90 results about "Genetic programming" patented technology

A system of self-organizing mobile robotic agents (MRAs) in a multi-robotic system (MRS) is disclosed. MRAs cooperate, learn and interact with the environment. The system uses various AI technologies including genetic algorithms, genetic programming and evolving artificial neural networks to develop emergent dynamic behaviors. The collective behaviors of autonomous intelligent robotic agents are applied to numerous applications. The system uses hybrid control architectures. The system also develops dynamic coalitions of groups of autonomous MRAs for formation and reformation in order to perform complex tasks.

A system, methods and apparatus are described involving the self-organizing dynamics of networks of distributed computers. The system uses intelligent mobile software agents in a multi-agent system to perform numerous functions, including search, analysis, collaboration, negotiation, decision making and structural transformation. Data are continuously input, analyzed, organized, reorganized, used and output for specific commercial and industrial applications. The system uses combinations of AI techniques, including evolutionary computation, genetic programming and evolving artificial neural networks; consequently, the system learns, anticipates and adapts. The numerous categories of applications of the system include optimizing network dynamics, collective robotics systems, automated commercial systems and molecular modeling systems. Given the application of complexity theory and modal and temporal logics to self-organizing dynamic networks, a novel model of intelligent systems is presented.

In a computer implemented learning and / or process control system, a computer model is constituted by the most currently fit entity in a population of computer program entities. The computer model defines fitness as a function of inputs and outputs. A computing unit accesses the model with a set of inputs, and determines a set of outputs for which the fitness is highest. This associates a sensory-motor (input-output) state with a fitness in a manner that might be termed "feeling".The learning and / or control system preferably utilizes a Compiling Genetic Programming System (CGPS) in which one or more machine code entities such as functions are created which represent solutions to a problem and are directly executable by a computer. The programs are created and altered by a program in a higher level language such as "C" which is not directly executable, but requires translation into executable machine code through compilation, interpretation, translation, etc. The entities are initially created as an integer array that can be altered by the program as data, and are executed by the program by recasting a pointer to the array as a function type. The entities are evaluated by executing them with training data as inputs, and calculating fitnesses based on a predetermined criterion. The entities are then altered based on their fitnesses using a genetic machine learning algorithm by recasting the pointer to the array as a data (e.g. integer) type. This process is iteratively repeated until an end criterion is reached.

A method utilizing genetic programming to construct history matching and forecasting proxies for reservoir simulators. Acting as surrogates for computer simulators, the genetic programming proxies evaluate a large number of reservoir models and predict future production forecasts for petroleum reservoirs.

The invention relates to compositions and methods for the in vivo production of polypeptides comprising one or more unnatural amino acids. Specifically, the invention provides plasmid systems for the efficient eubacterial expression of polypeptides comprising one or more unnatural amino acids at genetically-programmed positions.

A provably correct computer program can be generated using genetic programming techniques. A desired behavior is used to define a formal specification. An initial population of programs is created where each program has a meaning that can be defined using a formalization technique. A fitness function is applied to measure a distance between the meaning of a program, i.e., its actual behavior, and the specification. Any program having a zero value as the measure of distance between the meaning of the program and the specification is determined to be provably correct. After the fitness of some or all of the programs in the current generation of programs has been computed, a provably correct program has not yet been found in the current generation, mutation and / or crossover techniques are performed on at least some of the fittest individuals in the current generation to create the programs of a next generation.

The invention discloses an image retrieval method based on hierarchical features and genetic programming relevance feedback. The method includes the steps: (1), performing adaptive segmentation for a retrieval image submitted by a user to obtain segmented regions; (2) extracting global features of the retrieval image, and extracting local low-level features of the segmented regions; (3) computing an optimal region, corresponding to each segmented region, of each image in a standard image library; (4) constructing a global-optimal region similarity matched pattern; (5) by attaching average weight to various similarities in the similarity matched pattern, computing similarity of the retrieval image to each image in the standard image library, sorting according to the similarity to obtain an initial retrieval result, and returning a plurality of previous images most similar to the retrieval image of the user to a user side; and (6) enabling the user to participate in feedback until satisfactory images are retrieved. The method can be closer to retrieval intention of the user, and is capable of extracting content features of the image effectively and completing retrieval quickly and effectively.

