248 results about "Discrimination function" patented technology

A glucose sensor system comprising the steps of using as a sample discriminating parameter a ratio (I / ΔI) of a measured current value I to the time-differential value of the current value ΔI, defining a discrimination function that discriminates whether a sample is blood or control fluid and uses the discriminating parameter as an independent variable, quantitating as a discriminating index a numeric value obtained by substituting a discriminating parameter value into this discrimination function, and automatically discriminating, based on this index, whether the sample is blood or a control fluid, whereby a kind of the sample can be automatically quantitated by measuring electric current when a sensor system is used for quantitating the concentration of an analysis object in the sample.

An all-weather 96-point daily load curve prediction and optimization correction system. Historical tracking load samples and multi-weather samples are obtained to determine weight of weather of each city and calculate comprehensive meteorological factors; different data types of meteorological load data are sorted and screened, and a load extreme value inflection point prediction model suitable for different data types is established; an analogous meteorological daily load curve discrimination function is established, an analogous load curve is discriminated through similarity of predicted weather and historical weather, and combined with the extreme value inflection point prediction model, a daily load curve prediction model for different date types is established; a data type distinguishing module and a weather identification module are used to automatically judge the type and weather condition of the day to be predicted and an optimal model is selected to perform prediction; and a daily load typical curve database is built, a prediction curve obtained by calculation is corrected, a predicted value and curve are stored and a result is output, thereby realizing automation of short-term load curve prediction, improving load prediction accuracy, and realizing fine management of a power grid load.

The invention relates to devices that detect and / or treat tachyarrhythmias. The invention includes software systems that distinguish among various tachyarrhythmias in order to provide treatment for specific tachyarrhythmias. One aspect of the invention employs a methodology to provisionally detect ventricular tachycardia and / or fibrillation and thereafter apply a discrimination function to a series of measured intervals preceding the provisional detection. Discrimination is accomplished by sorting the intervals preceding provisional detection into bins corresponding to interval ranges and examining the relative distribution of the intervals within the bins.

Disclosed method and apparatus for automatic information filtering are capable of improving both precision and recall and accurately judging inappropriateness of the content even for a page that contains very few or no text information and only displays images, by utilizing an upper level URL of a URL given in a hierarchical structure. Also, disclosed method and apparatus for automatic information filtering are capable of setting weights of words easily and accurately and judging inappropriateness of the information by utilizing these weights, by using an automatic learning based on a linear discrimination function that can discriminate the inappropriate information and the appropriate information on a vector space.

Signal-processing devices having memristors are described for performing frequency-discrimination functions, amplitude-discrimination functions, and time-oriented functions. In each case, the time-domain behavior of the memristors described herein enables these functions to be performed. In one embodiment, memristance of an arrangement of memristors of a device is, after an initial transitional period, predominantly at a first level if frequency of an input signal of the device is less than a first frequency and predominantly at a second level if the frequency of the input signal is greater than a second frequency.

The invention provides a real-time traffic light recognition method based on space-time correlation and priori knowledge, and belongs to the field of traffic information detection in the intelligent transportation industry. The method includes the steps that firstly, regions of interest are positioned on an original image through the priori knowledge, and the regions unrelated to a traffic light are filtered out through empirical values; secondly, the red region and the green region of the traffic light are extracted and filtered on this basis through shape features; thirdly, sub-regions obtained through filtering are read in, the HOG features of the sub-regions are sequentially extracted, and a traffic light sample is trained through a classifier; fourthly, the current traffic light is recognized according to a discrimination function of the classifier, wherein if the front light is green, driving can be achieved, if the front light is red, a parking signal is sent out, and if both the green front light and the red front light exist, whether driving can be achieved or not is determined according to the space-time correlation information and lanes where vehicles are located. The method conforms to the detection and recognition characteristics of the traffic light, information of the traffic light can be accurately detected in real time, and the method is used in an intelligent vehicle and assists in correct and safe driving of the intelligent vehicle.

An inspection apparatus includes a discrimination function determination unit which determines whether or not a discrimination function forms an area including a discrimination sample. The discrimination function is used in non-parametric one-class discrimination. The discrimination sample is discriminated into a class as a single area in an input space where learning samples are plotted.

