Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

MEET: Mixture of Experts Extra Tree-Based sEMG Hand Gesture Identification

Naveen Gehlot, Ashutosh Jena, Rajesh Kumar, Mahipal Bukya

TL;DR

This work tackles hand-gesture recognition from noninvasive sEMG signals, a domain challenged by multi-class biases and variability across subjects. It introduces MEET, a mixture of experts built on Extra Trees with a gating mechanism, training experts on class-specific subsets and a gate to weight outputs. Using 17 handcrafted time- and frequency-domain features derived from two-channel sEMG data collected across four subjects and six gestures, MEET outperforms ten standard classifiers, achieving up to about 89% accuracy and favorable recall/F1 metrics. The study demonstrates MEET's potential for robust, scalable gesture decoding with implications for prosthetic control and human–computer interfaces, and outlines future work toward domain transfer, hybrid models, and hyperparameter optimization.

Abstract

Artificial intelligence (AI) has made significant advances in recent years and opened up new possibilities in exploring applications in various fields such as biomedical, robotics, education, industry, etc. Among these fields, human hand gesture recognition is a subject of study that has recently emerged as a research interest in robotic hand control using electromyography (EMG). Surface electromyography (sEMG) is a primary technique used in EMG, which is popular due to its non-invasive nature and is used to capture gesture movements using signal acquisition devices placed on the surface of the forearm. Moreover, these signals are pre-processed to extract significant handcrafted features through time and frequency domain analysis. These are helpful and act as input to machine learning (ML) models to identify hand gestures. However, handling multiple classes and biases are major limitations that can affect the performance of an ML model. Therefore, to address this issue, a new mixture of experts extra tree (MEET) model is proposed to identify more accurate and effective hand gesture movements. This model combines individual ML models referred to as experts, each focusing on a minimal class of two. Moreover, a fully trained model known as the gate is employed to weigh the output of individual expert models. This amalgamation of the expert models with the gate model is known as a mixture of experts extra tree (MEET) model. In this study, four subjects with six hand gesture movements have been considered and their identification is evaluated among eleven models, including the MEET classifier. Results elucidate that the MEET classifier performed best among other algorithms and identified hand gesture movement accurately.

MEET: Mixture of Experts Extra Tree-Based sEMG Hand Gesture Identification

TL;DR

This work tackles hand-gesture recognition from noninvasive sEMG signals, a domain challenged by multi-class biases and variability across subjects. It introduces MEET, a mixture of experts built on Extra Trees with a gating mechanism, training experts on class-specific subsets and a gate to weight outputs. Using 17 handcrafted time- and frequency-domain features derived from two-channel sEMG data collected across four subjects and six gestures, MEET outperforms ten standard classifiers, achieving up to about 89% accuracy and favorable recall/F1 metrics. The study demonstrates MEET's potential for robust, scalable gesture decoding with implications for prosthetic control and human–computer interfaces, and outlines future work toward domain transfer, hybrid models, and hyperparameter optimization.

Abstract

Artificial intelligence (AI) has made significant advances in recent years and opened up new possibilities in exploring applications in various fields such as biomedical, robotics, education, industry, etc. Among these fields, human hand gesture recognition is a subject of study that has recently emerged as a research interest in robotic hand control using electromyography (EMG). Surface electromyography (sEMG) is a primary technique used in EMG, which is popular due to its non-invasive nature and is used to capture gesture movements using signal acquisition devices placed on the surface of the forearm. Moreover, these signals are pre-processed to extract significant handcrafted features through time and frequency domain analysis. These are helpful and act as input to machine learning (ML) models to identify hand gestures. However, handling multiple classes and biases are major limitations that can affect the performance of an ML model. Therefore, to address this issue, a new mixture of experts extra tree (MEET) model is proposed to identify more accurate and effective hand gesture movements. This model combines individual ML models referred to as experts, each focusing on a minimal class of two. Moreover, a fully trained model known as the gate is employed to weigh the output of individual expert models. This amalgamation of the expert models with the gate model is known as a mixture of experts extra tree (MEET) model. In this study, four subjects with six hand gesture movements have been considered and their identification is evaluated among eleven models, including the MEET classifier. Results elucidate that the MEET classifier performed best among other algorithms and identified hand gesture movement accurately.
Paper Structure (18 sections, 19 equations, 8 figures, 1 table)

This paper contains 18 sections, 19 equations, 8 figures, 1 table.

Table of Contents

  1. Introduction
  2. Materials and Methods
  3. Data Collection
  4. Preprocessing and Feature Extraction
  5. ML model
  6. Decision Tree (DT)
  7. Random Forest (RF)
  8. Gradient Boosting (GB)
  9. Adaboost (ADB)
  10. Support Vector Machine (SVM)
  11. Bagging (BAG)
  12. Logistic Regression (LR)
  13. Naive Bayes (NB)
  14. k-Nearest Neighbour (KNN)
  15. Extra Tree (ET)
  16. ...and 3 more sections

Figures (8)

  • Figure 1: Flow architecture for MEET-based gesture classification
  • Figure 2: Hardware setup used to acquire surface Electromyography (sEMG) data
  • Figure 3: MEET: Mixture of Experts Extra Tree Architecture
  • Figure 4: Confusion matrix of classifier ET and MEET
  • Figure 5: Accuracy plot of all the classifiers with MEET
  • ...and 3 more figures