74 results about "Gene expression programming" patented technology

Gene expression profiling reveals four distinct subgroups of multiple myeloma that have significant correlation with various clinical characteristics. Diagnosis for multiple myeloma (and possibly monoclonal gammopathy of undetermined significance) based on differential expression of 14 genes, as well as prognosis for the four subgroups of multiple myeloma based on the expression of 24 genes are established. A 15-gene model that classifies myeloma into 7 groups is also reported. Gene expression profiling also allows placing multiple myeloma into a developmental schema parallel to that of normal plasma cell differentiation. Development of a gene expression- or developmental stage-based classification system for multiple myeloma would lead to rational design of more accurate and sensitive diagnostics, prognostics and tumor-specific therapies for multiple myeloma.

Provided herein is a method for gene expression profiling multiple myeloma patients into distinct subgroups via DNA hybridization and hierarchical clustering analysis of the hybridization data where the results may further be used to identify therapeutic gene targets. Also provided is a method for controlling bone loss in an individual via pharmacological inhibitors of DKK1 protein. In addition provided herein is a method for diagnosing multiple myeloma using a 15-gene model that classifies myeloma into groups 1-7.

Provided herein are methods for diagnosing and treating multiple myeloma based on statistical analysis of and subsequent increasing / inhibiting expression of subgroups of plasma cells and B cell genes. Also provided are methods for a developmental stage-based classification for multiple myeloma using hierarchical clustering analysis of plasma cell and B cell nucleic acids and for discriminating among normal, hyperplastic and malignant using gene expression array data and statistical analysis thereof. In addition methods for determining the risk of developing bone disease in a test individual by examining expression levels of a WNT signaling antagonist, such as DKK1, are provided. A kit comprising anti-DKK1 antibodies and detection reagents for measuring DKK1 protein levels also is provided.

The invention discloses an angle and myoelectricity continuous decoding method for a human body lower limb walking joint. The movement track of a lower limb body surface optical marking point in the human body walking process is recorded through an optical movement capture system, and the movement angle of the lower limb joint is precisely calculated through the human body lower limb kinematical modeling; surface electromyogram signals of eight main muscles related to lower limb movement in the human body walking process are synchronously acquired, the activity intensity information of the signals is extracted through filtering and rectifying preprocessing, and the optical independent feature vector set describing the intensity of the surface electromyogram signals is extracted through the principle component analysis method; a nonlinear regression model from surface electromyogram signal features (independent variables) to the vertical plane joint movement angles (dependent variables) is established through the gene expression programming symbol regression analysis method, and the lower limb movement track is predicted. The method is mainly applied to design and manufacture of medical rehabilitation machines.

The inveniton discloses an automatic testing and estimating tool of software in the monitoring system of computer software, which comprises the following parts: realizing too of testing and estimating frame of software, unit testing tool, optimizing tool of integrating testing, reliability testing and estimating tool of software, wherein the unit testing tool is simple technique to integrate black box testing and testing routine of testing data generated by random path; the optimizing tool of integrated testing is the testing optimizing model based on component; the reliability testing and estimating tool of software adopts data bin to collect and store ineffective data to build reliable predicting model based on gene expressive formula program, which analyzes the estimating result of multiple models to give perfect qualitative and quantitative reliable analyzing report. The invention solves the contradiction of incomplete mating between commercial testing tool and local software engineering, which affirms high quality to develop software.

The invention discloses a big data-based electric cable well state evaluation and early warning method, comprising the following steps: processing data collected in real time to obtain a new trainingsample data set; performing running state evaluation on the data to obtain a comprehensive score of the current electric cable well running state; assessing the risk level of the current electric cable well running state according to the comprehensive score; and carrying out displaying and warning by an operation control system according to an assessment result. According to the method in the invention, multiple indicators affecting the running state of the electric cable well are firstly selected and synthesized through a principal component analysis method so as to obtain a new training sample data set, and then, a gene expression programming algorithm is used for mining a functional relationship between the comprehensive score and each index data, and finally, the current electric cablewell running state data is taken as the input of the functional relationship to calculate the comprehensive score, the calculation result is submitted to a risk early warning module, a risk level knowledge rule base is queried to evaluate the risk level of the current electric cable well running state, and feasible reference comments are given out.

