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.
ในงานนี้เราได้เสนอการใช้อัลกอริทึมการเรียนรู้ของเครื่องที่ทำการแบ่งอัลกอริทึมได้เป็น 2 ประเภท คือ แบบตื้นและแบบลึกมาทดสอบประสิทธิภาพโดยแบบตื้นมีมีอัลกอริทึม Support Vector Machine (SVM) และ XGBoost แบบลึกมีอัลกอริทึม 1D-CNN และ Long Short-Term Memory (LSTM) เราพิจารณาข้อมูลการสังเกตที่ได้จากฐานข้อมูล Optical Gravitational Lensing Experiment-III (OGLE-III) ที่เป็นดาวแปรแสงในพื้นที่ Large Magellanic Cloud (LMC) ด้วยกล้องโทรทรรศน์ขนาด 1.3-m Warsaw ที่ติดตั้งที่หอดูดาวลาสคัมปานัส ประเทศชิลี ข้อมูลนี้ประกอบด้วยการสังเกตดาวแปรแสงมากกว่าหนึ่งแสนครั้งโดยพิจารณาจากกราฟแสง และใช้ข้อมูลสถิติต่างๆ เช่น Accuracy, Precision, Recall, F1-score, AUG, mPa, mcc และ kappa ซึ่งงานวิจัยนี้มีจุดมุ่งหมายเพื่อที่จะทดสอบประสิทธิภาพในการจำแนกประเภทของดาวแปรแสงโดยใช้ข้อมูลการวิเคราะห์ light curve ด้วยเทคนิคการเรียนรู้ของเครื่องทั้งสองประเภท เพื่อให้เห็นถึงความเข้าใจในลักษณะและพฤติกรรมของดาวแปรแสง ซึ่งใช้ในประโยชน์ต่างๆ เช่น ความรู้ในด้านดาราศาสตร์ฟิสิกส์หรือการค้นพบดาวเคราะห์ดวงใหม่ๆ และการป้องกันภัยจากดาวแปรแสงมีอาจจะมีผลกระทบต่อโลก อีกทั้งในเรื่องการประหยัดเวลาและทรัพยากรในการที่จะจำแนกประเภทดาวแปรแสงอย่างมีระบบและมีประสิทธิภาพ
คณะสถาปัตยกรรม ศิลปะและการออกแบบ
-
คณะวิศวกรรมศาสตร์
Motor control is a critical process for muscle contraction, which is initiated by nerve impulses governed by the motor cortex. This process is vital for performing activities of daily living (ADLs). Consequently, a disruption in communication between the brain and muscles, as seen in various chronic conditions and diseases, can impair bodily movement and ADLs. Evaluating the interaction between brain function and motor control is significant for the diagnosis and treatment of motor control disorders; moreover, it can contribute to the development of brain-computer interfaces (BCIs). The purpose of this study is to investigate brain activation in designed upper extremity motor control tasks in regulating the pushing force in different brain regions; and develop investigation methods to assess motor control tasks and brain activation using a robotic arm to guide upper extremity force and motor control. Eighteen healthy young adults were asked to perform upper extremity motor control tasks and recorded the hemodynamic signals. Functional Near-Infrared Spectroscopy (fNIRs) and robotic arms were used to assess brain activation and the regulation of pushing force and extremity motor control. Two types of motion, static and dynamic, move along a designated trajectory in both forward and backward directions, and three different force levels selected from a range of ADLs, including 4, 12, and 20 N, were used as force-regulating upper extremity motor control tasks. The hemodynamic responses were measured in specific regions of interest, namely the primary motor cortex (M1), premotor cortex (PMC), supplementary motor area (SMA), and prefrontal cortex (PFC). Utilizing a two-way repeated measures ANOVA with Bonferroni correction (p < 0.00625) across all regions, we observed no significant interaction effect between force levels and movement types on oxygenated hemoglobin (HbO) levels. However, in both contralateral (c) and ipsilateral (i) PFC, movement type—static versus dynamic—significantly affected brain activation. Additionally, cM1, iPFC, and PMC showed a significant effect of force level on brain activation.
คณะวิศวกรรมศาสตร์
This research suggested natural hemp fiber-reinforced ropes (FRR) polymer usage to reinforce recycled aggregate square concrete columns that contain fired-clay solid brick aggregates in order to reduce the high costs associated with synthetic fiber-reinforced polymers (FRPs). A total of 24 square columns of concrete were fabricated to conduct this study. The samples were tested under a monotonic axial compression load. The variables of interest were the strength of unconfined concrete and the number of FRRlayers. According to the results, the strengthened specimens demonstrated an increased compressive strength and ductility. Notably, the specimens with the smallest unconfined strength demonstrated the largest improvement in compressive strength and ductility. Particularly, the compressive strength and strain were enhanced by up to 181% and 564%, respectively. In order to predict the ultimate confined compressive stress and strain, this study investigated a number of analytical stress–strain models. A comparison of experimental and theoretical findings deduced that only a limited number of strength models resulted in close predictions, whereas an even larger scatter was observed for strain prediction. Machine learning was employed by using neural networks to predict the compressive strength. A dataset comprising 142 specimens strengthened with hemp FRP was extracted from the literature. The neural network was trained on the extracted dataset, and its performance was evaluated for the experimental results of this study, which demonstrated a close agreement.