gibbonR: gibbonR

In DenaJGibbon/gibbonR: gibbonR: An R package for the detection and classification of acoustic signals using machine learning

gibbonR

Description

This function identifies sound events using band-limited energy summation and then classifies the sound events using a trained support vector machine or random forest algorithm.

Usage

{input, input.type='list', feature.df,model.type.list=c("SVM"), tune = FALSE, target.signal = "female.gibbon",
short.wav.duration=300,min.freq = 400, max.freq = 2000,
noise.quantile.val=0.5, minimum.separation =5, n.windows = 9, num.cep = 12, spectrogram.window =1600,
pattern.split = ".wav", min.signal.dur = 4, maximum.separation =1,max.sound.event.dur = 12,
probability.thresh.svm = 0.75, probability.thresh.rf = 0.75, wav.output = "TRUE", output.dir = getwd(),
swift.time=TRUE,time.start=6,time.stop=12, write.table.output=TRUE,verbose=TRUE, random.sample='NA'}

Arguments

input	Either full path to directory containing .wav files, a list of .wav files, or a the path to a single .wav file
input.type	Either 'directory', 'list' or 'wav'
feature.df	Data frame of features from labeled sound files; first column must be class labels
model.type.list	Which machine learning model to use; SVM or RF
tune	Logical; if want to use 'tune' function for SVM; NOTE: for large datasets adds significant computing time
target.signal	Labeled signal(s) of interest from training data (feature.df); can include multiple classes.
short.wav.duration	Duration (s) to divide longer sound file to increase processing efficiency
min.freq	Minimum frequency (Hz) of signal of interest
max.freq	Maximum frequency (Hz) of signal of interest
noise.quantile.val	A quantile value between 0 to 1 for the band energy summation
minimum.separation	The minimum number of consecutive time windows that signals must be separated by to be considered a separate sound event
n.windows	Number of time windows to calculate for MFCCs
num.cep	Number of cepstra coefficients to calculate for MFCCs
spectrogram.window	Window length for spectrogram analysis (input to spectro fuction from 'seewave')
pattern.split	Pattern to find and remove to create full sound file name; currently set to ".wav"
min.signal.dur	The minimum duration (s) sound events must be to be considered sound events
maximum.separation	The maximum number of consecutive time windows that signals must be separated by to be considered a separate sound event
max.sound.event.dur	The maximum duration (s) sound events must be to be considered sound events; NOTE this only happens when writing text file
probability.thresh.svm	Probability threshold (provided by SVM) to be considered as target signal
probability.thresh.rf	Probability threshold (provided by RF) to be considered as target signal
wav.output	Logical; output .wav files of detections in specified directory
output.dir	Specified output directory; set to current working directory
swift.time	If file name is in structure recorder_YYYYMMDD_HHMMSS can subset files based on specific times
time.start	Time recordings start (hour)
time.stop	Time recordings stop (hour)
write.table.output	Logical; write Raven selection tables to output directory
verbose	Logical; print out steps
random.sample	If a random subset of files in a directory are desired specify a value, otherwise 'NA'

Value

If write.table.output=TRUE writes a .txt file for each sound file with detections

If write.table.output=TRUE writes a .txt file for each sound file with detections

Examples

MFCCFunction(input.dir = "FocalRecordings",min.freq = 400,max.freq=2500)

DenaJGibbon/gibbonR documentation built on Nov. 28, 2024, 2:52 a.m.