http://bura.brunel.ac.uk/handle/2438/8628 2026-03-26T07:13:21Z http://bura.brunel.ac.uk/handle/2438/32906 Title: Fair Benchmarking in Short‐Term Load Forecasting Authors: Xing, L; Kaheh, Z Abstract: Performance comparisons in short-term load forecasting are often confounded by differences in preprocessing pipelines rather than reflecting intrinsic architectural capability. Variations in feature engineering, scaling, temporal windowing and data partitioning can dominate reported accuracy and obscure the actual behaviour of forecasting models. This study examines preprocessing–architecture interaction by benchmarking random forest, LightGBM, long short-term memory (LSTM), transformer and Temporal Fusion Transformer (TFT) under a shared tabular preprocessing pipeline, ensuring strict control over data handling and evaluation conditions. Under this controlled setting, tree-based models exhibit strong predictive performance, whereas deep sequence models experience substantial degradation when temporal continuity is not explicitly represented. To isolate architectural sensitivity from preprocessing effects, we further conduct a within-architecture analysis by retraining an identical LSTM under a sequence-aware pipeline aligned with its temporal inductive bias. This realignment yields an order-of-magnitude reduction in RMSE, demonstrating that preprocessing design is a first-order determinant of deep sequence model performance. The results establish a transparent and reproducible benchmarking framework and highlight the importance of aligning data representation with model assumptions when interpreting comparative performance in time series forecasting. Description: Data Availability Statement: The data that support the findings of this study are available from the corresponding author upon reasonable request. 2026-02-24T00:00:00Z http://bura.brunel.ac.uk/handle/2438/32488 Title: Quantile regression and smoothed empirical likelihood for non-ignorable missing data based on semi-parametric response models Authors: Guo, J; Pan, J; Yu, K; Tang, ML; Tian, M Abstract: In the context of quantile regression with non-ignorable missingness in the response variable, we introduce a semi-parametric exponential tilting model that captures the missingness propensity. To address this, we propose three convolution smoothing-based estimators for quantile regression: inverse probability weighting (IPW), estimation equation imputation (EEI), and augmented IPW (AIPW). These estimators provide consistent estimates for quantile regression coefficients, utilizing the framework of empirical likelihood. We establish theoretical results regarding the asymptotic normality of the three quantile regression estimators, as well as the chi-square property of the corresponding adjusted logarithmic empirical likelihood ratios. Furthermore, we conduct numerical simulations to evaluate the finite-sample performance of these estimators, demonstrating their robustness. To further illustrate the effectiveness of the proposed methods, we apply them to HIV-CD4 data. This application allows us to investigate the differential impact of missing data mechanisms across treatment groups and explore the influence of baseline and previous CD4 and CD8 cell levels on current CD4 cell levels.; 摘要 在分位回归的响应变量存在不可忽略缺失的情形下,本文引入半参数指数倾斜模型刻画应答概率, 在此基础上提出 3 种卷积平滑分位数回归估计方程: 逆概率加权 (inverse probability weighting, IPW)、估计方程插补 (estimation equation imputation, EEI) 和增强逆概率加权 (augmented IPW, AIPW), 并在经验似然框架下得到倾斜参数和分位回归系数的估计量. 本文在理论上证明3种分位回归估计量等价的渐近正态性和对应调整对数经验似然比函数的渐近χ2性质. 数值模拟比较上述估计量的有限样本表现,验证估计量的稳健性. 本文所提出的方法被应用于CD4(clusterofdifferentiation 4) 数据分析,考察不同治疗组中缺失机制的差异以及基线和前期的CD4和CD8细胞水平对当期CD4细胞水平的影响. Description: MSC (2020) 主题分类 62G05, 62G08 2024-06-05T00:00:00Z http://bura.brunel.ac.uk/handle/2438/32367 Title: Optimality and solutions for conic robust multiobjective programs Authors: Chuong, TD; Yu, X; Eberhard, A; Li, C; Liu, C Abstract: This paper presents a robust framework for handling a conic multiobjective linear optimization problem, where the objective and constraint functions are involving affinely parameterized data uncertainties. More precisely, we examine optimality conditions and calculate efficient solutions of the conic robust multiobjective linear problem. We provide necessary and sufficient linear conic criteria for efficiency of the underlying conic robust multiobjective linear program. It is shown that such optimality conditions can be expressed in terms of linear matrix inequalities and second-order conic conditions for a multiobjective semidefinite program and a multiobjective second order conic program, respectively. We show how efficient solutions of the conic robust multiobjective linear problem can be found via its conic programming reformulation problems including semidefinite programming and second-order cone programming problems. Numerical examples are also provided to illustrate that the proposed conic programming reformulation schemes can be employed to find efficient solutions for concrete problems including those arisen from practical applications. Description: The authors would like to thank the referees for valuable comments and suggestions. Research was supported by a research grant from Australian Research Council under Discovery Program Grant DP200101197. The main results of this paper were presented at the 5th IMA and OR Society Conference on Mathematics of Operational Research (Birmingham, United Kingdom, 2025), and the first author would like to acknowledge the support of the Mid and Early Career Academic Research Support Scheme (Brunel University of London, United Kingdom, 2024-2025), which made this possible.; Mathematics Subject Classification: 65K10; 49K99; 90C46; 90C29. 2025-10-21T00:00:00Z http://bura.brunel.ac.uk/handle/2438/32366 Title: Decomposition for Large-Scale Optimization Problems: An Overview Authors: Chuong, TD; Liu, C; Yu, X Abstract: Formalizing complex processes and phenomena of a real-world problem may require a large number of variables and constraints, resulting in what is termed a large-scale optimization problem. Nowadays, such large-scale optimization problems are solved using computing machines, leading to an enormous computational time being required, which may delay deriving timely solutions. Decomposition methods, which partition a large-scale optimization problem into lower-dimensional subproblems, represent a key approach to addressing time-efficiency issues. There has been significant progress in both applied mathematics and emerging artificial intelligence approaches on this front. This work aims at providing an overview of the decomposition methods from both the mathematics and computer science points of view. We also remark on the state-of-the-art developments and recent applications of the decomposition methods, and discuss the future research and development perspectives. 2025-09-01T00:00:00Z