379results about How to "Improve classification efficiency" patented technology

The invention discloses a method and a system for detecting a Chinese phishing website. The method comprises the following steps: S1, acquiring a URL (Uniform Resource Locator) by a client; S2, extracting URL features and website page content features as feature vectors respectively; S3, performing classification trainings on the feature vectors through an SVM (Support Vector Machine), an extended website page content feature NBC (Naive Bayes Classifier), a decision tree algorithm and a link and form processing method; S4, performing classification integration on classification training results, and judging whether a website with the URL is a phishing website. According to the method and the system, the URL features and the website page content features are extracted as the feature vectors, the corresponding classification trainings are performed through the SVM, the NBC, the decision tree algorithm and the corresponding processing of links and forms, prediction results are integrated by virtue of classification integration to obtain a final result, and therefore the classification accuracy is greatly improved.

The invention discloses a network security accident classification and predicting method and a system, which are used for solving the problems of the prior art on lacking the capability of timely finding the characteristics of attack behaviors and accurately classifying the attack behaviors. The method comprises the following steps: S1. acquiring web access log of users in a whole network and http metadata in full-flow log; S2. segmenting the web access log and the url of the http metadata, and matching with a network attach illegal character feature library; S3. constructing a word vector and a document vector of the segmented url by utilizing word2vector; and S4. inputting the document vector as a feature and classifying the attack behavior by adopting a naive bayes model. The real-time monitoring of key points can be realized, the abnormal behavior carrying mainstream attack feature can be found by means of machine learning, the classification efficiency of network attack behaviors can be improved, and the time cost of manual check can be lowered, continuously changed attack behaviors can be adapted, and the classification detection accuracy can be enhanced, thus providing guarantee for network security.

The invention discloses an advertisement classification method and system based on a webpage characteristic. The method comprises the following steps of: extracting the webpage characteristic information from the webpage sample information and extracting the advertisement characteristic information from the advertisement sample information; mapping the webpage characteristic information and the advertisement characteristic information to a common characteristic space by use of a transfer learning method to obtain the webpage sample information and advertisement sample information mapped to the common characteristic space; training a classifier based on the webpage sample information mapped to the common characteristic space and a current training set, and classifying the advertisement sample information according to the trained classifier to obtain a classification result; establishing a link network between the webpage and the advertisement according to the historical release and click data of the advertisement sample information so that the classification result is transmitted along the link network and the corrected classification result is obtained; and updating the training set according to the corrected classification result. Through the invention, existing mark data can be sufficiently utilized, and a large amount of repeated work is avoided.

The invention belongs to the technical field of image processing, discloses a method for identifying and positioning power transmission line insulators in unmanned aerial vehicle aerial images, and solves the problems in the prior art that the detection precision of an identification algorithm of the insulators is not high, the robustness is low, and the identification algorithm is easy to be affected by sample number. A group of Gabor wavelet basis with different sizes and different directions and training sample images are taken as convolutions so as to form a group of characteristic vectors which accurately describe sample image texture characteristics. A random forest machine learning algorithm with a semi-supervised learning mode is used to train sample data sets of the known category and the unknown category so as to obtain an insulator identification model. Through the mode from left to right and from top to bottom, a detection window with the same size as the training sample traverses the input images with different sizes. The detection window combining the identification model detects and positions the positions of the insulators in the input images with different sizes. And finally the accurate positions of the insulators in the input image with the original size are determined by using a non-maximum inhibition method.

The invention discloses a sorting method and system for active learning. The sorting method comprises the following steps: firstly sorting all samples with relatively high uncertainty from original unmarked samples in a concentrated manner so as to obtain a most uncertain sample set; then dividing the most uncertain sample set into h different clusters by utilizing the similarity among the samples, dividing the samples with the relatively high similarity into the same cluster, and screening out most representative samples in each cluster to form the most representative sample set; and subsequently, carrying out information marking on the most representative sample set, and finally realizing the sorting of target objects by utilizing a marked sample train sorter and a trained analyzer. Therefore, the sorting method and system disclosed by the invention has the advantages that by clustering, the similar and relatively-high-redundancy samples are divided into the same type, and the screening is carried out on the basis of the clustering, so that the redundancy among the finally-selected samples to be marked is avoided, the marking time and workload are reduced and the sorting efficiency is improved.

