171results about How to "Simple classification" patented technology

A system and method for detecting fake accounts in OSNs is proposed to aid the OSN provider 20 against fake users, wherein a social graph G of the OSN, with n nodes, a non-Sybil region GH and a Sybil region GS, is obtained and the following steps are performed:a trust value T(i)(v) is computed through i power iterations on each node v of the social graph G, i=0, 1, . . . O(log n)the power iterations distribute the trust value T(i)(v) from each node v to its neighbour nodes,after O(log n) power iterations, ranking nodes by a degree-normalized trustT^v=T(w)(v)deg(v)in order to obtain a ranked list of nodes,detecting fake accounts based on the obtained ranked listassigning intervals in the ranked list to a fake portion, determined by manual inspection means of the OSN provider, based on the degree-normalized trust of the nodes belonging to the intervals.

The invention discloses an automatic classification method of an electrocardiosignal ST band. The automatic classification method is characterized by comprising the following steps: S1. acquiring an electrocardiosignal wave form of a human body and pretreating the electrocardiosignal wave form; S2. performing characteristic point detection to the pretreated electrocardiosignal wave form; S3. based on the characteristic point detection in the step S2, determining the wave form of the electrocardiosignal ST band, and acquiring the characteristic parameters on the wave form of the electrocardiosignal ST band so as to establish a to-be-classified characteristic input matrix; S4. classifying the wave form of the electrocardiosignal ST band into a training sample and a testing sample, and establishing a classifier model based on the training sample; and S5. inputting the testing sample into the classifier model for testing, and completing the final classification by combining decision fusion. The invention further discloses an automatic classification system and device of the electrocardiosignal ST band. By establishing the classifier model and decision fusion by using a nerve network method, calculation can be effectively reduced, the time cost can be decreased, the classification precision of the ST band can be improved, and the classification is easier.

The invention discloses a method for establishing a medical image atlas based on image segmentation and the CNN. A CNN method is used to segment medical images finely, image segmentation identification is carried out on the collected medical images, medical knowledge unit segmentation is carried out on medical diagnosis knowledge, and knowledge units of different medical images are formed; an image relation of image segmentation is analyzed to connect the different image knowledge units and communicate with an additional medical illness knowledge unit, a knowledge base association relation isestablished on the basis of connection between medical image identification and medical diagnosis knowledge; characteristic matching is carried out on the knowledge units after image segmentation, entities with the same type of attribute serves as entity nodes in the knowledge atlas, a knowledge base entity is established by fusion, and entities are aligned; and a knowledge atlas is established byusing the entities and the associations therebetween. Suspected diagnosis prompt and treatment suggestion are provided, and AI diagnosis is made possible.

The invention provides a traffic sign recognition method for a driverless car, and belongs to the technical field of image processing. According to the traffic sign recognition method, on the basis of algorithms such as a convex hull algorithm and a Hu invariant moment and transverse and longitudinal histogram scaling fast matching algorithm. Compared with existing traffic sign recognition methods, the traffic sign recognition method for the driverless car has the advantages of being large in recognition range, capable of recognizing a ban sign and an indicative sign, good in real-time performance, high in recognition accuracy and low in mistaken recognition rate.

The invention discloses a Chinese traditional musical instrument classification method based on a depth confidence network. During feature extraction of Chinese traditional musical instrument music, firstly, acoustic features of Chinese traditional musical instruments are extracted as primary features by employing a speech signal processing method, a depth learning network is constructed according to the depth confidence network, and more abstract features are extracted from the primary features of the Chinese traditional musical instruments by employing the depth learning network; and reconstruction abstract features of the Chinese traditional musical instruments are input to a softmax layer to predict the belonged type of the corresponding played musical instrument. The method is simple and feasible, the classification accuracy of the Chinese traditional musical instruments is improved, and more effective information is provided for the field of music information retrieval.

The invention discloses a moving target anti-fusion shielding tracking algorithm which specifically comprises the following steps of: firstly, judging whether the current moving target is in a fusion shielding state according to the target shielding judgment criterion; classifying all shielding targets according to the target moving information, and separating the active shielding targets and the passive shielding targets; obtaining the real positions of the targets by different template matching algorithms for different types of shielding targets respectively, wherein an overall template matching method based on fast Fourier transform and integral images is adopted for the active shielding targets, and an improved sub-block template matching method is adopted for the passive shielding targets; matching and estimating the moving displacement of the sub-block template by use of a target prospect adaptive block to realize the adaptive update of the template; and finally, realizing the anti-fusion shielding tracking of the target by combining the target overall template matching based on fast Fourier transform and integral images and the adaptive multi-sub-block template matching.

