• Title, Summary, Keyword: Dimensionality Reduction

Search Result 171, Processing Time 0.043 seconds

A Method for Microarray Data Analysis based on Bayesian Networks using an Efficient Structural learning Algorithm and Data Dimensionality Reduction (효율적 구조 학습 알고리즘과 데이타 차원축소를 통한 베이지안망 기반의 마이크로어레이 데이타 분석법)

  • 황규백;장정호;장병탁
    • Journal of KIISE:Software and Applications
    • /
    • v.29 no.11
    • /
    • pp.775-784
    • /
    • 2002
  • Microarray data, obtained from DNA chip technologies, is the measurement of the expression level of thousands of genes in cells or tissues. It is used for gene function prediction or cancer diagnosis based on gene expression patterns. Among diverse methods for data analysis, the Bayesian network represents the relationships among data attributes in the form of a graph structure. This property enables us to discover various relations among genes and the characteristics of the tissue (e.g., the cancer type) through microarray data analysis. However, most of the present microarray data sets are so sparse that it is difficult to apply general analysis methods, including Bayesian networks, directly. In this paper, we harness an efficient structural learning algorithm and data dimensionality reduction in order to analyze microarray data using Bayesian networks. The proposed method was applied to the analysis of real microarray data, i.e., the NC160 data set. And its usefulness was evaluated based on the accuracy of the teamed Bayesian networks on representing the known biological facts.

On Combining Genetic Algorithm (GA) and Wavelet for High Dimensional Data Reduction

  • Liu, Zhengjun;Wang, Changyao;Zhang, Jixian;Yan, Qin
    • Proceedings of the KSRS Conference
    • /
    • /
    • pp.1272-1274
    • /
    • 2003
  • In this paper, we present a new algorithm for high dimensional data reduction based on wavelet decomposition and Genetic Algorithm (GA). Comparative results show the superiority of our algorithm for dimensionality reduction and accuracy improvement.

  • PDF

Major gene interaction identification in Hanwoo by adjusted environmental effects (환경적인 요인을 보정한 한우의 우수 유전자 조합 선별)

  • Lee, Jea-Young;Jin, Mi-Hyun
    • Journal of the Korean Data and Information Science Society
    • /
    • v.23 no.3
    • /
    • pp.467-474
    • /
    • 2012
  • Human diseases and livestock economic traits are not typically the result of variation of a single genetic locus, but are rather the result of interplay between interactions among multiple genes and a variety of environmental exposures. We have used linear regression model for adjusted environmental effects and multifactor dimensionality reduction (MDR) method to identify gene-gene interaction effect of statistical model in general. Of course, we use 5 SNPs (single uncleotide polymorphism) which were studied recently by Oh et al. (2011). We apply the MDR (multifactor demensionality reduction) method on the identify major interaction effects of single nucleotide polymorphisms responsible for economic traits in a Korean cattle population.

A Novel Approach of Feature Extraction for Analog Circuit Fault Diagnosis Based on WPD-LLE-CSA

  • Wang, Yuehai;Ma, Yuying;Cui, Shiming;Yan, Yongzheng
    • Journal of Electrical Engineering and Technology
    • /
    • v.13 no.6
    • /
    • pp.2485-2492
    • /
    • 2018
  • The rapid development of large-scale integrated circuits has brought great challenges to the circuit testing and diagnosis, and due to the lack of exact fault models, inaccurate analog components tolerance, and some nonlinear factors, the analog circuit fault diagnosis is still regarded as an extremely difficult problem. To cope with the problem that it's difficult to extract fault features effectively from masses of original data of the nonlinear continuous analog circuit output signal, a novel approach of feature extraction and dimension reduction for analog circuit fault diagnosis based on wavelet packet decomposition, local linear embedding algorithm, and clone selection algorithm (WPD-LLE-CSA) is proposed. The proposed method can identify faulty components in complicated analog circuits with a high accuracy above 99%. Compared with the existing feature extraction methods, the proposed method can significantly reduce the quantity of features with less time spent under the premise of maintaining a high level of diagnosing rate, and also the ratio of dimensionality reduction was discussed. Several groups of experiments are conducted to demonstrate the efficiency of the proposed method.

Nearest-Neighbor Collaborative Filtering Using Dimensionality Reduction by Non-negative Matrix Factorization (비부정 행렬 인수분해 차원 감소를 이용한 최근 인접 협력적 여과)

  • Ko, Su-Jeong
    • The KIPS Transactions:PartB
    • /
    • v.13B no.6
    • /
    • pp.625-632
    • /
    • 2006
  • Collaborative filtering is a technology that aims at teaming predictive models of user preferences. Collaborative filtering systems have succeeded in Ecommerce market but they have shortcomings of high dimensionality and sparsity. In this paper we propose the nearest neighbor collaborative filtering method using non-negative matrix factorization(NNMF). We replace the missing values in the user-item matrix by using the user variance coefficient method as preprocessing for matrix decomposition and apply non-negative factorization to the matrix. The positive decomposition method using the non-negative decomposition represents users as semantic vectors and classifies the users into groups based on semantic relations. We compute the similarity between users by using vector similarity and selects the nearest neighbors based on the similarity. We predict the missing values of items that didn't rate by a new user based on the values that the nearest neighbors rated items.

