71results about How to "Reduce subjective influence" patented technology

The invention discloses a method for automatically identifying a breast tumor area based on an ultrasound image. The method comprises the following steps of acquiring the ultrasound image of the breast, and preprocessing the ultrasound image; segmenting the ultrasound image subjected to preprocessing through an image segmentation method to obtain a plurality of segmented subareas; extracting a grey level histogram, texture features, gradient features and morphological features of the ultrasound image, and combining the grey level histogram, the texture features, the gradient features and the morphological features of the ultrasound image with two-dimensional position information to obtain high-dimensionality feature vectors; selecting the most effective feature subset of the high-dimensionality feature vectors through feature ordering based on biclustering and a selection method; performing learning classification on the selected most effective feature subset through a classifier, and then automatically identifying the breast tumor area. By means of the method, the breast tumor area can be identified automatically from segment results of the breast tumor ultrasound image, therefore, automation performance of computer-aided diagnosis is improved, manual operation of clinical doctors is reduced, and subjective influence of clinical doctors is reduced.

The invention relates to a network security situation evaluation method based on CS and improved BP neural network. The method comprises four steps of S1. acquiring network security situation elements, forming a training sample set and a test sample set, and determining a BP neural network structure; S2. seeking an optimal initial weight and a threshold by using a CS algorithm; S3. introducing a momentum factor and a gradient factor to improve the BP neural network; S4. training the improved BP neural network, finally, using the trained network in network security situation evaluation so as toobtain a final situation value and a security level. Network security situation is evaluated precisely and quantitatively by using the improved BP neural network, so that subjective effects of expertopinions in traditional evaluation methods are lowered, and overall network security situation is reflected objectively and comprehensively; and the network security situation is improved by combining the CS algorithm and introducing the momentum factor and gradient factor, the convergence speed is improved, time and space overheads are reduced, and accuracy and practicability of network securitysituation evaluation are improved.

The invention relates to a fuzzy comprehensive assessment method of bridge life cycle environmental influence, comprising: using life cycle assessment technology provided by ISO14040 as basis, introducing fuzzy assessment theory in the environmental influence assessment, quantizing environmental influence index, determining index weight through analytic hierarchy process, and obtaining latent value of the environmental influence through the fuzzy comprehensive assessment. The bridge life cycle includes a designing phase, a raw material phase, a construction phase, a running and maintaining phase and a discarding phase. The invention is characterized by overall index, current assessment, convenient operation, small subjective effect and the like and wide application foreground.

The invention relates to a system and a method for realizing a video knowledge acquisition and marking function of a portable-type device, which belongs to the technical field of computer application. The system comprises a resource input module, a structuralized description module, a marking device module, a two-direction cutting module and a central control module. In the method, the structuralized description module generates structuralized description data; the marking device module conducts coarseness mark on a video and a picture file according to the structuralized description data; the video and the picture file are classified into a plurality of video clips with different semantics or different areas in a picture according to the coarseness mark; and then fineness mark is conducted for the video and the picture file. Due to the adoption of the system and the method, the subjective influence of the manual device mark standard on the video marking can be reduced, the precision of the video marking can be greatly improved, and convenience for automatically enlarging the video mark training set can be realized; and simplicity and convenience in application way of the system and the method can be realized, the realization cost is low, and the application range is wider.

The invention discloses a fuzzy mathematics-based gas pipeline third-party damage risk assessment method, which can realize quantitative assessment of gas pipeline third-party damage risk. According to the technical scheme, various possible conditions of a gas pipeline third-party damage accident are systematically analyzed by adopting an analytical hierarchy process and an MMESE system theory for characteristics of diversity, complexity, uncertainty and the like of the gas pipeline third-party damage accident, a three-level hierarchical structure model is built, and a triangular fuzzy number is introduced according to a fuzziness characteristic, so that a relative importance degree among factors is quantitatively represented, the limitation of the analytical hierarchy process is overcome, human subjective influence in a conventional assessment method is reduced, and weight allocation is more accurate, objective and reasonable. The method has the advantages that the limitation of the analytical hierarchy process is overcome, and the subjective influence of the human factors in the conventional assessment method is reduced; and the weight allocation is reasonable, and an assessment result is objective and accurate.

