Information Entropy Method Research Articles

Approaches to multiple attribute group decision making under interval-valued pythagorean fuzzy sets and applications to environmental design majors teaching quality evaluation

The environmental design major has certain practical characteristics. In the teaching process, it is necessary to effectively combine practical methods and theoretical knowledge in order to improve the overall quality and efficiency of education to a certain extent. The most important training measure currently is project-based teaching method, which has also been recognized by many researchers. The environmental design majors teaching quality evaluation is a classical multiple-attribute group decision-making (MAGDM). Recently, the Taxonomy has been used to cope with MAGDM problems. The interval-valued Pythagorean fuzzy sets (IVPFSs) are useful tools to depict uncertainty in MAGDM. This paper use Taxonomy method to solve MAGDM with IVPFSs. Firstly, the concepts of IVPFSs are presented. Then, the classical Taxonomy method is used to solve MAGDM with IVPFSs. Finally, a numerical example for environmental design majors teaching quality evaluation is proposed and a comparative analysis is also given to show the developed approach. The main study motivations of built paper are outlined: (1) the Taxonomy method is extended to IVPFSs; (2) the score function of IVPFSs and information entropy method is used to derive the attribute weights; (3) the interval-valued Pythagorean fuzzy Taxonomy (IVPF-Taxonomy) method is built to deal with MAGDM; (4) a case study about environmental design majors teaching quality evaluation is given to show the built method; (5) some comparative analysis are given to show the rationality of IVPF-Taxonomy method.

A novel evaluation method of renewable energy development based on improved rough set theory and grey cloud model

Renewable energy is an effective solution to alleviate the energy crisis and achieve sustainable development, and is gradually growing into an important energy source to support economic and social development. Different renewable energy technical plans have different characteristics under multiple criteria. Therefore, before the further exploitation of renewable energy sources, it is of great significance to evaluate the comprehensive performance of different plans and then determine the best renewable energy sources. Given this background, this paper proposes a novel evaluation method for renewable energy technical plans based on improved rough set theory and grey cloud model. Firstly, based on the normalized evaluation data, self-organizing map (SOM) clustering algorithm and system clustering analysis are adopted to discretize the evaluation attributes indexes and decision attributes indexes, respectively. Next, the improved rough set conditional information entropy method is used to calculate the index weights. Finally, the grey cloud model is employed to determine the grade classification of each evaluated plan. At the same time, each grade is quantified by assigning a corresponding score, and the comprehensive performances of renewable energy plans can be calculated, and then the ranking of different plans is achieved. Based on the actual renewable energy development data from a province in China, experiments were carried out to evaluate the performance of the proposed method. The results show that the proposed method performs better than some evaluation methods for renewable energy technical plans.

Evaluation of ecological buffer zone based on landscape pattern for non-point source pollution control: A case study in Hanjiang River basin, China

The deterioration of ecological environment caused by non-point source pollution (NPS) has seriously threatened human health and socioeconomic development. Effective identification of critical source areas and selecting appropriate best management practices (BMPs) for watersheds are the keys to controlling NPS. This paper, using Hanjiang River basin, the vital water source for the South-to-North Water Division, China, as a case study, presents a method for accurate critical source areas dentification according to the spatial distribution characteristics of underlying surface and pollution load by coupling NPS risk index (NPPRI), Minimum Cumulative Resistance (MCR) Model, and Soil and Water Assessment Tool (SWAT). In this research, ten single and three combined scenarios are set up in the critical source areas, including three non-engineering management practices, two engineering management practices, and five ecological buffer zones. Finally, the effect of BMPs for non-point source pollution is assessed by using landscape pattern theory and information entropy method. Furthermore, the influences of the five ecological buffer zones on the characteristics of landscape in watershed and the response relationship between the landscape pattern and NPS are analyzed. The following findings are obtained: (1) The critical source areas were mainly located in the south-central and southeastern part of the study area, accounting for 35.9 % of the total watershed area, and yielding 54.2 % and 60.7 % of the total nitrogen(TN) and total phosphorus(TP) loads in the watershed; (2) All ecological buffer zones play a positive role in NPS control with an average reduction rate of 32.1 % for TN and 46.7 % for TP, and the control effectiveness for TP are better than that for TN; (3) The deployment of the five ecological buffer zones have a significant impact on the interspersion juxtaposition index (IJI), the connectivity of the “sink” landscape is enhanced, the diversity of the “source” landscape is reduced and the “sink” landscape’s ability of interception is boosted; (4) The calculation result of information entropy shows the highest attribute value of practices in the ecological buffer zones is Buffer 200 m. Overall, the findings serve as a reference for NPS control and water environment management in the watershed and strengthen the feasibility of implementing of BMPs in the watershed.

