1093 results about "Evolutionary algorithm" patented technology

Described invention and its embodiments, in part, facilitate discovery of ‘Most Recent Common Ancestors’ in the family trees between a massive plurality of individuals who have been predicted to be related according to amount of deoxyribonucleic acids (DNA) shared as determined from a plurality of 3rd party genome sequencing and matching systems. This facilitation is enabled through a holistic set of distributed software Agents running, in part, a plurality of cooperating Machine Learning systems, such as smart evolutionary algorithms, custom classification algorithms, cluster analysis and geo-temporal proximity analysis, which in part, enable and rely on a system of Knowledge Management applied to manually input and data-mined evidences and hierarchical clusters, quality metrics, fuzzy logic constraints and Bayesian network inspired inference sharing spanning across and between all data available on personal family trees or system created virtual trees, and employing all available data regarding the genome-matching results of Users associated to those trees, and all available historical data influencing the subjects in the trees, which are represented in a form of Competitive Learning network. Derivative results of this system include, in part, automated clustering and association of phenotypes to genotypes, automated recreation of ancestor partial genomes from accumulated DNA from triangulations and the traits correlated to that DNA, and a system of cognitive computing based on distributed neural networks with mobile Agents mediating activation according to connection weights.

A method and apparatus is provided for constructing a predictive model for a system based on a priori qualitative modeling of the system and on historical database collected from past activity of the system or past events in the system. An expert provides grouping of parameters and qualitative dependencies between parameters and attributes, wherein some of the attributes may be conceptual or virtual attributes. The present invention extends existing methods of `evolutionary algorithms` in order to build successive sets of quantitative predictive models for the system, wherein parts of each model are evolved by the evolutionary algorithm and parts of each model are derived using the historical database. According to the present invention a model constructed by this method can be incorporated as a predictive model into a diagnosis or control apparatus without the need for human inspection, as the model complies with the expert's knowledge about the system. The present invention also provides a method to update the constructed model when new data is delivered, thus adjusting the model to changes in the environment.

The present invention provides a fault prediction and condition-based repair method of an urban rail train bogie. An optimum service life distribution model of a framework, a spring device, a connecting device, a wheel set and axle box, a driving mechanism, and a basic brake device of a bogie is determined by adopting a method based on survival analysis; a reliability characteristic function of each subsystem is obtained; then, a failure rate of each subsystem of the bogie is calculated by adopting a neural network model optimized by an evolutionary algorithm; and finally, proportional risk modelling is conducted by taking the failure rate and safe operation days of each subsystem of the bogie as concomitant variables; and on the basis of cost optimization, thresholds and control limits for condition-based repair of a bogie system are obtained.

The invention discloses a method and system for site selection of a base station. The method comprises the following steps: obtaining parameter information of a preset type according to a networking type and a zone type of a target zone and introducing the obtained parameter information into a preset mathematical model to form a mathematical model of the target zone; selecting a preset number of sub sets from a candidate base station set of the target zone; and according to the mathematical model of the target zone, using an evolutionary algorithm to carry out solving on the selected of sub sets with the preset number, thereby obtaining a station site and configuration of a newly-established base station. According to the method and system for site selection of a base station, according to different geographical environments and networking types of different target zones, a TD-LTE network base station site and configuration are selected, wherein the TD-LTE network base station site and configuration correspond to the geographical environment of the target zone; and according to the selected base station site and configuration, the new base station is established. Therefore, the data traffic requirement with high bandwidth and high quality can be met; and a high-speed wireless broadband service can be provided for a large number of users.

A system and method for modeling networks by auto-generation. The system generally comprises methods and systems for enabling the extraction, management and merging of models of networks and creating models of networks that can dynamically respond to changing context and computer requirements. The method includes ways of creating network models, maintaining n-dimensional graphs of networks; using adaptive and evolutionary algorithms for result emergence, using training and feedback to tune adaptive algorithms for solution optimization, and transformation of results into ontological and or data models.

A method, computer program storage medium and system that implement evolutionary algorithms on heterogeneous computers; in which a central process resident in a central computer delegates subpopulations of individuals of similar fitness from a central pool to separate processes resident on peripheral computers where they evolve for a certain number of generations after which they return to the central pool before the delegation is repeated.

