Package 'walking'

Estimate Steps with Unified Syntax

Description

Estimate Steps with Unified Syntax

Usage

estimate_steps_forest(data, ...)

have_forest()

estimate_steps_verisense(
  data,
  resample_to_15hz = FALSE,
  ...,
  method = c("original", "revised")
)

estimate_steps_sdt(data, ...)

Arguments

data	A data.frame with a column for time in POSIXct (usually HEADER_TIMESTAMP), and X, Y, Z
...	additional arguments to pass to specific method
resample_to_15hz	resample the data to 15Hz as verisense indicated that was the sample rate this was designed under.
method	Either using the original parameters verisense_count_steps() or the revised parameters verisense_count_steps_revised()

Value

A data.frame of seconds and steps

Examples

run_example = FALSE
csv_file = system.file("test_data_bout.csv", package = "walking")
if (requireNamespace("readr", quietly = TRUE)) {
  run_example = TRUE
  x = readr::read_csv(csv_file)
  colnames(x)[colnames(x) == "UTC time"] = "time"
  out = estimate_steps_verisense(x, sample_rate = 10L,
                                 method = "original")
  out = estimate_steps_verisense(x, sample_rate = 10L,
                                 method = "revised")
  out = estimate_steps_sdt(x, sample_rate = 10L)
}

  Sys.setenv("SSQ_PARALLEL" = 0)
  if (requireNamespace("readr", quietly = TRUE) &&
    reticulate::py_module_available("forest")) {
    out = estimate_steps_forest(x, sample_rate_analysis = 10L)
  }

---

Finds walking and calculate steps from raw acceleration data.

Description

Method finds periods of repetitive and continuous oscillations with predominant frequency occurring within know step frequency range. Frequency components are extracted with Continuous Wavelet Transform.

Usage

find_walking(
  data,
  sample_rate_analysis = 10L,
  min_amplitude = 0.3,
  step_frequency = c(1.4, 2.3),
  alpha = 0.6,
  beta = 2.5,
  min_duration_peak = 3L,
  delta = 20L,
  verbose = TRUE,
  disable_parallelization = TRUE
)

Arguments

data	A data.frame with a column for time in POSIXct (usually HEADER_TIMESTAMP), and X, Y, Z
sample_rate_analysis	sampling frequency (in Hz) for analyzing walking. Note, this is NOT the sampling frequency of the data.
min_amplitude	minimum amplitude (in g)
step_frequency	step frequency range
alpha	maximum ratio between dominant peak below and within step frequency range
beta	maximum ratio between dominant peak above and within step frequency range
min_duration_peak	minimum duration of peaks (in seconds)
delta	maximum difference between consecutive peaks (in multiplication of 0.05Hz)
verbose	print diagnostic messages
disable_parallelization	Whether to disable the CPU parallelization used by oak through ssqueezepy. Parallelization can speed up larger analyses but may conflict with an R/Python environment or its threading and OpenMP configuration. The default, TRUE, sets SSQ_PARALLEL=0 while this function runs. If forest fails to load, set Sys.setenv(SSQ_PARALLEL = 0) before calling py_require_forest() and reticulate::import("forest"). See https://github.com/OverLordGoldDragon/ssqueezepy#gpu–cpu-acceleration.

Value

A vector of number of steps per second

Examples

Sys.setenv("SSQ_PARALLEL" = 0)
  csv_file = system.file("test_data_bout.csv", package = "walking")
  if (requireNamespace("readr", quietly = TRUE) && reticulate::py_module_available("forest")) {
    x = readr::read_csv(csv_file)
    colnames(x)[colnames(x) == "UTC time"] = "time"
    res = find_walking(data = x)
  }

---

Preprocesses accelerometer bout to a common format.

Description

Resample 3-axial input signal to a predefined sampling rate and compute vector magnitude.

Usage

preprocess_bout(data, sample_rate = 10L)

preprocess_bout_r(data, sample_rate = 10L)

Arguments

data	A data.frame with a column for time in POSIXct (usually HEADER_TIMESTAMP), and X, Y, Z
sample_rate	sampling frequency, coercible to an integer. This is the sampling rate you're sampling the data into.

Value

A list of vm_bout, which is an unnamed list of length 2, containing times and VM (vector magnitude) interpolated. This will be passed into other forest functions. The list also contains vm_data, which transforms vm_bout into a data.frame after creating the required times.

