182 results about "Disease characteristic" patented technology

A method and a system for recognizing plant diseases and a recording medium are provided. The method includes: providing a plant disease database, for storing plant disease and disease characteristic image corresponding to the plant disease; after obtaining plant image by an image capture device, obtaining segmented plant image by an image processing unit according to a first processing technique, and obtaining suspected region image according to a second processing technique; calculating an area of the suspected region image, and when the area is greater than a preset area, using the suspected region image as syndrome image, and comparing the syndrome image with the disease characteristic image; and when the syndrome image matches any specific disease characteristic image, obtaining a corresponding specific plant disease.

The invention discloses a panoramic image CNN based tunnel disease automatic identification device. According to the device, firstly, a panoramic image of a tunnel inner wall is quickly acquired with a panoramic vision sensor; then the panoramic image is processed mainly by panorama unrolling, image preprocessing, binarization processing and the like to extract suspected disease region; and finally, the disease is subjected to automatic detection and classification identification by adopting a convolutional neural network. According to the scheme, the structure of the detection device in extracting a tunnel inner wall panoramic image is greatly simplified, and various tunnel disease characteristics can be automatically extracted, detected and identified by the end-to-end convolutional neural network, and an effective technical support is provided to tunnel maintenance and completion acceptance.

The present invention discloses an integrated similarity measurement and bi-directional random walk based pharmaceutical relocation method. When calculating pharmaceutical similarity and disease similarity, other than taking advantage of pharmaceutical characteristics information and disease characteristics information respectively, an integrated similarity measurement method further takes full account of effects on similarity measurement due to pharmaceutical-disease related information in a current data set, so that a calculated similarity value can better reflect similarity between pharmaceuticals and similarity between diseases. On this basis, a pharmaceutical-disease heterogeneous network is built, and based on the heterogeneous network, a bi-directional random walk algorithm is taken to predict a candidate disease for all pharmaceuticals. The method disclosed by the present invention is simple and effective, and compared with other methods, tests on multiple data sets prove that the method disclosed by the present invention has better prediction performance in pharmaceutical relocation.

The invention belongs to the technical field of medical machinery, and relates to an electronic stethoscope which is used for auxiliary diagnosis and is capable of intelligently distinguishing physiological parameters, such as heart sounds and breath sounds, judging the types of the heart sounds and the breath sounds, and extracting the disease characteristics. The electronic stethoscope comprises a processor unit, and a signal collection unit, an external drive unit, a storage unit and a data bus interface unit which are connected with the processor unit, wherein the signal collection unit is used for collecting the signals of the heart sounds and the breath sounds and implementing the pre-processing on the signals; the processor unit is used for implementing the pattern recognition algorithms on the heart sounds and the breath sounds, separating the two sounds from each other, intelligently distinguishing and classifying the signals of the heart sounds and the breath sounds, and managing the other hardware units; the storage unit is used for storing the programs and the extension programs thereof, storing the data of the heart sounds and the breath sounds, the standard heart sounds and the breath sounds, and the audition model of each typical case of the disease, and outputting and playing; and the external drive unit and the data bus interface unit are used for implementing external operation function drive and data communication.

The invention discloses a construction method of a general medical special disease data system. According to the method, clinical text analysis and knowledge extraction are carried out to integrate two kinds of heterogeneous clinical data sources including unstructured medical records and structured clinical data; and then a general medical special disease data system for disease characteristic analysis is constructed. The method is characterized in that on the basis of a special disease segmentation dictionary, the analysis is carried out by combing contexts of medical records, the structuralization of the electronic medical records is completed; with the pattern matching and feature mining technologies, characteristic value of diseases in the medical records are obtained to complete analysis and digging of the semantics of medical records, so that disease condition features and disease condition prognosis conditions of diseases in the unstructured electronic medical records are provided and dug. The analysis and mining of the disease characteristics, disease outcomes, and the treatment process of the medical special diseases are completed by integrating the structured clinical data and thus a comprehensive complete medical data system is built.

The invention discloses a chronic disease condition change event prediction device based on a recurrent neural network, and the device comprises a memory, a processor, and a computer program, a preprocessing module and a chronic disease condition change event prediction model are stored in the memory, and the prediction model comprises a preprocessing module, a condition feature extraction module,and a classification module. When the processor executes a computer program, the following steps are realized: receiving long-term longitudinal data generated by multiple hospitalization of a patient, performing data preprocessing on the number by the preprocessing module, and reconstructing the data of each hospitalization into a feature vector as a to-be-tested data set; Taking the to-be-detected data set as input, extracting disease characteristics by a disease characteristic extraction module, and inputting the disease characteristics into a classification module; And enabling the classification module to output the prediction probability of various events indicating that the illness state changes. The prediction device can predict the event that the chronic disease patient has markeddisease condition change in the target time window, thereby assisting the doctor to formulate reasonable diagnosis and treatment measures and reducing the medical expenditure.