A novel method for solving “Entrepreneurship and Entrepreneurship” career ability evaluation of local college students with triangular neutrosophic numbers

With the proposal of the “Double First Class” construction concept in Chinese universities, cultivating high-quality talents has become the main direction of university education. At present, local universities in China are actively adapting to the changes of the times, taking the construction of the Double First Class as an opportunity, continuously adjusting and deepening the reform of the double innovation and innovation talent cultivation mode, further improving the curriculum system, increasing investment in professional practical teaching, stimulating students’ enthusiasm for innovation and entrepreneurship (IAE), and focusing on improving students’ comprehensive abilities, achieving significant results in talent cultivation. The “Entrepreneurship and Entrepreneurship” career ability evaluation of local college students could be considered as multiple attribute decision-making (MADM). Recently, the Combined Compromise Solution (CoCoSo) method and information entropy method was employed to deal with MADM. The triangular fuzzy neutrosophic sets (TFNSs) are employed as a better tool for expressing uncertain information during the “Entrepreneurship and Entrepreneurship” career ability evaluation of local college students. In this paper, the triangular fuzzy neutrosophic number CoCoSo (TFNN-CoCoSo) based on the Hamming distance and Euclid distance is constructed to cope with the MADM under TFNSs. The information entropy method is employed to compute the weight values based on the Hamming distance and Euclid distance under TFNSs. Finally, a numerical example of “Entrepreneurship and Entrepreneurship” career ability evaluation of local college students is constructed and some decision comparisons are constructed to verify the TFNN-CoCoSo method.

Regional sustainable and renewable energy development in China: A comprehensive assessment and influencing factors

In order to address regional energy imbalances, it is necessary to assess Sustainable and Renewable Energy (SRE) development and to explore its influencing factors. However, existing literature only focused on one part of the aforementioned solutions, and remained controversial, especially in China. Based on provincial panel data from 2005 to 2020 in China, this study utilized the information entropy method to construct a comprehensive evaluation system for regional SRE development, and a panel model with fixed effects was established, with this composite score as the dependent variable, and with economic, demographic, environmental, and technological factors as independent variables. The results showed regional SRE development deepened from the western to the eastern part of China, and over time. The empirical evidence indicated that the significant positive predictors of SRE development were disposable income per capita, dependency ratio, urbanization rate, railroad mileage, and technology market turnover while the value added of secondary sectors had a significant negative impact on SRE development. No empirical evidence supported the significant association between chemical oxygen demand emissions and SRE development. The founding can provide data support and theory references for policymakers of energy sectors.

Optimal planning of distributed generation and energy storage systems in DC distribution networks with application of category-based multi-objective algorithm

The strategic positioning and appropriate sizing of Distributed Generation (DG) and Battery Energy Storage Systems (BESS) within a DC delivery network are crucial factors that influence its economic feasibility and dependable performance. To tackle this vital aspect, we have formulated a multi-objective optimization model aimed at determining the most advantageous locations and capacities for DG and BESS. Our approach establishes a framework for multi-objective optimization that systematically addresses all objectives, minimizing bias towards any specific set of objectives and enhancing overall efficiency. Furthermore, from a variety of collective objectives we introduce an improved Multi-Objective Particle Swarm Optimizer (IMOPSO) tailored to produce and choose Pareto best solutions. To identify the best placement and sizing options for DG and BESS among the Pareto optimal solutions, we apply the Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) strategy, integrating an information entropy method. We have conducted simulations using the 33-bus DC distribution grid of IEEE to validate the practical benefits of our suggested methodology.

