Wearable high-density EMG sleeve for complex hand gesture classification and continuous joint angle estimation

High-density electromyography (HD-EMG) can provide a natural interface to enhance human-computer interaction (HCI). This study aims to demonstrate the capability of a novel HD-EMG forearm sleeve equipped with up to 150 electrodes to capture high-resolution muscle activity, decode complex hand gestures, and estimate continuous hand position via joint angle predictions. Ten able-bodied participants performed 37 hand movements and grasps while EMG was recorded using the HD-EMG sleeve. Simultaneously, an 18-sensor motion capture glove calculated 23 joint angles from the hand and fingers across all movements for training regression models. For classifying across the 37 gestures, our decoding algorithm was able to differentiate between sequential movements with <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"><mml:mrow><mml:mn>97.3</mml:mn> <mml:mo>±</mml:mo> <mml:mn>0.3</mml:mn> <mml:mo>%</mml:mo></mml:mrow> </mml:math> accuracy calculated on a 100 ms bin-by-bin basis. In a separate mixed dataset consisting of 19 movements randomly interspersed, decoding performance achieved an average bin-wise accuracy of <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"><mml:mrow><mml:mn>92.8</mml:mn> <mml:mo>±</mml:mo> <mml:mn>0.8</mml:mn> <mml:mo>%</mml:mo></mml:mrow> </mml:math> . When evaluating decoders for use in real-time scenarios, we found that decoders can reliably decode both movements and movement transitions, achieving an average accuracy of <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"><mml:mrow><mml:mn>93.3</mml:mn> <mml:mo>±</mml:mo> <mml:mn>0.9</mml:mn> <mml:mo>%</mml:mo></mml:mrow> </mml:math> on the sequential set and <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"><mml:mrow><mml:mn>88.5</mml:mn> <mml:mo>±</mml:mo> <mml:mn>0.9</mml:mn> <mml:mo>%</mml:mo></mml:mrow> </mml:math> on the mixed set. Furthermore, we estimated continuous joint angles from the EMG sleeve data, achieving a <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"><mml:msup><mml:mi>R</mml:mi> <mml:mn>2</mml:mn></mml:msup> </mml:math> of <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"><mml:mrow><mml:mn>0.884</mml:mn> <mml:mo>±</mml:mo> <mml:mn>0.003</mml:mn></mml:mrow> </mml:math> in the sequential set and <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"><mml:mrow><mml:mn>0.750</mml:mn> <mml:mo>±</mml:mo> <mml:mn>0.008</mml:mn></mml:mrow> </mml:math> in the mixed set. Median absolute error (MAE) was kept below 10° across all joints, with a grand average MAE of <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"><mml:mrow><mml:mn>1.8</mml:mn> <mml:mo>±</mml:mo> <mml:mn>0</mml:mn> <mml:mo>.</mml:mo> <mml:msup><mml:mn>04</mml:mn> <mml:mo>∘</mml:mo></mml:msup> </mml:mrow> </mml:math> and <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"><mml:mrow><mml:mn>3.4</mml:mn> <mml:mo>±</mml:mo> <mml:mn>0</mml:mn> <mml:mo>.</mml:mo> <mml:msup><mml:mn>07</mml:mn> <mml:mo>∘</mml:mo></mml:msup> </mml:mrow> </mml:math> for the sequential and mixed datasets, respectively. We also assessed two algorithm modifications to address specific challenges for EMG-driven HCI applications. To minimize decoder latency, we used a method that accounts for reaction time by dynamically shifting cue labels in time. To reduce training requirements, we show that pretraining models with historical data provided an increase in decoding performance compared with models that were not pretrained when reducing the in-session training data to only one attempt of each movement. The HD-EMG sleeve, combined with sophisticated machine learning algorithms, can be a powerful tool for hand gesture recognition and joint angle estimation. This technology holds significant promise for applications in HCI, such as prosthetics, assistive technology, rehabilitation, and human-robot collaboration.