A white electroluminescent device realized by carbon quantum dots comprises a transparent sealing layer, a carbon quantum dot fluorescent layer, a transparent conductive layer, a light-emitting layer and a back conductive layer. The white electroluminescent device is characterized in that the carbon quantum dot fluorescent layer comprises carbon-containing nano fluorescent materials, has a light absorption range of 365-520 nm and a light emission range of 440-610 nm, and is used for converting the luminescent spectrums of the light-emitting layer into white light.

In a nuclear magnetic resonance tomography apparatus and a method for the operation thereof, on the basis of the 3-point Dixon method, spin collectives having different chemical shifts are separated by means of information maximization despite great field inhomogeneities. The unwrapping of the phases is implemented over interconnected pixel regions (phase unwrapping) proceeds initially only in regions with high signal amplitude and the regions of lower amplitudes are only successively acquired by increments. These are then assigned to the respectively correct spin type, such as fat or water.

The invention provides a preparation method of a carbon quantum dot fluorescent material. The method involves an ignitable plant leaf material, a combustion supporting substance, a solid fiber adsorption material layer, and a combustion furnace body. The method is characterized in that: the combustion furnace body is composed of an air inlet, a combustion chamber, and an exhaust gas outlet, and the solid fiber adsorption material layer is arranged at the exhaust gas outlet; when the plant leaf material combusts, the carbon quantum dot fluorescent material can be generated, is carried by gas and is adsorbed in the solid fiber adsorption material layer, when the solid fiber adsorption material is placed in water or a solvent, the carbon quantum dot fluorescent material can separate and precipitate out by itself. The method provided in the invention can directly use urban waste fallen leaves to prepare the carbon quantum dot fluorescent material and does not employ any chemical means to extract. The carbon quantum dot fluorescent material adsorbed in the solid fiber adsorption material layer is convenient for transportation and carrying, is pollution-free and nonhazardous, can be released by an aqueous solvent or static electricity, so that the carbon quantum dot fluorescent material can be taken out directly.

A method for the operation of a self-propelled agricultural working machine has at least one working element and a driver assistance system for generating control actions within the working machine. A sensor arrangement for generating surroundings information is provided, and the driver assistance system generates the control actions based on the surroundings information. The sensor arrangement comprises a camera-based sensor system and a laser-based sensor system, each of which generates sensor information regarding a predetermined, relevant surroundings area of the working machine. The sensor information of the camera-based sensor system is present as starting camera images. The starting camera images are segmented into image segments by an image processing system according to a segmentation rule, and the segmented camera images are combined by a sensor fusion module with the sensor information from the laser-based sensor system.

The invention relates to a statistical process control method and a statistical process control device applying the method. The method comprises the following steps: acquiring initial data to be analyzed during production, dividing the initial data into non-continuous distribution data, autocorrelation data, nonnormal distribution data and normal distribution data, determining the control limit according to different data types respectively, and monitoring and / or analyzing the production process according to the determined control limit. The statistical process control method simplifies classification of control charts through data classification, solves the problem of calculating the control limit of limited data points subjected to normal distribution and nonnormal distribution, realizes monitoring of a complex system with a large quantity of parameters which can not be realized in the prior art, saves the data processing time, and improves the work efficiency.

The invention discloses an all-network abnormal data stream classification method. The method comprises: step one, abnormal data stream extraction is carried out on an all-network data stream and an abnormal data stream set in the abnormal data stream is outputted; step two, an average value S-P of an abnormal data stream size during per-package counting of the abnormal data stream is calculated, wherein the P is larger than or equal to 1 and is less than or equal to i, an average value B-P of a package size during per-byte counting of the abnormal data stream is calculated, wherein the P is larger than or equal to 1 and is less than or equal to I, at least one feature of the abnormal data stream is extracted, statistics of a distribution entropy H of the extracted feature is carried out, and feature vectorization of the abnormal data stream is carried out by using the S-P, the B-P, and the distribution entropy H of the extracted features as coordinate values to form a point set of a multi-dimensional space; step three, coarse clustering is carried out on the point set by using a Canopy method to obtain a cluster center and a number K value of central points; and step four, according to the cluster center, and the K value, fine clustering is carried out on the abnormal data stream after feature vectorization by using a K-means calculation method and thus a precise classification result of the abnormal data stream is obtained.

