International Journal of Science and Innovative Technology

research Article Innovative E-learning of The Folk Handmade Culture of Ratchaburi Province

Piyanart Boonmepipit — Wed, 16 Apr 2025 00:00:00 +0700

The objectives of this research were 1) to decode the experience of the traditional handicraft culture 2) to develop learning innovation sets from the traditional handicraft cultural of Ratchaburi province.The target the research:1) an interview group, this included three groups focused on Ratchaburi's traditional handicraft local intellectuals, specifically those who worked in brickworks, Bankhubua Jok woven fabric, and brass bell. This group were selected purposefully using a snowball sampling technique, with at least two individuals from each group 2) an experimental group consisted of 30 Mathayom 3 students drawn by simple random sampling.The research instruments were an unstructured interview form and the traditional handcraft learning innovation. The data were analyzed by mean, standard deviation, E₁/E₂.

The research results were 1) The decoding experience (tacit knowledge) of the traditional handicraft cultural products through knowledge management process included Ratchaburi Mon brickworks, Bankhubua Jok woven fabric, brass bells of Bankhaoloymoonkho; 2)The set of learning innovations from traditional handicraft culture consisted of 3 sets of innovation. The E-Books had a validity score (IOC) of 1.00 and reliability scores of E₁ = 80.06 / E₂ = 85.56. The local curriculum for the cultural handicrafts of Ratchaburi also had a validity score (IOC) of 1.00, with reliability assessed by five experts, who evaluated its accuracy, appropriateness, feasibility, and potential for practical application, resulting in a score of 100%. This indicates that it is a high-quality curriculum that could be effectively used for teaching; 3) The results from focus group discussions with seven local intellectuals indicated that these sets of innovative learning materials were well-aligned with the principles of Ratchaburi's local culture and accurately reflected the region's traditional heritage. They believe it deserved to be preserved and shared with the younger generation to ensure that this cultural heritage remained alive in society and continued to endure.

Automated Defect Classification of Coffee Beans Using Deep-Stacking Ensemble Learning

Fri, 04 Apr 2025 00:00:00 +0700

Quality control in coffee production is essential for maintaining product standards and preserving market value. A key practice in this process is to identify and remove defective beans which ensures high-quality standards and enhances consumer experience. However, traditional methods of classifying coffee bean defect often rely on manual inspection which is labour-intensive, time-consuming and subject to human errors. As such, adopting image classification for coffee bean defects could improve accuracy and boosts operational efficiency. This study explores the effectiveness of stacking-based deep learning ensemble method for coffee bean defect classification. The methodology involves a performance study as a baseline approach from fourteen traditional machine learning algorithms, including Support Vector Machines (SVM) and Random Forest (RF), along with ten different feature extraction techniques, such as FOS and GLDS. Besides, twenty well-known deep learning architectures including ResNet50, ConvNeXt and EfficientNet were compared to fourteen lightweight models such as TinyNet and MobileNet. Additionally, the performance of stacking-based deep learning models is also analysed to optimise coffee bean defect classification. The results indicate that ConvNeXt achieved the highest testing accuracy at 72.94% across all DL architectures. Additionally, the stacking approach significantly improves classification performance as it achieved an accuracy improvement from 72.94% to 87.64%. This study contributes to a comprehensive benchmarking to evaluate a diverse range of machine learning and deep learning algorithms. It also highlights the effectiveness of the stacking ensemble model to enhance accuracy in coffee bean defect classification.

Value Co-Creation Strategy Model to Enhance the Environment and Bicycle Health on Tourism Area of Khung Bangkachao

Fri, 04 Apr 2025 00:00:00 +0700

This research aims to determine strategies for creating shared values affecting the engagement of cyclists in Kung Bang Krachao, Phra Pradaeng District, Samut Prakan Province. The research method used includes a combination of quantitative and qualitative research. The sample group consists of 384 cyclists and 3 groups of key informants, including 1) 5 bicycle rental operators, 2) 5 people of area administrators, community leaders, and tour guides, and 3) 7 tourism entrepreneurs, totaling 17 people. The quantitative research results indicated that the mean satisfaction value on the cycling route was 4.25 (S.D. = 0.62), reflecting a high level of satisfaction. The analysis of model consistency using the Goodness of Fit Index (GFI) of 0.988 and the root mean square error of approximation (RMSEA) of 0.027 indicated that the model is clearly consistent with the empirical data. The building of shared value by bicycle rental business entrepreneurs, area administrators, community leaders, tour guides, and tourism service operators all influence the satisfaction and engagement of tourists cycling in Bang Krachao. The most influential factor is the administration of areas and facilities, especially safe cycling routes, which has a standardized factor loading (β) of 0.891 and a predictive coefficient (R²) of 0.795 Community participation in tourism activities, such as organizing local markets and servicing tour guides, has a direct influence (DE) of 0.635 and a total influence (TE) of 0.906. The analysis of the relationship between service quality and overall satisfaction revealed that the correlation coefficient (r) was 0.812, reflecting the impact of good management, such as increasing the number of clean toilets and improving the rest areas. Tourists provided an average satisfaction score of 4.25 (S.D. = 0.62), which is in the high range. Organizing activities linked to community lifestyles, such as cultural tours, tree planting, and environmental conservation activities, has an indirect influence (IE) of 0.575 and a construct reliability of 0.875. The participation of knowledgeable and interesting storytelling tour guides helped create memorable experiences and promote word-of-mouth recommendations, which has a score of standardized factor loading of 0.889 (R² = 0.791).