The invention discloses a method for establishing virtual reality excavation dynamic smart load prediction models. The method includes the steps that the knowledge excavation technology is adopted so that a virtual reality analysis environment can be formed, the influence relation between fixed quantities is explored, and an input variable candidate set is determined; smart load prediction models of a support vector machine of a self-adaptive structure and an Elman neural network and the like are established, wherein input variables are determined by the support vector machine through the attribute screening technology and parameters are optimized by the support vector machine through a flora tendency differential evolutionary algorithm; a region load smart load prediction model based on data slice excavation is established; a load curve prediction model combined with dynamic electrovalence factors, user characteristics and the user response electric quantity is established, so that linked correcting prediction of loads, electrovalence and the response electric quantity is achieved. According to the method, the prediction models suitable for the actual condition of a smart power grid of China are established, the scale of construction of renewable energy sources is reasonably planned, more efficient power utilization of users is facilitated, and reasonable arrangement of power supply resources of power enterprises is facilitated.

A multiobjective evolutionary algorithm unit feeds a set of parameters of an individual to a search history storage device in a fitness estimating unit and to an optimization target. The optimization target outputs a set of sampled values of fitnesses on the basis of the set of parameters of the individual. The search history storage device stores the set of parameters of the individual and a set of sampled values as a search history. The fitness estimating module computes a set of estimated values of true fitnesses on the basis of the search history stored in the search history storage device for output to the multiobjective evolutionary algorithm unit. The multiobjective evolutionary algorithm unit determines a Pareto-optimal population in accordance with a genetic algorithm on the basis of a plurality of sets of estimated values.

A system and method that does trustworthy multi-objective structural synthesis of analog circuits, and extracts expert analog circuit knowledge from the resulting tradeoffs. The system defines a space of thousands of possible topologies via a hierarchically organized combination of designer-trusted analog building blocks, the resulting topologies are guaranteed trustworthy. The system can perform a search based on a multi-objective evolutionary algorithm that uses an age-layered population structure to balance exploration vs. exploitation, with operators that make the search space a hybrid between vector-based and tree-based representations. A scheme employing average ranking on Pareto fronts is used to handle a high number of objectives. Good initial topology sizings are quickly generated via multi-gate constraint satisfaction. To explicitly capture expert analog design knowledge, data mining is employed on the sized circuits to: automatically generate a decision tree for navigating from performance specifications to topology choice, to do global nonlinear sensitivity analysis, and to generate analytical models of performance tradeoffs.

A hybrid evolutionary algorithm (“HEA”) technique is described for automatically calculating well and drainage locations in a field. The technique includes planning a set of wells on a static reservoir model using an automated well planner tool that designs realistic wells that satisfy drilling and construction constraints. A subset of these locations is then selected based on dynamic flow simulation using a cost function that maximizes recovery or economic benefit. In particular, a large population of candidate targets, drain holes and trajectories is initially created using fast calculation analysis tools of cost and value, and as the workflow proceeds, the population size is reduced in each successive operation, thereby facilitating use of increasingly sophisticated calculation analysis tools for economic valuation of the reservoir while reducing overall time required to obtain the result. In the final operation, only a small number of full reservoir simulations are required for the most promising FDPs.

Methods and apparatuses are presented for balancing non-uniformly distributed network traffic in a wireless communications system having a plurality of digital remote units (DRUs). In some embodiments, a method comprises partitioning the plurality of DRUs into a plurality of DRU sectors, and dynamically repartitioning the plurality of DRU sectors depending on traffic conditions in at least one of the DRU sectors, such that the repartitioning satisfies at least one of a soft capacity constraint or a hard capacity constraint. The dynamic repartitioning may be based on at least one optimization algorithm.

The invention provides a multi-satellite earth-observation task scheduling and planning method and device.The method comprises the steps that an observation task and satellite resource data are read; the observation task is partitioned according to the satellite resource data, and an observation meta-task set is obtained; task planning is conducted on the observation meta-task set through an evolutionary algorithm, and a planning result is obtained; the planning result is decoded, and an observation sequence is obtained; in this way, when multiple satellites observe the earth, the characteristics such as intelligence and concurrency of the evolutionary algorithm are fully utilized, and the task scheduling problem of multiple observation satellites which need to work cooperatively is solved; a dynamic task planning method based on the evolutionary algorithm is utilized, a reasonable load scheduling scheme is made for an in-orbit operation satellite group, resource allocation of a satellite system is optimized, and satellite system resources are utilized fully and reasonably.

The invention discloses a system and a method for optimizing overall planning of distributed energy. The system comprises a matrix laboratory (MATLAB) optimization analysis part, and a Microsoft EXCEL system input part and a Microsoft EXCEL system output part which are combined with the MATLAB optimization analysis part. The optimization method comprises the following steps of: (1) predicting andanalyzing; (2) modeling and outputting an optimization variable, a performance parameter and a system power flow network chart by using a combined cooling heating and power (CCHP) energy system; (3) starting a scheme optimization process by using a CCHP energy overall planning optimization module; (4) verifying and evaluating an optimization scheme by using a system constraint subsystem; and (5) outputting an optimization scheme. Modeling description is effectively performed on thermal equipment in combination with a mathematical modeling measure, an overall evolutionary algorithm with high performance is optimized and microscopic configuration optimization, and annual operating strategy optimization are performed on the entire system; the system and the method support optimization of a simple cyclic energy system and a more complicated combined cyclic energy system; and the efficiency and economic benefit of the entire energy system are improved.