Support vector machine and multifactor dimensionality reduction for detecting major gene interactions of continuous data (서포트 벡터 머신 알고리즘을 활용한 연속형 데이터의 다중인자 차원축소방법 적용)

  • Lee, Jea-Young;Lee, Jong-Hyeong
    • Journal of the Korean Data and Information Science Society
    • /
    • v.21 no.6
    • /
    • pp.1271-1280
    • /
    • 2010
  • We have used multifactor dimensionality reduction (MDR) method to study genegene interaction effect of statistical model in general. But, MDR method could not be applied in the continuous data. In this paper, continuous-type data by the support vector machine (SVM) algorithm are proposed to the MDR method which provides an introduction to the technique. Also we apply the method on the identify major interaction effects of single nucleotide polymorphisms (SNPs) responsible for economic traits in a Korean cattle population.

Power and major gene-gene identification of dummy multifactor dimensionality reduction algorithm (더미 다중인자 차원축소법에 의한 검증력과 주요 유전자 규명)

  • Yeo, Jungsou;La, Boomi;Lee, Ho-Guen;Lee, Seong-Won;Lee, Jea-Young
    • Journal of the Korean Data and Information Science Society
    • /
    • v.24 no.2
    • /
    • pp.277-287
    • /
    • 2013
  • It is important to detect the gene-gene interaction in GWAS (genome-wide association study). There have been many studies on detecting gene-gene interaction. The one is D-MDR (dummy multifoactor dimensionality reduction) method. The goal of this study is to evaluate the power of D-MDR for identifying gene-gene interaction by simulation. Also we applied the method on the identify interaction effects of single nucleotide polymorphisms (SNPs) responsible for economic traits in a Korean cattle population (real data).

Genetic effects of sterol regulatory element binding proteins and fatty acid-binding protein4 on the fatty acid composition of Korean cattle (Hanwoo)

  • Oh, Dong-Yep;Lee, Jea-Young;Jang, Ji-Eun;Lee, Seung-Uk
    • Asian-Australasian Journal of Animal Sciences
    • /
    • v.30 no.2
    • /
    • pp.160-166
    • /
    • 2017
  • Objective: This study identifies single-nucleotide polymorphisms (SNP) or gene combinations that affect the flavor and quality of Korean cattle (Hanwoo) by using the SNP Harvester method. Methods: Four economic traits (oleic acid [C18:1], saturated fatty acids), monounsaturated fatty acids, and marbling score) were adjusted for environmental factors in order to focus solely on genetic effects. The SNP Harvester method was used to investigate gene combinations (two-way gene interactions) associated with these economic traits. Further, a multifactor dimensionality reduction method was used to identify superior genotypes in gene combinations. Results: Table 3 to 4 show the analysis results for differences between superior genotypes and others for selected major gene combinations using the multifactor dimensionality reduction method. Environmental factors were adjusted for in order to evaluate only the genetic effect. Table 5 shows the adjustment effect by comparing the accuracy before and after correction in two-way gene interactions. Conclusion: The g.3977-325 T>C and (g.2988 A>G, g.3977-325 T>C) combinations of fatty acid-binding protein4 were the superior gene, and the superior genotype combinations across all economic traits were the CC genotype at g.3977-325 T>C and the AACC, GACC, GGCC genotypes of (g.2988 A>G, g.3977-325 T>C).

Human Action Recognition Based on 3D Human Modeling and Cyclic HMMs

  • Ke, Shian-Ru;Thuc, Hoang Le Uyen;Hwang, Jenq-Neng;Yoo, Jang-Hee;Choi, Kyoung-Ho
    • ETRI Journal
    • /
    • v.36 no.4
    • /
    • pp.662-672
    • /
    • 2014
  • Human action recognition is used in areas such as surveillance, entertainment, and healthcare. This paper proposes a system to recognize both single and continuous human actions from monocular video sequences, based on 3D human modeling and cyclic hidden Markov models (CHMMs). First, for each frame in a monocular video sequence, the 3D coordinates of joints belonging to a human object, through actions of multiple cycles, are extracted using 3D human modeling techniques. The 3D coordinates are then converted into a set of geometrical relational features (GRFs) for dimensionality reduction and discrimination increase. For further dimensionality reduction, k-means clustering is applied to the GRFs to generate clustered feature vectors. These vectors are used to train CHMMs separately for different types of actions, based on the Baum-Welch re-estimation algorithm. For recognition of continuous actions that are concatenated from several distinct types of actions, a designed graphical model is used to systematically concatenate different separately trained CHMMs. The experimental results show the effective performance of our proposed system in both single and continuous action recognition problems.