The invention relates to an overvoltage computing method of a modular multi-level converter. An electromagnetic field theory is used in the method to compute converter stray parameters and build an overvoltage computing model, a circuit theory is used to compute overvoltage of converter electrical grids to the ground and between the electrical grids, the overvoltage is classified and analyzed based on metallic oxide arrester protection properties, and the method comprises the steps of extracting modular multi-level converter stray parameters, building a modular multi-level converter overvoltage model, and computing converter biggest overvoltage according to the arrester protection properties. By means of the overvoltage computing model, computing errors generated by assumed extraction of the stray parameters using equivalent capacitors or plate capacitors are avoided, overvoltage computing accuracy degree is improved, a protection level for direct protection of the modular multi-level converter arrester is confirmed, classification of modular multi-level converter overvoltage computing is simplified, overvoltage analysis difficulty and workload are lowered, device safety is ensured, and overvoltage analysis efficiency is improved.

A method for processing metals and materials consisting predominantly of metallic elements through the use of a multifunctional high-pressure particle jet that produces powders, cuts subject materials and performs surface treatment on particles and subject materials. The process comprises entraining metallic particles into a pressurized stream to form a particle jet, impacting the particle jet into a metallic subject material and then regulating or tuning the incident angle of impact relative to the subject matter, the pressure of the pressurized stream in a specific range and the physical and chemical properties of selected materials to conduct cutting, surface treatment of material or production of smaller particles of material.

Methods and apparatus for manipulation, detection, imaging, characterization, sorting and / or assembly of biological or other materials, involving an integration of CMOS or other semiconductor-based technology and microfluidics. In one implementation, various components relating to the generation of electric and / or magnetic fields are implemented on an IC chip that is fabricated using standard protocols. The generated electric and / or magnetic fields are used to manipulate and / or detect one or more dielectric and / or magnetic particles and distinguish different types of particles. A microfluidic system is fabricated either directly on top of the IC chip, or as a separate entity that is then appropriately bonded to the IC chip, to facilitate the introduction and removal of cells in a biocompatible environment, or other particles / objects of interest suspended in a fluid. The patterned electric and / or magnetic fields generated by the IC chip can trap and move biological cells or other objects inside the microfluidic system. Electric and / or magnetic field generating components also may be controlled using signals of various frequencies so as to detect one or more cells, particles or objects of interest, and even the type of particle or object of interest, by measuring resonance characteristics associated with interactions between samples and one or more of the field-generating devices. Such systems may be employed in a variety of biological and medical related applications, including cell sorting and tissue assembly.

A liver segmentation method based on spatial multi-scale U-net and superpixel correction comprises the following steps: firstly, enhancing the contrast of a liver image by using a window modulation algorithm, and suppressing noise interference through Gaussian filtering; secondly, segmenting the liver preprocessing image by using a cavity space pyramid pooling U-net model to obtain a liver preliminary segmentation result; thirdly, acquiring an over-segmentation result of the liver by utilizing a morphological expansion algorithm; and finally, correcting the liver preliminary segmentation imageby applying an FSLIC-E superpixel algorithm, and obtaining the accurate edge of the liver. According to the liver segmentation method, the respective advantages of ASPP-U-net and FSLIC_E superpixel algorithms are combined, so that a problem of relatively poor robustness of U-net for liver image segmentation is solved, and the liver segmentation method can be better applied to automatic segmentation of the liver image, so as to solve a problem of low segmentation precision of a traditional network for the blurred liver image, and realizes high segmentation precision.

The invention discloses a medical waste recycling and disinfecting device. The device comprises a rectangular base, wherein a first rectangular groove is formed in the center of the upper surface of the rectangular base, and a first rectangular carrying box is embedded in the first rectangular groove; a first separator is arranged in the first rectangular carrying box; a second separator is arranged in the first rectangular carrying box and is positioned on the right side of the first separator; a common waste recycling mechanism is arranged in the first rectangular carrying box and is positioned on the left side of the first separator; a special waste disinfection mechanism is arranged in the first rectangular carrying box and is positioned between the first separator and the second separator; a waste alcohol recall mechanism is arranged in the rectangular carrying box and is positioned on the right side of the second separator; a moving mechanism is arranged on the lower surface of the rectangular base; and a controller is arranged on the side surface of the first rectangular carrying box. The medical waste recycling and disinfecting device has the beneficial effects of simple structure and strong practicality.