Provided herein are methods of predicting cytogenetic abnormalities associated with a cancer in a subject, for example, multiple myeloma. A cytogenetic abnormalities model of a set of reference values obtained from an average of gene expression profile values based on copy number-sensitive genes that correlate to cytogenetic abnormalities associated with the cancer is utilized as a predictive tool. The cytogenetic abnormalities model, as a virtual model (i.e. a “virtual karyotype”), may be tangibly stored with program instructions to implement the model in a computer system. In particular embodiments, the methods and systems provided by the invention operate without FISH (fluorescent in situ hybridization).

The invention discloses a rainfall forecast method based on kernel principal component analysis and gene expression programming. According to the rainfall forecast method, forecast factors are selected on the basis of live historical rainfall data of a governed region and collecting and cleaning of meteorological factor historical time series data in the corresponding period; the forecast factors are subjected to kernel principal component analysis; a gene expression programming rainfall forecast model is created, and live weather data of the governed area are inputted into the model to acquire a rail forecast result. By the rainfall forecast method, the problems of change rule complexity and numerous influence factors in meteorological rainfall forecast can be solved, and rainfall forecast quality can be improved effectively.

The invention discloses a method for classifying N central points based on gene expression programming and belongs to the technical field of machine learning. The method includes the steps of firstly, partitioning to-be-classified training data into a classification-marker-contained data set and a classification-marker-free data set; secondly, searching classification central points from a multi-dimensional space of the classification-marker-free data set according to a distance formula; thirdly, assessing accuracy of the searched classification central points on the classification-marker-contained data set; fourthly, using a gene expression programming method for expressing, searching and updating the classification central points to obtain new classification central points; fifthly, classifying unknown points according to the distances between the unknown points and the new classification central points; sixthly, repeating the third step, the fourth step and the fifth step until an objective function satisfies stop conditions. By the aid of the method for classifying the N central points based on gene expression programming, calculated quantity can be decreased while susceptibility to unbalanced data is avoided.

Methods for generating a normalized expression signal for microarray data based on a theoretical distribution at the unit level to produce a normalized expression signal for the single microarray that is independent of other microarrays. The method typically includes receiving microarray data representing a plurality of probe pairs for a single microarray, determining, for each probe pair, differences between intensities of perfect match (PM) probes and intensities of mismatched (MM) probes, determining a difference signal, D, based on the determined differences, and scaling the difference signal, D, to produce an expression signal, DS. The method also typically includes normalizing the expression signal based on a theoretical distribution at the unit level to produce a normalized expression signal for the single microarray that is independent of other microarrays.

Gene expression profiling is a powerful tool that has varied utility. It enables classification of multiple myeloma into subtypes and identifying genes directly involved in disease pathogensis and clinical manifestation. The present invention used gene expression profiling in large uniformly treated population of patients with myeloma to identify genes associated with poor prognosis. It also demonstrated that over-expression of CKS1B gene, mainly due to gene amplification that was determined by Fluorescent in-situ hybridization to impart a poor prognosis in multiple myleoma. It is further contemplated that therapeutic strategies that directly target CKS1B or related pathways may represent novel, and more specific means of treating high risk myeloma and may prevent its secondary evolution.

The invention discloses a scenic-region-tourism-meteorological-disaster intelligent forecasting method based on difference correction. The scenic-region-tourism-meteorological-disaster intelligent forecasting method based on difference correction includes the steps that main meteorological factors of meteorological disasters occurring in a target scenic region are determined with the partial correlation analysis method, a difference set of historical data and numerical-forecasting-model output data of the main meteorological factors of the target scenic region is obtained, and a mapping relationship function set between the meteorological disasters and the main meteorological factors and a difference mapping relationship function set between the meteorological disasters and the main meteorological factors are calculated with the gene expression programming algorithm respectively; then a forecasting function set is subjected to difference superposition modification, and a forecasting model of the meteorological disasters of the target scenic region is obtained; all meteorological factor values output by a numerical forecasting model are substituted, and the possible occurring conditions of various meteorological disasters can be forecasted. By means of the scenic-region-tourism-meteorological-disaster intelligent forecasting method based on difference correction, the problems that in the prior art, the sample data requirements are high, the adaptive capacity is poor, and the calculation process is complex are solved, and a quite-good decision support can be provided for scenic-region-disaster controlling and management.

