38results about How to "Avoid Blind Searches" patented technology

The invention relates to an EHV (Extra-High Voltage) power grid fault rule mining method based on a rough set association rule. According to the method, a distributed data mining idea is adopted, historical fault data of an EHV power grid is subjected to fault rule mining by using an association rule mining method based on a rough set theory, a distributed decision table is subjected to attribute reduction by using an attribute reduction algorithm based on an information entropy, and then, an Apriori algorithm in association rules is applied to the decision table, which is subjected to reduction, so as to carry out fault rule extraction. According to the method, the problem of inadaptability to large-data-volume historical fault databases of traditional data mining methods can be solved effectively, the complexity of rule extraction is lowered, and the method has the advantage of high fault rule mining efficiency.

The invention relates to the technical field of biometric identification and discloses an iris positioning method and an iris identification system. The method and the system are based on mathematical morphology, Radon transform, canny operator and hough transform. The algorithm comprises the positioning of an inner edge and an outer edge, wherein in the positioning of the inner edge, based on a gray projection method of line detection, a binarized image is processed by using the principle of the mathematical morphology so as to remove the interference of noise; and in the positioning of the outer edge, an iris image is processed by using the principle of the mathematical morphology at first, then an upper eyelid and a lower eyelid are detected by the Radon transform to remove the interference, and finally, an edge is extracted by a canny algorithm and the external edge of the iris is detected by the hough transform. Therefore, large area blind searching can be avoided so as to improve positioning speed.

The present invention discloses an on-vehicle pedestrian area estimation method based on optical flow clustering, which comprises: carrying out optical flow estimation on the image obtained by a camera to obtain an image optical flow field; performing optical flow clustering again so as to estimate the background area; eliminating the background area; using the graph segmentation algorithm to segment the foreground area; finally, discriminating the areas in the foreground area; and identifying the valid pedestrian area. The on-vehicle pedestrian area estimation method based on optical flow clustering proposed by the invention avoids the blind search for pedestrian recognition caused by global template searching and matching adopted by a traditional pedestrian detection system, which is suitable for intelligently assisted driving or unmanned driving of vehicles in an on-vehicle environment and overcomes the problem that it is difficult to determine the Gaussian distribution of the background by common EM algorithm and clustering algorithm such as K-mean algorithm. The optical flow clustering algorithm proposed by this method can estimate the background area more effectively. In the process of discriminating the foreground pedestrian areas, the non-pedestrian area can be effectively eliminated and the pedestrian area can be obtained by using the morphological characteristics of the human body.

The invention discloses a vehicle-mounted intelligent parking guidance system which consists of a vehicle-mounted navigation unit and several wireless devices for transmitting the information of parking lots, wherein first wireless communication modules transmit the coordinates of the parking lots and the numbers of vacant parking spaces through 2.4G common communication channels, a GPS (Global Positioning System) module obtains the coordinate of the vehicle and then transmits the coordinate to a second microprocessor, a second wireless communication module receives the coordinates of the parking lots and the numbers of the vacant parking spaces transmitted by the first wireless communication modules, the second microprocessor compares the coordinate of the vehicle with the coordinates of the parking lots to calculate the distance from the vehicle to each of the parking lots, and the second microprocessor optimizes the distance to each parking lot and the vacant parking spaces, and predicts and dynamically optimizes the relative bearing of the parking lot. The vehicle-mounted intelligent parking guidance system is capable of conveniently, rapidly and flexibly guiding a driver to search a parking lot so as to conveniently and rapidly park the vehicle in an unfamiliar road network.

The invention discloses a low-energy-consumption task scheduling strategy for CPU-GPU heterogeneity, and provides an ant colony task scheduling algorithm capable of simultaneously paying attention toreal-time constraints and system energy consumption aiming at the characteristics of a heterogeneous multi-core system and the problems that a traditional ant colony algorithm only optimizes a singletarget and is too slow in convergence speed. The method comprises the following steps: firstly, providing guidance information in a pheromone initialization process according to the energy consumptionof a task on a heterogeneous core; accelerating algorithm convergence speed, then, the cores are screened through task real-time constraint conditions; the method comprises the steps of obtaining a heterogeneous core of a task, selecting an appropriate execution core according to the calculation energy consumption of the task on the heterogeneous core, the inter-core communication energy consumption of different tasks and the pheromone content, continuously searching a scheduling scheme with lower energy consumption through multiple iterations of an ant colony algorithm, and adjusting the pheromone content according to the obtained result to further accelerate the convergence speed of the algorithm. A final task scheduling scheme is obtained after a plurality of iterations, so that the energy consumption of the system can be optimized under the condition that the real-time constraint of the task is met.

