Search

To deal with the issues of high computational cost and prediction uncertainty of numerical models in train-induced ground-borne vibration prediction, a prediction method based on transfer learning is proposed in this study. In this method, the vehicle–track-coupled analytical model and three-dimensional finite element model are first used to calculate the train-induced ground vibration under various condition variables, and these data were used as training samples to pre-train the deep neural network models. Numerous train-induced ground vibration experiments were then conducted along the metro lines in Beijing, and those measured vibration data were used to fine-tune the pre-trained deep neural network model with the transfer learning strategy. A random variable obeying a Gaussian distribution is assumed over the predicted vibration acceleration levels to model the randomness of train-induced vibration, and the parameters of this distribution were determined by the statistical results of vibration monitoring data in the metro tunnels. The fully trained model could complete the prediction of train-induced ground vibration in seconds. Finally, a case study was carried out, by comparing the probabilistic prediction results with the statistical results of the field measurements, and the feasibility and the improvement of the proposed method were demonstrated. [ABSTRACT FROM AUTHOR]

In order to forecast prices of arbitrary agricultural commodity in different wholesale markets in one city, this paper proposes a mixed model, which combines ARIMA model and PLS regression method based on time and space factors. This mixed model is able to obtain the forecasting results of weekly prices of agricultural commodities in different markets. Meanwhile, this paper sets up variables to measure the price changing trend based on the change of exogenous variables and prices, thus achieves the warning of daily price changes using neural networks. The model is tested with the data of several types of agricultural commodities and error analysis is made. The result shows that the mixed model is more accurate in forecasting agricultural commodity prices than each single model does, and has better accuracy in warning values. The mixed model, to some extent, forecasts the daily price changes of agricultural commodities. [ABSTRACT FROM AUTHOR]

Finding students at high risk of poor academic performance as early as possible plays an important role in improving education quality. To do so, most existing studies have used the traditional machine learning algorithms to predict students' achievement based on their behavior data, from which behavior features are extracted manually thanks to expert experience and knowledge. However, owing to an increase in the varieties and overall volume of behavioral data, it has become more and more challenging to identify high-quality handcrafted features. In this paper, we propose an end-to-end deep learning model that automatically extracts features from students' multi-source heterogeneous behavior data to predict academic performance. The key innovation of this model is that it uses long short-term memory networks to capture inherent time-series features for each type of behavior, and it takes two-dimensional convolutional networks to extract correlation features among different behaviors. We conducted experiments with four types of daily behavior data from students of the university in Beijing. The experimental results demonstrate that the proposed deep model method outperforms several machine learning algorithms. [ABSTRACT FROM AUTHOR]

In the curling sport, the coefficient of friction between the curling stone and pebbled ice is crucial to predict the motion trajectory. However, the theoretical and experimental investigations on stone–ice friction are limited, mainly due to the limitations of the field measurement techniques and the inadequacy of the experimental data from professional curling rinks. In this paper, on-site measurement of the stone–ice friction coefficient in a prefabricated ice rink for the Beijing Winter Olympics curling event was carried out based on computer vision technology. Firstly, a procedure to determine the location of the curling stone was proposed using YOLO-V3 (You Only Look Once, Version 3) deep neural networks and the CSRT Object tracking algorithm. Video data was recorded during the curling stone throwing experiments, and the friction coefficient was extracted. Furthermore, the influence of the sliding velocity on the friction coefficient was discussed. Comparison with published experimental data and models and verification of the obtained results, using a sensor-based method, were conducted. Results show that the coefficient of friction (ranging from 0.006 to 0.016) decreased with increasing sliding velocity, due to the presence of a liquid-like layer. Our obtained results were consistent with the literature data and the friction model of Lozowski. In addition, the experimental results of the computer vision technique method and the accelerometer sensor method showed remarkable agreement, supporting the accuracy and reliability of our proposed measurement procedure based on deep learning. [ABSTRACT FROM AUTHOR]

