AirScript: A Surface Electromyography (sEMG) Dataset for Airwriting Recognition of English Alphabets

The 'AirScript' dataset consists of surface electromyography (sEMG) signals obtained while writing the uppercase English alphabets (A–Z) in free space. The Delsys Trigno device was used to record forearm muscle activity from 16 subjects. Every subject performs two trials for each letter, thus resulting in 52 samples per subject. sEMG signals obtained from all subjects were stored at a 2000 Hz sampling rate for high temporal resolution. The dataset consists of raw sEMG signals that are stored in subject-specific folders and saved as `.npy` files. Electrodes were placed on the flexor and extensor muscles of the forearm such as Flexor Pollicis Longus, Flexor Carpi Radialis, Extensor Digitorum, Flexor Carpi Ulnaris, and Brachioradialis.   This process was enabled by a custom-built Graphical user interface (GUI) using Tkinter, which automate the display of instruction during the air writing task. The Delsys Trigno system records signals from five channels capturing muscle activity during contraction for each trial. The dataset is suitable for studies in EMG-based alphabet categorization, gesture recognition, and human-computer interaction. In addition to advancing wearable technologies, this dataset aids in the development of deep-learning models for precise air writing identification.