Search

Due to the non-homology problem and the simple structural characteristics, a grey prediction model will have defects in modeling. In this paper, the structure of the GM (1 , 1 , x (1) ) model is deformed, and additional parameters are added. A novel four-parameter grey prediction model NFGM(1,1) is established to avoid the non-homology problem. The accumulation order of the NFGM(1,1) model is optimized to enhance its performance. This paper first introduces a nonlinear term and a linear term into the GM (1 , 1 , x (1) ) model to compensate for its structural defects, which can enhance the accuracy of the model in modeling complex modeling sequences. Secondly, a simplified basic formula of the model is proposed to estimate its parameters and iteratively establish the model, which can avoid the problem of non-homologous errors during modeling. Then a novel four-parameter grey prediction model NFGM(1,1) is constructed. Thirdly, the unbiasedness of NFGM(1,1) is proved and verified by matrix theory. Fourthly, by optimizing the order of the NFGM(1,1) model, the model is more flexible and adjustable, and a novel fractional-order four-parameter grey prediction model FNFGM(1,1) can be obtained. Finally, the FNFGM(1,1) model is applied to the prediction of natural gas production in China. The model results show that the FNFGM(1,1) model exhibits superior performance compared to the NFGM(1,1), TWGM(1,1), TDGM(1,1), DGM(1,1), and GM(1,1) models, with the mean relative simulation/prediction/comprehensive percentage errors of 0.92%/1.42%/1.07%, respectively. According to the predicted results, China's natural gas production will reach 3542.9 × 108 m3 in 2027 and some relevant policy recommendations are put forwarded. • On the basis of GM (1 , 1 , x (1) ) , a nonlinear term and a linear term are introduced to expand the model structure, and a novel four-parameter grey prediction model is proposed. • In order to avoid the non-homology problem of the differential equation and difference equation in traditional modeling, this paper uses the simplified basic formula of the model to estimate parameters, and does not directly derive the time response, but directly uses the iterative recurrence method to model. • The new model is proved to be unbiased by the matrix theory method and verified by arithmetic examples. • According to the objective function and constraints of fractional-order solving, PSO algorithm is used to optimize the order of the new model, which makes the model parameters changeable and improves the model performance. • The comprehensive performance of the new model is verified by a case study, the new model is applied to forecast China's natural gas production in the context of Xi Jinping's new era, and the results show that the new model has better accuracy, and the results obtained can help the government to formulate relevant policies. [ABSTRACT FROM AUTHOR]

The surge of machine learning (ML) applications and increasing usage of data driven approach for resilience enhancement provide great opportunities for applying ML techniques to power outage prediction (POP) during hurricanes. Considering the substantial damage that wind hazards can cause to power system network (PSN) in countries such as the USA and China, researchers have devised numerous approaches for disaster prevention to reduce their susceptibility. Since the selection of optimal ML algorithms for POP during hurricanes is a complex task, this paper helps researchers easily comprehend the numerous prediction techniques used worldwide for power outages during hurricanes. The paper provides a brief review of several categories of hurricanes and the damage it causes to the PSN more specifically to distribution side, the necessary measures to improve the PSN resilience, and finally a sequential approach for optimal ML model selection techniques that researchers and engineers can use to improve the POP during hurricanes. In this study the effectiveness of ML algorithms has been explored with the help of performance evaluation metrics which serve as the basic deciding criteria for optimal model selection. This research also highlights some of the key issues and challenges of integrating machine learning algorithms with existing PSN. • Reviewed various ML algorithms used for distribution system POP during hurricanes. • Effects of damage experienced by power system networks during hurricanes are widely investigated. • Provides an insight into the measures for improving power system resilience against hurricanes. • Provides a stepwise approach for using various ML algorithms in the context of POP. • Identification of key issues, challenges, and discussion of possible future research directions. [ABSTRACT FROM AUTHOR]

