243results about How to "Reduce sorting time" patented technology

The invention relates to a method for outputting traffic information in a motor vehicle. In order to present the driver with traffic information in such a way that he can adapt his driving behaviour and/or his selection of a route for his journey to the respective current traffic situation in time, there is a provision that traffic messages are stored together with the respective position of the route section to which they relate. The positions of the traffic messages are then compared with the respective position of a motor vehicle in which the traffic information is to be output in order to detect the distances between the respective position of the traffic messages and the position of this motor vehicle. The traffic messages are then output sorted according to distances, starting with the smallest distance.

The invention provides an electrocardiogram electrocardiosignal classification method with multi-scale characteristics combined. The method comprises the steps that (1), all electrocardiosignals in a database are read, and a base line and high-frequency noise in the electrocardiosignals are removed; (2), the electrocardiosignals are divided; (3), wavelet packet decomposition of the electrocardiosignals is calculated, and a fourth layer of wavelet packet decomposition coefficient is obtained; (4), electrocardiosignal characteristics extracted in a plurality of periods are arranged to form M-dimensional data, a generalized multidimensional independent component analysis method is applied to the M-dimensional data, and demixing matrixes of all modes are obtained; (5), a heartbeat signal to be tested is input, the fourth layer of wavelet packet decomposition coefficient is obtained through the step 1, the step 2 and the step 3, M-1-dimensional data are formed in an arranged mode, and the fuse characteristics of the tested heartbeat signal are obtained through the step 4; (6) the heartbeat signal fuse characteristics are classified through a classifier, and then the classification result of multiple normal and abnormal electrocardiosignals is obtained.

The invention provides a method for training a back propagation (BP) neural network for filtering junk mails. Weights among layers in the BP neural network are adjusted through a studying rate by the method. The method comprises the following steps of: calculating the weight of the keyword of a known mail and target values corresponding to various mail types, wherein the different mail types correspond to the different target values; inputting the weight of the known mail into a BP neural network to be trained to acquire an output value; and calculating an offset between the output value and the target value, if a training termination condition is not met, modifying the weight of the BP neural network and performing a next generation of training until the output value meets the training termination condition, wherein generations in a preset numerical value are set as one stage; and the studying rate is updated once every stage.

The invention discloses sorting technology for a coarse coal slurry damping pulsation interference bed. The sorting technology is formed by the mutual connection of an interference bed sorter, a feeding system, a peristaltic pump, a cleaned coal recovering system, and a water pump, and is characterized in that the inside of the interference bed sorter is added with a plurality of damping blocks and screens; the middle part of the interference bed sorter is connected with the feeding system to form a stable fluid bed; simultaneously, a diaphragm is additionally arranged on the lower part of the interference bed sorter and the upper part of a heavy product discharge port to generate a pulsating flow, so that particles with different densities gain the accelerating effect and retarding effect, and the leading action of the density on the separation effect is strengthened; the peristaltic pump is used for discharging heavy products, so that the processing capability of the equipment is improved; under the conditions of wide particle size range of the coarse coal slurry and heavy processing load, the good separation effect and high separation efficiency can also be achieved by the separation process.

The invention provides a RFID laundry tag as well as a relevant antenna matching design method; wherein, the tag comprises a waterproof, fire-resistant and environmental-protection front face material, the first layer of waterproof fire-resistant adhesive agent, a laundry environment matching antenna, an anti-corrosion antenna carrier layer, the second layer of waterproof fire-resistant adhesive agent, a waterproof, fire-resistant and environmental-protection back face material, and a chip; the tag is characterized in high mechanical strength, fire-resistance, waterproof and anti-soaking, and chemical corrosion resistance. The invention can: 1. Lower garment category time and reduce complicated operation; 2. No contradiction happens between clients and laundry shops due to garment loss; 3. Laundry shops can automatically communicate with clients for information, and provide other services with higher added-value and etc.

The invention discloses an image classification method based on an improved bag-of-visual word model. The method comprises the following steps: S1, fine-resolution SIFT feature points are extracted; S2, fine-resolution SIFT feature point pairs are extracted; S3, a visual dictionary is built; and S4, image classification is carried out. The method provides a visual phrase building algorithm based on a minimum spanning tree, the minimum spanning tree is built for all fine-resolution SIFT features of each training image, the SIFT feature point pairs are built on the basis, K-means clustering is then carried out, visual phrases containing the space information are thus obtained, the visual words and the visual phrases built by using the above method together build a visual histogram, and image classification is completed through an SVM. The image classification method based on an improved bag-of-visual word model has the beneficial effects that the computation complexity is reduced; the space information between local features is kept; the image classification accuracy is improved; the classification time is reduced; and the method of the invention can be widely applied to fields such as image retrieval, object tracking, scene classification and behavior recognition.

