 This study presents a novel wearable, intelligent A-channel electromyography EMG-based system for recognizing 21 types of gestures. An analog front-end, AFE-integrated chip, IC, was developed to detect the EMG signals and an integrated EMG signal acquisition device integrating an elastic armband was fabricated. A lightweight one-dimensional convolutional neural network, CNN, model was constructed and subjected to individualized training by using the SIAT database. The maximum signal recognition accuracy was 89.96% and the average model training time was 14 minutes and 13 seconds. Given its small size, the model can be applied on lower performance edge computing devices and is expected to be applied to smartphone terminals in the future. This article was authored by Zeng Jiu, Yi Chen Lu, Qi Yan and others.