A method for retrospective calibration of a glucose sensor uses stored values of measured working electrode current (Isig) to calculate a final sensor glucose (SG) value retrospectively. The Isig values may be preprocessed, discrete wavelet decomposition applied. At least one machine learning model, such as, e.g., Genetic Programming (GP) and Regression Decision Tree (DT), may be used to calculate SG values based on the Isig values and the discrete wavelet decomposition. Other inputs may include, e.g., counter electrode voltage (Vcntr) and Electrochemical Impedance Spectroscopy (EIS) data. A plurality of machine learning models may be used to generate respective SG values, which are then fused to generate a fused SG. Fused SG values may be filtered to smooth the data, and blanked if necessary.

A method and apparatus for the automatic creation of novel designs, specifically electronic circuits, controllers, antennas, and mechanical systems to satisfy prespecified design goals, using search procedures, such as genetic programming, genetic algorithms, simulated annealing and hill climbing is described. Further, the techniques include automatically creates designs which do not posses key characteristics of preexisting technology. The present invention uses a population of entities which may be evolved to generate structures that may potentially satisfy the design goals. The behavior of the structures is evaluated in view of the design goals, and the structures are compared to a preexisting structure. Those structures more closely meeting the design goals and not similar to the preexisting structure are favored further until a structure is generated that either meets the prespecified design goal or some other process completion criteria. In this manner, a novel structure may be obtained.

The invention provides a linear array SAR (Synthetic Aperture Radar) three-dimensional imaging method based on a threshold gradient tracking algorithm. The method comprises the steps of establishing a linear measurement model between linear array SAR original echo signals and a three-dimensional observation scene target scattering coefficient using a correlation among linear array SAR system parameters, motion platform parameters, space parameters of an observation scene target and original echo signals, and then reconstructing the observation scene target scattering coefficient using a TBGP (Total Blood Granulocyte Pool) method based on the signal linear measurement model. By using the contrast of maximum and minimum target scattering coefficients and the change rate of the target scattering coefficient as algorithm iteration termination conditions, the linear array SAR sparse imaging performance of a GP (Genetic Programming) algorithm under the condition that the sparsity of the observation scene is unknown is improved, the operation efficiency and the space storage efficiency are improved relative to an OMP (Orthogonal Matching Pursuit) algorithm, and the method can be applied in the fields of synthetic aperture radar imaging, earth remote sensing and the like.

An automated system and method for the online settling of a transaction is provided. The system comprises a server comprising a rules based engine including rules established on behalf of a party to the transaction and genetic programming logic configured to employ the rules and determine a plurality of transaction settlement offer sets, each transaction settlement offer set based on a set of circumstances and comprising multiple simultaneously presentable and individually selectable offers, each offer configured to provide an appearance of settling the transaction. The genetic programming logic creates a description of a current transaction settlement offer set, analyzes behavior and characteristics of the current transaction settlement offer set, establishes a fitness of the current transaction settlement offer set, and modifies the current transaction settlement offer set to produce a new transaction settlement offer set. The new transaction settlement offer set is provided to the user.

The invention discloses a genetic programming-based analog circuit fault test optimal sequential search method. A plurality of fault diagnosis trees are firstly randomly generated according to a test dependency matrix of a modular circuit, a genetic programming method is adopted to carry out selection, crossover and mutation on the fault diagnosis trees, a reciprocal of the test cost corresponding to the fault diagnosis tree serves as the individual fitness of the fault diagnosis tree, a fault rally point and a sub tree are exchanged only during the crossover process according to features of the fault diagnosis tree, a testing point is only selected for mutation during the mutation process, a sub tree under the testing point and the rally point is generated again, the fault diagnosis tree with the minimal test cost is selected from the current plurality of fault diagnosis trees after multiple times of iteration to serve as the final fault diagnosis tree. Through accurate search, a testing point sequence isolating the maximal fault points at the minimal test cost can be obtained, and guidance is provided for modular circuit fault test.

