From bde1f481bf90a4b508c0f8d1601401faed75eb86 Mon Sep 17 00:00:00 2001 From: david Date: Fri, 7 Feb 2025 11:51:20 -0700 Subject: [PATCH] hr-hrv block fixes --- .../ecg-hrv-block-arduino-portenta.md | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/novel-sensor-projects/ecg-hrv-block-arduino-portenta.md b/novel-sensor-projects/ecg-hrv-block-arduino-portenta.md index 8861102..b8a4a80 100644 --- a/novel-sensor-projects/ecg-hrv-block-arduino-portenta.md +++ b/novel-sensor-projects/ecg-hrv-block-arduino-portenta.md @@ -62,9 +62,9 @@ The ECG signal can also be combined with data from an accelerometer for enhanced The pads should be connected as follow: -Yellow pad to the left -Red pad to the right -Green pad below the red pad +- Yellow pad to the left. +- Red pad to the right. +- Green pad below the red pad. > Note: Remember to disconnect the AC from the laptop before sampling. @@ -80,7 +80,7 @@ Close the Serial Monitor and run `edge-impulse-data-forwarder`. Select the Edge Impulse project and check that the frequency shows `[SER] Detected data frequency: 50Hz`. -Go to https://studio.edgeimpulse.com/studio//acquisition/training +Go to [https://studio.edgeimpulse.com/studio/Your-Project-ID/acquisition/training](https://studio.edgeimpulse.com/studio/Your-Project-ID/acquisition/training) Select **Length 120.000 ms** and take around 10 to 20 samples for each category to classify. For example, regular working versus stressed. Set aside 10% of the samples for testing. @@ -102,8 +102,6 @@ Frequency-domain features are: Raw VLF Energy, Raw LF Energy, Raw HF Energy, Raw I have used ECG, filter preset 1, window size 40 and no HRV features. -![](../.gitbook/assets/ecg-hrv-block-arduino-portenta/wearable-1.jpg) - ## Model Training The training could require some parameters to be modified from the defaults. I have found the following parameters to work well for my dataset, with a 89.3% accuracy. Training cycles **40**, learning rate **0.005**, bacth size **30** and no auto weight. @@ -130,6 +128,8 @@ Now you will be able to use the model library with your own code. A sample ECG m > Note: If Arduino Portenta shows `Exit status 74`, double click "Reset", and select the correct port. +![](../.gitbook/assets/ecg-hrv-block-arduino-portenta/wearable-1.jpg) + ## Final Notes Thanks to machine learning, monitoring ECG signals no longer requires transmitting data to a remote computer for expert analysis. Instead, subtle health conditions can be detected by small, offline, wearable devices equipped with machine learning capabilities. These devices can identify over-stressed workers who may be unable to perform their tasks effectively, thus preventing serious harm or consequences.