The invention provides a method and device used for achieving state monitoring and fault diagnosis of a relay through monitoring and analyzing the change of a control system circuit and a controlled system circuit of the relay. According to the method used for state monitoring and fault diagnosis of the relay, a selected fault sample is processed by means of a mode recognition algorithm, a classifier used for state diagnosis of the relay is obtained, the discrimination function of each class is obtained, and a result of state monitoring and fault diagnosis and repairing and maintenance suggestions are provided for relevant workers. The method and device used for state monitoring and fault diagnosis of the relay of the relay have the advantages that defects of an existing relay detection technique are overcome, the timing sequence of turning on and turning off of the relay does not need to be learned, hidden danger of a fault can be predicated, and then the relay can be maintained in advance to avoid the fault.

A defect inspection method for inspecting a defect(s) on an object to be inspected, within a step for determining parameter includes: a step for extracting a defect candidate on the object to be inspected with using said discriminant function with determining an arbitrary parameter; and a step for automatically renewing the parameter of said discriminant function, upon basis of teaching of defect information relating to the defect candidate, which is extracted in the step for extracting the defect candidate.

In an image formation apparatus having a function to detect a direction of an original image, in a case where an image formation mode is set by using a touch panel, a keybutton to instruct whether or not direction detection is to be performed is displayed on a setting screen of an image formation mode to which direction detection is effective, while such the key is not displayed on a setting screen of an image formation mode to which direction detection is not effective. The image formation mode to which direction detection is effective includes a mode to record images of one-face originals onto two faces of a sheet, a mode to arrange and record images of plural originals onto one sheet, a mode to perform stapling at designated corner positions of sheets, and the like.

The invention provides a voice control method for a smart home and a voice control device for the smart home. The voice control method for the smart home comprises the steps of upon receiving the voiceprint information, triggering the smart home to collect the real-time image information; detecting whether the real-time image information contains the human body feature information or not; upon detecting the human body feature information, triggering to start the voice control function; after starting the voice control function, analyzing the voice information contained in the voiceprint information; detecting whether the voice information is matched with a pre-stored voice control command or not; on the condition that the voice information is matched with the pre-stored voice control command, controlling the smart home control to execute the pre-stored voice control command. According to the technical scheme of the invention, the real-time acquisition function of images and the discrimination function of voice control commands are additionally realized. Therefore, the misoperation probability of the smart home is effectively reduced. Meanwhile, the waste of electricity is avoided and the usage experience of users is improved.

The method discloses a robust video object tracking method, and the method comprises the steps: sampling a candidate target particle based on the particle filter importance sampling principle; filtering out divergent particles based on the cosine similarity between the candidate target particle and a former tracking result; representing the screened candidate target particle based on a template dictionary linearly; building a low-rank sparse mathematic model of a linear coefficient matrix; solving a coefficient matrix based on an incorrect lagrangian multiplier optimization algorithm; selecting an optimal candidate object according to a discrimination function to serve as a tracking result; and updating the template dictionary in an on-line manner. The robustness of the method guarantees that the method can meet various types of challenges, and achieves the accurate tracking of a target in a video. The method solves a problem of inaccurate tracking and drift of the target in the video, wherein the problem is caused by illumination variation, scale change, shading, deformation, movement fuzzy, quick movement, rotation, background clutter, low resolution and others.

The present invention belongs to the field of quantitative evaluation of human body's subhealth state and features that in personalized sports experiments, the testee's electrocardiogram, pulse wave and blood pressure are measured and recorded; hereby the characteristic physiological parameters including maximum systolic blood pressure, average rest heart rate, heart rate restoring time, the ratio between height and squared body weight and maximum heart rate are then obtained and substituted into judgment function to generate the evaluation value of human body's subhealth state; and the evaluation value is substituted into the membership function to obtain the subhealth state grade. The subhealth state grade lower than 75 is corresponding to subhealth state and or else the health state.Correspondingly, the computerized measuring and evaluating system is also provided.

The invention discloses a method for discriminating reservoir fluid by establishing a gas logging chart on the basis of discriminant analysis, relating to the technical field of oil and gas exploitation and development. The method includes the steps of: a, collecting the gas logging peak value data and the oil test results in an oil test completion well; b, according to the categories of the oil test results, grouping the gas logging peak value data of the logging display sections which have the same category of oil test results; c, establishing discrimination factors by taking the gas logging peak value data of the logging display sections as a base; d, selecting the established discrimination factors, and formulating discrimination functions which can effectively discriminate the property of the fluid on the basis of discriminant analysis; and e, according to the coincidence rates of the formulated discrimination functions, preferentially selecting two discrimination functions with the highest coincidence rates to be used as x axis and y axis to establish a gas logging chart to discriminate the property of the reservoir fluid. The method disclosed by the invention solves the problem that conventional gas logging charts are difficult for effectively discriminating the reservoir fluid, so the dominant regions of different fluids can be well marked out.

