51results about How to "Identification speed" patented technology

The invention provides a microblog rumor recognizing method and system based on propagation structures. The microblog rumor recognizing method includes the steps that according to the machine learning method of a support vector machine, feature data of information features, user features and propagation features of microblogs serves as data, a graph kernel function is calculated with a random walking method, and a support vector machine model is accordingly built in cooperation with a classical radial basis kernel function and used for recognizing rumor; each microblog is represented with a propagation tree and a feature vector, wherein the propagation trees are used for representing the propagation structures in the propagation features, and the dimensions of the feature vectors are the information features, the user features and the propagation features of non-propagation structures; when the microblogs are recognized, the to-be-recognized microblogs are classified through the support vector model built with a model building module, and whether the to-be-recognized microblogs are rumor or not is judged according to the classification result. According to the microblog rumor recognizing method and system, due to comparison of the propagation structures of microblog information, the microblog rumor identifying accuracy and the microblog rumor recalling rate can be greatly increased.

The invention belongs to the field of milk product analysis and particularly relates to a spectral fingerprint identification method for milk, mare milk, camel milk, goat milk and buffalo milk. The invention relates to the intermediate infrared spectroscopy. The method comprises the following steps: 1) taking fresh milk, mare milk, camel milk, goat milk and buffalo milk samples; 2) scanning the samples in a mid-red spectral range to obtain mid-infrared spectral data; 3) preprocessing original mid-infrared spectrum to remove abnormal values; 4) dividing the preprocessed data set into a trainingset and a test set according to a stratified sampling principle; 5) performing dimension reduction processing on the training set to improve the model training speed; 6) establishing a model for distinguishing milk, mare milk, camel milk, goat milk and buffalo milk through 10-fold cross validation by using algorithms such as nearest neighbors on the training set, and evaluating and screening themodel by using the use accuracy, the balance precision and the Kappa coefficient; and 7) estimating the generalization performance of the optimal model.

The invention provides a primer, a kit and a method for rapid identification of pigeon gender. The primer shown in the SEQ ID NO:1 and SEQ ID NO:2 has the advantages of high specificity, high accuracy, high resolution and the like in design of CHD gene sequence in pigeons; the amplification result is directly carried out by agarose gel electrohoresis, which provides higher identification so that the amplification result is intuitive and clear, and the pigeon gender can be easily distinguished. The invention further provides a molecular identification method of the pigeon gender by the aid of the primer. In the method, efficient nucleic acid lysate is further provided on the basis of the above the specific amplification of the primer, the process of obtaining DNA from feather pulp samples is greatly simplified, and time and economic cost in identification of the pigeon gender are reduced. The method and the kit for identification of pigeon gender with the PCR (polymerase chain reaction)-agarose electrophoresis technology and a genotyping method are simple in operation, rapid in identification, low in cost and abroad in the market utilization prospect.

The invention discloses a method for identifying a dendrobium officinale medicinal material based on near infrared spectroscopy. The method comprises the following steps: 1) acquisition and preparation of a dendrobium officinale sample; 2) acquisition of a near infrared spectroscopy of the dendrobium officinale sample; 4) selection of a best spectrum data pre-processing method; 4) selection of a best modeling spectrum scope; 5) establishment of a correction model for indentifying dendrobium officinale based on the near infrared spectroscopy data of dendrobium officinale; 6) evaluation of the performance of the correction model; and 7) acquisition and processing of the near infrared spectroscopy of the dendrobium officinale sample to be analyzed by the same method, and identification of the dendrobium officinale by using the correction model. The method has the advantages of reasonable design, strong operationality, fast identification speed, high identification accuracy, and no pollution for detection, and has important application value on quality control of the dendrobium officinale medicinal material and efficacy guarantee of the dendrobium officinale medicinal material.