The invention discloses an intelligent navigation algorithm based on real-time traffic status. According to the invention, an ant colony algorithm is applied to the field of automobile navigation; a traffic flow factor is considered; the traffic flow is served as a parameter influencing ant colony pheromone and the road section with short distance and smooth traffic is selected for the automobileas far as possible, so that the purposes of avoiding congested road section and balancing the traffic flow of a road network can be achieved; the performance of the algorithm is greatly promoted in amanner of dynamically adjusting the evaporation rate and introducing the thought of elitist ants, in order to overcome the defects of low convergence rate and possibility of falling into local part ofthe ant colony algorithm when the road network node is increased.

The invention relates to a reinforcement learning tri-state combination long-short-term memory neural network system. The system comprises a long-short-term memory neural network, a reinforcement learning unit and a monotone trend recognizer. The monotonous trend recognizer judges a trend state of the input time sequence, the reinforcement learning unit, according to a trend state according to theinput time sequence, selects the number of hidden layers, the number of hidden layer nodes and the long-short-term memory neural network adaptive to the change rule of the number of the hidden layersand the number of the hidden layer nodes, wherein the trend state of the input time sequence comprises three states, and each trend state corresponds to one hidden layer, the number of hidden layer nodes and the long-short-term memory neural network adaptive to the change rule of the number of the hidden layers and the number of the hidden layer nodes. According to the method, the trend of the input time sequence is judged, the optimal action is selected to be executed according to the updated Q value set, the network generalization capability is enhanced, and the relatively higher predictionprecision is achieved on the degradation trend of the rotary machine; and by outputting an error calculation reward, the convergence speed of the network is improved, and the calculation efficiency of the system is improved.

The invention relates to a reinforcement learning unit matching recurrent neural network system and a training and prediction method thereof. The system includes recurrent neural networks, a reinforcement learning unit, and a monotone trend recognizer. The recurrent neural network includes input and output, and a plurality of hidden layers. The hidden layers include a plurality of hidden layer nodes. The monotonous trend recognizer judges the trend state of a time sequence constructed by input, and the reinforcement learning unit selects a recurrent neural network with the number of hidden layers and the number of hidden layer nodes matched with the change rule of the hidden layer nodes according to the trend state of the input time sequence. According to the invention, the trend state ofthe input time sequence is judged. The trend state, different hidden layer numbers and hidden layer node numbers are used for representing the state and action of the Q value set respectively, the optimal action is selected to be executed according to the updated Q value set, the generalization capability and convergence speed of the RLUMRNN are enhanced, and the residual life prediction method applied to the rotary machine is high in precision.

The invention claims the protection of a method of positioning an instrument to be recognized for an electric inspection robot, and relates to the technical field of image processing application. The method includes the steps of taking pictures using preset parking of a robot at an instrument to be recognized; setting the number of pictures required to be taken at each position under a set focal length; positioning the position of the instrument accurately through a transform matrix and extracting information of a dial plate; then binarizing the region; and finding out the position of a pointer and the reading. The method has the characteristics of high reading accuracy of the position of the dial plate, low pre-processing requirement of the pictures, and strong robustness for illumination, shadows and other interference.

The invention discloses a preventive maintenance decision-making optimization model for key components of a train bogie based on maximum and minimum ant colony algorithms. The preventive maintenance decision-making optimization model for key components of the train bogie and the constraint conditions there of are built, and then the opportunity maintenance threshold and maintenance cost are obtained according to the maximum and minimum ant colony algorithms. A method employed by the model comprises the following steps: setting a node set Ci; setting relevant parameters; placing m ants on the nodes to start visit, and then counting the path length of each ant, and recording as a current best solution; updating the path information according to an information update principle until all nodesare visited; evaluating the solution of the access path of each ant according to an optimization target of a model E, and selecting a solution with the shorter path as an updating value, wherein thenumber of ants visiting the path will be gradually increased with the shorter path and stronger pheromones; finally, judging the relationship between the number of current iterations and the total number of times, and finding out an optimal solution. The model is high in calculation speed, is high on solving relation, and can effectively reduce the maintenance cost of the key parts.

The invention discloses a pupil accurate measurement method based on a rapid human eye semantic segmentation network. The method comprises the steps: (a) carrying out the accurate segmentation of a pupil based on the rapid human eye semantic segmentation network, so as to obtain a pupil region; (b) in the fast human eye semantic segmentation network, expanding convolution and common convolution are in parallel, and the local refinement capability is improved while the receptive field is expanded; and (c) introducing a plurality of attention generation modules, fully extracting semantic features, and obtaining a refined semantic result. Features of different levels are extracted through down-sampling, and reasoning is carried out by combining up-sampling to the size of an original image. According to the method, refined reconstruction of pupils is completed on the basis of pupil semantic feature extraction, so that automatic semantic segmentation is carried out. Some blind searches existing in previous algorithms are avoided.