The invention provides a mudslide early warning method based on rainfall monitoring. The mudslide early warning method comprises the following steps of according to historical rainfall data, establishing a mudslide event feature rainfall model, a surface runoff event feature rainfall model and a normal rainfall event feature rainfall model, and determining a discrimination function; according to the discrimination function, determining an attenuation coefficient, a weight coefficient and a critical threshold value; collecting rainfall data of previous n days, and using the attenuation coefficient to calculate the effective rainfall of previous n days; using the weight coefficient and the rainfall data of current day, and calculating the feature rainfall according to the weight coefficient, the rainfall data of current day and the effective rainfall of previous n days; comparing the feature rainfall with the critical threshold value, and determining whether the rainfall of current day is enough to cause a mudslide event or not according to the comparison result. The method has the advantage that the accuracy of early warning of the mudslide can be effectively improved.

The invention provides a relational network link predicting method based on a generalized relation hidden topic model and relates the field of computer application. The method includes the steps of S1, pretreating text relational network data, and extracting word bag text features and link relations among documents; S2, building a generalized relation hidden topic link predicting model according to the extracted word bag text features and link relations among documents; S3, training the generalized relation hidden topic link predicting model; and S4, using the trained generalized relation hidden topic link predicting model to predict link relations among documents. The defect that symmetrical relation discrimination functions are unreasonable, and data likelihood of relation discrimination functions, unbalance of two parts of loss functions and approximate reasoning mean field assumption cause non-ideal link relation predicting in the prior art are overcome, and practicality in tasks such as link relation predicting, network recommending and text retrieving is improved evidently.

A method and system for estimating the worst case corrosion in a pipeline for which pipeline wall thickness measurements are limited to sampled ultrasonic or radiography (UT / RT) measurements. A data library contains distributions of in-line inspection (IL) measurements for other pipelines, calibrated to correspond to UT / RT measurements as needed. These ILI datasets are randomly sampled multiple times, to obtain multiple sample sets from each ILI dataset. Candidate statistical distributions are evaluated for each sample set to determine which of the candidate statistical distributions most accurately estimates the worst case corrosion measured by ILI. A discriminant function is then derived from sample statistics and pipeline descriptors associated with the sample sets, along with the best candidate statistical distribution for that sample set. Sample statistics and pipeline descriptors for the pipeline with sampled UT / RT measurements are then applied to the discriminant function to determine the best one of the candidate statistical distributions for extreme value estimation, and the worst case corrosion is then determined using that best statistical distribution.

The invention discloses a high-dimensional mass data GMM (Gaussian Mixture Model) clustering method under a Hadoop framework. The high-dimensional mass data GMM clustering method is used for clustering high-dimensional mass data by structuring the clustering problem of mass data on a distributed platform, mainly aiming at the defects of the existing clustering algorithms. The high-dimensional mass data GMM clustering method comprises the following specific steps of: 1. constructing a local area network; 2. establishing a Hadoop platform; 3. uploading data to a cluster; 4. initially clustering, 5. calculating the parameter and the discrimination function of each cluster; 6. discriminating whether clustering is completed or not; 7. clustering again; 8. calculating the mean value and the weight of each class in a new cluster; 9. calculating the variance of each class in the new cluster; and 10. outputting clustering results. By using the characteristics of a MapReduce operation model in the Hadoop framework, using a Map parallelizing method to process parallelizable parts in the cluster and adopting two Map / Reduce tasks to respectively calculate the mean value and the variance, high-efficiency and high-accuracy clustering can be realized, and the scalability and the fault tolerance are better.

An image forming apparatus capable of determining whether a toner cartridge is a refilled toner cartridge and method thereof is provided. The image forming apparatus comprises a cartridge mount part configured to receive a toner cartridge with a toner memory. The toner memory stores information for determining whether a toner cartridge is a refilled toner cartridge. The image forming apparatus further comprises a display part for displaying messages according to the determination information in the toner memory, a control part for reading the determination information from the toner memory and determining toner cartridge condition. The control part directs output of the messages, thus indicating toner cartridge condition. Therefore, use of unauthorized refill toner cartridges can be prevented.