A system and method for detecting fake accounts in OSNs is proposed to aid the OSN provider 20 against fake users, wherein a social graph G of the OSN, with n nodes, a non-Sybil region GH and a Sybil region GS, is obtained and the following steps are performed:a trust value T(i)(v) is computed through i power iterations on each node v of the social graph G, i=0, 1, . . . O(log n)the power iterations distribute the trust value T(i)(v) from each node v to its neighbor nodes,after O(log n) power iterations, ranking nodes by a degree-normalized trustT^v=T(w)⁡(v)deg⁡(v)in order to obtain a ranked list of nodes,detecting fake accounts based on the obtained ranked listassigning intervals in the ranked list to a fake portion, determined by manual inspection means of the OSN provider, based on the degree-normalized trust of the nodes belonging to the intervals.

The invention discloses a single sample face recognition method based on semi-supervised block joint regression. The method comprises steps: a face is firstly divided into multiple blocks; a semi-supervised-based block joint regression model is then brought forward to make full use of face images with labels and with no labels to learn various change information of the face images, isometric constraints with each class of the face images with no labels in class label coordinate space are added to avoid influenced model discrimination by the data with no labels, a non-strict augmented Lagrange multiplier is used for acquiring a mapping matrix corresponding to each block; on the basis, regression classification on a test image block can be realized through the mapping matrix; and finally, all test image blocks are voted to finally determine a classification result. The single sample face recognition method has good robustness towards expressions, illumination variation and occlusion, and the recognition precision is high.

The invention discloses an intelligent water affair comprehensive information processing platform, which comprises a main monitoring module, a sub-monitoring module, a main analysis module, a sub-analysis module, a main scheduling module, a sub-scheduling module and an acquisition module; the acquisition module is used for acquiring water affair data of a single region and uploading the water affair data to the sub-analysis module; the sub-analysis module is used for preprocessing the water affair data of a single area and uploading the preprocessed water affair data to the sub-monitoring module for publishing; the main analysis module is used for receiving the water affair data from the plurality of sub-monitoring modules and carrying out overall planning processing on the water affair data; the main monitoring module is used for receiving the water affair data from the main analysis module and publishing the water affair data; the main monitoring module schedules and distributes theplurality of sub-monitoring modules through the main scheduling module, and the sub-monitoring modules schedules and distributes the acquisition modules through the sub-scheduling modules; The intelligent water affair comprehensive information processing platform has the beneficial effects of high comprehensiveness and efficient information processing and sharing.

A modeling and compensating method of nonlinear system includes setting up nonlinear model of said system and confirming parameter of said model according to input and output of nonlinear system, setting up inverse model of said nonlinear model and confirming parameter of said inverse model according to said set-up nonlinear model, carrying out compensation on said nonlinear system by utilizing set up nonlinear model and inverse model.

The invention discloses a block sparse structure low-rank representation based single-sample human face identification method. The method comprises the following steps: dividing a human face into a plurality of blocks, diving each block into a plurality of overlapped sub-blocks and supposing that the sub-blocks in the same block is in the same sub-space; based on a low-rank representation model, performing low-rank representation on a test matrix formed by the center sub-blocks of the corresponding blocks of all the test image by a local dictionary formed by all the sub-blocks in corresponding blocks of all training samples to realize effective division of the sub-spaces corresponding to each person, adding block sparse constraint to enhance the identification property of the model, and solving the model by a non-strict augmented lagrangian multiplication to obtain a low-rank representation coefficient matrix; on this basis, classifying the test image blocks by judging the value of the representation coefficient; finally, performing voting on all the test image blocks to finally determine the classification result. The block sparse structure low-rank representation based single-sample human face identification method has high robustness on expression, illumination variation, shielding and the like, has high identification accuracy and supports efficient parallel computation.

