34results about How to "High diagnostic efficiency" patented technology

A transformer winding fault diagnosis method based on wireless identification sensing includes the following steps: collecting transformer winding vibration signals in a normal state and when a fault occurs; denoising the transformer winding vibration signals by using singular entropy, and randomly dividing the denoised transformer winding vibration signals in the normal state into two groups, where one group is training data, and the other group is original measurement data; using the denoised transformer winding vibration signals obtained when the fault occurs as original threshold data; reconstructing the original threshold data to obtain reconstructed threshold data, and obtaining a transformer winding residual error threshold when the fault occurs; and reconstructing the original measurement data to obtain reconstructed measurement data, obtaining corresponding residual error data, and comparing the residual error data with the residual error threshold, to implement fault diagnosis on the transformer winding. The present invention implements remote, wireless, and unmanned fault diagnosis on a transformer winding. The diagnosis efficiency is high, the workload of a maintenance person is reduced, and the running efficiency of a transformer is increased.

A network diagnosis method, a cloud intelligent robot, a network device and a private network, relate to the technical field of communications, and are used for solving the technical problems of having low diagnosis efficiency and leakage risk for a private network in the prior art. The method comprises: an cloud intelligent robot transmitting a network monitoring instruction to a network device in a private network; receiving operation information transmitted by the network device according to the network monitoring instruction; diagnosing the network device according to the operation information to obtain a diagnosis result; and initiating a network configuration information update of the private network according to the diagnosis result.

The invention provides a rifampicin drug-resistant tuberculosis molecular marker, a detection reagent and an application thereof. Involved in the field of biomedical technology. The molecular markers include TRIM9, TRIM21 and TRIM56 genes and expression products thereof; the expression of the TRIM9, TRIM21 and TRIM56 genes is down-regulated in rifampicin-resistant tuberculosis patients. The invention can quickly, efficiently and sensitively identify rifampicin drug-resistant tuberculosis patients, and can be used for the screening of rifampicin drug-resistant tuberculosis.

The invention discloses a lung cancer model for the combined detection and diagnosis of peripheral blood methylation gene and IDH1. The invention provides the application of methylated SHOX2 gene, methylated PTGER4 gene and IDH1 protein as markers in the preparation of products for diagnosis or auxiliary diagnosis of lung cancer, and constructs a lung cancer model combined with three markers. Experiments have proved that compared with the single factor included, the diagnostic efficiency of the combined diagnosis model of the present invention is significantly enhanced. Therefore, the diagnostic efficiency of lung cancer can be improved by joint detection of blood markers.

The invention discloses an adaptive multi-part scanning imaging method and system based on deep learning, which is applied to multi-modal imaging equipment mainly based on nuclear medicine, and includes the following steps: Step A, aiming at multiple imaging targets Perform single-modal or multi-modal reconnaissance scanning imaging of the target site; step B, use image analysis software based on deep learning technology to analyze the reconnaissance scanning image data in step A, and combine relevant prior information to detect further Focus on the local area of ​​imaging and quantify its importance or risk; step C, based on the results of step B, select the optimized process and parameters to implement the next scan. The self-adaptive multi-part scanning imaging method proposed by the present invention maximizes the image diagnostic value contributed by the unit scanning time and / or radiation dose, realizes individual optimized precise image inspection for multi-part scanning and imaging applications such as tumors, and improves diagnostic efficiency. Has important practical value.

A method and device improve efficiency, depth and reliability of diagnosing technical condition of highly complex objects. The technical effect is achieved by signals received from a diagnosed object (DO). These signals are transformed into a technical condition initial estimate vector for the DO elements. Then, technical condition estimates for the DO elements are specified through a cyclical process and by using a reverse logical model and a direct logical model. A technical condition vector estimate is formed after the cyclical process is completed, and its variable components are used for deciding on technical condition of the diagnosed object elements. The device comprises an interface unit which inputs serve for connecting to the DO data outputs, a measuring unit, an initial estimate forming unit, a switching unit, a reverse triplex logical model and a direct triplex logical model, a result interpretation unit and a control unit.

The present invention relates to schizophrenia diagnostic products, in particular to the use of ApoF protein in the preparation or screening of schizophrenia diagnostic products, the ApoF protein can also be combined with age, gender, BMI, or with ApoA4 protein, AGT protein, AACT The combination of one or more of the proteins is used as an indicator in the preparation or screening of schizophrenia diagnostic products. The present invention discloses for the first time that ApoF protein, ApoA4 protein, AGT protein, AACT protein or their unique peptides are used as biomarkers for diagnosing schizophrenia. It provides a research basis for the preparation and screening of various diagnostic products.