KMITL

Permanent URI for this communityhttps://dspace.kmitl.ac.th/handle/123456789/1

Browse

Search Results

Now showing 1 - 9 of 9

Some of the metrics are blocked by your
consent settings
DDoS Detection Framework Using Machine Learning Optimized by Bayesian and PSO Techniques
(2026-07-01)
Sathaporn, Posathip
;
Krungseanmuang, Woranidtha
;
Chaowalittawin, Vasutorn
;
Benjangkaprasert, Chawalit
;
Archevapanich, Tuanjai
This paper presents a distributed denial of service (DDoS) detection framework using machine learning techniques enhanced with hyperparameter optimization for network traffic classification and evaluated on the BCCC-cPacket-Cloud-DDoS-2024 dataset. The framework includes data preprocessing with normalization and class imbalance handling via the synthetic minority over-sampling technique. A critical contribution of this study is the rigorous analysis of the trade-off between detection accuracy and model complexity. Unlike arbitrary feature selection methods, we empirically determined the optimal feature set using information gain, identifying that the top 100 features represent the saturation point that balances high accuracy with minimal overhead. Model performance was further improved through hyperparameter optimization using particle swarm optimization and Bayesian algorithms. The extreme gradient boosting (XGBoost) model optimized using Bayesian optimization and the top 100 features achieved the highest performance, with an accuracy of 99.29% and an F1-score of 98.91%. As a result, the proposed framework improves detection performance while reducing model complexity by selecting an optimal feature set to improve model stability and efficiency.
Some of the metrics are blocked by your
consent settings
Thai Morning Glory Price Forecasting Using Deep Learning
(2025-01-01)
Waeodi, Kanokwan
;
Boongasame, Laor
;
Thammarak, Karanrat
This study established advanced machine-learning-driven forecasting models to enhance the accuracy of price predictions for Thai morning glory, a widely consumed leafy green vegetable. The models were trained using historical price, weather, and rainfall data using time-series forecasting methods, specifically LSTM and CNN. The findings indicate that stepwise feature selection minimizes prediction errors and improves MSE, RMSE, MAPE, and MAE. Preliminary experiments revealed that the LSTM model with feature selection outperformed the other models, particularly in feature selection. Employing standard hyperparameters of 100 epochs, 32 batches, and five windows, the model demonstrated superior performance with a lower MSE (0.0010), RMSE (0.0274), MAPE (3.7803), and MAE (0.0158) than the CNN model. Statistical hypothesis testing revealed significant variations between the LSTM and CNN models, with feature selection p-values below 0.05. These results indicate that LSTM with feature selection models optimized through refined hyperparameters leads to more accurate Thai morning glory price forecasting, providing valuable insights for stakeholders in their decision-making processes. Additionally, this study can forecast prices for 5, 7, 14, and 21 days in advance based on different Window_len values, addressing various planning needs. The 5- and 7-day forecasts support short-term decision-making, such as scheduling harvest cycles and weekly market planning, whereas the 14-day forecast assists farmers in optimizing planting schedules and logistics. Furthermore, the 21-day forecast is beneficial for medium-term market planning, including negotiating forward contracts and adjusting distribution strategies to maximize profitability.
Some of the metrics are blocked by your
consent settings
Building a Rule-Based Expert System to Enhance the Hard Disk Drive Manufacturing Processes
(2024-01-01)
Kirdponpattara, Suppakrit
;
Sooraksa, Pitikhate
;
Boonjing, Veera
The manufacturing of hard disk drives involves the intricate assembly of numerous components, making the testing process time-consuming and resource intensive. To optimize the manufacturing process and increase testing efficiency, the development of a rule-based expert system is proposed. This system leverages predictive models constructed from assembly process data to identify potentially defective hard drives before undergoing extensive testing. By preemptively identifying defects, this approach substantially reduces testing time and enhances tester capacity. Given the categorical and imbalanced nature of assembly data, Decision Trees are employed as the prediction model. Specifically, three Decision Tree algorithms are explored: ID3, C4.5, and CART. In addition, four feature selection techniques, namely Information Gain, Gain Ratio, Chi-Square, and Symmetrical Uncertainty, are utilized to identify high-impact features. Our experimental findings reveal that Information Gain coupled with the C4.5 algorithm yields the most favorable results in terms of prediction accuracy, modeling efficiency, and rule generation. Moreover, our study establishes that setting the failure probability threshold between 0.15 and 0.70 provides the shortest total test time for the proposed process, as supported by a 95% confidence level. This achievement represents a statistically significant enhancement compared with the existing manufacturing process.
Some of the metrics are blocked by your
consent settings
An Alternative Method for Upgrading the Conventional Decision Tree Algorithm
(2024-01-01)
Kirdponpattara, Suppakrit
;
Boonjing, Veera
;
Sooraksa, Pitikhate
Decision tree algorithms are widely used for solving classification and regression problems. Their popularity can be attributed to their transparent nature, simplicity, easy interpretability, faster classification speed, and strong decision rules. However, decision tree induction algorithms face various inherent and external limitations, such as overfitting, high sensitivity to noise and outliers, and instability with minimal data variations. In this study, we introduce an innovative approach to enhance traditional decision tree algorithms [e.g., Iterative Dichotomiser 3 (ID3), C4.5, and Classification and Regression Trees (CART)] by incorporating feature selection techniques. The proposed approach aims to enhance the accuracy and efficiency of decision tree models. Experiments were conducted on a real-world dataset of a hard disk drive (HDD) manufacturing process using the proposed approach. In comparison with a baseline where all features were utilized, the study highlighted a significant improvement in accuracy, indicating that the approach holds immense potential for optimizing decision tree algorithms and improving the HDD manufacturing process.
Some of the metrics are blocked by your
consent settings
Improving Machine Learning-Based Wi-Fi Fingerprint Technique with Feature Selection and Grid Search Methods
