KMITL

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

Browse

Settings

Subject: search.filters.subject.ensemble learning

Search Results

Now showing 1 - 4 of 4
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    A Cascade of Encoder–Decoder with Atrous Convolution and Ensemble Deep Convolutional Neural Networks for Tuberculosis Detection
    (2025-07-01)
    Maneerat, Noppadol
    ;
    Narkthewan, Athasart
    ;
    Hamamoto, Kazuhiko
    Tuberculosis (TB) is the most serious worldwide infectious disease and the leading cause of death among people with HIV. Early diagnosis and prompt treatment can cut off the rising number of TB deaths, and analysis of chest X-rays is a cost-effective method. We describe a deep learning-based cascade algorithm for detecting TB in chest X-rays. Firstly, the lung regions were segregated from other anatomical structures by an encoder–decoder with an atrous separable convolution network—DeepLabv3+ with an XceptionNet backbone, DLabv3+X, and then cropped by a bounding box. Using the cropped lung images, we trained several pre-trained Deep Convolutional Neural Networks (DCNNs) on the images with hyperparameters optimized by a Bayesian algorithm. Different combinations of trained DCNNs were compared, and the combination with the maximum accuracy was retained as the winning combination. The ensemble classifier was designed to predict the presence of TB by fusing DCNNs from the winning combination via weighted averaging. Our lung segmentation was evaluated on three publicly available datasets: it provided better Intercept over Union (IoU) values: 95.1% for Montgomery County (MC), 92.8% for Shenzhen (SZ), and 96.1% for JSRT datasets. For TB prediction, our ensemble classifier produced a better accuracy of 92.7% for the MC dataset and obtained a comparable accuracy of 95.5% for the SZ dataset. Finally, occlusion sensitivity and gradient-weighted class activation maps (Grad-CAM) were generated to indicate the most influential regions for the prediction of TB and to localize TB manifestations.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Flood Susceptibility Mapping Using Machine Learning Models with Novel Flood Inventory Sampling Strategies
    (2025-01-01)
    Nusit, Korakod
    ;
    Tantanee, Sarintip
    ;
    Sooraksa, Pitikhate
    In this study, we introduce an innovative frequency-area-weighted sampling method to address spatial and temporal biases in flood inventory creation. Focusing on Thailand’s Nan River Basin, we integrated 13 flood conditioning factors and developed a point-based inventory that includes 3000 flood and 3000 non-flood samples, proportionally allocated on the basis of flood recurrence intervals and spatial distribution. We evaluated four machine learning models—artificial neural network, support vector machine, K-nearest neighbors, and random forest (RF) models—to assess their performance in flood susceptibility mapping (FSM). Among these, the RF model demonstrated the highest predictive capability, achieving an area under the curve (AUC) of 0.979 for the test set and an AUC of 0.984 for the verification set. The resulting susceptibility map identified 10.64% of the study area as “very high” risk, providing critical insights for prioritizing flood mitigation efforts. This work advances FSM methodology by effectively bridging the temporal flood frequency and spatial heterogeneity in inventory design, offering a robust framework for data-driven flood risk management in vulnerable regions.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Hybrid Multi-Model Fuzzy Ensemble Approach for Cardiovascular Diseases Detection
    (2023-01-01)
    Chugh, Manop
    ;
    Anantavrasilp, Isara
    ;
    Thiemjarus, Surapa
    Timely detection of cardiovascular diseases (CVDs) is crucial to reducing mortality rates. Recent advances in artificial intelligence (AI) and machine learning (ML) models for CVD detection often suffer from low model performance and hence lower accuracy and practicality of early CVD detection. In this study, we propose a novel hybrid ensemble learning framework that combines multiple ML algorithms and a fuzzy expert system to improve CVD diagnosis and prediction accuracy. We evaluate our proposed method on two standard datasets, namely the UCI Cleveland and Framingham, and compare it with four popular ensemble algorithms, namely Random Forest, Gradient Boosting, eXtreme Gradient Boosting, and Adaptive Boosting. Our results demonstrate that the proposed ensemble learning framework achieves higher accuracies of 91.2% (UCI Cleveland) and 91.7% (Framingham), surpassing existing algorithms by 3.3% and 8.8%, respectively.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    A Hybrid of Shallow and Deep Learning for Odor Classification Based on Adaptive Boosting
    (2019-11-01)
    Grodniyomchai, Boonyawee
    ;
    Chalapat, Khattiya
    ;
    Jitkajornwanich, Kulsawasd
    ;
    Jaiyen, Saichon
    An electronic nose is very useful for identifying an odor that is harmful to humans. To get the most accurate odor predictions from an electronic nose, we combined the models of traditional machine learning and deep learning, including deep neural network (DNN), support vector machine (SVM) and decision tree, to make a new hybrid model that adopts the AdaBoost algorithm to adjust the weights of weak classifiers to build a strong classifier using odor data. Experimental results from our model were compared with other models, including a single deep neural network, an ensemble of SVM models and an ensemble of decision trees. Our model achieved an averaged accuracy of 99.58%, which is better than other models, and the standard deviation, 0.67%, is also less than other models.