Gene expression profiles belonging to DNA microarrays are composed of thousands of genes at the same time, representing the complex relationships between them. In this context, the ability of designing methods capable...
详细信息
ISBN:
(纸本)3540454853
Gene expression profiles belonging to DNA microarrays are composed of thousands of genes at the same time, representing the complex relationships between them. In this context, the ability of designing methods capable of overcoming current limitations is crucial to reduce the generalization error of state-of-the-art algorithms. this paper presents the application of a self-organised growing cell structures network in an attempt to cluster biological homogeneous patients. this technique makes use of a previous successful supervised fuzzy pattern algorithm capable of performing DNA microarray data reduction. the proposed model has been tested with microarray data belonging to bone marrow samples from 43 adult patients with cancer plus a group of six cases corresponding to healthy persons. the results of this work demonstrate that classical artificial intelligence techniques can be effectively used for tumour diagnosis working with high-dimensional microarray data.
A model selection method based on tabu search is proposed to build support vector machines (binary decision functions) of reduced complexity and efficient generalization. the aim is to build a fast and efficient suppo...
详细信息
A model selection method based on tabu search is proposed to build support vector machines (binary decision functions) of reduced complexity and efficient generalization. the aim is to build a fast and efficient support vector machines classifier. A criterion is defined to evaluate the decision function quality which blends recognition rate and the complexity of a binary decision functions together. the selection of the simplification level by vector quantization, of a feature subset and of support vector machines hyperparameters are performed by tabu search method to optimize the defined decision function quality criterion in order to find a good sub-optimal model on tractable times.
this paper presents a fast algorithm for training relevance vector machine classifiers for dealing with large data set. the core principle is to remove dependent data points before training a relevance vector machine ...
详细信息
A novel shape descriptor, chord length function (CLF) which can be obtained by equal arc length partitions of a contour, is proposed. the difference of two shapes is measured by the distance between their correspondin...
详细信息
the rapid development of methods that select over/under expressed genes from RNA microarray experiments have not yet satisfied the need for tools that identify differential profiles that distinguish between experiment...
详细信息
ISBN:
(纸本)3540454853
the rapid development of methods that select over/under expressed genes from RNA microarray experiments have not yet satisfied the need for tools that identify differential profiles that distinguish between experimental conditions such as time, treatment and phenotype. We evaluate several microarray analysis methods and study their performance, finding that none of the methods alone identifies all observable differential profiles, nor subsumes the results obtained by the other methods. therefore, we propose a machine learning based methodology that identifies and combines the abilities of microarray analysis methods to recognize differential profiles. We encode the results of this methodology in decision making association rules able to decide which method or method-aggregation is optimal to retrieve a set of genes exhibiting a common profile. these solutions are optimal in the sense that they constitute partial ordered subsets of all method-aggregations bounded by the most specific and the most sensitive available solution. this methodology was successfully applied to a study of inflammation and host response to injury data set derived from the analysis of longitudinal blood microarray profiles of human volunteers treated with intravenous endotoxin compared to placebo. Our approach was able to uncover a cohesive set of differentially expressed genes and novel members exhibiting previously studied differential profiles. this guideline serves as a means to support decisions on new microarray problems.
A critical challenge of the postgenomic era is to understand how genes are differentially regulated even when they belong to a given network. Because the fundamental mechanism controlling gene expression operates at t...
详细信息
ISBN:
(纸本)3540454853
A critical challenge of the postgenomic era is to understand how genes are differentially regulated even when they belong to a given network. Because the fundamental mechanism controlling gene expression operates at the level of transcription initiation, computational techniques have been developed that identify cis-regulatory features and map such features into differential expression patterns. the fact that such co-regulated genes may be differentially regulated suggests that subtle differences in the shared cis-acting regulatory elements are likely significant. thus, we carry out an exhaustive description of cis-acting regulatory features including the orientation, location and number of binding sites for a regulatory protein, the presence of binding site submotifs, the class and number of RNA polymerase sites, as well as gene expression data, which is treated as one feature among many. these features, derived from different domain sources, are analyzed concurrently, and dynamic relations are recognized to generate profiles, which are groups of promoters sharing common features. We apply this method to probe the regulatory networks governed by the PhoP/PhoQ two-component system in the enteric bacteria Escherichia coli and Salmonella enterica. Our analysis uncovered novel members of the PhoP regulon as and the resulting profiles group genes that share underlying biological that characterize the system kinetics. the predictions were experimentally validated to establish that the Phol? protein uses multiple mechanisms to control gene transcription and is a central element in a highly connected network.
the mass function of evidential theory provides a means of representing ignorance in lack of information. In this paper we propose mass function models of aggregate views held as summary tables in a distributed databa...
详细信息
In this paper we develop and analyze methods for expanding automatedlearning of Relevance Vector Machines (RVM) to large scale text sets. RVM rely on Bayesian inference learning and while maintaining state-of-the-art...
详细信息
In this paper we develop and analyze methods for expanding automatedlearning of Relevance Vector Machines (RVM) to large scale text sets. RVM rely on Bayesian inference learning and while maintaining state-of-the-art performance, offer sparse and probabilistic solutions. However, efforts towards applying RVM to large scale sets have met with limited success in the past, due to computational constraints. We propose a diversified set of divide-and-conquer approaches where decomposition techniques promote the definition of smaller working sets that permit the use of all training examples. the rationale is that by exploring incremental, ensemble and boosting strategies, it is possible to improve classification performance, taking advantage of the large training set available. Results on Reuters-21578 and RCV1 are presented, showing performance gains and maintaining sparse solutions that can be deployed in distributed environments.
this paper proposes the utilization of rough set theory for predicting student scholar performance. the rough set theory is a powerful approach that permits the searching for patterns in e-learningdatabase using the ...
详细信息
ISBN:
(纸本)9783319108407;9783319108391
this paper proposes the utilization of rough set theory for predicting student scholar performance. the rough set theory is a powerful approach that permits the searching for patterns in e-learningdatabase using the minimal length principles. Searching for models with small size is performed by means of many different kinds of reducts that generate the decision rules capable for identifying the final student grade.
暂无评论