The invention discloses a vegetation coverage extraction method and system. The method comprises the steps of obtaining an aerial image collected by an unmanned aerial vehicle; De-noising processing is carried out on the aerial image; Carrying out image enhancement processing on the aerial image after noise removal; Calculating a vegetation index of the aerial image after image enhancement processing to obtain a vegetation index image; And taking the discrimination function of the information entropy of each surface feature category as a fitness function, and segmenting the vegetation type image from the vegetation index image by using a genetic algorithm, thereby obtaining the vegetation coverage. According to the vegetation coverage extraction method and system, the stability of image shooting and the precision of vegetation coverage extraction can be improved.

The invention relates to a train suspension system failure isolation method based on an LDA method. The train suspension system failure isolation method is based on data feature extraction of the Fisher discriminatory analysis method and the application of the Fisher discriminatory analysis method in a train suspension system failure diagnosis. Diagnosis discrimination functions are obtained by collecting and training simulated normal data and all types of failure data so that new test data can be discriminated and diagnosed. According to the train suspension system failure isolation method based on the LDA method, a precise mathematical model is not required, and any requirement for overall distributed situations is not made; a large number of characteristic variables are reduced to several linear combinations, so that smaller dimensionalities are formed for convenient expression; meanwhile, a test unit is simple in structure and not prone to being interfered by external factors, and therefore the reliability of a device is high.

The battery pack is charged by an electronic equipment and communicates with the electronic equipment. The battery pack is provided with a discrimination resistor electrically connected to communication lines, and a controller having a discrimination function for electronic equipment judgment of battery pack type from communication via the communication lines. The electronic equipment has a discrimination function that determines battery pack type utilizing the discrimination section of the battery pack controller. In addition, the electronic equipment has a discrimination function that applies voltage to the discrimination resistor to determine battery pack type.

The invention discloses a disease diagnosis method for leaf vegetables. The method comprises the following steps: S1, denoising a leaf surface image of a leaf vegetable to obtain a first hue image of the leaf surface image of the leaf vegetable; S2, carrying out color characteristic extraction on the first hue image to obtain a characteristic information value and a second hue image of the leaf surface image of the leaf vegetable; S3, carrying out texture characteristic extraction on the second hue image to obtain a texture characteristic value of the second hue image; S4, calculating mean values of the texture characteristic values of all the pictures in a preset leaf vegetable disease picture base; S5, obtaining a disease threshold value point according to the mean values of the texture characteristic values; S6, diagnosing that the leaf vegetables of which the characteristic information values of the leaf surface images of the leaf vegetables are linearly relative are diseased leaf vegetables according to a preset discrimination function and the disease threshold value point. According to the disease diagnosis method for the leaf vegetables, the professional disease knowledge is better combined with a computer technology, so that the leaf vegetable diseases can be diagnosed by an image processing and mode identification technology more quickly and accurately.

The invention relates to the field of petroleum and gas exploration and development, in particular to a sandy beach and bar sedimentary microfacies logging identification method based on Bayes discriminant analysis. On the basis that bar sand and beach sand are identified through drilling core data and exploration and development data, parameters capable of reflecting sand body characteristics are extracted according to logging response characteristics of beach and bar sand bodies, beach and bar sedimentary microfacies response comprehensive parameters are established, parameters which do not have a remarkable effect on discrimination are removed through a stepwise discriminant analysis method, and finally a Bayes discrimination function capable of discriminating beach and bar sedimentary microfacies is established. The method achieves the purpose of beach and bar sedimentary microfacies prediction and identification of wells without drilling coring data. Physical geography logging data have the advantages of being relatively low in price and high in continuity, and have good response to sandy beach and bar sedimentary microfacies with different characteristics. Consequently, on the basis of calibration of the drilling core data and the exploration and development data, the logging response parameters capable of representing beach and bar sand body sedimentary microfacies characteristics are extracted, discriminant analysis is conducted on sandy beach and bar sedimentary microfacies through a statistical method, cost is low, and application value is high.

The invention discloses a building seismic damage analysis method, and relates to the field of seismic damage assessment. The method comprises the following steps of: setting a contour sampling interval, extracting a point cloud set of different height of a building, then, obtaining a contour section profile line through a convex hull algorithm, and converting three-dimensional point cloud of the building into a two-dimensional contour polygon sequence; extracting shape discrete parameters of the building; and calculating standard deviation of building shape parameters, and through a Fisher discriminant analysis, performing statistics on the standard deviation obtained in a step S22 or a step S23, thereby obtaining a discrimination function corresponding to three types of degree of damage of the building. According to the invention, edge extraction, shape clustering and discriminant analysis are fused, and problems in building contour polygon sequence extraction, shape discrete parameter calculation, irregular building block segmentation and damage analysis are solved effectively.