The interpolation, prediction, and feature analysis of fine-gained air quality are three important topics in the area of urban air computing. The solutions to these topics can provide extremely useful information to support air pollution control, and consequently generate great societal and technical impacts. Most of the existing work solves the three problems separately by different models. In this paper, we propose a general and effective approach to solve the three problems in one model called the Deep Air Learning (DAL). The main idea of DAL lies in embedding feature selection and semi-supervised learning in different layers of the deep learning network. The proposed approach utilizes the information pertaining to the unlabeled spatio-temporal data to improve the performance of the interpolation and the prediction, and performs feature selection and association analysis to reveal the main relevant features to the variation of the air quality. We evaluate our approach with extensive experiments based on real data sources obtained in Beijing, China. Experiments show that DAL is superior to the peer models from the recent literature when solving the topics of interpolation, prediction, and feature analysis of fine-gained air quality. [ABSTRACT FROM AUTHOR]

To address the problems of high overflow rate of pipe network inspection well and low drainage efficiency, a rainwater control optimization design approach based on a self-organizing feature map neural network model (SOFM) was proposed in this paper. These problems are caused by low precision parameter design in various rainwater control measures such as the diameter of the rainwater pipe network and the green roof area ratio. This system is to be combined with the newly built rainwater pipe control optimization design project of China International Airport in Daxing District of Beijing, China. Through the optimization adjustment of the pipe network parameters such as the diameter of the rainwater pipe network, the slope of the pipeline, and the green infrastructure (GI) parameters such as the sinking green area and the green roof area, reasonable control of airport rainfall and the construction of sustainable drainage systems can be achieved. This research indicates that compared with the result of the drainage design under the initial value of the parameter, the green roof model and the conceptual model of the mesoscale sustainable drainage system, in the case of a hundred-year torrential rainstorm, the overflow rate of pipe network inspection wells has reduced by 36% to 67.5%, the efficiency of drainage has increased by 26.3% to 61.7%, which achieves the requirements for reasonable control of airport rainwater and building a sponge airport and a sustainable drainage system. [ABSTRACT FROM AUTHOR]

The majority of studies on road traffic flow prediction have focused on the flow of passenger cars or the flow of traffic as a whole, which ignore the significant impact of trucks with different sizes and operational characteristics on traffic flow efficiency. Therefore, in this paper, we focus on truck traffic flow and propose a Multifeatures Spatial-Temporal-Based Neural Network model (M-BiCNNGRU) to improve its prediction. The proposed model not only comprises conventional temporal characteristics and spatial relationships but also includes a range of multifeatures. These multifeatures include policy limit, optimal time delay, road resistance, and traffic congestion state. The impacts of upstream and downstream road sections are considered on the spatial relationship by using a Convolutional Neural Network (CNN). A Bidirectional Gated Recurrent Unit (Bi-GRU) is employed to account for the temporal characteristics. To evaluate the proposed model, traffic flow data were collected from a major expressway in Beijing and the results were compared with those derived from existing models. The results show that the prediction accuracy of the BiCNNGRU model, with spatial-temporal characteristics, and the M-BiGRU model, with multifeatures and temporal, is, respectively, 4.13% and 2.15% greater than that of the Bi-GRU model, with temporal characteristics. The prediction accuracy of the proposed M-BiCNNGRU model is 92.86%, which is 7.12% greater than that of the Bi-GRU model and 13.83% greater than that of the Support Vector Regression (SVR) model. In general, therefore, the proposed M-BiCNNGRU model, which combines multifeatures, temporal characteristics, and spatial relationships, can significantly improve accuracy in predicting truck traffic flow. [ABSTRACT FROM AUTHOR]

Along with the increasing proportion of urban public transportation trip, pedestrian flow in transportation hub areas increased. For effectively improving the emergency handling ability of related management apartments and preventing the incident of pedestrian congestion, this paper studied the method of pedestrian flow forecast in Beijing transportation hub areas. Firstly, 34 typical sidewalks in Beijing transportation hub areas were surveyed to obtain 2200 valid data. Secondly, correlation analysis was used to analyze the relationship between pedestrian flow and its influential factors. 11 significant influential factors were extracted. Thirdly, forecasting model was established with modular neural network. The surveyed pedestrian flow sample was fuzzy clustered according to the regional land use where the transportation hub existed. Then, membership function based on the distance measure was constructed. Through fuzzy discrimination, online selection for the subnetwork of the information can be achieved. Consequently, the self-adaptation of the neural network on information processing was improved. Finally, this paper tested the pedestrian flow sample of a transportation hub in Beijing. It was concluded that the accuracy of pedestrian flow forecasting model using modular neural network was higher than other neural network models. There was also improvement in the adaptability to environment. [ABSTRACT FROM AUTHOR]

