University of Illinois

Aura Systems Inc.

Sigmedics, Inc.

Sigmedics, Inc. of Delaware

Other

Gs Systems, Inc.

Grannet Corporation

Daniel Graupe

Amihadar Arber

Menachem H Graupe

Yunde Zhong

David W Carley

Stavros Basseas

Ishita Basu

Piotr L Suliga

Jonathan Waxman

Adam J Efron

Silvano A Romeo

Daniela Tuninetti

Apparatus and methods are disclosed for generating and outputting physiological event results from physiological data related to a patient. Physiological event results include results predicting and/or detecting individual physiological events related to a medical condition of the patient.

Detection and prediction of physiological events in people with sleep disordered breathing using a LAMSTAR neural network

A system that incorporates teachings of the present disclosure may include, for example, a Neuro Sensing and Stimulation Device having a conductive lead for implanting in a brain of a living entity, a sensor coupled to the conductive lead for collecting data associated with one or more electrical signals detected in the conductive lead, a stimulator coupled to the conductive lead to apply one or more electrical signals thereto, and a controller. The controller can be operable to collect data associated with one or more electrical signals detected in the conductive lead, determine a stimulation sequence from the collected data, and direct the stimulator to apply on the conductive lead one or more electrical signals determined from the stimulation sequence. Additional embodiments are disclosed.

Apparatus for managing a neurological disorder

A system that incorporates teachings of the present disclosure may include, for example, a device having a stimulation sequence generator device, at least one implantable electrode for insertion in a brain of a human being, where the at least one implantable electrode is coupled to the stimulation sequence generator, a sensor for placement on a body part of the human being, and a controller coupled to the stimulation sequence generator device and the sensor. The controller can be operable to receive a signal from the sensor, extract from the signal characteristics corresponding to desirable movements of the body part of the human being to generate output data, detect a condition from the output data for predicting an upcoming tremor, and cause the stimulation sequence generator device to apply a stimulation to the at least one implantable electrode for a first period responsive to the detected condition to prevent the upcoming tremor.

Method and apparatus for closed-loop deep brain stimulation in treating neurological diseases

A blind adaptive filter of an apparatus in an example employs a frequency domain ECG-feature vector and a time domain ECG feature vector with a maternal ECG parameter estimate and a set of candidate fetal ECG estimates that satisfy the frequency domain ECG-feature-vector, to extract a fetal ECG signal estimate from raw abdominal ECG signals of a pregnant female. The fetal ECG signal estimate satisfies the frequency domain ECG feature-vector and the time domain ECG feature vector.

Blind adaptive filter extraction of fetal electrocardiogram signal estimate

One or more fetal heart component signals in one example are separated from heart signal information obtained from a pregnant female based on singular value decomposition.

Separation of one or more fetal heart component signals from heart signal information obtained from a pregnant female

The spectral range of a stochastic time series of information, including unvoiced speech is reduced to allow transmission over a substantially narrowed frequency band. Sets of autoregressive (AR) parameters are identified for successive time windows of the original time series and of subsequent stages of subsampled reduced-spectrum models of each window of the original time series are used. The AR parameters are transmitted together with subsampled windows of the original data. These AR parameters are used to reconstruct a least square stochastic estimate of the transmitted subsampled time series in a backwards manner from the most subsampled spectrum back to the original spectrum using a sequence of predictive feedback algorithms. Past prediction outputs are feedback for prediction whenever samples are missing. This process yields a high quality reconstructed signal that preserves not only speech parameters and intelligibility, but also near-natural speaker identifiability.

N-stage predictive feedback-based compression and decompression of

A network system analyzes input words for the search and retrieval of pertinent information. The novel system then selects a module of a self organizing map (SOM) which contains the same dimension of classification as a selected input word and where neurons are interconnected horizontally (between modules) and vertically (at input and inside a module) by arrays of link weights. The system then determines what nodes or processing units within the SOM will be activated and subsequently compared to the selected input word. Feedback is utilized via a punishment/reward scheme to adjust the link weights so that the system learns the best paths and/or methods to create acceptable decisions or outputs.

Large memory storage and retrieval (LAMSTAR) network

The input signal is filtered by bandpass filters having different passbands. These filtered signals are input to power detectors that average the power present in each band. A comparator compares each power level signal to a predetermined power threshold to determine if information is present in any of the bands. If information is present in the upper bands, the information is transformed by a discrete wavelet transform and is thresholded and then shifted to the lower bands. The process by which the shifting operation was accomplished is stored in a code book band. An inverse wavelet transform generates the compressed signal by transforming the signals from the wavelet domain to the time domain. If the signal was compressed, the code book signal is transmitted with the compressed signal to a receiving unit for decompression. If the signal was not compressed, the code book signal and the original input signal is transmitted to the receiving unit. The receiving unit receives the transmitted signal and reconstructs the original input from the transmitted signal, either directly or by re-spreading and transforming the compressed signal from the transmitted signal responsive to the code book signal embedded with the transmitted signal.

Compression/decompression for preservation of high fidelity speech

A method and system for blind adaptive filtering an input signal having noise and information signal parameters that are separated by an identifier. An open loop filter stage generates an intermediate filtered signal from the noise parameters and the input signal parameters. A cost function generator generates a first cost function signal and an inverse first cost function signal from the open loop filter parameters. A residual signal is generated from the difference between the input signal and the intermediate filtered signal. Another cost function generator, coupled to the input signal and the residual signal generator, generates a second cost function signal and an inverse second cost function that maximize a stationarity feature of the residual signal. A combiner generates a combined cost function from the inverse first and second cost functions. A quasi-closed loop filter generates the filtered output signal from the intermediate filtered signal.