The invention belongs to a network optimization problem, relates to the optimization of a business routing distribution scheme in a power communication network, and especially relates to a communication network optimization method based on a hierarchical analysis method and a genetic algorithm. According to the invention, the method employs the hierarchical analysis method from the angle of the general risk degree of a power communication network and the node and business risk balance degree, combines the qualitative and quantitative methods, enables a complex decision-making system to be hierarchical, provides the quantitative analysis for the analysis and decision making through the level-by-level comparison of various kinds of correlated factors, and proposes a standard for the judgment of the quality of a communication network. The standard is taken as an objective, and the method employs the improved genetic algorithm, and proposes a new coding mode and variation mode, thereby solving a problem that the binary coding of a conventional genetic algorithm is not sufficient in expression of the problem, and achieving the optimization of the communication network.

The invention relates to a prior knowledge-based multi-modal ethnic identity sense quantitative measurement method and belongs to the intelligent pattern recognition and ethnology research crossing filed. According to the measurement method, ethnic minority emotion pictures are adopted as basic materials; ethnic minority identity sense survey questionnaire questions are converted into the induction materials of electrophysiological signals; after the EEG information of subjects is acquired, the EEG information implying identity senses is classified through a fuzzy neural network learning-basedEEG emotion feature extraction and classification algorithm; questionnaire survey results and EEG classification results are fused, so that ethnic identity sense quantitative measurement is realized;and the objective feeling of the subjects for the ethnic identity sense and national identity sense can be automatically analyzed. With the method of the invention adopted, the subjective influence of questionnaire surveys can be decreased, the objectivity of identity sense classification can be enhanced, and ethnic identity sense quantitative classification is more accurate and more efficient.

The invention relates to the technical field of game-based virtual learning, in particular to a method for embedding a knowledge ontology into a game model. The method comprises the following steps: constructing a game-oriented knowledge ontology; constructing a game atomic challenge ontology model of the game model according to a game type and constitution elements; calculating the similarity of a specific knowledge set in the knowledge ontology and each game atomic challenge ontology, and establishing map from the knowledge set to each game atomic challenge ontology according to the similarity; selecting the game atomic challenge ontology with the highest similarity in the knowledge set as an adaptive game atomic challenge model. Unified representation is performed on domain knowledge and a game by taking the ontology as the basis, and the intrinsic relation between the two is analyzed by calculating the similarity of the ontology, so automatic adaption of the knowledge and the game is realized, and the subjective influence of an individual designer is reduced.

The invention discloses a method for evaluating an inductive effect of a navigation product, a testing device and a construction method for the testing device, wherein the method for evaluating the inductive effect of the navigation product comprises the following steps: drawing induction GPS (global positioning system) points of the navigation product on a map, and saving induction information of the induction GPS points of the navigation product so as to display corresponding induction information when operating the induction GPS points; associating the induction GPS points of the navigation product with street view images in a street view map so as to display corresponding street view images when operating the induction GPS points; evaluating whether the induction information of the navigation product is accurate according to the displayed induction information and the displayed street view images when operating the induction GPS points. According to the method for evaluating the inductive effect of the navigation product, the testing device and the construction method for the testing device, an indoor evaluating manner is provided, so that the costs of manpower and material resources are reduced, the influence of weather, traffic and the like on evaluation is avoided, the subjective influence of evaluators is reduced, and the accuracy and the objectivity of evaluation results are guaranteed.

The invention provides a wind profile data prediction method. The laser radar measures the wind speed and direction; whether the wind speed and wind direction are lost and whether the data integrity rate of a single wind speed and wind direction is enough can be automatically judged; an applicable wind speed and wind direction prediction model can be automatically selected to predict and supplement wind speed and wind direction data; therefore, the common unscientific problem of current wind measurement data prediction is well solved, subjective influence on prediction caused by uneven levelsof different engineers is reduced to the maximum extent, and missing of the laser radar and wind measurement data with insufficient single wind speed and wind direction data are scientifically and accurately predicted.

The invention relates to a membrane performance comprehensive evaluation method based on an analytic hierarchy process (AHP). The method comprises the steps of according to the main influence factorsof the membrane performance, adopting the AHP to construct an index hierarchy structure and calculating the weight, and then combining an expert questionnaire method to determine the weight; introducing a membership function in the evaluation; constructing a membership matrix by dividing the evaluation grade boundary and according to the evaluation index detection value; and obtianig the membraneperformance membership grade and the comprehensive score by combining the weights. The method of the invention has the advantages of comprehensive index, reasonable system, small subjective influence,and the like, and simultaneously has the functions of evaluation and comparison, and has wide application prospect in membrane performance evaluation.

