302results about How to "Achieve accurate identification" patented technology

The invention discloses a touch panel, a display panel, a display device and a fingerprint identification method. The touch panel comprises a substrate, a plurality of fingerprint identification units arranged on the substrate, and an encapsulation layer covering the plurality of fingerprint identification units; and the fingerprint identification units include light-emitting devices and light-sensitive devices. In addition, the touch panel also includes optical path restricting structures arranged above all the light-emitting devices. Because of the optical path restricting structures arranged above the light-emitting devices, light emitted by the light-emitting devices is transmitted in the optical path restricting structures in a total reflection manner. Light of an emergent area is centralized in a small-angle range, so that light emitted by the light-emitting devices is sent out in a manner of quasi collimation; and thus the light irradiation range of the area of a to-be-identified fingerprint is reduced and the angles of reflected light are centralized. Most of light is irradiated on the light-sensitive devices corresponding to the light-emitting devices, so that the crosstalk of light received by the light-sensitive devices in different identification units is avoided and thus accurate fingerprint identification is realized.

The invention provides an opening-closing fault diagnosis method for an air circuit breaker based on vibration signals, wherein an acceleration sensor is used to collect machine body vibration signals generated during opening-closing courses of the air circuit breaker. The method comprises the steps that firstly, the acceleration sensor is used to collect the machine body vibration signals generated during opening-closing actions of the air circuit breaker and transform the vibration signals into digital signals, so that initial vibration signals are obtained; secondly, an improved wavelet packet threshold de-noising algorithm is used to process the collected vibration signals; thirdly, a complementary ensemble-average empirical mode decomposition algorithm is used to extract intrinsic mode function components from the de-noising vibration signals; fourthly, the quantity Z of the intrinsic mode function components is determined; fifthly, the intrinsic mode function components of the first Z orders are selected and extracted as sample entropies of a characteristic quantity; sixthly, binary tree multi-classifiers based on a relevance vector machine are established; and seventhly, the binary tree multi-classifiers based on the relevance vector machine obtained at the sixth step are used to establish a fault recognition model of the air circuit breaker.

The invention provides a method for analyzing and recognizing the structure of a handwritten mathematical formula in a natural scene image. The method comprises the steps of S1, converting the gray matrix of a natural scene image into a local contrast matrix, and conducting the binary classification on the local contrast matrix based on the otsu method to obtain a binary matrix; S2, analyzing the connected domains of the binary matrix obtained in the step S1, and removing non-character type connected domains to obtain character type connected domains; S3, detecting formula structural elements and other special structural elements in the character type connected domains based on the correlation coefficient method, and separately marking out all detected special structural elements; S4, dividing the binary matrix obtained in the step S1 based on the horizontal projection method; S5, recognizing each character type connected domain via a convolutional neural network; S6, defining an output sequence and outputting recognized results according to the corresponding sequence in the latex layout format. According to the technical scheme of the invention, by means of the method, the expression problem of elementary mathematical formulas during the OCR recognition process can be effectively solved.

The invention discloses a behavior identification method based on GPS speed and acceleration data of a smart phone. The method can be used to effectively identify human behaviors, as riding a bike and taking a bus, at different speeds. The method comprises that the Andorid smart phone is used to collect the real-time GPS speed data and tri-axial accelerometer data of a user; time-domain and frequency-domain features are extracted from the collected data; and an extracted characteristic vector and known behaviors corresponding to the characteristic vector serve as a training sample, the training sample is input to a support vector machine SVM and trained to obtain a classifier, and the classifier is used to identify instance samples and obtain a result of human behavior identification.

The invention discloses a traffic light identification method and device, and belongs to the field of traffic safety. The traffic light identification method comprises the steps that an original image is collected; threshold segmentation is conducted on three channel values of the original image in an RGB space to obtain a black region binary image; according to the characteristics of a light panel, the light panel area is positioned in the black region binary image; the portion, in the light panel region, of the original image is converted from the RGB space to a YCbCr space to obtain a red and yellow region binary image and a green region binary image through segmentation; according to the characteristics of traffic lights, traffic light candidate regions are determined on the red and yellow region binary image and the green region binary image; graying and normalization are conducted on the portion, in the traffic light candidate regions, of the original image, and Gabor wavelet transformation is conducted on the image obtained after graying and normalization to obtain a Gabor wavelet image; the amplitude of the Gabor wavelet image is sampled to obtain a feature vector; the similarity between the feature vector and a training sample is compared to determine the types of the traffic lights.

