| Title: | Detection of Chaotic and Regular Intervals in the Data |
|---|---|
| Description: | Finds regular and chaotic intervals in the data using the 0-1 test for chaos proposed by Gottwald and Melbourne (2004) <DOI:10.1137/080718851>. |
| Authors: | Radek Halfar [aut, cre] |
| Maintainer: | Radek Halfar <[email protected]> |
| License: | GPL-3 |
| Version: | 0.1.0 |
| Built: | 2024-11-04 04:48:55 UTC |
| Source: | https://github.com/cran/dydea |
Find chaotic motions in the data.
find_chaos(data, window_length, skip_window, skip_test01 = 1, test01_thresh = 0.05, find_thresh = 20)find_chaos(data, window_length, skip_window, skip_test01 = 1, test01_thresh = 0.05, find_thresh = 20)
data |
Analyzed data. |
window_length |
Length of the window for in which the 0-1 test for chaos will be computed. |
skip_window |
Length of the skip of the window moving in the data. |
skip_test01 |
Length of the skip to take data for calculation the 0-1 test for chaos in the window. |
test01_thresh |
The threshold to decide about motion. |
find_thresh |
Precision of found intervals. |
The list of optimized chaotic motion borders.
# Calculate the logistic map. cons <- 0.5 data.len <- 17000 chaos.start <- c(5536, 9768) vec.x <- matrix(cons, data.len, 1) vec.x[1] <- (2^0.5)/2 for (i in 2:data.len){ # x_n+1 = r*x_n(1-x_n) vec.x[i] <- 3.7*vec.x[i-1]*(1-vec.x[i-1]) } vec.x[1:(chaos.start[1]-1)] <-cons vec.x[(chaos.start[2]+1):data.len] <-cons tr1 <- seq(from = cons, to = vec.x[chaos.start[1]], length.out = 2001) tr2 <- seq(from = vec.x[chaos.start[2]], to = cons, length.out = 2001) vec.x[(chaos.start[1]-2000):chaos.start[1]] <- tr1 vec.x[chaos.start[2]:(chaos.start[2]+2000)] <- tr2 # Find chaotic intervals in vec.x and plot results. chaotic_borders <- find_chaos(vec.x, "skip_window" = 1000, "window_length" = 3000, "find_thresh" = 300)# Calculate the logistic map. cons <- 0.5 data.len <- 17000 chaos.start <- c(5536, 9768) vec.x <- matrix(cons, data.len, 1) vec.x[1] <- (2^0.5)/2 for (i in 2:data.len){ # x_n+1 = r*x_n(1-x_n) vec.x[i] <- 3.7*vec.x[i-1]*(1-vec.x[i-1]) } vec.x[1:(chaos.start[1]-1)] <-cons vec.x[(chaos.start[2]+1):data.len] <-cons tr1 <- seq(from = cons, to = vec.x[chaos.start[1]], length.out = 2001) tr2 <- seq(from = vec.x[chaos.start[2]], to = cons, length.out = 2001) vec.x[(chaos.start[1]-2000):chaos.start[1]] <- tr1 vec.x[chaos.start[2]:(chaos.start[2]+2000)] <- tr2 # Find chaotic intervals in vec.x and plot results. chaotic_borders <- find_chaos(vec.x, "skip_window" = 1000, "window_length" = 3000, "find_thresh" = 300)
Find regular and chaotic motions in the data and plots the results.
find_motions(data, window_length, skip_window, skip_test01 = 1, test01_thresh = 0.05, find_thresh = 20)find_motions(data, window_length, skip_window, skip_test01 = 1, test01_thresh = 0.05, find_thresh = 20)
data |
Analyzed data. |
window_length |
Length of the window for in which the 0-1 test for chaos will be computed |
skip_window |
Length of the skip of the window moving in the data. |
skip_test01 |
Length of the skip to take data for calculation the 0-1 test for chaos in the window. |
test01_thresh |
The threshold to decide about motion. |
find_thresh |
Precision of found intervals. |
The list of optimized regular and chaotic motion borders.
