Skill Profiling with Attributable Reasoning (SPAR): A Wearable Analysis System for Boxing

2026-09-24

AI Summary

This study addresses the limitation of existing wearable systems that recognize boxing punch types but fail to assess movement quality by proposing SPAR. The system fuses data from eight IMUs and pressure insoles, leveraging a frozen time-series foundation model to encode joint angle and plantar pressure features for precise classification via a lightweight Transformer. A core innovation is a three-tier attributable reasoning framework integrated with multimodal attribution analysis, translating predictions into actionable corrective feedback tailored for analysts, coaches, and athletes. Experiments involving 17 participants achieved a leave-one-out AUC of 0.842, while coach interviews validated the practical utility of the feedback mechanism. This work effectively bridges the research gap between movement classification and skill assessment in sports analytics.

Abstract

A punch is a ballistic, full-body action driven by a kinetic chain running from the legs through the trunk to the arm, where a small sequencing error separates a scoring strike from a miss. Wearable sensors can capture this movement in the gym, but most deployable systems only classify which punch was thrown rather than assess how well it was thrown. We present Skill Profiling with Attributable Reasoning (SPAR), an eight-IMU garment and pressure-insole system that classifies each punch as expert or novice and treats an explanation of that prediction as feedback. Feedback is only useful if the person receiving it can act on it, so SPAR explains the prediction at three tiers, a per-joint attribution for the analyst, a counterfactual over kinetic-chain layers for the coach, and a plain-language narrative of the two for the athlete. Across 17 participants and 4,713 punches, SPAR reaches a leave-one-participant-out AUC of 0.842 (95% CI [0.769, 0.907] over participants). A frozen time-series foundation model encodes the joint-angle and plantar-force series, and a small transformer trained on the cohort classifies the encoding. We audit the two quantitative tiers and report six themes from a thematic analysis of interviews with six practicing boxing coaches.

Problem

• boxing skill assessment
• wearable sensors
• punch quality evaluation
• attributable reasoning

Innovation

• Attributable Reasoning
• Wearable IMU System
• Time-Series Foundation Model
• Counterfactual Explanation
• Kinetic Chain