A novel group decision making model based on Interval neutrosophic sets for product modeling design quality evaluation

The energy consumption of mechanical products in China is enormous, and the energy utilization rate is low, which is increasingly receiving people’s attention. Conducting product design for energy optimization is of great significance for improving energy utilization efficiency. The scheme design of a product is the key to achieving innovation in product design, and the evaluation and decision-making of the design scheme directly affect the results of the later stage of the design. Therefore, correctly evaluating and making reliable decisions on product design schemes that are oriented towards fuzzy decision optimization is an important aspect of product innovation conceptual design. The product modeling design quality evaluation is a multiple attribute group decision making (MAGDM) problems. Recently, the Combined Compromise Solution (CoCoSo) method and information entropy method has been employed to cope with MAGDM issues. The interval neutrosophic sets (INSs) are employed as a tool for portraying uncertain information during the product modeling design quality evaluation. In this paper, the CoCoSo method is designed for MAGDM under INSs. Then, the interval neutrosophic numbers CoCoSo (INN-CoCoSo) method based on the Hamming distance and Euclidean distance is built for MAGDM. The information Entropy method is employed to produce the weight information based on the Hamming distance and Euclidean distance under INNSs. Finally, a practical numerical example for product modeling design quality evaluation is supplied to show the INN-CoCoSo method. The main contributions of this paper are constructed: (1) This paper builds the novel MAGDM based on CoCoSo model under INSs; (2) The information Entropy method is employed to produce the weight information based on the Hamming distance and Euclidean distance under INNSs; (3) The new MAGDM method is proposed for product modeling design quality evaluation based on INN-CoCoSo.

Competitiveness Evaluation of Express Delivery Enterprises Based on the Information Entropy and Gray Correlation Analysis

With the rise of e-commerce in China, the express delivery industry has developed rapidly; however, in this stage of rapid growth, the development of express delivery enterprises is uneven. There are problems such as high loss, damage rates, and poor service attitudes. An evaluation of the competitiveness of express delivery enterprises can help these companies understand their shortcomings and learn from each other’s strengths, which can promote the long-term development of express delivery enterprises. In this study, the information entropy method and the gray prediction method were used to establish an index system and analyze the core competitiveness of four listed express delivery companies in China, using indicators such as service quality, price level, market position, guarantee ability, and comprehensive strength; the purpose was to study the competitive advantages of these express companies. By using the gray correlation analysis to calculate the degree of correlation and comparing the size of the degree of correlation, it can be concluded that among the four express delivery companies, ZTO Express shows the strongest competitiveness and that Shentong Express is the weakest. Through the evaluation and analysis of the competitiveness of express delivery enterprises, this study provides a reference basis for operation development and competitiveness improvement of express delivery enterprises in China.

An Enhanced Multi-Constraint Optimization Algorithm for Efficient Network Topology Generation

In order to address a problem in the research related to the low stability and communication efficiency issues in the generation of optical communication constellation network topology, there is a critical component for sensing the interaction among satellites. This paper makes a novel contribution by proposing a multi-constraint optimization algorithm for optical communication constellation network topology generation. The proposed method significantly improves the existing systems by considering multiple attributes that influence the establishment of inter-satellite links and reducing the impact of subjective factors. This unique approach involves calculating the entropy weight of each attribute using the information entropy method based on the degree of change in each indicator. Subsequently, the weights of the indicators are corrected to obtain the objective weight of each attribute. The comprehensive weight of the link, computed based on the initial link attribute values and weights, serves as the decision basis for link selection, thereby forming the satellite network topology. Upon evaluation, the proposed method has shown remarkable superiority over the compared schemes in terms of communication efficiency and stability.

