10 results about "Heart sounds" patented technology

The invention discloses a heart sound signal acquisition and automatic classification method based on deep learning, and aims to solve the problems that wireless transmission time delay of heart sound signals is high, weak pathological features are difficult to extract and classification accuracy is low. The method comprises the following steps: acquiring signals of four auscultation areas by using a high-fidelity wireless digital stethoscope; high-speed and low-delay transmission of medical-level signals is realized by utilizing a star flash transmission module and combining predictive coding and Huffman coding compression mechanisms; in the preprocessing stage, self-adaptive wavelet denoising based on signal energy entropy is adopted, a multi-resolution fusion feature extraction strategy is provided, the problem of time-frequency resolution tradeoff is solved through narrow window and wide window dual-channel parallel processing, and transient positioning features and pathological frequency domain textures are captured at the same time; the classification model adopts a multi-scale parallel convolution structure and is matched with a recurrent neural network and an attention mechanism, so that the problem that transient and continuous heart sound features are difficult to consider at the same time in a single scale is solved. According to the method, the accuracy and robustness of heart sound classification are remarkably improved.

The invention discloses a preparation method of a triboelectric acoustic sensor. The preparation method comprises the following steps: washing animal leather with ethanol and deionized water respectively, and drying the animal leather; then PVDF is mixed with nanoparticles and then dissolved in an organic solvent, stirring is conducted for 4-12 h at the temperature of 40-70 DEG C till complete dissolution, and the obtained solution is subjected to electrostatic spinning to obtain a highly-polarized composite film; the dried animal leather is used as a positive friction layer of the sensor, a conductive material is used for plating a conductive layer on the surface, the obtained electrostatic spinning film is used as a negative friction layer, the friction layers are adhered through conductive glue, and the triboelectric acoustic sensor is obtained. The sensor is suitable for detecting heart sound, lung sound, intestine sound and other internal sound signals of the human body, can convert the picked weak sound signals into electric signals, and has guiding significance in early diagnosis of heart diseases, pneumonia and other diseases in the fields of biomedicine and the like.

The invention relates to the technical field of medical signal processing, and discloses an intelligent auscultation data optimization method and system based on big data, and the method comprises the steps: obtaining auscultation signal data, respectively extracting an energy feature sequence, a complexity feature sequence and a frequency feature sequence, and constructing a three-dimensional feature matrix; calculating local density distribution of each feature point in the three-dimensional feature matrix, and performing density segmentation on the three-dimensional feature matrix to form a manifold skeleton; projecting feature points in the three-dimensional feature matrix to a manifold skeleton, preliminarily separating heart sound signals and lung sound signals, and performing secondary projection on the preliminarily separated lung sound signals to obtain optimized lung sound signals; and calculating geodesic distances of adjacent sampling points on the surface of the manifold skeleton based on the preliminarily separated heart sound signals, identifying a signal damage area, calculating a shortest geodesic path, and mapping the shortest geodesic path back to a time domain for restoration to obtain optimized heart sound signals. And the physiological authenticity and the use benefit of auscultation data are effectively improved.

An example system includes an implantable medical device includes a heart sound sensor configured to sense heart sound signals; and an optical sensor configured to sense optical signals; and processing circuitry configured to: determine blood pressure values of a patient based on the optical signals; determine heart sound data using the heart sound signals; determine whether the heart sound data satisfies a heart sound blood pressure sampling threshold; in response to a determination that the heart sound data satisfies the heart sound blood pressure sampling threshold, adjust a rate of sensing optical signals via the optical sensor for determination of blood pressure values; and control determination of a blood pressure value of the patient via the optical sensor based on the adjusted rate of sensing optical signals.

Provided are an information processing method and the like capable of supporting determination of a state of a heart on the basis of feature amounts calculated from an electrocardiogram, a heart sound waveform, or a pulse wave waveform. According to the present invention, a computer acquires an electrocardiogram, a heart sound waveform, and a pulse waveform of a patient. The computer acquires: a first feature amount by a first formula using a I sound position or a II sound position obtained from the heart sound waveform, a Q wave position obtained from the electrocardiogram, and a notch position and a pulse wave rising position obtained from the pulse wave waveform; a second feature amount by a second formula using a maximum amplitude of the I sound or an area obtained by time-integrating a waveform of the I sound, or the maximum amplitude of the II sound or the area obtained by time-integrating a waveform of the II sound; and a third feature amount by a third expression using an element feature amount obtained by using the pulse wave waveform. In a case in which the first feature amount to the third feature amount are input, the computer inputs the first feature amount to the third feature amount thus acquired to a trained model trained so as to output an estimated value of an intracardiac pressure of the patient, thereby acquiring the estimated value of the intracardiac pressure of the patient.

