42 results about "Biclustering" patented technology

The invention discloses a method for automatically identifying a breast tumor area based on an ultrasound image. The method comprises the following steps of acquiring the ultrasound image of the breast, and preprocessing the ultrasound image; segmenting the ultrasound image subjected to preprocessing through an image segmentation method to obtain a plurality of segmented subareas; extracting a grey level histogram, texture features, gradient features and morphological features of the ultrasound image, and combining the grey level histogram, the texture features, the gradient features and the morphological features of the ultrasound image with two-dimensional position information to obtain high-dimensionality feature vectors; selecting the most effective feature subset of the high-dimensionality feature vectors through feature ordering based on biclustering and a selection method; performing learning classification on the selected most effective feature subset through a classifier, and then automatically identifying the breast tumor area. By means of the method, the breast tumor area can be identified automatically from segment results of the breast tumor ultrasound image, therefore, automation performance of computer-aided diagnosis is improved, manual operation of clinical doctors is reduced, and subjective influence of clinical doctors is reduced.

The invention discloses a pollution space analysis method and device based on massive atmosphere pollution concentration data, and belongs to the field of atmosphere pollution monitoring. The method comprises the steps of obtaining the atmosphere pollution concentration data of a target area monitored by a ground high-density monitoring network; arranging the obtained atmosphere pollution concentration data in a matrix mode to obtain an atmosphere pollution concentration data matrix; conducting biclustering treatment on the atmosphere pollution concentration data matrix to obtain multiple biclustering blocks of different sensor monitoring stations; interpolating the atmosphere pollution concentration data after biclustering treatment is conducted into a grid of an air quality model, and conducting grid treatment; comparing the atmosphere pollution concentration in each grid with that in a surrounding grid to determine a high-concentration exhaust grid and obtain high-value areas of the different biclustering blocks. According to the pollution space analysis method and device based on the massive atmosphere pollution concentration data, air quality change precise characteristics in the district and county level can be obtained, local pollution source characteristics are discriminated, and more systematized technical support is formed for environment management.

The invention discloses an automatic generating algorithm of a microblog user label based on biclustering. The automatic generating algorithm is characterized by comprising the following steps: a semantic ontology is constructed by adopting a biclustering algorithm on the basis of Wikipedia; microblog information of a microblog user is obtained and preprocessed, so as to obtain a bag-of-words model; words are extracted from the bag-of-words model by utilizing the semantic ontology, and disambiguation is performed on ambiguous words; the words subjected to disambiguation are mapped to corresponding category nodes in the Wikipedia, so as to construct a category subtree; the user label is collected by aiming at the microblog content of the user; finally, the user label is generated by adopting a voting strategy. According to the automatic generating algorithm, the semantic ontology is constructed by adopting the biclustering algorithm on the basis of the Wikipedia, equivalents of text words in microblog are positioned, the disambiguation is performed on the ambiguous words, categories accurately correspond to the words, and the label with high accuracy is generated for the user.

The invention belongs to the field of indoor positioning technology, and discloses an indoor positioning method based on CSI space-frequency characteristics and a reference point location clustering algorithm. According to the method, CSI data of which a physical layer is finer-grained and more robust is taken as physical information to ensure that the perceptual ability of the system is much higher than that of RSS, and the influence of multi-path effects can be effectively avoided; CSI space-frequency characteristic vector clustering and reference point location multi-index clustering technologies are adopted, members of which the geographical locations are relatively far away from other cluster members in an original cluster are separately divided into a cluster, and thus the phenomenon that reference points which have relatively far geographical locations and approximate CSI space-frequency characteristic vectors are merged into the same cluster can be avoided; and a biclustering technology including CSI space-frequency characteristic clustering and reference point location clustering is adopted, and the clusters that should not be split are merged into a cluster again, the integrity of the original clusters can be ensured while the processing of singular points is completed, and thus a better clustering effect can be achieved.

The invention discloses an order-preserving submatrix (OPSM) and frequent sequence mining based emotion classification method for e-commerce comments. The method comprises the following steps: (1) performing pretreatment and Chinese word segmentation on the e-commerce comments; calculating to obtain a TF-IDF weight vector of synonyms; and then mining a local mode in the weight vector through a biclustering algorithm based on OPSM; (3) mining classification frequent phrase characteristics through an improved PrefixSpan algorithm, and meanwhile, improving the capacity for distinguishing emotion tendency by the frequent phrases through limitation such as word intervals; and (4) converting the characteristics mined in steps (2) and (3) into a 0/ 1 vector to be used as an input of a classifier, and thus obtaining the emotion classification result of the e-commerce comments. With the adoption of the method, the emotion classification characteristics of the e-commerce comments can be accurately mined, so that potential customers can know the goods evaluation information before buying, and meanwhile, the businessman can fully know the suggestions of the customers and accordingly improve the service quality.