This invention provides an intra-frame prediction coding method based on image interpolation, comprising following steps: cutting input images into a plurality of sub-images; configuring a prediction reference frame through the interpolation operation; processing difference coding with the reference frame by using sub-image as a basic prediction unit, thereby avoiding the prediction process of per-pixel multi-mode of the traditional method. The inter-frame prediction using this invention is capable of greatly reducing the calculation load and has higher prediction precision; in addition, this method can be combined with other coding method so as to obtain better compressing effect. It has been found that the method is capable of obtaining better prediction effect when greatly reducing the calculation cost.

The present invention discloses a 4[Pi] space panorama radioactive source positioning system and method. The system comprises: a three-dimensional ray positioning detector which is a cuboid, wherein any one surface of the three-dimensional ray positioning detector is provided with a multi-channel electronic electrical circuit to obtain a three-dimensional effect position of a gamma ray on the detector; a plurality of collimators arranged on other surfaces of the detector; and a data processing center configured to obtain statistical distribution of a measurement event at each coordinate dimension to obtain distribution information, obtain incident plane information of the gamma ray and perform two-dimensional reconstruction according to coordinate information of other two-dimensional dimensions and the transmission matrix information of the collimators at the incident plane to obtain a two-dimensional position distribution diagram of the radioactive source at the incident plane. The system can obtain a two-dimensional position distribution diagram of the radioactive source according to the coordinate dimension of the measurement event, can obtain radioactive source 4[Pi] positioning field of view, can avoid blind search and can improve the efficiency of radioactive source search.

The invention discloses a mathematical formula search method and device, relates to the technical field of search and solves the problem that in the prior art, the search efficiency is low. The method comprises the steps of obtaining a to-be-searched symbol sequence, wherein the to-be-searched symbol sequence is the symbol sequence formed by converting a to-be-searched mathematical formula; extracting feature symbols in the to-be-searched symbol sequence; carrying out similarity comparison on the feature symbols and a plurality of stored feature symbol sets and outputting a plurality of similarity values, wherein the plurality of feature symbol sets are the symbol sets formed by the symbols with field features, wherein the field comprises mathematics, chemistry, physics and music; comparing each similarity value in the plurality of similarity values with a preset threshold, and when the similarity value is greater than the preset threshold, marking the feature symbol set corresponding to the similarity value; and searching a formula matching the to-be-searched symbol sequence from a formula library in which the marked feature symbol set is located and returning the formula.

The invention provides a communication control method for an interconnected satellite terminal, and the method comprises the steps of enabling the interconnected satellite terminal to collect the equipment information of the interconnected satellite terminal, and transmit the equipment information to a monitoring platform; acquiring time information of a satellite network searched by the interconnected satellite terminal in a future time period, wherein the time information is predicted by the monitoring platform according to the equipment information and the sending time of the equipment information; and after the mobile network communicating with the monitoring platform is lost, enabling the interconnected satellite terminal to switch the satellite network to communicate with the monitoring platform again according to the time information. The method provided by the invention can effectively reduce the power consumption waste of the interconnected satellite terminal.

The invention provides a radioactive source positioning method enabling a radioactive source to be found quickly. The method comprises: acquiring energy of a nuclear radiation event of a radiation source through a scintillation detector; processing the acquired energy to obtain an energy spectrum; comparing the obtained energy spectrum with a pre-stored standard energy spectrum to obtain a type and an incident angle of the radiation source, wherein the pre-stored standard energy spectrum stores a correspondence between the standard energy spectrum and the radiation source type and the radiation source incident angle; and according to spatial position information of the scintillation detector and the incident angle of the radioactive source, obtaining the direction of the radioactive source. The invention relates to the technical field of nuclear radiation detection.

The invention discloses an aircraft searching method and device, a storage medium and a processor. The method comprises the steps: determining a first area where an aircraft falls during falling and asecond area where remote control equipment is located, and the remote control equipment being used for controlling the aircraft; determining a third area including the first area and the second area;determining a first search path of the aircraft in the third area; and indicating a search objecting to search the aircraft according to the first search path. According to the invention, the technical problem of low aircraft searching efficiency is solved.