The surge of machine learning (ML) applications and increasing usage of data driven approach for resilience enhancement provide great opportunities for applying ML techniques to power outage prediction (POP) during hurricanes. Considering the substantial damage that wind hazards can cause to power system network (PSN) in countries such as the USA and China, researchers have devised numerous approaches for disaster prevention to reduce their susceptibility. Since the selection of optimal ML algorithms for POP during hurricanes is a complex task, this paper helps researchers easily comprehend the numerous prediction techniques used worldwide for power outages during hurricanes. The paper provides a brief review of several categories of hurricanes and the damage it causes to the PSN more specifically to distribution side, the necessary measures to improve the PSN resilience, and finally a sequential approach for optimal ML model selection techniques that researchers and engineers can use to improve the POP during hurricanes. In this study the effectiveness of ML algorithms has been explored with the help of performance evaluation metrics which serve as the basic deciding criteria for optimal model selection. This research also highlights some of the key issues and challenges of integrating machine learning algorithms with existing PSN. • Reviewed various ML algorithms used for distribution system POP during hurricanes. • Effects of damage experienced by power system networks during hurricanes are widely investigated. • Provides an insight into the measures for improving power system resilience against hurricanes. • Provides a stepwise approach for using various ML algorithms in the context of POP. • Identification of key issues, challenges, and discussion of possible future research directions. [ABSTRACT FROM AUTHOR]

At present, due to the lack of core technology and technological innovation ability, the design technology of traditional shipyards in China is backward. The operation mode of front-line workers in shipyards is highly dangerous. There are problems that endanger the physical and mental health of workers, such as noise and paint mist pollution, which lead to low production efficiency of workers and difficulties in personnel allocation. Under this background, "shipyard labor shortage" and other similar situations followed. If the concept of smart factory is introduced into traditional shipyards, the above problems can be effectively alleviated and solved. However, due to the complexity of ship product structure processing and manufacturing, the definition of smart shipyard in China is still vague, and the research process of smart shipyard is relatively slow. Aiming at the vague functional concept of smart shipyard, the lack of research on information design and management, smart production process and smart implementation process, this paper provides a conceptual architecture design model of civil smart shipbuilding factory. The functional definition of smart shipyard is discussed, and the initial conceptual model of smart shipyard is established, including information network platform model, smart production process model and smart implementation process model. The application case verifies the above model. Firstly, the information network platform model of α group is constructed, and the group brain control system is established. Secondly, the smart production process of shipyard A under α group is established. Finally, the smart implementation process of shipyard A is designed. The case study shows that: All ships completed 100% modeling, and the pre-outfitting rate increased to about 95%. By using the wire cutting robot, the production efficiency is increased by 70%. In the smart factory mode, the 60,000 tons bulk carrier can save 35thousand dollars labor costs and 11 million dollars in shipping fuel costs each year. The shell steel plate of the 300,000 tons ore carrier is reduced by 212 tons, and the weight is reduced by 10.5%. Case shipyard A under α group using the above smart factory model can save about 0.7 million dollars labor costs per year; reduce fuel costs by about 2.2 million dollars per year; saving 2.5 million steel usage per year. In total, shipyard A reduced expenditure by about 5.4 million dollars in one year. • This paper provides a civil intelligent ship manufacturing plant and its realization and optimization method, and introduces the construction content and method of the production process system of the intelligent shipyard. The key point of the construction of the intelligent shipyard is the intelligent production of ships, so as to finally realize the harmonious and unified operation of multiple robot groups. In order to better ensure the efficiency of the shipbuilding plant in production, reduce the pollution to the living environment, greatly reduce or even eliminate the production accidents caused by human factors. [ABSTRACT FROM AUTHOR]

Emergency decision-making is vital for nations or communities because it increases emergency management's effectiveness and legitimacy, which in turn greatly minimizes environmental damage, fatalities, and economic loss. The evaluation of emergency judgements must take into account significant inaccuracy, fuzzyness, and ambiguity. While high risk and uncertainty are frequently characteristics of emergency decision-making (EDM) circumstances. The current EDM methodologies do not take into account the psychological behavior of the decision makers in addition to the various emergency situations and the various responses. In this paper, we presented a new method based on a Complex Probabilistic Hesitant Fuzzy Soft Set (CPHFSS) as represented by membership in 2-D with hesitant probability. The idea that is being put forth captures the ambiguity and takes into account emergency situations while also taking into account the psychological state of the decision-makers involved in the EDM procedure. The introduction of a new score function for the CPHFSS serves as the second objective of this paper, which is to address a number of comparability issues. We examine a novel family of hybrid operators for CPHFSS that utilize numerous independent variables as a solution to these unforeseen issues. The group decision-making strategy and EDAS technique are then suggested employing these operators. Later, an emergency decision-making situation involving a major fire in China is used to demonstrate the validity of the algorithms. • Concept of complex probabilistic hesitant fuzzy soft set is presented. • Introduce a new score function for the CPHFSS. • Group decision-making strategy and EDAS technique presented. • Emergency decision-making problems discussed in the study. • Case study related to industrial disaster emergency decision-making discuss. [ABSTRACT FROM AUTHOR]