The invention discloses a method of classifying Naive Bayes scanned certificate images based on feature weighting. The method comprises the steps of carrying out round seal locating, dividing and sizing on certificate images processed, and extracting color feature vectors of an HSV (Hue, Saturation, Value) space of a round seal area and the length-width ratio of the images; building a certificate image database, processing each certificate image in the database according to the above steps, so as to obtain the round seal HSV color feature vector and the length-width ratio of each scanned certificate image in the data base, calculating the probability of different data combinations in the certificate image database according to the obtained feature vectors, and storing the data after the feature weighting; calculating an image category which is most possible to appear according to a Naive Bayes algorithm and the probability of different data combinations in the certificate image database, and judging the classification of the images when the probability meets a set threshold requirement. According to the method, the certificate images can be simply and quickly classified, and the certificate image retrieval efficiency can be improved.

A force-measuring device (1) for a gravimetric measuring instrument has a stationary part (11) and a load-receiving part (12). Parallel guide members (14, 15) connect the receiving parts. The device also has at least one balance beam (19) connected to the load-receiving part through a coupling member (17) acting on a first lever arm (18) thereof, and which, at a second lever arm (20) thereof, is connected to a measurement transducer (22) which is arranged on the stationary part. Further levers (29, 30) can be arranged, respectively, between the first lever arm and the load-receiving part, and between the second lever arm and the measurement transducer. At least one sliding weight (23, 23A, 23B) is arranged on the at least one balance beam, wherein the position of each of the sliding weights present can be varied in a controlled way by means of at least one drive mechanism.

The invention discloses a method using an electronic nose to identify vinegar varieties by extracting an optimization fuzzy identification vector. Several sensors are randomly selected from the sensors of the electronic nose. Collected data corresponding to the sensors are extracted from training samples and are used as new training samples. The class mean value of new training samples, the grand mean of new training samples, the inter-class dispersion matrix and the intra-class dispersion matrix of new training samples, the trace of the inter-class dispersion matrix and the trace and the optimal value of the intra-class dispersion matrix are calculated. The new training sample corresponding to the selected sensor is used as the optimal training sample when the optimal value is the maximum. The identification information of the optimal training sample is extracted. The optimal identification vector set is acquired. The optimal identification vector set is linearly transformed to acquire a projection sample set. The projection sample set is classified to identify vinegar varieties. According to the invention, the data dimension can be reduced without the loss of main information; the influence of noise is reduced; and the classification accuracy of vinegar varieties is improved.

The invention provides a high-stability carbon nanometer fluorescence dye. The high-stability carbon nanometer fluorescence dye is coated on the surface of a conventional luminescent material, can be used for changing a luminescent spectrum and comprises a carbon nano-dot fluorescent material, a thinning agent, a binding agent and a fluorescent dyeing matter. The high-stability carbon nanometer fluorescence dye is characterized in that the carbon nano-dot fluorescent material is mixed with the thinning agent to form a fluorescent solution containing the carbon nano-dot fluorescent material; the fluorescent solution is uniformly mixed with the binding agent to form a fluorescent binding agent; and the fluorescent binding agent is combined with the fluorescent material. The high-stability carbon nanometer fluorescence dye provided by the invention has the characteristics of transparency, stability, no toxicity, environmental protection, low cost, simplicity in use and the like. The high-stability carbon nanometer fluorescence dye can be widely applied to the fields such as color long afterglow, light emitting display, light conversion agents, anti-fake fluorescent materials and various coatings.

The invention discloses a vehicle trajectory classifying method for detecting traffic incidents, which comprises the following steps: extracting trajectories of vehicles and recording coordinates of trajectory points; performing least square fitting of quadratic polynomial y=ax<2>+bx+c with regard to the recorded trajectory coordinates; judging the driving way of the vehicle according to a fitting result. The method disclosed by the invention has advantages as follows: 1, the trajectory classification is simpler; the method adopts the least square fitting rather than a traditional clustering algorithm, so the obtained result is judged by direct calculation without providing some trajectories in advance; and 2, the obtained result is relatively precise. Comprehensive judgment of 'Double Fitting' is adopted in the method disclosed by the invention, so the obtained driving way of the vehicles is more precise.

The present invention discloses an apparatus and method for defining and enforcing rules of transition between two security domains, e.g., a transport domain and a persistent security domain. In turn, a border guard, e.g., a security device, is provided between these two domains that enforce rules for transition between the two security domains. This novel approach of defining a transport domain and a persistent security domain simplifies the classification of the digital content and its movement through the system. Namely, the border guard once established between the two systems can enforce DRM rules associated with how contents are moved between the two domains.