The invention relates to a water source pollution detection method based on an evidence theory, and the method uses an information processing technology to detect the pollution degree of water. A fuzzy number model of the water resource water quality index is generated according to existing data, the similarity between a sampling value in a water resource distribution system and the fuzzy number model of the existing index is obtained according to a similarity measurement method of the fuzzy number, basic possibility appointment is generated on the basis of the similarity, a classic fusion method is used to fuse the basic possibility appointment, a main focal element of a fusion result is determined, the pollution degree of the system is obtained according to the correspondence between the pollution level and function elements of the basic possibility appointment, and water resource pollution is detected. The detection method has the advantages of higher versatility, low computational complexity and high instantaneity, and can be conveniently used in water resource pollution detection.

The invention relates to a method for identifying the resistance of the wheat take-all disease. The method comprises the following steps of adopting a disease-susceptiblevariety of yangmai 158 as a control variety, carrying out identification of the resistance of the wheat take-all disease on the wheat to be measured, i.e., disinfecting seeds of the wheat to be measured and the yangmai 158, and putting the seeds in a culture dish for pregermination; selecting and moving a seedling with three germinated seed roots and the root length being 1.5-2.5cm into the culture dish padded with water-absorbing filtering paper; grafting the middle part of each seed root into a bacterial disk with strongly-pathogenic bacterial strain with gaeumannomyces graminis var. tritici, culturing for five days, measuring the length of lesionson the wheat to be measured and the yangmai 158, and calculating the severity of the wheat take-all disease of the wheat to be measured by comparison with the yangmai 158. The method has the advantages of short identification period, simple and convenient operation, small occupied space and high accuracy.

The invention relates to the software research and development management field and particularly relates to a performance calculation method based on multi-project parallel management. According to the method, firstly, an average department reference score A, a scope parameter M and the quantity m of project research and development people of different research and development departments are set by a project management office through a performance platform; priority scoring P for each project of a certain department is carried out by the project management office; work logs and output matters are checked and accepted by each project-in-charge person, and performance scoring Q for project participants is carried out; statistics of supporting n times of N projects carried out by the departments at a present month and respective project coefficients alpha of the N projects is carried out by the project management office, an average project supporting quantity R of each person and a reference radix C are calculated, and scores B are additionally scored for part-time project-in-charge persons and members providing special contributions; and all the parameters are required to input into the performance platform. Through the method, a present month performance score of each research and development member of the departments can be calculated by the system according to a formula, and problems of inaccurate parameter data, excessive subjective factors and scoring not based on work effects and values are solved.

The invention provides a determination index based low resistivity oil zone recognition method and device. The determination index based low resistivity oil zone recognition method comprises the steps that a low resistivity oil zone of a target exploration region is defined; data information of the target exploration region is obtained to find out the confirmed low resistivity oil zone; the causes of the low resistivity oil zone are analyzed to determine a low resistivity oil zone recognition method suitable for the target exploration region, the experience judging indexes corresponding to the low resistivity oil zone recognition method are calculated, and the distribution range of the experience judging indexes is obtained; a suspended low resistivity oil zone of the target exploration region is looked up, and the target judging indexes of the suspended low resistivity oil zone are calculated; and a recognition result of the suspended low resistivity oil zone is determined according to the distribution situation of the target judging indexes in the distribution range. By utilizing the embodiments of the method, multiple oil zone recognition methods can be comprehensively considered, the uncertainty and correct judgement probability in the judging process can be embodied in a quantitative mode, the subjective influence of artificial recognition can be reduced, and the recognition correction rate can be improved.

The embodiment of the invention discloses an image annotation method, and the method carries out the face quality comparison through employing two to-be-annotated images as a comparison pair, enablesa judgment basis of a user to have a measurable objective standard, and reduces the subjective impact. On the basis of the comparison result, the marked image is used as a node to construct a balancedbinary tree, and in any target node in the balanced binary tree, sub-nodes on different sides of the target node are different from the face quality comparison result of the target node. When face quality comparison is carried out on the target to-be-annotated image subsequently; an image related to the balanced binary tree can be selected from the balanced binary tree to form a comparison pair,wherein the face quality comparison result of the ith to-be-compared image and the (i-1) th to-be-compared image is the same as that of the target to-be-labeled image and the (i-1) th to-be-compared image in the (i-1) th comparison pair. Th number of comparison pairs in the process of identifying the to-be-annotated image set is reduced, and the annotation efficiency of the face image is improved.

