Intakosum, Sarun

Preferred name

Intakosum, Sarun

Main Affiliation

School of Science

sarun.in@kmitl.ac.th

Now showing 1 - 10 of 25

Some of the metrics are blocked by your
consent settings
XER: A recommendation for XML element
(2010-08-11)
Vacharaskunee, Sutheetutt
;
Intakosum, Sarun
The strong point of the XML is that it allows document owners to describe their documents in their own format (structure and element names). There might be the same information has been describe in various ways. When user wants to search some information from XML documents, user might not retrieve all related results because of the difference of elements (tag names). To retrieve all related results, user needs to have queries for all possible elements. XML Element Recommendation (XER) is an idea to make XML documents easier for searching. It receives XML document as an input and compares that input with XML documents from database. It compares word similarity and semantic of each element. For semantic similarity of each element, it checks those elements to find which element (word) should be used by using word ranking (most common words). The output is a recommendation for each element of input XML document. © 2010 IEEE.
Some of the metrics are blocked by your
consent settings
Automated Data Digitization System for Vehicle Registration Certificates Using Google Cloud Vision API
(2022-07-01)
Thammarak, Karanrat
;
Sirisathitkul, Yaowarat
;
Kongkla, Prateep
;
Intakosum, Sarun
This study aims to develop an automated data digitization system for the Thai vehicle registration certificate. It is the first system developed as a web service Application Programming Interface (API), which is essential for any enterprise to increase its business value. Currently, this system is available on “www.carjaidee.com”. The system involves four steps: 1) an embedded frame aligns a document to be correctly recognised in the image acquisition step; 2) sharpening and brightness filtering techniques to enhance image quality are applied in the pre-processing step; 3) the Google Cloud Vision API receives a prompt to proceed in the recognition step; 4) a specific domain dictionary to improve accuracy rate is developed for the post-processing step. This study defines 92 images for the experiment by counting the correct words and terms from the output. The findings suggest that the proposed method, which had an average accuracy of 93.28%, was significantly more accurate than the original method using only the Google Cloud Vision API. However, the system is limited because the dictionaries cannot automatically recognise a new word. In the future, we will explore solutions to this problem using natural language processing techniques.
Some of the metrics are blocked by your
consent settings
An efficient parallel construction of optimal independent spanning trees on hypercubes
(2012-12-01)
Werapun, Jeeraporn
;
Intakosum, Sarun
;
Boonjing, Veera
Reliable data broadcasting on parallel computers can be achieved by applying more than one independent spanning tree (IST). Using k-IST-based broadcasting from root r on an interconnection network (N=2 k) provides k-degree fault tolerance in broadcasting, while construction of optimal height k-ISTs needs more time than that of one IST. In the past, most research focused on constructing k ISTs on the hypercube Qk, an efficient communication network. One sequential approach utilized the recursive feature of Qk to construct k ISTs working on a specific root (r)=0 in O(kN) time. Another parallel approach was introduced for generating k ISTs with optimal height on Qk, based on HDLS (Hamming Distance Latin Square), single pointer jumping, which is applied for a source (r)=0 in O( k2) time for successful broadcasting in O(k). For broadcasting from r≠0, those existing approaches require a special routine to reassign new nodes' IDs for logical r=0. This paper proposes a flexible and efficient parallel construction of k ISTs with optimal height on Qk, a generalized approach, for an arbitrary root (r=0,1,2,..., or 2 k-1) in O(k) time. Our focus is to introduce the more efficient time (O(k)) of preprocessing, based on double pointer jumping over O( k2) of the HDLS approach. We also prove that our generalized parallel k-IST construction (arbitrary r) with optimal height on Qk is correctly set in efficient O(k) time. Finally, experiments were performed by simulation to investigate the fault-tolerance effect in reliable broadcasting. Experimental results showed that our efficient ISTs yielded 10%-20% fault tolerance for successful broadcasting (on N=16-1024 PEs). © 2012 Elsevier Inc. All rights reserved.
Some of the metrics are blocked by your
consent settings
Adaptation of design pattern retrieval using CBR and FCA
(2009-12-01)
Muangon, Weenawadee
;
Intakosum, Sarun
Software developers currently find design patterns through search tools for solving software design problem. However, these search tools still have keywordsearch problem. In this paper, we introduce the elementary idea to improve the design pattern retrieval tool. We propose the combination of Case Based Reasoning (CBR) and Formal Concept Analysis (FCA). Because of CBR lead to the smart solution and FCA provides flexible way to maintain indexing in the case base. © 2009 IEEE.
Some of the metrics are blocked by your
consent settings
Unleashing Hidden Business Insights: Harnessing Unstructured Big Data through Text Analysis, NLP, and Visualizations for Budgetary Decisions in Governmental Organizations
(2024-01-01)
Kongthong, Chanwit
;
Jitkajornwanich, Kulsawasd
;
Intakosum, Sarun
Processing Thai language texts can be a challenge due to the complexities of the language, particularly texts from social media and online platforms. This paper introduces an analysis and visualization framework specifically designed to tackle the intricacies associated with processing the Thai language data within the context of online textual content, by utilizing natural language processing (NLP) and visualization techniques. The objectives of this study were to develop an effective Thai text data analysis and visualization framework that allows us to effectively and automatically get a better understanding of the content embedded in Thai textual data. The methodology initiated with a review of existing analysis frameworks and visualization techniques with a specific focus on Thai. The data collection phase encompassed a diverse corpus of Thai text data gathered from online sources. The selected data underwent preprocessing to address language-specific challenges. The proposed Thai analysis and visualization framework consists of multiple stages. Each stage is tailored to accommodate the intricacies of the Thai language, facilitating improved information extraction and text comprehension. The proposed visualization techniques utilize interactive graphs, such as bar charts, line charts, pie charts and donut charts, to offer intuitive and insightful representations of the processed data. Results from our case study show the effectiveness of our Thai analysis framework and visualization techniques in capturing crucial information from online contents written in Thai from governmental organizations.
