EUVIMEDScopri EUVIMED
Crossref

Emotion- and Performance-in-the-Loop: Multimodal Difficulty-Adaptive Exergame System—Controlled Between-Participants Study

Liang Zhao iD, Dan Liu iD, Hanli Zhang iD, Guanci Yang iD, Donghua Zheng iD, Ling He iD

JMIR Serious Games · 2026-11-05 · 14 · e101438

DOI: 10.2196/101438 ↗

At a glance

Journal article in JMIR Serious Games, published online on 2026-11-05. Written by Liang Zhao and 5 co-authors. Institution: School of Mechanical Engineering, Guizhou University, Guiyang, Guizhou, China. 40 references.

AbstractSubjectsDati bibliograficiCiteRelated studies

Abstract (original language)

Background

Existing exergames predominantly adjust difficulty based on explicit performance metrics, neglecting the player’s implicit affective state, which often leads to early disengagement due to boredom or frustration.

Objective

To address this gap, we present a novel exergame system that implements joint emotion- and performance-driven dynamic difficulty adjustment (DDA), using a closed-loop controller that reasons over both motor performance and affective state.

Methods

The system integrates a computer-vision-based motion evaluation pipeline, a multimodal emotion recognition module that fuses facial action units (AUs), deep facial features, and motion-compensated heart rate variability (HRV) via an adaptive entropy-weighted decision-level fusion strategy, and a closed-loop difficulty controller. A controlled between-participants experiment (N=20) compared the adaptive system against a fixed-difficulty baseline during a 15-minute dance-exergame session.

Results

Emotion recognition accuracy reached 81.07% (macro-F1: 81.02%) for 7 emotional states. The adaptive group demonstrated significantly lower cognitive load (NASA-TLX [National Aeronautics and Space Administration Task Load Index], P

Subjects

Author keywords

affective computingdynamic difficulty adjustmentemotion recognitionexergamemultimodal fusion

Authors and institutions

  • School of Mechanical Engineering, Guizhou University, Guiyang, Guizhou, China.
  • North Alabama International College of Engineering and Technology, Guizhou University, Guiyang, Guizhou, China.
  • Key Laboratory of Advanced Manufacturing Technology, Ministry of Education, Guizhou University, Guiyang, Guizhou, China.
  • Department of Rehabilitation Medicine, The Third People's Hospital of Guizhou Province, Guiyang, Guizhou, China.

ORCID profiles: Liang Zhao, Dan Liu, Hanli Zhang, Guanci Yang, Donghua Zheng, Ling He

Cite

APA

Zhao, L., Liu, D., Zhang, H., Yang, G., Zheng, D., & He, L. (2026). Emotion- and Performance-in-the-Loop: Multimodal Difficulty-Adaptive Exergame System—Controlled Between-Participants Study. JMIR Serious Games, 14, e101438. https://doi.org/10.2196/101438

Vancouver

Zhao L, Liu D, Zhang H, Yang G, Zheng D, He L. Emotion- and Performance-in-the-Loop: Multimodal Difficulty-Adaptive Exergame System—Controlled Between-Participants Study. JMIR Serious Games. 2026;14:e101438. doi:10.2196/101438

BibTeX
@article{Zhao2026,
  author = {Zhao, Liang and Liu, Dan and Zhang, Hanli and Yang, Guanci and Zheng, Donghua and He, Ling},
  title = {Emotion- and Performance-in-the-Loop: Multimodal Difficulty-Adaptive Exergame System—Controlled Between-Participants Study},
  journal = {JMIR Serious Games},
  year = {2026},
  volume = {14},
  pages = {e101438},
  doi = {10.2196/101438}
}
Start for free →