The invention discloses a method for identifying a plurality of authentic touch points by using an infrared touch screen. Firstly, the infrared scanning is carried out in the directions of X, Y and Z axes; a scanning unit carries out the touch analysis for touch signals to generate the touch position information of the X, Y and Z axes; a controller is adopted to judge whether the touch position information belongs to the effective information; when the effective touch position information exists, the controller collects the information and arranges and combines the collected data to generate combination points; the controller respectively judges all of the combination points according to that X plus Y*tg(90 minus Alpha) equals Z, to see whether the combination point meeting the condition exists, wherein, Alpha is an included angle between the Z axis scanning unit and the X axis scanning unit; the obtained position information of each authentic touch point is transmitted to a computer system. The invention can fully cover the whole touch zone and the multi-point identification blind zone can be avoided in the whole touch zone so as to completely exclude false points and authentically realize the correct identification of a plurality of touch points.

The invention provides a method and system for detecting false attack sources. The method includes the steps that first domain name query request information sent by a cache domain name server to an authoritative domain name server is intercepted and received; a first cookie value is determined according to the source IP address and the destination IP address of the first domain name query request information, and virtual domain name information of the authoritative domain name server is generated according to the first cookie value and then sent back to the cache domain name server; second domain name query request information sent by the cache domain name server to the authoritative domain name server is intercepted and received; a second cookie value is determined according to the source IP address and the destination IP address of the second domain name query request information, and the second cookie value is compared with the first cookie value carried by the second domain name query request information. According to the method and system for detecting false attack sources, the false attack sources can be accurately recognized, the authoritative domain name server can be effectively protected from attack by false IP sources and can normally work, and normal domain name query requests can not be affected.

Disclosed is a generalized displacement hybrid monitoring damaged cable load progressive identification method. The method comprises the steps that on the basis of hybrid monitoring, whether a mechanical calculation reference model of a cable structure needs to be updated or not is determined by monitoring support generalized replacement, the temperature of the cable structure, the environment temperature, the load variation degree and the damaged degree of a damaged cable; a new mechanical calculation reference model, including the support generalized displacement, the load variation degree, the damaged degree of the damaged cable and the temperature, of the cable structure is obtained; on the basis of the model, according to the approximate linear relation between a current numerical vector of a monitored amount and a current initial numerical vector of the monitored amount, the approximate linear relation between the current numerical vector of the monitored amount and a unit damage monitored amount numerical variation matrix, and the approximate linear relation between the current numerical vector of the monitored amount and a current nominal damage vector to be solved, when the support generalized displacement and temperature variation exist, the influence of an interference factor can be removed, and the damaged cable and the load variable quantity can be accurately identified.

The invention discloses a mine rail locomotive unmanned automatic driving system based on vehicle computer control. The mine rail locomotive unmanned automatic driving system comprises a transportation dispatching commanding system, a vehicle control system, a rail turnout and signal control system, a network communication system, a remote ore drawing system, an ore unloading pit detection systemand a locomotive power supply line monitoring system. The mine rail locomotive unmanned automatic driving system is simple and reasonable in structure design and convenient to operate; the safety of locomotive driving under a communication fault condition is ensured and the possibility of rear-end accidents is avoided; the time of transporting each vehicle is shortened under the condition of safety driving and the transportation efficiency is improved; compared with manual and long-distance remote control parking and positioning, locomotive unmanned driving and accurate positioning of a locomotive in an ore drawing working link have the advantages that the ore loading working efficiency is high; the mine rail locomotive unmanned automatic driving system is adaptive to a foresight obstaclemonitoring system under various environments and each obstacle can be accurately identified; collision accidents are avoided and the safety of production and transportation is improved; the mine raillocomotive unmanned automatic driving system has a wide applicable range and is easy to generalize and popularize.