Disclosed are a method and a system for coal and rock boundary dividing based on coal and rock image feature extraction and classification and recognition. The method includes firstly, photographing coal and rock images on a coal mining working face, extracting texture feature information of the coal and rock images, and constructing a feature vector, wherein the texture feature information comprises the original images and the angular second moment, the contrast, the correlation, the mean value and the variance of every low-frequency coefficient image with Daubechies wavelet decomposition scale, and the texture feature information also comprises the total mean value and the total variance for calculating high-frequency coefficient images in horizontal, vertical and diagonal directions; and lastly, creating a best classifier to recognize the coal and rock boundary. The system comprises an image acquisition module, a feature module, a classification and recognition module, a result display interactive module, a memory module and a central control module. The method and the system for the coal and rock boundary dividing based on the coal and rock image feature extraction and the classification and recognition have simple calculation, less human intervention and low cost, can improve classification accuracy and efficiency of the coal and rock images in complex environments effectively, and provides accurate and reliable coal and rock boundary information.

The invention discloses an UAV onboard multi-target detection tracking and indication system and method, and belongs to the technical field of target detection tracking and indication. The invention discloses an UAV onboard multi-target detection tracking and indication system comprising a multi-target detection and tracking system and a multi-target laser indication system. The multi-target detection and tracking system comprises an infrared camera, a visible light image sensor and a high-speed parallel image processing and tracking feedback control circuit. The multi-target indication systemincludes an integrated laser, a fast reflector, a fast reflector control module, and a laser control module. In order to improve laser indication accuracy, the UAV onboard multi-target detection tracking and indication system also includes a laser pointing control system. The invention also discloses an UAV onboard multi-target detection tracking and indication method based on the UAV onboard multi-target detection tracking and indication system. The UAV onboard multi-target detection tracking and indication system and method realize multi-target all-weather detection tracking and high-precision stable laser indication under the condition of a UAV onboard platform.

The invention relates to the technical field of image processing, in particular to an image classification method and device, a storage medium and terminal equipment. The image classification method provided by the invention comprises the following steps: obtaining a to-be-classified image; inputting the to-be-classified image into a trained image classification model to obtain an image label output by the image classification model, wherein the image classification model comprises a teacher model and a student model, and the teacher model is a convolutional neural network model obtained by carrying out weak supervision training by utilizing noise data and non-noise data, and the student model is a model obtained by carrying out joint training according to a knowledge migration mechanism and a multi-task learning mechanism based on the teacher model; obtaining a classification result corresponding to the to-be-classified image according to the image label, using the teacher model to perform knowledge migration, and using the noise data and the non-noise data to perform multi-task learning training, thereby improving the classification efficiency and the classification accuracy of the image classification model.

The invention relates to a method for carrying out mangrove forest map making on intermediate resolution remote sensing image by utilizing object-oriented classification method, which relates to a method for mangrove forest map making and solves the problems of time and labor waste, bad timeliness and serious neglected and wrong classification of mangrove forest in positioning and map making of mangrove forest map making through conventional means at present. The method comprises the following steps: firstly, carrying out ortho-rectification and geometric exact correction on Landsat TM data so as to obtain Landsat TM images after registration; secondly, carrying out multi-layered multi-dimensioned division on the Landsat TM images after registration, wherein each division unit is used as an object; thirdly, extracting textural and topological characteristics, and calculating normalized vegetation index and ground surface humidity index; fourthly, removing a non-vegetated object so as to obtain a vegetated object; fifthly, extracting a mangrove forest object from the vegetated object; sixthly, exporting the mangrove forest object so as to generate a mangrove forest vector; and seventhly, manufacturing a mangrove forest thematic map. The method disclosed by the invention is used for mangrove forest map making.

