scholarly journals Combining machine learning and a universal acoustic feature-set yields efficient automated monitoring of ecosystems

2019 ◽  
Author(s):  
Sarab S. Sethi ◽  
Nick S. Jones ◽  
Ben D. Fulcher ◽  
Lorenzo Picinali ◽  
Dena J. Clink ◽  
...  
Keyword(s):  
Environmental Changes ◽  
Automatic Identification ◽  
Acoustic Feature ◽  
Natural Habitats ◽  
Ecosystem Monitoring ◽  
Environmental Behaviour ◽  
Acoustic Data ◽  
Ecosystem Level ◽  
The Common ◽  
Acoustic Space

Natural habitats are being impacted by human pressures at an alarming rate. Monitoring these ecosystem-level changes often requires labour-intensive surveys that are unable to detect rapid or unanticipated environmental changes. Here we developed a generalisable, data-driven solution to this challenge using eco-acoustic data. We exploited a convolutional neural network to embed ecosystem soundscapes from a wide variety of biomes into a common acoustic space. In both supervised and unsupervised modes, this allowed us to accurately quantify variation in habitat quality across space and in biodiversity through time. On the scale of seconds, we learned a typical soundscape model that allowed automatic identification of anomalous sounds in playback experiments, paving the way for real-time detection of irregular environmental behaviour including illegal activity. Our highly generalisable approach, and the common set of features, will enable scientists to unlock previously hidden insights from eco-acoustic data and offers promise as a backbone technology for global collaborative autonomous ecosystem monitoring efforts.

scholarly journals Characterizing soundscapes across diverse ecosystems using a universal acoustic feature set

2020 ◽  
Vol 117 (29) ◽  
pp. 17049-17055 ◽  
Author(s):  
Sarab S. Sethi ◽  
Nick S. Jones ◽  
Ben D. Fulcher ◽  
Lorenzo Picinali ◽  
Dena Jane Clink ◽  
...  
Keyword(s):  
Environmental Changes ◽  
Automated Detection ◽  
Automatic Identification ◽  
Acoustic Feature ◽  
Natural Habitats ◽  
Ecosystem Monitoring ◽  
Acoustic Data ◽  
Ecosystem Level ◽  
The Common ◽  
Acoustic Space

Natural habitats are being impacted by human pressures at an alarming rate. Monitoring these ecosystem-level changes often requires labor-intensive surveys that are unable to detect rapid or unanticipated environmental changes. Here we have developed a generalizable, data-driven solution to this challenge using eco-acoustic data. We exploited a convolutional neural network to embed soundscapes from a variety of ecosystems into a common acoustic space. In both supervised and unsupervised modes, this allowed us to accurately quantify variation in habitat quality across space and in biodiversity through time. On the scale of seconds, we learned a typical soundscape model that allowed automatic identification of anomalous sounds in playback experiments, providing a potential route for real-time automated detection of irregular environmental behavior including illegal logging and hunting. Our highly generalizable approach, and the common set of features, will enable scientists to unlock previously hidden insights from acoustic data and offers promise as a backbone technology for global collaborative autonomous ecosystem monitoring efforts.

scholarly journals Visual Comparison of Phylogenetic Trees Through iPhyloC, a New Interactive Web-based Framework

2021 ◽  
Author(s):  
Muhsen Hammoud ◽  
Charles Morphy Santos ◽  
Joao Paulo Gois
Keyword(s):  
Phylogenetic Trees ◽  
Binary Trees ◽  
Automatic Identification ◽  
Structural Comparison ◽  
Web Based ◽  
Visual Comparison ◽  
Large Trees ◽  
Cross Platform ◽  
The Common ◽  
Intuitive Design

Current side-by-side phylogenetic trees comparison frameworks face two issues: (1) accepting binary trees as input, and (2) assuming input trees having identical or highly overlapping taxa. We present a task abstraction of the problem of side-by-side comparison of two phylogenetic trees and propose a set-based measure for detailed structural comparison between two phylogenetic trees, which can be non-binary and not highly overlapping. iPhyloC is an interactive web-based framework including automatic identification of the common taxa in both trees, comparing input trees in several modes, intuitive design, high usability, scalability to large trees, and cross-platform support. iPhyloC was tested in hypothetical and real biological examples.