Spatiotemporal Evolution, Coupling Coordination Degree and Obstacle Factors of Urban High-Quality Development: A Case Study of Anhui Province

Anhui Province is located in the superposition area of the “Strategy of the Rise of Central China” and the “Strategy of Integrated Development of the Yangtze River Delta”. Analyzing the high-quality development of Anhui Province is crucial for regional development. This paper proposes a comprehensive evaluation system based on the “New development philosophy”. Then, the information entropy method is applied to measure the high-quality development index (HQDI). The Markov transition probability matrix is used to explore the evolutionary trend of the HQDI. This paper also analyzes the coupling coordination relationships between high-quality development subsystems. Finally, the obstacle factor diagnostic model is adopted to find the factors that impede high-quality development. The result shows that: (1) There exists a significant spatial gradient difference in Anhui Province. The overall spatial distribution of the HQDI shows a pattern of “high in the central and east, low in the north and south”. (2) The “club convergence effect” and the “Matthew effect” of urban high-quality development are observed. (3) Subsystem analysis verified the existence of regional differences. Hefei has the leading position in all development subsystems. (4) The coupling coordination degree of subsystems is relatively low, and the problem of disorder development within Anhui Province is significant. (5) The fixed assets’ investment, the total amount of imports and exports, the GDP, the total urban wastewater treatment and the urban road passenger volume are the main obstacle factors.

Modified GRA method for probabilistic hesitant fuzzy MAGDM and application to network health performance evaluation of radial distribution system

Radial distribution system is an important link connecting power supply and users, and its power supply reliability is directly related to users. Radial distribution network reconfiguration can transform the network structure by changing the switching state of the distribution network lines, and achieve the goals of reducing network operational losses, improving power quality, and power supply reliability while meeting various constraints such as radial operation, power supply and demand balance, capacity, and voltage. Radial distribution systems have the characteristics of multiple components and complex structures. How to quickly and accurately evaluate the health performance of radial distribution systems and find an optimal solution for network reconfiguration are important issues in distribution network analysis. The network health performance evaluation of radial distribution system is classical multiple attributes group decision making (MAGDM). The probabilistic hesitancy fuzzy sets (PHFSs) are used as a tool for characterizing uncertain information during the network health performance evaluation of radial distribution system. In this paper, we extend the classical grey relational analysis (GRA) method to the probabilistic hesitancy fuzzy MAGDM with unknown weight information. Firstly, the basic concept, comparative formula and Hamming distance of PHFSs are briefly introduced. Then, the definition of the score values is employed to compute the attribute weights based on the information entropy method. Then, probabilistic hesitancy fuzzy GRA (PHF-GRA) method is built for MAGDM under PHFSs. Finally, a practical case study for network health performance evaluation of radial distribution system is designed to validate the proposed method and some comparative studies are also designed to verify the applicability.

Multi-objective optimization of mechanical and microstructural characteristics in a stir casting process of MWCNTs/Al6082 composites using neutrosophic TOPSIS and GRA

ABSTRACT The objective of this paper is to find optimum process parameters of stir casting process for multi-walled carbon nanotubes (MWCNTs) reinforced Al6082 composites in a multi-objective optimization context. In this work, output parameters include ultimate tensile strength (UTS), hardness, compressive strength (CS), and uniform distribution of MWCNTs. Among these, first three parameters can be measured, and data can be obtained in quantitative terms. However, uniformity of distribution of MWCNT is a qualitative variable, and hence neutrosophic sets are used in this work. Each of the four input process parameters, such as fraction weight of MWCNTs, stirring speed, furnace temperature, and stirring time, are taken at three levels each, and experiments are designed using Taguchi L27 array. Information entropy method is used to compute the weights of output parameters. TOPSIS method is used to normalize the quantitative data, and neutrosophic TOPSIS is applied for normalizing the data related to uniformity. It is found that MWCNT’s percentage of 0.9, speed of 450 rpm, temperature of 800°C, and time of 10 minutes, yield best output parameters. Neutrosophic gray relational analysis is also used to find optimum solution for above case, and the optimum values obtained from both methods are compared.