A method, system, and device for reducing connection time to a wireless access point includes recording wireless connection information in a log, remotely computing parameters as a function of past wireless connection information in the log, generating an ordered list of wireless access points most likely to be available for reconnection at a desired time as a function of recent wireless connection information in the log, and directly probing a wireless access point instead of initiating a wireless access point scan. In some embodiments, remotely computing parameters as a function of past wireless connection information in the log comprises performing genetic programming operations to generate prediction programs for later prediction of wireless access points most likely to be available for reconnection at a desired time.

An XML-based symbolic computer language, interpreter, and corresponding execution environments are disclosed. The XML-based symbolic computer language, called “OLIN” (One Language Intelligent Network) enables a computer program to be written as an XML-compliant document. OLIN programs are interpreted by an interpreter by parsing the XML content to extract symbolic expressions embedded therein, and evaluating those symbolic expressions. The XML-based symbolic computer language is object-oriented and is based on inherent principles of the LISP programming language. Accordingly, code and data are treated the same. The language provides built-in structures and functions for implementing neural networks and genetic programming. OLIN programs may be executed by a single computer, or via a multiprocessing environment, including distributing processing environments and multiprocessor computers.

The invention belongs to the field of pipe network leakage monitoring and particularly relates to a pipe network leakage monitoring method combining a leakage probability calculation process and an acoustical signal-based leakage recorder monitoring process. In the invention, a genetic programming process is used to establish a functional relationship between independent variables, such as pipe age, pipe diameter and pipe length, and leakage times, and a pipe network geographic information system (GIS) platform is combined to determine key areas to be monitored; furthermore, the leakage recorder monitoring process is used to clear leakage and position leakage points. The method can greatly improve leakage monitoring efficiency, reduce labor intensity of manual leakage monitoring and improve operation management level of a pipe network. The method is not only suitable for leakage monitoring of urban water supply pipe network, but also the leakage monitoring pipes such as recycled water pipe networks, heat distribution pipe and oil and gas pipes.

A fault tolerant software environment, in which various program components (e.g., portions of computer programs, applications, etc) are objectized into entities represented by “codons.” This allows for improper syntax to occur, enabling, for example, combinatorial operations such as genetic programming. The present invention also contemplates such features as the ability to probabilistically execute individual codons, to switch between treating information as executable code or as data (or passing over it), provides that the individual codons can be tagged so that additional information can be associated with them, and provides for tagging of the stack.

Real-time video images of a human subject's face are processed by a plurality of classification algorithms developed in an off-line training process to determine the open vs. closed eye state of the subject. The off-line training process utilizes a genetic programming loop embedded within an adaptive boosting loop, and forms the classification algorithms and weighting factors for combining their classification scores. In the real-time process, the individual classification scores are combined and compared to a threshold to determine the open vs. closed eye state.

The invention discloses a method for quickly configuring and designing a large container crane. The method comprises the following steps: building a large container crane product configuration framework for quick design; analyzing and calculating local similarity, local green characteristic satisfaction degree and cooperation affinity between a case template and customer requirements, and building a 0-1 genetic programming evolutionary model with constraint. In combination with the characteristic of large scale of configuration and optimization problem of the large container crane products, a pseudo-random proportion rule of an ant colony algorithm is redesigned; a candidate gene case number reducing rule is provided on account of the problem that the number of candidate gene cases is often more; an x-Sigmoid function is designed, and the transition probability is adjusted according to the function, so that the algorithm searching speed is increased; the predatory strategy is carried out, so that the development of optimum areas is enhanced, and the searching capability is improved; by comprehensively utilizing the model and the algorithm disclosed by the invention, a satisfactory preliminary design scheme of the large container crane is obtained in a short time; the flexibility is better.