The invention relates to a collaborative scheduling method and device for distributed computing tasks. The method includes the following steps: determining expected finishing time for each task on each resource, and establishing a matrix of the expected finishing time; determining a number of tasks to be handled for each resource by using a gene expression programming algorithm; determining an evaluation value for each task according to a urgency degree and an importance degree of each task, and ranking the tasks according to the evaluation values of the tasks to obtain a task sequence; and distributing the tasks in the task sequence to the resources in order by using a Min-Min algorithm according to the matrix of the expected finishing time and the number of tasks to be handled for each resource. The effective method for distributing the tasks is studied according to the technical scheme provided by the invention. Effective resources are fully used for finishing to-be-submitted tasksin the shortest time.

Gene expression programming-based behavior monitoring is disclosed. A machine receives, as input, a plurality of data examples. A method can include receiving data indicating behaviors of the device, determining, using a gene expression programming (GEP) method, a data model that explains the data, and comparing further data indicating further behavior of the device to the data model to determine whether the further behavior is explained by the data model.

The invention discloses a cloud gene expression programming based music emotion recognition method. The method includes following steps: dividing music emotions into a plurality of emotion semantemes, and recording grades, to each emotion semanteme of multiple sample musical compositions, of P test takers; utilizing the cloud emotion labeling method to obtain a normal cloud model of each emotion semanteme of each sample musical composition; extracting voiceprint characteristic parameters of the sample musical compositions, corresponding each sample musical composition to the normal cloud model of the corresponding sample musical composition, and constructing to obtain a music emotion database; utilizing the music emotion database to construct an optimum relationship model of the voiceprint characteristic parameters and the emotion semantemes; and performing music emotion recognition to music according to the optimum relationship model and the voiceprint characteristic parameters of to-be-recognized music. The cloud gene expression programming based music emotion recognition method is based on ensemble learning and cloud gene expression programming, and the optimum relationship model of the music voiceprint parameters and the music emotions is constructed to recognize the music emotions effectively.

The invention provides a floating population information analysis and warning and alarming method based on biological instructive calculation. Wherein, with current floating population information system from department of public safety, extracting need information to calculate floating population data with the multilayer chromosome gene expression programming algorithm and overlap-expressive polygene evolution algorithm in biological instructive calculation filed; and completing data mine and classification and isolated-point analysis to realize the warning and alarm. This invention can take deep analysis to trace and trend of abnormal floating population and different criminal feature, builds a intelligent analysis platform, and can also provide useful information for local peace.

Gene expression patterns were analyzed that identified multiple genes associated with radiation enhanced colon carcinogenesis. Some of the genes modulated by radiation exposure may be involved in up-regulating the Wnt / β-catenin signaling pathway and promote colon carcinogenesis. Consumption of a fish oil / pectin diet caused a general down-regulation of genes encoding proteins involved in cell adhesion and receptor activity, which may be involved in down-regulating the Wnt / β-catenin signaling pathway. The data suggest that dietary fish oil / pectin may be an effective countermeasure against radiation-induced colon carcinogenesis. In accordance with this, gene expression profiles can be monitored to reduce the risk of radiation induced carcinogenesis in high risk personnel (i.e., for example, astronauts) before, during, and / or after radiation exposure (i.e., for example, spaceflight), and / or to detect radiation-induced carcinogenesis so that an appropriate countermeasure administration can be implemented. The techniques are also targeted at non-invasively monitoring cancer patients after the primary cancer has been resected to determine if / when a secondary tumor develops.