Assessing capacity to deploy direct air capture technology at the country level – an expert and information entropy comparative analysis

An ever-dwindling carbon budget, resulting in temperature rise of 1.5 °C above pre-industrial levels projected between 2030–2035, has generated a necessity to explore climate mitigation technologies such as direct air capture (DAC). DAC typically involves the use of materials and energy to capture CO2 directly from the atmosphere. However, DAC technologies remain a long way from the necessary level of development and scale needed to move the needle on carbon removal and mitigating against climate change. This study conducts a country-level analysis using an expert elicitation and an information entropy method, with a weighted group of variables identified from existing literature as necessary to develop and deploy low-temperature, electrochemical and high-temperature DAC technologies. Here we show that: (1) adopting the expert survey variable weighting, USA, Canada, China and Australia are best positioned to deploy the various DAC technologies; (2) the information entropy approach offers a broadly similar result with traditionally developed nations being best positioned, in addition to land rich countries, to deploy DAC technologies; (3) a comparatively developed policy and financing environment, as well as low carbon energy supply would raise a country’s DAC capacity; (4) developing countries such as China have significant potential to deploy DAC, owing to a well-rounded position across variables. These results produce wide-ranging policy implications for efforts to deploy climate mitigation technologies through the development of a multilateral, coordinated mitigation and carbon dioxide removal deployment strategy.

Aerosols characteristics, sources, and drive factors analysis in typical megacities, NW China

Cities in arid and semi-arid regions often confront harsher natural environments and severer industrial pollution. So these are frequently subjected to heavy air pollution, which has critical consequences for the health and production activities and well-being of local citizens. To curb the aggravation of air pollution, the Chinese government conducted an air pollution control action plan with unprecedented strength in September 2013. In this study, based on the fine-resolution aerosol optical depth (AOD) data, combined meteorological and other auxiliary data, utilizing information entropy, backward trajectory, source analysis, and multi-layer perceptron methods, we comprehensively analyzed the spatiotemporal characteristics and variations of AOD in typical arid and semi-arid areas megacities (Lanzhou and Urumqi) from 2010 to 2019, and further explore the potential pollution sources and nature and anthropic influences on AOD. The main results indicate that Lanzhou AOD remains higher than Urumqi in almost all different time windows, especially in the spring. Specifically, the AOD shows a single-peaked distributed trend on the monthly scale, but the peak occurred one month later in Lanzhou than in Urumqi. In the seasons, Lanzhou and Urumqi all show a trend that spring and winter AOD are higher than summer and fall. Lanzhou and Urumqi overall show a tortuous decreasing and then rebounded trend between 2010 and 2019, but the AOD variation in the Urumqi is more dramatic than in Lanzhou. The high AOD mainly concentrates in low altitude areas and there is a downward tendency of AOD in high-AOD areas, but an upward trend in low-AOD areas. The AOD intensity of change is higher in Lanzhou than in Urumqi, but Lanzhou has more concentration. The seasonal differences in backward trajectories are stronger in Lanzhou than in Urumqi, generally, Lanzhou's potential trajectory is mainly distributed in the Hexi Corridor, while Urumqi is along the northern slope of the Tianshan Mountains urban cluster distribution. The potential source area of AOD has a significant seasonal variation, and the closer to the object, the greater the contribution. Generally, Lanzhou pollution is more sensitive to the atmosphere condition and has a wider source area than Urumqi. The AOD was influenced by a combination of natural and anthropogenic factors, but natural variables seem to be more dominant. The impact of natural factors in Urumqi and Lanzhou is statistically obtained up to 75.04% and 52.01% respectively.

