KMITL

Permanent URI for this communityhttps://dspace.kmitl.ac.th/handle/123456789/1

Browse

Settings

Author: search.filters.author.Rathasamuth, WanthaneeSubject: search.filters.subject.Information gain

Search Results

Now showing 1 - 3 of 3
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Item,
    Discovery of significant porcine SNPs for swine breed identification by a hybrid of information gain, genetic algorithm, and frequency feature selection technique
    (2020-05-26)
    Pasupa, Kitsuchart
    ;
    Rathasamuth, Wanthanee
    ;
    Tongsima, Sissades
    Background: The number of porcine Single Nucleotide Polymorphisms (SNPs) used in genetic association studies is very large, suitable for statistical testing. However, in breed classification problem, one needs to have a much smaller porcine-classifying SNPs (PCSNPs) set that could accurately classify pigs into different breeds. This study attempted to find such PCSNPs by using several combinations of feature selection and classification methods. We experimented with different combinations of feature selection methods including information gain, conventional as well as modified genetic algorithms, and our developed frequency feature selection method in combination with a common classification method, Support Vector Machine, to evaluate the method's performance. Experiments were conducted on a comprehensive data set containing SNPs from native pigs from America, Europe, Africa, and Asia including Chinese breeds, Vietnamese breeds, and hybrid breeds from Thailand. Results: The best combination of feature selection methods - information gain, modified genetic algorithm, and frequency feature selection hybrid - was able to reduce the number of possible PCSNPs to only 1.62% (164 PCSNPs) of the total number of SNPs (10,210 SNPs) while maintaining a high classification accuracy (95.12%). Moreover, the near-identical performance of this PCSNPs set to those of bigger data sets as well as even the entire data set. Moreover, most PCSNPs were well-matched to a set of 94 genes in the PANTHER pathway, conforming to a suggestion by the Porcine Genomic Sequencing Initiative. Conclusions: The best hybrid method truly provided a sufficiently small number of porcine SNPs that accurately classified swine breeds.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Item,
    A Modified Binary Flower Pollination Algorithm: A Fast and Effective Combination of Feature Selection Techniques for SNP Classification
    (2019-10-01)
    Rathasamuth, Wanthanee
    ;
    Pasupa, Kitsuchart
    Single nucleotide polymorphism (SNP) is a genetic trait responsible for the differences in the characteristics of individuals of a living species. Machine learning has been brought in to classify swine breed according to their SNPs. However, since the number of samples (number of pigs sampled) is usually much smaller than the number of features (SNPs) to classify, there may occur an overfitting problem. Therefore, some feature selection techniques were applied to the entire SNPs to reduce them to a much smaller number of most significant SNPs to be used in the classification. In this study, we used information gain in combination with binary flower pollination algorithm for feature selection as well as a cut-off-point-finding threshold for specifying a 0 or 1 value for a position in the solution vector and a GA bit-flip mutation operator. We called it Modified-BFPA. The classifier was SVM. Evaluated against a few other feature selection techniques, our combination of techniques was, at the very least, competitive to those. It selected only 1.76 % of most significant SNPs from the entire set of 10,210 SNPs. The SNPs that it selected provided 95.12 % classification accuracy. Moreover, it was fast: an average of 1.60 iterations in combination with SVM to find a set of best SNPs that provided the highest classification accuracy.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Item,
    Selection of a minimal number of significant porcine snps by an information gain and genetic algorithm hybrid model
    (2019-01-01)
    Rathasamuth, Wanthanee
    ;
    Pasupa, Kitsuchart
    ;
    Tongsima, Sissades
    A panel of a large number of common Single Nucleotide Polymorphisms (SNPs) distributed across an entire porcine genome has been widely used to represent genetic variability of pigs. With the advent of SNP-array technology, a genome-wide genetic profile of a specimen can be easily observed. Among the large number of such variations, there exists a much smaller subset of the SNP panel that could equally be used to correctly identify the corresponding breed. This work presents a SNP selection heuristic that can still be used effectively in the breed classification. The features were selected by combining a filter method and a wrapper method-information gain method and genetic algorithm-plus a feature frequency selection step, while classification used a support vector machine. We were able to reduce the number of significant SNPs to 0.86 % of the total number of SNPs in a swine dataset with 94.80 % classification accuracy.