Discover the ultimate innovations of the future developed by Thai researchers! Meet the latest technology from KMITL that will transform our way of life and industry.
คณะวิทยาศาสตร์
In this paper, Vanadium dioxide (VO2) thin-film devices with two different use cases have been redesigned to introduce an asymmetrical resonant cavity structure. The structure is designed with the goal of enhancing the optical performance of the central VO2 layer and has an anti-reflection property in the cold state. The advantages and limitations of such a design are discussed.
คณะวิทยาศาสตร์
This special problem aims to compare the performance of machine learning methods in time series forecasting using lagged time periods as independent variables. The lagged periods are categorized into three groups: lagged by 10 units, lagged by 15 units, and lagged by 20 units. The study employs four machine learning methods: Decision Tree (DT), Random Forest (RF), K-Nearest Neighbors (KNN), and Support Vector Machine (SVM). The time series data simulated as independent variables diverse including characteristics: Random Walk data, Trending data, and Non-Linear data, with sample sizes of 100, 300, 500, and 700. The research methodology involves splitting the data into 90% for training and 10% for testing. Simulations and analysis are performed using the R programming language, with 1,000 iterations conducted. The results are evaluated based on the average mean squared error (AMSE) and the average mean absolute percentage error (AMAPE) are calculated to identify the best performing method. The research findings revealed that for Random Walk data, the best performing methods are Random Forest and Support Vector Machine. For Trend data, the best performing methods are Random Forest. For Non-Linear data, the best performing methods are Support Vector Machine. When tested with real-world data, the results show that for the Euro-to-Thai Baht exchange rate, the best methods are Random Forest and Support Vector Machine. For the S&P 500 Index in USD, the best performing methods are Random Forest. For the Bank of America Corp Index in USD, the best performing methods are Support Vector Machine.
คณะบริหารธุรกิจ
This project is a part of KMITL business student’s thesis. The topic is business plan about blazers and trousers made by recycled fabric
คณะวิทยาศาสตร์
The objective is to develop a web application for tool requests to issues arising from using Excel programs. The initial Excel file is copied from an existing SQL database and repeatedly duplicated, leading to excessive storage consumption. Additionally, the Excel files cannot be accessed concurrently by multiple users. Therefore, this web application aims to connect directly to the SQL database, eliminating the problems caused by using Excel files.
คณะอุตสาหกรรมอาหาร
This research aimed to isolate and culture four strains of lactic acid bacteria (LAB) isolated from fermented foods. The antimicrobial activity of the lactic acid bacteria was studied using the agar spot method and the antibiotic resistance properties of the lactic acid bacteria were studied using the agar overlay diffusion method. The results showed that each strain of lactic acid bacteria had different levels of antimicrobial activity and antibiotic resistance, which are safety properties of probiotic microorganisms.
คณะวิทยาศาสตร์
Nowadays, automobiles are the most widely used form of transportation. This increases the risk of accidents. Therefore, car users prefer to get insurance to reduce the risk in the event of an accident. As for the insurance company, the company will be responsible for damages according to the conditions of the policy. One of the duties of a company's claims department is to procure spare parts to control costs. However, in the case of compensation, there may be erroneous operations, such as ordering the wrong parts or ordering more than necessary. Currently, insurance companies do not have a very efficient management system. This research aims to develop a system for managing and storing automobile parts for insurance companies. The system is designed to be able to track the status of spare parts from storage to disbursement. It uses barcode technology to increase accuracy and reduce errors in data recording. Such a system will help insurance companies manage spare parts systematically, reduce unnecessary costs, and increase efficiency in providing services.
คณะวิทยาศาสตร์
This special problem aims to study and compare the performance of predicting the air quality index (AQI) using five ensemble machine learning methods: random forest, XGBoost, CatBoost, stacking ensemble of random forest and XGBoost, and stacking ensemble of random forest, SVR, and MLP. The study uses a dataset from the Central Pollution Control Board of India (CPCB), which includes fifteen pollutants and nine meteorological variables collected between January, 2021 and December, 2023. In this study, there were 1,024,920 records. The performance is measured using three methods: root mean square error (RMSE), mean absolute error (MAE), and coefficient of determination. The study found that the random forest and XGBoost stacking ensemble had the best performance measures among the three methods, with the minimum RMSE of 0.1040, the minimum MAE of 0.0675, and the maximum of 0.8128. SHAP-based model interpretation method for five machine learning methods. All methods reached the same conclusion: the two variables that most significantly impacted the global prediction were PM2.5 and PM10, respectively.
คณะอุตสาหกรรมอาหาร
Oral disintegrating films (ODFs) can dissolve in the mouth instantly upon contact with saliva, without the need for water. This study aimed to investigate the effect of sorbitol concentration on the properties of oral disintegrating films containing Capsicum Oleoresin extract, which has properties that stimulate saliva secretion, making swallowing easier. The film was developed to address difficulties in swallowing, especially for individuals with dysphagia. The films were prepared using different concentrations of sorbitol and tested for rheological properties, mechanical properties, moisture content, free water content, thickness, disintegration time, contact angle, color, and antioxidant activity. The results indicated that sorbitol played a key role in increasing the flexibility and reducing the brittleness of the films. Additionally, an optimal concentration of sorbitol helped maintain the stability of the Capsicum extract and enhanced its efficacy in stimulating saliva secretion, thereby making swallowing more convenient and reducing oral friction. The films developed in this study demonstrate potential as an alternative for individuals with swallowing difficulties.
คณะวิทยาศาสตร์
This project focuses on the study and development of a short-term investment framework via gold trading in the foreign exchange market. Machine learning techniques are applied to analyze and forecast pricing trends. Moreover, we develop the system using a stochastic process to determine optimal stop-loss points, with the aim of maximizing expected returns. Additionally, we apply game theory to guide the decision-making process regarding order holding or closure. The system is implemented and tested on the MetaTrader 5 (MT5) platform. This project outlined the clear process that includes data preparation, machine learning model training, probabilistic modeling of gold price movements, stop-loss strategy formulation, strategic decision modeling based on game theory, the development of an automated trading program, and backtesting to evaluate system performance.