1465 results about "Hide markov model" patented technology

A natural language interface control system for operating a plurality of devices consists of a first microphone array, a feature extraction module coupled to the first microphone array, and a speech recognition module coupled to the feature extraction module, wherein the speech recognition module utilizes hidden Markov models. The system also comprises a natural language interface module coupled to the speech recognition module and a device interface coupled to the natural language interface module, wherein the natural language interface module is for operating a plurality of devices coupled to the device interface based upon non-prompted, open-ended natural language requests from a user.

A medical device for predicting a user's future glycemic state includes a memory module, a processor module and a user alert module. The memory module is configured to receive and store a plurality of glucose concentrations as a function of time that were generated by a user's use of a continuous glucose monitor. The processor module is configured to derive first and second glucose prediction equations that are fits to the plurality of glucose concentrations stored in the memory module with the fits being based on first and second mathematical models, respectively. The processor module is also configured to calculate first and second predicted glucose concentrations at a future time using the first and second glucose prediction equations, respectively, and to also calculate an average predicted glucose concentration and a merit index based on the first and second predicted glucose calculations. The processor module is further configured to input the plurality of glucose concentrations as a function of time, the average predicted glucose concentration and the merit index into a trained model (e.g., a Hidden Markov Model) that outputs a set of glucose concentration probabilities for the future time and to then predict the user's future glycemic state based on the set of glucose concentration probabilities. The user alert module is configured to alert the user in a manner dependent on the predicted user's future glycemic state.

Analysis of individual's serial changes, also referred to as the physiological, pathophysiological, medical or health dynamics, is the backbone of medical diagnosis, monitoring and patient healthcare management. However, such an analysis is complicated by enormous intra-individual and inter-individual variability. To address this problem, a novel serial-analysis method and system based on the concept of personalized basis functions (PBFs) is disclosed. Due to more accurate reference information provided by the PBFs, individual's changes associated with specific physiological activity or a sequence, transition or combination of activities (for example, a transition from sleep to wakefulness and transition from rest to exercise) can be monitored more accurately. Hence, subtle but clinically important changes can be detected earlier than using other methods. A library of individual's PBFs and their transition probabilities (which can be described by Hidden Markov Models) can completely describe individual's physiological dynamics. The system can be adapted for healthcare information management, diagnosis, medical decision support, treatment and side-effect control. It can also be adapted for guiding health, fitness and wellness training, subject identification and more efficient management of clinical trials.

A method for predicting a user's future glycemic state includes measuring a user's glucose concentration at intervals over a time duration, thereby generating a plurality of glucose concentrations as a function of time. First and second glucose prediction equations that are fits to the plurality of glucose concentrations based on first and second non-identical mathematical models, respectively, are then derived. The method also includes calculating first and second predicted glucose concentrations at a future time using the first and second glucose prediction equations, respectively. Thereafter, an average predicted glucose concentration and a merit index are calculated based on the first and second predicted glucose calculations. The plurality of glucose concentrations as a function of time, the merit index and average predicted glucose concentration are input into a trained model (for example, a Hidden Markov Model) that outputs a set of glucose concentration probabilities. The user's future glycemic state is then predicted based on the set of glucose concentration probabilities.

The standard model creating apparatus which provides a high-precision standard model used for: pattern recognition such as speech recognition, character recognition, or image recognition using a probability model based on a hidden Markov model, Bayesian theory, or linear discrimination analysis; intention interpretation using a probability model such as a Bayesian net; data-mining performed using a probability model; and so forth, the apparatus comprising: a reference model preparing unit (102) operable to prepare at least one reference model; a reference model storing unit (103) operable to store the reference model (121) prepared by the reference model preparing unit (102); and a standard model creating unit (104) operable to create a standard model (122) by calculating statistics of the standard model so as to maximize or locally maximize the probability or likelihood with respect to the at least one reference model stored in the reference model storing unit (103).

An “Animation Synthesizer” uses trainable probabilistic models, such as Hidden Markov Models (HMM), Artificial Neural Networks (ANN), etc., to provide speech and text driven body animation synthesis. Probabilistic models are trained using synchronized motion and speech inputs (e.g., live or recorded audio / video feeds) at various speech levels, such as sentences, phrases, words, phonemes, sub-phonemes, etc., depending upon the available data, and the motion type or body part being modeled. The Animation Synthesizer then uses the trainable probabilistic model for selecting animation trajectories for one or more different body parts (e.g., face, head, hands, arms, etc.) based on an arbitrary text and / or speech input. These animation trajectories are then used to synthesize a sequence of animations for digital avatars, cartoon characters, computer generated anthropomorphic persons or creatures, actual motions for physical robots, etc., that are synchronized with a speech output corresponding to the text and / or speech input.

The invention discloses a real-time gesture interaction method based on computer vision, which comprises the following steps: acquiring a digital image from an image input device; detecting hands by a statistical learning method; initializing a hand contour tracker according to the detecting result, and calculating a skin color model of a specific hand; tracking the hand contour by a combined method of a conditional probability density transmission algorithm and a heuristic search technology; analyzing the moving track of the hands by a Hidden Markov Model to obtain the gesture identifying result; and applying the gesture analyzing result to the interaction of various application programs. The real-time gesture interaction method of the invention expands the interactive mode of the traditional mouse and keyboard, realizes automatic hand detection, tracking and gesture identification by the computer vision and image processing techniques, has real-time performance, robustness and easy realization and operation, and can enable computer users to interact with the computer more naturally, visually and intelligently by hand gestures.