MONITOR Questionnaire and Response Dataset

MONITOR: A Data-driven Intelligent MONITORring System to Improve Quality of Working Life

The project, MONITOR, aims to establish mobility of bilateral collaboration between Islamic University of Technology (IUT), Bangladesh, and Mälardalen University (MDH), Sweden in specific research and education domains of Science and Technology at an institutional level. MDH has been leading several projects to develop tools to classify physiological data for individualized classification of physiological sensor readings to monitor stress, fatigue, and mental load at work and home. The project was funded by Stiftelsen för internationalisering av högre utbildning och forskning (STINT) under Grant Agreement No. 202100-2916.

This project has unfolded many benefits for both partnering universities. It gave access to a wide variety of data regarding mental health-related parameters. Given the data collection was done in Bangladesh, it was challenging for the researchers to extract correct and accurate data under harsh/unsafe conditions. This trained the researchers to collect data under real complex conditions. In this project, MDH provided resources and knowledge to update the already developed AI algorithms to support Garment workers’ mental health monitoring. IUT provided expert human resources to develop a sensor-setting framework and assisted in collecting and analyzing the data.

Northern Tosrifa Group (NTG): A LEED-certified garment factory in Bangladesh, provided the test environment and subjects to collect and validate the system. The group has 5 companies under its operation and all the companies manufacture and export their products to markets in North America and Europe. As a partner of this project, NTG provided the necessary manpower and data collection environment for the project. 

Test Subject Demography

A total of 27 subjects (29.17% Male, 83.33% Female, Age Group: 18-40 years) were recruited in a random fashion from different job role with written consent to collect stress-related physiological parameters for this project. However, data from 24 subjects (29.17% Male, 70.83% Female, Age Group: 18-40 years) were considered due to inconsistencies in the data from 3 subjects owing to measurement inconsistencies, and device and/or human errors. 

Data Collection Unit

Two data collection devices were used simultaneously on the test subject. One of them is Shimmer Sensor  which is ISO certified for physiological data collection. The second data collection unit is PhysiCube which is assembled by the research team of MONITOR project as a low-cost solution. The dataset collected using Shimmer Sensor is available in https://zenodo.org/records/11523283 and the dataset collected using PhysiCube is available in https://zenodo.org/records/11518751.

Data Collection Sessions

Data were collected in the following three phases-

Baseline Session: The duration of a baseline session is 18~22 mins and took place in the morning in between normal working hour (Before Lunch). The physiological values like Heart rate, GSR etc. can vary time to time for different reasons even there is no event of stress. This session establishes the base line value of these parameter for individual subjects. During this time, test subject responds to a questionnair with an aim to establish the base stress level. 

After-Lunch Session: After-lunch session took place on the same day of Baseline session for an individual test subject with the assumption that a break in work allow a worker to relax. Test subjects were asked to relax and do some breathing exercise during this session.

Stress-Induced Session: This session took place on a different date. In this session the test subjects had to answer general knowledge and mathematical questions which people often get wrong, and did so under time pressure to induce stress [1]. After the session, test subjects were asked about the level of stress that they have felt during this session which indicates perceived stress level. 

Dataset Description

_test subject info.csv : This file contains the generic information about the test subject which may have relations with indivdual stress level. The informations are age group, gender, marital status, job role, approximate year of experience in current job role and approximate year of experience in Ready Made Garment (RMG) sector. To remove  Personal Identifiable Information (PII), the data is generalized (e.g. age group), summarized (e.g. instead fo exact designation job role is used). Here operations indicate sewing operator, cutter, pressing operator etc.; whereas Supervisor indicates line supervisor, qulaity control supervisor, floor manager, production manager etc. 

_baseline question.csv : This file contains the questionnair which was administered during the baseline session. There are 5 categories and each category has different set of questions.

_question option value.csv : Each question was answered with one of the five options and their assigned value can be found in this file.

_baseline score.csv : This file contains the response to each question. Each question is marked with CiQj. Here Ci meanse ith category and Qj means jth question of that category.

_stress induced score.csv: This file contains the score of perceived stress level in a scale of 1-10. Test subject were asked to score their own individual stress after the stress induced session.

Reference:

1. Almazrouei MA, Morgan RM, Dror IE. A method to induce stress in human subjects in online research environments. Behav Res Methods. 2023 Aug;55(5):2575-2582. doi: 10.3758/s13428-022-01915-3. Epub 2022 Jul 25. PMID: 35879504; PMCID: PMC9311341.