The factors influencing residents health have become complex and intertwined with the development of economy and society. Traditional research with a single factor on health will not provide an accurate picture of the situation. This paper collects data on economic, environmental and social factors to estimate their impact on regional health. Considering the data is multi-source and complex, this paper proposes a combined feature importance algorithm, which weighted the feature importance of RF, XGB and SOIL. The algorithm does not depend on the data and adaptively approximates the true results. The results show that economic factors have a significant and direct impact on health, environmental factors have a lag correlation with health level, and social factors have a more complicated effect on health. Finally, we provide policy suggestions for health on economic, environmental, and social development. [ABSTRACT FROM AUTHOR]

Accurate electricity consumption forecasting, especially monthly electricity consumption forecasting, plays an essential role in the stable and efficient operation of power systems. To improve forecasting performance and practicality, we propose a dynamic decomposition-denoising-ensemble model to predict monthly electricity consumption in this paper. Firstly, seasonal-trend decomposition procedure based on loess (STL) incorporated with a dynamic mechanism is used to decompose the original monthly electricity consumption series into trend component, seasonal component and residual component. Secondly, empirical wavelet transform (EWT) is introduced to denoise the residual component and obtain the denoised residual component. Thirdly, autoregressive integrated moving average (ARIMA), Holt-Winters (HW) and extreme learning machine (ELM) are used to predict the trend component, the seasonal component and the denoised residual components, respectively. Finally, the forecasting results of each component are added to obtain the final forecasting results. Furthermore, we take two real datasets from China as examples to verify the performance of our proposed model. The empirical results show that the proposed model performs better than the benchmark models and denoising the residual component can enhance the forecasting performance. Specifically, compared with benchmark models, the mean absolute percentage error (MAPE), mean absolute error (MAE) and root mean squared error (RMSE) values of the proposed model decrease by 5.81%–46.02% (12.15%–51.03%), 4.80%–42.24% (12.75%–53.53%) and 1.98%–41.02% (10.44%–55.27%). [ABSTRACT FROM AUTHOR]

The purpose of video process detection is to identify key processes of interest and associated semantic categories, which is an important computer vision task for localizing key processes in space science experiments. To detect experimental processes in space electrostatic suspension material experiment on China's Space Station, we propose a Slow-and-Fast Dual-Stream Network. It extracts multi-scale temporal semantic information by designing a Slow-and-Fast Temporal Stream structure and effectively detects the experimental processes with various temporal scales. In addition, the Two Path Temporal Pyramid Network (TP2N) enhances the bi-direction flow among multi-scale features on the temporal dimension to alleviate boundary sensitivity. The validation experiments on our established dataset demonstrate the effectiveness of our proposed method with 62.43% mAP, outperforming the related state-of-the-art temporal action localization methods with nearly 7% mAP gain. This paper is the first application of deep learning in space electrostatic suspension material experiments on China's Space Station and further provides important technical support for the identification of key processes in space science experiments. [ABSTRACT FROM AUTHOR]

In recent years, the new coronavirus COVID-19 has brought great disaster and loss to the world and is still spreading around the world. The situation in China is generally well controlled, and the lockdown has been removed, but the comments and messages about the epidemic persist online. For people working and living normally in China, their attitudes and views toward COVID-19 directly reflect the current situation of the pandemic. This paper collected Chinese microblogs, forums, and online comments, identified the latest comments about COVID-19, and conducted a sentiment analysis of them. Specifically, we proposed a new sentiment analysis method that integrated the semantics of words with the text analyzed. Different from the traditional sentiment analysis method which only relied on sentiment words, the proposed method extended the semantic concepts of affective words by integrating the semantic conceptual information about the affective words from the context of the comments and thus, provided information to support the final judgment of the affective opinions. The proposed approach incorporated the part-of-speech embedding information along with word embedding and relies on semantic concepts to enhance the emotional expression of words in context. The experimental results showed that by integrating the semantics of words, the accuracy of sentiment analysis is substantially improved, and it also reflected that different semantics of the same word have different influences on sentiment analysis. On several benchmark datasets, there was a 3–6% improvement in accuracy. [ABSTRACT FROM AUTHOR]

