5 results about "Network science" patented technology

The invention discloses a circRNA (Ribonucleic Acid) and miRNA (Micro Ribonucleic Acid) interaction prediction system and a circRNA and miRNA interaction prediction method of a graph Fourier pulse neural network. The method comprises the following steps: on the basis of high-throughput sequencing omics data of complex diseases, constructing a heterogeneous biological information network containing drugs, diseases, proteins, circRNA, miRNA and lncRNA; converting the topological features of the entities into a unified feature space by using a graph convolutional network; designing a pulse graph neural network in combination with Fourier coding and a pulse neural network, and extracting a topological structure and high-order semantic features in the network; fusing sequences, topologies and semantic features of circRNA and miRNA through a gate multilayer perceptron to obtain embedding features of circRNA and miRNA; and finally, the interaction of circRNA and miRNA is predicted by adopting a Bayesian classifier. According to the method, heterogeneous biological information is modeled from the perspective of network science, Fourier coding, spiking neurons and graph embedding learning are utilized, the action mechanism of circRNA and miRNA in complex diseases can be disclosed, and the method has good practicability and application prospects in the fields of artificial intelligence, life science, clinical medicine and the like.

The application discloses a cognitive value evaluation method of medical record data technology based on network science, and particularly relates to the technical field of cognitive value evaluation, and the method comprises the following steps: constructing a multi-scale medical data description set and establishing a medical cognitive relationship network, extracting a node structure stability coefficient and a knowledge propagation influence coefficient to form a node comprehensive stability index, combining a node centrality change to obtain a node cognitive contribution fluctuation index, and jointly constructing a cognitive value index with the node time scale weight, so that stable quantitative evaluation of the cognitive value of the medical record data is realized, and the accuracy and reliability of the cognitive value evaluation result in the multi-time scale medical data environment are improved.

The invention discloses a key node identification and price prediction method and system for a cryptocurrency market, and belongs to the technical field of cryptocurrency market analysis. The method comprises the following steps: firstly, acquiring historical price data of various cryptocurrency, and constructing a cryptocurrency price association network based on symbol correlation; secondly, performing community detection on the network by adopting an EDGly algorithm, and calculating and identifying key nodes in each community based on a Shapley value; and finally, acquiring historical price data and social media emotion data of the key nodes, inputting the historical price data and the social media emotion data into the trained Tuned BiLSTM-Sentient model, and outputting a future price prediction result. The system comprises a corresponding data input layer, a network construction module, a community and key node identification module and a price prediction module. Through organic integration of network science, game theory and deep learning, the problems that in the prior art, a market structure is not deeply depicted, key nodes are not completely recognized, and prediction precision is limited are solved, and a systematic solution is provided for market risk early warning and investment decision making.

The application relates to the field of complex systems and network science, and provides a network-type infrastructure system management method based on multi-dynamics coupling, which comprises the following steps: modeling an infrastructure system existing in a preset region in a current period and subjected to disturbance to obtain a network to be processed; under the action of LLRM and GLRM, a plurality of multi-dynamics mechanism coupling models corresponding to the network to be processed are built; dynamics simulation is performed on each multi-dynamics mechanism coupling model to obtain a cascading failure characteristic simulation result under each multi-dynamics mechanism coupling model; according to an evaluation target of the infrastructure system in the current period, the cascading failure characteristic simulation result is used to determine a target coupling model of the infrastructure system from the plurality of multi-dynamics mechanism coupling models, and the infrastructure system is managed based on a dynamics mechanism in the target coupling model. The application can realize effective management of the infrastructure system existing in the current period and subjected to disturbance.

The present application relates to a kind of anti-malware propagation methods based on network resistance, specifically includes: using network science theory to construct energy internet topology, and define the concept of network resistance;Based on the real-time feature analysis of each node neighbor node, identify the node attacked by virus malicious in network;By network topology formed by the rest of unqualified nodes network resistance maximization, the network is divided and detected, and the block of malicious software or virus propagation is realized.The present application method can be distinguished from the related research in the aspect of existing virus propagation dynamics, the network resistance concept is defined by using network science theory, the virus propagation risk is reduced by changing network structure, and the anti-malware propagation method is studied at the theoretical level.