The invention provides a method for classifying supervised waveforms in a three-dimensional seismic signal. The method mainly includes the steps of data preprocessing, feature selection and classified identification. The method has the advantages that the method is based on three-dimensional seismic signal resources and well logging data information, extracted attributive characters are optimized through a genetic algorithm, analyzed three-dimensional seismic target interval data undergoes waveform classification by means of an SVM classification algorithm, different seismic facies are recognized, and therefore reliable supports are provided for follow-up seismic resource explanation, and reliability of lithology prediction, sand body prediction, fractured reservoir prediction, elusive reservoir prediction and the like is improved. Compared with an SVM design classifier, the method carries out feature selection through addition of the genetic algorithm, design complexity of the SVM classifier is reduced, and therefore waveform classification processing efficiency is improved.

The invention discloses a method for recognizing and classifying road barriers based on video. According to the method for recognizing and classifying the road barriers based on the video, according to the urban road monitoring video, a barrier feature extraction and recognition algorithm is studied, a hybrid Gaussian modeling method self-adaptive to background update is provided, and the road background is updated selectively according to static barrier targets obtained through detection; a moving target segmentation method based on concave-convex outline characteristics of the targets is provided, further accurate extraction and separation of the moving targets are achieved through the method, and a foundation is laid for outline-based segmentation of a blocked target; an algorithm for automatic detection of an ROI of a road is provided, and automatic extraction of the ROI of the road in a monitoring image is achieved. A road barrier classifying method involving self-adaptive clipping of the ROI is adopted, road barriers are recognized and classified to be illegally parked vehicles and scattered objects. By the adoption of the method for recognizing and classifying the road barriers based on the video, the barrier handling efficiency of the traffic department can be improved easily, and a foundation is laid for preventing road accidents.

The invention discloses an automatic classifying method of flow cytometry and a relative device, which comprises A1, according to at least two paths of light signal generated by one-by-one passing collected each cell or particle through illuminated region, representing each cell or particle into one vector with at least two dimensions and relation with the light signal strength of each path, B1, calculating two-two distances of all effective cells or particles, while the similarity of two cells or particles is higher along with the distance reduction, C1, aggregating the cells or particles with high similarity into one class, D1, repeating the step C1, at least aggregating all effective cells or particles into classes not lower than L according to the measurement theory. The invention canaccurately, effectively and automatically classify particles.

The invention discloses a remote sensing image classification method based on active deep learning. The remote sensing image classification method includes the steps that (1), remote sensing image data to be classified are selected; (2), the remote sensing image data are processed by utilizing an algorithm configured in advance; (3), the optimal sample B is selected from unmarked samples U by applying the active learning algorithm nEQB; (4), the optimal sample B is subtracted from the unmarked samples U to obtain a new unmarked sample set U', and the optimal sample B is added to marked samples L to obtain a new marked sample set L'; (5), the step (2) is executed again, the process continues to be circulated, the circulation is completed until the unmarked sample set U'is a null set or a preset learning stopping index is met, and classification accuracy and a classification result graph matched with the classification accuracy are output. The remote sensing image classification method has the advantages that through deep learning and active learning, the defects caused by using unsupervised learning and supervised learning can be overcome, and the classification accuracy of the data is effectively improved.

The invention discloses a preparation technology of super pure coal, and is applicable to the technical field of mineral separation. The preparation technology comprises the steps that after minus 50 mm low-ash anthracite is crushed through a high-efficiency fine crusher, the crushed low-ash anthracite is introduced into a three-product interference bed for separation, and coarse clean coal, medium coal and recrement are obtained; coarse clean coal is classified through a three-product vortex sieve, and coarse clean coal remaining on the sieve is dehydrated through a coal slime centrifuge to obtain a coarse-particle super pure coal product; and after primary coarse grinding, medium coal is introduced into a sieve bend for classification, oversize material on the sieve bend is introduced into a spiral separator for tailing discharging, and after secondary fine grinding, a light product is introduced into a flotation device for flotation together with screen underflows of the three-product vortex sieve, overflows, the centrifugate of the coal slime centrifuge, and screen underflows of the sieve bend, and a fine-particle super pure coal product is obtained. According to the preparation technology, a two-stage ore grinding technology is adopted, so that an overgrinding phenomenon which often occurs during open-circuit grinding is avoided; tailings are discharged during primary ore grinding, so that efficiency and energy consumption are achieved; the two-stage floatation is adopted, so that low-ash clean coal can be obtained; and compared with a traditional separation technology, the preparation technology has the advantages that the principle of more crushing and less grinding is better met, efficiency and energy consumption are achieved, and the economic benefits are remarkable.

