Acquisition and Classification System of EMG Signals for Interpreting the Alphabet of the Sign Language

Abstract

Taking into account that in Peru, there is an increase in people with difficulties in speaking or communicating. According to the National Institute of Statistics and Informatics of Peru (INEI for its acronym in Spanish), around 80000 people use the gesturing language. For this reason, this research proposes to use the electromyography (EMG) signals to detect the hand movement and identify the alphabet of the sign language to provide essential communication to people who need it. The idea is to classify the signals and recognize the letters of the Spanish alphabet, interpreted in the Peruvian sign language. The results show the classification of the 27 letters of the alphabet with a general success rate of 93.9%.

Multi-Channel Muscle Armband Implementation: Electronic Circuit Validation and Considerations towards Medical Device Regulation Assessment

“…The ARM Cortex M4 offers direct memory access (DMA) for peripheral ports which offers time efficiency and does prevent the system from blocking execution while reading signals [11].…”

“…It can be seen that the offset of the signal is amplified by the instrumental amplifier in proportion to its gain (11), in general offsets are suppressed largely by a high pass filter; however, this filter leaves a small offset of up to 24mV approximately. Which is amplified in the following stages where this offset becomes very noticeable.…”

SDAV 1.0: A Low-Cost sEMG Data Acquisition & Processing System For Rehabilitatio

“…Various research groups have investigated the complicated structure of sEMG signals using commercial or low-cost setups. Witman et al [7,8] examined it for recognizing finger movement and interpreting the alphabet of sign language; Kumar et al [9], Arjunan et al [10,11], Naik et al [12], Meltzner et al [13], Larraz et al [14], Agnihotri et al [15], Vyas et al [16], Kachhwaha et al [17], and Chandrashekhar [18] explored it for silent speech content recognition; Russo et al [19] studied it for a prosthetic robotic hand; Sidik et al [20] and Kareem et al [21] probed it to acquire lower arm motion, and Crawford et al [22] used it to capture facial expressions. Due to its non-invasive, safe, and effective method for measuring muscle activity, sEMG is a valuable tool for evaluating muscle function, diagnosing muscle disorders, monitoring muscle activity during physical activity, and designing ergonomic equipment.…”

“…According to research findings presented by [16,20,21], authors recommend that complex algorithms capable of performing many jobs concurrently were required to gather accurate data in low-cost setups. According to [7,8,16], individuals have difficulty computing features and their storage in real-time as data is captured utilizing low-cost equipment. This real-time feature vector computation task encourages us to develop an algorithm utilizing low-cost hardware for sEMG data acquisition.…”

Neural Decoding of Chinese Sign Language With Machine Learning for Brain–Computer Interfaces

“…Researchers have also discovered that sign language recognition based on physiological signals can overcome the trouble of image sign language recognition. Witman et al [46] suggested using EMG signals to detect hand movement, identifying the alphabet of sign language to classify signals, identifying letters in the Spanish alphabet, and interpreting them in Peruvian sign language. Ajiboye et al [47] predicted the American Sign Language alphabet based on the muscle activity of the hands and forearms in 33 postures statically imitated by the subjects.…”