From 58ccc69fe1c6a6262af70b4de8257516d86464d2 Mon Sep 17 00:00:00 2001 From: Eitan Hemed <37670372+EitanHemed@users.noreply.github.com> Date: Tue, 17 Oct 2023 18:12:42 +0300 Subject: [PATCH] Changed EEG to ECG in tutorial (#928) Corrected EEG to ECG (electrocardiogram), the recording of the heart's electrical activity. --- docs/Tutorial_Pattern_Matching.ipynb | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/Tutorial_Pattern_Matching.ipynb b/docs/Tutorial_Pattern_Matching.ipynb index 92a9c4616..bff9eabac 100644 --- a/docs/Tutorial_Pattern_Matching.ipynb +++ b/docs/Tutorial_Pattern_Matching.ipynb @@ -432,7 +432,7 @@ "\n", "Now, you might wonder which subsequences of `T` count as matches of `Q`. Earlier, we manually sorted the distance profile in ascending order and defined the top 16 matches to be the 16 subsequences with the lowest distance. While we can emulate this behavior with `stumpy.match` (see the end of this section), the preferred way is to return all subsequences in `T` that are closer to than some threshold. This threshold is controlled specifying the `max_distance` parameter. \n", "\n", - "STUMPY tries to find a reasonable default value but, in general, this is very difficult because it largely depends on your particular dataset and/or domain. For example, if you have EEG data of a patient's heartbeat and you want to match one specific beat, then you may consider using a smaller threshold since your time series may be highly regular. On the other hand, if you try to match a specific word in a voice recording, then you would probably need to use a larger threshold since the exact shape of your match could be influenced by how the speaker pronounces the given word.\n", + "STUMPY tries to find a reasonable default value but, in general, this is very difficult because it largely depends on your particular dataset and/or domain. For example, if you have ECG data of a patient's heartbeat and you want to match one specific beat, then you may consider using a smaller threshold since your time series may be highly regular. On the other hand, if you try to match a specific word in a voice recording, then you would probably need to use a larger threshold since the exact shape of your match could be influenced by how the speaker pronounces the given word.\n", "\n", "Let's plot all of the discovered `matches` to see if we need to adjust our threshold:" ]