The first-order grey model is appropriate for monotonic time series, while the grey Verhulst model is appropriate for periodic time series. The grey Verhulst model is widely used for predicting practical nonlinear time series that contain fluctuations. Despite the successful application of the grey models in practice, researchers show that grey models still have room for improvement. Moreover, recent research shows that grey models are sensitive to initial conditions. In many practical problems, the value of initial conditions is not accurate and suffers from noise or approximation errors, resulting in inaccurate prediction. To address these difficulties, an improved grey Verhulst method using particle swarm optimization is proposed in this paper. The proposed model consists of two stages. In the first stage, a second-order polynomial with unknown coefficients is used to approximate the 1- AGO. In the second stage, the initial element of the time series is modified to improve the accuracy of the prediction. The particle swarm optimization method is used to search for the unknown coefficients. It is found that PSO is a suitable optimization method for the proposed method because it is stable and generates a sequence of points that converges to a globally optimal solution. To demonstrate the efficiency and stability of the proposed method, it was applied to five practical problems, namely, gas production in China, the number of hazardous chemical accidents, CO2 emissions in Russia, the number of domestic tourists in China, and traffic flows in Canada. Numerical results show that the method is more accurate and robust than existing methods. • The proposed method needs only four elements for predicting the future elements of time series. • The paper proposes a second order polynomial for approximating 1-AGO. • The method makes more accurate prediction than existed methods. • The proposed method is applied on various practical forecasting problems successfully. [ABSTRACT FROM AUTHOR]

Scientific and accurate prediction of energy production is important for exploring energy alternative paths, adjusting energy structure and industrial layout in a targeted manner, and promoting strategic energy transformation. In this paper, a time-lagged logistic grey forecasting model with harvesting term is established by combining the Logistic model, which has the ability of historical recurrence and short- and medium-term forecasting ability, and the grey forecasting model, which has the characteristics of strong adaptability and small computational effort. The least squares method is used to estimate the parameters of the new model, and the mathematical method is used to calculate the time response equation of the new model, and the modeling steps and flow chart of the new model are obtained. Finally, the oil production data of a province in China is used as the validity analysis of the model, and the new model is compared with two classical grey prediction models, three optimized grey prediction models, and one other prediction model. Through the comparison of seven indicators, the results show that the new model is significantly better than other models. Based on the validity analysis results, the new model is applied to the energy production forecast of three typical provinces in China. The horizontal and vertical comparison shows that the model can effectively predict the three kinds of energy production, and can provide technical support for the strategy and measures to adjust the energy security structure and promote the healthy and sustainable development of the energy industry. • A novel model (HDLGM(1,1,τ)) is established by considering the time-lagged Logistic. • Logistic harvest items are introduced into the novel model. • Modeling short- and medium-term forecasting ability was Enhanced. • The proposed model has been effectively applied to energy production. [ABSTRACT FROM AUTHOR]

A scientometric approach is utilized to investigate the dynamic maps of relationships among researchers, institutes, and countries in the field of Artificial Intelligence for Fluid-flow and Heat-transfer (AIFH). The Web of Science database was searched for related publications during the last 40 years (1982 and 2022). A total of 6151 articles were discovered, which were analyzed in detail. Using a bibliometric analysis, the most relevant and most cited sources of publications were identified. The most active researchers, institutions, and countries leading AIFH were reported. Then, the worldwide dynamic collaboration maps and coupling maps of relationships were reported. The Islamic Azad University (1893 T.C.), the Chinese Academy of Sciences (1374 T.C.), and Beihang University (1266 T.C.) were the most influential institutes in AIFH. The most influential countries were China, the USA, and Iran. The dynamic map of collaborations shows a good worldwide collaboration distribution. The USA and China established the most connection with the rest of the world. ANNs are the most studied topic (19.5% of publications), followed by Machine Learning (17.9%) and Neural Networks (15.4%). Support Vector Machines lag behind at 1.4%. ANNs boast the highest total citations (17,064) and H-index (63). Most ANIF papers were published by Medical Physics (119 T.P.). Half of the articles in AIFH were published by five journals of Medical Physics, Neurocomputing, International Journal of Heat and Mass Transfer, International Journal of Radiation Oncology Biology Physics, and IEEE Access. The International Journal of Heat and Mass Transfer received the most citations in AIFH. [ABSTRACT FROM AUTHOR]