As a main type of urban construction land, urban-industrial land is used to provide the judging criteria for construction land scale in the planning period when urban population, industrial development, investment scale, and other conditions are uncertain in China; however, research on expected indicator such as urban-industrial land in overall land use plan mainly focuses on qualitative analysis; quantitative analysis research has not yet been carried out. Using MATLAB R2016a software modeling tools to establish GM (1, 1) model and RBF neural network model, respectively, this paper predicted the demand of urban-industrial land in Beijing-Tianjin-Hebei Urban Agglomeration. Comparing the predicated results with the actual value of urban-industrial land in Beijing, Tianjin, and 11 prefecture-level cities in Hebei Province, we determined the reasonable prediction model for urban-industrial land after testing the accuracy of the two prediction models. The results showed that the RBF neural network model was the more reasonable prediction model for urban-industrial land. Using the predicted results of the RBF neural network model, combining expected indicators of overall land use plan (2006–2020) in Beijing and Tianjin, as well as 11 prefecture-level cities in Hebei Province in the planning target year, determined remaining usable time of urban-industrial land. Finally, combined with the actual scale of urban-industrial land in 2015 and the predicated scale of urban-industrial land in 2020, the remaining usable time of each city's urban-industrial land was calculated in terms of the average annual growth rate of urban-industrial land from 2009 to 2015. According to the comparative relationship between the remaining usable time and the remaining time of the overall land use plan (5 years), urban-industrial lands were divided into three kinds of regulation zones: reasonable reduction zone, optimized adjustment zone, and core development zone. The policy implications for urban-industrial land in each regulation zone were also provided. This paper can provide reference for regulation zoning of urban-industrial land in developing countries and regions. [ABSTRACT FROM AUTHOR]

Forest stock volume (FSV) is a key indicator for measuring forest quality, evaluating forest management capabilities, and the main factor for evaluating forest carbon sequestration levels. In this study, to achieve an accurate estimation of FSV, we used Ninth Beijing Forest Inventory data (FID), and Landsat 8 OLI and Sentinel-2 MSI imagery to establish FSV models. The performance of Landsat 8 and Sentinel-2 imagery data in estimating forest volume in Huairou District, Beijing, China was compared. The combination of Landsat 8 and Sentinel-2 satellite data was employed to create a new data source. Two variable selection methods, linear stepwise regression (LSR) and recursive feature elimination (RFE), were used to extract feature variables. The multiple linear regression(MLR) models, Back Propagation (BP) neural network models, and Random Forest (RF) models were employed to estimate forest volume in the study area based on the feature variables obtained from both data sources. The research results indicate (1) the Sentinel-2-based model achieved higher accuracy compared to the same model based on the Landsat 8 factor set. The correlation between the red-edge band of Sentinel-2 imagery and FSV is more significant than that of other characteristic variables used. Variables derived from the red-edge band have the potential to reduce model errors; (2) the estimation accuracy of the model can be significantly improved by using the RFE (Recursive Feature Elimination) method to select remote sensing feature variables. RFE is based on the importance ranking of all feature variables and selects the feature variables that contribute the most to the model. In the variable group selected by RFE, the texture features and the derived features from the red-edge band, such as S e n B 5 , S e n R V I , S e n m N D V I r e , and S e n B 5 M e a n , contribute the most to the improvement of model accuracy. Furthermore, in the optimal Landsat 8–Sentinel-2 RFE-RF model, where texture features are involved, the rRMSE is greatly reduced by 3.7% compared to the joint remote sensing RFE-RF model without texture features; (3) the MLR, BP, and RF models based on the modeling factor set established on Sentinel-2 have accuracy superior to the model accuracy established based on the modeling factor set of Landsat 8. Among them, the Random Forest (RF) method inverted by the recursive feature elimination (RFE) method using Sentinel-2A image has the best inversion accuracy effect ( R 2 = 0.831, R M S E = 12.604 m 3 ha − 1 , r R M S E = 36.411%, M A E = 9.366 m 3 ha − 1 ). Comparing the performance of the models on the test set, the ranking is as follows, Random Forest (RF) model > Back Propagation (BP) neural network model > multiple linear regression (MLR) model. The feature variable screening based on the Random Forest's recursive feature elimination (RFE) method is better than the linear stepwise regression (LSR). Therefore, the RFE-RF method based on the joint variables from Landsat 8 and Sentinel-2 satellite data to establish a new remote sensing data source provides the possibility to improve the estimation accuracy of FSV and provides reference for forest dynamic monitoring. [ABSTRACT FROM AUTHOR]

