Accurate forecasting of construction material prices is essential for effective cost control and risk management in construction projects. However, due to the influence of various complex factors, building material prices exhibit high nonlinearity and instability, often making traditional prediction methods inadequate for achieving optimal results. This study introduces an innovative prediction model, CEEMDAN-VMD-GRU-ARIMA, specifically designed for forecasting the price of prestressed steel bars. This model uniquely combines CEEMDAN and VMD to address nonlinear characteristics, and it innovatively incorporates sample entropy for the adaptive selection of either GRU or ARIMA for prediction. Additionally, a VMD decomposition mode number K value optimization method, based on a sparse index, is proposed. Experimental results demonstrate that the model performs exceptionally well, achieving an adjusted R-squared value of 81.10%, with various error indicators significantly surpassing the results for the baseline model. This approach offers new insights for short-term price prediction of building materials and contributes to enhancing the economic benefits and management efficiency of construction projects.

Accurate forecasting of construction material prices is essential for effective cost control and risk management in construction projects. However, due to the influence of various complex factors, building material prices exhibit high nonlinearity and instability, making traditional prediction methods often inadequate for achieving optimal results. This study introduces an innovative prediction model, CEEMDAN-VMD-GRU-ARIMA, specifically designed for forecasting the price of prestressed steel bars. This model uniquely combines CEEMDAN and VMD to address nonlinear characteristics, and it innovatively incorporates sample entropy for the adaptive selection of either GRU or ARIMA for prediction. Additionally, a VMD decomposition mode number K value optimization method based on a sparse index is proposed. Experimental results demonstrate that the model performs exceptionally well, achieving an Adjusted R-squared value of 0.81, with various error indicators significantly surpassing those of the baseline model. This approach offers new insights for short-term price prediction of building materials and contributes to enhancing the economic benefits and management efficiency of construction projects.

The safe and stable operation of hydropower units, as core equipment in clean energy systems, is crucial for power system security. However, anomaly detection under complex operating conditions remains a technical challenge in this field. This paper proposes a hydropower unit anomaly detection method based on K-means seeded quadratic discriminant clustering and an adaptive density-aware ensemble anomaly detection algorithm (KSQDC-ADEAD). The method first employs the KSQDC algorithm to identify different operating conditions of hydropower units. By combining K-means clustering’s initial partitioning capability with quadratic discriminant analysis’s nonlinear decision boundary construction ability, it achieves the high-precision identification of complex nonlinear condition boundaries. Then, an ADEAD algorithm is designed, which incorporates local density information and improves anomaly detection accuracy and stability through multi-model ensemble and density-adaptive strategies. Validation experiments using 14-month actual operational data from a 550 MW unit at a hydropower station in Southwest China show that the KSQDC algorithm achieves a silhouette coefficient of 0.64 in condition recognition, significantly outperforming traditional methods, and the KSQDC-ADEAD algorithm achieves comprehensive scores of 0.30, 0.34, and 0.23 for anomaly detection at three key monitoring points, effectively improving the accuracy and reliability of anomaly detection. This method provides a systematic technical solution for hydropower unit condition monitoring and predictive maintenance.

Improving water resource utilization efficiency is crucial for balancing economic development, resource conservation, and environmental protection in large river basins. This study develops a measurement prediction-optimization framework for 11 provincial-level regions in the Yangtze River Basin from 2010 to 2023. A super-efficiency epsilon-based measure model with undesirable outputs is used to measure efficiency and identify spatiotemporal patterns. An adaptive particle swarm optimization–LightGBM model is developed for efficiency prediction, with SHAP used to interpret key drivers. A constrained multi-objective particle swarm optimization model optimizes fixed asset investment, labor input, and total water use. The results show that basin-wide efficiency increased from 0.269 in 2010 to 0.732 in 2023, showing lower-reach leadership, upper-reach catch-up, and middle-reach differentiation. The APSO-LightGBM model achieved a test R² of 0.894 and an RMSE of 0.093, with GDP, wastewater discharge, and total water use as the main contributors. Optimization generated feasible solutions for all 154 observations, increasing average predicted efficiency from 0.410 to 0.435 while reducing fixed asset investment, labor input, and water use by 4.26%, 1.81%, and 6.88%, respectively. Sensitivity analyses indicate that the resource adjustments depend on the solution-selection threshold and empirical bounds, especially for investment and employment. The results describe conditional input-saving opportunities rather than directly achievable policy targets.

Cross-domain intrusion detection is essential for securing heterogeneous Internet of Things (IoT) deployments. However, detectors trained in one environment degrade sharply under domain shift, which arises from systematic differences in protocols, device types, and network architectures across IoT domains. Existing approaches typically focus on single-domain training or require explicit feature alignment, both of which limit practical deployment. To address this, this paper presents a systematic multi-domain benchmark on a public IoT adaptation dataset comprising 7,000 labeled traffic samples with 39 features spanning six domains, and proposes the Maximum Mean Discrepancy-Weighted Ensemble (MMD-WE), a multi-source ensemble that weights per-domain XGBoost classifiers by Maximum Mean Discrepancy (MMD)-derived similarity scores without any explicit feature alignment. CORAL (Correlation Alignment), a widely used second-order domain adaptation method, serves as a baseline for comparison. In-domain detection reaches 92.86% accuracy and an area under the ROC curve (AUC) of 0.9825; single-source cross-domain transfer yields off-diagonal accuracies ranging from 89.6% to 93.7%; and in leave-one-domain-out multi-source adaptation, MMD-WE attains 92.80% average accuracy, marginally exceeding a pooled multi-source baseline of 92.69% and significantly outperforming a CORAL-aligned variant of 92.22%. Analysis with SHapley Additive exPlanations (SHAP) further shows that adaptation-aware features, led by communication reliability and payload entropy, dominate predictions, and that the dataset’s adaptation status stratifies risk: attack prevalence rises from 2.9% under low shift to 81.8% under high shift. These findings support shift-aware alert triage and label-free deployment of robust IoT intrusion detectors.