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 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 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 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.

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 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 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 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.