-
-
คณะวิทยาศาสตร์
With the development of space technology, wide-field sky surveys using telescopes have expanded the range of new data available for time-domain astronomical research. Traditional data analysis methods can no longer respond quickly and accurately enough to the growing volume of data. Thus, classifying time-series data, such as light curves, has become a significant challenge in the era of big data. In modern times, analyzing light curves has become essential for using machine learning techniques to handle and filter through massive amounts of data. Machine learning algorithms can be divided into two categories: shallow learning and deep learning. Numerous researchers have proposed and developed a variety of algorithms for light curve classification. In this study, we experimented with Support Vector Machine (SVM) and XGBoost, which are shallow machine learning algorithms, as well as 1D-CNN and Long Short-Term Memory (LSTM), which are deep learning algorithms, which are branches of deep machine learning, to classify variable stars. The training and testing data used in this study were from the Optical Gravitational Lensing Experiment-III (OGLE-III), consisting of variable star data from the Large Magellanic Cloud (LMC), categorized into five main classes: Classical Cepheids, δ Scutis, eclipsing binaries, RR Lyrae stars, and Long-period variables. The results demonstrate the performance analysis of each machine learning algorithm type applied to light curve data, while also highlighting the accuracy and statistical metrics of the algorithms used in the experiments.
คณะอุตสาหกรรมอาหาร
The growing interest in antioxidant-rich foods is driven by their potential to reduce the risk of chronic diseases such as cancer, cardiovascular conditions, and cellular degeneration. Ginger (Zingiber officinale), banana inflorescence (Musa paradisiaca L.), and roselle (Hibiscus sabdariffa L.) are herbal plants known for their high phenolic content, a crucial component in antioxidant activity. However, the bioactive compounds in these plants are often unstable when exposed to light, temperature, and oxygen, leading to a reduction in their efficacy. This study aims to investigate the optimal ratio of ginger, banana inflorescence, and roselle for encapsulation in liposomes—a technique designed to enhance the stability of bioactive compounds and improve their delivery efficacy. The research evaluates the antioxidant activity of the extracts using DPPH, ABTS, and FRAP methods, alongside total phenolic content (TPC) measurement. The most effective ratio for antioxidant activity will be selected for liposomal encapsulation, employing phospholipids as key structural components. The encapsulation efficiency (EE%) will be calculated to assess the effectiveness of the liposomal delivery system. The findings are expected to identify the optimal combination of ginger, banana inflorescence, and roselle that maximizes antioxidant potency and enhances the stability of bioactive compounds through liposomal encapsulation. This approach offers a promising strategy for developing herbal health supplements that maintain their biological properties over time.
คณะบริหารธุรกิจ
This research aimed to develop the mixed tea from longan peels and seeds. Population studied were longan farmers who planted longan and preserved the longan product in Ampur Wang Nam Yen, Sa Kaeo Province. From the results, it was found that from By-product in the production of dehydrated longan, longan peels and seeds, which can be processed into ready-to-drink powdered tea. This not only helps reduce waste from the production process but also contributes to generating additional income from these by-products.