The invention provides a knowledge graph based acupuncture and moxibustion decision support method and apparatus. The method comprises the steps of marking medical information entities of acupuncture and moxibustion points and acupuncture and moxibustion concepts belonging to the medical information entities in a large amount of acupuncture and moxibustion treatment literatures to obtain an acupuncture and moxibustion knowledge graph; and extracting medical information entities involved in medical record information of patients and acupuncture and moxibustion concepts belonging to the medical information entities from a large amount of acupuncture and moxibustion medical records to obtain a medical record marking graph, combining a marking combination of the acupuncture and moxibustion literatures with the consistent acupuncture and moxibustion concepts with a marking combination of the acupuncture and moxibustion medical records to form an acupuncture and moxibustion-medical record knowledge graph, inputting disease characteristics of a target patient, and searching for a diagnostic decision from the acupuncture and moxibustion-medical record knowledge graph. The medical information is pre-marked, so that decisions not conforming to a conventional medical principle can be reduced and an accurate acupuncture and moxibustion decision support can be provided for users; and not only medical records and later treatment situations of patients similar to those of doctor-seeing patients but also a complete acupuncture and moxibustion knowledge network can be provided for physicians, so that the knowledge query demands of the physicians are met.

The invention discloses a system based on a TCM syndrome differentiation artificial neural network algorithm model, which can enhance the syndrome differentiation classification capability of different dominant diseases, improve the efficiency and accuracy of TCM syndrome differentiation diagnosis and treatment, can expand the scope of treated diseases of TCM doctors, improve the diagnosis and treatment capability of incurable diseases, and shorten the clinical experience accumulation time of young TCM doctors. The system includes a symptom input layer module for receiving the input patient disease data; a first hidden layer module for performing quantization coding of the input disease data; a second hidden layer module for performing correlation function calculation according to the quantization coding of the disease data to obtain the corresponding disease cause, disease location, disease nature and disease characteristic classification; and a syndrome-type output layer module for outputting the result data of the symptom and the corresponding syndrome type when the coincidence of the disease cause, disease location, disease nature and disease characteristic of the disease and the nature and flavor characteristic of the medicinal material is higher than the preset threshold.

The invention discloses a production method of a formula feed for meat geese and provides a new production process with optimal formulation according to the food and disease characteristics of meat geese. The method includes the steps of saccharifying corn straws and sweet potato seedlings, which are easily available, have wide sources and high fiber content, to convert hard crude fibers into soft materials containing xylitol, mixing the saccharified materials with green plants (such as cucumber, witloof and wild buckwheat) with nutritional and health-care functions and low production costs and processed potatoes, pumpkins, bone powder and the like, granulating and drying to produce the nutritional and health-care daily feed for geese, which is rich in dietary fiber, pectin, plant protein and vitamins, can promote appetite, meet the herbivorous habit of geese and promote goose growth, and has the functions of clearing away heat and toxic materials and relaxing bowel. The feed has a high return rate, is convenient in feeding, is high in palatability due to a high saccharified material proportion in a formula, and solves the annual supply problem of feeds in autumn and winter and for large-scale goose breeding.

The invention discloses a remote monitoring early-warning method of a track structure disease. The remote monitoring early-warning method comprises the steps of calculating normal track noise data when different locomotive trains run under different working conditions, and regarding the normal track noise data as sample noise data; generating standard noise data of different mileages of a track line on the basis of the sample noise data; using a sound transducer to collect train bottom noise radiation data in a train running process; conducting comparative analysis on the train bottom noise radiation data and the standard noise data, and judging that disease characteristics occur in a track structure when the deviation of the train bottom noise radiation data and the standard noise data is larger that a disease threshold value. The remote monitoring early-warning method of the track structure disease has the advantage that a detection device is installed on a running train, the situation of the track can be subjected to real-time and rapid detection, and the problem that the artificial detection is low in efficiency is solved.