Examples

csv_file = system.file("test_data_bout.csv", package = "walking")
  if (requireNamespace("readr", quietly = TRUE)) {
    x = readr::read_csv(csv_file)
    colnames(x)[colnames(x) == "UTC time"] = "time"
    if (reticulate::py_module_available("forest")) {
      res = preprocess_bout(data = x)
      res2 = preprocess_bout_r(data = x)
      testthat::expect_equal(res$vm_bout, res2$vm_bout, tolerance = 1e-4)
    }
  }

---

Require Forest module

Description

Require Forest module

Usage

py_require_forest(python_version = "3.11", ...)

Arguments

python_version	Python version to use, passed to reticulate::py_require()
...	additional arguments passed to reticulate::py_require()

Value

invisible NULL

Examples

files <- list.files()
py_require_forest()
walking:::cleanup_uv_lock_files()
stopifnot(length(setdiff(list.files(), files)) == 0L)

---

Estimate Steps via SDT

Description

Estimate Steps via SDT

Usage

sdt_count_steps(
  data,
  sample_rate,
  order = 4L,
  high = 0.25,
  low = 2.5,
  location = c("wrist", "waist"),
  verbose = TRUE
)

Arguments

data	A data.frame with a column for time in POSIXct (usually HEADER_TIMESTAMP), and X, Y, Z
sample_rate	sampling frequency (in Hz)
order	order of bandpass Butterworth filter order
high	highpass threshold for filter
low	lowpass threshold for filter
location	location of the device, which indicates a different threshold for peaks
verbose	print diagnostic messages

Value

A data.frame of timeand steps

Examples

csv_file = system.file("test_data_bout.csv", package = "walking")
if (requireNamespace("readr", quietly = TRUE)) {
  x = readr::read_csv(csv_file)
  colnames(x)[colnames(x) == "UTC time"] = "time"
  res = sdt_count_steps(data = x, sample_rate = 100L)
}

---

Count Steps According to Gu et al, 2017 Method

Description

This method is based off finding peaks in the summed and squared acceleration signal and then using multiple thresholds to determine if each peak is a step or an artifact. An additional magnitude threshold was added to the algorithm to prevent false positives in free living data.

Usage

verisense_count_steps(
  data,
  sample_rate,
  k = 3,
  periodicity_range = c(5, 15),
  similarity_threshold = -0.5,
  continuity_window_size = 4,
  continuity_threshold = 4,
  variance_threshold = 0.001,
  vm_threshold = 1.2,
  peak_finder = c("fast", "original"),
  verbose = TRUE,
  global_vm_threshold = 0.025
)

verisense_count_steps_revised(
  ...,
  k = 4,
  periodicity_range = c(4, 20),
  similarity_threshold = -1,
  continuity_window_size = 4,
  continuity_threshold = 4,
  variance_threshold = 0.01,
  vm_threshold = 1.25
)

Arguments

data	A data.frame with a column for time in POSIXct (usually HEADER_TIMESTAMP, not required), and X, Y, Z
sample_rate	sampling frequency of the input data
k	window size for controlling peak finding.
periodicity_range	a length-2 vector of the range of periodicity. These are integers that represent samples not seconds.
similarity_threshold	threshold (in g) for similarity between magnitude of peaks
continuity_window_size	Window size for continuity
continuity_threshold	Threshold for continuity
variance_threshold	Variance threshold for the signal
vm_threshold	vector magnitude threshold for a peak to be called a peak
peak_finder	function to find peaks, either the "original" from the code, or the optimized "fast" version.
verbose	print diagnostic messages
global_vm_threshold	Global acceleration VM threshold (in standard deviation) for the total vector. If sd(acc) < thresh no steps are estimated. Set to 0 to run estimation regardless.
...	not used, used to passes arguments from verisense_count_steps_revised to verisense_count_steps

Value

A vector of length round(nrow(input_data) / sample_rate) of the estimated steps, where the data is rounded to seconds

Note

the ⁠_revised⁠ version is the same algorithm with different defaults for the parameters as based on https://doi.org/10.3390/s22249984.

Author(s)

Matthew R Patterson [email protected], MIT license, Copyright (c) 2020 Shimmer

Examples

csv_file = system.file("test_data_bout.csv", package = "walking")
if (requireNamespace("readr", quietly = TRUE)) {
  x = readr::read_csv(csv_file)
  colnames(x)[colnames(x) == "UTC time"] = "time"
  out = verisense_count_steps(x, sample_rate = 10L)
}
input_data <- matrix(runif(500 * 3, min = -1.5, max = 1.5), ncol = 3)
verisense_count_steps(input_data, sample_rate = 15L)
verisense_count_steps(input_data, sample_rate = 15L, peak_finder = "fast")
acc = sqrt(rowSums(input_data^2))
verisense_count_steps(acc, sample_rate = 15L, peak_finder = "fast")

---