Search

The problem of global warming is getting more serious, and vehicle emission is the main cause. In recent years, the number of locomotives in China has been increasing at a rate of more than 20% per year, and the problem of automobile pollution is becoming more serious. The transportation industry is the main source of fossil fuel combustion and environmental pollution. Therefore, in this paper, we propose a multi-view deep neural network (MVDNN) to analyze the key factors affecting the fuel consumption of automobiles. The experiments show that the introduction of human input improves the prediction accuracy and the root mean square error (RMSE) achieves 0.993. In addition, this paper also finds that for drivers, driving habits, driving frequency, and safety awareness are the most important factors affecting the fuel consumption of vehicles by combining Lasso regression with MVDNN. Finally, by comparing the prediction accuracy of different experiments, relevant policy suggestions are made. [ABSTRACT FROM AUTHOR]

• The paper proposes a methodology for a hybrid model that can capture complex non-linear relationships and help understand the interactions between input and output features. • The model overcomes the limitation of traditional neural network models in predicting across different spaces. • The proposed model is an intelligent water quality prediction model that can provide decision support for predicting COD Mn concentration and managing watershed risks in the Changdang Lake basin, with good application prospects and practical value. The organic pollution of lake water can cause a tremendous threat to the water ecosystem and human health. The COD Mn is one of the crucial indicators of lake water quality and is commonly utilized to gauge the extent of organic pollution in lake water. Therefore, this paper selected COD Mn as the research object and used the water quality monitoring data of Changdang Lake in China and its upstream and downstream to predict the COD Mn concentration in the lake. In order to study the spatial relationship between the lake and upstream and downstream water quality, reflect the joint action of multiple water quality factors in prediction and the interaction between different feature factors. This study combined the XGBoost feature filtering algorithm, maximum mutual information coefficient (MIC), and improved recurrent neural network (GRU) and proposes a hybrid model called XGB-MIC-GRU. The model first used XGBoost to screen and extract the relative importance of water quality characteristics and used the Shapley addition extension (SHAP) method to explain XGBoost feature extraction. Then, the correlation between the lake and the upstream and downstream water quality is calculated through MIC analysis. Finally, the selected water quality factor characteristics and spatial characteristics are input into the GRU model for prediction. The experimental results showed that water temperature, total phosphorus, and total nitrogen are the most important to COD Mn , and the upstream US1 and downstream DS1 and DS2 stations are the most closely related to the concentration of COD Mn in the lake. By comparing the prediction effect of the model in different time steps, the best 16-time steps related data were selected to predict the value of the next time. MAE, RMSE, and R2 of the model are 0.10, 0.13, and 0.96, respectively. The model has better prediction accuracy and correlation error than the traditional SVR and GPR. The proposed mixed model can accurately predict the concentration of COD Mn in the lake. It can assist decision-makers in timely implementation of effective measures to safeguard the lake ecosystem. [ABSTRACT FROM AUTHOR]

Accurate traffic flow prediction can effectively improve traffic efficiency and safety. This has become a trending topic in intelligent transportation systems. However, the occurrence of traffic accidents will cause great fluctuations of traffic flow in a short time, thus affecting the accuracy of flow prediction. This paper analyses the influence of traffic accident information on traffic flow, and proposes a grey convolutional neural network called G-CNN for traffic flow prediction. First, considering the small sample size of traffic accidents and the incomplete information description, the traffic flow and traffic speed change rate are defined to represent traffic accident grey information, and a grey fixed-weight clustering method for extracting the characteristics of traffic accident grey information is established. Second, the spatiotemporal characteristics of traffic flow are analysed, and a third-order tensor is developed to fuse them with the accident characteristics and serve as the input of the G-CNN. Then the G-CNN model is built to predict traffic flow in a traffic accident environment. The Canadian Whitemud Drive experiment on traffic flow without traffic accident information reveals that the developed G-CNN model has a better ability to predict future traffic flow with better accuracy and stability. Meanwhile, it is verified that the fluctuation of the traffic change rate will cause traffic accidents, and the probability of traffic accidents at a certain time point will be obtained through feature extraction of traffic accidents. Finally, the model is verified for the traffic flow of Hangzhou Viaduct in China, which demonstrates that the G-CNN model outperforms all of the compared models. [ABSTRACT FROM AUTHOR]

Energy piles have attracted much attention in recent years because they provide a profitable solution for efficient shallow geothermal energy utilization in different climatic regions. However, the long-term performance design of energy piles under different thermal scenarios currently relies on time-consuming and computationally expensive methods such as numerical simulations, which seriously hinders the further engineering application of energy piles. To this end, this paper provides a high-precision and computationally efficient model for predicting the long-term performance of energy pile design through an artificial neural network machine learning process. First, experimentally validated numerical models are developed. Then, they are utilized to generate the training and evaluate datasets for the proposed model by inputting sixty typical thermal load distributions in different regions of China. Finally, the performance of the proposed model is evaluated by comparing its calculations with those obtained using numerical models. The results show that the proposed model can predict the long-term performance of energy piles and enrich the current methods for the long-term design of energy piles. Furthermore, its features that tremendously reduce the computational time and minimum required resources make it an excellent supplement compared with numerical simulations. [ABSTRACT FROM AUTHOR]

This paper investigates vehicle trajectory prediction problems in real traffic scenarios by fully harnessing the spatio-temporal dependencies between multiple vehicles. The existing GCN-based trajectory predictions are often considered in a single traffic scene without time attributes, complete interaction information, dynamic graph-based model, etc. Time and interaction aware models are more challenging than the existing ones. Despite very well does the graph-based model describe the relationship between driving vehicles, the critical problem in the traffic scene is how to deeply explore the spatio-temporal characteristics of dynamic graphs. Therefore, a novel dynamic graph and interaction-aware neural network model called as DGInet is proposed by combining a semi-global graph mechanism and an M-product based graph convolutional network, which are built into novel dual-network architecture in the entire model. The DGInet is built by exploiting the dynamic interaction in depth between driving vehicles in urban traffic scenarios, and then realized by utilizing semi-global graph convolution operations on the input data cell to capture the basic spatial interaction features of the driving scene. Meanwhile, the dynamic graph is further extracted by a novel M-product approach, in which the embedding of the model is then established along with the embedding of the semi-global network to perform the final embedding. Extensive experiments have been conducted on the two public datasets, named NGSIM and Apollo respectively, to show that our approach outperforms the existing ones with better performance and less computing time. Besides the real-world Shenzhen traffic dataset, China, is also developed to verify the effectiveness of our approach. • We propose a novel vehicle trajectory prediction approach called as DGInet. • This work fully leverages the current popular Graph Convolutional Networks (GCNs). • The DGInet features a M-product based GCN module to process dynamic graphs. • The DGInet can efficiently extract spatio-temporal features in driving scenes. • This work conducts comprehensive experiments on two well-known traffic datasets, and a real-world Shenzhen traffic data, China. [ABSTRACT FROM AUTHOR]

In recent years, sustainable digital economy development goals have received increasing attention because of the serious influence environment with the development of the rapid economy. Meanwhile, Multiple Criteria Decision-Making (MCDM) methods are efficient ways to measure sustainable developments, which can controls environmental pollution and protects sustainability improvement. However, assessment results are unconvincing by using the common MCDM methods because various areas that caused pollution conditions are inconsistent. Therefore, the purpose of this paper is to design an interpretable MCDM method with uncertain weights for various areas evaluation. In particular, MCDM can be used to evaluate environmental sustainability development efficiently, and deep neural networks can supply credible weights to MCDM. Interpretability is used to understand key factors in the decision-making process. Referring to the national policy and urgent areas from central areas in China, six areas are conducted to assess the sustainable digital economy problem, which could be interpreted as demonstrating the effectiveness and feasibility of the proposed approach. Besides, the experimental results demonstrate that the sustainable developmental level of Hubei is the best in the latest year. [ABSTRACT FROM AUTHOR]