D number theory is a relatively new uncertainty reasoning approach and its application has been gaining momentum due to its distinctive features and potential advantages. This theory aims to generalize Dempster-Shafer theory with two properties such that the elements in discernment frame do not require being mutually exclusive and the completeness constraint is also relaxed. Due to these properties, D number theory has found a wide application range, particularly in handling the vagueness nature of linguistic assessment. We aim to provide a systematic review of the application of D numbers since the inception in 2012 in the field of operations research and management science. By searching the term "D numbers" in the title, abstract and keywords of publications, the raw data has been collected on 30th December 2022 from Scopus and Web of Science. To ensure the quality of research, we only focus on the journal articles written in English from peer-reviewed journals with impact factor ≥1.5 located in the first or second SJR quartile. This filtering yields a final set of 72 articles from 40 international journals. The findings of this review indicate that the number of articles on D numbers has been increasing and have attracted cross-disciplinary attention. But it can be realized that there are very challenging tasks such as combination rule, integration function, belief and plausibility functions, distance function and uncertainty/reliability measure which have been far less studied and the lack of attention given to them can dramatically hinder the development of D number theory. The most popular research direction has been "decision making under uncertainty". "Expert Systems with Applications" is the most prominent journal with most publications and the largest number of influential articles and " China" with the highest number of publications is the traditional leader in this field. Although 20 countries contribute to this study, D numbers research has not attracted widespread attention around the globe and the lack of literature from many countries with high academic influence is clear. Considering the fact that the research on D number theory is still evolving, this work has important guiding significance for the later research. The findings are expected to provide researchers with a comprehensive understanding of research trends of D numbers and promote further and deeper studies in this context. [Display omitted] • This paper provides a systematic review of D numbers and its applications. • Bibliometric analysis is conducted to provide insights into the research theme. • Research gaps and future research direction are identified. [ABSTRACT FROM AUTHOR]

PM2.5 Prediction is a complex task of large-scale spatio-temporal analysis, which not only needs comprehension of static geospatial knowledge and relative features but also needs to analyze the real-time situation. This paper discusses the characteristics of the static graph and the dynamic graph in spatio-temporal series tasks. An Adaptive Scalable Spatio-temporal Graph Convolutional Network(ASGCN) model is proposed to predict PM2.5. To capture and analyze the characteristics of the time series period of PM2.5, a time convolution network based on the strategies of inception and gating is proposed and used as a temporal module. A dynamic graph idea is adopted to distinguish the spatio-temporal similarity of different periods. And an adaptive weighted multilayer graph convolution network is used to process static and dynamic graphs, aiming to analyze the spatial relationship of PM2.5 stations. The convolution network with the inception and gating improves the time-series feature capture ability, and adaptive static and dynamic graphs enhance the spatial relationship analysis ability. The temporal and spatial modules of the model are relatively independent, which benefits obtaining the potential information of datasets to improve the prediction accuracy. At the same time, these modules cooperate to make the model adaptable to various data. We choose a great number of comparative models and design a thorough experimental scheme including single-step prediction, multi-step prediction, hyperparameter experiments, and ablation experiments on two real PM2.5 datasets collected in China. Finally, the model achieves performance close to or better than the current state-of-the-art models selected for comparison in prediction tasks. [ABSTRACT FROM AUTHOR]

Food safety is a global issue; risk prevention and control of food physical and chemical testing (PCT) data are critical. However, existing studies have not considered the risk status of qualified products near the detection limit. Therefore, this paper presents a data-driven paradigm to detect the combined risk of multiple indicators across products in real-world food safety datasets for the first time. The following challenges exist to achieve this goal. (1) In real-world scenarios, neighboring samples are somewhat correlated; however, capturing and quantifying the actual testing sample correlation network remains an open problem in food computing. (2) The low-frequency nature of the unqualified samples leads to label imbalance in the data. (3) Labeling dependency limits the application scenarios. This article proposes a novel self-supervised framework (SUCOLA) to address the abovementioned challenges. That jointly learns the optimal graph topology and also inferences the connections between every product node and its well-designed subgraph, helping to resist label imbalance. We applied it to a real-world sterilized PCT dataset from a province in China. Extensive experiments show that SUCOLA performance is outstandingly better than several baselines of the current graph self-supervision field. Meanwhile, we conducted generalizability experiments on five well-known benchmark datasets. The proposed SUCOLA surpasses the current state-of-the-art by a considerable margin (0.39%–8.7% AUC) on public datasets. Thus, our study provides a new idea for early warning research on PCT data in food computing and fills the gap in the study of structural learning under category imbalance. [ABSTRACT FROM AUTHOR]