The invention discloses a safety evaluation method of a gas storage and distribution station based on a BP neural network. The method comprises the following steps: 1, according to the execution standard and the process flow of the gas storage and distribution station, determining an index system of the safety evaluation of the gas storage and distribution station, including an evaluation index and a scoring standard; 2, constructing the topological structure of the BP neural network, and establishing a safety evaluation model based on the BP neural network; 3, collecting the evaluation indexparameters and safety evaluation results of the gas storage and distribution station as training samples of the neural network; 4, obtaining a safety evaluation model of learning and train from a training sample and constructing a database; 5, forming an inference mechanism in which that network output error is within the allowable range; Step 6, the safety of the gas storage and distribution station being predicted: the safety evaluation grade is determined as A safety, B safety, C general safety, D relatively unsafe, E unsafe. The invention has the advantages that the subjective influence ofmanual evaluation is reduced and the accuracy and objectivity are improved; easy operation and high efficiency are realized.

The embodiment of the invention provides a method and a device for judging asthma and relates to the technical field of data processing. The method comprises the steps of after obtaining the treatmentinformation of a patient, extracting the feature values of a plurality of preset features of the patient from the treatment information, inputting the feature values of the plurality of preset features of the patient into a linear classification model to determine the category of the patient. The linear classification model determines whether the patient suffers from asthma or not the plurality of preset features of the patient. Compared with a conventional method in the prior art that whether the patient suffers from asthma or not is diagnosed only according to symptoms or disease courses, the method is higher in accuracy. Meanwhile, a classification model can automatically determine whether the patient suffers from asthma or not according to the plurality of features of the patient. Therefore, the subjective influence of doctors is small, and the asthma judging efficiency is improved at the same time.

The invention relates to color fastness standard fabric for blue series in textile and further relates to an application of the standard fabric in textile color fastness detection and rating. The standard fabric adopts cotton plain cloth as grey cloth and is prepared by adopting the following specific preparation method comprising steps of pre-processing and dyeing; according to the standard fabric, color fastness to rubbing relates to eight color fastness grades, color fastness to perspiration relates to four color fastness grades, and color fastness to saliva relates to four color fastness grades. The original grey card rating is converted into standard fabric comparison rating, the rating is more visual, subjective influence of a detection worker is reduced, and the accuracy rate of the detection is increased; through improvement of the technology of the standard fabric, the preparation process of the standard fabric is controllable, the color accuracy is high, and the application prospect is wide.

The invention discloses a non-contact railway relay supporting piece gap measuring system and method. The system comprises a computer, a CCD image acquisition sensor, an adjustng assembly, a railway relay contact alignment device base, parallel light illumination equipment, and a CCD camera lens. A tested product is inserted into the railway relay contact alignment device base. The CCD image acquisition sensor is installed on one side of a tested object through the adjusting assembly to carry out image acquisition. The parallel light illumination equipment is arranged on the two sides of the CCD image acquisition sensor. A lens of the CCD camera is connected to the CCD image acquisition sensor. Rulers are adhered to a supporting sheet and a reed on the side surface of a railway relay. According to the system and the method, the coordinates of angular points at the top end of the supporting piece can be obtained more accurately, and a reed reflection area can be more obvious and real; point-to-point distance is represented by point-to-straight line distance, so that a measurement result is attached to a real supporting piece gap value, and the negative influence of the parameter measurement process on relay parameters is avoided.

The invention relates to a target user selection method, system and equipment. The method comprises the following steps of: obtaining a selection instruction sent by a control device, and in response to the selection instruction, reading attribute information which representing incidence relation between each user and a preset constraint condition; selecting a target user from the users according to the attribute information; and obtaining a unique identifier corresponding to a reception device of the target user, and sending a notification message to the reception device of the target user according to the unique identifier, wherein unique identifiers which are mutually distinguished are arranged on the reception devices, and each identifier corresponding to one unique user. The target user selection method, system and equipment can be used for decreasing the subjective influences of choice subjects and improving the correctness of target selection.

The invention discloses a bridge crack detection data set pre-screening and calibration method, and aims to reduce the workload of a complicated process of manually screening data of tens of thousands of images and labeling images meeting requirements, and effectively reduce the subjective factor influence of a screener in the screening process. Firstly, a bridge image is acquired, edge detection and threshold segmentation based on a traditional algorithm are performed on the acquired bridge image, contour features are extracted, and a non-crack image is preliminarily judged and abandoned by formulating a screening rule. Thirdly, fine screening work is further carried out manually, a coarse screening result is corrected, and finally a bridge crack detection data set is obtained. According to the method, manpower and calculation time can be saved, and the detection cost for solving corresponding crack detection and other building problems is reduced.