Some of the metrics are blocked by your
consent settings
From use cases to framelets for building application frameworks
(2008-05-27)
Intakosum, Sarun
Framework-based software development has been proven a useful technique to develop an application. However, the development of a large application framework itself is considered complex. There are two major causes for this problem, the size of a framework and the vague framework requirements. The idea of framelet a small but complete framework, can be applied to solve the former. The Framelet-based Approach for Framework Development (FAFD) has been proposed to address the later. There are some improvements in term of use case requirements description to the approach after it was first presented. This paper aims to report such improvements as well as the ongoing researches on the FAFD. © 2008 IEEE.
Some of the metrics are blocked by your
consent settings
Comparative analysis of Tesseract and Google Cloud Vision for Thai vehicle registration certificate
(2022-04-01)
Thammarak, Karanrat
;
Kongkla, Prateep
;
Sirisathitkul, Yaowarat
;
Intakosum, Sarun
Optical character recognition (OCR) is a technology to digitize a paper-based document to digital form. This research studies the extraction of the characters from a Thai vehicle registration certificate via a Google Cloud Vision API and a Tesseract OCR. The recognition performance of both OCR APIs is also examined. The 84 color image files comprised three image sizes/resolutions and five image characteristics. For suitable image type comparison, the greyscale and binary image are converted from color images. Furthermore, the three pre-processing techniques, sharpening, contrast adjustment, and brightness adjustment, are also applied to enhance the quality of image before applying the two OCR APIs. The recognition performance was evaluated in terms of accuracy and readability. The results showed that the Google Cloud Vision API works well for the Thai vehicle registration certificate with an accuracy of 84.43%, whereas the Tesseract OCR showed an accuracy of 47.02%. The highest accuracy came from the color image with 1024×768 px, 300dpi, and using sharpening and brightness adjustment as pre-processing techniques. In terms of readability, the Google Cloud Vision API has more readability than the Tesseract. The proposed conditions facilitate the possibility of the implementation for Thai vehicle registration certificate recognition system.
Some of the metrics are blocked by your
consent settings
Improvement Classification Approach in Tomato Leaf Disease using Modified Visual Geometry Group (VGG)-InceptionV3
(2022-01-01)
Thomkaew, Jiraporn
;
Intakosum, Sarun
This paper presents a new method for optimizing tomato leaf disease classification using Modified Visual Geometry Group (VGG)-InceptionV3. Improved performance of VGG-16 model as a base model with InceptionV3 block reduced the number of convolution layers of VGG-16 from 16 to 10 layers, and added an InceptionV3 block that was improved by adding convolution layer from 3 to 4 layers to increase the accuracy of tomato leaf disease classification and reduce the number of parameters and computation time of the model. The experiments were performed on tomato leaves from the PlantVillage dataset of 10 classes, consisting of nine classes of diseased leaves and one class of healthy leaves. The results showed that the proposed method was able to reduce the number of parameters and computation time with and accuracy of tomato leaf disease classification was 99.27%. Additionally, the proposed approach was compared with state-of-the-art Convolutional Neural Network (CNN) models such as VGG16, InceptionV3, DenseNet121, MobileNetV2, and RestNet50. Comparative results showed that the proposed method had the highest accuracy in the tomato leaf disease classification and required a smaller number of parameters and computational time
Some of the metrics are blocked by your
consent settings
Borderline over-sampling in feature space for learning algorithms in imbalanced data environments
(2016-01-01)
Savetratanakaree, Kittipat
;
Sookhanaphibarn, Kingkarn
;
Intakosum, Sarun
;
Thawonmas, Ruck
In this paper, we propose a new approach to over-sample new minority-class instances along the borderline using the Euclidean distance in the feature space to improve support vector machine (SVM) performance in imbalanced data environments. SVM has been an outstandingly successful classifier in a wide variety of applications where balanced class data distribution is assumed. However, SVM is ineffective when coping with imbalanced datasets whereby the majorityclass instances far outnumber the minority-class instances. Our new approach, called Borderline Over-sampling in the Feature Space, can deal with imbalanced data to effectively recognize new minority-class instances for better classification with SVM. The results of our class prediction experiments using the proposed approach demonstrate better performance than the existing SMOTE, Borderline-SMOTE and borderline over-sampling methods in terms of the g-mean and F-measure.
Some of the metrics are blocked by your
consent settings
XML element recommendation by semantic ranking
(2010-05-28)
Vacharaskunee, Sutheetutt
;
Intakosum, Sarun
From the strong point of XML that allows document owners to describe their documents in their own format, it is difficult to search information if those XML documents use different formats. Moreover, users might not retrieve all relevant information from differently formatted XML documents. To allow users to retrieve all relevant results, users need to have as many as queries for all possible formats. SXER (Semantic Ranking for XML Element Recommendation) is an idea to make XML documents easier for searching. It receives XML document as an input, checks all possible semantics for each element, and checks those semantic elements to find which element (word) should be used. The output is a recommendation for each element of input XML document. ©2010 IEEE.

Intakosum, Sarun

Filters

Settings

Sort By

Results per page