The leading causes of earthquakes are crustal movements, plate movements, and collisions. In recent years, many researchers in earthquake prediction have been predicting earthquakes from historical seismic data in local areas. This approach ignores the underlying internal patterns of crustal motion, plate movement, and collisions. This paper proposes a purely data-driven deep learning model called EPT. The model uses gated feature extraction blocks (GFEB) to mine potential crustal motion and plate movement patterns from global historical seismic catalog data. It uses them to aid mainshock prediction in each local, provincial region. Experiments show that this approach improves model prediction accuracy by up to 50 percent. We also use multi-headed self-attention for the first time to capture long-term dependencies within regional time series, highlighting links between focal features and compensating for the difficulty of focusing on longer-term information in long-term time series with long short-term memory networks (LSTM). In addition, we also use the gradient harmonization mechanism classification (GHMC) loss function for the first time in earthquake prediction, effectively addressing the problem of uneven data distribution across different earthquake magnitude ranges. Finally, we validated the effectiveness of the EPT model in five provincial datasets in mainland China, and the experimental results all achieved an accuracy of over 90 percent. [ABSTRACT FROM AUTHOR]

Sudden-onset disasters put forward new requirements for on the state authorities' ability to analyze public opinion sentiment. However, traditional sentiment analysis methods ignore the contextual semantic relationships and out-of-vocabulary words, and their computational resource utilization is excessive compared to their expected accuracy. In this paper, an ALBERT-based model combined with a text convolution neural network, a hierarchical attention mechanism and the latent Dirichlet allocation is proposed to create a hybrid model enhanced with topic knowledge for sentiment analysis of sudden-onset disasters. Weibo text data from a rainstorm disaster in China are used to evaluate the model's performance. Compared with the XLNet, DistilBERT and RoBERTa models, the experimental results demonstrate that the proposed approach is capable of achieving better performance by incorporating external topic knowledge into the language representation model to compensate for the limited vocabulary data. [ABSTRACT FROM AUTHOR]

The accurate prediction of carbon emissions is of great significance for countries to implement scientific and effective policies and measures. In this paper, a novel multivariable grey differential dynamic prediction model is established to analyse and forecast China's carbon emissions. The differential term of the correlation variables is introduced to consider the influence of the rate of change of the related factors on the system. The linear correction term and grey action are introduced to increase the stability and adaptability of the model. The whitening differential equation of the model is solved by the Sadik transform, and the time response of the model is obtained. In the case study, the model used China's carbon emissions and related data from 2004 to 2019 to calculate four cases. Its minimum simulation and prediction errors are 1.4435% and 3.1739%, respectively. Compared with the other four models, this model has better simulation and prediction accuracy, which proves the model's effectiveness. Finally, the model forecasts China's carbon emissions from 2020 to 2024, and some suggestions are put forwards based on the predicted results. • A novel grey differential dynamic prediction model with new structures (DDGM(1,N)) is proposed. • The differential terms of relevant variables, linear term and grey action are introduced into the model structure. • The Sadik transform is used to solve the model. • China's carbon emissions have been effectively predicted. [ABSTRACT FROM AUTHOR]

The accurate and reasonable prediction of natural gas consumption is important for enhancing national energy security and alleviating the environmental problems caused by energy consumption. Starting with the traditional nonlinear grey Bernoulli model, in this paper, we expand the development coefficient a and grey action quantity b, propose a new self-adaptive time-varying grey Bernoulli prediction model, deduce the time response formula of the model, and explore the relationship between model parameters and model accuracy. Then, the nonlinear parameter and power parameter coefficient of the new model are optimized by a genetic algorithm, and the effectiveness of the model is analyzed by the natural gas consumption of China, the United States, and Russia. The results show that, compared with other traditional grey prediction models, the new model has a better simulation effect, higher prediction accuracy, and stronger applicability. Meanwhile, the model was used to forecast the natural gas consumption of China, the United States, and Russia in the period from 2022 to 2026. The prediction results show that China's natural gas consumption will continue to steadily increase in the future, which is consistent with the global goal of adhering to the orderly development of natural gas. The prediction results can provide a theoretical basis for relevant departments to formulate relevant natural gas policies. [ABSTRACT FROM AUTHOR]

