Your browser doesn't support javascript.
loading
Show: 20 | 50 | 100
Results 1 - 3 de 3
Filter
Add more filters










Database
Language
Publication year range
1.
Sensors (Basel) ; 24(9)2024 May 01.
Article in English | MEDLINE | ID: mdl-38733008

ABSTRACT

Bats play a pivotal role in maintaining ecological balance, and studying their behaviors offers vital insights into environmental health and aids in conservation efforts. Determining the presence of various bat species in an environment is essential for many bat studies. Specialized audio sensors can be used to record bat echolocation calls that can then be used to identify bat species. However, the complexity of bat calls presents a significant challenge, necessitating expert analysis and extensive time for accurate interpretation. Recent advances in neural networks can help identify bat species automatically from their echolocation calls. Such neural networks can be integrated into a complete end-to-end system that leverages recent internet of things (IoT) technologies with long-range, low-powered communication protocols to implement automated acoustical monitoring. This paper presents the design and implementation of such a system that uses a tiny neural network for interpreting sensor data derived from bat echolocation signals. A highly compact convolutional neural network (CNN) model was developed that demonstrated excellent performance in bat species identification, achieving an F1-score of 0.9578 and an accuracy rate of 97.5%. The neural network was deployed, and its performance was evaluated on various alternative edge devices, including the NVIDIA Jetson Nano and Google Coral.


Subject(s)
Chiroptera , Echolocation , Neural Networks, Computer , Chiroptera/physiology , Chiroptera/classification , Animals , Echolocation/physiology , Acoustics , Signal Processing, Computer-Assisted , Vocalization, Animal/physiology
2.
J Hered ; 103(1): 64-70, 2012.
Article in English | MEDLINE | ID: mdl-22140252

ABSTRACT

The Asian houbara bustard Chlamydotis macqueenii is a partial migrant of conservation concern found in deserts of central Asia and the Middle East. In the southern part of the species range, resident populations have been greatly fragmented and reduced by sustained human pressure. In the north, birds migrate from breeding grounds between West Kazakhstan and Mongolia to wintering areas in the Middle East and south central Asia. Extensive satellite tracking has shown substantial partitioning in migration routes and wintering grounds, suggesting a longitudinal barrier to present-day gene flow among migrants. In this context, we explored genetic population structure using 17 microsatellite loci and sampling 108 individuals across the range. We identified limited but significant overall differentiation (F(CT) = 0.045), which was overwhelmingly due to the differentiation of resident Arabian populations, particularly the one from Yemen, relative to the central Asian populations. Population structure within the central Asian group was not detectable with the exception of subtle differentiation of West Kazakh birds on the western flyway, relative to eastern populations. We interpret these patterns as evidence of recent common ancestry in Asia, coupled with a longitudinal barrier to present-day gene flow along the migratory divide, which has yet to translate into genetic divergence. These results provide key parameters for a coherent conservation strategy aimed at preserving genetic diversity and migration routes.


Subject(s)
Animal Migration , Birds/genetics , Endangered Species , Animals , Asia , Cluster Analysis , Egypt , Genetic Variation , Heterozygote , Microsatellite Repeats , Phylogeography
3.
PLoS One ; 6(6): e20570, 2011.
Article in English | MEDLINE | ID: mdl-21687684

ABSTRACT

Information on migratory pathways and connectivity is essential to understanding population dynamics and structure of migrant species. Our manuscript uses a unique dataset, the fruit of 103 individual Asian houbara bustards captured on their breeding grounds in Central Asia over 15 years and equipped with satellite transmitters, to provide a better understanding of migratory pathways and connectivity; such information is critical to the implementation of biologically sound conservation measures in migrant species. At the scale of the distribution range we find substantial migratory connectivity, with a clear separation of migration pathways and wintering areas between western and eastern migrants. Within eastern migrants, we also describe a pattern of segregation on the wintering grounds. But at the local level connectivity is weak: birds breeding within the limits of our study areas were often found several hundreds of kilometres apart during winter. Although houbara wintering in Arabia are known to originate from Central Asia, out of all the birds captured and tracked here not one wintered on the Arabian Peninsula. This is very likely the result of decades of unregulated off-take and severe habitat degradation in this area. At a time when conservation measures are being implemented to safeguard the long-term future of this species, this study provides critical data on the spatial structuring of populations.


Subject(s)
Animal Migration , Birds , Telemetry , Animals , Asia , Birds/physiology , Conservation of Natural Resources , Female , Flight, Animal/physiology , Male , Population Dynamics , Satellite Communications , Seasons , Time Factors
SELECTION OF CITATIONS
SEARCH DETAIL
...