Microseismic technology has been widely used in geological hazard monitoring. However, the effective identification and classification of microseismic events in mines have always been a challenge in hazard monitoring. In this paper, a new method combining the empirical mode decomposition (EMD) algorithm and artificial neural network is proposed for the classification and identification of microseismic waveforms. This is the first study to explore such a model in the microseismic monitoring of coal mines. The data for this study were collected from a coal mine in northern China. A total of 2768 microseismic events and 2435 non-microseismic events were manually selected from a large amount of data. Firstly, the microseismic waveform reconstruction was performed using the 4th to 8th Intrinsic Mode Function (IMF) obtained by the EMD algorithm. Secondly, the peak factor, clearance factor, impulse factor, kurtosis, skewness, and waveform factor of each reconstructed microseismic waveform were used as features. Subsequently, the convolutional neural network (CNN) was used to classify microseismic events. Among them, data from 3600 microseismic events were used as the training set, and data from 1603 microseismic events were used as the test set. Finally, the original waveform data were used as input and compared with the classification results processed with the EMD algorithm. The classification methods of the BP neural network and Radial Basis Function (RBF) neural network were used for verification. The results of the processed features showed a significant increase in accuracy. The classification accuracy of CNN, BP neural network, and RBF neural network are 97.37%, 91.99%, and 94.23%, respectively. The results show that the utilization of the feature processing technique and CNN algorithm in this study demonstrates superior efficacy in microseismic event classification, which can be used in practice. • The EMD algorithm and ANN was constructed to classify microseismic waveforms. • Six features of the reconstructed waveform were selected as the classification basis. • The EMD algorithm was used to make the six waveform characteristics more significant. [ABSTRACT FROM AUTHOR]

• Robust and accurate prediction of PWR safety parameters is provided by TCNN. • Sparse connections greatly improve the global awareness of the mode. • Convolutional kernels effectively enhance local feature extraction ability. • Basic blocks consist of residual connections prevent the gradient loss. Accurate forecasts for pressurized water reactor safety parameters are essential to ensure the safe operation of nuclear reactors. Potential of artificial neural networks on this task is limited owing to the lack of extracting the core location information. Sparse connections have unique advantages in discovering correlation between neighboring components and convolution kernels are designed to deal with two-dimensional information. In this paper, topological information embedded convolutional neural network (TCNN) was firstly established and utilized. This model enhanced the ability of fusing location features and component attributes through sparse connections and convolution layers. Datasets of China's Qinshan Nuclear Power Plant Phase II PWR was used to evaluate the performance of TCNN. Comparative and ablation experiments demonstrated that TCNN has superiority in working as efficient predictor for pressurized water reactor safety parameters, indicating that the proposed model promoted the digitalization of nuclear power plants. [ABSTRACT FROM AUTHOR]

• We construct a fine-grained classification dataset of wet Age-related macular degeneration (AMD). • A knowledge-driven deep learning model, KFWC, is proposed to improve accuracy in fine-grained disease classification with insufficient data. • KFWC can detect 10 signs of lesions on medical images and can diagnose two subtypes of wet-AMD. • Multiple experiments demonstrate the effectiveness and interpretability of the proposed KFWC. Automated diagnosis using deep neural networks can help ophthalmologists detect the blinding eye disease wet Age-related Macular Degeneration (AMD). Wet-AMD has two similar subtypes, Neovascular AMD and Polypoidal Choroidal Vasculopathy (PCV). However, due to the difficulty in data collection and the similarity between images, most studies have only achieved the coarse-grained classification of wet-AMD rather than a fine-grained one of wet-AMD subtypes. Therefore, designing and building a deep learning model to diagnose neovascular AMD and PCV is a great challenge. To solve this issue, in this paper, we propose a Knowledge-driven Fine-grained Wet-AMD Classification Model (KFWC) to enhance the model's accuracy in the fine-grained disease classification with insufficient data. We innovatively introduced a two-stage method. In the first stage, we present prior knowledge of 10 lesion signs through pre-training; in the second stage, the model implements the classification task with the help of human knowledge. With the pre-training of priori knowledge of 10 lesion signs from input images, KFWC locates the powerful image features in the fine-grained disease classification task and therefore achieves better classification. To demonstrate the effectiveness of KFWC, we conduct a series of experiments on a clinical dataset collected in cooperation with a Grade III Level A ophthalmology hospital in China. The AUC score of KFWC reaches 99.71%, with 6.69% over the best baseline and 4.14% over ophthalmologists. KFWC can also provide good interpretability and effectively alleviate the pressure of data collection and annotation in the field of fine-grained disease classification for wet-AMD. The model proposed in this paper effectively solves the difficulties of small data volume and high image similarity in the wet-AMD fine-grained classification task through a knowledge-driven approach. Besides, this method effectively relieves the pressure of data collection and annotation in the field of fine-grained classification. In the diagnosis of wet-AMD, KFWC is superior to previous work and human ophthalmologists. [ABSTRACT FROM AUTHOR]

The reservoir rocks in the volcanic weathered crust are characterized by plentiful dissolution pores, caverns and fractures. However, as an essential control factor of the reservoir distribution, volcanic dissolution is often ignored in quantitative studies. In this paper, we propose a complete artificial intelligence workflow to model and predict the volcanic dissolution distribution by integrating the image logging semi-quantitative analysis with seismic prediction. A synthetic reservoir property named DCV (Dissolution Comprehensive Values) is generated as logging curves from XRMI resistivity pseudo-pictures to indicate the intensity of dissolution. These curves are then used as the target for the seismic-based prediction in an artificial intelligence framework. A multi-layer artificial neural network (ANN) model is constructed in order to map the seismic attributes into the DCV. The methodology is demonstrated on a real case study from the Junggar basin in northwestern China. The maps and profiles from the prediction represent the dissolution values in the volcanic weathered crust. The predictions are consistent with the geological volcanic dissolution model provided by geological knowledge. It is concluded that the spatial dissolution distribution in volcanic weathered crust can be reliably predicted by this integrated method. • An image logging semi-quantitative method is proposed to estimate the volcanic dissolution intensity in 1D profiles. • A artificial neural network method is employed to map seismic attributes into the dissolution intensity. • An intuitive for the spatial distribution of the dissolution spaces in the volcanic weathered crust is provided. [ABSTRACT FROM AUTHOR]

[Display omitted] • In the case of a small number of known deposits and mineral occurrences, the prospecting prediction model based on the Siamese network can extract effective features without relying on prior knowledge to realize supervised prospecting prediction. • On the basis of sliding window data enhancement, this paper generates paired sample data sets by randomly combining deposit samples and non-deposit samples, which can further enhance the data and improve the generalization ability and prediction accuracy of the model to a certain extent. • Compared with the prediction results of the weight of evidence method and the convolutional neural network, the prediction results of the Siamese network are better, and 7 new gold prospecting areas have been discovered in Zhangjiakou, Hebei Province, China. Supervised neural networks constitute an important research area for the intelligent prediction of locations for prospecting mineral deposits. Accurate training of a supervised neural network requires many training samples, something that is often difficult to obtain. This paper reports the use of geological, geochemical, and geophysical data by a Siamese network to overcome the problem of insufficient training samples, and implements a supervised deep learning prospecting prediction method based on the Siamese network. Intelligent prediction for gold deposits prospecting is carried out for the Chongli mineral concentrate area in Zhangjiakou, Hebei Province, China, and compared with the weight of evidence method and convolutional neural network model. The results show that:(a) the performance of the Siamese network model is no less than that of the convolutional neural network (CNN) model and better than that of the weight of evidence (WOE) method; (b) the gold prospective areas differentiated by the established models are strongly consistent with geological and metallogenic characteristics in the study area. This study suggests Siamese network model as an effective mineral prospectivity modeling tool. This method is also suitable for prospecting prediction using geoscience data in other areas. [ABSTRACT FROM AUTHOR]