The monitoring and recognition of operational states pattern is a crucial part for maintaining the safety, reliability and profitability of oil and gas pipeline systems. However, there are fewer methods to monitor the operational status of long-distance pipelines through operational data alone. In this paper, a purely data-driven approach is proposed for detecting and identifying the operational status of pipeline systems based on machine learning methods and the data log of pipelines. Firstly, a logic rule-based method is proposed to enrich the labels for each segment of operational data. Secondly, a change point-based detection model is used to detect the change of operational state in pipeline system or equipment. Then, a framework of oil pipeline operational pattern recognition methods based on graph structural features is proposed. Finally, the proposed model is applied to a real-world data from a pipeline system in China. Both the accuracy and the breadth of the recognition results can be improved by the use of real-time data validation and a human-machine interface. The results show that the precision of a change point-based detection model can reach more than 85% for different scenarios, and a reduction in missed rate of 17%–26%. Compared with the statistical feature-based method, the proposed method has improved the accuracy for all types of scenarios to a certain extent. The most significant improvement in recognition accuracy was achieved in the valve switch state and the combined state, with an increase of 30.8% and 5% respectively. • Graph-based representation methods is established for complex oil pipeline system. • A graph structure feature methods is proposed for time-series pattern recognition. • Change point detection method is employed to segment pipeline operating states. • The methodology is applied to a real-world multi-product pipeline in China. [ABSTRACT FROM AUTHOR]

Energy production and conversion have a significant impact on the economic development of all countries in the world. China's energy production and conversion are large. Therefore, accurate mid-to-long term China's energy production and conversion forecasting is becoming more and more important for integrating energy systems and energy strategic planning. For this purpose, a novel fractional grey sequence is proposed based on Grunwald–Letnikov fractional calculus. Furthermore, a novel self-adaptive fractional multivariable grey model is proposed based on the novel sequence. In this article, we compare several classical optimization algorithms and finally choose Particle Swarm Optimization (PSO) to compute the parameters. In addition, Monte-Carlo simulation and probability density analysis (PDA) are presented in this article to verify the model's performance. Monte-Carlo simulation reduces the randomness of the results of the model runs to a certain extent. Probability density analysis visualizes this randomness through kernel density estimation (KDE). This paper compares the new model with the existing seven grey models and predicts the total energy consumption per capita, energy conversion efficiency and total renewable energy in China, respectively. The experimental results show that the new model is superior to the other seven models in terms of stability and prediction accuracy. [ABSTRACT FROM AUTHOR]

It will be beneficial to devise an effective approach for short-term macroeconomic forecasting. Existing traditional statistics-based macroeconomic forecasting mainly focuses on exploring feasible methods for improving the accuracy of long-term predictions. However, the performance of short-term predictions was far less impressive under the impact of unexpected incidents. Furthermore, some deep learning-based approaches can achieve fine-grained variable frequency forecasting and preliminarily demonstrate effective results, but the interpretability is still controversial. Therefore, how to consider both the performance and the interpretability has already become a universal concern and an urgent unsolved problem. In this paper, we identified the above issue and proposed an interpretable data-driven approach, named EcoForecast 1 1 The code and data are available at https://github.com/navfour/ecoforecast. , for short-term macroeconomic forecasting based on the N-BEATS (neural basis expansion analysis for interpretable time series forecasting) neural network. To the best of our knowledge, EcoForecast is the first interpretable purely data-driven unified normative scheme for macroeconomic forecasting that achieves variable forecast frequencies and prediction domains, surpassing traditional statistics-based and deep learning-based approaches in performance or interpretability. EcoForecast used a three-level hierarchical signal encoding, including the fully connected neural network (FCNN) level, the block level, and the stack level. The FCNN level implemented both forecast and backcast information extraction for the temporal prediction and parameter learning of context. Block levels were connected by residuals so that the block's backcast could be sequentially filtered on the input. The stack level was used to form the top-level system of EcoForecast, where each stack was constrained to specialize in different inductive functions. To some extent, EcoForecast can balance effectiveness, efficiency, generalizability and interpretability while conditions such as forecast frequency and time window change, even when unexpected incidents occur. Based on the actual macroeconomic data for China from 1992 to 2022, the data-driven EcoForecast demonstrated high stability in different sequence learning scenarios and the accompanying high-accuracy performance. This stability was reflected in smaller prediction error expectation and variance, tolerance of fewer input samples, and robustness across prediction domains. The experimental results indicated that EcoForecast improved the accuracy up to 3.94 times compared with the traditional BVAR. In the robustness test, EcoForecast required only a quarter of the data to achieve 2.51 times smaller forecast errors than the BVAR while also improving the accuracy of varied macroeconomic indicators such as the Purchasing Managers' Index (PMI) and national electricity generation (ELEC)forecasting by 2.38 and 1.45 times. EcoForecast had a high sensitivity to the emergence of economic inflection points and adapts quickly when the economic environment changes, thus demonstrating a performance that exceeds traditional solutions in GDP forecasting during epidemics and PMI forecasting during economic turmoil. Interfacing with traditional economics research, the interpretable EcoForecast can uncover the trends and cycles of economic change, from which the conclusions are validated with the actual economics practice in China. Our findings can provide a new possible research direction for short-term macroeconomic forecasting. [ABSTRACT FROM AUTHOR]

