Finger Gesture Recognition Using Sensing and Classification of Surface Electromyography Signals With High-Precision Wireless Surface Electromyography Sensors

Abstract

Finger gesture recognition (FGR) plays a crucial role in achieving, for example, artificial limb control and human-computer interaction. Currently, the most common methods of FGR are visual-based, voice-based, and surface electromyography (EMG)-based ones. Among them, surface EMG-based FGR is very popular and successful because surface EMG is a cumulative bioelectric signal from the surface of the skin that can accurately and intuitively represent the force of the fingers. However, existing surface EMG-based methods still cannot fully satisfy the required recognition accuracy for artificial limb control as the lack of high-precision sensor and high-accurate recognition model. To address this issue, this study proposes a novel FGR model that consists of sensing and classification of surface EMG signals (SC-FGR). In the proposed SC-FGR model, wireless sensors with high-precision surface EMG are first developed for acquiring multichannel surface EMG signals from the forearm. Its resolution is 16 Bits, the sampling rate is 2 kHz, the common-mode rejection ratio (CMRR) is less than 70 dB, and the short-circuit noise (SCN) is less than 1.5 μV. In addition, a convolution neural network (CNN)-based classification algorithm is proposed to achieve FGR based on acquired surface EMG signals. The CNN is trained on a spectrum map transformed from the time-domain surface EMG by continuous wavelet transform (CWT). To evaluate the proposed SC-FGR model, we compared it with seven state-of-the-art models. The experimental results demonstrate that SC-FGR achieves 97.5% recognition accuracy on eight kinds of finger gestures with five subjects, which is much higher than that of comparable models.

Emergence of integrated biosensing-enabled digital healthcare devices

“…Table 4 presents some recent advancements in detection and diagnosis for biosensing applications. 96–128 Sensors based on diverse functionalities and constituents, such as capacitive pressure sensing, healing wearable sensors, pressure, wireless, FRET-based genetically encoded sensors for silver ions, oxygen sensors on an optofluidic platform, location tracking, metamaterials based on soft tactile, electrospinning-based PVDF-TrFE nanofiber sensors, glycine–chitosan-based biodegradable piezoelectric sensors, and DNA-regulated CRISPR-Cas12a sensors, represent important advances in the biosensor field. 96–106 Detection is based on diverse approaches, including paper-based devices, 3D-printing electrochemical, MoS 2 quantum dots, 2D nanomaterial-enhanced plasmonic functionality, smartphone-integrated colorimetric, PVDF-TrFE nanofiber, electronic, machine learning, fluorescent DNA, non-enzymatic glucose, and silicon nanowire biosensing platforms for the (bio)detection of various analytes ranging from metal, pollutants, cells, genetic materials, and even post-translational modification.…”

Characteristics of glucose change in diabetes mellitus generalized through continuous wavelet transform processing: A preliminary study

“…Recently, the continuous wavelet transform (CWT) method was utilized for the analysis of oscillating data obtained from clinical diagnostic tools, such as those produced by electroencephalography[ 3 , 4 ], electromyography[ 5 , 6 ], electroretinography[ 7 ], phonocardiography[ 8 , 9 ], ultrasound sonoelastography[ 10 ], and electrocardiography including a longitudinal wave[ 5 , 11 - 14 ]. This type of processing has epochal merit for simultaneously exploring the time and frequency domains, although Fourier transform is unable to analyze a time domain[ 15 - 17 ].…”