Browsing by Author "Theera Piroonratana"

Filter results by typing the first few letters
Now showing 1 - 8 of 8
  • No Thumbnail Available
    PublicationMetadata only
    Classification of complete blood count and haemoglobin typing data by a C4.5 decision tree, a naïve Bayes classifier and a multilayer perceptron for thalassaemia screening
    (2012-03-01) Damrongrit Setsirichok; Theera Piroonratana; Waranyu Wongseree; Touchpong Usavanarong; Nuttawut Paulkhaolarn; Chompunut Kanjanakorn; Monchan Sirikong; Chanin Limwongse; Nachol Chaiyaratana; King Mongkut's University of Technology North Bangkok; Mahidol University
    This article presents the classification of blood characteristics by a C4.5 decision tree, a naïve Bayes classifier and a multilayer perceptron for thalassaemia screening. The aim is to classify eighteen classes of thalassaemia abnormality, which have a high prevalence in Thailand, and one control class by inspecting data characterised by a complete blood count (CBC) and haemoglobin typing. Two indices namely a haemoglobin concentration (HB) and a mean corpuscular volume (MCV) are the chosen CBC attributes. On the other hand, known types of haemoglobin from six ranges of retention time identified via high performance liquid chromatography (HPLC) are the chosen haemoglobin typing attributes. The stratified 10-fold cross-validation results indicate that the best classification performance with average accuracy of 93.23% (standard deviation = 1.67%) and 92.60% (standard deviation = 1.75%) is achieved when the naïve Bayes classifier and the multilayer perceptron are respectively applied to samples which have been pre-processed by attribute discretisation. The results also suggest that the HB attribute is redundant. Moreover, the achieved classification performance is significantly higher than that obtained using only haemoglobin typing attributes as classifier inputs. Subsequently, the naïve Bayes classifier and the multilayer perceptron are applied to an additional data set in a clinical trial which respectively results in accuracy of 99.39% and 99.71%. These results suggest that a combination of CBC and haemoglobin typing analysis with a naïve Bayes classifier or a multilayer perceptron is highly suitable for automatic thalassaemia screening. © 2011 Elsevier Ltd. All rights reserved.
  • No Thumbnail Available
    ItemMetadata only
    Conceptual legal framework of open government data for Thailand : data governance aspects
    (Mahidol University. Mahidol University Library and Knowledge Center, 2018) Natcha Dumthanasarn; Sotarat Thammaboosadee; Smitti Darakorn Na Ayuthaya; Theera Piroonratana
    Data Governance for open government data is a significant process which defines the roles and responsibilities of the person in charge of data management in a government agency to gain the open government data and to use it correctly, ensure the security of personal data including defining the standardization of data, consistency and effectively link and use open data between the agencies. Many countries in the world have considered data governance and dissemination of open government data to the citizens imperative, therefore there is need for a prescribed law that regard this issue. Although, Thailand has prescribed a draft of public information act, data governance for government data is still unclear. Therefore, this research proposed a conceptual legal framework for open government data in terms of data governance aspects by doing a gap analysis and comparative results between Public Information Act of the United State of America, the Republic of Korea and the current draft of Public Information Act of Thailand on the issues of organizational structure and roles and responsibilities of Public Information Committee. This included defining the standardization and security on open data by taking data governance framework of Data Governance Institute (DGI framework) as a guideline for determining the procedures and compliance according to the data governance framework for Thailand. The evaluation of issues that had a legal impact on the use of public data was done by the legal expert. The results of this research would be a guideline for the revision of the Public Information Act in the future.
  • No Thumbnail Available
    PublicationMetadata only
    Identification of ancestry informative markers from chromosome-wide single nucleotide polymorphisms using symmetrical uncertainty ranking
    (2010-11-18) Theera Piroonratana; Waranyu Wongseree; Touchpong Usavanarong; Anunchai Assawamakin; Chanin Limwongse; Nachol Chaiyaratana; King Mongkut's University of Technology North Bangkok; Mahidol University
    Ancestry informative markers (AIMs) have been proven to contain necessary information for population classification. In this article, round robin symmetrical uncertainty ranking for preliminary AIM screening is proposed. Each single nucleotide polymorphism (SNP) is assigned a rank based on its ability to separate two populations from each other. In a multi-population scenario, all possible population pairs are considered and the screened SNP set incorporates top-ranked SNPs from every pair-wise comparison. After the preliminary screening, SNPs are further screened by a wrapper which is embedded with a naive Bayes classifier. A classification model is subsequently constructed from the finally screened SNPs via a naive Bayes classifier. The application of the proposed procedure to the HapMap data indicates that AIM panels can be found on all chromosomes. Each panel consists of 11 to 24 SNPs and can be used to completely classify the CEU, CHB, JPT and YRI populations. Moreover, all panels are smaller than the AIM panels reported in previous studies. © 2010 IEEE.