The invention relates to a vehicle intelligent voice control system suitable for a complex environment and a construction method thereof. The control system comprises an audio input and output unit, asignal preprocessing unit, a signal denoising unit, a signal blind source separation unit, a signal classification unit, a speech keyword recognition unit, a data analysis unit, and a function execution unit, which are connected to each other. The advantages of the invention are as follows: 1) a wavelet threshold denoising method is used to remove complex noise, an optimal wavelet basis can be adaptively selected, and a threshold can be selected according to changes in noise; 2) an underdetermined blind source separation method is introduced to separate a speech instruction from a mixed audioincluding many interferences, thereby improve the recognition rate of the speech instruction; 3) the system only uses a binary microphone as an audio input end, which saves the cost; and 4) all the interfaces adopt a common interface standard, the compatibility is strong, and the system is easily applied to various vehicle platforms.

The invention discloses an identifying and graph-auditing method of a building industry engineering CAD drawing. The method comprises the following steps: S1, parsing CAD drawing data, and extractingpixels; S2, denoising and normalizing the pixels; S3, constructing graphics, which need to be identified, by the normalized pixels; S4, establishing determined relationships among the graphics; S5, inversely deducing undetermined relationship graphics through the graphics of the determined relationships to exclude suspected graphics; and S6, submitting the graphics and the data to a service end for rule verification, and returning a verification result. According to the identifying and graph-auditing method of the drawing of the invention, all CAD-format drawings can be identified, whether theCAD drawings drawn by construction industry designers go against national standards can be judged, graph-auditing efficiency is improved, and manpower and time consumed for graph-auditing are saved.

The invention relates to a recognition device and a recognition method for the fold of a paper currency. The recognition device for the fold of the paper currency comprises a laser light source, a rectangular raster, an area array photoelectric sensor, an imaging lens assembly and a signal processing module, wherein the laser light source is used for giving out laser light rays, the rectangular raster is located above the laser light source and is used for modulating the laser light rays into stripes which are changed to be bright or dark in accordance with the regular rules on the surface of the paper currency, and the area array photoelectric sensor is used for acquiring images; the imaging lens assembly is located above the area array photoelectric sensor and is used for gathering an image of the surface of the paper currency on the area array photoelectric sensor, and the signal processing module is electrically connected with the area array photoelectric sensor and is used for processing image signals. According to the recognition method for the fold of the paper currency realized by the device is used for converting the inspection whether any fold exists into the inspection whether the feature images of the raster stripes are bent, therefore the influence on the fold of the paper currency caused by a color shift phenomenon due to the change of a grey level of the image acquired of the paper currency at different temperatures can be effectively prevented, and the recognition on the fold of the paper currency can be improved.

The invention relates to an identification method of point-distributed coding marks, comprising the following steps of: firstly, determining an initial point set and searching a point 3, a point 1 and a point 2; secondly, searching a point 4 and a point 5; and finally carrying out affine transformation and determining a coded value until all coded marks are identified. By using the method, accurate identification of all coded marks can be realized and the reasonability of the design of all point-distributed coding marks can be verified simultaneously.

According to the Chinese tourism field named entity identification method based on the graph convolution neural network, the graph convolution neural network comprises an input layer, an embedded layer, a graph convolution layer and a hierarchical structure, and an input body comprises a named entity and a non-entity; the method comprises the following steps: S1, simultaneously expanding to two sides by taking any non-entity of a tourism domain text as a center until a single character in a complete sentence is traversed; S2, extracting character features; S3, extracting character features; S4, inputting and training; S5, optimizing a graph convolution layer; S6, labeling all named entities in the tourism field text data, introducing a Laplace regularization loss function into the graph convolution layer so as to mine node internal structure information and extract character features; and S7, obtaining a hierarchical relationship between the named entity and the non-entity. According to the method, the character feature extraction method is constructed by using the graph convolution neural network, and semantic modeling is performed on the character features so as to realize correct identification of the named entities in the text.

The invention discloses an SNP (Single Nucleotide Polymorphism) marker for identifying dendrobium huoshanense C.Z. Tang et S.J.Cheng and a molecular detection method for the SNP marker, and provides application of SNP of the following SNP site in a dendrobium genome or a substance for detecting the SNP of the following SNP site in the dendrobium genome to identification or auxiliary identification of dendrobium. The SNP site in the dendrobium genome corresponds to the 113th site of a nucleotide sequence shown in sequence 3 in a sequence table; a nucleotide at the SNP site is T or G. According to the SNP marker and the molecular detection method, sequencing analysis is performed on 27 kinds of dendrobium samples comprising all species of dendrobium huoshanense C.Z. Tang et S.J.Cheng complexes to find the functional SNP molecular marker only existing in the dendrobium huoshanense C.Z. Tang et S.J.Cheng by virtue of an RAD (Restriction Site Associated) technology, and the detection method for the SNP marker is established to accurately identify the dendrobium huoshanense C.Z. Tang et S.J.Cheng and other dendrobium (comprising hybrids of the dendrobium huoshanense C.Z. Tang et S.J.Cheng and the other dendrobium).