# Calculate the logistic map. cons <- 0.5 data.len <- 17000 chaos.start <- c(5536, 9768) vec.x <- matrix(cons, data.len, 1) vec.x[1] <- (2^0.5)/2 for (i in 2:data.len){ # x_n+1 = r*x_n(1-x_n) vec.x[i] <- 3.7*vec.x[i-1]*(1-vec.x[i-1]) } vec.x[1:(chaos.start[1]-1)] <-cons vec.x[(chaos.start[2]+1):data.len] <-cons tr1 <- seq(from = cons, to = vec.x[chaos.start[1]], length.out = 2001) tr2 <- seq(from = vec.x[chaos.start[2]], to = cons, length.out = 2001) vec.x[(chaos.start[1]-2000):chaos.start[1]] <- tr1 vec.x[chaos.start[2]:(chaos.start[2]+2000)] <- tr2 # Find chaotic and regular intervals in vec.x and plot results. find_motions(vec.x, "skip_window" = 1000, "window_length" = 3000, "find_thresh" = 300)# Calculate the logistic map. cons <- 0.5 data.len <- 17000 chaos.start <- c(5536, 9768) vec.x <- matrix(cons, data.len, 1) vec.x[1] <- (2^0.5)/2 for (i in 2:data.len){ # x_n+1 = r*x_n(1-x_n) vec.x[i] <- 3.7*vec.x[i-1]*(1-vec.x[i-1]) } vec.x[1:(chaos.start[1]-1)] <-cons vec.x[(chaos.start[2]+1):data.len] <-cons tr1 <- seq(from = cons, to = vec.x[chaos.start[1]], length.out = 2001) tr2 <- seq(from = vec.x[chaos.start[2]], to = cons, length.out = 2001) vec.x[(chaos.start[1]-2000):chaos.start[1]] <- tr1 vec.x[chaos.start[2]:(chaos.start[2]+2000)] <- tr2 # Find chaotic and regular intervals in vec.x and plot results. find_motions(vec.x, "skip_window" = 1000, "window_length" = 3000, "find_thresh" = 300)
Find regular motions in the data.
find_regularity(data, window_length, skip_window, skip_test01 = 1, test01_thresh = 0.05, find_thresh = 20)find_regularity(data, window_length, skip_window, skip_test01 = 1, test01_thresh = 0.05, find_thresh = 20)
data |
Analyzed data. |
window_length |
Length of the window for in which the 0-1 test for chaos will be computed. |
skip_window |
Length of the skip of the window moving in the data. |
skip_test01 |
Length of the skip to take data for calculation the 0-1 test for chaos in the window. |
test01_thresh |
The threshold to decide about motion. |
find_thresh |
Precision of found intervals. |
The list of optimized regular and chaotic motion borders.
# Calculate the logistic map. cons <- 0.5 data.len <- 17000 chaos.start <- c(5536, 9768) vec.x <- matrix(cons, data.len, 1) vec.x[1] <- (2^0.5)/2 for (i in 2:data.len){ # x_n+1 = r*x_n(1-x_n) vec.x[i] <- 3.7*vec.x[i-1]*(1-vec.x[i-1]) } vec.x[1:(chaos.start[1]-1)] <-cons vec.x[(chaos.start[2]+1):data.len] <-cons tr1 <- seq(from = cons, to = vec.x[chaos.start[1]], length.out = 2001) tr2 <- seq(from = vec.x[chaos.start[2]], to = cons, length.out = 2001) vec.x[(chaos.start[1]-2000):chaos.start[1]] <- tr1 vec.x[chaos.start[2]:(chaos.start[2]+2000)] <- tr2 # Find regular intervals in vec.x and plot results. regular_borders <- find_regularity(vec.x, "skip_window" = 1000, "window_length" = 3000, "find_thresh" = 300)# Calculate the logistic map. cons <- 0.5 data.len <- 17000 chaos.start <- c(5536, 9768) vec.x <- matrix(cons, data.len, 1) vec.x[1] <- (2^0.5)/2 for (i in 2:data.len){ # x_n+1 = r*x_n(1-x_n) vec.x[i] <- 3.7*vec.x[i-1]*(1-vec.x[i-1]) } vec.x[1:(chaos.start[1]-1)] <-cons vec.x[(chaos.start[2]+1):data.len] <-cons tr1 <- seq(from = cons, to = vec.x[chaos.start[1]], length.out = 2001) tr2 <- seq(from = vec.x[chaos.start[2]], to = cons, length.out = 2001) vec.x[(chaos.start[1]-2000):chaos.start[1]] <- tr1 vec.x[chaos.start[2]:(chaos.start[2]+2000)] <- tr2 # Find regular intervals in vec.x and plot results. regular_borders <- find_regularity(vec.x, "skip_window" = 1000, "window_length" = 3000, "find_thresh" = 300)