Credit scoring is an efficient tool for financial institutions to implement credit risk management. In recent years, many novel machine learning models have been developed for credit scoring. Among the existing machine learning models, the heterogeneous ensemble model receives much attention because of its superior performance. This paper presents a new heterogeneous ensemble model based on the generalized Shapley value and the Choquet integral. To do this, the model first uses the fuzzy measure to express the interactive characteristics between any two coalitions of base learners. Based on the accuracy and diversity objective function, a linear programming model for determining the fuzzy measure is built. To retain the original information as much as possible in the training stage, the normal fuzzy number is employed to express the base learner predicted values. Then, the generalized Shapley Choquet integral (GSCI) aggregation operator is defined to calculate the comprehensive predicted value of the ensemble model. Based on the defined aggregation operator and linear programming model, a GSCI approach is proposed for ensemble credit scoring. To illustrate the efficiency and feasibility of the GSCI approach, an experiment of thirteen machine learning models over four public credit scoring datasets and three real-world P2P leading datasets with large volumes of samples is made. Furthermore, robust tests and comparatives analysis are made to demonstrate the adaptability and performance of the GSCI-based ensemble model.

The scientific and reasonable evaluation of the carrying capacity of water resources is of guiding significance for solving the issues of water resource shortages and pollution control. It is also an important method for realizing the sustainable development of water resources. Aiming at an evaluation of the carrying capacity of water resources, an evaluation model based on the cloud model theory and evidential reasoning approach is studied. First, based on the existing indicators, a water resources evaluation index system based on the pressure-state-response (PSR) model is constructed, and a classification method of carrying capacity grade is designed. The cloud model theory is used to realize the transformation between the measured value of indicators and the degree of correlation. Second, to obtain the weight of the evaluation index, the weight method of the index weights model based on the entropy weight method and evidential reasoning approach is proposed. Then, the reliability distribution function of the evaluation index and the graded probability distribution of the carrying capacity of water resources are obtained by an evidential reasoning approach. Finally, the evaluation method of the carrying capacity of water resources is constructed, and specific steps are provided. The proposed method is applied to the evaluation of water resources carrying capacity for Hunan Province, which verifies the feasibility and effectiveness of the method proposed in the present study. This paper applies this method of the evaluation of the water resources carrying capacity of Hunan Province from 2010 to 2019. It is concluded that the water resources carrying capacity of Hunan Province belongs to III~V, which is between the critical state and the strong carrying capacity state. The carrying capacity of the province’s water resources is basically on the rise. This shows that the carrying capacity of water resources in Hunan Province is in good condition, and corresponding protective measures should be taken to continue the current state.

Accurate residential load forecasting is crucial for the stable operation of the energy internet, which plays a significant role in advancing sustainable development. As the construction of the energy internet progresses, the proportion of residential electricity consumption in end-use energy consumption is increasing, the peak load on the grid is growing year on year, and seasonal and regional peak power supply tensions, mainly for household electricity consumption, grow into common problems across countries. Residential load forecasting can assist utility companies in determining effective electricity pricing structures and demand response operations, thereby improving renewable energy utilization efficiency and reducing the share of thermal power generation. However, due to the randomness and uncertainty of user load data, forecasting residential load remains challenging. According to prior research, the accuracy of residential load forecasting using machine learning and deep learning methods still has room for improvement. This paper proposes an improved load-forecasting model based on a time-localized attention (TLA) mechanism integrated with LSTM, named TLA-LSTM. The model is composed of a full-text regression network, a date-attention network, and a time-point attention network. The full-text regression network consists of a traditional LSTM, while the date-attention and time-point attention networks are based on a local attention model constructed with CNN and LSTM. Experimental results on real-world datasets show that compared to standard LSTM models, the proposed method improves R² by 14.2%, reduces MSE by 15.2%, and decreases RMSE by 8.5%. These enhancements demonstrate the robustness and efficiency of the TLA-LSTM model in load forecasting tasks, effectively addressing the limitations of traditional LSTM models in focusing on specific dates and time-points in user load data.

With the proliferation of distributed energy resources, advanced metering infrastructure, and advanced communication technologies, the grid is transforming into a flexible, intelligent, and collaborative system. Short-term electric load forecasting for individual residential customers is playing an increasingly important role in the operation and planning of the future grid. Predicting the electrical load of individual households is more challenging with higher uncertainty and volatility at the household level compared to the total electrical load at the feeder and regional levels. The previous research results show that the accuracy of forecasting using machine learning and a single deep learning model is far from adequate and there is still room for improvement.

The alignment of Image Quality Assessment (IQA) models with diverse human preferences remains a challenge, owing to the variability in preferences for different types of visual content, including user-generated content and AI-Generated Content (AIGC), etc. Despite the significant success of existing IQA methods in assessing specific visual content by leveraging knowledge from pre-trained models, the intricate factors impacting final ratings and the specially designed network architecture of these methods result in gaps in their ability to accurately capture human preferences for novel visual content. To address this issue, we propose Align-IQA, a novel framework that aims to generate visual quality scores aligned with diverse human preferences for various types of visual content. Align-IQA contains two key designs: (1) A customizable quality-aware guidance injection module. By injecting specializable quality-aware prior knowledge into general-purpose pre-trained models, the proposed module guides the acquisition of quality-aware features and allows for various adjustments of features to be consistent with diverse human preferences for different types of visual content. (2) A multi-scale feature aggregation module. By simulating the multi-scale mechanism in the human visual system, the proposed module enables the extraction of a more comprehensive representation of quality-aware features from the human perception perspective. Extensive experimental results demonstrate that Align-IQA achieves better or comparable performance to State-Of-The-Art (SOTA) methods. Notably, Align-IQA outperforms the previous best results on AIGC datasets, achieving Pearson's Linear Correlation Coefficients (PLCCs) of 0.890 (+3.73%) on AGIQA-1K and 0.924 (+1.99%) on AGIQA-3K. Additionally, Align-IQA reduces training parameters by 72.26% and inference overhead by 78.12%, while maintaining SOTA performance.

Water pollution prevention and control of the Xiang River has become an issue of great concern to China's central and local governments. To further analyze the effects of central and local governmental policies on water pollution prevention and control for the Xiang River, this study performs a big data analysis of 16 water quality parameters from 42 sections of the mainstream and major tributaries of the Xiang River, Hunan Province, China from 2005 to 2016. This study uses an evidential reasoning-based integrated assessment of water quality and principal component analysis, identifying the spatiotemporal changes in the primary pollutants of the Xiang River and exploring the correlations between potentially relevant factors. The analysis showed that a series of environmental protection policies implemented by Hunan Province since 2008 have had a significant and targeted impact on annual water quality pollutants in the mainstream and tributaries. In addition, regional industrial structures and management policies also have had a significant impact on regional water quality. The results showed that, when examining the changes in water quality and the effects of pollution control policies, a big data analysis of water quality monitoring results can accurately reveal the detailed relationships between management policies and water quality changes in the Xiang River. Compared with policy impact evaluation methods primarily based on econometric models, such a big data analysis has its own advantages and disadvantages, effectively complementing the traditional methods of policy impact evaluations. Policy impact evaluations based on big data analysis can further improve the level of refined management by governments and provide a more specific and targeted reference for improving water pollution management policies for the Xiang River.