• Publications
  • Influence
Acoustic identification of twelve species of echolocating bat by discriminant function analysis and artificial neural networks.
TLDR
This is the first published study to use artificial neural networks to classify the echolocation calls of bats to species level and the use of a hierarchical classification system had little effect on correct classification rates by discriminant function analysis but did improve rates achieved by perceptrons.
Kiwi Forego Vision in the Guidance of Their Nocturnal Activities
TLDR
It is proposed that the Kiwi visual system has undergone adaptive regressive evolution driven by the trade-off between the relatively low rate of gain of visual information that is possible at low light levels, and the metabolic costs of extracting that information.
A continental-scale tool for acoustic identification of European bats
TLDR
iBatsID is the first freely available and easily accessible continental- scale bat call classifier, providing the basis for standardized, continental acoustic bat monitoring in Europe, and can provide key information to managers and conservation planners on distribution changes and changes in bat species activity through time.
Terrestrial locomotion of the New Zealand short-tailed bat Mystacina tuberculata and the common vampire bat Desmodus rotundus
TLDR
The kinematics of locomotion in both species, and the kinetics of locomotions in M. tuberculata are described, which observed that both species possess symmetrical lateral-sequence gaits similar to the kinematically defined walks of a broad range of tetrapods.
Evolution of Brain Size in the Palaeognath Lineage, with an Emphasis on New Zealand Ratites
TLDR
The results indicate that the Palaeognaths possess relatively smaller brains and cerebral hemispheres than the Neognaths, with the exception of the kiwi radiation (Apteryx spp.), and challenge the current rules that govern changes in relative brain size in birds.
ADVANTAGES AND DISADVANTAGES OF TECHNIQUES FOR TRANSFORMING AND ANALYZING CHIROPTERAN ECHOLOCATION CALLS
TLDR
Bat researchers currently use a variety of techniques that transform echolocation calls into audible frequencies and allow the spectral content of a signal to be viewed and analyzed, and it is important for bat researchers to be familiar with the advantages and disadvantages of each technique.
Classification of Echolocation Calls from 14 Species of Bat by Support Vector Machines and Ensembles of Neural Networks
TLDR
Five parameters were most important for classifying calls correctly while seven others contributed little to classification performance, and both SVMs and ENNs outperformed DFA for every species.
Echolocation Calls and Wing Morphology of Bats from the West Indies
TLDR
Echolocation calls of 119 bats belonging to 12 species in three families from Antillean islands of Puerto Rico, Dominica, and St. Vincent were recorded by using time-expansion methods to describe the wing morphology of each taxon and related to the structure of its echolocated calls and its foraging ecology.
Search-phase echolocation calls of the New Zealand lesser short-tailed bat (Mystacina tuberculata) and long-tailed bat (Chalinolobus tuberculatus)
TLDR
The search-phase echolocation calls of lesser short-tailed bats and long-tailed bat showed regional variation, and discriminant function analysis was able to fit calls to regional groups with a high rate of success.
Human vs. machine : identification of bat species from their echolocation calls by humans and by artificial neural networks
TLDR
This work compared humans with artificial neural networks (ANNs) in their ability to classify short recordings of bat echolocation calls of variable signal to noise ratios, which are typical of those obtained from remote automated recording systems that are often used in large-scale ecological studies.
...
...