48 results about "Respiratory sounds" patented technology

The invention discloses a child mouth breathing monitoring method, device and equipment and a medium, and the method comprises the steps that a non-contact sensor group is used for synchronously collecting multi-mode physiological data of a target child in the sleep period, and the multi-mode physiological data at least comprises a face thermal imaging video stream, a thoracic and abdominal micro-motion signal and an environment audio signal; the multi-modal physiological data is processed, multi-modal features related to respiration are extracted respectively, and the multi-modal features comprise thermodynamic change features of mouth and nose areas extracted based on a face thermal imaging video stream, respiratory effort waveforms extracted based on thoracic and abdominal micro-motion signals, and the respiratory effort waveforms extracted based on the thoracic and abdominal micro-motion signals; extracting a sound source spatial position and a spectrum feature of breathing sound based on the environment audio signal; inputting the multi-modal features into a pre-trained mouth breathing recognition model, and outputting a judgment result of the functional mouth breathing event of the target child within a specific time period; and generating a mouth breathing monitoring report of the target child based on the judgment result.

The invention particularly relates to a respiratory disease diagnosis device and method, and the device comprises a respiratory sound signal collection unit which is used for obtaining a current respiratory sound signal; the breathing sound signal preprocessing unit is used for performing segmentation processing and denoising processing on the current breathing sound signal to obtain a preprocessed breathing sound signal; the feature extraction unit is used for extracting multi-modal features of the preprocessed breath sound signals; and the detection unit is used for inputting the multi-modal features into a preset deep learning network model to obtain a respiratory system disease detection result. Therefore, through multi-modal feature extraction, dynamic fusion and an efficient classification strategy, the problems of relatively low feature identification degree, relatively low disease classification accuracy and the like in the process of researching disease diagnosis based on the breath sound signals in related technologies are solved, and the detection performance of chronic respiratory system diseases based on the breath sound signals is remarkably improved.

The invention discloses a throat mucosa intelligent state evaluation and inflammation early warning management system and method. The method comprises the following steps: synchronously acquiring a throat mucosa image, breath sound / cough sound / sounding signals, airflow data and body temperature or environment relative humidity data, evaluating image definition, shielding degree and coverage rate, and outputting acquisition guide superposition information and triggering re-acquisition when the image does not reach the standard; reliability is calculated for the multi-modal features, weight fusion output state vectors and confidence coefficients are determined in combination with quality gating, and cross-modal consistency verification is executed to trigger re-sampling or strategy adjustment; generating a risk index based on the change of the sliding time window, and outputting an early warning level by adopting hysteretic classification; and writing the threshold, the weight and the sampling and guiding strategy into a parameter library and a fusion model configuration area to form a closed loop. According to the system, improper electroencephalogram fusion and multi-terminal collaborative optimization can be selected, and daily scene evaluation stability and early warning reliability are improved.

The invention discloses an intelligent nasopharyngeal catheter and a breath sound monitoring system.The intelligent nasopharyngeal catheter comprises a nasopharyngeal catheter body, a first acoustic sensing part and an optical fiber, the nasopharyngeal catheter body comprises a first body and a second body, and the first body is connected with the second body; the cross sectional area of the second body is gradually increased from one end, close to the first body, of the second body to one end far away from the first body; at least part of the optical fiber is embedded in the first body, the first acoustic sensing part is arranged on the optical fiber and located in the first body, the first acoustic sensing part is used for converting vibration and / or pressure fluctuation of breathing sound waves of a patient into optical signals, and the optical fiber is used for being connected with a demodulation host so that the demodulation host can receive the optical signals from the first acoustic sensing part. Therefore, the breathing signal can be collected through the first acoustic sensing part, and the breathing signal of the patient can be transmitted to the demodulation host, so that the breathing condition of the patient can be monitored in real time to guarantee the safety of the patient.