The invention discloses an audio classification method, device and a computer readable storage medium, and belongs to the technical field of electronics. The method comprises: collecting an audio signal; intercepting or supplementing the audio signal to adjust the duration of the audio signal to a preset duration; converting the audio signal to a target audio according to the frequency informationof the audio signal; extracting audio features of the target audio through a convolutional network contained in a preset classifier; extracting time-order features of the audio features through a threshold circulation network contained in the preset classifier; and determining a probability that a category of the target audio is a preset category identified by each of multiple preset category identifiers through a fully-connected network contained in the preset classifier according to the time-order features; and determining the preset category identified by a preset category identifier having the highest probability among the multiple preset category identifiers as the category of the target audio. With the adoption of the method, segmentation of the target audio is avoided, the integrity of the target audio is preserved, and the classification accuracy is relatively high.

The invention discloses a fruit near infrared spectrum sorting method based on fuzzy clustering. The fruit near infrared spectrum sorting method based on the fuzzy clustering comprises the steps of carrying out dimension reduction processing of characteristic sequencing on a near infrared spectrum of a fruit sample, and extracting identification information of the near infrared spectrum data processed by the dimensionality reduction with a characteristic extraction method, and sorting the quality of the fruits by a rapid fuzzy clustering method. The fruit near infrared spectrum sorting method has the advantages of high detection speed, high sorting accuracy, high sorting efficiency, no damages on fruits, and the like, and can realize the assortment of one kind of fruits with different inner quality and the assortment of different kinds of fruits in the same category.

The invention discloses a garbage classification and recognition method based on artificial intelligence, and relates to the technical field of image processing. The method comprises: establishing a data set, and preprocessing junk pictures in the data set; forming a garbage classification model by a convolutional deep neural network, and training the garbage classification model by using the dataset preprocessed in the step; preprocessing junk photos to be classified, inputting the preprocessed junk photos into the trained junk classification model, and outputting a classification result. According to the method, the garbage image set is trained through the established deep neural network to complete establishment of the garbage recognition model, the thrown garbage is accurately recognized through the established garbage recognition model, the garbage classification efficiency of a user can be improved, and time and cost are saved.

A method for classifying enterprise domains and screening enterprise keywords is disclosed by the invention. The method obtains the feature words of the related fields through training the enterprisedomain corpus as a classification dictionary, and then uses the classification dictionary to classify the enterprise profile documents. After classification, the method can also extract the industry label representing the enterprise domain from the enterprise profile documents. In addition, the method can overcome the influence of most noisy words in Chinese text processing, and has low error rate, high classification efficiency and excellent comprehensive performance.

The invention relates to an Alzheimer's disease multi-classification diagnosis system based on deep study. The Alzheimer's disease multi-classification diagnosis system comprises an image characteristic extracting module, an index characteristic selecting module, a vector linear merging module and a disease classification and diagnosis module, wherein the image characteristic extracting module is used for extracting characteristic vectors of a cerebral three-orthogonal plane MRI image according to a neural network model; the index characteristic selecting module is used for selecting checking indexes according to medical pertinent literatures to form index characteristic vectors; the vector linear merging module is used for adopting a multivariate data linear merging method based on canonical correlation analysis to merge the characteristic vectors of the image and the index characteristic vectors; and the disease classification and diagnosis module is used for inputting the merged vectors to a multi-classification classifier to distinguish the three stages of the Alzheimer's disease. The Alzheimer's disease multi-classification diagnosis system disclosed by the invention can assist the multi-classification diagnosis of the Alzheimer's disease.