The invention relates to a discrimination method of traditional Chinese medicine Xuezhining pill; wherein discrimination of anthraquinones active ingredients in the Xuezhining pill and / or discrimination of nunciferine in Xuezhining pill all adopt thin-layer chromatography. Chrysophanol and physcion thin-layer chromatography in the discrimination method adopts acid hydrolysis method, thus greatly improving thin-layer spot detection effect, being convenient for observation and discrimination and improving discrimination efficiency; lotus leaf thin-layer chromatography in the discrimination method adopts alkalinity developing solvent cyclohexane-ethyl acetate-concentrated ammonium liquid, developing speed can be effectively improved, and discrimination speed of the whole Xuezhining pill can be improved. Repetitive operation of hawthorn thin-layer discrimination method is cancelled in the discrimination method, so that the whole quality control method is optimized, quality control time isshortened, and quality control efficiency is improved. The discrimination method of the invention is simple and easy to operate, eliminates the interference in discrimination as prepared polygonum multiflorum and semen cassiae all contain anthraquinones and is rapid and accurate for discrimination of traditional Chinese medicine Xuezhining pill.

The invention discloses a rapid identification technique of new crop type in the agriculture domain, which is characterized by the following: adapting digital information technique to collect the plant image, SSR digital fingerprint of molecular mark and DUS field test property; identifying, counting and comparing to obtain the difference with the known type; judging whether the type is new; adjusting the sampling period and data log-in pattern; improving the identification speed and accuracy; avoiding error judgment and fault quality identification.

The invention discloses a method for rapidly identifying authenticity and quality of Cordyceps sinensis. The method comprises detecting samples by using an electronic nose and an electronic tongue, and analyzing and identifying the samples by using PCA and DFA analytical method to identify the authenticity and quality of Cordyceps sinensis. The method for rapidly identifying authenticity and quality of Cordyceps sinensis has high recognition rate and fast identification speed.

The invention belongs to the field of milk product analysis, and particularly relates to a methodfor quickly identifying milk and mare milk, which is relates to intermediate infrared spectroscopy. The method comprises the following steps: 1) taking fresh mare milk and milk samples; 2) scanning the samples in anintermediate infrared spectral range to obtain intermediate infrared spectral data; 3) preprocessing the original intermediate infrared spectrum to remove abnormal values; 4) dividing the preprocessed data set into a training set and a test set according to a stratified sampling principle; 5) performing dimension reduction processing on the training set to improve the model training speed; 6) on the training set, establishing a model for distinguishing mare's milk from milk through 10-fold cross validation by using algorithms such as a nearest neighbor algorithm, and evaluating and screening the model by using accuracy, specificity, sensitivity and AUC; and 7) estimating the generalization performance of the optimal model.

The invention discloses a breeding method for speckle-feather laying hens laying green-shell eggs. The breeding method comprises the following steps: firstly, hybridizing cocks of a low-feathering Rhode Island Red strain with Sussex hens to obtain F1-generation chicks, wherein hatched female chicks are red-feather female chicks, hatched male chicks are white-feather female chicks, and the red-feather female chicks are bred into adult hens; 2, mating fast-feathering speckle-feather cocks hatched by green-shell eggs with the F1-generation red-feather hens obtained in the step 1 to obtain F2-geneeration chicks, wherein the hatched male chicks are slow-feathering chicks, the hatched female chicks are fast-feathering chicks, and the adult female chicks are speckle-feather hens laying green-shell eggs. According to the production method, the egg laying quantity is greatly increased while the two characteristics, namely speckle feathers and laying of green-shell eggs are kept; finally, the female chicks and the male chicks are identified by means of the feathering speed, and thus the economic benefit of breeding the speckle-feather laying hens laying the green-shell eggs is increased.