The present application relates to the technical field of health monitoring, in particular to a kind of infant asphyxia risk autonomous monitoring method and system based on laryngeal respiratory sound, comprising: utilize high sensitivity MEMS microphone to collect the airflow and respiratory sound signal of infant larynx, and utilize micro accelerometer to monitor the thoracic movement data of infant synchronously;The airflow and respiratory sound signal are denoising, and the denoising respiratory sound signal is obtained;The denoising respiratory sound signal is separated according to respiratory event Signal, and is enhanced and combined into respiratory sound data set;Respiratory sound feature is extracted in respiratory sound data set, and asphyxia anomaly classification model is constructed based on respiratory sound feature by machine learning model, and dynamic baseline model that adapts individual respiratory difference is established according to respiratory sound feature.The present application utilizes the hardware device of high sensitivity MEMS microphone and micro accelerometer and artificial intelligence model to combine, realizes the use of laryngeal respiratory sound signal in home environment and autonomously completes infant asphyxia risk identification and early warning.

The invention relates to the field of breath sound monitoring, and discloses a tracheal intubation device and a breath sound monitoring system.The tracheal intubation device comprises a tracheal catheter used for being inserted into an airway of a patient; the first sound detection piece is an optical fiber sound sensor, the first sound detection piece is installed on the tracheal catheter, the first sound detection piece is used for detecting breathing sound wave information in the airway of a patient, and the first sound detection piece is used for being in communication connection with the monitoring host so as to transmit the detected breathing sound wave information to the monitoring host. Therefore, the first sound detection piece is installed on the tracheal catheter, the first sound detection piece can be directly located in the internal environment of the airway of the patient, the accuracy of monitoring breathing sound and sound wave information of the patient through the tracheal intubation device can be improved, and the first sound detection piece transmits the breathing sound and sound wave information to the monitoring host in real time; the medical staff can monitor the breathing condition of the patient in real time through the monitoring host, find out abnormal breathing of the patient in time and carry out treatment.

The invention discloses an intelligent ward risk assessment method and system, a product and a medium. The method comprises the following steps: synchronously monitoring breathing audio and mattress pressure signals of a patient, and identifying discrete action events with remarkable amplitude and duration from pressure data; further judging whether the breathing of the patient is abnormal or not before and after the action events occur, for example, the breathing rhythm is interrupted for a long time or the breathing cycle obviously deviates from a baseline; when the two conditions of the violent action and the abnormal breathing cooperatively occur, an effective cooperative event record is confirmed; according to the amplitude and the duration of the action in the event and the severity of the abnormal breathing, weighted summation is carried out through a preset risk weight, and a single event risk score is calculated; and accumulating all event risk scores in an evaluation period to obtain a comprehensive risk score, comparing the comprehensive risk score with a risk threshold, and outputting a risk level. By implementing the technical scheme provided by the invention, the accuracy of clinical compound action risk early warning of the patient is improved.

The invention relates to the technical field of health monitoring, in particular to an infant suffocation risk autonomous monitoring method and system based on laryngeal breathing sound, and the method comprises the steps: collecting airflow and breathing sound signals of the throat of an infant through a high-sensitivity MEMS microphone, and synchronously monitoring thoracic motion data of the infant through a miniature accelerometer; performing noise reduction processing on the airflow and the breathing sound signal to obtain a denoised breathing sound signal; performing signal separation on the denoised breathing sound signals according to a breathing event, and enhancing and combining the denoised breathing sound signals into a breathing sound data set; extracting breath sound features from the breath sound data set, constructing a suffocation anomaly classification model based on the breath sound features through a machine learning model, and establishing a dynamic baseline model adapted to individual breath differences according to the breath sound features; hardware devices of a high-sensitivity MEMS microphone and a micro accelerometer are combined with an artificial intelligence model, and infant asphyxia risk identification and early warning are autonomously completed in a home environment by using laryngeal respiration sound signals.