Blind adaptive filtering of unknown signals in unknown noise in

A method and system for filtering a noisy input comprised of an information signal and a noise signal. No prior time domain value information or frequency domain parameter information on the information signal or noise signal is available. A whitening filter renders the noise part of a noise signal into a substantially white noise signal. A fourier transform system provides an amplitude spectrum output and a phase output. A multiplier squares the amplitude spectrum output thus providing a power spectrum output. A zero mean sub-system generates a zero mean power spectrum output from the power spectrum output. A square root sub-system squares the zero mean power spectrum output thus providing a resultant output. An inverse Fourier transform sub-system inversely transforms the resultant output to provide a time domain resultant output. An inverse whitening filter provides a substantially noise free output from the time domain resultant output.

Non-linear deterministic stochastic filtering method and system

This disclosure relates to a self-adaptive noise cancellation system that may be employed in a noise environment at the vicinity of an acoustic noise source to produce noise signals denoted as anti-noise signals that are directed towards a geometric region of the same environment and which counter the first acoustic noise source thus rendering the geometric region relatively quiet. The system monitors the acoustic noise source to identify its signal parameters thus retrieving the noise parameters that are required for the device to tune itself in order to cope with variations in the parameters of the noise source and to adapt its own anti-noise output to keep adequate noise cancellation in said geometric region in the face of the changes in the characteristics of the noise source, such as changes in power or in frequency spectrum of the noise source.

Noise cancellation system

A system is provided to reduce noise from a signal of speech that is contaminated by noise. The present system employs an artificial intelligence that is capable of deciding upon the adjustment of a filter subsystem by distinguishing between noise and speech in the spectrum of the incoming signal of speech plus noise. The system does this by testing the pattern of a power or envelope function of the frequency spectrum of the incoming signal. The system determines that the fast changing portions of that envelope denote speech whereas the residual is determined to be the frequency distribution of the noise power. This determination is done while examining either the whole spectrum, or frequency bands thereof, regardless of where the maximum of the spectrum lies. In another embodiment of the invention, a feedback loop is incorporated which provides incremental adjustments to the filter by employing a gradient search procedure to attempt to increase certain speech-like features in the system's output. The present system does not require consideration of minima of functions of the incoming signal or pauses in speech. Instead, the present system employs an artificial intelligence system to which is input the envelope pattern of the incoming signal of speech and noise. The present system then filters out of this envelope signal the rapidly changing variations of the envelope over fixed time windows.

Artificial intelligence pattern-recognition-based noise reduction system

In accordance with the present invention, a functional electrical stimulation system enables upper-motor-neuron paraplegic patients and certain other paralyzed or partially paralyzed patients to stand and to take steps with the support of a walker in an independent fashion so that they are in control of the stimulation and, noting that they have very little or no sensation, that they still can obtain some feedback on the state of the system. In one embodiment, a compact and safe battery-operated stimulation system is provided that is of pocket size and that allows for non-invasive safe and controlled stimulation using skin surface electrodes. The system of the present invention is a stimulation system for providing upper-motor-neuron paralyzed patients with capabilities of unbraced standing and unbraced walking, which consists of a single pulse power and amplifier that outputs various trains of stimulation pulses and which is totally under microprocessor generation and control, where the microprocessor's microcomputer selectively performs multiplexing of the pulse trains and their selective alternate distribution to the various surface electrodes attached to the skin of the patient at the appropriate stimulation locations. It also controls pulse-width, pulse-duration, pulse-amplitude and pulse-shape. Furthermore, the system can compute and activate (audible and/or visual) warning signals to warn the patient when the system is close to its maximal output. This would happen when muscle fatigue is such that no further increase in stimuli level can keep the patient upright. The system computes and outputs indications of the various stimuli levels to a visual display, and it provides automatic fail-safe and override capabilities to help ensure that the patient does not fall in case of major circuit or system failure or misactivation. This is a critical capability since this system will be used by paraplegics who lack sensation in their lower extremities.

Microprocessor-controlled multiplexed functional electrical stimulator

In accordance with the present invention, a functional electrical stimulation system enables upper-motor-neuron paraplegic patients and certain other paralyzed or partially paralyzed patients to stand and to take steps with the support of a walker in an independent fashion so that they are in control of the stimulation and, noting that they have very little or no sensation, that they still can obtain some feedback on the state of the system. In one embodiment, a compact and safe battery-operated stimulation system is provided that is of pocket size and that allows for non-invasive save and controlled stimulation using skin surface electrodes. The system of the present invention is a stimulation system for providing upper-motor-neuron paralyzed patients with capabilities of unbraced standing and unbraced walking, which consists of a single pulse power and amplifier that outputs various trains of stimulation pulses and which is totally under microprocessor generation and control, where the microprocessor`s microcomputer selectively performs multiplexing of the pulse trains and their selective alternate distribution to the various surface electrodes attached to the skin of the patient at the appropriate stimulation locations. It also controls pulse-width, pulse-frequency, pulse-amplitude and pulse-shape. The system measures, analyzes, computes, activates and implements safety measures to protect the patient during steps, when sitting down, and in case of a malfunctioning electrode.

Microprocessor-controlled enhanced multiplexed functional electrical

Muscle fatigue of an electrically stimulated quadriceps muscle of an upper motor neuron paraplegic is detected and compensated for by monitoring the myoelectric (EMG) signal produced by the stimulated muscle and controlling one or more of the following parameters of the electrical stimulation (ES) signal; its pulse repetition rate, its amplitude, and its pulse width.

Growing community of inventors

Highland Park, IL, United States of America

Daniel Graupe