.sits_keras_binary_class

<p>Predicted values from the keras model
for the binary classification case
(data.table with one column)</p>

prediction

<p>For binary classification, the prediction function produces only
one column (the probability of label 1). For compatibility with the
code in the sits package, this function includes a second column
in the prediction values to match the results of multi-class classification.</p>

internal

A set of tools for working with satellite image time series, both as individual data or as part of data cubes.
Builds data cubes from collections in AWS, Brazil Data Cube, and Digital Earth Africa.
Provides different visualisation methods for image time series.
Provides smoothing methods for noisy time series.
Includes functions for smoothing based on Bayesian inference.
Enables different clustering methods, including dendrograms and self-organized maps (SOM).
Matches noiseless patterns with noisy time series using the time-weighted dynamic time warping (TWDTW) method for shape recognition.
Provides machine learning methods for time series classification, including support vector machines (SVM), random forests and deep learning.
Minimum recommended requirements: 8 GB RAM and 1 CPU dual-core.

Gilberto Camara

sits

Satellite Image Time Series Analysis for Remote Sensing Data Cubes

Rolf Simoes

Felipe Souza

Lorena Santos

Alexandre Carvalho

Pedro Andrade

Karine Ferreira

Alber Sanchez

Gilberto Queiroz

.sits_keras_binary_class function

Adjust keras prediction for the binary classification case — .sits_keras_binary_class

Adjust keras prediction for the binary classification case

.sits_keras_binary_class: Adjust keras prediction for the binary classification case

Description

Usage

Arguments

Value