# A Preliminary Data-Driven Approach for Classifying Knee Instability During Subject-Specific Exercise-Based Game with Squat Motions

## TL;DR

This paper presents a game-based system that tracks squat movements to detect knee instability in real time with high accuracy.

## Contribution

A novel multimodal sensor approach using LSTM and SVM models for real-time knee instability classification during exercise.

## Key findings

- Knee instability events were classified with 96% accuracy using LSTM and SVM models.
- Multimodal sensor features improved classifier performance over single-modality inputs.
- Spearman correlation-based feature selection identified optimal input combinations.

## Abstract

Lower limb functional degeneration has become prevalent, notably reducing the core strength that drives motor control. Squats are frequently used in lower limb training, improving overall muscle strength. However, performing continuously with improper techniques can lead to dynamic knee instability. It worsens with little to no motivation to perform these power training motions. Hence, it is crucial to have a gaming-based exercise tracking system to adaptively enhance the user experience without causing injury or falls. In this work, 28 healthy subjects performed exergame-based squat training, and dynamic kinematic features were recorded. The five features acquired from a depth camera-based inertial measurement unit (IMU) (1—Knee shakiness, 2—Knee distance, and 3—Squat depth) and an Anima forceplate sensor (4—Sway velocity and 5—Sway area) were assessed using a Spearman correlation coefficient-based feature selection method. An input vector that defines knee instability is used to train and test the Long Short-Term Memory (LSTM) and Support Vector Machine (SVM) models for binary classification. The results showed that knee instability events can be successfully classified and achieved a high accuracy of 96% in both models with sets 1, 2, 3, 4, and 5 and 1, 2, and 3. The feature selection results indicate that the LSTM network with the proposed combination of input features from multimodal sensors can successfully perform real-time tracking of knee instability. Furthermore, the findings demonstrate that this multimodal approach yields improved classifier performance with enhanced accuracy compared to using features from a single modality during lower limb therapy.