The invention provides a method of resolving a shortest distance between any two polyhedrons in a three-dimensional space. The method is characterized by comprising the following steps of first, rasterizing surface triangles of three-dimensional models of a polyhedron Mx and a polyhedron My and pre-processing so as to obtain processing information; second, processing the processing information byusing a back-culling algorithm so as to obtain a vertex selection area, wherein the vertex selection area comprises multiple text vertex pairs consisting of vertexes of the polyhedron Mx and the polyhedron My; third, resolving a shortest distance between two vertexes of a text vertex pair in the vertex selection area by using both gene expression programming and an Alopex algorithm so as to obtaina closes vertex pair, wherein the distance between the closest vertex pair is an approximate solution of shortest distance between the polyhedron Mx and the polyhedron My; and fourth, resolving an accurate shortest distance between the polyhedron Mx and the polyhedron My by using the closest vertex pair so as to obtain a shortest distance. The method can obtain highly accurate solution and has high convergence performance.

A gene expression programming genetic algorithm for performing symbolic regression is provided. The algorithm avoids expression bloating and over fitting by employing a fitness function that depends inversely on the mathematical expression complexity. Members of a population that are evolved by the algorithm are represented as a set arrays (e.g., in the form of a matrix) of indexes that reference operands and operators, thus facilitating selection, mutation, and cross over operations conducted in the course of evolving the population. The algorithm comprises a syntax checking part that may be applied to population members without their having to be converted to executable programs first. An object-oriented programming language data structure is providing for encapsulating basic data for each codon (e.g., operand, operator) used by the algorithm.

The invention relates to a biomarker used for prognosis of lung cancer. 95 lung cancer prognosis specific genes are selected from 2738 lung cancer gene expression programming data from various countries through statistical analysis, wherein 85 of the selected genes are related to survival probability and postoperative relapse probability that reported for the first time. Furthermore, the 95 lung cancer prognosis specific genes are subjected to single-factor analysis, multi-factor analysis and survival curve analysis to finally accurately select seven representive genes. Clinical data in various countries proves that the gene markers can be very effectively used for predicting the survival probability and postoperative relapse probability of lung cancer, and according to this, lung cancer patiens are divided into low-, medium- and high-risk groups.

The invention discloses a human body behavior recognition method based on self-feedback gene expression programming. According to the method, for a deep human body behavior image, three-dimensional time series data of a plurality of joints of the human body are extracted from the image as samples; modeling is carried out on the samples by using self-feedback gene expression programming constructed by adding a TIS insertion string operation into gene expression programming after intersection and variation, thereby obtaining a human body motion model, wherein the TIS insertion string operation indicates the operation of inserting a function string into a joint motion sequence head; and then gradient information is extracted as a model feature. The model characteristics of the human body motion model of the training sample are input to a neural network and training is carried out to obtain a neural network model as a human body behavior classifier; and model characteristic of a human body movement model corresponding to a tested sample are inputted into the obtained human body behavior classifier to obtain a human body behavior recognition result. The method has advantages of high human body behavior identification accuracy and fast identification speed.

A program storage device is provided readable by machine, tangibly embodying a program of instructions executable by the machine to perform method steps for classification of biological tissue by gene expression profiling. The method steps include providing a training set of gene expression profiles of known tissue samples, providing a first-layer strong classifier of the known tissue samples by combining weak classifiers using boosting, creating two sample sets based on the first classifier, populating the two sample sets with a next-layer of classifiers based on a previous-layer classifier, organizing the classifiers in a tree data structure, and outputting the tree data structure as a probabilistic boosting tree classifier for tissue sample classification and disease subtype discovery. A multi-class diagnosis problem is transformed to a two-class diagnosis process by finding an optimal feature and dividing the multi-class problem into two-classes.

The invention relates to an ore rock intensity prediction method based on component thermodynamic gene expression programming. With a provided component thermodynamic gene expression programming algorithm, the invention adopts a water absorption rate, a dry density, wave impedance, a dynamic Poisson's ratio, and a dynamic elastic modulus as input variables, adopts compressive strength as an output variable, automatically and intelligently digs out a mathematical model of the ore rock intensity, and thus predicts the compressive strength of the ore rock. The invention can quantitatively harmonize the balance between a selected pressure and population diversity in the gene expression programming, and thus improves the rate of convergence, solving precision and algorithmic stability of traditional gene expression programming when applied to the prediction of ore rock intensity.

