939 results about "Signal classification" patented technology

The present invention relates to a method and device for improving concealment of frame erasure caused by frames of an encoded sound signal erased during transmission from an encoder (106) to a decoder (110), and for accelerating recovery of the decoder after non erased frames of the encoded sound signal have been received. For that purpose, concealment/recovery parameters are determined in the encoder or decoder. When determined in the encoder (106), the concealment/recovery parameters are transmitted to the decoder (110). In the decoder, erasure frame concealment and decoder recovery is conducted in response to the concealment/recovery parameters. The concealment/recovery parameters may be selected from the group consisting of: a signal classification parameter, an energy information parameter and a phase information parameter. The determination of the concealment/recovery parameters comprises classifying the successive frames of the encoded sound signal as unvoiced, unvoiced transition, voiced transition, voiced, or onset, and this classification is determined on the basis of at least a part of the following parameters: a normalized correlation parameter, a spectral tilt parameter, a signal-to-noise ratio parameter, a pitch stability parameter, a relative frame energy parameter, and a zero crossing parameter.

Abstract of Disclosure A system and method for managing the spectrum utilization of a frequency band that is shared, both in frequency and time, by multiple devices. At one or more devices operating in the frequency band, pulses associated with signals occurring in the frequency band are detected by sampling part or all the frequency band for a time interval. From the detected signal pulses, the signals can be classified. In addition, overall spectrum activity can be measured. Using classification information for signals detected in the frequency band, policies can be executed so that a device may take certain actions in order to avoid interfering with other signals, or to optimize simultaneous use of the frequency band with the other signals. Signal detection occurs at one or more devices operating in a frequency band. Signal classification and measurement, as well as policy execution may occur within a processor of the same device where signal detection occurs, or in another device (located remotely or within the operating region of the frequency band).

In a method of cognitive communication for non-interfering transmission, wherein the improvement comprises the step of conducting radio scene analysis to find not just the spectrum holes or White spaces; but also to use the signal classification, machine learning and prediction information to learn more things about the existing signals and its underlying protocols, to find the Gray space, hence utilizing the signal space, consisting of space, time, frequency (spectrum), code and location more efficiently.

In a method of cognitive jamming where smart and energy efficient jamming techniques are suggested based on sensing, classification and machine learning of the existing signals.

An audio encoder has a window function controller, a windower, a time warper with a final quality check functionality, a time/frequency converter, a TNS stage or a quantizer encoder, the window function controller, the time warper, the TNS stage or an additional noise filling analyzer are controlled by signal analysis results obtained by a time warp analyzer or a signal classifier. Furthermore, a decoder applies a noise filling operation using a manipulated noise filling estimate depending on a harmonic or speech characteristic of the audio signal.

A device and method for estimating a tonality of a sound signal comprise: calculating a current residual spectrum of the sound signal; detecting peaks in the current residual spectrum; calculating a correlation map between the current residual spectrum and a previous residual spectrum for each detected peak; and calculating a long-term correlation map based on the calculated correlation map, the long-term correlation map being indicative of a tonality in the sound signal.

A method and apparatus to determine an encoding mode of an audio signal, and a method and apparatus to encode an audio signal according to the encoding mode. In the encoding mode determination method, a mode determination threshold for the current frame that is subject to encoding mode determination is adaptively adjusted according to a long-term feature of the audio signal for a frame (the current frame) that is subject to encoding mode determination, thereby improving the hit rate of encoding mode determination and signal classification, suppressing frequent oscillation of an encoding mode in frame units, improving noise tolerance, and improving smoothness of a reconstructed audio signal.

A display device and a driving method thereof includes categorizing red-color, green-color, and blue-color image signals as belonging to one of first and second signal regions, detecting if the image signals have more signals belonging to the first signal region than the second signal region or if the image signals have more signals belonging to the second signal region than the first signal region, driving an image display portion in a first manner if the image signals are detected to have more signals belonging to the first signal region than the second signal region, and driving the image display portion in a second manner if the image signals are detected to have more signals belonging to the second signal region than the first signal region, the image display portion including a plurality of pixels, each of the pixels having red-color, green-color, blue-color, and white-color sub-pixels.

An apparatus and method for detecting swallowing activity is provided. In an embodiment, a method includes receiving an electronic signal from an accelerometer that represents swallowing activity, extracting at least two features from the signal, classifying the signal as a type of swallowing activity based on the extracted features, and generating an output of the classification. Exemplary activities include swallows, aspirations, movement and vocal artifacts. By indicating whether an activity is a swallow or an aspiration, the manner in which a patient afflicted with an increased likelihood for aspirations is fed can be adjusted to increase the likelihood of achieving a swallow instead of an aspiration during feeding. In turn this could reduce hospitalizations for aspiration pneumonia in patients with acute or chronic injury.

Low bit rate audio coding such as BWE algorithm often encounters conflict goal of achieving high time resolution and high frequency resolution at the same time. In order to achieve best possible quality, input signal can be first classified into fast signal and slow signal. This invention focuses on classifying signal into fast signal and slow signal, based on at least one of the following parameters or a combination of the following parameters: spectral sharpness, temporal sharpness, pitch correlation (pitch gain), and/or spectral envelope variation. This classification information can help to choose different BWE algorithms, different coding algorithms, and different postprocessing algorithms respectively for fast signal and slow signal.