The invention discloses a multi-class medical image judgment method and system. The method comprises the steps of processing medical images to obtain image features, analyzing different kinds of medical images, and obtaining an optimal feature subset based on a random deep forest classifier; processing the optimal feature subset through a support vector machine to output a classification result and endow the classification result with a type label corresponding to the medical image; and selecting a corresponding disease image processing algorithm based on the type label to process the medicalimage again to obtain disease characteristics, and processing the disease characteristics based on a classification network to output a diagnosis result. The system is for executing corresponding method. The method comprises the following steps: processing a medical image to obtain image features, and obtaining an optimal feature subset based on a classifier. The classification result is output through the support vector machine, the disease image processing algorithm is selected according to the classification result to process the medical image to obtain the disease characteristics, the disease characteristics are processed based on the classification network to output the diagnosis result, the medical image processing speed can be increased, and the processing burden of doctors is reduced.

The invention provides a method and system for automatically extracting human disease symptom characteristics. The method comprises a step of extracting a medical record of a patient, and further comprises the following steps: analyzing and summarizing dimension information in the medical record; summarizing the basic medical knowledge according to the dimension information; performing segmentation and semantic analysis on a disease characteristic sentence in the medical record; corresponding the disease knowledge information to disease and dimension information to generate json-format entityinformation; repeating the steps, and updating an iterative knowledge map. The invention provides the method and the system for automatically extracting the human disease symptom characteristics, through which a method for extracting symptom and sign information is researched on the basis of an outpatient clinical medical record text, the dimension is established through the symptom and sign information to form a symptom and sign model, and then a requirement on extraction of symptom phenotype entities from a current clinical medical history text is met by NLP, feature learning and other methods.

The invention relates to a medicine use information processing method based on a disease characteristic and disease degree information. The method comprises the following steps of receiving a patientprescription/medical advice information, and extracting diagnosis correlation information and medicine uses information from the prescription/medical advice information; calling the first medicine userule set of the diagnosis correlation information corresponding to disease state identification information from a reasonable medicine use knowledge base; extracting the disease characteristic and the disease degree information from diagnosis information, and determining whether to accord with the first medicine use rule set; if the characteristic and information accord with the first medicine use rule set, calling the second medicine use rule set of reasonable judgment of a single kind of medicine or among a plurality of medicine from the reasonable medicine use knowledge base; determining whether the name of the medicine, an administration route, dosage of administration and the frequency of administration accord with the second medicine use rule set; and if the name of the medicine, the administration route, the dosage of administration and the frequency of administration do not accord with the second medicine use rule set, generating caution information and sending to terminal equipment. By using the method, according to specific disease information and the disease degree information, medicine use rationality determination can be performed, a computer is used to carry out dataprocessing, work efficiency is increased and work is comprehensive and accurate.

The invention discloses a preparation method for turkey formula granulated feed. The preparation method comprises the following steps of: optimizing partner matching according to the food and disease characteristics of the turkey; cleaning, processing and pulping fresh stem leaf, water spinach stem leaf, pumpkin, onion, hot green pepper of green plant roots with convenience in getting materials, extensive source, nutrition and health care function, and low cost; adding corn and bone meal to prepare nutritional and health-care daily feed for turkey through such processes as dosing, pelletizing, drying and the like, wherein the nutritional and health-care daily feed is rich in chlorophyll, pectin, vegetable protein and multivitamin, is not only capable of appetizing, satisfying grazing habit of the turkey and promoting the growth of the turkey, but also has the functions of clearing away lung-heat, preventing dysentery and detoxifying, relaxing bowels and the like. The turkey formula granulated feed is convenient to feed and good in palatability.

A system (100), method and computer program product for determining plant diseases. The system includes an interface module (110) configured to receive an image (10) of a plant, the image (10) including a visual representation (11)of at least one plant element (1). A color normalization module (120) is configured to apply a color constancy method to the received image (10) to generate a color-normalized image. An extractor module (130) is configured to extract one or more image portions (11e) from the color-normalized image wherein the extracted image portions (11e) correspond to the at leastone plant element (1). A filtering module (140) configured: to identify one or more clusters (C1 to Cn) by one or more visual features within the extracted image portions (11e) wherein each cluster isassociated with a plant element portion showing characteristics of a plant disease; and to filter one or more candidate regions from the identified one or more clusters (C1 to Cn) according to a predefined threshold, by using a Bayes classifier that models visual feature statistics which are always present on a diseased plant image. A plant disease diagnosis module (150) configured to extract, byusing a statistical inference method, from each candidate region (C4, C5, C6, Cn) one or more visual features to determine for each candidate region one or more probabilities indicating a particulardisease; and to compute a confidence score (CS1) for the particular disease by evaluating all determined probabilities of the candidate regions (C4, C5, C6, Cn).