• A novel vector field-based SVR for building energy consumption prediction (ECP) is proposed. • Nonlinearity of the ECP models is transformed into linearity via vector field-based SVR. • Two high precision, generalization capability, and robustness energy consumption prediction models are established. • A real case study demonstrates the superiority of this study compared with previous studies. Building energy consumption prediction plays an irreplaceable role in energy planning, management, and conservation. Data-driven approaches, such as artificial neural networks, support vector regression, gradient boosting regression and extreme learning machine are the most advanced methods for building energy prediction. However, owing to the high nonlinearity between inputs and outputs of building energy consumption prediction models, the aforementioned approaches require improvement with regard to the prediction accuracy, robustness, and generalization ability. To counter these shortcomings, a novel vector field-based support vector regression method is proposed in this paper. Through multi-distortions in the sample data space or high-dimensional feature space mapped by a vector field, the optimal feature space is found, in which the high nonlinearity between inputs and outputs is approximated by linearity. Hence, the proposed method ensures a high accuracy, a generalization ability, and robustness for building energy consumption prediction. A large office building in a coastal town of China is used for a case study, and its summer hourly cooling load data are used as energy consumption data. The results indicate that the proposed method achieves better performance than commonly used methods with regard to the accuracy, robustness, and generalization ability. [ABSTRACT FROM AUTHOR]

Abstract The spatial heterogeneity of geochemical background is often ignored in geochemical anomaly recognition, leading to ineffective recognition of valuable anomalies for geochemical prospecting. In this paper, a Spatially Constrained Multi-Autoencoder (SCMA) approach is proposed to deal with such an issue in multivariate geochemical anomaly recognition, which includes two unique steps: (1) with the consideration of both chemical similarity and spatial continuity of geochemical samples, a region is divided into multiple sub-domains to discriminate the various backgrounds over space, through multivariate clustering, spatial filtering, and spatial fusion; and (2) the geochemical background of each sub-domain is learned and reconstructed by a multi-autoencoder structure, which is designed to reduce the effects of random initialization of weights in an autoencoder neural network. Finally, the anomaly score is calculated as the difference between the observed geochemical features and the reconstructed features. The performance of SCMA was demonstrated by a case study involving Cu, Mn, Pb, Zn and Fe 2 O 3 in stream sediment samples from the Chinese National Geochemical Mapping Project, in the southwestern Fujian province of China. The results showed that the spatial domain constraining greatly improved the quality of anomaly recognition, and SCMA outperformed several existing methods in all aspects. In particular, the anomalies from SCMA were the most consistent with the known Fe deposits in the area, achieving an AUC of 0.89. Highlights • Spatial partitioning discriminates spatial heterogeneity of geochemical background. • Multi-autoencoders reduce effects of random weight initialization of autoencoder. • SCMA outperformed other methods in experiments, achieving an AUC of 0.89. [ABSTRACT FROM AUTHOR]

Highlights • A novel two-stage modeling framework based on event sequence is developed. • A SIASA algorithm is presented to re-optimize the solution of first-stage model. • A data-driven method is proposed to accomplish the fast optimization of pipeline scheduling. • The experimental results of 50 cases are given to illustrate the superiority of the proposed method. Abstract The detailed scheduling of distributing products through pipelines is one of the most essential tasks in the management of multiproduct pipelines. The current methods of scheduling optimization are still limited by the dilemma between optimality and efficiency, especially when dealing with real-world scheduling issues. This paper introduces a two-stage mathematical model based on the event sequence, whose model scale greatly decreases after stripping the terms of event sequence. Then, a data-driven method is presented to learn a large number of existing scheduling data and accelerate the calculation of first-stage model. The method is decomposed into three parts: (1) take cold start to generate a good deal of basic training data; (2) train the neural network for the fast solution of first-stage model; (3) take real-world cases to improve the self-learning of neural network. A multiproduct pipeline in China is taken as the example to prove the practicability and superiority of the proposed method. The experimental results show that the proposed method could decrease the computation time from about several hours to several minutes. [ABSTRACT FROM AUTHOR]

Abstract Systems for monitoring the deformation and stress conditions of excavated high rock slopes are usually implemented for safety reasons and to predict the stability of future works. This paper adopts Bayesian methods for updating important geomechanical parameters namely: E (III 1), E (III 2), E (IV 2), E (f 8), c (III 1), c (III 2), c (V 1) and c (f 8) in these types of cases. The proposed method utilizes parametric sensitivity analysis, the BP neural network (back propagation neural network), and Bayesian updating to effectively reduce the number of variables, improve the computational efficiency and gradually update the random variables by using progressive monitoring information. The high rock slope excavation on the left bank at the Lianghekou Hydropower Station in China is illustrated as a detailed case study. Initially, only one type of measurement is first used for Bayesian updating (measured displacements or anchorage forces), and then both types of measurements are used. Compared to using only one type of measurement, the parameter uncertainty is reduced and the model accuracy is improved when both types of measurements are employed. Highlights • A Bayesian updating framework for rock slopes with multiple responses is proposed. • Random variables are gradually updated by using progressive monitoring information. • The effectiveness of three groups of data in Bayesian updating is discussed. • The proposed framework can be used for the prediction of subsequent excavation step. [ABSTRACT FROM AUTHOR]

Abstract Numerous machine learning-based land change models have been presented by researchers over the last two decades. To date, however, far less have simulated multiple land use classes and specific land use subclasses at the same time. In some areas of the world, it is important to simulate both of these dynamics to understand fully the drivers and consequences of land change. One important example is the process of urbanization in China, as urban policies have been developed that guide urban expansion, rural protections, and urban subclass development. This paper presents a new model integrating geographic information systems (GIS) with artificial neural networks (ANNs) to predict multiple transitions among land use types and urban subclasses in the Zhanggong District of Ganzhou city in China. We show that the model produces satisfactory goodness of fit values-based on location, quantity and spatial configuration-between simulated and observed land use maps for 2015. Our simulated future maps produced by the model for 2020 and 2025 demonstrate that transitions from farmland and forest to urban will remain the main pathway of urbanization although we predict that the rate will slow after 2025. The goals of urban planning should be aligned with land use planning according to "Combining multiple laws and regulations" in China. Taking into account the current and future land use transitions will enhance the accuracy and timeliness of land use policy making and urban land planning. For the sustainable land use in Zhanggong District, we argue for a strengthened regulation of the land market by government and believe that planning officials should guide the spatial distribution of land supply actively. Furthermore, improving the production, living and ecological functions of land resources are the key points to optimize urban land use functions and the allocation of land resources. We discuss how our model can be adapted to other areas to benefit land use management and urban planning in China. Highlights • GIS and ANNs were used to predict multiple land use transitions and urban subclasses. • A case study demonstrates that the model performs relatively well validated with several measures for goodness of fit. • The simulated maps suggest that farmland and forest are the most common candidates for urban expansion. • The methodology can be adapted to other study areas to benefit land use management and urban planning in China. [ABSTRACT FROM AUTHOR]

Recently security issues like investment and financing in China's power industry have become increasingly prominent, bringing serious challenges to the financial security of the domestic power industry. Thus, it deserves to develop financial safety evaluation towards the Chinese power industry and is of practical significance. In this paper, the GA (genetic algorithm) is used to optimize the connection weights and thresholds of the traditional BPNN (back propagation neural network) so the new model of BPNN based on GA is established, hereinafter referred to as GA-BPNN (back propagation neural network based on genetic algorithm). Then, an empirical example of the electric power industry in China during the period 2003–2010 was selected to verify the proposed algorithm. By comparison with three other algorithms, the results indicate the model can be applied to evaluate the financial security of China's power industry effectively. Then index values of the financial security of China's power industry in 2011 were obtained according to the tested prediction model and the comprehensive safety scores and grades are calculated by the weighted algorithm. Finally, we analyzed the reasons and throw out suggestions based on the results. The work of this paper will provide a reference for the financial security evaluation of the energy industry in the future. [ABSTRACT FROM AUTHOR]

