KMITL

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

Browse

Settings

Subject: search.filters.subject.Naive Bayes

Search Results

Now showing 1 - 3 of 3
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Effectiveness of Six Text Classifiers for Predicting SET Stock Price Direction
    (2020-01-01)
    Netisopakul, Ponrudee
    ;
    Saewong, Woranun
    Six text classification methods were compared to find the best model for predicting Stock Exchange of Thailand stock prices. News headlines, on individual stocks, were classified as causing “change” and “no-change” based on a preset change threshold, 2.5%. The training dataset was collected by matching stock news in 2018 with stock names and filling in stock price changes. 258 news were associated with a “change” and 636 news with “no-change”. The Thai text news items were preprocessed and converted to TF-IDF vector representation. Six machine learning text classification methods are applied to create six text classifier models and create a confusion matrix, then compared with actual changes to obtain accuracy scores. We found that a deep learning classifier (with 85.6% accuracy) scored better than other classifiers for one day price movement to assist short-term investments.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    A new ensemble model based on linear mapping, nonlinear mapping, and probability theory for classification problems
    (2015-08-24)
    Charleonnan, Anusorn
    ;
    Jaiyen, Saichon
    Currently, various perspectives of neural networks are proposed for solving classification problems. Some of them are based on two types of mapping functions, namely, linear and nonlinear, for mapping an input space into a feature space. In addition, some neural networks are proposed based on probability theory. Since some models are appropriated for some kinds of data, depending on a distribution of the data, some data are appropriated for linear mapping, some is for nonlinear mapping, and some is for probabilistic models. Due to the fact that the data distribution in classification problems are various, we propose the new ensemble model based on linear mapping, nonlinear mapping, and probability theory for classification problems. According to the experimental results, they have shown that our proposed model can improve the accuracy of classification on the testing data sets.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Edited audio detection using ensemble learning
    (2015-02-27)
    Suwan, Takdanai
    ;
    Jaiyen, Saichon
    ;
    Wiangsripanawan, Rungrat
    Detecting edited audios is the challenging problem that can help forensic scientists to separate genuine, unedited recording from edited recordings. This paper proposes the technique for detecting edited audios using Ensemble Learning. This problem can be considered as a two-class classification problem which audio data are classified into two classes including edited and unedited audios. The performance of the proposed model is compared with the performance from the Support Vector Machine, Naïve Bayes, Radial Basis Function Neural Network, and Probabilistic Neural Networks. The experimental results demonstrate that the proposed model is the most appropriated method for detecting the edited audios.