Phaisarn Sutheebanjard

Learn More
Block-based connected components labeling is by far the fastest algorithm to label the connected components in 2D binary images, especially when the image size is quite large. This algorithm produces a decision tree that contains 211 leaf nodes with 14 levels for the depth of a tree and an average depth of 1.5923. This article attempts to provide a faster(More)
Named Entity (NE) extraction for Thai language is a difficult and time consuming task because sentences in Thai language are composed of a series of words formed by a stream of characters. Moreover, there are no delimiters (blank space) to show word boundaries. Currently, most named entity extraction methods for Thai language are associated with word(More)
In this paper, we investigate predicting the Stock Exchange of Thailand Index movement. Currently, there are two stock markets in Thailand; the Stock Exchange of Thailand (SET) and the Market for Alternative Investment (MAI). This paper focuses on the movement of the Stock Exchange of Thailand Index (SET Index). The back propagation neural network (BPNN)(More)
To achieve the best results from an OCR system, the pre-processing steps must be performed with a high degree of accuracy and reliability. There are two critically important steps in the OCR pre-processing phase. First, blocks must be extracted from each page of the scanned document. Secondly, all blocks resulting from the first step must be arranged in the(More)
The principles of decision-analytic decision support, implemented in GeNIe (Graphical Network Interface) and SMILE (Structural Modeling, Inference, and Learning Engine) can be applied in practical decision support systems (DSSs). GeNIe plays the role of a developer's environment and SMILE plays the role of the reasoning engine. A decision support system(More)
Since online news articles are updated daily, hourly and sometimes every minute, therefore the data from online news articles are glowing rapidly. These data seem like a large corpus of text mining. This research focuses on Thai personal names that appear in the online news which sometimes have slightly different spelling but they actually refer to the same(More)
This paper analyzed the time period and amount of training data that were used in applying the prediction function to forecast the Stock Exchange of Thailand index (SET Index). The training data were grouped into one year and two years over the period of 2003–2008, and the testing data were collected from January 2005 to March 2009. This paper(More)
This paper proposes a new prediction function for the Stock Exchange of Thailand (SET index). Included in the proposed prediction function are the important economic factors: namely, the Dow Jones, Nikkei, and Hang Seng indexes; the minimum loan rate (MLR); and the previous SET index. The tuning coefficients of each factor in this research were calculated(More)
3-D connected components labeling is the fundamental technique in Magnetic Resonance Imaging (MRI). This research presents the decision tree for 3-D connected components labeling operation (26-connectivity) in 3-D binary images. This method will be used at the first round of the two-scan connected components labeling process. The distinctive characteristic(More)
  • 1