The invention relates to a method for realizing fast-speed short text bi-cluster. The method comprises the following steps of: (1) preprocessing short text disturbance items, and carrying out fast-speed unrelated-language and word-class recognition and processing recognition on short texts with the support of an unrelated-language dictionary and a word-class dictionary; (2) calculating the similarity of two preprocessed short texts to form a short text similarity sparse matrix; (3) carrying out short text first-level clustering on the short text similarity sparse matrix, and dividing similar short texts into clusters one by one according to the calculation result of the short text similarity; and (4) carrying out second-level clustering on the basis of the result of the first-level clustering.

Methods and systems for improved unsupervised learning are described. The unsupervised learning can consist of biclustering a data set, e.g., by biclustering subsets of the entire data set. In an example, the biclustering does not include feeding know and proven results into the biclustering methodology or system. A hierarchical approach can be used that feeds proven clusters back into the biclustering methodology or system as the input. Data that does not cluster may be discarded. Thus, a very large unknown data set can be acted on to learn about the data. The system is also amenable to parallelization.

The invention discloses an intelligent coordinate expression gene analyzer comprising a gene chip and a single chip computer. A gene expression profile of a biological sample is obtained through a gene chip collecting technique, and a gene set of coordinate expression is obtained by means of the single chip computer through an embedded analyzing technique. The single chip computer comprises a gene chip expression profile read module, a coordinate expression gene extraction module, a storing module and an output module. The extraction process of coordinate expression genes of the coordinate expression gene extraction module includes kernel function selection, immune clone memetic kernel biclustering algorithm coordination, obtaining of overlapped biclustering and the gene set of the coordinate expression. The intelligent coordinate expression gene analyzer can extract or express gene sets with a consistent trend or reversely expresses the related gene sets in the gene expression profile of the biological sample. Through searching for co-expression genes, not only are prompts provided for function researches of the genes, but also inspirations are provided for researches of gene regulation ways and gene regulation networks.

The invention discloses a bi-order genetic calculation-based gene expression data bi-clustering algorithm. A kth column is subtracted from each column in a matrix M to obtain a matrix M (k), and k is equal to 1, 2, ..., n; hierarchical clustering is performed on each column of M (k) to obtain a set of biclustering seeds; performing genetic calculation to obtain a corresponding bicluster. According to the algorithm, the defect that the conventional genetic calculation-based biclustering algorithm can only perform selection aiming at the bicluster can be solved, optimization is performed on rows and columns simultaneously, the search efficiency can be improved, and a more superior biclustering analysis effect is obtained.

The invention discloses a power consumer industry dimension power utilization mode identification and analysis method and system based on a biclustering method, and belongs to the technical field of power system load characteristic analysis. The method comprises: forming typical daily load data of each power consumer in the same industry through a method of calculating an average value; carrying out first load clustering by adopting a Ward clustering algorithm, and carrying out second clustering by taking a result of the Ward clustering algorithm as an initial value of an FCM clustering algorithm to obtain different power consumption modes of power consumers in the industry, thereby finishing power consumption mode identification analysis of the power consumer industry dimension. Accordingto the method, the reasonable initial value is generated through the Ward clustering method and substituted into the FCM clustering algorithm to analyze the power consumption mode of the user, and the problem that the clustering effect is poor due to initial value sensitivity of a traditional clustering method is solved.

The invention provides a hyperspectral image waveband selection method based on biclustering and a neighborhood analysis. The method comprises the following steps of extracting a dual-spectral angle characteristic and a hyperspectral-image original wave band; clustering the characteristic; clustering the acquired characteristics respectively and then constructing connection between two clustering results; according to the acquired wave band clustering results, selecting one representative from each cluster, and simultaneously considering a specificity of each representative and expressivity of each representative in the corresponding cluster so as to deciding a cluster representative, which means that the final wave band is selected; and using the acquired wave band to carry out hyperspectral image classification. In the invention, a bicharacteristic idea is provided, and a limitation that a wave band gray value is only used as a spectral characteristic in a traditional cluster algorithm is overcome so that wave band selection precision is increased.

The invention discloses a stock trading behavior prediction method based on biclustering mining, naive Bayesian and AdaBoost, which selects stock data within a certain period of time as the training set of the forecasting model, and first utilizes biclustering algorithm to mine stock data. According to different stock technical indicators, the stock price change trend can be divided into three situations: rising, flat and falling, which correspond to the buying point, holding point and selling point in stock trading. Then use the mined transaction patterns to construct a classifier based on Naive Bayesian, and finally use the AdaBoost algorithm to combine multiple weak classifiers to form a strong classifier with strong generalization ability and high classification accuracy. The proposed method can predict the changing trend of stock prices and provide valuable reference for investors' trading behavior.

The invention discloses a stock trading rule prediction method based on biclustering mining and fuzzy reasoning. The stock trading rule prediction method comprises the steps of firstly, selecting stock data in a period of time as a data set for mining biclustering, calculating a technical index value corresponding to stock original data of each day according to different technical index formulas, constructing an index matrix A=(a<ij>) <m*n>, mining the biclustering in the data set by adopting a biclustering algorithm, wherein each biclustering corresponds to a mode of trading rules in the stock data set, constructing fuzzy rules with pertinence by utilizing the mined biclustering, and finally constructing a fuzzy prediction model and predicting the trading rules according to all the obtained fuzzy rules. The prediction model provided by the stock trading rule prediction method can be used for predicting the trading rules in stock price curves, provides the best stock buying or selling reference opportunity for investors, and solves the problems in the traditional method that the rule for constructing fuzzy rules according to expert experiences is not objective and the expert experiences are difficult to obtain.