Deep learning provides a promising approach for air pollution prediction. The existing deep learning-based predicted models generally consider either the temporal correlations of air quality monitoring stations or the nonlinear relationship between the PM2.5 (particulate matter with an aerodynamic diameter of less than 2.5 μm) concentrations and explanatory variables. Spatial correlation has not been effectively incorporated into prediction models, therefore exhibiting poor performance in PM2.5 prediction tasks. Additionally, determining the manner by which to expand longer-term prediction tasks is still challenging. In this paper, to allow for spatiotemporal correlations, a spatiotemporal convolutional recursive long short-term memory (CR-LSTM) neural network model is proposed for predicting the PM2.5 concentrations in long-term prediction tasks by combining a convolutional long short-term memory (ConvLSTM) neural network and a recursive strategy. Herein, the ConvLSTM network was used to capture the complex spatiotemporal correlations and to predict the future PM2.5 concentrations; the recursive strategy was used for expanding the long-term prediction tasks. The CR-LSTM model was used to realize the prediction of the future 24 h of PM2.5 concentrations for 12 air quality monitoring stations in Beijing by configuring both the appropriate time lag derived from the temporal correlations and the spatial neighborhood, including the hourly historical PM2.5 concentrations, the daily mean meteorological data, and the annual nighttime light and normalized difference vegetation index (NDVI). The results showed that the proposed CR-LSTM model achieved better performance (coefficient of determination (R2) = 0.74; root mean square error (RMSE) = 18.96 μg/m3) than other common models, such as multiple linear regression (MLR), support vector regression (SVR), the conventional LSTM model, the LSTM extended (LSTME) model, and the temporal sliding LSTM extended (TS-LSTME) model. The proposed CR-LSTM model, implementing a combination of geographical rules, recursive strategy, and deep learning, shows improved performance in longer-term prediction tasks. [ABSTRACT FROM AUTHOR]

Chinese address element segmentation is a basic and key step in geocoding technology, and the segmentation results directly affect the accuracy and certainty of geocoding. However, due to the lack of obvious word boundaries in Chinese text, the grammatical and semantic features of Chinese text are complicated. Coupled with the diversity and complexity in Chinese address expressions, the segmentation of Chinese address elements is a substantial challenge. Therefore, this paper proposes a method of Chinese address element segmentation based on a bidirectional gated recurrent unit (Bi-GRU) neural network. This method uses the Bi-GRU neural network to generate tag features based on Chinese word segmentation and then uses the Viterbi algorithm to perform tag inference to achieve the segmentation of Chinese address elements. The neural network model is trained and verified based on the point of interest (POI) address data and partial directory data from the Baidu map of Beijing. The results show that the method is superior to previous neural network models in terms of segmentation performance and efficiency. [ABSTRACT FROM AUTHOR]