Fuzzy evaluation on the integrated benefit of regulated deficit irrigation for pear-jujube tree based on information entropy.

Based on the experimental data of regulated deficit irrigation at different growth stages on field pear-jujube tree (Zizyphus jujube Mill.) during 2005-2007 in Northwest China, the regulated deficit irrigation integrated benefits (RDIIB) with different water deficit treatments at different growth stages were evaluated and classified using a model. The results in 2005-2006 showed that the RDIIB under single-stage water deficit at fruit maturity stage were better than the other treatments, and the best RDIIB were gained under moderate (IVSD) or severe deficit (IVMD) at fruit maturity stage. The results in 2006-2007 also indicated that the four double-stage water deficit schemes have the better RDIIB, and the best scheme was severe water deficit at bud burst to leafing stage plus moderate water deficit at fruit maturity stage. The RDIIB evaluation model based on information entropy method provided the reliable technical guidance for the optimal RDI scheme of pear-jujube tree.

A Novel Fault Diagnosis of a Rolling Bearing Method Based on Variational Mode Decomposition and an Artificial Neural Network

In recent years, artificial neural networks have been widely used in the fault diagnosis of rolling bearings. To realize real-time diagnosis with high accuracy of the fault of a rolling bearing, in this paper, a bearing fault diagnosis model was designed based on the combination of VMD and ANN, which ensures a higher fault prediction accuracy with less computational time. This paper works from two aspects, including fault feature extraction and neural network structural parameter optimization to obtain an ANN bearing fault diagnosis model with high performance. The raw vibration signals of 10 fault types were divided into training, verification and testing datasets by the random step increment slip method. The variational mode decomposition method was used to decompose the raw vibration signal into several intrinsic mode functions. A new definition of the energy of each intrinsic mode function based on discrete Fourier transform and information entropy method were used as the input for the artificial neural network. Furthermore, the structural parameters of the artificial neural network were designed to obtain a high-performance neural network. The artificial neural network used in this paper had three hidden layers and 13 neurons in each hidden layer. Compared with several machine and deep learning algorithms, the artificial neural network can better fulfill the classification task of rolling bearing fault types with a mean prediction accuracy of 99.3% and computation time of 2.4 s based on a small training dataset.

Identification and prediction of mixed-use functional areas supported by POI data in Jinan City of China

The urban development of China is changing from incremental expansion to stock renewal mode. The study of urban functional areas has become one of the important fundamental works in current urban renewal and high-quality urban development. In recent years, big spatiotemporal data has been well applied in the urban function field. However, the study of spatial–temporal evolution characteristics and forecasting optimization for mixed-use urban functional areas has not been examined well. Thus, in this study, we proposed a new approach that applies a revised information entropy method to analyze the degrees of mixing for urban functional areas. We applied our approach in Jinan City, Shandong Province as the study area. We used Point-of-Interest, OpenStreetMap and other datasets to identify the mixed-use urban functional areas in Jinan. Then, the CA–Markov model simulated the urban layout in 2025. The results showed that: (1) the combination of road network and kernel density method has the highest accuracy of identifying urban functional areas. (2)The mixing degree model is constructed by using the improved information entropy, which makes up for the shortcoming of identifying the mixed functional areas simply by the frequency ratio of POI data. (3) The “residence and business” functional area has the highest proportion in the central area of Jinan from 2015 to 2020, and the total area of mixed-use unban functional areas continuously increased during this period. (4) The total area of the central area in Jinan has significantly increased in 2025. The optimization of urban functions should expand mixed-use functional areas and increase the proportion of infrastructure. Also, Jinan should improve the efficiency of space development.