The present invention relates to an operating method of a lung monitoring system operated by at least one processor, the operating method comprising the steps of: acquiring a plurality of electrical impedance tomography (EIT) images of the chest of a patient and a plurality of respiratory sound intensity images generated on the basis of respiratory sound signals acquired from the chest of the patient; mapping, on the basis of a plurality of pieces of respiratory interval information acquired by binning a respiratory signal of the patient, an EIT image and a respiratory sound intensity image corresponding to each respiratory interval to each other; and inputting, into a respiratory anomaly prediction model, at least one pair of the EIT image and the respiratory sound intensity image included in each respiratory interval, to acquire a prediction result for respiratory anomalies of the patient.

The application discloses an obstructive sleep apnea device and method; the device comprises a mouthpiece carrier, an electrode stimulation module and a control unit, the electrode stimulation module comprises an integrated flexible circuit board transmission link, the transmission link is integrated with a stimulation electrode with a nickel-titanium alloy support strip on the inner side of the mouthpiece carrier, and the stimulation electrode can apply electric stimulation to the genioglossus muscle or hypoglossal nerve; the external control unit is provided with a microcontroller and an acoustic sensor; the method first collects an environmental background signal, processes the signal to generate a signal determination threshold, then collects a human respiratory acoustic vibration signal in real time, processes the signal to generate a respiratory sound energy value, compares the two to determine an abnormal respiratory event; after determining the abnormality, a gradient output electric stimulation is output, and a dynamic feedback mechanism is combined to adjust the stimulation intensity; when the stimulation intensity is zero and there is no abnormal signal, it is determined that the intervention is completed and the standby state is entered; the application can adapt to environmental noise, avoid current mutation discomfort, closed-loop control intervention intensity, and is suitable for sleep apnea auxiliary intervention.

An artificial intelligence-based system and method for scalable screening of individuals for respiratory infection, such as COVID-19. The system is trained to distinguish distinct latent features of cough sounds produced by a COVID-19 infected person from cough sounds produced by patients suffering from any other respiratory infection or involuntary cough sounds produced by a healthy person. Cough sound samples from individuals can be remotely collected and evaluated by the system for likelihood of the COVID-19 infection. Additionally, images of affected body parts, biomarkers, metadata, and other respiratory sound samples can also be used for screening.

The invention belongs to the field of artificial intelligence and non-contact measurement, and relates to a lung ventilation function measurement method and device based on a smartphone microphone. A built-in microphone of the smart phone is used for collecting breathing audio signals of a user in the measurement process, and a lung ventilation function true value is obtained through the lung function instrument to serve as reference data; dividing an inspiration phase and an expiration phase of the breathing audio signal based on a threshold method, and extracting an expiration phase audio clip; processing the expiration signal by using a self-adaptive convolution frequency domain enhancement network, dynamically adjusting a convolution kernel to adapt to different frequency bands by self-adaptive convolution, and enhancing low-frequency components by combining frequency domain enhancement with fast Fourier transform; the transformation type convolutional network models time sequence dependence through causal convolution and jump convolution, and the feature learning ability is enhanced through residual connection and dense connection; and finally predicting lung ventilation function parameters through full connection layer regression. According to the invention, the accuracy of lung ventilation function measurement based on the microphone of the smart phone is improved, and the user can conveniently carry out self-health monitoring.

The invention discloses an anesthesia period respiration monitoring method, device, system and equipment and a storage medium, and relates to the technical field of medical monitoring. The method is executed by signal processing equipment which is respectively in communication connection with a sound acquisition unit and a display, and specifically comprises the following steps: firstly, carrying out real-time denoising processing and preprocessing on an audio signal acquired by the sound acquisition unit in real time to obtain current frame audio data; and inputting the current frame of audio data into a breathing sound type identification model which is based on a deep learning algorithm and has completed pre-training, outputting to obtain a current breathing sound type identification result, and finally transmitting the current breathing sound type identification result to a display in real time for output and display. Therefore, the identified breathing sound type can be used as an index for reflecting whether the lung function state is normal or not and is output and displayed in real time, an anesthetist can know the lung function state of a patient in the operation anesthesia period at any time without using a stethoscope, the abnormal condition is responded in time, and the energy of the anesthetist is saved.