The invention provides a cultivating method of a parent generation and commodity generation dual auto-sexing male and female meat chicken. According to the cultivating method, three pairs of sex-linkage traits of the chicken dark color shank and the chicken light color shank, the transverse spot feather and the non-transverse spot feather, the quick feather and the slow feather are utilized to design the parent genotype and the hybridization process, in the cultivating process, whether the chicken is male or female can be directly authenticated according to the phenotype of the commodity generation and the parent generation of the chicken, the authentication accuracy of the parent generation can reach up to 99.8%, and the authentication accuracy of the commodity generation can reach up to99.5%. The cultivating method is simple and easy to operate, training special authentication personnel is not needed, a large amount of cost is saved, the authentication speed and the accuracy are high, the chickens are not injured, and the survival rate of the chickens is increased.

The invention belongs to the field of milk product analysis, and particularly relates to a batch identification model and method for camel milk and mare milk. The invention relates to mid-infrared spectroscopy analysis. The method comprises the following steps: 1) taking fresh mare milk and camel milk samples; 2) scanning the samples in a mid-red spectral range to obtain mid-infrared spectral data; 3) preprocessing the original mid-infrared spectrum to remove abnormal values; 4) dividing the preprocessed data set into a training set and a test set according to a stratified sampling principle; 5) performing dimension reduction processing on the training set to improve the model training speed; 6) on the training set, establishing a model for distinguishing mare milk from camel milk through 10-fold cross validation by using algorithms such as nearest neighbors, and evaluating and screening the model by using accuracy, specificity, sensitivity and AUC; and 7) estimating the generalization performance of the optimal model.

The invention discloses an edible oil quality fast identification method and identification device based on the three-dimensional fluorescence spectrum. The identification device comprises a computer with a pre-stored edible oil database, a data acquiring card, a CCD image sensor, a cuvette, a monochrometer, a focusing lens, a control circuit and a xenon lamp, the structure is simple and the connection is convenient; and a light signal emitted by the xenon lamp is divided into monochromatic light through the monochrometer, and then the monochromatic light is emitted to the cuvette with a to-be-tested oil sample to motivate the to-be-tested oil sample to emit the fluorescence, the fluorescence is received by the CCD image sensor after being collected by the focusing lens, and then the data acquiring card is used for composing the obtained fluorescence spectrum as a matrix array to be transmitted to the computer, the computer is used for contrastively analyzing the data and the edible oil database to obtain a result. The identification method is simple, the identification speed is fast, the identification accuracy is high, and the specificity is strong.

The invention discloses a Raman spectrum discriminating method of natural dyeing silk fabrics, and comprises the following steps: (1) indigo dyeing: a natural indigo dye is adopted to dye silk fabrics with a reduction dyeing method, and a sample 1, a sample 2, and a sample 3 are obtained; (2) a copper coin substrate is prepared; (3) UV aging: the sample 2 and sample 3 are placed in a UV aging test machine for aging for a period of time; and (4) Raman spectrum test: the substrate is placed on a Fourier infrared Raman spectrometer, then the sample 1, sample 2, sample 3 are placed in batches in the Fourier infrared Raman spectrometer to acquire Raman spectrums. In the invention, non-invasive Raman spectrum technology is adopted for performing characterization test for natural indigo dyed silk fabrics and synthetic indigo dyed silk fabrics, and achieves the goal for quickly discriminating the fabrics, and has a significance in food development, fabric dyeing and discrimination and maintenance for ancient textiles.

The invention relates to a multiple PCR (Polymerase Chain Reaction) kit for quickly identifying plant hopper species and an identifying method thereof, which belong to the technical field of molecularbiology identification. The kit comprises (1) three upstream primers and three downstream primers; (2) a positive control recombinant plasmid template; (3) a PCR reaction fluid. According to the multiple PCR kit for quickly identifying the plant hopper species and the identifying method thereof, on the basis of aiming at an ITS sequence of three plant hoppers and verifying the ITS area sequence,a primer pair and a matching ratio are designed and optimized, and a coarse tissure sample is used as a template, so that the time and the reagent consumed for extracting DNA are saved, the multiple PCR kit for quickly, accurately, sensitively, high-throughput and low-cost identifying the three plant hoppers and the identifying method are built, and options are provided for identifying brown planthoppers, imitated brown planthoppers and fake brown planthoppers through a molecular biology method.