The invention discloses a multi-unmanned aerial vehicle auxiliary edge computing resource allocation method based on task prediction. The method comprises the following steps of: firstly, modeling a communication model, a computing model and an energy loss model in an unmanned aerial vehicle auxiliary edge computing unloading scene; modeling a system total energy consumption minimization problem of the unmanned aerial vehicle auxiliary edge computing unloading network into task predictable process of terminal devices; obtaining prediction model parameters of different terminal devices by adopting centralized training through accessing historical data of the terminal devices; obtaining a prediction task set of the next time slot by utilizing the prediction model based on the task information of the current access terminal devices; and based on the prediction task set, decomposing an original problem into an unmanned aerial vehicle deployment problem and a task scheduling problem for joint optimization. The response time delay and completion time delay of the task can be effectively reduced through the deep learning algorithm, so that the calculation energy consumption is reduced; anevolutionary algorithm is introduced to solve the problem of joint unmanned aerial vehicle deployment and task scheduling optimization, the hovering energy consumption of the unmanned aerial vehicleis greatly reduced, and the utilization rate of computing resources is increased.

The invention discloses a quick feedback analyzing system in a tunnel constructing process. The system adopts a scheme: understanding currently adopted designing construction parameters; establishing a tunnel excavation three-dimensional finite element numerical grid calculation model; acquiring surrounding rock layering and convergent displacement monitoring information after a tunnel is excavated; establishing a non-linear support vector machine model; fixing an anchoring parameter according to the actual construction parameter, and optimally identifying rock mechanic parameters by adoptinga differential optimization algorithm; optimizing the construction parameter of an anchoring scheme by adopting a differential evolution algorithm; and optimizing the rock mechanic parameters by calling the differential evolution and optimization algorithms to further solve the construction parameter of the anchoring scheme, and outputting the construction parameter of the optimized anchoring scheme as a construction scheme through a computer display screen to guide the constructors to construct. The quick feedback analyzing system ensures that the monitoring information is used for optimizing the anchoring parameter while being used for identifying the surrounding rock parameters, so that the dynamic information construction is improved to a level of quantitative analysis.

The invention discloses a dynamic flexible job-shop scheduling method based on a multi-objective evolutionary algorithm. The dynamic flexible job-shop scheduling method based on the multi-objective evolutionary algorithm mainly aims to solve the problems that existing methods are poor in dynamic change environment adaptive ability and low in search efficiency. The dynamic flexible job-shop scheduling method based on the multi-objective evolutionary algorithm comprises the first step of carrying out initialization, specifically, reading information of jobs, machine attributes and the like, defining an optimal object and setting a constraint condition, the second step of simultaneously optimizing time of completion, tardiness and the maximum machine loading based on a static multi-objective evolutionary algorithm at initial moments, and the third step of adopting a rescheduling mode driven by emergent dynamic events in a shop production process, quickly generating a new scheduling scheme in a new environment based on a dynamic multi-objective evolutionary algorithm in order to simultaneously optimize the time of completion, tardiness, the maximum machine loading and stability of workpieces to be scheduled. Compared with a traditional scheduling method, the dynamic flexible job-shop scheduling method based on the multi-objective evolutionary algorithm can timely respond to happening of emergent dynamic events, adjust a search strategy in a self-adaptation mode according to the dynamic environment, and the generated scheduling scheme has the advantages of being high in efficiency and excellent in stability.

The system and method described herein may be used to construct outperforming portfolios relative to target benchmarks. In particular, the system and method described herein may use multi-factor models that employ multi-objective evolutionary algorithms and mean variance optimization calculations to select constituents from a target benchmark index to include in a portfolio. The selected constituents may then be weighed to construct or rebalance the portfolio in a manner that can consistently outperform the target benchmark index while satisfying real-world constraints that relate to turnover limits, minimum and maximum stock positions, cardinalities, target market capitalizations, investment strategies, and other characteristics associated with the portfolio.