The invention provides a wearable wireless stethoscope early warning device for monitoring acute attack of an asthma patient, the wearable wireless stethoscope early warning device comprises a vest, a first binding belt and a second binding belt, the first binding belt and the second binding belt are arranged on two sides of the vest, two adjusting belts are arranged above the vest, and the two adjusting belts are connected with the vest; a miniature sound signal sensor, a miniature lung sound discriminator and a signal microprocessor are arranged in the vest, the miniature sound signal sensor is used for collecting breathing sound signals, and the miniature lung sound discriminator is used for recognizing dry rale, wet rale and normal breathing sound. The breathing sound of an asthma patient, especially a child patient, is monitored in real time, abnormal breathing sound characteristics are accurately recognized, timely early warning of acute attack is achieved, by means of wireless transmission and a remote diagnosis technology, a doctor can remotely obtain illness state information of the patient, timely diagnosis and treatment guidance is provided for the patient, and the patient experience is improved. The risk caused by acute attack of asthma is reduced, and the health management level of patients is improved.

The invention discloses a children pneumonia screening method and system based on multi-modal deep learning, and is applied to the technical field of artificial intelligence assisted medical diagnosis. Comprising the following steps: acquiring respiration audio data and structured clinical medical history data of a to-be-screened child; converting the respiratory audio data into a time-frequency graph, and inputting the time-frequency graph into a pre-trained feature extractor to extract a high-dimensional acoustic feature vector; screening key clinical indexes in the structured clinical medical history data based on a feature selection algorithm, and inputting the key clinical indexes into a pre-trained multi-layer perceptron model to obtain clinical feature vectors; and carrying out weighted splicing on the high-dimensional acoustic feature vector and the clinical feature vector, and inputting the spliced high-dimensional acoustic feature vector and the clinical feature vector into a classification multilayer perceptron model to obtain the pneumonia prediction probability of the to-be-screened child. According to the method, the problem of data scarcity is solved through a two-stage transfer learning strategy, and the accuracy, specificity and generalization ability of children pneumonia screening in different clinical environments are remarkably improved by simulating the comprehensive diagnosis and treatment thinking of clinicians.

The application provides a medical and home non-invasive ventilator based on multi-channel regulation and a control method thereof, and belongs to the technical field of clinical medical instruments. The ventilator comprises a mask breathing sound collecting device for collecting mask breathing sound signals of a user, a chest wall breathing sound collecting device for collecting chest wall breathing sound signals of the user, a pneumatic measuring device for collecting pressure and flow signals of the ventilator, an acoustic signal processor connected with the mask breathing sound collecting device, the chest wall breathing sound sensor device and the pneumatic measuring module device, for quantifying the filtered mask breathing sound signals, the chest wall breathing sound signals, the pressure and flow signals, and generating a confidence degree, and a fusion controller for adjusting the operation mode of the ventilator according to the confidence degree. The medical and home non-invasive ventilator based on multi-channel regulation and the control method thereof can obtain more stable phase determination and more timely automatic titration control under complex working conditions.

The invention relates to the technical field of pathological characteristic sound detection, and provides a Velcro rale detection method and system based on respiratory auscultation sound, and the method comprises the steps: firstly determining the collection position of lung sound, obtaining the lung sound data of a subject, carrying out the preprocessing, carrying out the initial feature extraction of a preprocessed respiratory sound data set, and obtaining a frequency spectrum representation; then, a pre-trained double-flow multi-view Velcro rale detection model is used for processing: the Velcro rale characteristic acoustic biomarker features represented by the frequency spectrum are enhanced, feature fusion is performed on the enhanced frequency spectrum representation, and multi-view fusion advanced feature representation is obtained; time domain feature representation is extracted from the preprocessed breath sound data set; and finally, integrating the multi-view fusion advanced feature representation and the time domain feature representation to form multi-dimensional time-frequency joint representation, and outputting a detection result. According to the method, the time-frequency distribution mode of the Velcro rale is fully considered, the Velcro rale is accurately and reliably detected, and a non-invasive, economical and efficient means is provided for early screening of IPF.