The invention relates to the technical field of artificial intelligence, and provides a semantic-based document clustering method, which comprises the steps of obtaining an input document and preprocessing the input document; performing word frequency statistics and inverse document frequency calculation on each word contained in the processed input document to construct a word frequency-inverse document matrix; inputting words adopted in word frequency statistics into a pre-stored natural language processing model as objects to obtain a similarity matrix matched with the word frequency-inverse document matrix; performing semantic propagation on the word frequency-inverse document matrix according to the similarity matrix to obtain a second word frequency-inverse document matrix; and performing bidirectional clustering on the second word frequency-inverse document matrix to obtain at least one biclustering cluster, the biclustering cluster comprising a document cluster and a word cluster, and performing label endowing on each document in the document cluster according to feature words contained in the word cluster. According to the invention, the problem of low accuracy of a document clustering result in the prior art is solved. The invention also relates to the field of blockchains, wherein the natural language processing model can be stored on the blockchain.

The invention provides a medical treatment fraud behavior detection method and system based on multi-view biclustering. The method comprises the steps: obtaining treatment information and demographicinformation, and carrying out the preprocessing of the obtained data; according to the medical insurance medical records of the medical insurance insured individuals obtained after preprocessing, performing double clustering on a first view formed by the insured person set, the medical seeking time and the medical seeking place information set and a second view formed by the insured person set andthe medicine information set at the same time to obtain a patient cluster with consistent cross views as a medical seeking fraud behavior group; according to the method, a biclustering algorithm is utilized, Meanwhile, a health medical knowledge base is introduced, so that suspicious patient groups frequently seeing a doctor at the same time and the same place can be mined, and misjudged normal patients caused by long-term regular doctor seeing can be filtered, and therefore, medical insurance fraudulent behaviors can be identified more accurately.

Provided is a device and method for detecting co-fit genes. The GRACOB device and method may detect co-fit genes from growth phenotype profiling data. The GRACOB device and method may discover the maximal constant-column biclusters, fully taking advantage of the properties of the growth phenotype profiling data. The identified co-fit genes may guide systems biology and synthetic biology studies and industries by determining important candidates for the growth of the respective microorganisms.

The invention discloses a stock transaction point prediction method and system based on a minimum entropy score, and a storage medium. The method comprises the steps: obtaining stock data, obtaining the technical indexes of a plurality of transaction days according to the stock data, and constructing an index matrix according to the obtained technical indexes; calculating a future return rate according to the stock data, obtaining a trend grade according to the future return rate, and obtaining a data matrix in combination with the trend grade and the index matrix; mining a stock trend mode ofthe data matrix by adopting a biclustering algorithm based on a minimum entropy score to obtain a transaction rule; and predicting transaction operations in combination with the transaction rules anda preset neural network, wherein the transaction operations include selling, no operation and buying. According to the method, the biclustering algorithm based on the minimum entropy score can effectively help to find transaction information and rules hidden behind stock historical data, transaction prediction information with high reference value can be provided for investors, and the method canbe widely applied to prediction of stock market transaction operation.

The invention discloses a weight control method based on a bi-clustering adaptive fuzzy neural network, which is characterized in that according to habits of field operators, existing data are utilized to realize weight control under the conditions of no target value record and expert experience. The method comprises the following steps: obtaining a weighing bin weight target value and a fuzzy rule among weighing bin weight deviation, deviation change rate and feeding quantity deviation by utilizing biclustering, further learning the fuzzy rule by utilizing a fuzzy neural network, and finally obtaining a biclustering adaptive fuzzy neural network controller, thereby realizing control on the weight of the weighing bin. According to the invention, the target value of the weight of the weighing bin can be adaptively obtained, and the experience of an operator is learned to obtain the dual-clustering adaptive fuzzy neural network controller, so that the real-time control of the weight of the weighing bin can be realized.

The invention discloses a single pilot driving mode task-function distribution verification method, and the method comprises the steps: constructing a flight scene model, a system organization architecture model, a system operation state model and a task organization management model of a double-pilot driving mode and a single pilot driving mode; task-function matrixes of a double-pilot driving mode and a single-pilot driving mode are extracted from the model and then combined, and a TsCluster algorithm is adopted to carry out differential use task-function bi-clustering and low use task-function bi-clustering mining and coverage rate calculation on the combined matrixes; and verifying and analyzing whether the single-person driving function decomposition can meet the requirement of a double-person driving task or not. According to the method, the constructed system model is combined with a bi-clustering mining algorithm, and based on a mining result, the coverage rate of a single pilot driving mode covering double-person driving requirements is calculated, verified and analyzed.