The invention aims at providing equipment adopting mechanical operation and separating rapidly, and discloses centrifugal minitype express item sorting and inputting equipment. The centrifugal minitype express item sorting and inputting equipment is characterized in that a first sorting mechanism comprises a first rotating disk, a first baffle, a first rotating shaft and a first transmission mechanism; a second sorting mechanism comprises a second rotating disk, a second baffle, a second rotating shaft and a second transmission mechanism; the first rotating shaft is arranged in the second rotating shaft and is connected with the second rotating shaft in a rolling manner; the second rotating shaft is mounted in a support cylinder in a rolling manner; the first rotating shaft is connected with a sorting driving motor by the first transmission mechanism; the second rotating shaft is connected with the sorting driving motor by the second transmission mechanism; the first rotating disk is positioned at the upper part of the second rotating disk; the first baffle is overhung the first rotating disk; the second baffle is overhung the second rotating disk; and an outlet of an inputting slide is formed at an eccentric position of the first rotating disk. According to the centrifugal minitype express item sorting and inputting equipment, separation of express items is performed by centrifugal effects of the first rotating disk and the second rotating disk; a sorting speed is high; the sorting efficiency is high; and an accident of rough sorting is avoided.

The invention relates to an intrusion detection method based on a fast k-nearest neighbor (KNN) algorithm. The method comprises the following steps: carrying out data pretreatment; receiving original data of intrusion detection; carrying out data pretreatment on the original data, wherein data pretreatment includes continuous data discretization treatment and character data digitalization treatment; reducing features; carrying out feature reduction on the pretreated data by adopting a mutual information-based feature reduction algorithm; detecting in a classified manner; carrying out classified detection on the data after feature reduction by adopting the fast KNN algorithm, and outputting the classified result. Compared with the prior art, the intrusion detection method has the advantages of high classification effectiveness, high classification accuracy and the like.

The invention discloses an improved PCAnet-based SAR image classification method which mainly solves a problem that high classification computation complexity and low classification computation efficiency are caused by low filter initialization efficiency and slow renewal learning of in synthetic aperture radar high resolution SAR image classification processes via technologies of the prior art. The improved PCAnet-based SAR image classification method comprises the following steps: (1) a step of data reading, (2) a step of slicing, (3) a step of normalization pretreatment, (4) a step of extracting an image low frequency component, (5) a step of training a principle component analysis net PCAnet, (6) a step of obtaining characteristic vectors of a test set, (7) a step of classification accuracy calculation and (8) a step of outputting a classification result. The improved PCAnet-based SAR image classification method is advantaged by short SAR image classification time and high classification accuracy.

The invention discloses a method for plastic sample element identification based on laser-induced breakdown spectroscopy. The method includes a step (1) of establishing an elemental characteristic line database based on an NIST database; a step (2) performing an experiment on a plastic sample through am LIBS device to obtain a plastic sample 2D data matrix; a step (3) of performing baseline correction on LIBS spectra based on a discrete wavelet transform method; a step (4) of performing spectral peak identification on the corrected spectra according to a continuous wavelet transform method; and a step (5) of comparing data in LIBS with data in the established characteristic line database to determine an element attribution of a spectral peak. According to the method, elements in the plastic sample can be automatically identified, the influence of garbage on the recognition process is reduced, and the goals of improving the element identification accuracy rate, reducing the classification time, and reducing the calculation cost are achieved.

The invention discloses a method for sorting recyclable logistics implements attached with wireless tags. The method comprises the following steps: a mobile terminal is set, and then the sorting is started; a person holding the mobile terminal begins to walk around the recyclable logistics implements to be sorted, and utilizes the mobile terminal for calculating own relative geographical positions in a real-time manner and detecting a plurality of RSSI values within and outside a target scope while walking; after the walking process is partly finished, spatial calculation is carried out for deciding which signals corresponding to the RSSI values are located on one side of a delineated topological graph formed in the walking process, so as to complete the sorting process. Through the adoption of the method, the conventional equipment can be conveniently utilized for quickly sorting the recyclable logistics implements, so that time is saved, and cost is reduced.

The invention provides an information recommendation result sorting method and device and a server. The information recommendation result sorting method comprises the steps that a sorting model for sorting information recommendation results is established according to information characteristics in the known information recommendation results; the information characteristics corresponding to the known information recommendation results are obtained from the information to be sorted; according to the information characteristics in the information to be sorted, the sorting model is utilized to sort the information to be sorted, and then the sorted information recommendation results are sent to a user. One of the above technical schemes has the following advantages that the sorting model forsorting information recommendation results is established according to information characteristics included in the known information recommendation results, multi-dimension information characteristicsand characteristic combination can be increased, the characteristic complexity is reduced, and the sorting performance is greatly improved through reasonable characteristic calculation.