The invention provides a vehicle counting method and system, data processing equipment and intelligent shooting equipment, and relates to the technical field of vehicle counting. The vehicle countingmethod comprises the steps that firstly, similarity measurement matching is conducted on a motion trail and at least one model trail; secondly, determining a model trajectory corresponding to an optimal result as a target model trajectory of the motion trajectory according to the optimal result in at least one matching result matched in response to the similarity measure; wherein the target modeltrack belongs to one of the at least one model track; then, judging whether the lifetime corresponding to the motion trail is matched with a standard lifetime corresponding to the target model trail or not; and finally, during matching, counting the to-be-identified vehicles corresponding to the motion trails. Through the arrangement, the recognition rate of the motion trails of the vehicles can be improved, and accurate counting of the vehicles is effectively achieved.

The invention relates to a problematic cable / concentrated load progressive recognition method on the basis of generalized displacement cable power monitoring, which is on the basis of cable power monitoring. Bracket generalized displacement, cable structure temperature and ambient temperature are monitored to determine whether a mechanical calculation reference model of the cable structure needs to be updated, thereby obtaining a mechanical calculation reference model of the cable structure counting in the bracket generalized displacement, cable structure temperature and ambient temperature; and the calculation is performed on the basis of the model to obtain unit-damage monitored quantity value change matrix. The noninferior solution of the evaluated object current nominal damage vector is calculated according to the near linear relationship among the monitored quantity current value, monitored quantity current initial value vector, unit-damage monitored quantity value change matrix and unknown evaluated object current nominal damage vector, thereby eliminating the influence of interference factors and recognizing the concentrated load variation and problematic cable in the presence of bracket generalized displacement and temperature change.

The invention brings forward an image fuzzy identification method of a standard constant temperature bath glass thermometer. The method comprises the following main steps: acquiring a fuzzy image of the thermometer, converting the acquired fuzzy image into a gray-scale map, performing threshold processing on the gray-scale map; performing rotation correction on the fuzzy image after the threshold processing, and obtaining a liquid column position of the thermometer by use of a projection method; segmenting the fuzzy image after the rotation correction to obtain a graduation line subarea, a liquid column subarea and an indication character subarea; performing morphological processing on the subareas to obtain pixel coordinates of a graduation line and a liquid column fixed point; and performing character search on the indication character subarea to identity characters and obtain temperature information of the graduation line, and finally obtaining an indication temperature of the thermometer in the acquired fuzzy image. According to the invention, thermometer characters are identified by use of a fuzzy closeness algorithm, fuzzy closeness digital repair is performed on incomplete digits, correct identification of incomplete characters is realized, the correct rate of the identification is about 96%, and the thermometer reading accuracy can reach 95%.

The invention provides a linear displacement progressive type identification method for strain monitoring of a damaged cable and an intensive load. According to the linear displacement progressive type identification method, whether a mechanical calculation reference model of a cable structure needs to be updated or not is determined based on the strain monitoring through monitoring support linear displacement, a temperature of the cable structure, an environment temperature, an integrated load change degree and a damage degree of the damaged cable to obtain a new mechanical calculation reference model of the cable structure, which includes the support linear displacement, the integrated load change degree, the damage degree of the damaged cable and the temperature; when the support linear displacement and the temperature are changed, influences of interference factors are eliminated based on the model according to a similar linear relation of a current numerical value vector of a monitored amount, a current initial numerical value vector of the monitored amount, a monitored amount numerical value change matrix of a unit damage and a current nominal damage vector to be solved, and the change amounts of the damaged cable and the intensive load are identified accurately.

