Closed-loop three-layer interpretable ITS architecture linking multimodal scoring, expressive diagnostics, and conversational coaching

Design · All designs
Evidence · 2 claims (2 for) · 1 study (1 associational), q3 · 1 of 1 report an effect size · 2 claims rest on one study

Description

The article proposes an ITS architecture that treats assessment not as an endpoint but as part of a closed loop of practice, feedback, and behavioral adjustment. It is "structured as a closed-loop feedback system with three distinct layers": a performance layer presenting Overall Rating and six BARS dimension scores, an emotion-aware expressive diagnosis layer treating audience-facing cues as behavioral signals, and a Conversational AI Tutor that resolves learner queries using retrieved analytic evidence. The design aims to move learners from performance awareness to interpretation to actionable change.

Design Implications

Context

Requirements

• Rubric-aligned (BARS) annotated training data so scores trace to observable performance cues
• A retrieval layer restricting tutor generation to the learner's own multimodal records

Constraints

• Asynchronous, upload-based design; no real-time feedback during live performance
• Multimodal signals are summarized rather than modeled temporally
• Adapting to a new rubric or domain requires re-annotation and retraining (cold-start dependency)

Target Learners

• adult learners and working professionals practicing on-camera oral presentation

Learning Goals

• on-camera oral presentation delivery and content skills

Claims

• Its Prepost Gains All Seven Bars Dimensions [+M]
• Practice Frequency Predicts Posttest Performance [+M]

Related Designs

• cc-self-train adaptive learning system: a three-layer hook-based engagement observation and scaffolding adjustment mechanism
• Closed-loop adaptive teaching assistance model integrating perception, evaluation, generation and feedback for music education
• Intelligent tutoring systems as three-model architectures operationalizing formative assessment
• AI Expert Feedback Ecology: a closed-loop cognition framework linking AI Twins, AI Tutors, dashboards, and learners

Examples

-

Key Sources

• Hung-Yue Suen and Kuo-En Hung. (2026). An Interpretable Closed-Loop Intelligent Tutoring System for Multimodal Affective Feedback in Asynchronous Presentation Training. IEEE Transactions on Learning Technologies. https://doi.org/10.1109/TLT.2026.3693864

Page metadata

Field	Value
type	design
id	closed-loop-three-layer-interpretable-its-architecture
title	Closed-loop three-layer interpretable ITS architecture linking multimodal scoring, expressive diagnostics, and conversational coaching
description	The article proposes an ITS architecture that treats assessment not as an endpoint but as part of a closed loop of practice, feedback, and behavioral adjustment.
status	review
generated	by process:settle-candidates on 2026-10-11
trust	unverified — no one has confirmed this page's content
sources	1 — hung-yue-suen-and-kuo-en-hung-2026

Frontmatter is the page's machine-readable record — see the Schema & Guide.