KMITL

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

Browse

Search Results

Now showing 1 - 10 of 12

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
Predicting Flexural Strength of FRP-Strengthened Waste Aggregate Concrete Beams with Machine Learning: A Step Towards Sustainability
(2026-04-01)
Sangthongtong, Arissaman
;
Chatveera, Burachat
;
Sua-iam, Gritsada
;
Nawaz, Adnan
;
Mehmood, Tahir
Using waste materials in the manufacture of concrete has many environmental advantages. However, it can be difficult to estimate structural performance, especially when beams are reinforced with fiber-reinforced polymers (FRP). In order to provide a data-driven approach to sustainable structural design, this work explores the use of machine learning (ML) approaches to forecast the flexural strength of FRP-strengthened waste aggregate concrete beams. A total number of 92 experimental datasets were used to develop and assess four ML algorithms: Random Forest (RF), Decision Tree (DT), Neural Network (NN), and Extreme Gradient Boosting (XGBoost). Regression plots, Taylor diagrams, statistical measures (R2R^2R2, RMSE, MAE, MSE), and explainable AI (XAI) tools, including SHAP, LIME, and partial dependence plots (PDPs), were used to evaluate the model’s performance. RF outperformed NN in terms of predictive accuracy, while XGBoost exhibited similar performance to RF. The most significant predictors, according to a SHAP analysis, were beam length and fiber length, with the lower followed by steel tensile strength, fiber width, and concrete compressive strength. LIME offered local interpretability for individual predictions, but PDPs demonstrated optimal parameter ranges and a nonlinear feature strength relationship. The findings provide engineers with a strong decision-support tool for designing green infrastructure, since they show that ensemble-based models can accurately represent the intricate, nonlinear dynamics controlling flexural behavior in sustainable FRP-strengthened waste aggregate concrete beams.
Some of the metrics are blocked by your
consent settings
Thermo-Mechanical Stress Prediction in Steel IPE Profiles under Asymmetric Thermal Loading: A Finite Element and XGBoost-Based Approach
(2026-03-01)
Shaik, Nagoor Basha
;
Derakhshan, Ali
;
Nasim, Maryam
;
Jongkittinarukorn, Kittiphong
Accurate prediction of thermally induced stresses in structural members remains a significant challenge in engineering, especially under complex real-world conditions. Traditional analytical and numerical methods, while robust, often struggle to capture the complicated relationship between uneven thermal loads and structural responses without significant computational effort. This study investigates the effect of asymmetric thermal loading on standard steel IPE profiles, which are widely employed in buildings and structures. These members, often exposed partially to outdoor conditions, experience uneven temperature distributions across their cross-sections, resulting in complex internal stress patterns. To simulate such scenarios, a range of thermal conditions is applied to beams and columns with varying geometries using the Finite Element Method (FEM) numerical analysis. The resulting stress components, including von Mises, axial, and shear stresses, are analyzed in detail. This study introduces a mixed approach that integrates FEM with eXtreme Gradient Boosting (XGBoost) to forecast thermal stresses in steel IPE profiles subjected to asymmetrical temperature gradients. The suggested technique, in contrast to traditional assessments that emphasize uniform heating, accounts for the interrelated impacts of irregular thermal exposures and geometric variations among IPE sections. The FEM database enabled the training of an improved XGBoost model that achieved exceptional accuracy (R² > 0.98) in predicting multiple stress components. The results highlight the critical role of cross-sectional geometry in stress development under thermal gradients and underscore the effectiveness of machine learning techniques in forecasting structural responses. This integration offers a quick, adaptable method for assessing thermal impacts in steel IPE structures, with considerable promise for design and real-time structural evaluation in industrial settings. This approach offers substantial benefits to the petroleum and broader oil and gas sectors, particularly in enhancing structural dependability under thermal and mechanical stresses.
Some of the metrics are blocked by your
consent settings
Evaluation of Machine Learning Techniques for Denial-of-Service Attack Detection in Digital Information Exchange
(2026-01-01)
Suwimol, Piyapol
;
Chimmanee, Krishna
;
Pomsathit, Auttapon