This paper explores the optimization scheme of carbon trading in China based on a novel energy-saving and emission-reduction (ESER) system with carbon price constraints. With the aid of nonlinear dynamics theory, the dynamics behavior of the novel system is discussed. Genetic algorithm and back propagation neural network is used to identify the quantitative coefficients according to the statistical data of the second period in European Union (EU). Taking the actual situation in EU for instance, the variables which are sensitive to carbon trading are detailedly researched. Enlightened by the EU’s experience, an optimal road of China ’ s carbon trading is put forward. The results show that carbon emissions could be controlled by carbon trading. The investment to carbon trading hampers economic growth in the near future, and ESER technical progress is negatively correlated with carbon trading in the long run. Demand and supply relationship is closely related to carbon price, both are the important issues in carbon trading system. Excessive government control and extortionate carbon price will deliver the opposite effect and even fatal influence on carbon trading system. [ABSTRACT FROM AUTHOR]

This paper attempts to explore the evolvement rule of energy-saving and emission-reduction with changing economic growth rate based on a novel energy-saving and emission-reduction system with multi-variable constraints. Energy structure adjustment, economic growth rate, new energy technology progress and other constrained variables are introduced into the novel system with the aid of nonlinear dynamics. The dynamic behavior of the new system is discussed by means of nonlinear dynamics theory. The quantitative coefficients of the actual system are identified based on the genetic algorithm-back propagation neural network. A scenario study of the actual system is carried out, and some valuable conclusions are presented. Energy structure adjustment is driven more by economic considerations according to China’s national conditions. Energy structure adjustment could perfectly control energy intensity, without obvious potential negative impact on economic growth. New energy technology progress has a better effect on controlling energy intensity, and the more mature the technology is, the better the effect is. Energy intensity is sensitive to economic growth rate. There is an optimal interval of economic growth rate, and energy intensity could be effectively controlled by adjusting corresponding constraint condition in this interval. [ABSTRACT FROM AUTHOR]

The coordinated control systems (CCS) in ultra-supercritical thermal power unit, like many other industrial systems, is a complex multivariable system with severe nonlinearity, strong multivariable coupling and uncertainties. In order to meet the requirements of operational stability, economy. etc in ultra-supercritical unit, it is necessary to establish its accurate mathematical model and further design the advanced controller. Against this background, a new fuzzy neural network modeling method is proposed in this paper. First of all, the incremental model is considered separately to improve the rationality of the local linear model structure. Then, the parameters in antecedent part is initialized by a kernel k -means++ algorithm, in which Xie-Beni index is used to optimize the number of fuzzy rules. Finally, supervised adaptive gradient descent algorithm and artificial immune particle swarm optimization algorithm work in stages to complete the training of the consequent part parameters. The proposed modeling method in this paper is applied to a 1000 MW unit in China and shows satisfactory accuracy. In the established model, the MSE of power output, main steam pressure and separator outlet steam temperature are 0.0099, 1.21E-4, 0.0023, respectively. Both numerical and graphical simulation results confirm the effectiveness of the presented fuzzy neural network in modeling. [ABSTRACT FROM AUTHOR]

Abstract: Building cooling load prediction is one of the key factors in the success of energy-saving measures. Many computational models available in the industry today have been developed from either forward or inverse modeling approaches. However, most of these models require extensive computer resources and involve lengthy computation. This paper discusses the use of data-driven intelligent approaches, a probabilistic entropy-based neural (PENN) model to predict the cooling load of a building. Although it is common knowledge that the presence and activity of building occupants have a significant impact on the required cooling load of buildings, practices currently adopted in modeling the presence and activity of people in buildings do not reflect the complexity of the impact occupants have on building cooling load. In contrast to previous artificial neural network (ANN) models, most of which employ a fixed schedule or historic load data to represent building occupancy in simulating building cooling load, this paper introduces two input parameters, dynamic occupancy area and rate and uses it to mimic building cooling load. The training samples used include weather data obtained from the Hong Kong Observatory and building-related data acquired from an existing grade A mega office buildings in Hong Kong with tenants including many multi-national financial companies that require 24-h air conditioning seven days a week. The dynamic changes that occur in the occupancy of these buildings therefore make it very difficult to forecast building cooling load by means of a fixed time schedule. The performance of simulation results demonstrate that building occupancy data play a critical role in building cooling load prediction and that their use significantly improves the predictive accuracy of cooling load models. [Copyright &y& Elsevier]

Abstract: The suitability of the project delivery system (PDS) selected for a project greatly influences the efficiency to conduct a project. It is not an easy task to select an appropriate PDS as a large amount of ambiguous information exists. The paper aims to develop a PDS selection model to help owners to make a decision. The similar projects are identified through the similarity metrics between the target project to be predicted and those in the database. In addition, some of the indicator values are examined and modified through DEA-BND model, and then they are trained by ANN model to predict an appropriate PDS for the target project. A survey was conducted by postal questionnaire to empirically validate the reliability of the model in China. The indicator system for the selection of an appropriate PDS is established. Through the comparison of results predicted by different models, it is found that the PDS selection model developed in this paper can predict PDS precisely, and shows higher reliability than the ANN model. A PDS selection model is developed by inputting project-specific data, which proves to be more accurate and less dependent on experts’ judgment. Its practical application will benefit the owner’s decision making in the selection of the PDS. [ABSTRACT FROM AUTHOR]

Abstract: In this paper, we investigate the statistical properties of the fluctuations of the Chinese Stock Index, and we study the statistical properties of HSI, DJI, IXIC and SP500 by comparison. According to the theory of artificial neural networks, a stochastic time effective function is introduced in the forecasting model of the indices in the present paper, which gives an improved neural network – the stochastic time effective neural network model. In this model, a promising data mining technique in machine learning has been proposed to uncover the predictive relationships of numerous financial and economic variables. We suppose that the investors decide their investment positions by analyzing the historical data on the stock market, and the historical data are given weights depending on their time, in detail, the nearer the time of the historical data is to the present, the stronger impact the data have on the predictive model, and we also introduce the Brownian motion in order to make the model have the effect of random movement while maintaining the original trend. In the last part of the paper, we test the forecasting performance of the model by using different volatility parameters and we show some results of the analysis for the fluctuations of the global stock indices using the model. [Copyright &y& Elsevier]

Environmental pollution and low resource utilization efficiency caused by pyrometallurgy have seriously restricted the sustainable development of secondary lead smelting industry. A large number of studies focus on the research of hydrometallurgy to replace pyrometallurgy aiming at pollution prevention. However, due to economic cost, quality of secondary lead product and secondary pollution, hydrometallurgy hasn't been widely applied by now. At present, most of the researches of pyrometallurgy focus on its environmental pollution assessment, or merely focus on the recovery efficiency of secondary lead. There are fewer researches on the synergic optimization methodology of pollution prevention and resource recovery for secondary lead smelting process. BP neural network is a type of model widely used in industrial processes optimization. While the gradient method adopted by the BP neural network often falls into a local minimum. If the fitting function is too complicated, there may be multiple fitting local minima, which will cause great obstacles to practical applications. Therefore, according to the characteristics of secondary lead smelting process, this paper uses a BP neural network-based nonlinear optimization combined with an approximate global optimization method to obtain the optimal smelting parameters. The innovative feature of this paper is that after the first stage of the neural network preprocessing has formed the fitting of the smelting process, the smelting parameters optimization process is carried out based on the fitted neural network model. According to the characteristics of the entire two-stage process, as well as the corresponding conditional constraints and the smoothing process of the BP neural network output function, we have formed a two-stage BPNLP network model with formally unified constraint by adopting the approximate global optimal search method. Compared with the average level of pollution prevention and lead recovery efficiency of pyrometallurgy technology in China, the pollution load Sulphur, lead, arsenic and cadmium in smelting flue gas per unit secondary lead product has been reduced by 78.40%, 52.00%, 72.63% and 16.00% respectively, and the recovery efficiency of lead increased by 8.85%. Thus, the two-stage BPNLP model can achieve the goal of synergic optimization of pollution prevention and resource recovery of pyrometallurgy technology of secondary lead smelting industry which can also provide effective methodological guidance for the related research of other industries. Image 1 • A synergic optimization methodology of pollution prevention and resource recovery for secondary lead smelting process. • A two-stage BPNLP network model with formally unified constraint by adopting the approximate global optimal search method. • It reduced the pollution load by 16.00%∼ 78.40% and increased lead recovery by 8.85% based on this optimization. • It is necessary to issue cleaner production technology guide of this industry in China. [ABSTRACT FROM AUTHOR]