The invention provides a lung sound signal acquisition method, electronic equipment and a storage medium, and relates to the technical field of signal processing.The method comprises the steps that when an electronic stethoscope is used for acquiring a heart and lung mixed sound signal, a pulse signal acquisition device is used for acquiring a pulse signal so as to acquire the heart and lung mixed sound signal and the pulse signal; inputting the pulse signal into a target electrocardiosignal prediction model to obtain an electrocardiosignal output by the target electrocardiosignal prediction model; performing time sequence alignment on the heart and lung mixed sound signal, the pulse signal and the electrocardiosignal; inputting the cardiopulmonary mixed sound signal, the pulse signal and the electrocardiosignal after time sequence alignment into a target lung sound signal prediction model to obtain a lung sound signal output by the target lung sound signal prediction model; according to the method, a plurality of complete heartbeat cycles do not need to be collected in advance, a heart sound template does not need to be created, low-delay real-time processing is supported, scenes such as arrhythmia can be effectively handled, and the quality of the obtained lung sound signals is remarkably improved.

The invention provides an intracardiac sound signal identification and classification method based on a deep learning architecture, and the method comprises the steps: obtaining an original intracardiac sound signal, and carrying out the filtering and noise reduction of the signal; performing short-time Fourier transform on single heartbeat signal data, and converting the single heartbeat signal data into a spectrogram of heartbeat signals; constructing a cyclic convolution residual network model, inputting the training set into the model for training, performing short-time Fourier transform on heartbeat signals in a test set needing to be identified, and generating a spectrogram required by the network model; the spectrogram of the heartbeat signals is input into the trained cyclic convolution residual network model, the model analyzes the spectrogram, and an atrial fibrillation or ventricular fibrillation recognition result is output; and executing the step on all data in the test set to obtain an atrial fibrillation or ventricular fibrillation identification result of each heartbeat signal.

1. Name of the product in this design: Heartbeat Signal Acquisition Instrument. 2. Purpose of this design: For collecting heart sound wave signals. 3. The key design feature of this product is its shape. 4. The image or photograph that best illustrates the design's key points: a 3D model.

Embodiments herein are directed to a vehicle seat that has a rear surface and an occupant contact surface spaced apart from the rear surface to define a cavity therebetween is provided. The vehicle seat includes a sensor positioned within the cavity, at least one fluid medium positioned within the cavity and extending to the occupant contact surface, and at least one deflector member positioned within the cavity. The at least one deflector member is shaped and sized to at least partially surround the at least one fluid medium such that the at least one deflector member is configured to constrain and direct a plurality of heart sound waves through the at least one fluid medium to the sensor when an occupant is in contact with the occupant contact surface.

The invention relates to the technical field of medical data processing, and discloses a heart sound detection model construction method and system, and the method comprises the steps: obtaining heart sound signal data of a target old group, and carrying out the preprocessing; respectively inputting the processed one-dimensional heart sound signal and a Mel time-frequency spectrogram obtained by converting the processed one-dimensional heart sound signal into a time domain feature analysis branch and a time frequency feature analysis branch in a double-branch neural network for feature extraction; and fusing the extracted two paths of high-dimensional features by using a bidirectional long-short-term memory network based on an attention mechanism, and training to obtain a heart sound detection model. The time domain and frequency domain features of the heart sound signals are fully mined through the double-branch structure, the focusing capacity of the model for key information is enhanced in combination with an attention mechanism, the heart sound classification accuracy and the model interpretability are improved, meanwhile, low calculation complexity is kept, deployment in embedded equipment is facilitated, and the method is suitable for popularization and application. Effective technical support is provided for early screening and remote auxiliary diagnosis of cardiopulmonary diseases.