Skip to content

matlab/matlab-agentic-toolkit / skills-catalog/signal-processing/matlab-prepare-signal-data

matlab-prepare-signal-data

Verified

Use this skill when conditioning, loading, preparing, or labeling signal data for analysis or ML training. Covers: cleaning a single signal (fill gaps, remove drift, deoutlier, denoise, resample/align a time base) BEFORE analysis; building a `signalDatastore` pipeline; creating a `labeledSignalSet` for Signal Labeler; deriving labels (filename, folder, in-file, ROI, time-frequency ROI); stratified train/val/test splits; framing long signals; parallel processing; and shaping datastore output for `trainnet`. Triggers include "clean up this signal", "remove drift / detrend", "fill gaps", "remove spikes / outliers", "denoise", "resample to a uniform rate", "align channels", "labels from filenames", "stratified split", "prepare for Signal Labeler", and function names like `fillgaps`, `fillmissing`, `detrend`, `filloutliers`, `smoothdata`, `resample`, `synchronize`, `signalDatastore`, `labeledSignalSet`, `filenames2labels`, `folders2labels`, `splitlabels`, `framesig`, `framelbl`, `createDatastores`.

FileKindSize
SKILL.mdskill md9.5 KB
manifest.yamlconfig650 B
references/fn-countlabels.mdmarkdown2.1 KB
references/fn-detrend.mdmarkdown4.6 KB
references/fn-filenames2labels.mdmarkdown4.8 KB
references/fn-fillgaps.mdmarkdown3.3 KB
references/fn-fillmissing.mdmarkdown4.2 KB
references/fn-filloutliers.mdmarkdown5.0 KB
references/fn-folders2labels.mdmarkdown3.4 KB
references/fn-framelbl.mdmarkdown7.1 KB
references/fn-framesig.mdmarkdown4.1 KB
references/fn-hampel.mdmarkdown3.3 KB
references/fn-labeledsignalset.mdmarkdown9.1 KB
references/fn-labelspectrogramoptions.mdmarkdown4.6 KB
references/fn-medfilt1.mdmarkdown3.3 KB
references/fn-partition.mdmarkdown4.6 KB
references/fn-resample.mdmarkdown4.6 KB
references/fn-retime.mdmarkdown4.7 KB
references/fn-sgolayfilt.mdmarkdown3.5 KB
references/fn-signaldatastore.mdmarkdown11.9 KB
references/fn-signallabeldefinition.mdmarkdown5.9 KB
references/fn-signalmask-getmask.mdmarkdown8.6 KB
references/fn-smoothdata.mdmarkdown4.8 KB
references/fn-splitlabels.mdmarkdown5.3 KB
references/fn-subset.mdmarkdown3.9 KB
references/fn-synchronize.mdmarkdown4.7 KB
references/fn-wdenoise.mdmarkdown5.2 KB
references/wf-align-channels.mdmarkdown6.6 KB
references/wf-custom-readfcn.mdmarkdown5.0 KB
references/wf-denoise.mdmarkdown2.6 KB
references/wf-detrend-smooth-deoutlier.mdmarkdown6.6 KB
references/wf-envelope.mdmarkdown5.3 KB
references/wf-frame-and-label.mdmarkdown4.7 KB
references/wf-handoff-to-dl.mdmarkdown9.1 KB
references/wf-label-and-export.mdmarkdown8.7 KB
references/wf-load-and-split.mdmarkdown4.6 KB
references/wf-parallel-process.mdmarkdown4.8 KB
references/wf-repair-missing.mdmarkdown6.7 KB
references/wf-uniform-rate.mdmarkdown4.2 KB

references/fn-medfilt1.md

View on GitHub
# Function: `medfilt1`

> Used in: wf-detrend-smooth-deoutlier.md
> Toolbox: Signal Processing Toolbox

One-dimensional median filter. Every output sample is the median of an
`n`-sample window around it. This is a **denoiser, not an outlier tool**: it
replaces every sample, distorting clean samples along with corrupted ones. It
belongs in the outlier discussion only as the escape hatch for *dense* impulse
noise, where windowed outlier detection breaks down.

On a matrix, it filters each column.

## Signature

```matlab
y = medfilt1(x)                                  % n=3
y = medfilt1(x, n)                               % nth-order median filter
y = medfilt1(x, n, [], dim)                      % operate along dim
y = medfilt1(___, nanflag, padding)              % NaN + edge handling
```

## Arguments

| Argument | Default | Purpose |
|---|---|---|
| `n` | `3` | Filter order. For odd `n`, `y(k)` is the median of `x(k-(n-1)/2 : k+(n-1)/2)`. For even `n`, it averages the two middle sorted values. Larger `n` = more smoothing = more clean-sample distortion. |
| `dim` | first non-singleton | Dimension to filter along. Pass `medfilt1(x, n, [], 2)` for row-wise. The `blksz` slot before `dim` is legacy and ignored (pass `[]`). |
| `nanflag` | `'includenan'` | `'includenan'` makes any window containing NaN produce NaN. `'omitnan'` computes the median of the non-NaN values instead. |
| `padding` | `'zeropad'` | `'zeropad'` treats the signal as 0 beyond the ends (biases end samples toward 0). `'truncate'` computes medians of shorter end-segments instead. |

## Why it is the dense-noise escape hatch

`medfilt1` sidesteps outlier *detection* entirely: it median-filters every
sample, accepting the distortion of clean samples as the price. That is exactly
what you want when impulse noise is dense enough that windowed detectors break
down - a `filloutliers`/`hampel` window needs a normal majority to estimate a
clean local median, and when the burst dominates the window, the local median
*is* the noise and detection fails.

The sparse-vs-dense choice between this and the windowed detectors (and the
density threshold that separates them) is the workflow decision - see
wf-detrend-smooth-deoutlier.md (Step 1).

## Gotchas

- **Not an outlier remover.** It has no detection step and no threshold. It
  median-filters every sample regardless of whether it was an outlier. Do not
  reach for it to clean a few spikes out of an otherwise-clean signal.
- **Default zero padding biases the endpoints.** The first/last `n/2` samples
  are pulled toward 0. Use `medfilt1(x, n, [], 1, "omitnan", "truncate")` to
  compute shorter-segment medians at the edges instead.
- **NaN defaults to propagating** (`'includenan'`): any window covering a NaN
  gap returns NaN, widening the gap. Pass `'omitnan'` to median the non-NaN
  values, or fill gaps first (fn-fillmissing.md / fn-fillgaps.md).
- **Distorts peak shapes.** Median filtering flattens narrow peaks. If peak
  shape matters, use `sgolayfilt` (Savitzky-Golay) instead.

## See also

- fn-filloutliers.md / fn-hampel.md — the sparse-spike alternatives that only
  touch flagged samples.
- `sgolayfilt` — shape-preserving smoother when peaks matter.
- `median` / `movmedian` — the underlying statistic as a primitive.

----

Copyright 2026 The MathWorks, Inc.

----
finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the workStars: 322kUpdated Claude CodeCodexVerifiedInstall
systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixesStars: 322kUpdated Claude CodeCodexVerifiedInstall
test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation codeStars: 322kUpdated Claude CodeCodexVerifiedInstall
skill-creatoranthropics/skillsCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.Stars: 198kUpdated Claude CodeCodexVerifiedInstall