The invention provides a wire cut electric discharge machine with a machining state discrimination function. In a wire cut electric discharge machine, based on a voltage applied to a machining gap between a workpiece and a wire electrode, machining states are classified into at least three states of ''open'', ''discharge'', and ''short'' for each voltage application, and state discrimination signals corresponding to the respective states are respectively counted. Based on the counting results, an increase of a discharge gap, a reduction in a machining gap, retention of machining sludge, and so on are determined as machining states.

The invention discloses a structure and an application of a three-dimensional fluorescence standard spectrum library used for recognizing toxic-to-fish algae. The hemolytic activity and the change of the toxic-to-fish algae in different growing periods and under the control of environmental factors, and a chlorophyll three-dimensional fluorescence spectrum of the toxic-to-fish algae are researched and contrasted with a chlorophyll three-dimensional fluorescence spectrum of large sample nontoxic-to-fish algae, three-dimensional fluorescence spectrum analysis and recognition methods are screened, a fluorescence characteristic spectrum closely related to the toxic-to-fish algae and the hemolytic activity of the toxic-to-fish algae is extracted, and three-dimensional fluorescence standard spectrum libraries of the toxic-to-fish algae and the nontoxic-to-fish algae are screened by a clustering method; based on the three-dimensional fluorescence standard spectrum libraries, a Fisher discrimination function for recognizing the toxic-to-fish algae and a function for discriminating the degree of the hemolytic activity of the toxic-to-fish algae are established respectively. Discrimination results obtained by utilizing the discrimination functions are more stable, accuracy and reliable. The method provided by the invention realizes highly correct diagnosis and recognition functions for the toxic-to-fish algae in an in-place red tide water body and the hemolytic activity of the toxic-to-fish algae.

A glucose sensor system comprising the steps of using as a sample discriminating parameter a ratio (I / DELTA I) of a measured current value I to the time-differential value of the current value DELTA I, defining a discrimination function that discriminates whether a sample is blood or control fluid and uses the discriminating parameter as an independent variable, quantitating as a discriminating index a numeric value obtained by substituting a discriminating parameter value into this discrimination function, and automatically discriminating, based on this index, whether the sample is blood or a control fluid, whereby a kind of the sample can be automatically quantitated by measuring electric current when a sensor system is used for quantitating the concentration of an analysis object in the sample.

The invention discloses a music model training method. The music model training method comprises the following steps: acquiring a MIDI music data set, wherein the MIDI music data set comprises a plurality of MIDI music scores; extracting the feature vector of each MIDI music score; inputting the feature vectors into a structured support vector machine for training, so that a music model is obtained, the step specifically comprises the following substeps: constructing a discrimination function f(x;w), wherein x is a feature vector, w is a parameter vector, carrying out outputting by adopting the data value (with the calculation formula shown in the description) of the maximal discrimination function f(x;w) as the predicted value, calculating the predicted value and the true value accordingto a preset loss function (shown in the description), wherein P is the probability distribution of data, which is replaced with the empirical risk (shown in the description) obtained through calculation with the trained sample data, solving the unique parameter vector omega by adopting the optimizing formula (as shown in the description) of SVM, so that the empirical risk (shown in the description) obtained through the trained sample data is 0, solving the discrimination function f(x; omega), and finally, outputting the music time sequence. The invention further provides a music creation method, devices, a terminal and a storage medium. In the technical scheme, artificial intelligence is used for music model training for the first time, for the trained music model, the feature extraction capacity of the MIDI music score can be improved.

The invention discloses a correlation method for flight tracks of an airborne radar and an infrared sensor. According to the method, angle information observed by the airborne radar and the infrared sensor is fully utilized, wherein the angle information comprises an azimuth angle and a pitch angle. The correlation method comprises the steps of: on the basis of ambiguous comprehensive functions, establishing comprehensive discrimination functions by utilizing the observed information of the airborne radar and the infrared sensor; formulating a decision criterion; and finally determining judgment thresholds through counting characteristics and a correlation rate of the comprehensive judgment functions and then carrying out related judgment. The correlation method for the flight tracks of the airborne radar and the infrared sensor has the positive effect that on the basis of researching the sensor measurement origin uncertainty problem, by taking the airborne radar and the infrared sensor as examples, a driving / driven sensor flight track correlation method is disclosed on the basis of an ambiguous comprehensive theory; and the driving / driven sensor flight track correlation method not only can be used for solving the measurement origin uncertainty problem of multi-sensor observed information, but also can be applied to the flight track correlation problems related to multi-sensor multi-target tracking in the military or civil field.