Atchara Choompol

Dr. Atchara Choompol

orcid

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

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

Representative Publications

View All Publications
2 May 2024 in Journal of Current Science and Technology
Verified
Journal Article
Open access
PDF file
MSMongkol Saensuk
Mongkol Saensuk
SWSuwiwat Witchakool
Suwiwat Witchakool
ACAtchara Choompol
Atchara Choompol
Fake news has emerged as a pervasive issue within the modern information ecosystem, leading to widespread dissemination of misinformation and erosion of trust. This paper introduces a novel hybrid approach for effectively detecting fake news in the Thai language by combining the CRITIC method with multiple machine learning models. The initial step involves collecting Thai-language fake news data from websites. Subsequently, the data undergoes a preprocessing phase. In the second step, the preprocessed data is used for validation through three basic machine learning models, namely, Naive Bayes, Decision Tree, and K-Nearest Neighbors. In the third step, the accuracy results from these three models are employed to calculate the significance weights of each model using the CRITIC method. In the final step, predictions are recalculated using the proposed method. The proposed method achieves an 83.37% accuracy, surpassing Naive Bayes (80.83%), Decision Tree (80.37%), and K-Nearest Neighbors (75.75%). This indicates a significant enhancement in performance, with the proposed method outperforming the established models by up to 7.62%. Consequently, the proposed method can enhance the performance of fake news detection in Thai language by utilizing an ensemble of the original models. A significant advantage of this approach is its simplicity coupled with high efficacy. It is postulated that this method can be adapted for detecting fake news in other languages as well.

16 March 2025 in Computers
Verified
Journal Article
Open access
PDF file
ACAtchara Choompol
Atchara Choompol
SGSarayut Gonwirat
Sarayut Gonwirat
NWNarong Wichapa
Narong Wichapa
ASAnucha Sriburum
Anucha Sriburum
STSARAYUT THITAPARS
SARAYUT THITAPARS
RSRonnachai Sangmuenmao
Ronnachai Sangmuenmao
Automating fish freshness assessment is crucial for ensuring quality control and operational efficiency in large-scale fish processing. This study evaluates deep learning models for classifying the freshness of Barbonymus gonionotus (Silver Barb) and optimizing their deployment in an automated fish quality sorting system. Three lightweight deep learning architectures, MobileNetV2, MobileNetV3, and EfficientNet Lite2, were analyzed across 18 different configurations, varying model size (Small, Medium, Large) and preprocessing methods (With and Without Preprocessing). A dataset comprising 1200 images, categorized into three freshness levels, was collected from the Lam Pao Dam in Thailand. To enhance classification performance, You Only Look Once version 8 (YOLOv8) was utilized for object detection and image preprocessing. The models were evaluated based on classification accuracy, inference speed, and computational efficiency, with Technique for Order Preference by Similarity to Ideal Solution with Linear Programming (TOPSIS-LP) applied as a multi-criteria decision-making approach. The results indicated that the MobileNetV3 model with a large parameter size and preprocessing (M2-PL-P) achieved the highest closeness coefficient (CC) score, with an accuracy of 98.33% and an inference speed of 6.95 frames per second (fps). This study establishes a structured framework for integrating AI-driven fish quality assessment into fishery-based community enterprises, improving productivity and reducing reliance on manual sorting processes.

27 January 2025 in Decision Analytics Journal
Verified
Journal Article
Open access
NWNarong Wichapa
Narong Wichapa
ACAtchara Choompol
Atchara Choompol
RSRonnachai Sangmuenmao
Ronnachai Sangmuenmao

