2026-03-12
【學術亮點】一種結合注意力機制的表格網路和整合學習以及產生對抗網路的混合框架，用於剛度模量預測
字體大小
小
中
大
Intelligent Cultivation: Crop digital twin for growth adversity index and disaster damage assessment【Department of Civil Engineering / Ming-Der Yang / Tenured Distinguished Professor】
智慧栽培：數位分身作物生長逆境指標與災損監測【土木工程學系楊明德終身特聘教授】
上架日期2025-10-15
智慧栽培：數位分身作物生長逆境指標與災損監測【土木工程學系楊明德終身特聘教授】
| 論文篇名 | 英文：A hybrid framework of attention-based tabular network and ensemble learning with generative adversarial network for stiffness modulus prediction 中文：一種結合注意力機制的表格網路和整合學習以及產生對抗網路的混合框架，用於剛度模量預測 |
| 期刊名稱 | Case Studies in Construction Materials |
| 發表年份, 卷數, 起迄頁數 | 2025, 23, no. e05401 |
| 作者 | Yared Bitew Kebede;Yang, Ming-Der (楊明德)* |
| DOI | 10.1016/j.cscm.2025.e05401 |
| 中文摘要 | 動態模量是路面工程中的基本屬性，它量化了瀝青混合料在循環荷載作用下的黏彈性剛度，是模擬路面對交通荷載和溫度變化響應的力學-經驗設計框架的關鍵參數。然而，動態模量的現場測量仍然成本高、耗時費力且技術要求高，因此迫切需要準確且有效率的預測模型。傳統的機器學習方法已被用於估計動態模量，但其預測能力通常受限於稀缺且異質的資料集，從而限制了模型的泛化能力。為了應對這些挑戰，本研究提出了一種混合學習框架，該框架將基於注意力機制的表格網路（TabNet）-極端梯度提升（XGB）與條件表格生成對抗網路（CTGAN）相結合，用於合成資料增強。該框架利用TabNet基於注意力機制的深度特徵表示和XGB的提升能力，在資料稀缺的情況下提高了預測精度和穩健性。使用不同統計指標進行的全面評估表明，基於 CTGAN 合成資料訓練的模型始終優於僅使用真實資料訓練的模型以及使用其他資料增強方法的模型，其決定係數 (R²) 高達 0.98。 Shapley 加性解釋分析進一步確定了 Marshall 穩定性 (28.7%)、流度 (18.8%) 和瀝青含量 (13.4%) 是動態模量預測中最具影響力的特徵。 CTGAN 增強的混合模型將平均絕對誤差降低了 67.30%，R² 提高了 13.27%，標準誤差降低了 59.38%，所有評估指標均有顯著提升。這些發現凸顯了基於 GAN 的數據增強在推進預測建模和促進路面工程中更高效的數據驅動實踐方面的巨大潛力。 |
| 英文摘要 | The dynamic modulus is a fundamental property in pavement engineering, quantifying the viscoelastic stiffness of asphalt mixtures under cyclic loading and critical in mechanistic-empirical design frameworks for modeling pavement responses to traffic loads and temperature variations. However, its in-situ measurement remains costly, time-consuming, and technically demanding, creating a pressing need for accurate and efficient predictive models. Traditional machine learning approaches have been explored to estimate the dynamic modulus, but their predictive capabilities are often constrained by scarce, heterogeneous datasets, limiting generalization. To address these challenges, this study proposes a hybrid learning framework that integrates Attention Based Tabular Network (TabNet)-Extreme Gradient Boosting (XGB) with Conditional Tabular Generative Adversarial Networks (CTGAN) for synthetic data augmentation. The framework leverages TabNet’s attention-based deep feature representation and XGB’s boosting capabilities to enhance predictive accuracy and robustness under data-scarce conditions. A comprehensive evaluation using different statistical metrics demonstrated that the proposed model trained on CTGAN-synthesized data consistently outperformed models trained solely on real data and those using alternative augmentation methods, achieving a superior coefficient of determination (R²) of 0.98. SHapley Additive exPlanations analysis further identified Marshall Stability (28.7 %), Flow (18.8 %), and asphalt content (13.4 %) as the most influential features in dynamic modulus prediction. The CTGAN-augmented proposed hybrid model reduced Mean Absolute Erro by 67.30 %, improved R² by 13.27 %, and decreased Standard Error Ratio by 59.38 %, reflecting significant improvements across all evaluation metrics. These findings highlight the transformative potential of GAN-based data augmentation to advance predictive modeling and promote more efficient data-driven practices in pavement engineering. |
| 發表成果與AI計畫研究主題相關性 | 目前發展的AI 模式以道路鋪面為溫度預測對象，可以應用在農地土壤分層溫度之預測。 |