The features that are presented to an evolutionary algorithm are preprocessed to generate combination features that may be more efficient in distinguishing among classifications than the individual features that comprise the combination feature. An initial set of features is defined that includes a large number of potential features, including the generated features that are combinations of other features. These features include, for example, all of the words used in a collection of content material that has been previously classified, as well as combination features based on these features, such as all the noun and verb phrases used. This pool of original features and combination features are provided to an evolutionary algorithm for a subsequent evaluation, generation, and determination of the best subset of features to use for classification. In this evaluation and generation process, each combination feature is processed as an independent feature, independent of the features that were used, or not used, to form the combination feature. In this manner, for example, a particular phrase that is generated as a combination of original feature words may be determined to be a better distinguishing feature than any of the original feature words and a more efficient distinguishing feature than an unrelated selection of the individual feature words, as might be provided by a conventional evolutionary algorithm. The resultant best performing subset is subsequently used to characterize new content material for automated classification. If the automated classification includes a learning system, the evolutionary algorithm and the generated combination features are also used to train the learning system.

The present invention discloses systems and methods of conducting multi-objective evolutionary algorithm (MOEA) based engineering design optimization of a product (e.g., automobile, cellular phone, etc.). Particularly, the present invention discloses an archive configured for monitoring the progress and characterizing the performance of the MOEA based optimization. Further, an optimization performance indicator is created using the archive's update history. The optimization performance indicator is used as a metric of the current state of the optimization. Finally, a stopping or termination criterion for the MOEA based optimization is determined using a measurement derived from the optimization performance indicators. For example, a confirmation of a “knee” formation has developed in the optimization performance indicators. The optimization performance indicators include, but are not limited to, consolidation ratio, improvement ratio, hypervolume.

A framework for managing approximate models in generation-based evolution control is proposed. This framework is well suited for parallel evolutionary optimization that is able to guarantee the correct convergence of the evolutionary algorithm and to reduce the computation costs as much as possible. Control of the evolution and updating of the approximate models are based on the estimated fidelity of the approximate model. The frequency at which the original function is called and the approximate model is updated is determined by the local fidelity of the approximate model. By local fidelity the fidelity of the model for the region where the current population is located is designated. The lower the model fidelity is, the more frequently the original function should be called and the approximate models should be updated.

Systems and methods are provided for a core management system for parallel processing of an evolutionary algorithm. The systems and methods may include identifying, for a processing environment, a plurality of arriving processors available for utilization; configuring a first number of the plurality of arriving processors as master processors for the processing environment; configuring a respective second number of the plurality of arriving processors as slave processors, where each master processor is assigned one or more of the slave processors for the processing environment, where each master processor maintains timing data associated with available processing resources at the respective master processor, where each master processor is operative to calculate a respective target number of slaves based upon the respective timing data; and reconfiguring a current number of slave processors assigned to one or more respective master processors based upon the respective timing data calculated for the one or more respective master processors.

The invention relates to a power distribution network reestablishing method, in particular to a multi-target network reestablishing method for an active power distribution network. On the basis of a new requirement of the active power distribution network for network reestablishing, a new hybrid evolutionary algorithm is put forward to be used for reestablishing the power distribution network, an initial network close to the optimal solution is rapidly obtained through the optical flow pattern algorithm, then the optimal solution is found through a tree-shaped structure coding monolepsis algorithm, the tree-shaped structure coding is conducted on the initial network, and solving is conducted through the monolepsis algorithm. The method has the advantages that when network reestablishing is conducted on the active power distribution network, the influences of distributed type power supplies are taken into full consideration, force output constraints of the distributed power supplies are contained in the constraint conditions, the influences of distributed type power supply plan islands are taken into full consideration in reliability calculation, the network loss of the power distribution network where network reestablishing is conducted is greatly reduced, the power supply reliability is improved, and meanwhile the reestablishing result better conforms to the actual situation that a lot of distributed type power supplies are connected into the active power distribution network.

The invention discloses a method for predicting a protein three-dimensional structure based on Monte Carlo local shaking and fragment assembly. The method comprises the following steps that firstly, according to the difficult problem that search space of protein high-dimensional conformation space is complex, the effectiveness of fragment replacement is judged under a Rosetta force field model through the Monte Carlo statistical method according to a protein database configuration fragment bank; under a differential evolution group algorithm framework, the complexity of the search space is reduced through fragment assembly, meanwhile, false fragment assembly is removed through the Monte Carlo statistical method, and the conformation search space is gradually reduced through the diversity of an evolutionary algorithm, and therefore the searching efficiency is improved; meanwhile, a module with coarseness is adopted, a side chain is ignored, and cost of a search is effectively reduced. The method for predicting the protein three-dimensional structure based on Monte Carlo local shaking and fragment assembly can effectively obtain optimal local stable conformation and is high in predicting efficiency and good in convergence correctness.