The invention discloses a multi-labeled scene classification method based on incremental linear discriminant analysis and mainly solves the problems of the prior art in image dimensional reduction and multi-label classification. The method includes: decomposing a multi-label into a plurality of single labels; using an initial sample to compute a transformation matrix for initial linear discriminant analysis, using an added sample to incrementally updating the transformation matrix for initial linear discriminant analysis, and projecting high-dimensionality data to a low-dimensionality space; randomly selecting training samples and test samples from a sample set subjected to dimensional reduction, and using a single-sample multi-labeled K-nearest neighbor classifier to classify feature samples subjected to dimensional reduction so as to obtain test sample output values; predicting labels of the test samples to obtain classification results. The method has the advantages that classification precision is higher, classification time is shorter and the multi-labeled data of high quantity, high dimensionality and high diversity can be quickly and accurately classified.

The invention provides a circuit board with a quality identification tag, and the circuit board with the quality identification tag includes a primary board, plural secondary boards, two first main identification points and plural first sub identification points, wherein the primary board includes a product area and two first identification areas, the two first identification areas are arranged on both sides of the product area, the plural secondary boards are arranged in the product area, the two first main identification points are respectively arranged in the two first identification areas, of the plural first sub identification points are equivalently arranged in the two first identification areas, and each two of the first sub identification points are arranged relatively on both sides of each sub secondary board. When at least one of the secondary boards is a bad product in the product area, the first main identification points are covered with tags; when the secondary boards are bad, the first sub identification points relative to both sides of the secondary boards are covered with the tags. The circuit board with the quality identification tag and an identification method of the circuit board with the quality identification tag can shorten the time of classifying different qualities of boards, improve finished product yield and activation of a drilling crew, and meet the identification conditions of different kinds of production devices over bad boards.

The invention discloses a method for carrying out benign and malignant discrimination on a lung tumor CT image by adopting high-dimensional feature selection, and the method comprises the steps of obtaining a lung tumor CT image with a clear diagnosis conclusion in a lung image database, and forming a single sample; segmenting the preprocessed ROI by adopting a maximum between-cluster variance method so as to accurately describe the shape, texture and gray features of the lung tumor CT image; carrying out region feature extraction on the obtained lung CT image, and carrying out 82-dimensionalfeature component normalization on the extracted features so as to jointly quantify the ROI; carrying out attribute reduction by utilizing BRS and GA algorithms to reduce the time complexity and the space complexity of the classifier and improve the classification performance; and carrying out parameter global optimization and classification operation by using a cuckoo algorithm and an SVM mode, and carrying out lung tumor high-dimensional feature selection. The method has a very good auxiliary effect on lung cancer diagnosis, and the missed diagnosis rate and the misdiagnosis rate can be effectively reduced.

The embodiment of the present invention discloses a community express logistics storage and an intelligent sorting system. The system comprises an express storage compartment, an unmanned aerial vehicle, a cloud service platform and a sorting robot. The express storage compartment and the unmanned aerial vehicle establish communication connection with the cloud service platform; each community isfixedly arranged numbers in advance; the sorting robot scans and identifies address information on an express, big data of the cloud service platform is transferred to spray the numbers and two-dimensional codes of the destination communities on express, send the numbers and two-dimensional codes of the destination communities to the cloud service platform or a control center and send the numbersand two-dimensional codes of the destination communities to receiving clients, the sorting robot performs sorting according to areas, puts city-wide expresses into a city-wide cargo box to facilitatetimely delivery, and puts expresses except the city-wide expresses to the other cargo box to send the expresses except the city-wide expresses to an area sorting center; the cloud service platform isconfigured to control the flight routes of the unmanned aerial vehicle and process special conditions; and the unmanned aerial vehicle is employed to transport cargo to avoid a delay delivery phenomenon of human factors such as traffic jam and improve the delivery efficiency.

A horizontal type cigarette carton sorting mechanism comprises a sorting device and a main conveyor belt. The sorting device comprises a rack, and a conveying rolling way is arranged on the rack. A replenishment tipper hopper is arranged at the front end of the conveying rolling way, and a separation rolling way is connected to the tail end of the conveying rolling way. A sorting bin is arranged at an outlet end of the separation rolling way, and a pusher mechanism for pushing a stack of cigarettes into the sorting bin is arranged above the separation rolling way, and the pusher mechanism comprises a pusher plate, a power device and a guide rail which are capable of moving up and down and moving horizontally. The horizontal type cigarette carton sorting mechanism has the advantages that the drawing speed of cigarette cartons and the speed of the main conveyor belt are homodromous and synchronous by means of arranging the cigarette outlet direction of the cigarette outlet and the main conveyor belt in parallel. Phenomena of rolling, inclination, overlapping and the like of cigarette cartons cannot occur even when the cigarette cartons are drawn rapidly, and not only the sorted orderly and dense cigarette cartons are convenient for subsequent stacking packaging, but also the cigarette carton capacity per unit length of the main conveyor belt is increased; besides, the main conveyor belt is long, accordingly, the capacity is larger, and the efficiency is higher than the prior art.