The invention discloses a breath sound classification method and device, a storage medium and a computer program product, and relates to the technical field of acoustic signal processing. The breath sound classification method is applied to the head-mounted equipment, and comprises the following steps: acquiring a bone conduction audio stream collected by a bone conduction sensor in the head-mounted equipment, and extracting frequency domain features of the bone conduction audio stream; a breathing sound classification model obtained through pre-training is adopted to process the frequency domain features, a breathing sound classification result is obtained, the breathing sound classification result is at least used for representing whether the bone conduction audio stream contains breathing sound or not, and the breathing sound classification model comprises a backbone network and a classifier; the backbone network comprises at least two layers of time sequence convolutional network structures which are connected in sequence, and each layer of time sequence convolutional network structure comprises a time sequence one-dimensional convolutional network module and a time sequence two-dimensional convolutional network module which are connected in sequence. According to the method, a set of complete bone conduction breath sound analysis process is realized, and the breath sound classification accuracy in a complex environment is improved.

This invention discloses a respiratory monitoring device and its working method, relating to the field of pulmonary function monitoring technology. The respiratory monitoring device includes a flexible chest strap and a flexible shoulder strap. One end of the flexible shoulder strap is sewn to the flexible chest strap. A chest rise and fall acquisition mechanism is installed on one side of the front end of the flexible chest strap, and a lung sound acquisition mechanism is installed on the other side of the front end of the flexible chest strap. A control box is installed on the outer wall of the flexible shoulder strap, and a wire is installed at the upper end of the control box. A respiratory sound acquisition mechanism is installed at one end of the wire. This solution solves the problems of existing pulmonary function monitoring devices being unable to perform real-time monitoring, only being able to monitor pulmonary function through inhaled and exhaled gases, having a single measurement parameter, and low accuracy.

The invention relates to a multi-modal fusion decision-making remote medical guidance first-aid transfer method and device. The method comprises the following steps: acquiring a real-time data stream including heart rate, oxyhemoglobin saturation, body temperature, respiratory rate, blood pressure, posture, limb activity and gait through wearable equipment of a patient terminal; acquiring an on-site video stream through a camera carried on a first-aid personnel terminal; acquiring moan sound, breathing sound, environmental noise and voice information of a patient or an accompanying person through a microphone; inputting the on-site video stream, the voice information and the real-time data stream into a trained multi-mode emotion recognition neural network for real-time analysis, and reasoning a preliminary analysis result, a potential risk and a first-aid transfer scheme of the patient; the first-aid transfer scheme comprises on-site emergency treatment measures, transfer postures, transfer routes and calling of specific medical staff. According to the invention, the traffic risk and the disease deterioration probability of the patient are comprehensively considered, and the efficiency and safety of first-aid transfer are improved.

The present application relates to the field of old-age service management, and particularly relates to a smart old-age service management system based on the Internet of Things, which is provided with an observation and collection module, which comprises an image collection unit for collecting infrared images of a monitoring target and an audio collection unit for collecting respiratory sound volumes of the monitoring target; a behavior analysis module, which is used to identify respiratory behavior characteristics based on the infrared images of the monitoring target every monitoring period, analyze respiratory state abnormality characteristic values for the monitoring target based on the respiratory behavior characteristics, and divide respiratory state abnormality tendency categories of the monitoring target; and a behavior analysis module, which is used to adaptively analyze the monitoring target according to the respiratory state abnormality tendency categories. The present application analyzes the characteristic state presented by the monitoring target during night sleep, discovers the sleep abnormality of the monitoring target in time, issues a warning prompt information so as to enable a caretaker to check in time, ensures the sleep health of the monitoring target, and reduces the risk of occurrence of other health problems.

