Watcharaphong Yookwan

Watcharaphong Yookwan

Auto-generated profile, based on publicly available information

Watcharaphong Yookwan

Burapha University,Faculty of Informatics,Thailand

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
15 August 2023 in IEEE Access
Verified
Journal Article
Open access
RKRatanak Khoeun
Ratanak Khoeun
WYWatcharaphong Yookwan
Watcharaphong Yookwan
PCPonlawat Chophuk
Ponlawat Chophuk
ARAnnupan Rodtook
Annupan Rodtook
KCKrisana Chinnasarn
Krisana Chinnasarn
The effectiveness of the existing approaches of facial expression recognition is significantly impacted by the necessity of wearing a facial mask during the Covid-19 outbreak. A large number of significant features on the lower face such as mouth, nose, and cheek, are completely eliminated. In this study, we propose an approach to extract features for recognizing emotions in a partial facial image that is based on Star-Like Particle Polygon Estimation (SLPPE). There are 3 primary steps in the proposed SLPPE. First, the lower part of the original facial input image is obscured by a synthetic mask. The process of representing regions is then used in the upper face image. Secondly, SLPPE is adopted as a feature extraction procedure. It is used to extract probability-based vectors of features that efficiently manifest the occluded facial image’s properties. Unlike other CNN based methods that bring the input image known as a raster form into several Conv modules in order to perform feature extraction process, we extract features from the original input image using our proposed SLPPE feature extraction technique in order to eliminate the issues of extracting unexpected features caused by the facial mask region provided by the Conv modules. Our proposed SLPPE feature extraction module produce the potential transformed data in the form of feature vectors without applying Conv modules. Finally, by utilizing LSTM and ANN networks, the SLPPE is adapted to the datasets of CK+, FER2013, and RAF-DB in order to evaluate the proposed methodology. With the accuracy of 99.01%, 98.7%, and 94.62% on CK+, FER2013, and RAF-DB, respectively, our proposed method outperforms the common CNN approaches which are currently in use and yields better results.

17 March 2025
Verified
Book Chapter
Open access
WYWatcharaphong Yookwan
Watcharaphong Yookwan
KCKrisana Chinnasarn
Krisana Chinnasarn
WVWaranrach Viriyavit
Waranrach Viriyavit
The widespread adoption of the internet has transformed communication, work, and information access, emphasizing the need for high-speed connectivity. Accurate prediction of network latency, particularly Ping, is essential for enhancing user experiences and optimizing network efficiency. This study focuses on predicting Ping latency using data from ADSL internet speed tests, incorporating variables such as geographical coordinates (longitude and latitude), subscribed package download and upload speeds, and internet provider band. The dataset is split into training and testing sets for model evaluation. Through our analysis of ADSL speed test data, we achieve a Mean Absolute Percentage Error (MAPE) of 11.98% for Ping prediction. These results provide valuable insights for stakeholders aiming to enhance the reliability and efficiency of broadband services. For network operators and service providers, our results provide a roadmap for optimizing infrastructure and refining management approaches to deliver superior service quality. Likewise, end-users stand to benefit from improved network performance, leading to smoother online interactions and heightened satisfaction.

16 November 2023
Verified
Conference Paper
Closed access
WYWatcharaphong Yookwan
Watcharaphong Yookwan
KBKamal Baha
Kamal Baha
AOAthita Onouen
Athita Onouen
SSSupawadee Srikamdee
Supawadee Srikamdee
KCKrisana Chinnasrn
Krisana Chinnasrn
Fundus image registration plays a crucial role in ophthalmology for various diagnostic and treatment purposes. In this research paper, we propose a novel approach for fundus image registration using extremal regions of extremum levels. This method aims to improve the accuracy and robustness of fundus image registration, particularly in cases with significant anatomical variations or pathologies. We present the theoretical foundations, methodology, experimental results, and clinical implications of this approach, highlighting its potential to enhance the quality of ophthalmic diagnosis and treatment planning.

11 October 2023
Verified
Conference Paper
Closed access
WYWatcharaphong Yookwan
Watcharaphong Yookwan
JSJiranun Sangrueng
Jiranun Sangrueng
JOJanya Onpans
Janya Onpans
SSSupawadee Srikamdee
Supawadee Srikamdee
KCKrisana Chinnasarn
Krisana Chinnasarn
This paper introduces a novel method for intravascular ultrasound (IVUS) image registration based on geometric spatial energy. By combining geometric vessel features with spatial energy computations, the proposed approach achieves accurate image alignment, even in the presence of vessel deformations. Key geometric features serve as reference points, guiding the optimization process to minimize spatial energy and achieve optimal image correspondence. Extensive experiments on diverse IVUS image pairs demonstrate the method's superior performance over traditional techniques, promising enhanced clinical applications in vessel analysis and treatment planning. The performance of the proposed method are 10.33 of MSE, 10.55 of HD, and 0.15 of TRE, respectively.