The invention discloses an optimal deployment method of a large-scale industrial wireless sensor network based on differential evolution algorithm, which ensures the system reliability through carrying out optimization deployment on nodes, and relates to two fields of industrial wireless sensor network and intelligent computation. The method comprises the following steps of: carrying out automatic coordination on spaces according to actual spaces of industrial sites, obstacles, wireless sensor power and accurate requirement; and using the total number of nodes and minimum load standard difference of cluster heads as targets, wherein a node deployment model is established for restriction conditions based on the redundancy requirement, '1' represents arrangement of the cluster heads corresponding to mesh points, and '0' represents no arrangement. The invention provides a new binary differential evolution algorithm for optimizing and solving the model. By using a new probability prediction operator, the population is updated by a generated binary variation individual. The method can ensure the system reliability, and can reduce the construction cost of the system at the same time, balances the system energy consumption and prolongs the network life cycle through the optimization deployment of the nodes.

The invention relates to a clustered wireless sensor network cluster head election model based on an evolutionary game trust mechanism. The cluster head election model comprises three system models, namely, a wireless sensor network model, a JDL (Joint Director of Laboratories) model, and an evolutionary game model. According to the clustered wireless sensor network cluster head election model based on an evolutionary game trust mechanism provided by the invention, an improved JDL model and an evolutionary game algorithm are adopted, the dynamic characteristic of network communication and the time-effectiveness of trust are fully considered, an optimal cluster head is elected on the premise of considering trust factors such as communication, energy and data, and moreover, the computation overhead is optimized, and the energy of nodes is saved.

Roughly described, a data mining arrangement for developing high quality classifiers using an evolutionary algorithm, includes a plurality of “mid-chain” evolutionary coordinators, down-chain of a main (top-chain) evolutionary coordinator and up-chain of evolutionary engines. Multiple levels of mid-chain evolutionary coordinators can be used in a hierarchy, and the various branches of the hierarchy need not have equal length. Each evolutionary coordinator (other than the top-chain evolutionary coordinator) appears to its up-chain neighbor as if it were an evolutionary engine, though it does not actually perform any evolution itself. Similarly, each evolutionary coordinator (including the top-chain evolutionary coordinator) also appears to its down-chain neighbors as a top-chain evolutionary coordinator. Each mid-chain evolutionary coordinator maintains its own local candidate pool, reducing the load on the top-chain evolutionary coordinator pool, as well as reducing bandwidth requirements. Only the evolutionary engines perform actual testing of candidate individuals on training data.

In the field of multi-objective optimization using evolutionary algorithms conventionally different objectives are aggregated and combined into one objective function using a fixed weight when more than one objective needs to be optimized. With such a weighted aggregation, only one solution can be obtained in one run. Therefore, according to the present invention two methods to change the weights systematically and dynamically during the evolutionary optimization are proposed. One method is to assign uniformly distributed weight to each individual in the population of the evolutionary algorithm. The other method is to change the weight periodically when the evolution proceeds. In this way a full set of Pareto solutions can be obtained in one single run.

The invention discloses a combined optimization method algorithm to an irregularly-arranged sub-array four-dimensional antenna array. The definition of information entropy is introduced into a four-dimensional array, the originally-complicated optimization problem is divided into two sub-problems, optimization is performed according to two steps, in the first step, an information entropy-based genetic algorithm is employed, the array topology structure with maximum information entropy value is optimized according to a sub-array arrangement algorithm, in the second step, information such as a static excitation phase of each sub-array of the sub-arrays, the closing continuous time of a switch and the initial closing time of the switch is optimized by a differential evolutionary algorithm according to the requirement of low sideband and low side lobe, so that the whole optimization problem can be more efficiently solved. The maximum innovation lies in that the intrinsic characteristic ofthe original optimization problem is dug, optimization is performed by combining the information entropy-based generic algorithm and the differential evolutionary algorithm, the complexity of the original optimization problem is reduced, T / R modules are saved by half, and meanwhile, the characteristics of low sideband and low side lobe under large-angle scanning are ensured.

Methods are described for near optimal Antenna and / or sensor selection via population-based probabilistic evolutionary algorithms such as estimation of distribution algorithm (EDA) and bio-inspired Optimization (BIO). The aspects of the invention includes a method for joint transmit and receive antenna selection using EDA; and an enhanced EDA, which uses cyclic shift register and biased estimation of distribution; and methods for joint transmit and receive antenna selection using improved population-based optimization. The proposed EDA-based and bio-inspired selection methods results in performances that are close to the ESA (exhaustive search algorithm) and yet impose mush less computational burden than ESA. Another advantage of our methods is that they can be easily implemented on parallel processors.