The classification of active speech vs. inactive speech in noisy speech is an important pan of speech applications. typically in order to achieve a lower bit-rate. In this work, the error rates for raw classification (i.e. with no hangover mechanism) of noisy speech obtained with traditional classification algorithms arc compared to the rates obtained with Neural Network classifiers, trained with different leaming algorithms. The traditional classification algorithms used are the linear classifier, some Nearest Neighbor classifiers and the Quadratic Gaussian classifier. The training algorithms used for the Neural Networks classifiers arc the Extended Kalman Filter and the Levenberg-Marquadt algorithm. An evaluation of the computational complexity for the different classification algorithms is presented. Our noisy speech classification experiments show that using Neural Network classifiers typically produces a more accurate and more robust classification than other traditional algorithms, while having a significantly Iowcr computational complexity. Neural Network classifiers may therefore be a good choice for the core component of a noisy speech classifier, which would typically also include a hangover mechanism and possibly a speech enhancement algorithm.

Wearing a mask greatly reduced the possibility of infection during the COVID-19 pandemic. However, major inconveniences occur regarding patients with upper limb amputations, as they cannot independently wear masks. As a result, bacterial contamination is caused by medical staff touching the quilt when helping. Furthermore, this effect can occur with ordinary people due to accidental touch. This research aims to design an automatic and portable face shield assistive device based on surface electromyography (sEMG) signals. A concise face shield-wearing mechanism was built through 3D printing. A novel decision-making control method regarding a feature extraction model of 16 signal features and a Softmax classification neural network model were developed and tested on an STM32 microcontroller unit (MCU). The optimized electrode was fabricated using a carbon nanotube (CNT)/polydimethylsiloxane (PDMS). The design was further integrated and tested, showing a promising future for further implementation.

Back Propagation (BP) neural network can learn and store a large number of input-output model nonlinear relationships with simple structure. Niche ant colony algorithm (NACA) combines the ant colony algorithm (ACA) with the niche technology in order to add its local search ability to ACA with preserving the intelligent search ability and robustness of ACA. To optimize predicting model establishment of the dam monitoring data, NACA and BP neural network modeling method are combined to establish a prediction model of horizontal displacement monitoring data. The traditional BP neural network prediction model is established to make a comparison with the NACA. The results show that NACA-BP neural network method can speed up the convergence rate of BP neural network and enhance local search ability and prediction accuracy.