The present invention provides a coin sorting device, which comprises a bearing platform (2), a coin separating and extracting mechanism, a sensor, a coin transmission mechanism, a coin collecting mechanism and a control system. The coin separating and extracting mechanism is mounted on the bearing platform (2). The coin transmission mechanism and the coin collecting mechanism are sequentially arranged on the downstream of the coin separating and extracting mechanism. The sensor is located on the circumferential part of the transmission mechanism. In combination with the classification information fed back by the sensor, the control system respectively sends a control instruction to the coin separating and extracting mechanism, the coin transmission mechanism and the coin collecting mechanism to complete the coin separating operation, the coin transmitting operation and the coin collecting operation. According to the technical scheme of the invention, the traditional manner that banknotes must be manually put and sorted one by one for multiple times is replaced by the above process. Therefore, the banknote sorting efficiency is improved when a larger number of banknotes are to be sorted. Moreover, the coin sorting device is simple in overall structure, easy to install and debug, and strong in applicability.

The invention discloses a motor imagery electroencephalogram signal classification method based on deep learning, and belongs to the technical field of mode recognition and brain-computer interfaces.The method comprises the following steps: analyzing and preprocessing electroencephalogram signals, carrying out two-dimensional conversion on the electroencephalogram signals, and constructing a convolutional neural model of motor imagery electroencephalogram signal classification; and training the neural network to obtain a motor imagery electroencephalogram signal classification model, and carrying out test and performance evaluation on the model. Compared with the prior art, the method has the advantages that the data of each time point are used as samples, 2D conversion and deep learningmethods are carried out, the classification accuracy of the motor imagery electroencephalogram signals is improved, and meanwhile the classification instantaneity and stability are improved.

The invention discloses an intelligent logistics classification system. The intelligent logistics classification system comprises a first conveyor belt, a first motor and a rotary table. The feed end and the discharge end of the first conveyor belt are provided with a first support and a third support correspondingly. The upper end of the first support is provided with an opposite-type photoelectric sensor, and the upper end of the third support is provided with a bar code scanner. A second conveyor belt is arranged on the rotary table. The discharge end of the second conveyor belt and the discharge end of the first conveyor belt are connected in a matched mode. A second support is arranged at one end of the second conveyor belt. The top end of the second support is provided with a reflective photoelectric sensor. A collection barrel is arranged below the discharge end of the second conveyor belt. A magnetic sensor is further arranged on the upper surface of a shell on a base and is used for positioning the rotary table. The sensors and the bar code scanner are all electrically connected with a PLC host. The intelligent logistics classification system can achieve intelligent classification of different types of packages, avoids the error probability to the maximum extent, improves the logistics classification efficiency, reduces the amount of labor of staff and is suitable for being extensively popularized.

Provided are a screening method and system for a fundus image of glaucoma based on deep learning. The screening method comprises the steps that the fundus image to be identified is acquired; an FCN model is extracted through an optic disk to position and cut the optic disk, and optic disk sub-images are extracted and obtained; the optic disk sub-images are identified through a classification CNN model, and a classification result of the fundus image of glaucoma is obtained. According to the screening method and system for the fundus image of the glaucoma based on deep learning, identificationis only conducted on the cut and extracted optic disk, so that information processing amount is reduced, and the screening method and system can assist a doctor in improving the detection efficiency of glaucoma.

The present application provides a text classification method and device, wherein, the method comprises the following steps: acquiring text information of a user; inputting the text information into apre-trained local information classification model to generate a first probability value of each of the tags corresponding to the text information; inputting the text information into a pre-trained global information classification model to generate a second probability value of each of the tags corresponding to the text information; and determining at least one tag corresponding to the text information based on the first probability value and the second probability value. Embodiments of the present application determine the at least one tag corresponding to the text information by inputtingthe obtained text information of the user into different classification models, so as to realize classification of the text information.

