# A Preprocessing Pipeline for Pupillometry Signal from Multimodal iMotion Data

## TL;DR

This paper introduces a preprocessing pipeline for pupillometry data from iMotion's multimodal platform to improve data quality and integration.

## Contribution

A systematic pipeline for preprocessing pupil diameter data using MAD, MA, and PCHIP methods in multimodal iMotion data.

## Key findings

- The pipeline effectively removes artifacts and outliers in pupillometry data.
- Interpolation using PCHIP improves missing data handling in pupil diameter measurements.
- The pipeline successfully integrates pupillometry with facial expression data for multimodal analysis.

## Abstract

Pupillometry is commonly used to evaluate cognitive effort, attention, and facial expression response, offering valuable insights into human performance. The combination of eye tracking and facial expression data under the iMotions platform provides great opportunities for multimodal research. However, there is a lack of standardized pipelines for managing pupillometry data on a multimodal platform. Preprocessing pupil data in multimodal platforms poses challenges like timestamp misalignment, missing data, and inconsistencies across multiple data sources. To address these challenges, the authors introduced a systematic preprocessing pipeline for pupil diameter measurements collected using iMotions 10 (version 10.1.38911.4) during an endoscopy simulation task. The pipeline involves artifact removal, outlier detection using advanced methods such as the Median Absolute Deviation (MAD) and Moving Average (MA) algorithm filtering, interpolation of missing data using the Piecewise Cubic Hermite Interpolating Polynomial (PCHIP), and mean pupil diameter calculation through linear regression, as well as normalization of mean pupil diameter and integration of the pupil diameter dataset with facial expression data. By following these steps, the pipeline enhances data quality, reduces noise, and facilitates the seamless integration of pupillometry other multimodal datasets. In conclusion, this pipeline provides a detailed and organized preprocessing method that improves data reliability while preserving important information for further analysis.