Turning Up the Volume of Inner Speech

2018 ◽  
pp. 94-113
Author(s):  
Angela Frattarola
Keyword(s):  
Popular Culture ◽  
James Joyce ◽  
Turn Of The Century ◽  
Inner Speech ◽  
Historical Study ◽  
Stream Of Consciousness ◽  
Surrounding World ◽  
The Common ◽  
Acoustic Space

Chapter 4 questions how the common turn-of-the-century practice of listening to the telephone, phonograph, and radio through headphones may have aided modernists in turning up the volume and recording interior monologue—one’s “inner speech” that sounds out within the auditory imagination. Using Jonathan Sterne’s historical study of how headphones created a “private acoustic space,” this chapter postulates that listening to voices and music through headphones created a new sense of a personal and aesthetically objectified space within one’s head. Just as headphones brought unfamiliar sounds and voices into one’s private headspace, James Joyce represents the stream of consciousness as a collage of voices and sounds from literature, religion, popular culture, and the soundscape. In Ulysses (1922), Joyce creates an auditory cosmopolitanism, by allowing the languages and sounds of the surrounding world to penetrate and influence the interior monologues of his characters.

Acoustic Feature Analysis for Hypernasality Detection in Children

2008 ◽  
pp. 16-22
Author(s):  
Genaro Daza ◽  
Luis Gonzalo Sánchez ◽  
Franklin A. Sepúlveda ◽  
Castellanos D. Germán
Keyword(s):  
Feature Selection ◽  
Multivariate Analysis ◽  
Latent Variable ◽  
Search Algorithms ◽  
Feature Analysis ◽  
Automatic Identification ◽  
Acoustic Features ◽  
Acoustic Feature ◽  
Analysis Techniques ◽  
Heuristic Search Algorithms

The present work analyzes the statistical effectiveness of different acoustic features in the automatic identification of hypernasality. Acoustic features reflect part of information contained in perceptual analysis; in part, due to their estimation is derived directly or indirectly from the vocal cords behavior. Consequently, it is convenient to apply multivariate analysis techniques in determining the effectiveness of voice features. The effectiveness is studied by using multivariate analysis techniques that are meant for feature extraction and feature selection, as well (latent variable models, heuristic search algorithms).

scholarly journals Disease epidemic and a marine heat wave are associated with the continental-scale collapse of a pivotal predator (Pycnopodia helianthoides)

2019 ◽  
Vol 5 (1) ◽  
pp. eaau7042 ◽  
Author(s):  
C. D. Harvell ◽  
D. Montecino-Latorre ◽  
J. M. Caldwell ◽  
J. M. Burt ◽  
K. Bosley ◽  
...  
Keyword(s):  
Disease Outbreaks ◽  
Sea Surface ◽  
Sea Star ◽  
Wasting Disease ◽  
Infectious Disease Outbreaks ◽  
Continental Scale ◽  
Endemic Birds ◽  
Ecosystem Level ◽  
The Common ◽  
Trawl Surveys

Multihost infectious disease outbreaks have endangered wildlife, causing extinction of frogs and endemic birds, and widespread declines of bats, corals, and abalone. Since 2013, a sea star wasting disease has affected >20 sea star species from Mexico to Alaska. The common, predatory sunflower star (Pycnopodia helianthoides), shown to be highly susceptible to sea star wasting disease, has been extirpated across most of its range. Diver surveys conducted in shallow nearshore waters (n= 10,956; 2006–2017) from California to Alaska and deep offshore (55 to 1280 m) trawl surveys from California to Washington (n= 8968; 2004–2016) reveal 80 to 100% declines across a ~3000-km range. Furthermore, timing of peak declines in nearshore waters coincided with anomalously warm sea surface temperatures. The rapid, widespread decline of this pivotal subtidal predator threatens its persistence and may have large ecosystem-level consequences.

