Patents
Literature
Hiro is an intelligent assistant for R&D personnel, combined with Patent DNA, to facilitate innovative research.
Hiro

105 results about "Muscle activation" patented technology

Gesture synthesizer for electronic sound device

A MIDI-compatible gesture synthesizer is provided for use with a conventional music synthesizer to create musically realistic<DEL-S DATE="20020416" ID="DEL-S-00001" / >ally<DEL-E ID="DEL-S-00001" / > sounding gestures. The gesture synthesizer is responsive to one or more user controllable input signals, and includes several transfer function models that may be user-selected. One transfer function models properties of muscles using Hill's force-velocity equation to describe the non-linearity of muscle activation. A second transfer function models the cyclic oscillation produced by opposing effects of two force sources representing the cyclic oppositional action of muscle systems. A third transfer function emulates the response of muscles to internal electrical impulses. A fourth transfer function provides a model representing and altering virtual trajectory of gestures. A fifth transfer function models visco-elastic properties of muscle response to simulated loads. The gesture synthesizer outputs <DEL-S DATE="20020416" ID="DEL-S-00002" / >MIDI-compatible<DEL-E ID="DEL-S-00002" / > continuous pitch data, tone volume and tone timbre information. The continuous pitch data is combined with discrete pitch data provided by the discrete pitch generator within the conventional synthesizer, and the combined signal is input to a tone generator, along with the tone volume and tone timbre information. The tone generator outputs tones that are user-controllable in real time during performance of a musical gesture.
Owner:LONGO NICHOLAS

Silent speech recognition method based on face and neck surface myoelectricity

ActiveCN113288183AImprove the performance of silent speech recognitionAids in unvoiced speech recognitionDiagnostic recording/measuringSensorsEngineeringElectrode array
The invention discloses a silent speech recognition method based on face and neck surface electromyography, and the method comprises the steps: carrying out the data preprocessing and feature extraction of surface electromyography signals collected by a high-density electrode array and discrete electrodes, obtaining a high-density sEMG image set and a channel sparse sEMG image set, and constructing a source domain database and a target domain database; then training the word classification deep neural network by using the source domain database, and completing the calibration of the network in the target domain database by using transfer learning; and if the test user expresses the words silently under the input of the discrete electrodes, wherein the calibrated network can complete word classification and realize silent speech recognition. According to the invention, the capability of capturing abundant muscle activation mode information of a high-density electrode array and the portability and easiness in wearing of discrete electrodes are considered, certain robustness is provided for slight electrode offset and cross-user conditions, and the performance of silent speech recognition under discrete electrode input is improved; and a new thought is provided for the silent speech recognition method.
Owner:UNIV OF SCI & TECH OF CHINA

Method for recognizing upper limb and hand rehabilitation training action of stroke patient

ActiveCN111184512AEasy to distinguish operationReserve space propertiesDiagnostic recording/measuringSensorsBiologyRehabilitation training
The invention discloses a method for recognizing upper limb and hand rehabilitation training action of a stroke patient. The method comprises the following steps: performing blind source separation onelectromyographic signal data by using a non-negative matrix factorization model, and removing non-stationary muscle activation information to obtain a stable time-varying blind source separation result; performing further pattern recognition by using the factorized time-varying blind source separation result data to improve the stability and accuracy of recognition; and making learning featuresmaintain time and space characteristics at the same time through a CNN-RNN model. The CNN-RNN model does not require manual data feature extraction and screening, directly processes the data, automatically extracts the features and completes classification recognition, can realize end-to-end rehabilitation training action recognition analysis, and is combined with an attention layer for attentionweighting of a hidden state of a second layer in a two-layer two-way GRU layer to give a greater weight to data with a greater contribution degree, so that the data can play a greater role, and the accuracy of classification recognition is further improved.
Owner:UNIV OF ELECTRONICS SCI & TECH OF CHINA
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products