Comparative Study of Machine Learning Algorithms to Classify Hand Gestures from Deployable and Breathable Kirigami-Based Electrical Impedance Bracelet

Abstract

Wearable devices are gaining recognition for their use as a biosensor platform. Electrical impedance tomography (EIT) is one of the sensing techniques that utilizes wearable sensors as its primary data acquisition system. It measures the impedance or resistance at the peripheral (skin) level and calculates the conductivity distribution throughout the body. Even though the technology has existed for several decades, modern-day EIT devices are still costly and bulky. The paper proposes a novel low-cost kirigami-based wearable device that has soft PEDOT: PSS electrodes for sensing skin impedances. Simulation results show that the proposed kirigami structure for the bracelet has a large deformation during actuation while experiencing relatively lower stress. The paper also presents a comparative study on a few machine learning algorithms to classify hand gestures, based on the measured skin impedance. The best classification accuracy (91.49%) was observed from the quadratic support vector machine (SVM) algorithm with 48 principal components.

MyoSpring: 3D Printing Mechanomyographic Sensors for Subtle Finger Gesture Recognition

“…This can lead to any performance outcome purely due to chance. Therefore, as with similar prior work, a 10-fold cross-validation approach was used to reduce the effects of overfitting, and it is suitable for evaluating how the models would work with unseen data [5,36,45,47,83]. We observed that SMO achieved the most consistent classification performance, compared to the other algorithms which tend to exhibit a higher degree of variability.…”

A Review of EMG-, FMG-, and EIT-Based Biosensors and Relevant Human–Machine Interactivities and Biomedical Applications

“… The generation, processing, and application of FMG, EMG, and EIT signals. ( a ) Use FMG to predict forces in two directions [ 12 ]; ( b ) a novel kirigami-based bracelet senses the skin impedance signals, which is used to distinguish between different gestures [ 13 ]; ( c ) identify the movement intention based on sEMG [ 14 ]; ( d ) an EIT-based technique for assessing spinal cord injury [ 15 ]. …”

“…Peripheral blood vessel puncture control system based on electrical impedance measurement [ 119 ]. A novel kirigami-based bracelet is used to sense the skin impedance signals for distinguishing between different gestures [ 13 ]. A method based on EMG, MMG, and ultrasound images to study internal muscle morphological changes in stroke survivors while walking [ 120 ].…”

“…The generation, processing, and application of FMG, EMG, and EIT signals are showed in Figure 1. to predict forces in two directions [12]; (b) a novel kirigami-based bracelet senses the skin impedance signals, which is used to distinguish between different gestures [13]; (c) identify the movement intention based on sEMG [14]; (d) an EIT-based technique for assessing spinal cord injury [15]. [12]; (b) a novel kirigami-based bracelet senses the skin impedance signals, which is used to distinguish between different gestures [13]; (c) identify the movement intention based on sEMG [14]; (d) an EIT-based technique for assessing spinal cord injury [15].…”