69 results about "Network characterization" patented technology

Deployment of an application is managed using available resources from a resource system. A resource dependency characterization of the application is established to enable deployment of the application. A logical characterization and a network characterization of a desired deployment are also established. A deployment plan containing an outline for resources and configurations used for deployment is developed based on the resource dependency characterization, the logical characterization and the network characterization. The deployment plan is processed for correlation with the available resources. The processed deployment plan is then implemented.

A method of selecting a gateway node in a remote network and for handing over to the selected gateway node. Nodes in a remote energy aware network connect through a gateway node to a backbone network in an interplanetary communications network. Each node optimizes a stability function describing communications to neighboring nodes and to the backbone. Optimization is for maximum network stability and for efficient node energy consumption. Optimization identifies a handover time and nodes initiate handover sufficiently in advance of the identified handover time to complete at that time. Nodes continually monitor and update network characterization parameters to identify a next optimal handover time.

Embodiments of a method of calculating the equivalent series resistance of a matching network using variable impedance analysis and matching networks analyzed using the same are provided herein. In one embodiment, a method of calculating the equivalent series resistance of a matching network includes the steps of connecting the matching network to a load; measuring an output of the matching network over a range of load impedances; and calculating the equivalent series resistance of the matching network based upon a relationship between the measured output and the load resistance. The load may be a surrogate load or may be a plasma formed in a process chamber.

A method of characterizing a wiring network is implemented in a system which includes a test controller and at least two probes. On commands from the test controller, at least one of the probes changes its impedance between the nominal impedance of the wiring network and a mismatch impedance. Reflectometry measurements are performed before and after of switching the impedance of the second probe. At the first probe, an RF signal is generated and a reflected signal is measured. Then, the impedance of the second probe is changed, and again an RF signal is generated and a reflected signal is measured at the first probe. Additionally, a frequency response may be measured at the second probe. The results of the measurements are used for characterization of a transmission line between the first and second probes

The invention provides a network representation learning method based on a meta-structure and a graph neural network. According to the method, the information of the neighbor nodes is aggregated through the graph neural network and the weighted attention mechanism, the candidate meta-structure set is generated through the hierarchical search algorithm, meta-structures do not need to be defined inadvance, and compared with a previous meta-path, the method can consider more complex structure information between the nodes. According to the method, the strong learning ability of the graph neuralnetwork and the rich semantics of the meta-structure are fused, and the problems that an existing meta-path-based method is single in consideration structure and needs to depend on experience to specify the meta-structure are effectively solved. Moreover, the introduction of a weighted attention mechanism can explicitly consider the quantity information in the meta-structure. And a final node which is more accurate than a result of a traditional representation classification mode is generated, and the final node can be used as vector representation to be used in subsequent other machine learning figures.

The invention discloses a rapid network representation learning algorithm based on a width learning system. The method comprises the following steps of S1, importing a network graph module based on atext, parsing and storing a network topological structure in a dictionary format, wherein keys in the dictionary represent network nodes, values corresponding to the keys form a list and represent a node sequence at the other end of the edge where the nodes are located; S2, performing random walk on the network nodes to generate a walk sequence; S3, constructing a network representation learning model based on a width learning system, taking the walking sequence generated in the step S2 and a representation vector with the dimension of K as input, generating a feature vector of a network nodein a feature vector layer, and enhancing the nonlinear classification capability of a network representation learning model by introducing an activation function in an enhancement vector layer to finally realize text-based network multi-label classification. A width learning system model is adopted in the algorithm, and representation learning of network nodes can be rapidly completed.

The invention discloses a personalized commodity recommendation method and system based on multilayer heterogeneous attribute network representation learning, and the method comprises the steps: taking an interaction behavior between a user and a commodity as an edge, constructing a multilayer heterogeneous attribute network, and carrying out the decoupling of the multilayer heterogeneous attribute network into a plurality of simple binary networks; performing weighted accumulation on the adjacency matrixes of all the binary networks to obtain a newly combined adjacency matrix, and performingspectrogram conversion; fusing the adjacency matrix and the node attribute characteristic matrix after spectrum conversion, and finally obtaining representation vectors of all nodes by using a randomprojection method; obtaining a verification set from the historical data to perform parameter adjustment, and obtaining a representation vector of each node; and measuring the preference of the user to the commodity by utilizing cosine similarity so as to carry out personalized recommendation. According to the invention, various interaction behaviors between the user and the commodity are considered at the same time; the interactive relationship among various behaviors can be captured without human intervention; attribute information of users and commodities is effectively fused; network representation learning is carried out by using random projection so that the method efficiency is greatly improved and the recommendation performance is improved.

A medical image super-resolution reconstruction method based on multi-attention residual feature fusion combines two modules of a channel attention mechanism and a space attention mechanism, and enables a network to perform weighting processing on features of an input image, thereby solving the problem of insufficient network characterization capability caused by equal processing of the input features. A residual attention feature fusion module (RAFF) is provided, local features in the neural network are fused, and global features are fused, so that local residual features in the whole network can be more fully utilized, and the problem that the deep neural network is too deep and the learning ability of the network is insufficient is solved. According to the method, super-resolution reconstruction is effectively carried out on the medical image, and the image super-resolution reconstruction performance of a deep super-resolution network can be improved.

