What Is This Tool?

This interactive web app allows you to upload time series data with multiple signals (like sensor readings) and apply a summary filter (Moving Average, Gaussian, or Median) across the selected signals. It’s ideal for smoothing noisy data, comparing signal behavior, and creating an aggregated summary trend.

🌍 Why Is This Tool Relevant?

If you’re working with multiple sensors or time-series signals, you know the data is often noisy, inconsistent, or overwhelming to interpret individually.

This tool helps you:

• Reduce noise
• Aggregate multiple signals into a clean trendline
• Visually compare filtered and raw data
• Export the cleaned dataset for further analysis

Use cases include:

• IoT sensor data
• Environmental monitoring
• Biomedical signal fusion
• Industrial analytics

Dataset Example

You can use your own CSV, but here’s the required format:

csv
Time,Sensor_1,Sensor_2,Sensor_3
2025-01-01 00:00,22.1,23.0,21.5
2025-01-01 01:00,22.3,23.2,21.7
...

Time column must be parseable as datetime.

• At least three numeric signal columns are required.

If no file is uploaded, the app uses a synthetic dataset with 3 simulated sensor signals.

How to Use the App

1. Upload a CSV (or use the demo dataset).
2. The app detects all columns except “Time” as signals.
3. Select at least 3 signals for filtering.
4. Choose a filtering method:
   • Moving Average
   • Gaussian Smoothing
   • Median Filter
5. Adjust parameters like window size or sigma.
6. View:
   • A combined plot of all signals + the filtered summary.
   • Individual plots comparing each signal to the summary.
7. Download the filtered data.

🔍 Understanding the Filters

Each method provides a different smoothing effect:

• Moving Average: Smooths data by averaging over a sliding window (over time) after taking the median of the “n” signals provided.
• Gaussian Filter: Similar to moving average but uses a bell-shaped weight distribution.
• Median Filter: Takes the median over the “n” signals provided.

All filters operate across time and across selected signals, producing a single summary trendline.

Example Results

Say you upload data from 3 temperature sensors. Using a Gaussian filter with sigma = 2.0, the app outputs:

• A summary plot with all signals plus a bold black line (the smoothed trend).
• Individual plots for each sensor showing how it aligns with the summary.
• A downloadable CSV including the original data and a new Filtered_Summary column.

This lets you visually assess signal consistency and export a cleaner trendline for modeling or reporting.

Moving Average Filter

Gaussian filter

Median Filter

🚀 Try It Yourself

You can run the app for free by visiting our web site and looking at the Demo Tools https://aisciencetalk.blog/demo-tools/

Need Something Similar?

This is a hands-on example of how data analysis can be applied in real-world industrial engineering scenarios.

If you have sensor data (even raw), and want to extract value from it — let’s talk.

Contact Me → https://aisciencetalk.blog/contact-us/ or Book an Appointment → https://aisciencetalk.blog/book-an-appointment/

Disclaimer

This content has been generated by an artificial intelligence language model. While we strive for accuracy and quality, please note that the information provided may not be entirely error-free or up-to-date. We recommend independently verifying the content and consulting with professionals for specific advice or information. We do not assume any responsibility or liability for the use or interpretation of this content.

Copyright

Author: Simone Togni

Platform: aisciencetalk.blog