The invention discloses an oropharynx ventilation device and a breath sound monitoring system, and relates to the technical field of medical instruments.The oropharynx ventilation device comprises a ventilation catheter, the ventilation catheter is made of a shape memory alloy skeleton and an elastic layer, the shape memory alloy skeleton is coated with the elastic layer, and a ventilation flow channel is formed in the ventilation catheter; the sound sensor is fixed to the ventilation catheter and used for being in communication connection with the monitoring host so as to transmit detected breathing sound information to the monitoring host. The sound sensor is fixed to the ventilation catheter, the sound sensor is used for detecting breathing sound information of a patient in real time, the sound sensor is used for being in communication connection with the monitoring host so as to transmit the detected breathing sound information to the monitoring host, the pharyngeal cavity breathing sound can be continuously collected in real time, and a blocked or abnormal breathing mode can be rapidly recognized in the early stage; in addition, the sound sensor is small in size and free of electromagnetic interference, the requirement of a disposable passive instrument is met, and the respiratory tract safety can be effectively improved.

The application relates to the technical field of atomizer control, and discloses a child intelligent atomizer capable of quantitatively guiding a breathing mode and a control system, which comprises a user analysis unit used for receiving real-time breathing frequency and body temperature data of a user through a mobile terminal, comparing and analyzing the collected real-time breathing frequency and body temperature data of the user with a standard database, identifying the use condition of the user, and generating a control instruction; the application increases the interactive feeling through voice guidance, pacifies the emotion, guides the breathing, and makes the small children naturally calm down through music; the light prompts abnormal conditions, sets up the atmosphere, effectively reduces the fear of the children for treatment, compared with common atomizers, the application can prompt correct breathing modes, the medicine deposition effect is better, in addition, the music is self-defined, the childlike and lovely appearance is matched, the atomizer is more like a music toy, the attention of the children can be transferred from the discomfort of treatment, and the cooperation degree is improved.

The embodiment of the application discloses a kind of master identification method and terminal equipment, it is applicable to computer technology field, the method comprises: terminal equipment responds to the unlocking operation of target content to the user data of the user to be measured of the user to be measured, wherein, target content is in the state of being locked, user data includes at least one of the following: the face image of the user to be measured, the respiratory audio data of the user to be measured, the IMU data of the user to be measured and the touch screen data of the user to be measured;According to user data and pre-recorded master template, master identification is carried out, master template includes at least one of the following: face template, respiratory sound feature template, cross-modal feature template, cross-modal feature template is used to describe the comprehensive characteristics of master in multiple modes;In the case where master is identified, target content is unlocked.The embodiment of the application can be used in the process of terminal equipment, and master identification is carried out based on respiratory sound feature, to protect the safety of master private information.

This invention provides a controllable generative enhancement method for respiratory sound categories based on discrete tokens and Transformer, belonging to the interdisciplinary field of medical signal processing and artificial intelligence. The method employs a two-stage framework: In the first stage, a conditional vector quantization autoencoder is trained, injecting pathological category labels during encoding and introducing multi-scale category prototypes based on statistical analysis of similar samples during decoding and reconstruction, thereby constructing a discrete latent space with explicit semantic structure. In the second stage, an autoregressive Transformer model is trained to learn the category conditional distribution of token sequences within this space. In the enhancement stage, for the target minority categories, the Transformer generates new token sequences, which are then fused with the corresponding category's multi-scale prototypes and broadcast decoded to reconstruct high-fidelity, pathologically semantically consistent synthetic respiratory sound samples. Finally, the synthetic samples are added to the training set to balance the data distribution, effectively improving the downstream respiratory sound classification model, especially its performance and overall robustness in identifying a minority of abnormal categories.

The application provides an in-vivo respiratory sound monitoring method and system, which is suitable for the technical field of medical treatment, and the method is as follows: starting an auxiliary light source and a measuring light source to output first reference light, second reference light and combined light; reflecting the combined light through a respiratory sound collection optical fiber to obtain first reflected light; the respiratory sound collection optical fiber is integrated on a respiratory catheter, and the respiratory sound collection optical fiber is placed into the airway of a patient synchronously with the catheter to construct an in-situ monitoring link of the airway source; and respiratory sound monitoring results are obtained by using the first reference light, the second reference light and the first reflected light, so that the real-time, high-fidelity and low-interference continuous collection of in-vivo respiratory sound signals is realized.