The invention discloses a method for recognizing a pedestrian in a monitoring system without an overlapped area. The method comprises the following steps of performing color correction among a plurality of cameras, and ensuring that a corrected image is IMi, i=(R, G, B); representing the corrected image IMi, i=(R, G, B) in the step 1 as a product of an intrinsic reflective image RIi, i=(R, G, B) and a radiation image SIi, i=(R, G, B), and extracting the intrinsic reflective image RIi, i=(R, G, B) of the target image; extracting a spatial histogram according to the intrinsic reflective image RIi, i=(R, G, B); recognizing a target; and calculating the similarity of spatial histograms of images acquired by all cameras in the monitoring system and a camera 1, and when the obtained maximum similarity is more than or equal to a set threshold value Th, confirming that the two images are the same target, otherwise, indicating that the target walks out of a monitoring field. The invention has the beneficial effect that the same target is correctly recognized by different cameras under different light sources in different environments.

The invention discloses a recognition method for uplink interference types. The recognition method includes the steps that for each cell, interference reference indexes of the cell are counted in each statistics period, and evaluation parameters of the cell in the current statistics period are calculated according to the statistics result, wherein the interference reference indexes comprise cell telephone traffic ERL, cell-level interference band statistical values OUTB1 and carrier-frequency-level interference statistical values trxinterf, and the evaluation parameters comprise the standard deviation delta of carrier-frequency-level interference statistical values trxinterf of all carrier frequencies in the cell; for each cell, when each interference determining period is reached, the current interference type of the cell is determined according to the statistical values of the interference reference indexes and the evaluation parameters. The uplink interference types can be rapidly, effectively and accurately recognized by the adoption of the recognition method.

The invention discloses a hybrid-monitoring linear displacement progressive identification method for a defective cable and concentrated loads. On the basis of hybrid monitoring, whether a mechanical calculation reference model of a cable structure needs to be updated or not is determined by monitoring temperature of the cable structure and environment temperature, a mechanical calculation reference model of the cable structure taking the temperature of the cable structure and the environment temperature into consideration is obtained, and on the basis of the model, a numerical value changing matrix of unit damage monitored quantities is obtained through calculation. According to the approximate linear relation between current numeric vectors of monitored quantities, current initial numeric vectors of the monitored quantities, the numerical value changing matrix of the unit damage monitored quantities, and current nominal damage vectors of evaluated objects to be solved, the non-inferior solution of the current nominal damage vectors of the evaluated objects to be solved is calculated, and accordingly, when the temperature changes, linear displacement of a supporting seat, variable quantities of the concentrated loads and the defective cable can be identified at the same time.

The invention discloses an automobile and road speed limit sign recognition method and device, and the method comprises the following steps of obtaining a road speed limit sign image, carrying out theequalization processing of the road speed limit sign image, obtaining a corresponding equalization image, and enabling the road speed limit sign image to be a grayscale image; carrying out binarization processing on the equalization image to obtain a binary image with a foreground pixel point and a background pixel point of the road speed limit signboard; carrying out segmentation processing on the binary image according to the foreground pixel points to obtain a character sequence image with speed limit value characters; and respectively carrying out matching calculation on the character sequence image and the plurality of character template images to obtain a speed limit value corresponding to the road speed limit signboard. According to the road speed limit sign recognition method, theaccurate recognition of the speed limit value corresponding to the road speed limit sign can be achieved, and the driving safety can be improved.

The invention relates to a problematic cable / concentrated load progressive recognition method on the basis of linear displacement angle monitoring, which is based on angle monitoring. Bracket linear displacement, cable structure temperature and ambient temperature are monitored to determine whether a mechanical calculation reference model of the cable structure needs to be updated, thereby obtaining a mechanical calculation reference model of the cable structure counting in the bracket linear displacement, cable structure temperature and ambient temperature; and the calculation is performed on the basis of the model to obtain unit-damage monitored quantity value change matrix. The noninferior solution of the evaluated object current nominal damage vector is calculated according to the near linear relationship among the monitored quantity current value, monitored quantity current initial value vector, unit-damage monitored quantity value change matrix and unknown evaluated object current nominal damage vector, thereby eliminating the influence of interference factors and recognizing the concentrated load variation and problematic cable in the presence of bracket linear displacement and temperature change.

The invention provides a degradation fault point identification method, device and system. The identification method comprises the following steps: deploying nationwide network quality probes, acquiring real-time Trace data of a poor-quality link; according to the IP address information of the dial testing source of each poor-quality link, obtaining IP address information; determining a first province, determining the degradation fault point according to the real-time Trace data and historical Trace data of all nodes to the path in the first province. Accurate identification of network degradation and accurate positioning of the degradation occurrence position are realized, and thus operation and maintenance management of a large-scale network is facilitated.

