Now showing items 1-10 of 10

  • Thumbnail

    A combination of graph ranking and term collocation information for image annotation 

    Krittapad Suriya; Ohm Sornil (National Institute of Development Administration, 2006)

    In a large image database, an automatic image annotation plays an important role to assign a caption to an image. There are many applications of image annotation which include information extraction, knowledge acquisition, finding answers from specific questions, etc. In this research, we propose an image annotation approach using a graph ranking algorithm on a novel structure which includes similarities among regions within images and caption term collocation information. Caption terms are selected using a graph random walk method biased ...
  • Thumbnail

    A filter-based feature selection using two criterion functions and evolutionary fuzzification 

    Jitwadee Chaiyakarn; Ohm Sornil (National Institute of Development Administration, 2013)

    In information age, data has become increasingly large, in both dimension (the number of features) and volume. Data mining processes, such as data classification and data clustering, performed on high dimensional data can be time-consuming and can produce poor results due to the problem so called curse of dimensionality. Feature selection is one of the fundamental techniques that selects only the most significant features and eliminates irrelevant and redundant features from the entire set of features. Filter-based feature selection is the ...
  • Thumbnail

    A PAIRING-FREE IDENTITY-BASED CRYPTOSYSTEM 

    Poonsuk Ponpurmpoon; Poonsuk Ponpurmpoon; Ohm Sornil; โอม ศรนิล; Ohm Sornil; โอม ศรนิล (National Institute of Development Administration, 7/1/2022)

    ID-based cryptosystems (IBCs) allow the use of publicly identifiable information in public encryption keys, which reduces the overhead of certificate management and eliminates the need for a certificate authority in the public-key infrastructure. Up to now, bilinear pairing technology is usually used in ID-based paradigms. However, it is expensive in computation time and is unsuitable for mobile networks. Over recent years, the evolution of mobile devices has seen them transformed from a voice communication device to a daily life information ...
  • Thumbnail

    Abstractive Thai opinion summarization 

    Orawan Chaowalit; Ohm Sornil (National Institute of Development Administration, 2013)

    With the advancement of the Internet technology, customers can easily share opinions about services and products in forms of reviews. There can be large amount of reviews for popular products. Manually summarizing those reviews for important issues is a daunting task. Automatic opinion summarization is a solution to the problem. The task is more complicated for reviews written in Thai. Thai words are written continuously without space, and there is no symbol to identify the end of a sentence. Many reviews are written informally, thus accurate ...
  • Thumbnail

    An adaptive multi-level sequential floating feature selection 

    Knitchepon Chotchantarakun; Ohm Sornil (National Institute of Development Administration, 2020)

    Dealing with a large amount of available data becomes a major challenge in data mining and machine learning. Feature selection is a significant preprocessing step for selecting the most informative features by removing irrelevant and redundant features, especially for large datasets. These selected features play an important role in information searching and enhancing the performance of machine learning models such as classification and prediction. There have been several strategies proposed in the past few decades. In this dissertation, we ...
  • Thumbnail

    Collaborative resource discovery in mobile peer-to-peer networks 

    Ajay Arunachalam; Ohm Sornil (National Institute of Development Administration, 2015)

    Resource discovery is the process to find the queried object also referred as resource searching. With the rapid development of mobile hardware and wireless internet access, it became feasible to use mobile devices in P2P network. Deploying unstructured Peer-to-Peer (P2P) applications over Mobile Ad-hoc Network (MANET) has seen a decade effort, but still has many limitations and challenges. Searching in such resultant networks are not efficient and further ineffective mainly due to mobility, peer discovery and connectivity issues. Typical resource ...
  • Thumbnail

    Feature selection using genetic algorithm 

    Kanyanut Homsapaya; Ohm Sornil (National Institute of Development Administration, 2017)

    In this dissertation, a method of feature selection in machine learning, and more particularly supervised learning is presented. Supervised learning is a machine learning task that infers answers from a training data set. In machine learning, training datasets are employed in order to create a model which enables reasonable predictions, while in supervised learning, each training example is a training set consisting of instances and labels, and the learning objective is to be able to predict the label of a new unseen instance with as few ...
  • Thumbnail

    Thai soundex using Thai phonetic distance algorithm 

    Chonlasith Jucksriporn; Ohm Sornil (National Institute of Development Administration, 2014)

    Homophones are words with similar sound. Searching for homophones is not only looking for the words with similar spelling, but it should also be looking for the words with similar pronunciation. Specifically in Thai, some consonant clusters can be pronounced in different ways, such as // can be pronounced as // or // depending on cach particular word. This makes Thoi word pronunciation and dictation more dilliculi Thai sounder could not handle these consonant clusters properly: for example, many Thai soundex methods showed cncoded results of a ...
  • Thumbnail

    Using conceptual space and cultural evolution in language game 

    Theerapol Limsatta; Ohm Sornil (National Institute of Development Administration, 2016)

    Agreement on word-object pairing in communication depends on the intensity of belief that gradually emerges in a society of agents under the condition that no one is born with embedded knowledge. In know-nothing word-object pairing, the agents in communication find meaning until they reach a consensus on what an object should be called. A language game is a social process of finding agreement on word-object pairing which enables its communication in a multi-agent system. In this research, techniques are proposed to discover the association ...
  • Thumbnail

    WORD SEGMENTATION AND PART-OF-SPEECH TAGGING FOR THAI LANGUAGE USING MINIMUM TEXT AND CONDITIONAL RANDOM FIELD 

    Kannikar Paripremkul; Kannikar Paripremkul; Ohm Sornil; โอม ศรนิล; Ohm Sornil; โอม ศรนิล (National Institute of Development Administration, 13/8/2021)

    Thai word segmentation and Part-of-Speech (POS) tagging is still a very active research area. However, previous studies mostly focus on rule-based models or generative models such as the Hidden Markov Model (HMM), which may not suitable for segmenting an unknown word. In this research, we present a novel technique to deal with the problem of word segmentation for a language without explicit word boundary delimiters, like Thai, Chinese, or Korean. This research proposes a machine learning model called the Conditional Random Field (CRF) to segment ...