Chantana Chantrapornchai

Dr. Chantana Chantrapornchai


Research Focus & Metrics

Academic Career Length

25Years (2002-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
3 July 2021 in Water
Verified
Journal Article
Open access
PDF file
LKLattawit Kulanuwat
Lattawit Kulanuwat
CCChantana Chantrapornchai
Chantana Chantrapornchai
MMMontri Maleewong
Montri Maleewong
PWPapis Wongchaisuwat
Papis Wongchaisuwat
SWSupaluk Wimala
Supaluk Wimala
SBSurajate Boonya-Aroonnet
Surajate Boonya-Aroonnet
Water level data obtained from telemetry stations typically contains large number of outliers. Anomaly detection and a data imputation are necessary steps in a data monitoring system. Anomaly data can be detected if its values lie outside of a normal pattern distribution. We developed a median-based statistical outlier detection approach using a sliding window technique. In order to fill anomalies, various interpolation techniques were considered. Our proposed framework exhibited promising results after evaluating with F1-score and root mean square error (RMSE) based on our artificially induced data points. The present system can also be easily applied to various patterns of hydrological time series with diverse choices of internal methods and fine-tuned parameters. Specifically, the Spline interpolation method yielded a superior performance on non-cyclical data while the long short-term memory (LSTM) outperformed other interpolation methods on a distinct tidal data pattern.

20 December 2016 in SpringerPlus
Verified
Journal Article
Open access
PDF file
CCChantana Chantrapornchai
Chantana Chantrapornchai
CCChidchanok Choksuchat
Chidchanok Choksuchat
Ontology is one of the key components in semantic webs. It contains the core knowledge for an effective search. However, building ontology requires the carefully-collected knowledge which is very domain-sensitive. In this work, we present the practice of ontology construction for a case study of health tourism in Thailand. The whole process follows the METHONTOLOGY approach, which consists of phases: information gathering, corpus study, ontology engineering, evaluation, publishing, and the application construction. Different sources of data such as structure web documents like HTML and other documents are acquired in the information gathering process. The tourism corpora from various tourism texts and standards are explored. The ontology is evaluated in two aspects: automatic reasoning using Pellet, and RacerPro, and the questionnaires, used to evaluate by experts of the domains: tourism domain experts and ontology experts. The ontology usability is demonstrated via the semantic web application and via example axioms. The developed ontology is actually the first health tourism ontology in Thailand with the published application.

26 December 2022 in IEEE Transactions on Biomedical Engineering
Verified
Journal Article
Closed access
ACAmrest Chinkamol
Amrest Chinkamol
VKVetit Kanjaras
Vetit Kanjaras
PSPhattarapong Sawangjai
Phattarapong Sawangjai
Yifan ZhaoYifan Zhao
Yifan Zhao
TSThapanun Sudhawiyangkul
Thapanun Sudhawiyangkul
TWTheerawit Wilaiprasitporn
Theerawit Wilaiprasitporn
Objective: While the microvasculature annotation within Optical Coherence Tomography Angiography (OCTA) can be leveraged using deep-learning techniques, expensive annotation processes are required to create sufficient training data. One way to avoid the expensive annotation is to use a type of weak annotation in which only the center of the vessel is annotated. However, retaining the final segmentation quality with roughly annotated data remains a challenge. Methods: Our proposed methods, called OCTAve, provide a new way of using weak-annotation for microvasculature segmentation. Since the centerline labels are similar to scribble annotations, we attempted to solve this problem by using the scribble-based weakly-supervised learning method. Even though the initial results look promising, we found that the method could be significantly improved by adding our novel self-supervised deep supervision method based on Kullback-Liebler divergence. Results: The study on large public datasets with different annotation styles (i.e., ROSE, OCTA-500) demonstrates that our proposed method gives better quantitative and qualitative results than the baseline methods and a naive approach, with a p-value less than 0.001 on dice's coefficient and a lot fewer artifacts. Conclusion: The segmentation results are both qualitatively and quantitatively superior to baseline weakly-supervised methods when using scribble-based weakly-supervised learning augmented with self-supervised deep supervision, with an average drop in segmentation performance of less than 10%. Significance: This work gives a new perspective on how weakly-supervised learning can be used to reduce the cost of annotating microvasculature, which can make the annotating process easier and reduce the amount of work for domain experts.