A low-energy task scheduling strategy for CPU-GPU heterogeneity. Aiming at the characteristics of heterogeneous multi-core systems and the problems of traditional ant colony algorithm that only optimizes a single objective and the convergence speed is too slow, a new method that pays attention to real-time constraints is proposed. and ant colony task scheduling algorithm for system energy consumption. The method firstly provides guidance information in the process of pheromone initialization according to the energy consumption of tasks on heterogeneous cores to speed up the algorithm convergence speed, and then filters the cores according to the real-time constraints of tasks, and then according to the computing power of tasks on heterogeneous cores. According to the energy consumption of different tasks, the energy consumption of inter-core communication and the pheromone content of different tasks to select the appropriate execution core, and finally through the multiple iterations of the ant colony algorithm, the scheduling scheme with lower energy consumption is continuously searched, and the pheromone content is adjusted according to the obtained results. Speed ​​up algorithm convergence. After several iterations, the final task scheduling scheme is obtained, which can optimize the energy consumption of the system under the condition of satisfying the real-time constraints of the task.

The invention relates to the technical field of extreme learning machine classification algorithms, in particular to an extreme learning machine classification algorithm based on an improved crow search algorithm. The method includes the following steps that an ELM network model is built, an ICSA algorithm is adopted, input weights and threshold values generated randomly by the ELM model are optimized, global and local search performance is balanced by introducing an AP value dynamic gradient function, a Levy flight search method is introduced to avoid blind search, a multi-individual variable factor weighted learning method is introduced to guarantee population diversity, and the global and local search performance is improved. And an adjacent-generation dimension crossing method is introduced to enhance the quality of the optimal individual food storage position, so that a local optimal value is prevented from being obtained, and an accurate prediction result is realized. According to the method, a series of defects caused by randomly generating input weights and threshold values are overcome, the ELM model classification precision is improved, and when ELM model parameters are optimized, based on a traditional CSA algorithm, global and local search performance is balanced by introducing an AP value dynamic gradient function, and blind search is avoided by introducing a Levy flight search method.

The invention discloses a positioning system and a positioning method for a radiation source. The positioning system comprises the components of at least two nuclear radiation detectors, a blocking plate and an information processing center. The detectors are used for a nuclear radiation number and energy of the radiation source. The blocking plate is arranged between the detectors and is used for blocking partial nuclear radiation number which is received by at least one nuclear radiation detector. The information processing center is used for reading the signal of the detector and determines direction information of the radiation source. Furthermore according to a position azimuth, the radiation source is searched through driving a trolley, an unmanned aerial vehicle, an unmanned underwater vehicle or a handheld terminal. The positioning system and the positioning method for the radiation source have advantages of low cost, high repeatability and long-term stable operation. The positioning system and the positioning method are used for determining the azimuth, thereby realizing a relatively large positioning visual field, preventing blind searching and improving radiation source searching efficiency. Simple and quick positioning process is realized. Furthermore damage caused by long-term exposure to the radiation source can be reduced.

The invention discloses a robot path planning method based on an improved ant colony algorithm. The method comprises the following steps: introducing a pre-planned path; adding inflection point parameters; and building a deadlock prohibition list. The method improves searching efficiency and effectively avoids the deadlock problem.

The invention provides a client operation management method and a client. The management method comprises the steps that a user registers and logs in the client and sequentially fills in personal information according to a table provided by the client; the client saves the personal information filled by the user and sends the personal information to a cloud through a wireless network; after receiving the personal information of the user, the cloud recommends corresponding service content to the user according to content of the personal information; and the user adds a corresponding service onthe client according to the individual demand. Accordingly, the defects of the prior art are overcome, the design is reasonable, various services can be provided according to the user information, thesearching time of the user is shortened, the user is served in a targeted mode in time, the operation of downloading multiple clients is not needed, the storage memory and the operation memory of a mobile phone are saved, and the user experience is improved.

The invention claims to protect a method for locating an instrument to be identified by a power inspection robot, which relates to the technical field of image processing applications, and includes the following steps: using the robot to stop at the preset instrument to be identified to take pictures, and setting each position needs to be done in the setting The number of pictures taken at the focal length, the position of the instrument is precisely positioned through the transformation matrix and the dial information is extracted, and then the area is binarized to find the position of the pointer and read. The characteristics of this method: it has high reading accuracy of the dial position, has low requirements for image preprocessing, and has strong robustness to interference such as light and shadow.

