• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제2권1호
• /
• pp.26-32
• /
• 2002

The objectives of this paper are twofold. First is to introduce a model for representing documents with semantics relatedness using rough sets but with tolerance relations instead of equivalence relations (TRSM). Second is to introduce two document hierarchical and nonhierarchical clustering algorithms based on this model and TRSM cluster-based information retrieval using these two algorithms. The experimental results show that TRSM offers an alterative approach to text clustering and information retrieval.

• Steel and Composite Structures
• /
• 제52권2호
• /
• pp.145-163
• /
• 2024

This paper presents six novel hybrid machine learning (ML) models that combine support vector machines (SVM), Decision Tree (DT), Random Forest (RF), Gradient Boosting (GB), extreme gradient boosting (XGB), and categorical gradient boosting (CGB) with the Harris Hawks Optimization (HHO) algorithm. These models, namely HHO-SVM, HHO-DT, HHO-RF, HHO-GB, HHO-XGB, and HHO-CGB, are designed to predict the ultimate strength of both rectangular and circular reinforced concrete (RC) columns. The prediction models are established using a comprehensive database consisting of 325 experimental data for rectangular columns and 172 experimental data for circular columns. The ML model hyperparameters are optimized through a combination of cross-validation technique and the HHO. The performance of the hybrid ML models is evaluated and compared using various metrics, ultimately identifying the HHO-CGB model as the top-performing model for predicting the ultimate shear strength of both rectangular and circular RC columns. The mean R-value and mean a20-index are relatively high, reaching 0.991 and 0.959, respectively, while the mean absolute error and root mean square error are low (10.302 kN and 27.954 kN, respectively). Another comparison is conducted with four existing formulas to further validate the efficiency of the proposed HHO-CGB model. The Shapely Additive Explanations method is applied to analyze the contribution of each variable to the output within the HHO-CGB model, providing insights into the local and global influence of variables. The analysis reveals that the depth of the column, length of the column, and axial loading exert the most significant influence on the ultimate shear strength of RC columns. A user-friendly graphical interface tool is then developed based on the HHO-CGB to facilitate practical and cost-effective usage.

• Asian review of World Histories
• /
• 제1권1호
• /
• pp.45-84
• /
• 2013

Empirical research into Đại Việt before the $14^{th}$ century has made little progress since the 1990s. To improve this situation, I here examine how the L$\acute{y}$ dynasty (1009-1226), the first long-lasting dynasty of Đại Việt, established stable local ruleafter the "Tang-Song Transition" in China that changed the entire picture of East Asia (including both Southeast and Northeast Asia). This paper focuses on two issues. First are the local administrative units and their governors. The nature of both higher units like lộ(circuits), phủ and ch$\hat{a}$u (provinces), and basic units like hươg and gi$\acute{a}$p (districts?) will be examined. Second, I examine non-institutional channels of local rule by the imperial family. By combining such administrative and non-administrative means, the L$\acute{y}$ central court enforced a considerably stable local rule for two centuries. Finally, I attempt some preliminary comparisons with the local rule of Goryeo (918-1392) in the Korean peninsula, a polity that shared many features with Đại Việt in the process of localization of the Tang and Song models. I hope this approach of viewing small empires from the standpoint not of their "goal" (modern states) but of their "start" (charter polities), will enrich the discussion of East Asian small empires.

• Journal of Electrochemical Science and Technology
• /
• 제15권2호
• /
• pp.291-298
• /
• 2024

Due to its high theoretical capacity, Silicon (Si) has shown great potential as an anode material for lithium-ion batteries (LIBs). However, the large volume change of Si during cycling leads to poor cycling stability and low Coulombic efficiency. In this study, we synthesized Si/Carbon C45:Graphene composites using a ball-milling method with a fixed Si content (20%) and investigated the influence of the C45/Gr ratio on the electrochemical performance of the composites. The results showed that carbon C45 networks can provide good conductivity, but tend to break at Si locations, resulting in poor conductivity. However, the addition of graphene helps to reconnect the broken C45 networks, improving the conductivity of the composite. Moreover, the C45 can also act as a protective coating around Si particles, reducing the volume expansion of Si during charging/discharging cycles. The Si/C45:Gr (70:10 wt%) composite exhibits improved electrochemical performance with high capacity (~1660 mAh g^-1 at 0.1 C) and cycling stability (~1370 mAh g^-1 after 100 cycles). This work highlights the effective role of carbon C45 and graphene in Si/C composites for enhancing the performance of Si-based anode materials for LIBs.

• Steel and Composite Structures
• /
• 제51권6호
• /
• pp.679-695
• /
• 2024

This paper presents a novel technique that combines machine learning (ML) with moth-flame optimization (MFO) methods to predict the axial compressive strength (ACS) of concrete filled double skin steel tubes (CFDST) columns. The proposed model is trained and tested with a dataset containing 125 tests of the CFDST column subjected to compressive loading. Five ML models, including extreme gradient boosting (XGBoost), gradient tree boosting (GBT), categorical gradient boosting (CAT), support vector machines (SVM), and decision tree (DT) algorithms, are utilized in this work. The MFO algorithm is applied to find optimal hyperparameters of these ML models and to determine the most effective model in predicting the ACS of CFDST columns. Predictive results given by some performance metrics reveal that the MFO-CAT model provides superior accuracy compared to other considered models. The accuracy of the MFO-CAT model is validated by comparing its predictive results with existing design codes and formulae. Moreover, the significance and contribution of each feature in the dataset are examined by employing the SHapley Additive exPlanations (SHAP) method. A comprehensive uncertainty quantification on probabilistic characteristics of the ACS of CFDST columns is conducted for the first time to examine the models' responses to variations of input variables in the stochastic environments. Finally, a web-based application is developed to predict ACS of the CFDST column, enabling rapid practical utilization without requesting any programing or machine learning expertise.