The scientific and reasonable prediction of wastewater discharge is of great significance for regional water environment management and water resources protection. To this end, a new high-performance grey prediction model suitable for wastewater discharge prediction named FDGM(1,1, k , r) is proposed based on the three-parameter discrete grey prediction model (TDGM(1,1) for short) in this paper. Firstly, the mechanism and structure defects of TDGM(1,1) are systematically analysed and made up in FDGM(1,1, k , r) by adding a nonlinear correction term and new grey generation operator with real number field (r ∈ R). Then, the new information priority principle (Metabolic Thought) is introduced into the new model according to the dynamic nature of wastewater discharge prediction. Thirdly, the empirical results of wastewater discharge in Chongqing show that the mean relative percentage error of new model is only 0.216%, which is superior to other mainstream grey forecasting models of wastewater. Lastly, the new model is used to forecast the wastewater discharge in Chongqing China, and the prediction results show that the wastewater discharge in Chongqing will be as high as about 3.1 billion tones in Year 2025, and the government should formulate timely countermeasures to deal with the rapidly increasing wastewater discharge in the future. [ABSTRACT FROM AUTHOR]

In the context of small sample and poor information, the data often change rapidly and interact with multiple factors which make it a challenge to analyse and predict multivariate sequences efficiently. Due to the fact that real systems usually show fractional order characteristics, the aim of this paper is to consider the approach improving the forecast results of multivariate interval grey prediction model via exploiting fractional accumulation. Noting that fractional accumulation could disturb the exponential law, the connotation prediction method is introduced to balance the disturbance. Correspondingly, a fractional connotation prediction method is constructed. In addition, traditional background value coefficient is optimized by using the particle swarm optimization algorithm (PSO). Therefore, a multivariate interval grey fractional accumulative connotation prediction model with optimized background value coefficient is constructed, in which the interval grey number time series are transformed into kernel series and radius series. Finally, the developed model is applied to clean energy prediction in China to verify the feasibility and validity. [Display omitted] • A multivariate interval grey prediction model via fractional accumulation is bulit. • The dynamic background value is optimized by integral mean value theorem and PSO. • The developed model is applied to model clean energy datum in China. [ABSTRACT FROM AUTHOR]

Forecasting landslide displacement is an important issue in engineering geology. In this field, it is difficult to accurately forecast the displacement of the step point of a step-type landslide. In this study, a novel grey multivariate model is proposed for forecasting landslide displacement. The proposed model transforms the original sequence by using the Hausdorff derivative operator, determines the model parameters by using the particle swarm optimization algorithm, and uses the trapezoidal integral formula to calculate the predicted value. Two numerical examples show that the average absolute relative error and mean squared error of the proposed model are smaller than those of the recursive discrete multivariate grey model and the multivariable grey model with structure compatibility. The proposed model is used to forecast the displacement of the Bazimen landslide in the Three Gorges Reservoir area of China. The previous month's displacement, precipitation, and change in the reservoir water level are used as input variables. The results show that the performance of the proposed model is superior to that of the extreme learning machine model. This paper provides an effective method for forecasting displacement of the step point of a step-type landslide. [ABSTRACT FROM AUTHOR]

Industry 4.0 with its fusion of technologies has brought an unprecedented growth in all sectors. In this paper, we first present the several pillars of Industry 4.0 which have contributed to the advancement of this field. Then, we perform a bibliometric profile of the Industry 4.0 publications in Web of Science by analyzing the publications and citation structure, most referenced publications, most productive and influential authors, organizations and countries. Further, an extensive analysis of the key words is presented along with the citation bursts of top keywords. Various visualizations tools have been to used show relationships between different bibliometric profiles. The individual growth of different research areas over the year is also presented. The results show promising growth of Industry 4.0 as a research area, various collaborative groups have been identified which are working extensively in the growth of the domain, spearheaded by China, however, considerable contribution of developing countries is also there. An abstract analysis is done using K-means clustering and Latent Dirichlet Allocation (LDA) to identify key research themes. [ABSTRACT FROM AUTHOR]