The invention discloses a passive respiratory disease early warning device based on respiratory audio spectrum feature separation and a bidirectional long short-term memory network, which is characterized in that signal preprocessing is triggered when a posture is static by continuously collecting respiratory sound and synchronizing body position and motion state data; cardiopulmonary sounds are separated in real time by adopting an online non-negative matrix factorization technology, pure respiratory signals are extracted, and a dynamic signal environment is adapted through an incremental updating mechanism; key frequency band features are extracted in combination with wavelet transform time-frequency analysis, and breathing micro-variation features such as expiratory phase extension and wet rale are quantized by using a dynamic time bending algorithm; a two-way LSTM fused with an external attention mechanism is introduced to model breathing time sequence characteristics, key frequency domain information is focused, abnormal probabilities of pneumonia, asthma and chronic obstructive pulmonary disease are output, and when a preset early warning condition is met, a prompt is triggered; respiration feature extraction and desensitization are completed through local edge calculation, and only abnormal fragment ciphertexts are uploaded to guarantee data privacy. The method solves the problems that in the prior art, breathing sound separation precision is insufficient, single-mode analysis is limited, time sequence modeling adaptability is poor and the like, and zero-intervention and high-precision early passive monitoring of respiratory system diseases is achieved.

The invention discloses a breath sound classification detection method based on an improved convolutional neural network, and the method comprises the steps: firstly carrying out the preprocessing and feature extraction of a breath sound signal collected in real time, and constructing a breath sound cepstrum feature matrix; and then the breath sound features are input into an improved convolutional neural network comprising a convolution module, a channel attention mechanism module and a lightweight feature extraction module for training and classification, and accurate recognition of breath sound categories is realized. The method realizes real-time, efficient and high-precision classification detection of breath sound, has the advantages of low calculation complexity, strong real-time performance and high identification accuracy, and is suitable for the field of biomedical signal processing.

This invention discloses a non-invasive rapid detection and diagnosis system for upper airway function, belonging to the field of upper airway function detection and medical diagnostic technology. It is applicable to upper airway function assessment in patients with mandibular retrusion and non-invasive diagnosis of adenoid hypertrophy in children. The system consists of a three-tiered architecture comprising a multimodal oral-nasal co-measurement instrument, a data acquisition and transmission module, and an intelligent diagnostic module. It integrates multiple types of sensors to simultaneously collect multimodal signals such as oral and nasal airflow, lip status, and neck airway breath sounds. After standardized processing, it achieves accurate grading and diagnosis of upper airway function and adenoid hypertrophy through hierarchical logic including three-dimensional feature extraction, respiratory pattern discrimination, core + auxiliary indicator grading diagnosis, and machine learning model verification. It is also equipped with multiple supporting functional modules and features non-invasiveness, dynamic operation, portability, and high diagnostic accuracy, filling a gap in related technologies.

The invention discloses a multi-sign fusion lung respiration monitoring system and method based on an LSTM neural network, and the system achieves the dynamic monitoring of multi-sign parameter cooperation through collecting the physiological parameters and lung respiration sound signals of a user. Meanwhile, based on the collected multi-modal sign data, multi-modal characteristic data is generated in combination with physiological index standard data, and then the lung respiration health probability of the user is generated by means of an LSTM model; therefore, an effective data processing means is provided for the monitored multiple physical sign parameters; finally, the probability threshold value of the user in the current monitoring period is determined by using historical probability threshold value data of the user; on the basis, respective probability thresholds can be generated for different users, so that the self-adaptive change of the alarm threshold based on the patient is realized; and finally, the probability threshold value and the lung respiration health probability are sent to a medical care terminal, so that an accurate auxiliary basis can be provided for medical staff.