According to the invention, a laser technology is adopted to carry out distance measurement on a biological form to generate initial multi-dimensional animal and plant harmful biological form contourpoint cloud data; the method comprises steps of 'denoising' the initial multi-dimensional animal and plant harmful organism form contour point cloud data; reconstructing accurate multi-dimensional animal and plant harmful organism form contour point cloud data, and splitting the accurate multi-dimensional animal and plant harmful organism form contour point cloud data to obtain local form featurepoint cloud data for distinguishing animal and plant harmful organisms based on a harmful organism retrieval table; comparing with a corresponding morphological characteristic standard point cloud database in a pre-trained pest retrieval table, and performing classified retrieval to determine animal and plant pest species. According to the method, the multi-dimensional forming time of the biological sample is greatly shortened, and the Fresnel adding efficiency is improved; and moreover, the method has a memory capability, and the higher the use frequency is, the higher the identification speed is, and the higher the accuracy is.

The invention discloses a quality detection method of Shen Kui vein-dredging granules. According to the method, contents of calycosin-7-glucoside, salvianolic acid B and icariin are detected by HPLC,and radix astragali preparata, radix salviae miltiorrhizae, herba epimedii and pericarpium citri reticulatae are detected by thin-layer chromatography. The provided quality detection method is reasonable in technical design and high in operability, an optimal extraction technology of the Shen Kui vein-dredging granules is screened by a lot of experiments, and an optimal content determination method including liquidity composition, gradient system conditions is screened by a lot of experiments; and the optimal thin-layer chromatography is obtained by screening. The method of the invention is high in identification speed and accuracy, can comprehensively control the quality of the Shen Kui vein-dredging granules, and has significance in guaranteeing the quality of the Shen Kui vein-dredginggranules.

The invention provides a method for intelligently identifying industrial waste gas pollution sources, and relates to the technical field of waste gas identification. The method comprises the followingsteps of collecting of an industrial waste gas sample, selecting of proper sample feeding time, collection of electronic nose data, analyzing of principal components in all waste gas, analyzing of principal components in waste gas samples of different industries, determining of a principal component analysis model for intelligent identification or not, analyzing of judgment factors of waste gas samples of different industries, and verification of waste gas of target emission source. The method has the characteristics that the identification accuracy is high, the application range is broad, the operation is simple, and the identification speed is quick.

The invention discloses a primer and a method for identifying pseudosciaena crocea of daiqu species and min-yuedong species. The primer is characterized in that primer sequences are a primer pair J1 of 5-GGCATTTAGGCACAAGGAC-3 and 5-GGGGGCACAACTCAGAGG-3 and a primer J2 of 5-CAGGCCCCACCATACTAGT-3 and 5-GGGTGCCGGTTCCTGAC-3. The method for identifying specifically comprises the following steps: extracting pseudosciaena crocea total deoxyribose nucleic acid (DNA) and quantitatively detecting; preparing a polymerase chain reaction (PCR) amplification system and carrying out amplification reaction; finally, carrying out agarose gel electrophoresis detection on a product, if bands within the ranges of 300-400bp and 600-700bp of a map appear, determining that the DNA sample is obtained from pseudosciaena crocea of daiqu species; and if not, determining that the DNA sample is obtained from pseudosciaena crocea of min-yuedong species. The method has the advantages of high stability, good repeatability, quick identification speed, low false positive rate and the like.

The present disclosure is directed to identifying shapes in an image. For example, a shape identification system may identify an unknown shape represented by a Bézier path that has at least one Bézier curve. The shape identification system may also identify a stored Bézier path that has at least one stored Bézier curve, for example, in a database of known shapes. Using the Bézier curve of the unknown shape and the stored Bézier curve of the known shape, the shape identification system can determine a transformation matrix that transforms the transforms the Bézier curve of unknown shape to the stored Bézier curve of the known shape. Then, the shape identification system can compare the transformed Bézier curve to the stored Bézier curve to determine whether the unknown shape matches the known shape.