Anomaly detection plays a critical role in mitigating cybersecurity threats, particularly Distributed Denial of Service (DDoS) attacks. This study evaluates the performance of tree-based and ensemble learning models, including Decision Tree, Random Forest, and XGBoost, for classifying Snort log data, alongside the application of Isolation Forest for time-series anomaly detection. The experiments were conducted using ICMP-based Ping Flood attacks in a controlled network environment, with data collected from Snort intrusion detection system logs. The classification results indicate that XGBoost achieved the highest performance, with 99.81% accuracy, 99.93% precision, 99.65% recall, and 99.79% F1-score under a 70–30 train-test split. Random Forest and Decision Tree also demonstrated strong performance, while Logistic Regression showed lower effectiveness due to its limitations in modeling nonlinear patterns. For anomaly detection, Isolation Forest was applied to time-series data collected over a 19-day period. The model detected 93 anomaly points, of which 41 overlapped with Wireshark-confirmed events. However, a false positive rate of 41.67% was observed, indicating the need for parameter tuning to balance detection sensitivity and operational efficiency. Overall, the findings demonstrate that ensemble-based learning approaches, particularly XGBoost, are effective for detecting DDoS-related patterns within the experimental setting. However, the results are limited to ICMP-based attack scenarios in a controlled environment. Further validation, including cross-validation, multi-attack evaluation, and deployment-level performance analysis, is required to assess generalizability and practical applicability.
Some of the metrics are blocked by your
consent settings
Innovative Anomaly Detection in PCB Hot-Air Ovens Using Adaptive Temporal Feature Mapping
(2025-10-01)
Cheng, Chen Yang
;
Chien, Chuan Min
;
Chen, Tzu Li
;
Yuangyai, Chumpol
;
Kong, Pei Ling
As automated equipment in PCB manufacturing becomes increasingly reliant on precision hot-air ovens, ensuring operational stability and reducing downtime have become critical challenges. Existing anomaly detection methods, such as Support Vector Machines (SVMs), Deep Neural Networks (DNNs), and Long Short-Term Memory (LSTM) Networks, struggle with high-dimensional dynamic data, leading to inefficiencies and overfitting. To address these issues, this study proposes an innovative anomaly detection system specifically designed for fault diagnosis in PCB hot-air ovens. The motivation is to improve accuracy and efficiency while adapting to dynamic changes in the manufacturing environment. The core innovation lies in the introduction of the Adaptive Temporal Feature Map (ATFM), which dynamically extracts and adjusts key temporal features in real time. By combining ATFM with Bi-Directional Dimensionality Reduction (BDDR) and eXtreme Gradient Boosting (XGBoost), the system effectively handles high-dimensional data and adapts its parameters based on evolving data patterns, significantly enhancing fault detection accuracy and efficiency. The experimental results show a fault prediction accuracy of 99.33%, greatly reducing machine downtime and product defects compared to traditional methods.
Some of the metrics are blocked by your
consent settings
Data-driven prediction of failure loads in low-cost FRP-confined reinforced concrete beams
(2025-07-01)
Talpur, Shabbir Ali
;
Thansirichaisree, Phromphat
;
Anotaipaiboon, Weerachai
;
Mohamad, Hisham
;
Zhou, Mingliang
This study investigates the application of machine learning (ML) models to predict the ultimate failure load of reinforced concrete (RC) beams confined with low-cost fiber-reinforced polymers (FRP), relatively underexplored area. A dataset of 100 samples, including beams designed to fail in flexure and shear, was compiled from literature and experimental testing. Four ML models—XGBoost, Random Forest (RF), Neural Network (NN), and Decision Tree (DT)—were evaluated using k-fold cross-validation with performance metrics such as Mean Absolute Error (MAE), Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and R². XGBoost outperformed the other models, achieving the highest R² of 0.96 and the lowest RMSE of 12.81, while SHAP analysis identified beam height, bottom rebar strength, and beam width as key predictors. These results highlight the effectiveness of ensemble methods for predicting failure loads in RC beams and provide insights into the most influential features affecting structural performance.
Some of the metrics are blocked by your
consent settings
Modeling and Forecasting Dead-on-Arrival in Broilers Using Time Series Methods: A Case Study from Thailand
(2025-04-01)
Jainonthee, Chalita
;
Sivapirunthep, Panneepa
;
Pirompud, Pranee
;
Punyapornwithaya, Veerasak
;
Srisawang, Supitchaya
Antibiotic-free (ABF) broiler production plays an important role in promoting sustainable and welfare-oriented poultry farming. However, this production system presents challenges, particularly an increased susceptibility to stress and mortality during transport. This study aimed to (i) analyze time series data on the monthly percentage of dead-on-arrival (%DOA) and (ii) compare the performance of various time series models. Data on %DOA from 127,578 broiler transport truckloads recorded between 2018 and 2024 were aggregated into monthly %DOA values. The data were then decomposed to identify trends and seasonal patterns. The time series models evaluated in this study included SARIMA, NNAR, TBATS, ETS, and XGBoost. These models were trained using data from January 2018 to December 2023, and their forecasting accuracy was evaluated on test data from January to December 2024. Model performance was assessed using multiple error metrics, including MAE, MAPE, MASE, and RMSE. The results revealed a distinct seasonal pattern in %DOA. Among the evaluated models, TBATS and ETS demonstrated the highest forecasting accuracy when applied to the test data, with MAPE values of 21.2% and 22.1%, respectively. These values were considerably lower than those of NNAR at 54.4% and XGBoost at 29.3%. Forecasts for %DOA in 2025 showed that SARIMA, TBATS, ETS, and XGBoost produced similar trends and patterns. This study demonstrated that time series forecasting can serve as a valuable decision-support tool in ABF broiler production. By facilitating proactive planning, these models can help reduce transport-related mortality, improve animal welfare, and enhance overall operational efficiency.