The invention provides a nuclear radiation detection sensitivity amplifier which can be applied to a CCD / CMOS camera, which belongs to the technical field of nuclear radiation detection. The amplifier comprises a high density amplifier main body, a light shielding cover, a fixation clip and a photoprotection sealing gasket. The high density amplifier main body is used for causing ray which comes into a CCD / CMOS sensor and cannot be detected around the sensor to generate physical interaction with the high density amplifier main body to generate scattering particles and secondary particles and enabling the scattering particles and the secondary particles to come in to the CCD / CMOS sensor at certain probability. The light shielding cover and the photoprotection sealing gasket are respectively located at the upper opening and the bottom of the high density amplifier main body to prevent visible light from coming into the camera. The detachable fixation clip is used to fix the nuclear radiation detection sensitivity amplifier at the camera. The fixation clip can be removed, and the nuclear radiation detection sensitivity amplifier is adhered to a lens for use. According to the invention, the amplifier has the advantages of simple structure, low cost, easy use, good reproducibility and long-term stability; and the nuclear radiation detection sensitivity amplifier can be used with an ideal radiation pick-up algorithm to effectively improve the nuclear radiation detection efficiency and precision of the camera and reduce hazards caused by a radiation source which is exposed for a long time.

The invention discloses a management method of the converged personal network, an apparatus and a system thereof, relating to the converged personal network technical field. According to the invention, the interaction frequency between PN GWs (Personal Network Gateways) and CPNS (Converged Personal Network Service) server is substantially reduced and the information storage operation on the CPNS server is minimized. Thus system resource is saved and work efficiency is improved. The embodiment of the invention provides a management method of the converged personal network. The method comprises the following steps: receiving a merging request message sent by the first Personal Network Gateway in a first personal network; according to the received merging request message, carrying out capability coupling on Personal Network Equipment which is connected with the first Personal Network Gateway and confirming coupling Personal Network Equipment; and merging the Personal Network Equipment into a second personal network.

The invention discloses a heuristic one-dimensional blanking method based on a stratified random search algorithm. The method includes: A, using a parameterized model to signify one-dimensional blanking problems; B, preprocessing billets for combination; C, obtaining various stock layout modes through the stratified random search algorithm combined by random search and deep search; D, picking out an optimal stock layout mode according to a heuristic rule; E, adding the optimal stock layout mode and a time which does not exceed the current needed maximum time of reusing the billets into a current stock layout scheme, and updating a billet set to be laid; F, repeating processes of C, D and E until the total length of the billets to be laid less than the length of raw materials, and outputting the current stock layout scheme; and G, repeating processes of B, C, D, E and F for many times, and then performing compared screening on all stock layout schemes so as to obtain an optimal stock layout scheme. The heuristic one-dimensional blanking method based on the stratified random search algorithm can avoid blindness of a traditional random search algorithm and is high in computation speed, and the obtained stock layout scheme adapts to practical production needs.

The invention discloses a vehicle-mounted intelligent parking guidance system which consists of a vehicle-mounted navigation unit and several wireless devices for transmitting the information of parking lots, wherein first wireless communication modules transmit the coordinates of the parking lots and the numbers of vacant parking spaces through 2.4G common communication channels, a GPS (Global Positioning System) module obtains the coordinate of the vehicle and then transmits the coordinate to a second microprocessor, a second wireless communication module receives the coordinates of the parking lots and the numbers of the vacant parking spaces transmitted by the first wireless communication modules, the second microprocessor compares the coordinate of the vehicle with the coordinates of the parking lots to calculate the distance from the vehicle to each of the parking lots, and the second microprocessor optimizes the distance to each parking lot and the vacant parking spaces, and predicts and dynamically optimizes the relative bearing of the parking lot. The vehicle-mounted intelligent parking guidance system is capable of conveniently, rapidly and flexibly guiding a driver to search a parking lot so as to conveniently and rapidly park the vehicle in an unfamiliar road network.

The invention discloses a vehicle-mounted pedestrian area estimation method based on optical flow clustering, which performs optical flow estimation on images acquired by a camera to obtain an image optical flow field; then performs optical flow clustering to estimate the background area; and eliminates the background area , use the graph segmentation algorithm to segment the foreground area; finally, distinguish each area in the foreground area, and identify the effective pedestrian area. The method for estimating the vehicle pedestrian area based on optical flow clustering proposed by the present invention avoids the use of global templates in traditional pedestrian detection systems. The blind search for pedestrian recognition caused by search matching recognition is suitable for vehicle intelligent assisted driving and unmanned driving in the vehicle environment. It overcomes the problem that the usual EM algorithm and clustering algorithms such as K-means are difficult to determine the Gaussian distribution of the background. The optical flow clustering algorithm proposed in this method can estimate the background area more effectively. In the process of identifying the foreground pedestrian area, the human body shape feature can be used to effectively eliminate the non-pedestrian area and obtain the pedestrian area.