The invention belongs to the field of milk product analysis, and particularly relates to a method for identifying buffalo milk and mare milk by utilizing a spectrum, which is related to mid-infrared spectroscopy. The method comprises the following steps: 1) taking fresh mare milk and buffalo milk samples; 2) scanning the samples in a mid-red spectral range to obtain mid-infrared spectral data; 3) preprocessing the original mid-infrared spectrum to remove abnormal values; 4) dividing the preprocessed data set into a training set and a test set according to a stratified sampling principle; 5) performing dimension reduction processing on the training set to improve the model training speed; 6) establishing a model for distinguishing mare milk from buffalo milk through 10-fold cross validation by using algorithms such as nearest neighbors on the training set, and evaluating and screening the model by using accuracy, specificity, sensitivity and AUC; and 7) estimating the generalization performance of the optimal model.

The invention belongs to the field of dairy cow performance determination and milk quality detection, and discloses an intermediate infrared rapid batch detection method for alpha s1-casein in milk. According to the intermediate infrared rapid batch detection method, on the basis of data obtained by an infrared spectrometer in original Fourier transform, wave bands with much noise and less effective information are removed, manual dimension reduction is carried out, and the intermediate infrared rapid batch detection method for the alpha s1-casein in the milk is finally obtained by preprocessing spectral data through using an SG convolution first-order derivative, extracting intermediate infrared spectral characteristic variables through a competitive adaptive reweighting method, and constructing a regression model by using training set data through a support vector machine regression algorithm. The intermediate infrared rapid batch detection method has the advantages of high identification speed, high precision, low cost, simplicity in operation, batch detection, high practicability and the like, and is suitable for large-scale popularization.

The invention discloses a method for identifying tea oil based on a 3D fluorescence spectrum technology. The method comprises the following steps of detecting the three-dimensional fluorescence (3D fluorescence spectrum) of the to-be-detected sample oil subjected to extraction treatment or adsorption treatment under the spectrum conditions that the excitation wavelength is 250-500 nm, the emission wavelength is 300-600 nm, the slit width is 2-10 nm and the step diameter is 2-10 nm by adopting a fluorospectro photometer; if the three-dimensional fluorescence excited and emitted by the tea oil characteristics exists, showing that the tea oil is pure and is not adulterated; and if showing the overall three-dimensional fluorescence spectrum morphology, the characteristic spectrum peak and the fluorescence intensity different from those of the pure tea oil, indicating that the tea oil is doped with other oil products. The identification method disclosed by the invention is simple, high in identification speed, high in identification accuracy and strong in specificity, and provides reliable technical guarantee for the tea oil safety and the advanced food oil industry authentic identification.

The invention aims to solve the current problem of feather color auto-sexing of new meat goose breeding lines or complete set lines in the goose industry and provide a breeding method for auto-sexingmale and female gooses. The breeding method comprises the steps of screening of maple male gooses, propagation expanding of mutant groups, breeding of pure male and female parent lines and establishment of complete set lines. By adopting the method, stress and injury to young gooses are greatly decreased, prevention and control of infectious diseases of gooses are facilitated, and lots of cost forthe link of manually turning anus to distinguish male and female young gooses is saved.

The invention belongs to the technical field of dairy product analysis and particularly relates to a spectrum grading method for excellent high-quality milk, high-protein special milk, high-cream special milk and common milk. The method is related to the field of mid-infrared spectrum analysis. The method is characterized in that the optimal modeling wave band is the wave band of 925-1597 cm<-1> and the optimal modeling wave band of 1712-3024 cm<-1>; the method comprises the following steps of (1) taking a milk sample to be detected as a detection sample; (2) collecting mid-infrared spectrum data; (3) selecting a spectral band; (4) preprocessing the original mid-infrared spectrum data; (5) extracting a mid-infrared spectrum characteristic wavelength; (6) predicting samples in the test set by using the model; (7) comparing and evaluating the model; and (8) through comparative analysis, selecting an optimal grading model. The method is advantaged in that the model is established by utilizing the characteristic variable combination, so the model is simplified, and model precision and the detection speed are improved.