Obtaining crowd flow distribution with recognized human intention is extremely valuable for a series of applications for metropolitan cities. Previous solutions look at spatial correlation and temporal periodicity based on historical crowd flow information to calculate future crowd flow distribution. However, these mechanisms cannot recognize the intention behind crowd flow. We address this problem by leveraging a key insight – people's intention behind their movement is highly correlated with the point-of-interest (POI) distribution of the corresponding regions and adjacent regions. Therefore, we propose DeepFlowGen to model the complicated relationship between crowd flow, POI, check-ins, and time to generate intention-aware crowd flow. Specifically, we solve the conflict between dynamic crowd flow and static POI distribution by fusing the information in both time and POI domains. Besides, we employ a sequence of residual blocks in DeepFlowGen to address the challenges of modeling the diverse temporal rhythms and heterogeneous influence of POI. Furthermore, we examine the generated intention-aware crowd flow from two aspects to substantiate the reasonability of DeepFlowGen. Extensive experiments demonstrate that our model outperforms the state-of-the-art solutions by at most 30 percent in terms of NRMSE of total crowd flow. Moreover, the correlation between the generated intention-aware crowd flow and the check-in distribution across different categories of POIs is as high as 0.90 and 0.80 in Beijing and Shanghai. Combined with extensive case studies, we demonstrate the strong ability of our model in generating intention-aware crowd flow. [ABSTRACT FROM AUTHOR]

The emission of greenhouse gases, especially CO2, is the main factor causing global warming. Due to incomplete statistical data on energy consumption at and below the urban scale of Beijing-Tianjin-Hebei (BTH), in this study, Defense Meteorological Satellite Program Operational Linescan System (DMSP-OLS) and Suomi National Polar-orbiting Partnership Visible Infrared Imaging Radiometer Suite (NPP-VIIRS) data were combined, and a neural network model and weighted average method based on DN (Digital Number) value were used to obtain CO2 emissions at the municipal and county scales with a resolution of 1 km × 1 km from 2000–2019. Next, a spatial-temporal analysis model and spatial econometric model were used to study the CO2 emissions at different scales of BTH. This study also solved the problem that STIRPAT analysis cannot be carried out due to insufficient urban statistical CO2 emissions data. The results show that the energy CO2 emissions in BTH present a distribution pattern of "East greater than West", with a trend of first rising and then slowing down. Moreover, the rapid growth areas are mainly located in Chengde and Tianjin. The degree of regional spatial aggregation decreased year by year from 2000–2019. Population, affluence and technology factors were positively correlated with CO2 emissions in Tianjin and Hebei. For Beijing, in addition to foreign investment, factors such as urbanization rate, energy intensity, construction and transportation factors all contributed to the increase in CO2 emissions. Among them, the growth of population is the main reason for the increase of CO2 at the urban scale in BTH. Finally, based on the research results and the specific situation of the cities, corresponding policies and measures are proposed for the future low-carbon development of the cities. [ABSTRACT FROM AUTHOR]

Green development is the inevitable choice for global sustainable development, and China has chosen green development as its national strategy. Land use changes will affect a soil's organic matter by changing the land's productivity, soil quality and fertility. It is of great significance for ensuring soil fertility, improving the environment and promoting the carbon cycle that the concept of green development is implemented in the process of land use activity. Establishing an indicator system and evaluation method for a green land use benefit evaluation suitable for green development is helpful for strengthening the responsibility and consciousness of such land use, and to provide theoretical guidance and decision-making references for promoting such developments and evaluations. In this study, based on a connotation analysis of green land use, the entropy weight method and BP (Back Propagation) neural network model method were used to construct an evaluation index system for green land use benefits, including four criterion layers and eighteen evaluation indexes, and the entropy-BP neural network evaluation method was proposed to reveal the problems in green land use benefits in the Beijing–Tianjin–Hebei region. The results showed that the green land use benefit level in the region was low, while the spatial pattern was high in the north, low in the middle and high in the south. Langfang, Beijing and Handan were the lowest centers of green land ecological benefit, while Beijing and Tianjin were the lowest centers of green land economic benefit. The green governance benefit and green space benefit were in a relative spatial equilibrium. The cultivated land area, forestry products, sewage centralized treatment degree and built-up area ratio were the most important influences on the green ecological benefit, green economic benefit, green governance benefit and green space benefit, respectively. The entropy-BP neural network evaluation system and method have certain applications in the design of relevant assessment reward-and-punishment systems. Accelerating the optimization of the Beijing–Tianjin–Hebei territorial space's development and utilization pattern, and constructing a green benefit sharing mechanism of land use, are important strategies to improve the benefits of green land use. [ABSTRACT FROM AUTHOR]