The invention relates to the field of artificial intelligence, and discloses a medical image recognition method, device and equipment, and a storage medium. The method, the device and the equipment are applied to the field of smart medical treatment, and are used for improving the medical image recognition efficiency. The method comprises the following steps: receiving an initial image sent by a user terminal; classifying the initial image, and determining the image type of the initial image; when the initial image is a medical feature image, performing image segmentation on the medical feature image through a preset double-attention network model to obtain a medical foreground image; correcting the medical foreground image to obtain a corrected medical foreground image; performing text detection on the corrected medical foreground image to obtain a target text; performing character recognition on the target text to obtain a recognized field; correcting and checking the index field inthe identified field to obtain a corrected field; and classifying the corrected field to obtain a classification result, and sending the classification result to the target terminal.

The embodiment of the invention discloses a pseudo base station recognition method and a terminal. The method comprises steps: if a to-be-recognized base station is connected, the identity information of the to-be-recognized base station is acquired; the current position information of the terminal is acquired; according to the position information, a legal base station list in a preset range corresponding to the position information is acquired from a preset server, and the preset server pre-stores a corresponding relationship between the identity information of a legal base station and the position of the legal base station; and if the identity information of the to-be-recognized base station is not included in the legal base station list, the to-be-recognized base station is determined to be a suspected pseudo base station. According to the embodiment of the invention, the corresponding legal base station list is searched from the preset server through using the position information, whether the to-be-recognized base station is included in the legal base station list is judged, accurate recognition on the pseudo base station can be realized, leakage detection is not caused, the existing legal base station does not need to be changed, and the realization cost is reduced.

The invention relates to an identity management method for material files and material data of the structure construction industry. According to the method, file type detection and conversion are performed on the material files of the structure construction industry, and effective type files are determined, so that the obtained files can be processed according to a unified way; the effective type files are detected, and effective data files are determined, so that efficiency of subsequent identity and management is improved; material names and material attribute values of the effective data files are identified from the effective data files by utilizing a preset national standard material database, so that accurate identity of the material data is realized; associate attribute data is formed by the material names and the material attribute values, subsequent query and use are facilitated, and the efficiency and accuracy of query and use are improved favorably. According to the identity management method, the identity and management of the material files and material data are finished automatically without relying on manual operation too much, the work efficiency can be improved greatly, and the operation cost is obviously lowered.

Disclosed is a strain-monitoring damaged cable centralized load generalized displacement recognition method. The strain-monitoring damaged cable centralized load generalized displacement recognition method is based on strain monitoring. Whether a mechanical calculation reference model of a cable structure needs updating or not is determined through monitored cable structure temperature and environment temperature, and the mechanical calculation reference model, where the cable structure temperature and the environment temperature are reckoned, of the cable structure is acquired. A unit damage monitored amount numerical value variation matrix is acquired on the basis of the model. The non-inferior solution of an evaluated object current name damage vector is worked out according to the approximate linear relation between a monitored amount current numeric vector and a monitored amount current initial numerical value vector, the unit damage monitored amount value variation matrix and the evaluated object current name damage vector to be worked out. Accordingly, when temperature changes, a support generalized displacement, centralized load variable quantity and a damaged cable can be recognized.

The invention discloses a progressive type damaged rope and concentrated load identification method based on angular displacement strain monitoring. Whether a mechanical calculation reference model of a rope structure is required to be updated can be determined by monitoring an angular displacement of a support, a temperature of the rope structure, an ambient temperature, the change degree of concentrated load and the damage degree of the damaged rope based on strain monitoring, so that a new mechanical calculation reference model taking the angular displacement of the support, the change degree of the concentrated load, the damage degree of the damaged rope and the temperature into consideration is obtained; on the basis of the model, the influence of interference factors can be eliminated according to a similarly linear relation among a current numeric vector of a monitored value and a current initial numeric vector of the monitored value, a unit damage monitored value numeric change matrix as well as a current nominal damage vector to be calculated under the conditions that the angular displacement of the support and the temperature are changed, so that the damaged rope and the change value of the concentrated load can be accurately identified.