Food risk analysis technique is of great significance in human health and safety. This paper investigates the issue of food safety risk identification and early warning based on heterogeneous graph attention network. First, the selection of food safety risk heterogeneous indicators (such as food category, hazard, region, etc.) is analyzed, since they are the effective factors to describe risk levels, then a food safety risk assessment index system is constructed based on these factors. Second, a heterogeneous graph attention network is proposed to fuse the heterogeneous risk indicators, resulting in the novel risk profile of food safety. Finally, the proposed heterogeneous graph attention network is implemented to the problem of food safety risk early warning, which could provide some basis of risk management decision. A data set of food detection in China is used to verify the proposed method, the case study results suggest that the proposed risk profile is a valuable way to identify the food safety risk. • The main risk factors affecting food safety are analyzed, and a food safety risk evaluation index system is established. • Heterogeneous graph attention network is used to train heterogeneous data and establish food safety risk reasoning model. • The model can accurately predict the risk level of various kinds of food. [ABSTRACT FROM AUTHOR]

The F2 layer critical frequency of the ionosphere ( f oF2) is one of the most significant parameters for studying the ionosphere. To investigate the large-scale characteristics of the ionosphere over particular regions, modeling f oF2 is an effective method. In this paper, we use both the Kriging (KG) and neural network (NN) methods to reconstruct f oF2 maps over North China. The neural network is trained by the genetic algorithm (GA) to avoid the ‘local minimum’ phenomenon in most NN applications. We then carry out a comparison between f oF2 provided by both the KG and NN methods with vertical model operation of ionosonde data including Beijing, Qingdao, Suzhou, and Changchun. All of the f oF2 data used in the comparison are obtained from the oblique and vertical mode operation of ionosonde from the China Ground-based Seismo-ionospheric Monitoring Network. To allow for a possible seasonal and diurnal variation, data obtained from summer, winter, and equinox months are applied in the present comparison. In addition, we make a comparison during a magnetic storm period. The results of our comparisons demonstrate that both the KG and NN methods are appropriate tools for modeling f oF2 maps. However, when the data set is spare, the performance of the NN method is better than the KG method. On the other hand, the KG method is more robust than the NN method during a magnetic storm. [ABSTRACT FROM AUTHOR]

[Display omitted] • Wavelet-based neural network with Monto Carlo simulation is introduced for data-driven mineral prospectivity mapping. • The proposed algorithm alleviates the data imbalance issue and accesses the uncertainties in mineral prospectivity mapping. • We present a mineral prospectivity map of W-Sn ore deposits in the Nanling metallogenic province, China. The Nanling Range in South China is endowed with abundant W-Sn and other important rare metal resources associated with granitic intrusions, but the rate of new major mineral discoveries has been drastically diminished over the last decades. Data-driven mineral prospectivity mapping (MPM) using machine learning is emerging as a powerful tool in support of mineral exploration targeting at regional or camp scale. However, MPM based on supervised learning faces some general problems, notably including subtle information obscured in exploration data and imbalanced training samples. In this paper, we proposed a novel ensemble scheme for MPM using wavelet neural network (WNN) and Monte Carlo simulation (MCs) to address the forementioned issues. Specifically, the purpose of using WNN based on multiscale wavelet analysis is to capture weak or hidden (geophysical and geochemical) information caused by concealed ore deposits, while an undersampling MCs (UMCs) algorithm is employed to assess uncertainties caused by data imbalance and lessen its impact on MPM. Subtle (weak and mixing) information related to concealed mineralization, including geophysical and geochemical anomalies, were extracted using wavelet analysis at first, and then a dozen of predictive evidences was integrated based on WNN using UMCs for producing a W-Sn perspectivity map. The results suggest that WNN has a higher prediction accuracy (∼90%) in comparison to the artificial neural network (ANN) (∼85%). Moreover, the improved AUC value (∼0.9) of WNN based on UMCs compared to the classic ANN (∼0.82) and WNN (∼0.85) suggests that the proposed ensemble algorithm improves the geological generalization of machine learning. Revisiting WNN predictions by uncertainties produced more sharply focused exploration targets of W-Sn deposits (covering ∼5% of the study area). The resulting predictive map provides important clues of W-Sn deposit occurrences which could guide and stimulate future mineral exploration in the Nanling Range. [ABSTRACT FROM AUTHOR]

Abstract: In clinical treatment processes, inpatient length of stay (LOS) is not only a readily available indicator of hospital activity, but also a reasonable proxy of resource consumption. Accurate inpatient LOS prediction has strong implications for health service delivery. Major techniques proposed (statistical approaches or artificial neuronal networks) consider a priori knowledge, such as demographics or patient physical factors, providing accurate methods to estimate LOS at early stages of the patient (admission). However, unexpected scenarios and variations are common places of clinical treatment processes that have a dramatical impact on the LOS. Therefore, these predictors should deal with adaptability, considering the temporal evolution of the patient. In this paper, we propose an inpatient LOS prediction approach across various stages of clinical treatment processes. This proposal relies on a kind of regularity assumption demanding that patient traces of the specific treatment process with similar medical behaviors have similar LOS. Therefore, this approach follows a Case-based Reasoning methodology since it predicts an inpatient LOS of a partial patient trace by referring to the past traces of clinical treatment processes that have similar medical behaviors with the current one. The proposal is evaluated using 284 patient traces from the pulmonary infection CTPs, extracted from Zhejiang Huzhou Central Hospital of China. [Copyright &y& Elsevier]

Abstract: In clinical treatment processes, inpatient length of stay (LOS) is not only a readily available indicator of hospital activity, but also a reasonable proxy of resource consumption. Accurate inpatient LOS prediction has strong implications for health service delivery. Major techniques proposed (statistical approaches or artificial neuronal networks) consider a priori knowledge, such as demographics or patient physical factors, providing accurate methods to estimate LOS at early stages of the patient (admission). However, unexpected scenarios and variations are commonplaces of clinical treatment processes that have a dramatical impact on the LOS. Therefore, these predictors should deal with adaptability, considering the temporal evolution of the patient. In this paper, we propose an inpatient LOS prediction approach across various stages of clinical treatment processes. This proposal relies on a kind of regularity assumption demanding that patient traces of the specific treatment process with similar medical behaviors have similar LOS. Therefore, this approach follows a Case-based Reasoning methodology since it predicts an inpatient LOS of a partial patient trace by referring to the past traces of clinical treatment processes that have similar medical behaviors with the current one. The proposal is evaluated using 284 patient traces from the pulmonary infection CTPs, extracted from Zhejiang Huzhou Central Hospital of China. [Copyright &y& Elsevier]

• A DRL based approach is applied to adaptive control of STATCOM-ADC parameters. • An ANN-based estimator is proposed for system identification. • The proposed novel control agent is adaptive and robust. • An online application strategy is proposed to avoid frequent parameter adjustment. Due to the fluctuation characteristics of the wind turbine (WT) production, the design of the control system needs to ensure the stability of the power system at different wind speeds. In this context, a WT-oriented adaptive robust control agent for a static synchronous compensator having additional damper controller (STATCOM-ADC) is proposed in this paper. An artificial neural network based estimator for system identification which can identify the equivalent transfer function of the whole system in real time is used in this paper. Then a Deep Deterministic Policy Gradient (DDPG) algorithm is adopted to train the agent on learning the adaptive robust control strategy for STATCOM-ADC. Compared with other control strategies, the proposed method has modelled self-learning abilities, and the parameter settings provided by the agent for one operation state of the system are still applicable to other states. Simulation results on the actual wind farm located in China Ningxia province show that the proposed method can enhance the stability of the system under different fault conditions and wind speeds. [ABSTRACT FROM AUTHOR]

