ECG Heartbeat Categorization Data

In this article, we describe a technique for AI-training ECG data from testers and patients to infer health abnormalities.

Table of Contents

1. Data Introduction
2. Data Visualization with Machbase Neo
3. Table Creation and Data Upload in Machbase Neo
4. Experimental Methodology
5. Experiment Code
6. Experimental Results

1. Data Introduction

• DataHub Serial Number: 2024-10.
• Data Name: ECG Heartbeat Categorization Data.
• Data Collection Methods:
  • MIT-BIH Arrhythmia Database: Collection of 2-channel ambulatory ECG obtained from 47 subjects studied at the BIH Arrhythmia Laboratory between 1975 and 1979.
  • PTB Diagnostic ECG Database: Collected from healthy volunteers and patients with various heart conditions.
• Data Source: MIT-BIH Arrhythmia Database Link
• Data Source: PTB Diagnostic ECG Database Link
• Raw data size and format: 555MB, CSV.
• Number of tags: 564.

• MIT-BIH Arrhythmia Database State : 4.

• PTB Diagnostic ECG Database State : 2.
  • Normal & Abnormal.
• Data Time Range: 2024-10-14 00:00:00 to 2024-12-29 00:03:00.
• Number of data records collected: 23,310,872.
• CSV data URL: https://data.yotahub.com/2024-10/datahub-2024-10-ECG-HeartBeat.csv.gz
• Data Migration: ECG Heartbeat Categorization Data Migration

2. Data Visualization with Machbase Neo

• Data visualization is possible through the Tag Analyzer in Machbase Neo.
• Select desired tag names and visualize them in various types of graphs.

• Below, access the 2024-10 DataHub in real-time, select the desired tag names from the data of 564 tags, visualize them, and preview the data patterns.

DataHub Viewer

3. Table Creation and Data Upload in Machbase Neo

• In the DataHub directory, use setup.wrk located in the ECG Heartbeat Categorization Dataset folder to create tables and load data, as illustrated in the image below.

1) Table Creation

• The table is created immediately upon pressing the "Run" button in the menu.
• If the ecg table exists, execute the first line and then the second. If it does not exist, start from the second line.

2) Data Upload

• Loading tables in two different ways.

Method 1) Table loading method using TQL in Machbase Neo (since machbase-neo v8.0.29-rc1

• Pros

  • Markbase Neo loads as soon as you hit the launch button.

• Cons

  • Slower table loading speed compared to other method.

Method 2) Loading tables using commands

• Pros

  • Fast table loading speed.

• Cons

  • The table loading process is cumbersome.
  • Run cmd window - Change machbase-neo path - Enter command in cmd window.

• If run the below script from the command shell, the data will be entered at high speed into the ecg table.

curl http://data.yotahub.com/2024-10/datahub-2024-10-ECG-HeartBeat.csv.gz | machbase-neo shell import --input - --compress gzip --header --method append --timeformat ns ecg

• If specify a separate username and password, use the --user and --password options (if not sys/manager) and add the options as shown below.

curl http://data.yotahub.com/2024-10/datahub-2024-10-ECG-HeartBeat.csv.gz | machbase-neo shell import --input - --compress gzip --header --method append --timeformat ns ecg --user USERNAME --password PASSWORD

4. Experimental Methodology

• Model Objective: ECG Heartbeat Classification.
• Tags Used: MIT-BIH Arrhythmia Data tags.
• Model Configuration: ResNet 1d.

• Learning Method: Supervised Learning + Cost Sensitive Learning.
  • Train: Model Training.
  • Validation: Model validation.
  • Test: Model Performance Evaluation.
• Model Optimizer: Adam.
• Model Loss Function: CrossEntropyLoss.
• Model Performance Metric: F1 Score.
• Data Loading Method
  • Loading the Entire Dataset.
  • Loading the Batch Dataset.
• Data Preprocessing
  • MinMax Scaling.
  • Principal Component Analysis.

5. Experiment Code

• Below is the code for each of the two ways to get data from the database.
• If all the data can be loaded and trained at once without causing memory errors, then method 1 is the fastest and simplest.
• If the data is too large, causing memory errors, then the batch loading method proposed in method 2 is the most efficient.

Method 1) Loading the Entire Dataset

• The code below is implemented in a way that loads all the data needed for training from the database all at once.
• It is exactly the same as loading all CSV files (The only difference is that the data is loaded from Machbase Neo).
• Pros
  • Can use the same code that was previously utilizing CSVs (Only the loading process is different).
• Cons
  • Unable to train if trainable data size exceeds memory size.

• The entire code can be run through 10.ECG_HeartBeat_General.ipynb.

Method 2) Loading the Batch Dataset

• Method for loading data from the Machbase Neo for a single batch size.
• The code below is for fetching a time range sequentially for a single batch size.
• Pros
  • It is possible to train the model regardless of the data size, no matter how large it is.
• Cons
  • It takes longer to train compared to method 1.

• The entire code can be run through 10.ECG_HeartBeat_New_Batch.ipynb.

6. Experimental Results

Method 1) Loading the Entire Dataset Result

Method 2) Loading the Batch Dataset Result

• The F1 score for loading the entire dataset resulted in 0.89, loading the batch dataset resulted in same 0.89.
  
  
  
  

※ Various datasets and tutorial codes can be found in the GitHub repository below.

datahub/dataset/2024 at main · machbase/datahub

All Industrial IoT DataHub with data visualization and AI source - machbase/datahub

GitHubmachbase

Back to Top