  • No Thumbnail Available
    PublicationMetadata only
    An omnibus permutation test on ensembles of two-locus analyses can detect pure epistasis and genetic heterogeneity in genome-wide association studies
    (2013-06-14) Damrongrit Setsirichok; Phuwadej Tienboon; Nattapong Jaroonruang; Somkit Kittichaijaroen; Waranyu Wongseree; Theera Piroonratana; Touchpong Usavanarong; Chanin Limwongse; Chatchawit Aporntewan; Marongx Phadoongsidhi; Nachol Chaiyaratana; King Mongkut's University of Technology North Bangkok; King Mongkuts University of Technology Thonburi; Mahidol University; Chulalongkorn University
    This article presents the ability of an omnibus permutation test on ensembles of two-locus analyses (2LOmb) to detect pure epistasis in the presence of genetic heterogeneity. The performance of 2LOmb is evaluated in various simulation scenarios covering two independent causes of complex disease where each cause is governed by a purely epistatic interaction. Different scenarios are set up by varying the number of available single nucleotide polymorphisms (SNPs) in data, number of causative SNPs and ratio of case samples from two affected groups. The simulation results indicate that 2LOmb outperforms multifactor dimensionality reduction (MDR) and random forest (RF) techniques in terms of a low number of output SNPs and a high number of correctly-identified causative SNPs. Moreover, 2LOmb is capable of identifying the number of independent interactions in tractable computational time and can be used in genome-wide association studies. 2LOmb is subsequently applied to a type 1 diabetes mellitus (T1D) data set, which is collected from a UK population by the Wellcome Trust Case Control Consortium (WTCCC). After screening for SNPs that locate within or near genes and exhibit no marginal single-locus effects, the T1D data set is reduced to 95,991 SNPs from 12,146 genes. The 2LOmb search in the reduced T1D data set reveals that 12 SNPs, which can be divided into two independent sets, are associated with the disease. The first SNP set consists of three SNPs from MUC21 (mucin 21, cell surface associated), three SNPs from MUC22 (mucin 22), two SNPs from PSORS1C1 (psoriasis susceptibility 1 candidate 1) and one SNP from TCF19 (transcription factor 19). A four-locus interaction between these four genes is also detected. The second SNP set consists of three SNPs from ATAD1 (ATPase family, AAA domain containing 1). Overall, the findings indicate the detection of pure epistasis in the presence of genetic heterogeneity and provide an alternative explanation for the aetiology of T1D in the UK population. © 2013 Setsirichok et al.
  • No Thumbnail Available
    PublicationMetadata only
    An omnibus permutation test on ensembles of two-locus analyses for the detection of purely epistatic multi-locus interactions
    (2009-12-01) Waranyu Wongseree; Anunchai Assawamakin; Theera Piroonratana; Saravudh Sinsomros; Chanin Limwongse; Nachol Chaiyaratana; King Mongkut's University of Technology North Bangkok; Mahidol University
    Purely epistatic multi-locus interactions cannot generally be detected via single-locus analysis in case-control studies of complex diseases. Recently, many two-locus and multi-locus analysis techniques have been shown to be promising for the epistasis detection. However, exhaustive multi-locus analysis requires prohibitively large computational efforts when problems involve large-scale or genome-wide data. Furthermore, there is no explicit proof that a combination of multiple two-locus analyses can lead to the correct identification of multi-locus interactions. 2LOmb which performs an omnibus permutation test on ensembles of two-locus analyses is proposed. The algorithm consists of four main steps: two-locus analysis, a permutation test, global p-value determination and a progressive search for the best ensemble. 2LOmb is benchmarked against a set association approach, a correlation-based feature selection technique and a tuned ReliefF technique. The simulation results from multi-locus interaction problems indicate that 2LOmb has a low false-positive error. Moreover, 2LOmb has the best performance in terms of an ability to identify all causative single nucleotide polymorphisms (SNPs), which signifies a high detection power. 2LOmb is subsequently applied to type 1 and type 2 diabetes mellitus (T1D and T2D) data sets, which are obtained as a part of the UK genome-wide genetic epidemiology study by the Wellcome Trust Case Control Consortium. After primarily screening for SNPs that locate within or near candidate genes and exhibit no marginal single-locus effects, the T1D and T2D data sets are reduced to 2,359 SNPs from 350 genes and 7,065 SNPs from 370 genes, respectively. The 2LOmb search reveals that 28 SNPs in 21 genes are associated with T1D while 11 SNPs in four genes are associated with T2D. The findings provide an alternative explanation for the aetiology of T1D and T2D in a UK population. © 2009 Springer-Verlag Berlin Heidelberg.
