• 제목/요약/키워드: sparse functional data

검색결과 5건 처리시간 0.018초

클럽발 자료를 위한 함수적 군집 분석: 사례연구 (Functional clustering for clubfoot data: A case study)

  • 이미애;임요한;박천건;이경은
    • Journal of the Korean Data and Information Science Society
    • /
    • 제25권5호
    • /
    • pp.1069-1077
    • /
    • 2014
  • 클럽발은 발이 안쪽으로 굽어있는 상태로 태어나는 선천적인 발 기형의 일종이다. 본 연구에서는 한 쪽 클럽발 환자들의 수술 후 시간에 따른 양 쪽 발의 상대적인 차이 커브들을 군집분석 하려고 한다. 관측값들이 일정하지 않은 (irregular) 시점에서 희박하게 (sparsely) 관측되어서 일반적인 함수적 군집모형을 사용할 수 없어 James와 Sugar (2003) 가 제안한 희박한 자료의 함수적 군집 모형 (functional clustering model)을 이용하여 모수들을 추정하였다. 그리고 Sugar와 James (2003)의 왜곡함수 (distortion function)를 이용하여 군집의 수를 결정하여 군집분석하여 두 개의 군집을 발견하였다.

Classification of Cognitive States from fMRI data using Fisher Discriminant Ratio and Regions of Interest

  • Do, Luu Ngoc;Yang, Hyung Jeong
    • International Journal of Contents
    • /
    • 제8권4호
    • /
    • pp.56-63
    • /
    • 2012
  • In recent decades, analyzing the activities of human brain achieved some accomplishments by using the functional Magnetic Resonance Imaging (fMRI) technique. fMRI data provide a sequence of three-dimensional images related to human brain's activity which can be used to detect instantaneous cognitive states by applying machine learning methods. In this paper, we propose a new approach for distinguishing human's cognitive states such as "observing a picture" versus "reading a sentence" and "reading an affirmative sentence" versus "reading a negative sentence". Since fMRI data are high dimensional (about 100,000 features in each sample), extremely sparse and noisy, feature selection is a very important step for increasing classification accuracy and reducing processing time. We used the Fisher Discriminant Ratio to select the most powerful discriminative features from some Regions of Interest (ROIs). The experimental results showed that our approach achieved the best performance compared to other feature extraction methods with the average accuracy approximately 95.83% for the first study and 99.5% for the second study.

An integrated Bayesian network framework for reconstructing representative genetic regulatory networks.

  • Lee, Phil-Hyoun;Lee, Do-Heon;Lee, Kwang-Hyung
    • 한국생물정보학회:학술대회논문집
    • /
    • 한국생물정보시스템생물학회 2003년도 제2차 연례학술대회 발표논문집
    • /
    • pp.164-169
    • /
    • 2003
  • In this paper, we propose the integrated Bayesian network framework to reconstruct genetic regulatory networks from genome expression data. The proposed model overcomes the dimensionality problem of multivariate analysis by building coherent sub-networks from confined gene clusters and combining these networks via intermediary points. Gene Shaving algorithm is used to cluster genes that share a common function or co-regulation. Retrieved clusters incorporate prior biological knowledge such as Gene Ontology, pathway, and protein protein interaction information for extracting other related genes. With these extended gene list, system builds genetic sub-networks using Bayesian network with MDL score and Sparse Candidate algorithm. Identifying functional modules of genes is done by not only microarray data itself but also well-proved biological knowledge. This integrated approach can improve there liability of a network in that false relations due to the lack of data can be reduced. Another advantage is the decreased computational complexity by constrained gene sets. To evaluate the proposed system, S. Cerevisiae cell cycle data [1] is applied. The result analysis presents new hypotheses about novel genetic interactions as well as typical relationships known by previous researches [2].

  • PDF

Group Contribution Method 및 Support Vector Regression 기반 모델을 이용한 방향족 화합물 물성치 예측에 관한 연구 (Group Contribution Method and Support Vector Regression based Model for Predicting Physical Properties of Aromatic Compounds)

  • 강하영;오창보;원용선;유준;이창준
    • 한국안전학회지
    • /
    • 제36권1호
    • /
    • pp.1-8
    • /
    • 2021
  • To simulate a process model in the field of chemical engineering, it is very important to identify the physical properties of novel materials as well as existing materials. However, it is difficult to measure the physical properties throughout a set of experiments due to the potential risk and cost. To address this, this study aims to develop a property prediction model based on the group contribution method for aromatic chemical compounds including benzene rings. The benzene rings of aromatic materials have a significant impact on their physical properties. To establish the prediction model, 42 important functional groups that determine the physical properties are considered, and the total numbers of functional groups on 147 aromatic chemical compounds are counted to prepare a dataset. Support vector regression is employed to prepare a prediction model to handle sparse and high-dimensional data. To verify the efficacy of this study, the results of this study are compared with those of previous studies. Despite the different datasets in the previous studies, the comparison indicated the enhanced performance in this study. Moreover, there are few reports on predicting the physical properties of aromatic compounds. This study can provide an effective method to estimate the physical properties of unknown chemical compounds and contribute toward reducing the experimental efforts for measuring physical properties.

난소를 절제한 흰쥐 자궁상피의 호르몬투여에 대한 전자현미경적 연구 (Ultrastructural Study on the Luminal Epithelium of the Ovariectomized Rat Uterus after Hormonal Treatment)

  • 이재현;이헌주
    • Applied Microscopy
    • /
    • 제14권2호
    • /
    • pp.29-37
    • /
    • 1984
  • 난소절제한 흰쥐에서 $17{\beta}$-estradiol과 progesterone을 장기간 주사햐여 자궁상피의 형태적 변화를 전자현미경으로 관찰하였다. 난소절제 후 자궁상피는 막성구조물과 지방구 기타의 구조물을 포함하는 vacuole의 출현이 특이적으로 나타났다. 상피는 낮은 입방형이며 세포 유리면에 소수의 짧은 microvilli를 볼 수 있었다. Estradiol투여시 상피는 높은 윈주형을 나타내며, 분비계는 비교적 잘 발달되고, 세포 유리면에 소수의 긴 microvilli도 관찰되었다. Progesterone 처리시의 상피는 세포 첨단부에 다수의 vacuole과 핵하부에 다수의 지방구의 집적이 관찰되었다. 이상의 결과로 보아 자궁상피는 형태학적 및 기능적인 상태에서 estrogen과 Progesterone 양자에 의해 변화를 받으며 이들 호르몬은 상피세포에 대해 독특한 영향을 나타낸다고 생각된다.

  • PDF