Determining the Impact of Emotive Intelligent Spaces

NCT04836286 | Completed

• 1 other identifier: 20-048
• Study Type: interventional
• Target: 40
• Locations: 1 country
• Sites: 1

Brief Summary

Many children (age 3-6) living in the Mountain West (MW) region face unique challenges that can affect their health and welfare, such as lower socioeconomic status, and limited access to healthcare and education. The proposed project aims to address those health and education gaps by improving children's self-regulation (i.e., the ability to control emotional and behavioral impulses), a critical cognitive skill that underpins future mental health and academic achievement. The project will test the effectiveness of an innovative intervention mechanism, the Emotive Intelligent Space (EIS). The EIS consists of two adjacent 3 x 5 sq. ft. wooden wall panels with colored LED lights, creating a 90-degree semi-private space. The adaptable colored lightings are controlled by a machine learning algorithm that is developed based on a co-investigator's prior study. The EIS harnesses the power of artificial intelligence to detect children's emotions from physiological data in real-time and to translate physiological signals into environmental changes (i.e., adaptable colored lighting) that adequately respond to children's emotions, resulting in improved self-regulation, physiological stress responses, and cognitive performance. The objective of this proposal is to determine the effect of EIS on children's (age 3-6) self-regulation, physiological, and cognitive outcomes by employing a repeated ABAB experimental design (A = no intervention, B = EIS intervention). The hypothesis is that EIS will positively impact children's self-regulation, physiological stress response, and cognitive performance. Based on a priori power analysis, 40 preschool and kindergarten children will be recruited from early childhood programs in the rural areas near Moscow, ID. During the experiment, children will be assessed under a combination of A and B conditions. A digital wristband will capture children's real-time physiological responses (i.e., Galvanic skin response, body temperature, and blood volume pulse). A machine learning algorithm will immediately translate the physiological data into three basic emotions (i.e., happy, angry/fearful, sad) represented by children's choice of colors on the EIS. A series of ANCOVA analyses will be used to determine the mean differences in self-regulation, physiological, and cognitive scores under baseline and treatment conditions.

Conditions

Color Perception

Keywords

Self-regulation; Color-emotion association; Cognitive performance

Outcome Measures

Primary Outcomes (5)

• Self-regulation

  Self-regulation will be measured by the Head Toes Knees Shoulder task. This task measures cognitive skills such as inhibitory control, attention, and working memory, which are indicators of self-regulation. Children will be asked to play a game where they must do the opposite of what the experimenter says.

  10 minutes

• Body temperature

  Body temperature will be measured in fahrenheit using the wristband.

  30 minutes

• Galvanic skin response

  Skin Conductance (SC) will be measured as an indicator of the continuous variations in the electrical characteristics of the skin, using the wristband.

  30 minutes

• Blood volume pulse

  Blood volume pulse will be measured as the number of heart beat per minutes, using the wristband.

  30 minutes

• Cognitive performance

  This outcome will be measured with will be measured as working memory efficiency by the Woodcock Johnson Number Reversed subset. WJ-4 is a brief, age-appropriate, and well-validated cognitive ability assessment that evaluates young children's ability to retrieve and retain information required for ongoing cognitive processes.

  3 minutes

Study Arms (1)

single group repeated design

EXPERIMENTAL

The Emotive Intelligent Spaces (EIS) leverages innovations across multiple disciplines, including sensory environment, computer science, psychology, and real-time human-computer interface. The colors of the LED lights on the EIS wooden panels are controlled by an artificial intelligence computer algorithm that will translate children's physiological responses (Galvanic skin response, body temperature, and blood volume pulse), captured by a digital wristband, into their emotional state and the associated preferred colored lighting. The algorithm was created in a co-investigator's published study, using fuzzy logic and machine learning techniques (i.e., Decision Tree; accuracy 86%).To successfully carry out this project, our team blends expertise in educational psychology, early intervention, computer science, architecture, and interior design.

Behavioral: Emotive Intelligent Spaces (EIS)

Interventions

Emotive Intelligent Spaces (EIS) BEHAVIORAL

The EIS leverages innovations across multiple disciplines, including sensory environment, computer science, psychology, and real-time human-computer interface. The colors of the LED lights on the EIS wooden panels are controlled by an artificial intelligence computer algorithm that will translate children's physiological responses (Galvanic skin response, body temperature, and blood volume pulse), captured by a digital wristband, into their emotional state and the associated preferred colored lighting. The algorithm was created in a co-investigator's published study11, using fuzzy logic and machine learning techniques (i.e., Decision Tree; accuracy 86%).To successfully carry out this project, our team blends expertise in educational psychology, early intervention, computer science, architecture, and interior design.

single group repeated design

Eligibility Criteria

• Age: 3 Years - 6 Years
• Sex: all
• Healthy Volunteers: Yes
• Age Groups: Child (0-17)

You may qualify if:

• Typically developing children without color blindness

You may not qualify if:

• Children with color blindness

Sponsors & Collaborators

• University of Idaho: lead
• Washington State University: collaborator

Study Sites (1)

University of Idaho

Moscow, Idaho, 83844, United States

Location

MeSH Terms

Conditions

Self-Control

Condition Hierarchy (Ancestors)

Social Behavior; Behavior

Study Officials

• Shiyi Chen, PhD

  University of Idaho

  PRINCIPAL INVESTIGATOR

Study Design

• Study Type: interventional
• Phase: not applicable
• Allocation: NA
• Masking: NONE
• Purpose: SUPPORTIVE CARE
• Intervention Model: SINGLE GROUP
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: Assistant Professor

Model Details: ABAB design

Study Record Dates

• First Submitted: November 16, 2020
• First Posted: April 8, 2021
• Study Start: April 1, 2021
• Primary Completion: June 21, 2022
• Study Completion: June 21, 2022
• Last Updated: November 3, 2022

Record last verified: 2022-11

Data Sharing

• IPD Sharing: Will share
• Shared Documents: STUDY PROTOCOL, SAP, CSR, ANALYTIC CODE
• Time Frame: Data will be available from August 2021. Data will be available for the foreseeable future.
• Access Criteria: Data requester must have appropriate IRB approval. Data can only be used for research purposes.

Locations

US (1)