EMG-based silent speech recognition has achieved favorable performance recently, providing the possibility of assisted therapy for speech disorders and communication in specialized settings. Aiming at handling the dramatic degradation of classification accuracy caused by biological variations and articulation bias across speakers, we propose an optimized heuristic domain adaptive architecture extracting global features, speaker-related domain-specific features, and speakerindependent domain-invariant features from myoelectric signals, respectively. Through separate alignment and optimization in parallel, the effectiveness of the extracted features and the classification performance have been significantly enhanced. Experimental results show that our method achieves a classification accuracy of 94.40%, exceeding the state-of-the-art model by almost 10 percent, in a scenario with 60 subjects for training and 10 new subjects for validation.
Most of the existing hand data collection procedures rely on complex and bulky image acquisition systems, in fact, the data directly acquired by the acquisition systems do not have a realistic context, and the neural network models trained from these data perform not well in real-world situations, especially when people are wearing gloves in scenes with changing illumination. However, to improve the consistency of the image the traditional image fusion methods sacrifice the authenticity of the background and the supervised methods are limited by the data acquisition system which cannot generate high quality fusion image. Therefore, based on an unsupervised generative adversarial network, this paper introduced a generator based on a global attention module and proposed a histogram similarity-based image selection module to filter the input images. Our goal is to decrease the difficulty of the image migration task for the network. The model had been trained using a self-built dataset consisting of composited and real data, including images of hands wearing IMU data gloves and photographs taken in real life with similar backgrounds. Extensive experiments on image segmentation tasks demonstrated the effectiveness of the proposed model, which obtained a precision of 0.88 and a recall of 0.86 with a mean NIMA value of 4.27 compared to other state-of-the-art methods such as UEGAN and DoveNet.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.