Using arctools package to compute physical activity summaries | Reading PA data | Computing summaries with activity_stats method | Output explained | Additionalactivity_stats method options | Summarizing PA within a fixed set of minutes only | Summarizing PA within a subset of weekdays only | Summarizing PA with a fixed set of minutes excluded | Summarizing PA with in-bed time excluded | ActiLife-estimated in-bed data | Components of activity_stats method | Expand the length of minute-level AC vector to integer number of full 24-hour periods by NA-padding with midnight_to_midnight | Get wear/non-wear flag with get_wear_flag | Get valid/non-valid day flag with get_valid_day_flag | Impute missing data with impute_missing_data | Create PA characteristics with summarize_PA

Raw accelerometry data sample | Running trial | Sensor and accelerometry data | Sensor location | Data set acc_running | Note on date_time column values | Accelerometry data visualization | Sub-second level accelerometry data | Note on sensors desynchronization | Vector magnitude | Vector magnitude count | Walking strides segmentation | Segmentation with Approach 1: use existing stride templates | Left ankle | Left hip | Results: estimated stride duration time | Results: subject-specific stride pattern (left ankle) | Correlation clustering of segmented walking strides | Segmentation with Approach 2: derive stride templates semi-manually | Deriving stride patterns in a semi-manual way: left ankle | Deriving stride patterns in a semi-manual way: left hip | Segmentation | References

runstats | Installation | Usage | Running statistics | Performance | Compare with a conventional method

Introduction | ADEPT method | Pattern template | Install and load adept package | Pattern segmentation with adept package | Examples 1: signal with no noise, same-length pattern | Simulate data | Example 1(a): segment pattern | segmentPattern output | Example 1(b): use pattern.dur.seq to modify a grid of pattern duration | Example 1(c): use x.fs to modify x time-series frequency | Examples 2: signal with no noise, pattern duration varies | Example 2(a): segment pattern | Example 2(b): use pattern.dur.seq to modify a grid of pattern duration | Example 2(c): use similarity.measure to modify similarity statistic | Examples 3: signal with no noise, pattern duration and pattern shape vary | Example 3(a): segment pattern | Example 3(b): use similarity.measure.thresh to modify the threshold of minimal similarity | Example 3(c): use multiple templates simultaneously | Examples 4: signal with noise, pattern duration and pattern shape vary | Example 4(a): segment pattern | Example 4(b): use x.adept.ma.W to smooth x for similarity matrix computation | Example 4(c): use fine-tune procedure for peak detection | Example 4(d): use fine-tune procedure and smooth signal for peak detection | References