The present invention provides a gas-solids fluidization coupling equipment. It at least includes an one-stage gas-solids fluidized bed body, said fluidized bed body is a vertically-placed cylinder body. Said invention also provides the concrete structure of said gas-solids fluidized bed body. Besides, said invention also provides a coupling method capable of utilizing said equipment to implement multistage mixing, heat exchange, reaction and classification of granules with large difference.

The invention belongs to the technical field of metal corrosion morphology grade judgment, and discloses a corrosion grade information processing method and system based on image recognition, and themethod comprises the steps: obtaining a labeled laboratory metal morphology picture as a data set; carrying out the de-duplication on the obtained training data set, randomly selecting a half of images of each category as a test set, and taking other images as training set images; expanding the training data set, namely carrying out the data enhancement; building a convolutional neural network model by using a Keras framework, carrying out model training, and storing optimal model parameters; and analyzing the grade of the corrosion morphology of the metal surface by utilizing the trained optimal model. According to the method, the judgment of the metal corrosion morphology grade is realized by using a computer vision technology, so the judgment efficiency is greatly improved and the judgment uniformity and objectivity are ensured under the condition of ensuring the judgment accuracy. The method can assist engineers engaged in material research in judging the metal corrosion grade, andvarious difficulties of a previous judgment method are solved.

The invention provides a mineral separation process and system for an ultra-lean magnetite ore. The mineral separation process for the ultra-lean magnetite ore comprises the following steps of sequentially carrying out coarse crushing, intermediate crushing and fine crushing on a raw magnetite ore to obtain a fine-particle ore; carrying out dry magnetic separation on the fine-particle ore, and throwing tailings to obtain a dry concentrate; and carrying out wet grinding and separation on the dry concentrate. The dry pre-separation step is additionally arranged in the mineral separation process, so that the technical problems of high ore grinding and magnetic separation energy consumption, high cost, high mineral separation water consumption, tailing pond construction and the like are solved.

One or more embodiments of the invention provide an image classification method and device, and the method comprises the steps: building a residual network model, replacing a standard convolution in an original side diameter of the residual network model with a cavity convolution, and generating a cavity residual network trunk; generating a weight layer of the residual error network model based ona channel attention module and a space attention module of an attention mechanism model; generating a residual attention mechanism model composed of the cavity residual network trunk and the weight layer, and training the residual attention mechanism model; and inputting image data into the residual attention mechanism model, and identifying and classifying the image data. According to one or more embodiments of the present specification, a residual mechanism is integrated into the attention model, and contextual information inside the attention mechanism is combined without increasing parameters, so that the attention model is helped to extract features of interest of an image classification task more accurately, and the efficiency and accuracy of image classification are improved.

The invention discloses an aluminum plate surface defect classification method based on a BP neural network and a support vector machine. The method comprises the steps that feature values of aluminum plate surface defects are extracted as the input quantity of a BP neural network classification model, and oil spots and the first class of defects are adopted as the output quantity to construct the BP neural network classification model; a plurality of support vector machine classification models are constructed through the first class of defects in a one-to-one classification method; learning samples are obtained, and the BP neural network classification model and the support vector machine classification models are trained; the oil spots and the first class of defects are classified through the BP neural network classification model, the BP neural network classification model is regarded as a testing sample of the oil spots to be removed, and the rest of the first class of defects are classified again through the support vector machine classification models; a classification result is obtained finally through statistics. According to the method, the recognition and classification rate of the oil spots on the surface of a cold rolling aluminum plate is improved, meanwhile, the overall recognition rate of the cold rolling aluminum plate surface defects is improved, and the method can be used for recognizing and classifying other metal surface defects and is simple and easy to implement.

The invention discloses a power customer service work order processing system and method, the system comprises a server and one or more user terminals, and the server comprises a personnel managementmodule recording personnel skilled processing items; a work order classification module used for classifying the received work orders; and a work order distribution module used for carrying out work order distribution according to the types of work orders and items which are processed by one person without permission. When one person has a plurality of work orders which are not processed, the plurality of work orders are sorted according to the work order generation time and the work order negative emotion degree, and the plurality of work orders are pushed to the user terminal. The work orders can be intelligently classified and distributed, and the work order processing efficiency is improved.