Acoustic Feature-Based Clustering Analysis for Phonetic Degree of Chinese Phonogram

2012 ◽  
Vol 459 ◽  
pp. 518-522
Author(s):  
Min Ma
Keyword(s):  
Clustering Analysis ◽  
Chinese Characters ◽  
Acoustic Features ◽  
Acoustic Feature ◽  
Empirical Estimation ◽  
Empirical Claim ◽  
Feature Based ◽  
Inherent Problem ◽  
The Common

A significant portion of the Chinese characters is phonogram, whose phonetic part can be used for overall sound inference. Phonetic degree is an inherent problem in the inference because low phonetic degree implies little phonetic dependence between the phonogram and its phonetic components. Solving the phonetic degree problem requires association each phonogram with the acoustic features. This paper introduces acoustic feature-based clustering, a classifying model that divides the common phonogram by defining new similarity of the sounds. This allows phonetic degree to be evaluated more reasonable. We demonstrate the clustering outperformed the traditional empirical estimation by having more accurate and real expressiveness. Acoustic feature-based clustering output 48.6% as phonetic degree, less than the empirical claim which is around 75%. As a clustering classifier, our model is competitive with a much clearer boundary on the phonogram dataset

scholarly journals To the study of herpetofauna of "Yelanetskyi steppe" nature reserve and adjoined territоries

2019 ◽  
Vol 78 (2) ◽  
pp. 35-40
Author(s):  
O. Nekrasova ◽  
O. Marushchak ◽  
O. Oskyrko
Keyword(s):  
Nature Reserve ◽  
Original Data ◽  
Natural Habitats ◽  
Amphibian Species ◽  
Marsh Frog ◽  
Pond Turtle ◽  
Green Toad ◽  
Reptile Species ◽  
Sand Lizard ◽  
The Common

As a result of monitoring research conducted in 2015-2017 on the territory of the nature reserve “Yelanetskyi steppe" and adjacent areas, 5 amphibian species (fire-bellied toad, green toad, common spadefoot, marsh frog, H. arborea) and 7 species of reptiles (sand lizard, green lizard, blotched snake, large whipsnake, grass snake, dice snake, pond turtle). The presence of some of the species specified in the project of the reserve creation, namely pond turtle, green lizard, large whipsnake, steppe viper, common toad and common newt has not been confirmed on the reserve's territory. The presence of 8 species was registered directly on the territory of the reserve, and another 4 species were registered in the vicinity of the rivers Gromokliya and Gniloy Yelanets. The most numerous among the identified amphibians are the semi-terrestrial species, such as the common spadefoot and the marsh frog. Sand lizard is the most widespread reptile species within the reserve territory and its population is characterized by an exceptional variety of coloration morphology. It should be noted that for more than a 30-year period a unique numerous population of the blotched snake has been preserved here. According to original data, more than two dozen snake specimens were registered in the vicinity of the Rosa beam. Due to climatic changes, it is proposed to expand the reserve's territory in ecotone river areas where there are finds of blotched snakes and large whipsnakes (RBU, 2009), green lizards (RBU, 2009) and pond turtles (IUCN (LR/NT)) to conserve biodiversity and protect rare species. In particular, the expansion of the boundaries of the reserve is necessary in the context of climate change, as it leads to a shift in the natural habitats of certain amphibian and reptile species, and is also an important step towards the expansion of the Emerald Network of Ukraine

scholarly journals Bowhead and beluga whale acoustic detections in the western Beaufort Sea 2008–2018