The invention relates to the technical field of network characterization, in particular to a network characterization method based on cross-double-layer network random walk, which comprises the following steps of: A) establishing a network topological structure; B) obtaining a role similarity matrix; C) establishing a double-layer hybrid network; D) obtaining a random walk sequence; And E) obtaining the representation of the network by using the continuous bag-of-words model. The method for establishing the role similarity matrix S comprises the following steps of: B1) listing all subgraphs with sizes smaller than or equal to a given size k; B2) enumerating a non-isomorphic track, and recording the number as m; B3) expressing the condition that each node participates in m roles by using avector with the length of m; And B4) taking the similarity of the role representation vectors of every two nodes as the similarity of the two nodes and a role similarity matrix S. The method has the advantages that by means of the random walk model and the continuous bag-of-words model, representation of network adjacency and structural similarity is fused at the same time, and effective representation of non-connected network nodes with similar roles can be achieved.

The invention provides a fungus image recognition method and device, electronic equipment and a storage medium. The method comprises the steps that at least one base network of a pre-trained fusion network model is used for extracting features of a plurality of fungus images, fusion features are obtained, the base network represents a neural network for conducting convolution operation and fusionoperation on the images, and the angles or growth periods of fungi in the fungus images are different; and the classification layer of the fusion network model is used to identify the fusion featuresto obtain the classification of the fungus images. In the implementation process, the features of the fungus images are extracted by using at least one base network of the fusion network model to obtain the fusion features, and the classification layer of the fusion network model is used for identifying the fusion features to obtain the classification of the fungus images, so that the efficiency of identifying the fungus images is effectively improved.

The invention discloses a network service anomaly detection method and device based on attribute network representation learning, and the method comprises the steps: obtaining initial network servicedata, constructing a heterogeneous information network based on the initial network service data, and obtaining a node attribute set; constructing an attribute vector set based on the node attribute set, and constructing an attribute information network according to the attribute vector set and the heterogeneous information network; constructing a target function based on the attribute informationnetwork, and constructing a mapping relationship between nodes in the attribute information network and vector representations corresponding to the nodes based on vectors corresponding to the nodes to be learned in network representation learning obtained by solving the target function; and training based on the training set data to obtain an anomaly detection model, and calculating an anomaly probability of each piece of network service data in the test set data according to the anomaly detection model. According to the method, the relevance of the nodes in the attribute information networkis enhanced, the generalization ability of the anomaly detection model is improved, and better guarantee is provided for anomaly detection, anomaly interception and fund security protection of users and enterprises.

The invention relates to a network characterization method based on an adversarial attention mechanism. The method comprises a double-mapping-function model, the first mapping function is used for distributing different weights to different node pairs through a graph attention network according to node attribute information and network topology information of real data, and an original network ismapped to a low-dimensional space to obtain more accurate low-dimensional expression of the real data; the second mapping function is node attribute information and network topology information whichare obtained by combining the obtained low-dimensional expression of the real data with disturbance to obtain noise and inputting the noise into a generator to be mapped into noise; the two functionsare used as two tuples to be input into a discriminator to be discriminated, optimization of a generator and an encoder is carried out through a result given by the discriminator, and finally low-dimensional expression which is good in robustness and capable of completely storing original network information is obtained. According to the method, the graph attention network is adopted for network representation, the correlation degree between different nodes is considered, the method is closer to the actual situation, and the effect is better.

The invention provides a network representation acquisition method based on deep learning. The method comprises the following steps: 1, obtaining a network containing node content, the network containing the node content comprises |V| nodes, selecting any one node from the |V| nodes as a current root node, performing random walk on the network containing the node content according to the current root node to obtain a content sequence and a node identification sequence; and step 2, inputting the content sequence into a deep learning model based on an attention mechanism to obtain a predicted identification vector sequence, i.e., a network representation vector, and randomly walking the network containing the node content according to the current root node to obtain a content sequence and anode identification sequence. According to the method, the research result of the deep learning technology in the machine translation direction is applied to network representation learning, and the content and the structure of the network are fused from the perspective of machine translation to obtain an appropriate network representation vector.

A protein and nucleic acid binding site prediction method based on graph neural network characterization comprises the following steps: constructing a protein and nucleic acid interaction data set, extracting the position and feature information of each residue in the protein and the structural context thereof after sample fusion processing, and constructing graph representation of the structural context of the residues according to the graph representation. And predicting the graph representation of the to-be-predicted protein through the hierarchical graph neural network to obtain the probability that each residue is combined with DNA/RNA, thereby realizing prediction of the binding site of the protein and the nucleic acid. Key structures and feature patterns of binding sites are learned from graph representations through graph representations based on residues of structural context and a hierarchical graph neural network model.

The invention relates to a network characterization algorithm stability measurement method, which comprises the following steps of: utilizing a network characterization algorithm to keep the characteristic of a relation between network nodes, and judging the stability by using whether a nearest neighbor set of nodes in a characterization space is consistent or not; Mapping a network into a multi-dimensional continuous dense vector space by adopting a certain representation method, and calculating the first K nodes closest to each node as the basis of stability measurement by utilizing cosine similarity; a plurality of vector spaces are generated for multiple times by adopting the same representation method for one network, and the similarity of nearest neighbor sets in the vector spaces iscalculated for one node, including the coincidence rate of the nodes and the ranking information of the coincidence nodes. According to the method, the stability performance of different algorithms on different network sets can be effectively measured, so that the influence of any factor on the stability of network characterization and the influence magnitude can be further disclosed.