Variability in echolocation call design of 26 Swiss bat species: consequences, limits and options for automated field identification with a synergetic pattern recognition approach

Abstract

Pattern recognition algorithms offer a promising approach to recognizing bat species by their echolocation calls. Automated systems like synergetic classifiers may contribute significantly to operator-independent species identification in the field. However, it necessitates the assembling of an appropriate database of reference calls, a task far from trivial. We present data on species specific flexibility in call parameters of all Swiss bat species (except

Local concentration of foraging noctule bats (Nyctalus noctula) as a possible tool to assess the density of bats in large forest complexes

“…After sunset, echolocation calls were also recorded (Avisoft UltraSoundGate running Avisoft-Recorder software, sampling rate 384 kHz, 16 bit; Avisoft) and later analyzed in Sas Lab Pro. Visual observation, pictures, video records, and voice recordings confirmed observations of noctule bats (Obrist et al, 2004;Walters et al, 2012). Leisler's bats, Nyctalus leisleri, are also present in the region, and can be mistaken for noctule bats (Russo and Jones, 2002;Obrist et al, 2004;Ruczyński et al, 2010).…”

A holtfa és egyéb erdőökológiai tényezők jelentősége a denevérek számára

“…A fajhatározásnál a legfőbb paraméterek a hanggörbe formája, maximális és minimális frekvenciaértéke, az aktív hangtartomány hossza és a hangimpulzus legerősebb jelének frekvenciaértéke, de ezeken túl több egyéb faj specifikus jellemzőket is vizsgálunk a fajhatározás során. A fajcsoportokra jellemző határozóbélyegeket szakirodalmakból vettük át (Ahlén1981, Ahlén & Baagoe 1999, Barataud 2015, Dietz & Kiefer 2014, Fenton& Bell 1981, Griffin et al 1960, Jones 1999, Obrist et al 2004, Russo & Jones 2002, Vaughan et al 1997, illetve részben saját gyűjtésekre és megfigyelésekre alapoztuk. Az egyes paramétereket a számítógépes programunk olvassa be és a változók segítségével egyezőségi valószínűség lévén azonosítja be a hangokat fajra, fajcsoportra vagy nemzetségre.…”

An Extensive Review of Methods of Identification of Bat Species through Acoustics

“…Support Vector Machines(SVM) [18][19][20], Artificial Neural Networks(ANN) [21] and Synergetic Pattern Recognition [22] are the frequently used to classify bats. Redgwell et.al.…”

“…Although these previous studies accurately classify many of the species on which they are trained and prove the concept and value of quantitative call identification, they have not been made publicly accessible and are restricted to a regional(often national) level (eg. Venezuela [8]; Greece; Italy [13]; Meditteranean area [23]; UK [24]; Switzerland [22];). Therefore, they cannot be used to generate comparable classifications at a continental scale [2].…”

“…[22] have found a variability in echolocation call design of twenty six Swiss bat species and have put forth the consequences, limits and options for automated field identification with a synergetic pattern recognition approach. They used pattern recognition algorithms for recognizing bat species by their echolocation calls.…”