The invention discloses a risk identification model optimization method and device. The method comprises the following steps: acquiring a false identification sample and N alternative samples; inputting the error identification sample and the feature vector of each alternative sample into a deep learning model for processing, and extracting the processed feature vector from the middle layer of thedeep learning model to serve as a standardized feature vector of the corresponding sample; according to the standardized feature vector of the false identification sample and the standardized featurevectors of the M alternative samples, determining K alternative samples similar to the false identification sample from the M alternative samples by adopting a K nearest neighbor algorithm, and taking the K alternative samples as similar samples; and determining the mark of each similar sample as a first risk type, and optimizing the risk identification model based on the error identification sample and each similar sample.

The invention discloses a petrochemical enterprise safety evaluation method based on a PSO-BP neural network. The petrochemical enterprise safety evaluation method comprises the steps of 1, determining an index system (influence factors) of a petrochemical enterprise safety state; step 2, constructing a PSO-BP neural network model; 3, collecting a data sample; step 4, inputting the training sample to train the PSO-BP neural network; step 5, obtaining parameters such as corresponding weights of the PSO-BP neural network and a trained neural network security evaluation model; and 6, evaluating the safety state of the petrochemical enterprise. According to the method, the workload of manual evaluation is reduced, the subjective influence of evaluation personnel is greatly reduced, the accuracy and objectivity of the safety evaluation result of the petrochemical enterprise are improved, and technical support is provided for mastering the safety operation of the petrochemical enterprise.

The invention provides an automatic exposure control method and system, and the method comprises the steps: enabling a to-be-photographed object to enter a photographing region, carrying out the graphic collection of the to-be-photographed object, and obtaining the position information of a to-be-photographed part; determining an exposure radiation field of the flat panel detector based on the relative position of the to-be-photographed object and the flat panel detector; and selecting an exposure irradiation radiation field of the flat panel detector, exposing the to-be-photographed part, and triggering image acquisition by the flat panel detector after exposure is completed. According to the invention, the visual device is used for collecting information, the irradiation radiation field selection range is obtained through calculation and analysis, the subjective influence of operators is reduced, and the exposure irradiation radiation field selection is more accurate; automatic exposure control is realized based on exposure dose detection of an exposure irradiation radiation field area, the structure is simple, and the cost is low; the exposure dose is predicted through an algorithm, so that exposure dose errors can be effectively avoided, accurate exposure control is realized, and the imaging quality is improved; and an image is automatically acquired immediately after exposure is detected, so that the image acquisition period is shortened.

The invention relates to a surrounding rock grading correction method and device based on tunnel buried depth and weathered layer thickness. The method comprises the steps that 1, for a tunnel section, fully located at a single weathered stratum, of a tunnel hole section, a standard regulation method is adopted for basic surrounding rock grading to obtain an initial surrounding rock grade; 2, according to the tunnel buried depth and the weathered layer thickness, the initial surrounding rock grade is graded and corrected to obtain the corrected surrounding rock grade. Since the influence of the tunnel buried depth and weathered layer thickness is not considered during surrounding rock grading in the prior art, the invention provides the brand-new surrounding rock grading correction method.According to the tunnel buried depth and weathered layer thickness, the initial surrounding rock grade is graded and corrected, the subjective influence is reduced, and through surrounding rock gradequantification, the tunnel surrounding rock distinction correction effect is obvious.

The embodiment of the invention provides equipment for judging asthma, and relates to the technical field of data processing. The equipment for judging asthma obtains the treatment information of a patient through an input module, and then extracts the characteristic values of a plurality of preset characteristics of the patient from the treatment information by adopting a preprocessing module. After that, the characteristic values of the preset characteristics are input into a classification module. The classification module determines the type of the patient according to the characteristic values of the plurality of preset characteristics. The type of the patient comprises asthma and non asthma. The equipment is higher in accuracy compared with the prior art that whether a patient suffers from asthma or not is diagnosed only according to symptoms or disease courses. Meanwhile, a classification model can automatically determine whether the patient suffers from asthma or not accordingto the plurality of characteristics of the patient. The subjective influence of doctors is small. Meanwhile, the asthma judging efficiency is improved.

The invention belongs to the technical field of traffic facilities, and particularly discloses a novel traffic light. The novel traffic light comprises a light box, traffic lights and a camera, wherein the traffic lights and the camera are arranged on the light box; the camera is used for taking photos of evidence; and the camera and the traffic lights are respectively and electrically connected with a control system. The novel traffic light adopts an integrated modern processing mode, i.e., the traffic lights and the camera adopt the same control system to complete; and the novel traffic light has the advantages of high processing speed, high stability and simplicity and convenience for construction, installation and debugging.