Recognition of Hand Gesture Sequences by Accelerometers and Gyroscopes
| Autor: | Yun Jie Jhang, Wen-Jyi Hwang, Tsung-Ming Tai, Yen Cheng Chu |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2020 |
| Předmět: |
Computer science
02 engineering and technology Residual 01 natural sciences Convolutional neural network lcsh:Technology lcsh:Chemistry human–machine interface 0202 electrical engineering electronic engineering information engineering General Materials Science Instrumentation lcsh:QH301-705.5 Fluid Flow and Transfer Processes Artificial neural network business.industry lcsh:T Process Chemistry and Technology 010401 analytical chemistry General Engineering Feed forward Pattern recognition artificial intelligence feedforward neural networks hand gesture recognition lcsh:QC1-999 0104 chemical sciences Computer Science Applications lcsh:Biology (General) lcsh:QD1-999 Gesture recognition lcsh:TA1-2040 Hit rate Feedforward neural network 020201 artificial intelligence & image processing Artificial intelligence business lcsh:Engineering (General). Civil engineering (General) lcsh:Physics Gesture |
| Zdroj: | Applied Sciences, Vol 10, Iss 6507, p 6507 (2020) Applied Sciences Volume 10 Issue 18 |
| ISSN: | 2076-3417 |
| Popis: | The objective of this study is to present novel neural network (NN) algorithms and systems for sensor-based hand gesture recognition. The algorithms are able to classify accurately a sequence of hand gestures from the sensory data produced by accelerometers and gyroscopes. They are the extensions from the PairNet, which is a Convolutional Neural Network (CNN) capable of carrying out simple pairing operations with low computational complexities. Three different types of feedforward NNs, termed Residual PairNet, PairNet with Inception, and Residual PairNet with Inception are proposed for the extension. They are the PairNet operating in conjunction with short-cut connections and/or inception modules for achieving high classification accuracy and low computation complexity. A prototype system based on smart phones for remote control of home appliances has been implemented for the performance evaluation. Experimental results reveal that the PairNet has superior classification accuracy over its basic CNN and Recurrent NN (RNN) counterparts. Furthermore, the Residual PairNet, PairNet with Inception, and Residual PairNet with Inception are able to further improve classification hit rate and/or reduce recognition time for hand gesture recognition. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|