Taking the Huaidian Sluice on the Shaying River in China as an example, this paper establishes the calculation model of the free flow based on artificial neural network and regression analysis. Four forms of discharge coefficient calculation equations were obtained by regression analysis, and three neural network models were established. The model is fully verified by using the measured data. The experimental results show that the third-order polynomial and multilayer perceptron neural network have better adaptability. The advantages and disadvantages of the different methods are analyzed and the cause of the error is identified. It provides a theoretical basis for dealing with the discharge calculation of small and medium dam. • Applying traditional regression methods and artificial neural networks to the calculation of sluice free outflows is an important innovation. • This paper establishes a multivariate and multi-combined input data set, which no one has tried. • By comparing the results of the two methods, we analyze the difference of the results in principle and find out the rules. It provides a new entry point for other scholars to study this. [ABSTRACT FROM AUTHOR]

• Multi-feature & stacking were used for automatic grading cataract into six levels based on the fundus images. • Two support vector machine (SVM) classifiers are used as base-learners and fully connected neural network (FCNN) are used as meta-learner to output the final classification result. • Multi-feature & Stacking achieve higher grading performance and lower volatility than grading using high-level features and texture features. • Automatic cataract grading can be used to help government assist people more accurately in poor areas. The shortage of ophthalmologists in rural areas in China causes a lot of cataract patients not getting timely diagnosis and effective treatment. We develop an algorithm and platform to automatically diagnose and grade cataract based on fundus images of patients. This method can help government assisting poor population more accurately. The novel six-level cataract grading method proposed in this paper focuses on the multi-feature fusion based on stacking. We extract two kinds of features which can effectively distinguish different levels of cataract. One is high-level features extracted from residual network (ResNet18). The other is texture features extarcted by gray level co-occurrence matrix (GLCM). Then a frame is proposed to automatically grade cataract by the extracted features. In the frame, two support vector machine (SVM) classifiers are used as base-learners to obtain the probability outputs of each fundus image, and fully connected neural network (FCNN) are used as meta-learner to output the final classification result, which consists of two fully-connected layers. The accuracy of six-level grading achieved by the proposed method is up to 92.66% on average, the highest of which reaches 93.33%. The proposed method achieves 94.75% accuracy on four-level grading for cataract, which is at least 1.75% higher than those of the exiting methods. Six-category cataract classification algorithm show that Multi-feature & Stacking proposed in this paper helps achieve higher grading performance and lower volatility than grading using high-level features and texture features respectively. We also apply our algorithm into four-level cataract grading system and it shows higher accuracy compared with previous reports. [ABSTRACT FROM AUTHOR]

At present, integrating investor sentiment into the prediction of stock market crisis has attracted more and more attention. However, the existing researches only considered the impact of the market indicators and the micro investor sentiment on stock market, while ignored the impact of the macro one. Therefore, in this paper, we develop an early warning system for predicting stock market crisis via market indicators and mixed frequency investor sentiments. The proposed early warning system consists of five components, which includes the construction of mixed frequency investor sentiments that consider both macro and micro investor sentiments, the identification of stock market crisis, the determination of the forecast horizon using Ensemble Empirical Mode Decomposition (EEMD), the definition of the early warning signal, and the building of prediction model using artificial neural network (ANN). Lastly, we apply the developed warning system to China's stock markets. Experimental results show that mixed frequency investor sentiments can improve the early warning ability in predicting the stock market crisis, and the ANN model has better performance than other methods including Support Vector Machine (SVM), Decision Tree (DT), Random Forest (RF), Gradient Boosting Decision Tree (GBDT), K-Nearest Neighbor (KNN), and Logistic Regression (LR). • Combine investor sentiment to predict stock market crisis. • Construct the mixed frequency investor sentiments. • Extensive experimental results verify the effectiveness of constructed sentiments. [ABSTRACT FROM AUTHOR]

Abstract: The main purpose of this study is to compare the following six GIS-based models for susceptibility mapping of earthquake triggered landslides: bivariate statistics (BS), logistic regression (LR), artificial neural networks (ANN), and three types of support vector machine (SVM) models that use the three different kernel functions linear, polynomial, and radial basis. The models are applied in a tributary watershed of the Fu River, a tributary of the Jialing River, which is part of the area of China affected by the May 12, 2008 Wenchuan earthquake. For this purpose, eleven thematic data layers are used: landslide inventory, slope angle, aspect, elevation, curvature, distance from drainages, topographic wetness index (TWI), distance from main roads, distance from surface rupture, peak ground acceleration (PGA), and lithology. The data layers were specifically constructed for analysis in this study. In the subsequent stage of the study, susceptibility maps were produced using the six models and the same input for each one. The validations of the resulting susceptibility maps were performed and compared by means of two values of area under curve (AUC) that represent the respective success rates and prediction rates. The AUC values obtained from all six results showed that the LR model provides the highest success rate (AUC=80.34) and the highest prediction rate (AUC=80.27). The SVM (radial basis function) model generates the second-highest success rate (AUC=80.302) and the second-highest prediction rate (AUC=80.151), which are close to the value from the LR model. The results using the SVM (linear) model show the lowest AUC values. The AUC values from the SVM (linear) model are only 72.52 (success rates) and 72.533 (prediction rates). Furthermore, the results also show that the radial basis function is the most appropriate kernel function of the three kernel functions applied using the SVM model for susceptibility mapping of earthquake triggered landslides in the study area. The paper also provides a counter-example for the widely held notion that validation performances of the results from application of the models obtained from soft computing techniques (such as ANN and SVM) are higher than those from applications of LR and BA models. [Copyright &y& Elsevier]

Abstract: Wind power forecasting system is useful to increase the wind energy penetration level. Latest statistics show that China has been the biggest wind energy market throughout the world. However, few studies have been published to introduce the wind energy forecasting technologies in China. This paper presents the performance evaluation and accuracy enhancement of a novel day-ahead wind power forecasting system in China. This system consists of a numerical weather prediction (NWP) model and artificial neural networks (ANNs). The NWP model is established by coupling the Global Forecasting system (GFS) with the Weather Research and Forecasting (WRF) system together to predict meteorological parameters. In addition, Kalman filter has been integrated in this system to reduce the systematic errors in wind speed from WRF and enhance the forecasting accuracy. The numerical results from a real world case are proven the effectiveness of this forecasting system in terms of the raw wind speed correction and wind power forecasting accuracy. The Normalized Root Mean Square Error (NRMSE) has a month average value of 16.47%, which is an acceptable error margin for allowing the use of the forecasted values in electric market operations. This forecasting system is profitable for increasing the wind energy penetration level in China. [Copyright &y& Elsevier]

Abstract: In this paper, a modified EMD-FNN model (empirical mode decomposition (EMD) based feed-forward neural network (FNN) ensemble learning paradigm) is proposed for wind speed forecasting. The nonlinear and non-stationary original wind speed series is first decomposed into a finite and often small number of intrinsic mode functions (IMFs) and one residual series using EMD technique for a deep insight into the data structure. Then these sub-series except the high frequency are forecasted respectively by FNN whose input variables are selected by using partial autocorrelation function (PACF). Finally, the prediction results of the modeled IMFs and residual series are summed to formulate an ensemble forecast for the original wind speed series. Further more, the developed model shows the best accuracy comparing with basic FNN and unmodified EMD-based FNN through multi-step forecasting the mean monthly and daily wind speed in Zhangye of China. [Copyright &y& Elsevier]