The invention provides a vision-based chick male and female intelligent identification method and system, and the method comprises the steps: obtaining and collecting a plurality of images at the anus of a chick through an optical imaging module, and forming a chick male and female image data set; enabling the chick male and female identification module to identify the network model according to the chick male and female image data set and then perform multi-task model learning according to the basic identification network model to obtain N chick male and female identification models for N chicken breeds; enabling the optical imaging module to collect an image of the anus of a to-be-detected chick and inputting the image into the chick male and female identification module, and enabling the chick male and female identification module to judge and output a male and female result according to the chick male and female identification model of the corresponding chicken breed. The method and system have the advantages that the male and female chicks are distinguished through the identification model, the human eye distinguishing function is replaced, and the human eyes are liberated; the accuracy is improved, the labor cost is reduced, and the working efficiency is greatly improved.

The invention provides a virtual reality discriminator, a virtual reality discrimination method and application of the virtual reality discrimination method. A detection signal transmitting device, adetection signal receiving device, a microprocessor and a display screen are combined to identify virtual reality. A user can compare a map image on a display screen and a real environment to determine whether the to-be-identified target is real reality (the image is consistent with the to-be-identified target) or virtual reality (the image is inconsistent with the to-be-identified target), the identification process is simple and fast, the accuracy is high, it is guaranteed that a user is not shielded or deceived by the virtual reality before eyes, and injuries of people, money, objects and the like are avoided.

The invention relates to the field of drug analysis, in particular to a sequence analysis method and an identification method of insulin or analogues thereof. An appropriate disulfide bond reduction method is adopted, an insulin double-chain structure is reduced into two independent peptide chains, and the most abundant mass spectrum fragment information is obtained through liquid chromatography separation, high-resolution tandem mass spectrometry analysis and appropriate secondary mass spectrum collision energy and is matched with a theoretical sequence, so that the 100% sequence coverage rate is obtained; and a powerful technical support is provided for quality control and counterfeiting work of insulin.

The invention belongs to the field of milk product analysis, and particularly relates to a spectral identification model and method for milk and goat milk, which are related to intermediate infrared spectroscopy. The method comprises the following steps: 1) taking a fresh goat milk sample and a fresh milk sample; 2) scanning the samples in a intermediate infrared spectral range to obtain mid-infrared spectral data; 3) preprocessing the original mid-infrared spectrum to remove abnormal values; 4) dividing the preprocessed data set into a training set and a test set according to a stratified sampling principle; 5) performing dimension reduction processing on the training set to improve the model training speed; 6) on the training set, establishing a model for distinguishing mare's milk from milk through 10-fold cross validation by using algorithms such as nearest neighbors, and evaluating and screening the model by using accuracy, specificity, sensitivity and AUC; and 7) estimating the generalization performance of the optimal model.

The invention discloses a cotton and linen blend fiber morphological characteristic identification system. The system comprises a fiber sample acquisition module used for acquiring a fiber sample, a fiber edge cutting module which is used for carrying out fiber edge detection on each fiber sample to obtain a fiber area, a single fiber segmentation module which is used for segmenting a plurality offibers in each fiber area, a fiber quantity counting module which is used for counting the fiber quantity, a fiber quantity up-to-standard judgment module which is used for judging whether the fiberquantity reaches the standard or not, a fiber posture adjusting module which is used for adjusting the fiber posture of each fiber to be a preset reasonable posture, a fiber category judging module which is used for judging the fiber category of each fiber, and a cotton and linen blended fiber classification result output module which is used for outputting a fiber type judgment result. The fibertype judgment result made by the system is more objective, scientific and accurate, and the identification speed is greatly improved. The invention further provides a cotton and linen blend fiber morphological characteristic identification method.