(2024-01-01)
Nimnaul, Tanapol
;
Wongwirat, Olarn
This paper presents the enhancement of the WiFi-based fingerprint technique for an indoor positioning system applied to a real experimental area. In typical Wi-Fi-based fingerprint techniques, classification algorithms such as k-nearest neighbor (k-NN), decision tree (DT), and random forest (RF) are used for position estimation. However, these algorithms do not perform well with high-dimensional and large datasets. They also face limitations related to overfitting and uninformative features in datasets. This paper overcomes these challenges by deploying feature selection based on filter methods. This process removes uninformative features from the datasets before feeding them to construct a training model. The grid search method is also employed to perform hyperparameter tuning, which is used to construct the outperforming models. The experimental setup involved collecting received signal strength indicators (RSSIs) from access points (APs) in the real indoor environment to create the radio map. The accuracy performance of the proposed methods was tested by employing the feature selection method on the radio map dataset and using the grid search method to find optimized hyperparameters for constructing the training models based on the k-NN, DT, and RF algorithms. The accuracy results were compared with those of non-feature selection and default hyperparameters used for the three algorithms. The computational results demonstrate that the RF algorithm outperforms the other two algorithms. Furthermore, performance is improved when using grid search and feature selection as proposed.
Some of the metrics are blocked by your
consent settings
Comparative Study of Prediction Models for Final GPA Score: A Case Study of Rajabhat Rajanagarindra University
(2018-09-14)
Putpuek, Narongsak
;
Rojanaprasert, Natcha
;
Atchariyachanvanich, Kanokwan
;
Thamrongthanyawong, Thananya
Recently, the analysis of educational data has become important to all universities. Rajabhat Rajanagarindra University, Thailand, wanted to study and analyze the students' performance based on their personal background. Thus, this research aimed to compare prediction models for the level of the final grade point average (GPA) score of graduated students using the data from the Faculty of Education during the 2010 to 2012 academic years. Two decision tree (C4.5 and ID3) algorithms, plus Naïve Bayes and K-nearest neighbor data mining techniques were adopted to analyze the data according to the CRISP-DM process. Factors that were proposed to influence the graduation GPA include the student's gender, scholarship awarded, previous educational background, admission type, talent and province of high school. The analysis revealed that the Naïve Bayes algorithm gave the best overall accuracy of 43.18%. This could help predict the graduation GPA score of students in the future and support teachers to make educational advice for their students and to develop the student quality in the future.
Some of the metrics are blocked by your
consent settings
E-commerce web page classification based on automatic content extraction
(2015-08-24)
Petprasit, Warid
;
Jaiyen, Saichon
Currently, There are many E-commerce websites around the internet world. These E-commerce websites can be categorized into many types which one of them is C2C (Customer to Customer) websites such as eBay and Amazon. The main objective of C2C websites is an online market place that everyone can buy or sell anything at any time. Since, there are a lot of products in the E-commerce websites and each product are classified into its category by human. It is very hard to define their categories in automatic manner when the data is very large. In this paper, we propose the method for classifying E-commerce web pages based on their product types. Firstly, we apply the proposed automatic content extraction to extract the contents of E-commerce web pages. Then, we apply the automatic key word extraction to select words from these extracted contents for generating the feature vectors that represent the E-commerce web pages. Finally, we apply the machine learning technique for classifying the E-commerce web pages based on their product types. The experimental results signify that our proposed method can classify the E-commerce web pages in automatic fashion.
Some of the metrics are blocked by your
consent settings
Adaptive power system stabilizer design using optimal support vector machines based on harmony search algorithm
(2014-04-04)
Pahasa, Jonglak
;
Ngamroo, Issarachai
Abstract - This article presents the application of support vector machines to adaptive power system stabilizer design in a multi-machine power system based on the harmony search algorithm. Data from a multi-machine power system are the input features of the support vector machines. Support vector machine parameters and power system features are simultaneously optimized by harmony search based on the k-fold cross-validation technique. The proposed algorithm is trained by the optimal support vector machine parameters and optimal power system features. Power system stabilizer parameters produced by the proposed algorithm can be adapted by various operating conditions when the power system operates either inside or outside the training ranges. Simulation studies in the IEEJ Western Japan ten-machine power system demonstrate that the proposed algorithm is far superior to conventional power system stabilizers with fixed parameters and those designed by a robust coupled vibration model under various operating conditions and severe disturbances. © 2014 Copyright Taylor and Francis Group, LLC.
Some of the metrics are blocked by your
consent settings
Prediction of reference evapotranspiration with missing data in Thailand
(2013-01-01)
Pasupa, Kitsuchart
;
Thamwiwatthana, Ek
Artificial Neural Networks (ANNs) has been used in prediction of reference evapotranspiration for a recent decade. Its performance is competitive to a widely used method the so-called 'Penman-Monteith' method. In this study, we aim to estimate the crop evapotranspiration by ANNs from climatic data in Thailand and compare the performance with the Penman-Monteith method. As missing data is inevitable, we also included the missing data situation into the study. This can be solved by expectation-maximization algorithm. The accuracy of the prediction decreases when the amount of missing values increases. Furthermore, we exploit the feature selection in the study. It shows that sunshine duration is the most important feature followed by temperature and wide speed, respectively. © 2013 IEEE.

KMITL

Browse

Filters

Settings

Sort By

Results per page

Search Results