The invention provides a group behavior logic optimization method and a computer readable storage medium. According to the group behavior logic optimization method, firstly abstract discrete group behaviors and behavior execution logic are mapped to a behavior tree BT, then the behavior tree is mapped to an expression tree ET which can be optimized by a gene expression programming GEP algorithm, and the BT is optimized through the specific code in the ET optimized by the GEP algorithm, so that the optimization of the group behavior logic is finally realized. The group behavior logic optimization method provided by the invention has good optimization performance, so that a large amount of time can be saved when the optimized group behavior logic executes the task.

The invention discloses a mould thermal treatment workshop dynamic batch scheduling method. According to the method, a gene expression programming algorithm is applied, a batch gene and a structural gene are acquired according to the workpiece attributes, wherein the batch gene carries a priority calculation formula of the primary workpiece family and the structural gene determines the loading order of all batches of workpieces, and the outstanding individuals of each generation are enabled to be reserved through the algorithm and further inherited so that the optimal scheme is obtained.

The invention discloses a fractal image compression coding method based on CNN and GEP, which comprises the following steps: respectively segmenting an image to be compressed into a plurality of valuedomain sub-blocks which are not overlapped and a plurality of overlapped definitional domain sub-blocks, forming a value domain block pool by the plurality of value domain sub-blocks, and forming a definitional domain block pool by the plurality of definitional domain sub-blocks; utilizing the optimal convolutional neural network model to classify the value domain block pool and the definitionaldomain block pool respectively to obtain a corresponding value domain block classification pool and a corresponding definitional domain block classification pool; and calculating a transformation parameter corresponding to each value domain sub-block set in the value domain block classification pool and a definitional domain sub-block set of the same category in the definitional domain block classification pool by utilizing an optimal gene expression programming model, so as to realize fractal image compression coding. According to the method, the compression encoding speed can be greatly increased, the encoding time is shortened, a high compression ratio is obtained, and the actual use requirement can be met.

The invention discloses a gene expression programming (GEP) bidirectional prediction-based short elliptic arc fitting method, belongs to the technical field of digital measurement, and relates to related knowledge in aspects of GEP prediction modeling and least square fit. The method comprises the step of firstly performing denoising processing on original observation data of a short elliptic arc by adopting a wavelet filtering method, and secondly performing bidirectional finite length prediction on the denoised observation data of the short elliptic arc by utilizing a constructed GEP prediction model, equivalently, extending the length of the short elliptic arc in essence. The invention proposes an adaptive definition method for a mutation rate of a GEP algorithm, which can effectively inhibit the occurrence of an algorithm prematurity phenomenon and increase the algorithm convergence speed. Finally, the predicted observation data of the short elliptic arc is fitted by adopting a weighted least square fit algorithm, so that the fitting precision and stability of the short elliptic arc are remarkably improved.

The invention provides a flexible flow shop combinatorial scheduling rule generation method considering batch processing. The method provided by the invention comprises the following steps: decomposing an FFSP-BPM problem involved in the invention, constructing corresponding scheduling rules, and combining the scheduling rules to generate a combined scheduling rule for solving an original problem; building a multi-objective optimization model by considering the FFSP-BPM problem of incompatible workpiece group batch operation under the conditions of workpiece dynamic arrival and uncertain working hours; and adopting an improved gene expression programming algorithm to generate a combinatorial scheduling rule to solve the FFSP-BPM problem, and providing improved strategies of repeated individual elimination, variable neighborhood search and self-adaptive genetic operators for the defects that repeated individuals are likely to occur in the algorithm and local optimum is caused. According to the method, a combined scheduling rule generation method is adopted for a flexible assembly batch workshop scheduling process considering incompatible workpiece family parallel batch processing so that the production efficiency is improved, and meanwhile, the scheduling process can be effectively guided.