38results about How to "Improve diagnostic sensitivity" patented technology

The invention discloses a turbine generator rotor interturn short-circuit fault diagnosis method based on the end distortion effect. The method includes the steps of firstly, installing a magnetic field detection coil on an end distortion magnetic flux path of a turbine generator; secondly, online collecting voltage signals sensed by the magnetic field detecting coil through a data collecting instrument, conducting fast fourier transformation on the signals, and obtaining a spectrogram of the signals; thirdly, diagnosing whether the interturn short-circuit fault exists in rotor windings of the turbine generator or not according to the amplitude changing situation of all spectrum components of the signals. The interturn short-circuit fault in the rotor windings of the turbine generator is diagnosed according to the amplitude changing situation of some characteristic frequency components in the voltage signals sensed by the magnetic field detecting coil, and the turbine generator rotor interturn short-circuit fault diagnosis method has the advantages that diagnosing flexibility is high and sensors are convenient to install, is universally suitable for various types of turbine generators in an electric system, and has wide application prospects.

The application relates to the field of biological detection, and specifically discloses a sealing agent for biological detection, a preparation method thereof, a coated plate and a kit using the coated plate. Each liter of sealing agent is made of the following raw materials: 2.5-9g of water-soluble alcoholic organic matter, 0-1.1g of polyglucosamine, 0-0.7g of gelatin, 0.1-0.4g of antioxidant, 0.07-0.2g of preservative, and the balance It is water; the water-soluble alcoholic organic matter is selected from at least two of ethylene glycol, polyvinyl alcohol and polyethylene glycol. The preparation method of the sealing agent comprises the following steps: uniformly mixing water-soluble alcoholic organic matter, polyglucosamine, gelatin, antioxidant, preservative and water according to the formula quantity. The coated plate is prepared after being sealed with the above sealing agent, and the kit includes the above prepared coated plate. The use of the blocking agent of the present application can effectively reduce the non-specific reaction in the detection process, with few false positive results and high diagnostic specificity.

An automatic identification system for acute myocardial infarction positioning based on CNN neural network, which relates to the technical field of myocardial infarction positioning and identification, including a data acquisition system, a cloud platform data storage system, a positioning identification analysis system and a data display system; a wearable ECG monitor and a The person to be judged connects, records and generates a 12-lead original ECG; the ECG acquisition system obtains the 12-lead original ECG data, including the amplitude of the P wave, the amplitude of the QRS complex, the amplitude of the ST segment and the amplitude of the T wave; positioning discriminant analysis The system uses the positioning discrimination model based on the training of the CNN neural network to perform convolution calculation to obtain the discriminant intermediate data, and the discriminant intermediate data is mapped by the sigmoid function to obtain the discrimination result data, so as to make the location discrimination of the acute myocardial infarction occurrence site of the person to be discriminated; this application Provided is an automatic judging system for locating acute myocardial infarction based on CNN neural network, which can accurately judge whether the person to be judged is the site of acute myocardial infarction.

The invention discloses an automatic acute myocardial infarction fixed period discrimination system based on a CNN, and relates to the technical field of myocardial infarction fixed period discrimination. The automatic acute myocardial infarction fixed period discrimination system comprises a data acquisition system, a cloud platform data storage system, a fixed period discrimination and analysissystem and a data display system. A wearable ECG monitor is connected with a person to be discriminated, and records and generates 12-lead original electrocardiograms; an electrocardiogram acquisitionsystem acquires data of the 12-lead original electrocardiograms such as P wave amplitudes, QRS wave group amplitudes, ST segment wave amplitudes and T wave amplitudes; and the fixed period discrimination and analysis system uses a fixed period discrimination model obtained by training based on the CNN neural network to carry out convolution calculation to obtain discrimination intermediate data,and then obtains discrimination result data through sigmoid function mapping, so that fixed period discrimination of an occurrence period of acute myocardial infarction of the person to be discriminated is performed. The automatic acute myocardial infarction fixed period discrimination system based on the CNN neural network can accurately discriminate whether a person to be discriminated is in theacute myocardial infarction occurrence period or not.

The invention discloses a quantitative analysis method of substantia nigra hyperecho intensity by transcranial ultrasound, which comprises the following steps: 1) obtaining the original TCS picture of the patient and the corresponding labeled picture after interpretation by the clinician, and randomly dividing them into a training set and a training set. Test set; 2) Deeply learn the adversarial network on the training set and perform network training to establish a model for analyzing substantia nigra echo images; 3) use the test set to verify the model for analyzing substantia nigra echo images; The predicted image is first converted into a grayscale image, and then converted into a binary image; 5) Morphological analysis of the grayscale value is performed to extract the images of the left and right substantia nigra hyperechoic areas in the midbrain; 6) Extract feature parameters; 7) Calculate Obtain the substantia nigra hyperechoic total intensity value. The quantitative analysis method of substantia nigra hyperecho intensity of the transcranial ultrasound of the present invention can realize quantitative interpretation and analysis of substantia nigra hyperecho, makes the change of substantia nigra echo more intuitive, and assists clinicians to improve the ability of identifying and diagnosing PD.