PLoS ONE ◽  
2021 ◽  
Vol 16 (6) ◽  
pp. e0253929
Author(s):  
Kathleen M. Stafford ◽  
John J. Citta ◽  
Stephen R. Okkonen ◽  
Jinlun Zhang
Keyword(s):  
Sea Ice ◽  
Environmental Changes ◽  
Beaufort Sea ◽  
Zooplankton Biomass ◽  
Beluga Whale ◽  
Environmental Drivers ◽  
Cetacean Species ◽  
Sea Transport ◽  
Bowhead Whales ◽  
Acoustic Data

The Distributed Biological Observatory (DBO) was established to detect environmental changes in the Pacific Arctic by regular monitoring of biophysical responses in each of 8 DBO regions. Here we examine the occurrence of bowhead and beluga whale vocalizations in the western Beaufort Sea acquired by acoustic instruments deployed from September 2008-July 2014 and September 2016-October 2018 to examine inter-annual variability of these Arctic endemic species in DBO Region 6. Acoustic data were collected on an oceanographic mooring deployed in the Beaufort shelfbreak jet at ~71.4°N, 152.0°W. Spectrograms of acoustic data files were visually examined for the presence or absence of known signals of bowhead and beluga whales. Weekly averages of whale occurrence were compared with outputs of zooplankton, temperature and sea ice from the BIOMAS model to determine if any of these variables influenced whale occurrence. In addition, the dates of acoustic whale passage in the spring and fall were compared to annual sea ice melt-out and freeze-up dates to examine changes in phenology. Neither bowhead nor beluga whale migration times changed significantly in spring, but bowhead whales migrated significantly later in fall from 2008–2018. There were no clear relationships between bowhead whales and the environmental variables, suggesting that the DBO 6 region is a migratory corridor, but not a feeding hotspot, for this species. Surprisingly, beluga whale acoustic presence was related to zooplankton biomass near the mooring, but this is unlikely to be a direct relationship: there are likely interactions of environmental drivers that result in higher occurrence of both modeled zooplankton and belugas in the DBO 6 region. The environmental triggers that drive the migratory phenology of the two Arctic endemic cetacean species likely extend from Bering Sea transport of heat, nutrients and plankton through the Chukchi and into the Beaufort Sea.

scholarly journals Genome features of common vetch (Vicia sativa) in natural habitats

2021 ◽  
Author(s):  
Kenta Shirasawa ◽  
Shunichi Kosugi ◽  
Kazuhiro Sasaki ◽  
Andrea Ghelfi ◽  
Koei Okazaki ◽  
...  
Keyword(s):  
De Novo ◽  
Population Level ◽  
Wild Plants ◽  
Wild Plant ◽  
Vicia Sativa ◽  
Natural Environments ◽  
Common Vetch ◽  
Natural Habitats ◽  
Crop Species ◽  
The Common

AbstractWild plants are often tolerant to biotic and abiotic stresses in their natural environments, whereas domesticated plants such as crops frequently lack such resilience. This difference is thought to be due to the high levels of genome heterozygosity in wild plant populations and the low levels of heterozygosity in domesticated crop species. In this study, common vetch (Vicia sativa) was used as a model to examine this hypothesis. The common vetch genome (2n = 14) was estimated as 1.8 Gb in size. Genome sequencing produced a reference assembly that spanned 1.5 Gb, from which 31,146 genes were predicted. Using this sequence as a reference, 24,118 single nucleotide polymorphisms were discovered in 1,243 plants from 12 natural common vetch populations in Japan. Common vetch genomes exhibited high heterozygosity at the population level, with lower levels of heterozygosity observed at specific genome regions. Such patterns of heterozygosity are thought to be essential for adaptation to different environments. These findings suggest that high heterozygosity at the population level would be required for wild plants to survive under natural conditions while allowing important gene loci to be fixed to adapt the conditions. The resources generated in this study will provide insights into de novo domestication of wild plants and agricultural enhancement.HighlightSequence analysis of the common vetch (Vicia sativa) genome and SNP genotyping across natural populations revealed nucleotide diversity levels associated with native population environments.

Sign in / Sign up

Export Citation Format

Share Document