  • No Thumbnail Available
    ItemMetadata only
    Risk assessment and prescriptive analytics for electrical devices production based on an integration of requirement forecasting and customer segmentation models
    (Mahidol University. Mahidol University Library and Knowledge Center, 2018) Preuksa Wongpitak; Sotarat Thammaboosadee; Smitti Darakorn Na Ayuthaya; Theera Piroonratana
    Material requirement planning is an important role of a manufacturing business. Manufacturers need to find an effective way to manage material planning among the changes. This research is designed to create an integrated model of time series forecasting of material requirements and customer segmentation model for risk assessment for electrical equipment procurement. The research was based on data from an electronic component manufacturing company from 2016 to 2017 for data mining process with Cross Industry Standard Process (CRISP-DM) concept. The method used in prediction to compare Gradient Boosted Tree (GBT), Artificial Neural Network (ANN) and Decision Trees (DT) and the K-means is method for clustering customer segmentation, using data in the form of RFM (Recency-Frequency-Monetary). The result shows that Gradient Boosted Trees provides more than 90% accuracy in predicting the LED rank and can save cost of resistor order around THB 4.6 million per month. Customer can be classified into three groups, Good, Moderate and Normal. The results of DT were then used to generate a risk assessment matrix. There is a level of credibility that determines customer priorities in the event of an order in less than the quotation period and optimization of time series forecasting models. Finally, the results of GBT were analyzed with Prescriptive analytics to do a strategy and allocate parts which align to customer behavior and according to the company policy. The results show that LED rank EX, EY and JUJ3 is for market in Europe, Asia and Local, respectively. Thus, the research is helpful and can be used in material purchasing planning and creating market strategy
  • No Thumbnail Available
    PublicationMetadata only
    Small Ancestry Informative Marker panels for complete classification between the original four HapMap populations
    (2012-11-27) Damrongrit Setsirichok; Theera Piroonratana; Anunchai Assawamakin; Touchpong Usavanarong; Chanin Limwongse; Waranyu Wongseree; Chatchawit Aporntewan; Nachol Chaiyaratana; King Mongkut's University of Technology North Bangkok; Thailand National Center for Genetic Engineering and Biotechnology; Mahidol University; Chulalongkorn University
    A protocol for the identification of Ancestry Informative Markers (AIMs) from genome-wide Single Nucleotide Polymorphism (SNP) data is proposed. The protocol consists of three main steps: identification of potential positive selection regions via F ST extremity measurement, SNP screening via two-stage attribute selection and classification model construction using a Naïve Bayes classifier. The two-stage attribute selection is composed of a newly developed round robin Symmetrical Uncertainty (SU) ranking technique and a wrapper embedded with a Naïve Bayes classifier. The protocol has been applied to the HapMap Phase II data. Two AIM panels, which consist of 10 and 16 SNPs that lead to complete classification between CEU, CHB, JPT and YRI populations, are identified. Moreover, the panels are at least four times smaller than those reported in previous studies. The results suggest that the protocol could be useful in a scenario involving a larger number of populations. Copyright © 2012 Inderscience Enterprises Ltd.
  • No Thumbnail Available
    PublicationMetadata only
    The Study of Hospital Information Systems in the 8thHealth Region
    (2016-01-01) Pichitpong Soontornpipit; Chanvit Taratep; Watcharawan Teerawat; Pratana Satitvipawee; Theera Piroonratana; Mahidol University; Thailand Ministry of Public Health
    © 2016 The Authors. The research aims to explore the existing hospital information system (HIS) and their resources in the 8thhealth region according to the roadmap for the National Health Information Center (NHIC) from Ministry of Public Health (MOPH). In order to determine the functions and flows between each system module for data interconnect and exchange, health provider levels from the primary care unit (first-level hospital) up to the provincial hospital (advance-level hospital) were analyzed. Four major categories, both the front-office and back-office, were evaluated by using questionnaire, survey, and interview. Medical services, inventory for drug and medical supply, monetary and fiscal, human resource, and surveillance process modules are mentioned. Infrastructures and their protocols are included in this investigation.