address needs all contributors stakeholders into future.

Language: Английский

Citations

71
A review of automatic recognition technology for bird vocalizations in the deep learning era DOI Open Access
Jiangjian Xie,

Yujie Zhong,

Junguo Zhang

et al.

Ecological Informatics, Journal Year: 2022, Volume and Issue: 73, P. 101927 - 101927

Published: Nov. 25, 2022

Language: Английский

Citations

62
Effectiveness of acoustic indices as indicators of vertebrate biodiversity DOI Creative Commons
Slade Allen‐Ankins, Donald T. McKnight, Eric J. Nordberg

et al.

Ecological Indicators, Journal Year: 2023, Volume and Issue: 147, P. 109937 - 109937

Published: Jan. 25, 2023

Effective monitoring tools are key for tracking biodiversity loss and informing management intervention strategies. Passive acoustic promises to provide a cheap effective way monitor across large spatial temporal scales, however, extracting useful information from long-duration audio recordings still proves challenging. Recently, range of indices have been developed, which capture different aspects the soundscape, may estimate traditional measures. Here we investigated relationship between 13 obtained passive estimates various vertebrate taxonomic groupings manual surveys at six sites spanning over 20 degrees latitude along Australian east coast. We found number individual that correlated well with species richness, Shannon's diversity index, total count survey methods. Correlations were typically greater avian than anuran non-avian biodiversity. Acoustic also better richness index. Random forest models incorporating multiple provided more accurate predictions single alone. Out tested, cluster count, mid-frequency cover spectral density contributed greatest predictive ability models. Our results suggest could be tool certain groups. Further work is required understand how site-specific variables can incorporated into improve capabilities taxa besides avians, particularly anurans.

Language: Английский

Citations

25
Speech and speaker recognition using raw waveform modeling for adult and children’s speech: A comprehensive review DOI
Kodali Radha, Mohan Bansal, Ram Bilas Pachori

et al.

Engineering Applications of Artificial Intelligence, Journal Year: 2024, Volume and Issue: 131, P. 107661 - 107661

Published: Jan. 2, 2024

Language: Английский

Citations

11
Advancements in preprocessing, detection and classification techniques for ecoacoustic data: A comprehensive review for large-scale Passive Acoustic Monitoring DOI Creative Commons
Thomas R. Napier, Euijoon Ahn, Slade Allen‐Ankins

et al.

Expert Systems with Applications, Journal Year: 2024, Volume and Issue: 252, P. 124220 - 124220

Published: May 16, 2024

Computational ecoacoustics has seen significant growth in recent decades, facilitated by the reduced costs of digital sound recording devices and data storage. This progress enabled continuous monitoring vocal fauna through Passive Acoustic Monitoring (PAM), a technique used to record analyse environmental sounds study animal behaviours their habitats. While collection ecoacoustic become more accessible, effective analysis this information understand monitor populations remains major challenge. survey paper presents state-of-the-art approaches, with focus on applicability large-scale PAM. We emphasise importance PAM, as it enables extensive geographical coverage monitoring, crucial for comprehensive biodiversity assessment understanding ecological dynamics over wide areas diverse approach is particularly vital face rapid changes, provides insights into effects these changes broad array species ecosystems. As such, we outline most challenging tasks, including pre-processing, visualisation, labelling, detection, classification. Each evaluated according its strengths, weaknesses overall suitability recommendations are made future research directions.

Language: Английский

Citations

11
Exploring explainable AI methods for bird sound-based species recognition systems DOI
Nabanita Das,

Neelamadhab Padhy,

Nilanjan Dey

et al.

Multimedia Tools and Applications, Journal Year: 2024, Volume and Issue: 83(24), P. 64223 - 64253

Published: Jan. 15, 2024

Language: Английский

Citations

6
Improved analysis of deep bioacoustic embeddings through dimensionality reduction and interactive visualisation DOI Creative Commons
Francisco J. Bravo Sanchez, Nathan B. English, Md Rahat Hossain

et al.

Ecological Informatics, Journal Year: 2024, Volume and Issue: 81, P. 102593 - 102593

Published: April 12, 2024

Deep neural networks (DNN) are a popular tool to process environmental sounds and identify sound-producing animals, but it can be difficult understand the decision-making logic, particularly when does not produce expected results. Here we describe new enhanced visual interactive analysis of embeddings explore its application in bioacoustics. Embeddings output penultimate layer DNN, an N-dimensional vector that, only one step removed from final output, represent inner-workings DNN model. Using existing dimensionality reduction techniques converted into 2 or 3-dimensional arrays displayed scatterplots. By incorporating sound samples scatterplots developed aural interface demonstrate utility assessing performance trained bioacoustic models, facilitating post-processing results, error detection, input selection detection rare events, which reader experience online examples with publicly available code.

Language: Английский

Citations

5
Applications of machine learning to identify and characterize the sounds produced by fish DOI Creative Commons
Viviane R. Barroso, Fábio Contrera Xavier, Carlos E. L. Ferreira

et al.

ICES Journal of Marine Science, Journal Year: 2023, Volume and Issue: 80(7), P. 1854 - 1867

Published: Aug. 11, 2023

Abstract Aquatic ecosystems are constantly changing due to anthropic stressors, which can lead biodiversity loss. Ocean sound is considered an essential ocean variable, with the potential improve our understanding of its impact on marine life. Fish produce a variety sounds and their choruses often dominate underwater soundscapes. These have been used assess communication, behaviour, spawning location, biodiversity. Artificial intelligence provide robust solution detect classify fish sounds. However, main challenge in applying artificial recognize lack validated data for individual species. This review provides overview recent publications use machine learning, including deep detection, classification, identification. Key challenges limitations discussed, some points guide future studies also provided.

Language: Английский

Citations

13
A lightweight multi-sensory field-based dual-feature fusion residual network for bird song recognition DOI
Shipeng Hu,

Yihang Chu,

Lu Tang

et al.

Applied Soft Computing, Journal Year: 2023, Volume and Issue: 146, P. 110678 - 110678

Published: July 27, 2023

Language: Английский

Citations

11