Multilanguage-handwriting self-powered recognition based on triboelectric nanogenerator enabled machine learning

Abstract

Handwriting signature is widely used and the main challenge for handwriting recognition is how to obtain comprehensive handwriting information. Triboelectric nanogenerator is sensitive to external triggering force and can be used to record personal handwriting signals and associated characteristics. In this work, micro/nano structure textured TENG acting as a smart self-powered handwriting pad is developed and its effectiveness for handwriting recognition is demonstrated. Three individuals' handwriting signals of English words, Chinese characters and Arabic numerals are acquired by leaf-inspired TENG, and the other three people's handwriting signals of English sentences and the corresponding Chinese sentences are obtained by cylindrical microstructured PDMS based TENG, and these signals exhibit unique features. Combined with the machine learning method, the people's handwriting was successfully identified. The classification accuracies of 99.66%, 93.63%, 91.36%, 99.05%, and 97.73% were reached for English words, Arabic numerals, Chinese characters, English sentences, and the corresponding Chinese sentences, respectively. The results strongly suggested that the textured TENG exhibited great potential in personal handwriting signature identification, security defense, and private information protection applications. This work presented a killer approach for multilanguage handwriting signal sensing and recording. We reported a smart self-powered handwriting pad based on micro/nano-structures textured TENG for sensing different individuals’ handwriting. The obtained signals exhibited unique features both in time domain and frequency domain which could be used in personal handwriting signature identification. For the first time, a novel solution for recognizing personal handwriting combing TENG based smart self-powered device, advanced signal processing and machine learning method was reported. We successfully demonstrated that extremely high classification accuracies achieved by using the proposed advanced technology. • TENG based self-powered handwriting pad was designed and fabricated. • The handwriting pad was sensitive and rapidly-responding to handwriting behavior. • Handwriting was recognized by combing the handwriting pad and machine learning method. • Extremely high classification accuracies were obtained for three kinds of characters.