Abstract: Urbanization induces detrimental effects on the eco-environment that are beginning to be extensively described. However, the adoption of suitable indicators and reliable methods still requires attention to provide a basis for a more accurate understanding of eco-environmental effects from urbanization. The aggregated index system representing the coupling relationships between urbanization and eco-environment was introduced and an integrated sustainable development approach (ISD) to simulate and evaluate the integrative effects was developed in this paper. The ISD consists of modules of the coupling relationship assessments, systematic analysis of potential eco-environmental changes, and sustainability evaluation. An interpretative structural modeling (ISM) and grey relative technique (GRT) are used to analyze the systematical structure and assess the coupling relationships. A system dynamics model (SD) and artificial neural network (ANN) are used to simulate the potential environmental changes and compare the sustainability, respectively. An application study of Jiangsu province in China was performed, where the general eco-environmental integrity is under significant urbanization pressure. The potential eco-environmental scenarios from 2010 to 2015 under natural, populated, economic, spatial and social urbanization patterns were simulated and analyzed. The result reveals that the urbanization sustainability may be met on condition that either populated urbanization or social urbanization pattern is adopted in Jiangsu province, China. The aggregated indexes and ISD may help local authorities better understand and address the complex coupling relationship, and develop improved regional environmental management strategies that better balance urbanization and eco-environmental conservation. [Copyright &y& Elsevier]

Abstract: As a regular data-driven method, Artificial Neural Networks (ANNs) are popular in building energy prediction. In this paper, an alternative approach, namely, hybrid genetic algorithm-adaptive network-based fuzzy inference system (GA-ANFIS) is presented. In this model, GA optimizes the subtractive clustering’s radiuses which help form the rule base, and ANFIS adjusts the premise and consequent parameters to optimize the forecasting performance. a hierarchical structure of ANFIS is also suggested to solve the probably curse-of-dimensionality problem. The performance of the proposed model is compared with ANN using two different data sets, which are collected from the Energy Prediction Shootout I contest and a library building located in Zhejiang University, China. Results show that the hybrid GA-ANFIS model has better performance than ANN in term of prediction accuracy. The proposed model also has the same scale of modeling time as ANN if parameters in GA procedure are carefully selected. It can be regarded as an alternative method in building energy prediction. [Copyright &y& Elsevier]

Abstract: Wind energy, which is intermittent by nature, can have a significant impact on power grid security, power system operation, and market economics, especially in areas with a high level of wind power penetration. Wind speed forecasting has been a vital part of wind farm planning and the operational planning of power grids with the aim of reducing greenhouse gas emissions. Improving the accuracy of wind speed forecasting algorithms has significant technological and economic impacts on these activities, and significant research efforts have addressed this aim recently. However, there is no single best forecasting algorithm that can be applied to any wind farm due to the fact that wind speed patterns can be very different between wind farms and are usually influenced by many factors that are location-specific and difficult to control. In this paper, we propose a new hybrid wind speed forecasting method based on a back-propagation (BP) neural network and the idea of eliminating seasonal effects from actual wind speed datasets using seasonal exponential adjustment. This method can forecast the daily average wind speed one year ahead with lower mean absolute errors compared to figures obtained without adjustment, as demonstrated by a case study conducted using a wind speed dataset collected from the Minqin area in China from 2001 to 2006. [Copyright &y& Elsevier]

Abstract: Crop acreage estimation is a key aspect to forecast crop production. Maize acreage estimation becomes more and more important because the fast production changes every year due to the dynamics of the prices. This paper focuses on maize acreage estimation in the North China Plain using ENVISAT MERIS and CBERS-02B CCD data of 2008. Firstly, adaptive maximum likelihood classification of CBERS-02B CCD images based on ground survey provided reliable maize area fraction image (AFI). CBERS derived AFIs (as reference AFI) were used to train a 3-layer back-propagation neural network, this was then used to the whole MERIS data to generate MERIS AFIs (AFIe). To estimate maize acreage, the maize AFI from MERIS was masked with cropland dataset and maize acreages were estimated by zonal statistic of maize AFI at district level. The statistical results were also modified using a non-arable coefficient to remove the effects of non-arable factors. The results showed a close relationship between estimated and statistical maize acreage (R 2 ≈0.88). At province level, the estimation error is approximately 8%. This method is valuable for wide-scale, regional crop acreage estimation at the early stage of growing season. The study gives suggestions about high resolution image acquisition, spatial distribution and cropland datasets. [Copyright &y& Elsevier]

Abstract: The three-dimensional energy resources demand-supply system is established for two regions of China, in which determination of unknown parameters is significant for the real energy resources demand-supply system. In this paper, based on Shanghai’s energy statistic data (1999–2005), the parameters of the energy resources demand-supply system can be identified by using the neural network method, and an energy resources demand-supply system reflecting the real energy resources demand-supply relationship in Shanghai is obtained. The dynamical behavior of this system is also analyzed. Theoretical analysis and numerical simulation indicate that the obtained energy resources demand-supply system has the capacity of self-regulation and demonstrates a steady state. Finally, to ensure the steady development of the energy resources demand-supply system, corresponding measures are proposed. [Copyright &y& Elsevier]

Abstract: Suitability evaluation of urban construction land based on geo-environmental factors is the process of determining the fitness of a given tract of land for construction. This process involves a consideration of the geomorphology, geology, engineering geology, geological hazards, and other geological factors and is the basis of urban construction land planning and management. With the support of Geographic Information Systems (GIS), grid analysis, and geo-spatial analysis techniques, four factor groups comprising nine separate subfactors of geo-environmental attributes were selected to be used in the evaluation of the suitability level for construction land in Hangzhou. This was based on K-means clustering and back-propagation (BP) neural network methods due to their advantages in fast computing, unique adaptive capacity, and self-organization. Simultaneously, the evaluation results based on K-means clustering and BP neural network were compared and analyzed, and the accuracy evaluation was set. The results showed that the geo-environmental suitability evaluation results of construction land based on K-means clustering and BP neural network were similar in terms of the distribution and scale of construction land suitability level. At the same time, the results of the two evaluation methods were consistent with the variability in suitability level, engineering geology, and hydrogeology of Hangzhou. The results also showed that the real advantage of the methods proposed in this paper lies in their capacity to streamline the mapping process and to ensure that the results are consistent throughout. The suitability level of the urban construction land based on the geo-environment in Hangzhou was divided into four construction sites: land for building super high-rise and high-rise buildings, land for building multistorey buildings, land for low-rise buildings, and nonbuilding land. The results of the suitability evaluation for each category will provide a scientific basis for decision-making in urban development in Hangzhou. [Copyright &y& Elsevier]

Abstract: Nitrate nitrogen (NO3 −-N) from agricultural activities has become the main source of groundwater pollution. A spatial distribution pattern of groundwater NO3 −-N pollution is vital for agricultural ecological and environmental management. The objective of this paper is to investigate the potential of artificial neural network to explore the spatial distribution of groundwater NO3 −-N pollution in Shandong intensive farming regions of China. A detailed field campaign has been carried out to obtain the 216 sample site data focusing on the intensive farming regions in Shandong province. Considering the practical difficulty of the complex nonlinear relationship between multi-factors and groundwater nitrate, a Back Propagation Neural Network (BPNN) was developed for modeling groundwater NO3 −-N concentration. In order to perform the analysis, both natural and anthropogenic factors have been studied, such as soil characteristics, fertilizer usage and terrain factors and so on. Finally, soil organic matter content, total nitrogen content and nitrogen fertilizer data were chosen as input features of the BPNN for having the best correlation with groundwater NO3 −-N concentration. The results indicated that areas with higher NO3 −-N concentration in groundwater are mainly located in the region of excessive use of nitrogen fertilizer and low groundwater runoff modulus. The application results suggested that the BPNN provide a promising approach for analyzing the spatial variability of the groundwater NO3 −-N concentration. [Copyright &y& Elsevier]