The invention discloses a method for monitoring average life loss of a transformer group. The method comprises the following steps: acquiring hot spot temperature, ambient temperature and load currentdata actually measured by a transformer; Establishing an explicit hot spot temperature prediction model based on genetic programming; Calculating the relative aging rate of the transformer by combining the established hot spot prediction model and the relative aging rate model; Calculating the average life loss of the transformer according to the relative aging rate and life loss model; And according to the environment temperature and the load current monitored by the substation in real time, monitoring the average life loss of the transformer group with the same capacity in the same line orthe same area in real time. The method has the beneficial effects that on-line monitoring of the average service life loss of the transformer can be achieved only through the environment temperature and the load current monitored by the substation in real time; According to similar thermal characteristics and load characteristics of transformers of the same capacity model in the same line or the same area, the average life loss of the transformer group can be monitored in batches.

The invention discloses a ferrograph abrasive particle composite characteristic construction method based on heredity programming, which comprehensively utilizes the characteristics that the ferrograph abrasive particle is direct in form and easy to obtain and the advantage of the heredity programming on the composite characteristic structure. The invention is applicable to the extraction of the oil-water ferrograph abrasive particle graph and the machine wearing state mode identification in the mechanical operation state monitoring. The ferrograph abrasive particle composite characteristic construction method takes the form characteristics of various ferrograph abrasive particles as a sample population, performs combination and optimization on the multiple form characteristics through the heredity programming to obtain composite characteristics, and is used for the classification of various fault abrasive particle. The invention overcomes the blindness in the traditional characteristic construction which is time-consuming and labor-wasting, breaks through the tradition that the prior art only can perform analysis on the off-line image, integrates the multiple form characteristic information of the ferrograph abrasive particles, can effectively improve the capability of utilizing the ferrograph image identification machinery device common fault and provides the strong support to the healthy and reliable operation of the machinery device.

The invention discloses a quantitative strategy generation system based on genetic programming, and relates to the field of information processing related to online quantitative investment. The present invention adopts the B / S architecture, and sets a strategy generating system on the client side to allow users to set relevant parameters of the strategy to run and view the result of the strategy operation, receive the strategy parameters at the server end, run the strategy and execute the strategy based on genetic programming Tune to make the strategy more effective. Through the above method, the present invention can reduce the use threshold of strategy generation, only need to set parameters to generate and execute strategies, and view strategy results. In addition, genetic programming is also used to target projects that investors are concerned about, such as the rate of return and Sharpe ratio, to seek better execution logic for the user's quantitative strategy and make the strategy more effective.

A predictive algorithm for predictive at least one output variable based on a plurality of input variables is developed using a genetic programming technique that evolves a population of candidate algorithms through multiple generations. Within each generation, the candidate algorithms are evaluated based on three fitness criteria: (i) an accuracy criterion that evaluates each candidate algorithm's ability to predict historical measurements of the at least one output variable based on corresponding historical measurements of the input variables; (ii) a complexity criterion that evaluates each candidate algorithm's complexity; and (iii) a smoothness criterion that evaluates each candidate algorithm's nonlinearity. The predictive algorithm may be implemented in an inferential sensor that is used to monitor a physical, chemical, or biological process, such as an industrial process in an industrial plant.

The invention discloses a method for cement hydration simulation and macroscopic attribute predication based on microcosmic image characteristics. At first, a three-dimensional micro computer fault scanner is adopted to obtain evolution of a cement microstructure, and macroscopic attributes of the cement microstructure are measured at the same time; then, three-dimensional image characteristics are adopted to describe microstructures of cement on each age, and a Genetic programming type algorithm is utilized to directly set up a dynamic relation described in a power system mode between the image characteristics and the macroscopic attributes; the obtained power system is used for simulating cement hydration and predicating the macroscopic attributes. According to the method, complicated image segmentation and phase classification for microcosmic images of the cement are avoided, physical and chemical knowledge does not need to be considered, the three-dimensional image characteristics are calculated from images themselves, the dynamic relation between the image characteristics and the macroscopic attributes is further obtained, influences brought by incorrect phase analysis and image segmentation are avoided, and thus prediction accuracy for development and variation tendencies of the macroscopic attributes is improved.