Some of the metrics are blocked by your
consent settings
Prediction of Water Quality Index (WQI) Using Machine Learning
(2025-01-01)
Kularbphettong, Kunyanuth
;
Raksuntorn, Nareenart
;
Boonseng, Chongrag
The purpose of this project is to assess Water Quality Index (WQI) by using five machine learning techniques including the Support Vector Machine (SVM), Random Forest (RF), Decision Tree (DF), Extreme Gradient Boosting (XGBoost), and Adaptive Boosting (AdaBoost). In this case, we are using Thailand as a base country for assessing water quality of the rivers and canals. The data set was collected from Bangkok Metropolitan Authority of Thailand during the period January 2018 to January 2021. The data set included 43,776 records and each record comprised 12 quantitative measurements related to water quality. Hence, they were used as feature inputs of the assessment model; for instance, pH, DO (Dissolved Oxygen), BOD (Biochemical Oxygen Demand), TP (Total Phosphorus), TCB (Total Coloniform Bacteria), FCB (Fecal Coloniform Bacteria), NO3-N (Nitrogen-Nitrogen), No2-N (Nitrogen-Suspended Solid), NH3-N (Ammonia-Nitrogen), TS (Total Solid), and Total Dissolved Solid (TDS). During the phase of preprocessing K-Nearest Neighbors (KNN) and Random Forest were employed to handle missing data and detecting outliers. KNN imputation was applied to address missing values, while Random Forest was implemented to eliminate outliers, so generating the dataset appropriate for model training. The effectiveness of each machine learning model was assessed employing four principal metrics: accuracy, precision, recall, and F1 score. The findings revealed that all five methodologies excelled in predicting WQI; however, the XGBoost model surpassed the others, attaining the highest values across all metrics, including an accuracy of 91%.
Some of the metrics are blocked by your
consent settings
Improving Classification Efficiency Based on Combination of Extreme Gradient Boosting and Deep Transfer Learning
(2023-01-01)
Phankokkruad, Manop
;
Wacharawichanant, Sirirat
The leading causes of blindness and low vision are ocular disease. Ocular disease such as glaucoma, cataract, diabetic retinopathy, and macular degeneration, which are diseases in which the risk of vision loss. Unfortunately, some ocular diseases have no symptoms until the late stages. Therefore, early-stage diagnosis of ocular disease is the best way to prevent vision loss. This work proposed the classification models for ocular disease classification using XGBoost in combination with deep transfer learning of CNN as the feature extractor. In the model training process, we used the pre-trained model including Xception and ResNet50 based on the transfer learning technique to extract different features. The proposed model was used to classify ocular disease into eight patterns. The XGBoost in combination with the ResNet50 model achieved an accuracy level of 87.82%, precision of 88.15%, sensitivity of 87.82%, and F1 score of 87.82%. The XGBoost in combination with the Xception model acquired an accuracy level of 87.02%, precision of 87.35%, sensitivity of 87.02%, and F1 score of 87.02%. By considering the F1 score, XGBoost in combination with transfer learning of CNN models gave a high score. Therefore, all evaluation parameters clearly indicate the high performance of the ocular disease classification model. The conclusion presents that the proposed method acquires more excellent performance than individual deep learning models.
Some of the metrics are blocked by your
consent settings
Performance Analysis and Comparison of Cerebral Stroke Prediction Models on Imbalanced Datasets
(2022-01-01)
Phankokkruad, Manop
;
Wacharawichanant, Sirirat
A cerebral stroke is an interrupt blood flow to the brain leading cause of death. A number of risk factors increase the risk of stroke occurence because of lifestyle. Machine learning is effective techniques can be applied in prediction of stroke. The different kind of algorithms give the various accuracy and performance in the prediction. This study has proposed the four machine learning algorithm for classifiers to predict of cerebral stroke. The proposed model with various classifier has considered the risk factors such as age, hypertension, heart disease, average glucose level, BMI, and smoking status as feature attributes to predict cerebral stroke. This study conducted on two stroke datasets, and improve the imbalanced of between classes by using SMOTE. The result shows that XGBoost provided the highest accuracy of around 98.08% and 96.73% by comparing to the other machine learning algorithms. In addition, this study evaluates the models by analyzing the statistical parameters include accuracy, precision, sensitivity, F1 score, and AUC. The evaluation reveals that the XGBoost, Random Forest, AdaBoost and KNN classifier achieved the average AUC value of 0.851, 0.868, 0.670 and 0.851, respectively. All models provided the high confidence values, whereas the model with XGBoost classifier gave the highest performance.

KMITL

Browse

Filters

Settings

Sort By

Results per page

Search Results