28 November 2024 in MethodsX
Verified
Journal Article
Open access
NWNarong Wichapa
Narong Wichapa
PNPariwat Nasawat
Pariwat Nasawat
NKNattapat Kanchanaruangrong
Nattapat Kanchanaruangrong
ACAtchara Choompol
Atchara Choompol
The utilization of agricultural waste for producing charcoal briquettes is gaining significant attention as a sustainable alternative energy source. Converting these residues into charcoal briquettes not only addresses energy shortages but also provides an efficient solution for managing agricultural waste, contributing to environmental sustainability. This study proposes a novel methodology integrating a Data Envelopment Analysis Variant (DEAV) with the Best-Worst Method (BWM) to assess and rank biomass materials for charcoal briquette production. The DEAV-BWM model enhances the evaluation process by considering multiple criteria simultaneously and incorporating both efficiency and consensus among different evaluation methods. The key highlights of the methodology are as follows: • A novel method, called the DEAV model, for evaluating efficiency scores has been established, incorporating both Data Envelopment Analysis (DEA) and Multi-Attribute Decision Making (MADM) concepts. • This paper introduces a novel hybrid method that combines the DEAV model with the BWM to evaluate and rank biomass materials for charcoal briquette production, enhancing the reliability and robustness of the decision-making process. • The proposed method can be adapted and applied to other areas of biomass utilization and beyond, providing a versatile tool for researchers and practitioners in the field of sustainable energy, engineering, and operations research.

28 October 2026 in Preprints.org
Verified
Preprint
Open access
PDF file
NTNoppakun Thongmual
Noppakun Thongmual
RSRonnachai Sangmuenmao
Ronnachai Sangmuenmao
ACAtchara Choompol
Atchara Choompol
NWNarong Wichapa
Narong Wichapa
Data Envelopment Analysis (DEA) offers flexible endogenous weighting but was originally developed for input–output efficiency assessment rather than complete multicriteria ranking. This study develops a Preference-Integrated Assurance-Region Multiplicative DEA (PI-AR-MDEA) framework that advances DEA toward a stand-alone multi-criteria decision-making (MCDM) method. The framework combines a unified benefit–cost multiplicative structure with alternative-specific endogenous criterion exponents constrained by Assurance Region bounds around an external preference structure. CRITIC is used to derive objective reference weights, while PI-AR-MDEA ranks alternatives directly from positive raw data through unit-invariant pairwise ratios. In the FMS benchmark, setting γ=1 reproduced the published FMDEA ranking exactly, with a maximum score deviation of 0.000069. In the empirical assessment of 20 Northeastern Thai provinces using six criteria, Nakhon Ratchasima, Khon Kaen, and Ubon Ratchathani ranked first to third under all seven compared methods, and PI-AR-MDEA showed the strongest agreement with FMDEA (ρs=0.996992). Across 36 weight-perturbation scenarios and 1,500 Monte Carlo runs, the first-ranked province and ordered top three were retained in 100% of cases. These findings indicate that PI-AR-MDEA provides a preference-constrained, adaptive, and robust extension of DEA for multicriteria ranking and strategic regional screening.

19 August 2026 in SSRN Electronic Journal
Verified
Preprint
Open access
NWNarong Wichapa
Narong Wichapa
ACAtchara Choompol
Atchara Choompol
This article presents a log-linear external-weight-restricted self-efficiency extension of multiplicative data envelopment analysis for multi-criteria decision-making problems containing both cost and benefit criteria. The method preserves the multiplicative aggregation structure of the original FMDEA model while providing a linear and computationally tractable formulation. Natural-logarithm transformation is used to reformulate the multiplicative efficiency model, and externally supplied criterion weights are incorporated through Assurance Region restrictions on multiplier ratios. This treatment controls excessive multiplier flexibility and avoids applying external weights directly to already normalized criterion data. The method produces criterion-specific optimal multipliers, log self-efficiency values, multiplicative self-efficiency scores, and final rankings of alternatives. It can be implemented using standard linear programming software and is applicable to decision-support problems in engineering, logistics, manufacturing, and related fields.• Linearizes multiplicative self-efficiency through natural logarithms.• Integrates external preferences through Assurance Region restrictions.• Supports reproducible ranking of mixed cost–benefit alternatives.