Abstract: The fire signals are much weaker in low oxygen concentration and low pressure environment such as Tibet. Fire detectors which were calibrated in correlating standard conditions cannot work well in such condition. This paper presents a synthesis method of GM(1,1) grey prediction model and adaptive neuro-fuzzy inference system (ANFIS) in advance to detect fire and to make it work in the environment. The theoretical analysis of the algorithm and experimental evaluation in Tibet are presented. In this process, the grey GM(1,1) predict model can anticipate the development of fire signals without any assumption, thus allowing earlier fire alarm than traditional fire detection equipments, meanwhile, ANFIS can make sure the data processing more accurate to avoid false alarms. This work will supply useful suggestions with the fire detectors design in low ambient pressure and low oxygen concentration such as Tibet, etc. [Copyright &y& Elsevier]

Abstract: Under limited resources in corporation education training, to enhance human resources quality, making education training program planning more efficient is a significant issue in training future talents. In accordance with Taiwan TrainQuali System (TTQS), the basic training structure is ton specify P (Plan) and D (Design). Ensuing results will be easier and successful. From TTQS database of Bureau of Employment and Vocational Training, corporations in Taoyuan, Hsinchu and Miaoli winning Gold Medals (Group B) have gaps outside control line in P and D. Enhancement is needed in the gap. The paper aims at a certain company winning Gold Medals in Taoyuan, Hsinchu and Miaoli to locate hidden or unobvious information with data mining, which will help future education training course planning and design. The researchers use two-stage clustering (SOM and K-means) under data mining theory to collect personnel training data of Automobile Corporation A in Taiwan and China with data mining and analysis. The results under the two algorithms will serve as reference for future education training courses. In the end, in combination of back-propagation neural network to develop education training prediction model, the research offers reference for writing knowledge management system to enhance effects of personnel participation in training at corporations. [ABSTRACT FROM AUTHOR]

Abstract: Financial volatility refers to the intensity of the fluctuations in the expected return on an investment or the pricing of a financial asset due to market uncertainties. Hence, volatility modeling and forecasting is imperative to financial market investors, as such projections allow the investors to adjust their trading strategies in anticipation of the impending financial market movements. Following this, financial volatility trading is the capitalization of the uncertainties of the financial markets to realize investment profits in times of rising, falling and side-way market conditions. In this paper, an intelligent straddle trading system (framework) that consists of a volatility projection module (VPM) and a trade decision module (TDM) is proposed for financial volatility trading via the buying and selling of option straddles to help a human trader capitalizes on the underlying uncertainties of the Hong Kong stock market. Three different measures, namely: (1) the historical volatility (HV), (2) implied volatility (IV) and (3) model-based volatility (MV) of the Hang Seng Index (HSI) are employed to quantify the implicit volatility of the Hong Kong stock market. The TDM of the proposed straddle trading system combines the respective volatility measures with the well-established moving-averages convergence/divergence (MACD) principle to recommend trading actions to a human trader dealing in HSI straddles. However, the inherent limitation of the MACD trading rule is that it generates time-delayed trading signals due to the use of moving averages, which are essentially lagging trend indicators. This drawback is intuitively addressed in the proposed straddle trading system by applying the VPM to compute future projections of the volatility measures of the HSI prior to the activation of the TDM. The VPM is realized by a self-organising neural-fuzzy semantic network named the evolving fuzzy semantic memory (eFSM) model. As compared to existing statistical and computational intelligence based modeling techniques currently employed for financial volatility modeling and forecasting, eFSM possesses several desirable attributes such as: (1) an evolvable knowledge base to continuously address the non-stationary characteristics of the Hong Kong stock market; (2) highly formalized human-like information computations; and (3) a transparent structure that can be interpreted via a set of linguistic IF–THEN semantic fuzzy rules. These qualities provide added credence to the computed HSI volatility projections. The volatility modeling and forecasting performances of the eFSM, when benchmarked to several established modeling techniques, as well as the observed trading returns of the proposed straddle trading system, are encouraging. [Copyright &y& Elsevier]

Abstract: Using a ball mill coal-pulverizing system as a motivating/application example, a class of complex industrial processes is investigated in this paper, which has strong couplings among loops, high nonlinearities and time-varying dynamics under different operation conditions. Focusing on such processes, an intelligent decoupling control method is developed, where the effects of nonlinearities are dealt with by neural network compensations and coupling effects are handled by specifically designed decoupling compensators, while the effect of time-varying dynamics is treated by a switching mechanism among multiple models. The stability and convergence of the closed-loop system are analyzed. The proposed method has been applied to the ball mill coal-pulverizing systems of 200MW units in a heat power plant in China. Application results show that the system outputs are maintained in desired scopes, the electric energy consumption per unit coal has been reduced by 10.3%, and the production rate has been increased by 8%. [Copyright &y& Elsevier]

Abstract: This paper proposes the use of a coupled fault tree analysis (FTA) and artificial neural network (ANN) model to improve the prediction of the potential risk of coal and gas outburst events during the underground mining of thick and deep Chinese coal seams. The model developed has been used to investigate the gas emission characteristics and the geological conditions that exist within the Huaibei coal mining region, Anhui province, China. The coal seams in this region exhibit a high incidence of coal and gas outbursts. An analysis of the results obtained from an initial application of an FTA model, identified eight dominant model parameters related to the gas content or geological conditions of the coal seams, which characterize the potential risk of in situ coal and gas outbursts. The eight dominant model parameters identified by the FTA method were subsequently used as input variables to an ANN model. The results produced by the ANN model were used to develop a qualitative risk index to characterize the potential risk level of occurrence of coal and gas outburst events. Four different potential risk alarm levels were defined: SAFE, POTENTIAL, HIGH and STRONG. Solutions to the prediction model were obtained using a combination of quantitative and qualitative data including the gas content or gas pressure and the geological and geotechnical conditions of coal seams. The application of this combined solution method identified more explicit and accurate model relationships between the in situ geological conditions and the potential risk of coal and gas outbursts. An analysis of the model solutions concluded that the coupled FTA and ANN model may offer a reliable alternative method to forecast the potential risk of coal and gas outbursts. [ABSTRACT FROM AUTHOR]

Abstract: Ecological footprint (EF) forecasting is essential for dynamically evaluating human impact on earth as well as for planning for a sustainable future. In this paper, a radial basis function neural network (RBFNN) model was developed to forecast the total ecological footprint (TEF) from 2006 to 2015. For a case study of Wuhan city, Hubei province in central China, per capita ecological footprint (EF) and biological capacity (BC) were calculated from 1988 to 2005. Partial least square (PLS) was used to select the important impact factors. We put the selected socio-economic factors as input and the TEF as output together to build RBFNN model and predict the development trends of the TEF in the following 10 years. Five-fold cross-validation was conducted to validate the model in the process of input selection and RBFNN model training. From the results, continuous increase of per capita EF (1988–2005) indicated stronger and stronger human effect on the district and Wuhan''s ecological state is in the ecological deficit. Up to 2015, the district would have been bearing accumulative TEF of 24.782 million gha, which is near 2.5 times of that in 1988. Although the increase rate of gross domestic product (GDP) would be restricted in a lower level from 2006 to 2015, the urban ecological environmental burden could only respond to the socio-economic circumstances moderately. [Copyright &y& Elsevier]

Abstract: In this paper, an artificial neural network (ANN) model is developed for estimating monthly mean daily global solar radiation of 8 typical cities in China. The feed-forward back-propagation algorithm is applied in this analysis. The results of the ANN model and other empirical regression models have been compared with measured data on the basis of mean percentage error (MPE), mean bias error (MBE) and root mean square error (RMSE). It is found that the solar radiation estimations by ANN are in good agreement with the measured values and are superior to those of other available empirical models. In addition, ANN model is tested to predict the same components for Kashi, Geermu, Shenyang, Chengdu and Zhengzhou stations over the same period. Data for Kashi, Geermu, Shenyang, Chengdu and Zhengzhou are not used in the training of the networks. Results obtained indicate that the ANN model can successfully be used for the estimation of monthly mean daily global solar radiation for Kashi, Geermu, Shenyang, Chengdu and Zhengzhou. These results testify the generalization capability of the ANN model and its ability to produce accurate estimates in China. [Copyright &y& Elsevier]