Class types of input signals having unknown class types are automatically classified using a neural network. The neural network learns features associated with a plurality of different observed signals having respective different known class types. The neural network then recognizes features of the input signals having unknown class types that at least partially match at least some of the features associated with the plurality of different observed signals having respective different known class types. The neural network determines probabilities that each of the input signals has each of the known class types based on strengths of the matches between the recognized features of the input signals and the features associated with plurality of different observed signals. The neural network classifies each of the input signals as having one of the respective different known class types based on a highest determined probability.

A method of converting image signals for a display device including six-color subpixels is provided, which includes: classifying three-color input image signals into maximum, middle, and minimum; decomposing the classified signals into six-color components; determining a maximum among the six-color components; calculating a scaling factor; and extracting six-color output signals.

A method for accurate and rapid automated detection of atrial fibrillation (AF), sinus rhythm (SF), and atrial flutter (AFL) is disclosed, which allows distinguishing of these cardiac signals with lowered risk of errors by implanted pacemakers and like devices. The method includes training episodes of intra-cardiac signals (called the closed data set CDS) to evaluate five feature parameters with a discriminator classifying the signal into AF, AFL or sinus rhythm (SR). Comparison with the independent decisions of experienced physicians for each episode reveals specificity, accuracy and sensitivity of greater than 97%. Each episode is a window of intracardiac signal of interval 1-2 seconds with the discriminator providing results in less than 0.25 s. In another aspect, the method is resistant to the presence of noise in the data. In yet another aspect, more feature parameters may be used in alternative implementations including for detecting signals other than AF, AFL & SR.

A system and method for classifying radar emitters includes: (a) receiving a plurality of signals from the radar emitters; (b) generating data components for each signal received from the radar emitters; (c) forming multi-dimensional samples using the generated data components; and (d) sorting the multi-dimensional samples into a plurality of data clusters, based on their respective proximity to the data clusters, each data cluster representing a classification of a radar emitter.

Systems and methods of using machine-learning in a cognitive radio to avoid a jammer are described. Smoothed power spectral density is used to detect activity in a sub-band and basic characteristics of different signals therein extracted. If unable to classify the signals as either a valid signal or a jammer using the basic characteristics, ANN-based classification with cumulants features of the signals is used. Multiple periods are used to train sensing and communications (S/C) polices to track and avoid a jammer using RL (e.g. Q learning). The ANN has input neurons of higher order cumulants of a sensing channel and a single output neuron. The S/C polices are coupled during training and communication using negative or decreasing rewards based on the time the sensing policy takes to determine jammer presence and that the cognitive radio is jammed. A feedback channel provides a new communications channel to a radio transmitting to the cognitive radio.

Wind noise is detected in and removed from an acoustic signal. Features may be extracted from the acoustic signal. The extracted features may be processed to classify the signal as including wind noise or not. The wind noise may be removed before or during processing of the acoustic signal. The wind noise may be suppressed by estimating a wind noise model, deriving a modification, and applying the modification to the acoustic signal. In audio devices with multiple microphones, the channel exhibiting wind noise (i.e., acoustic signal frame associated with the wind noise) may be discarded for the frame in which wind noise is detected.

An apparatus and a method of measuring a blood pressure of an examinee while detecting the body activity of the examinee uses a pressurizing unit of a blood pressure gauge having first and second driving modes for pressurizing a cuff. A central processing unit classifies signals, which represent the movement, the position, or the direction of the blood pressure gauge detected by a sensor installed in a body of the blood pressure gauge, into a plurality of groups, and selectively performs the first driving mode or the second driving mode according to signal bands classified into the groups. The central processing unit is configured to generate blood pressure data so that the variation in the blood pressure of the examine is exactly determined according to the activity degree and the posture of the examinee.

The invention provides an online anomaly monitoring and diagnosis method and system. The method comprises the steps that the causal relation and conditional relation among all signals are defined based on a directed graph model; based on definitions of the signals by the directed graph model, the signals in acquired historical data are classified, and a training set of the historical data is established to perform model training and determine model parameters; and based on real-time data theoretical values of the signals in real-time data obtained after the real-time data acquired through online monitoring is input into a trained model, whether the signals in the real-time data are abnormal is determined. The system adopting the method and a computer readable medium storing a program executing the method are also included. Through the method, the system and the computer readable medium, a complete logic relation and casual relation are constructed for the whole process of industrial production and operation through the directed graph model, and more reasonable, more correct, more accurate and efficient production online anomaly diagnosis prediction is realized in combination with machine learning.

The present invention discloses a feature extraction and state recognition method for one-dimensional physiological signal based on depth learning. The method comprises: establishing a feature extraction and state recognition analysis model DBN of a on-dimensional physiological signal based on depth learning, wherein the DBN model adopts a "pre-training+fine-tuning" training process, and in a pre-training stage, a first RBM is trained firstly and then a well-trained node is used as an input of a second RBM, and then the second RBM is trained, and so forth; and after training of all RBMs is finished, using a BP algorithm to fin-tune a network, and finally inputting an eigenvector output by the DBN into a Softmax classifier, and determining a state of an individual that is incorporated into the one-dimensional physiological signal. The method provided by the present invention effectively solves the problem that in the conventional one-dimensional physiological signal classification process, feature inputs need to be selected manually so that classification precision is low; and through non-linear mapping of the deep confidence network, highly-separable features/feature combinations are automatically obtained for classification, and a better classification effect can be obtained by keeping optimizing the structure of the network.