16 September 2021 in Journal of Big Data
Verified
Journal Article
Open access
PDF file
PMPisit Makpaisit
Pisit Makpaisit
CCChantana Chantrapornchai
Chantana Chantrapornchai
Resource Description Framework (RDF) is commonly used as a standard for data interchange on the web. The collection of RDF data sets can form a large graph which consumes time to query. It is known that modern Graphic Processing Units (GPUs) can be employed to execute parallel programs in order to speedup the running time. In this paper, we propose a novel RDF data representation along with the query processing algorithm that is suitable for GPU processing. Since the main challenges of GPU architecture are the limited memory sizes, the memory transfer latency, and the vast number of GPU cores. Our system is designed to strengthen the use of GPU cores and reduce the effect of memory transfer. We propose a representation consists of indices and column-based RDF ID data that can reduce the GPU memory requirement. The indexing and pre-upload filtering techniques are then applied to reduce the data transfer between the host and GPU memory. We add the index swapping process to facilitate the sorting and joining data process based on the given variable and add the pre-upload step to reduce the size of results’ storage, and the data transfer time. The experimental results show that our representation is about 35% smaller than the traditional NT format and 40% less compared to that of gStore. The query processing time can be speedup ranging from 1.95 to 397.03 when compared with RDF3X and gStore processing time with WatDiv test suite. It achieves speedup 578.57 and 62.97 for LUBM benchmark when compared to RDF-3X and gStore. The analysis shows the query cases which can gain benefits from our approach.

30 June 2023 in Scientific Reports
Verified
Journal Article
Open access
PDF file
CCChantana Chantrapornchai
Chantana Chantrapornchai
SKSupasit Kajkamhaeng
Supasit Kajkamhaeng
PRPhattharaphon Romphet
Phattharaphon Romphet
Convolutional Neural Network (CNN) models have been commonly used primarily in image recognition tasks in the deep learning area. Finding the right architecture needs a lot of hand-tune experiments which are time-consuming. In this paper, we exploit an AutoML framework that adds to the exploration of the micro-architecture block and the multi-input option. The proposed adaption has been applied to SqueezeNet with SE blocks combined with the residual block combinations. The experiments assume three search strategies: Random, Hyperband, and Bayesian algorithms. Such combinations can lead to solutions with superior accuracy while the model size can be monitored. We demonstrate the application of the approach against benchmarks: CIFAR-10 and Tsinghua Facial Expression datasets. The searches allow the designer to find the architectures with better accuracy than the traditional architectures without hand-tune efforts. For example, CIFAR-10, leads to the SqueezeNet architecture using only 4 fire modules with 59% accuracy. When exploring SE block insertion, the model with good insertion points can lead to an accuracy of 78% while the traditional SqueezeNet can achieve an accuracy of around 50%. For other tasks, such as facial expression recognition, the proposed approach can lead up to an accuracy of 71% with the proper insertion of SE blocks, the appropriate number of fire modules, and adequate input merging, while the traditional model can achieve the accuracy under 20%.

17 April 2024 in Energy Informatics
Verified
Journal Article
Open access
PDF file
WCWithit Chatlatanagulchai
Withit Chatlatanagulchai
CCChantana Chantrapornchai
Chantana Chantrapornchai
Objective: Energy usage in has been increased due to the rising demand of cloud infrastructure. The government policy has been focused on building the green IT data center. The energy data need to be collected in order to monitor the energy usage. However, in an old typical data center, the building has been built with no support of such data collection. In this research, we aim to design the energy data collection system for our existing data center, a case study of data center in Thailand at the university. Based on the collected data, an energy usage monitoring system and prediction can be developed. Methods: In the case study of Kasetsart University data center, the building and electric layouts were predetermined. The building layout and existing IT hardware were investigated. We designed the meter types and the number of meters to be installed for the building the energy data collection system. The corresponding database system was also designed for data logging, data visualization and analysis purpose. Results: As a result, 25 installed meters along with the add-on network system were installed for logging data. A data usage example was demonstrated by building the data visualization and analysis. The presented 1 year dataset collected showed the changes of energy usages which can be used to compare with real activities happening in the campus. This encourages the integration of other related environment data such as outside temperature which may affect the electric billing cost. The dataset can be used for prediction of the electric usage; thus, the policy for reducing the electric billing cost could be established. In this paper, as a data note, we focus on the methodology of data collection required for data center.