Spatiotemporal evolution analysis of human disturbances on giant panda: A new approach to study cumulative influences with large spatial scales

The disturbance of wildlife habitats by human activities has become an important driving force in the evolution of ecological landscapes. However, human disturbances in panda habitats are highly diverse and complex. To study the changes in the temporal and spatial dynamics of human disturbances affecting panda populations, an analysis model for the evolution of human interference was designed using information entropy and statistical methods. Based on data from the third and fourth National Wild Giant Panda surveys in China, we analyzed the developmental trend, spatial distribution, and characteristics of the current state and regional distribution of human disturbances affecting panda populations. The results showed that shoot gathering, farming, and tourism were key local distribution factors, whereas hunting, road infrastructure, and logging had a more widespread impact on panda habitat. Livestock and herb gatherings, however, showed no clear distribution patterns. The influence of the main disturbance factors (logging, livestock, road infrastructure, and shoot gathering) tended to increase over time, whereas the development of the relative strength and weakness of the disturbances showed an evolutionary trend. Although logging, livestock, shoot gathering, and road infrastructure have historically been the main panda habitat disturbances, the impact of logging and shoot gathering has been diminishing over time, with road infrastructure emerging as the leading disturbance factor. Farming has shaped the distribution area of giant panda habitats over the past several hundred years. Additionally, logging has caused current fragmentation patterns for several decades. Moreover, it is estimated that road infrastructure will have a broad and profound impact in the coming decades. Our results indicate that the information entropy theory can be effectively used to analyze the temporal and spatial characteristics of human disturbances that affect wildlife. Our findings will provide a basis for ecological policies that aid the preservation of threatened panda populations and guide future research on habitat disturbance.

Structure Simulation and Equilibrium Evaluation Analysis of Regional Water Resources, Society, Economy and Ecological Environment Complex System

Currently, the implementation of water resource spatial equilibrium strategy is a fundamental policy of water resource integrated management in China; it is also a considerable challenge to explore the relationship structure features of water resources, society, economy and ecological environment (WSEE) complex system. For this purpose, firstly, we applied information entropy, ordered degree and connection number coupling method to reveal the membership characteristics between different evaluation indicators and grade criterion. Secondly, the system dynamics approach was introduced to describe the relationship features among different equilibrium subsystems. Finally, the ordered degree, connection number, information entropy and system dynamics integrated model was established to conduct relationship structure simulation and evolution trend evaluation of the WSEE system. The application results in Hefei city, Anhui Province, China, demonstrated that: (1) the variation of overall equilibrium conditions of WSEE system in Hefei city, 2020-2029 was higher compared to that of 2010-2019, though the increasing rate of ordered degree and connection number entropy (ODCNE) became slower after 2019; and (2) the annual ODCNE value from 2020 to 2029 of WSEE system under dry year scenarios increased about 0.0812, which indicated that the construction of Yangtze-Huaihe Diversion (YHD) project could play significant positive role in mitigating the equilibrium situation of WSEE system in Hefei city in the future. On the whole, this study is capable of providing the guidance basis for constructing a theoretical framework of structure simulation and equilibrium evaluation analysis of WSEE complex system.

Image Restoration Quality Assessment Based on Regional Differential Information Entropy.

With the development of image recovery models, especially those based on adversarial and perceptual losses, the detailed texture portions of images are being recovered more naturally. However, these restored images are similar but not identical in detail texture to their reference images. With traditional image quality assessment methods, results with better subjective perceived quality often score lower in objective scoring. Assessment methods suffer from subjective and objective inconsistencies. This paper proposes a regional differential information entropy (RDIE) method for image quality assessment to address this problem. This approach allows better assessment of similar but not identical textural details and achieves good agreement with perceived quality. Neural networks are used to reshape the process of calculating information entropy, improving the speed and efficiency of the operation. Experiments conducted with this study's image quality assessment dataset and the PIPAL dataset show that the proposed RDIE method yields a high degree of agreement with people's average opinion scores compared with other image quality assessment metrics, proving that RDIE can better quantify the perceived quality of images.