A system and method for detecting, diagnosing, and monitoring a disease and determining a disease signature including accessing patient deviation scores indicative of differences between patient data and reference data representative of a population segment, the patient deviation scores derived from longitudinal patient data such that the patient deviation scores include a plurality of sets of patient deviation scores, each set indicative of differences between patient data collected at a respective point in time and the reference data. The system and method also includes identifying a trend in the patient deviation scores for at least one clinical parameter, generating a report including a visual indication of the trend, and outputting the report. The report includes one or more views including Z, T, D, DT, and D feedback on T views, using image and non-image data.

The invention discloses an SVM based Alzheimer's disease characteristic classification method and system. The method comprises that magnetic resonance imaging data of the Alzheimer's disease is obtained; an improved genetic algorithm is used to carry out characteristic optimization searching on the obtained magnetic resonance imaging data to obtain key characteristics of the Alzheimer's disease; and an SVM classifier is used to classify data to be classified according to the extracted key characteristics, and a classification result of the Alzheimer's disease is obtained. The system comprisesa data obtaining module, a characteristic optimization searching module and a classification module. A device comprises a memory and a processor. The improved genetic algorithm takes the average classification accuracy as the fitness value to improve the feature extraction efficiency of the Alzheimer's disease, the SVM classifier ensures the classification performance of the Alzheimer's disease, and the method and system are visual and easy to realize, can be generalized effectively, and has a good identification performance. The method and device can be widely applied to the field of computeraided diagnosis.

The invention discloses an intelligent evaluation and diagnosis method and a system for heart disease types and severity degrees. The method comprises the steps of acquiring disease characteristic data and demographic characteristic data, and analyzing the acquired ultrasonic echocardiogram report data and the patient demographic characteristic data by utilizing a learning model to obtain a modelevaluation index, a heart disease type and a heart disease severity. According to the invention, a data mining method is adopted, so that data preprocessing, data screening and other operations are carried out on data through the data mining correlation method. The method is adopted for selecting a noise ratio during the characteristics selection process. A random forest model is adopted for carrying out the classification prediction of the heart disease severity. Meanwhile, an effective research method is obtained through comparing and analyzing the algorithm performances and the learning effects of the random forest model, a naive Bayes classifier, a decision tree model and a BP neural network model. Moreover, a standard for the severity classification of heart disease patients and a prediction method for predicting the treatment risk of the heart disease operation are provided.

The invention discloses a BIM technology based railway tunnel disease detection system and an application method thereof. The system includes a BIM technology disease detection module, a VR interaction module and a server module which are connected to the BIM technology disease detection module, and a railway tunnel disease management decision-making module and a railway tunnel disease detection device which are connected to the server module. The kernel of the system is the BIM technology disease detection module, and the omnidirectional observation of railway tunnel disease can be realized by establishing a railway tunnel three-dimensional BIM model, so that management personnel can master the whole situation, and railway tunnel disease detection and processed electronic and informationmanagement can be realized based on the BIM model; the railway tunnel disease detection device is small in size and can store and upload detailed information of diseases, so that the detection efficiency and filing accuracy of the diseases can be greatly enhanced; and railway tunnel disease characteristics can be controlled in real time, and the server module can rate traffic accidents according to big data so as to select appropriate disease processing schemes.

The invention provides a degradable gasket with anti-bacterial anti-adhesion performance. The degradable gasket is prepared via weaving or knitting of a plurality of bundles of magnesium-based metal wire, or via punching of magnesium-based metal sheets. The magnesium-based metal wire can be made of pure magnesium or a magnesium-based alloy of different elements based on disease characteristics and treatment requirements. The degradable gasket possesses excellent biocompatibility; in vivo degradation and absorption can be realized; degradation speed can be controlled; the degradable gasket is capable of preventing postoperative adhesion and infection, and promoting wound healing, can be used for preventing epidural adhesion after orthopedic surgery laminectomy, adhesion after tendon rupture repairing operation, adhesion after knee surgery, dura adhesion after transcranial surgery, eye socket soft tissue adhesion, intestinal adhesion after abdominal surgery, and intrauterine adhesion, is capable of reducing infection risk of the above surgeries, and possesses significant clinical application value.

The invention provides a rail fastener disease detection method and system. The method comprises steps that images of to-be-detected rail fasteners are acquired; the images of the to-be-detected railfasteners are inputted to a trained convolutional neural network, and the original output result of the convolutional neural network is obtained and outputted; based on the preset decision discrimination conditions, the original output result is detected and discriminated, and the images of the target rail fasteners having diseases are determined. The method is advantaged in that the powerful adaptive learning capability of the convolutional neural network is utilized, disease characteristics of the fasteners are automatically learned, the function of automatically detecting the fastener diseases is realized, the detection speed is fast, and detection is accurate.