Short-term traffic prediction (e.g., less than 15 min) is challenging due to severe fluctuations of traffic data caused by dynamic traffic conditions and uncertainties (e.g., in data acquisition, driver behaviors, etc.). Substantial efforts have been undertaken to incorporate spatiotemporal correlations for improving traffic prediction accuracy. In this paper, we demonstrate that closely located road segments exhibit diverse spatial correlations when characterized using different measurements, and considering these multi-fold correlations can improve prediction performance. We propose new measurements to model multiple spatial correlations among traffic data. We develop a Multi-fold Correlation Attention Network (MCAN) that achieves accurate prediction by capturing multi-fold spatial correlation and multi-fold temporal correlations, and incorporating traffic data of heterogeneous sampling frequencies. The effectiveness of MCAN has been extensively evaluated on two real-world datasets in terms of overall performance, ablation study, sensitivity analysis, and case study, by comparing with several state-of-the-art methods. The results show that MCAN outperforms the best baseline with a reduction in mean absolute error (MAE) by 13% on Singapore dataset and 11% on Beijing dataset. • We propose a Multi-fold Correlation to model dynamic associations in traffic data. • We jointly consider multi-fold spatial and temporal correlations. • We handle heterogeneous frequency of traffic data using graph convolution network. [ABSTRACT FROM AUTHOR]

Improved-performance day-ahead electricity demand forecast is important to deliver necessary information for right decision of energy management of microgrids. It supports microgrid operators and stakeholders to have better decisions on microgrid flexibility, stability and control. The available conventional forecasting methods for electricity demand at national or regional level are not effective for electricity demand forecasting in microgrids. This is due to the fact that the electricity consumption in microgrids is many times less than the regional or national demands and it is highly volatile. In this paper, an integrated Artificial Intelligence (AI) based approach consisting of Wavelet Transform (WT), Simulated Annealing (SA) and Feedforward Artificial Neural Network (FFANN) is devised for day-ahead prediction of electric power consumption in microgrids. The FFANN is the basic forecasting engine of the proposed model. The WT is utilized to extract relevant features of the target variable (electric load data series) to obtain a cluster of enhanced-feature subseries. The extracted subseries of the past values of the electric load demand data are employed as the target variables to model the FFANN. The SA optimization technique is employed to obtain the optimal values of the FFANN weight parameters during the training process. Historical information of actual electricity consumption, meteorological variables, daily variations, weekly variations, and working/non-working day indicators have been employed to develop the forecasting tool of the devised integrated AI based approach. The approach is validated using electricity demand data of an operational microgrid in Beijing, China. The prediction results are presented for future testing days with one-hour time interval. The validation results demonstrated that the devised approach is capable to forecast the microgrid electricity demand with acceptably small error and reasonably short computation time. Moreover, the prediction performance of the devised approach has been evaluated relative to other four approaches and resulted in better prediction accuracy. [ABSTRACT FROM AUTHOR]

Based on Beijing's Air Quality Index (AQI) and concentration changes of the six major pollutants from 2019 to 2021, the results are visualized through descriptive statistics, and the air pollution status and influencing factors of Beijing's AQI are analyzed using the ARIMA model and neural network. A forecast system is built and the fitting effects of the two models are compared. The results show that PM2.5, PM10, and O3 of the six major pollutants have the greatest impact on AQI. Beijing's air quality now shows a trend of improvement in recent years; however, there is obvious seasonal evidence that the summer pollution index has been high. Therefore, special attention should be paid to the treatment of ozone pollution in summer. Both models are useful for the forecast of AQI, but the forecast effect of the neural network model is better than that of the ARIMA model. Moreover, when using the additive seasonal model for the long-term forecast of monthly data, it is found that the Beijing AQI still shows seasonal cyclicality and has a slightly decreasing trend in the next two years. This research provides a basis for the forecast of air quality and policy enlightenment for environmental protection departments to deal with air pollution. [ABSTRACT FROM AUTHOR]

With the tide of electrifying urban transportation systems by introducing electric vehicles, the differences between fuel vehicles and electric vehicles in driving styles and strategies to achieve eco-driving have become a burden for efficient operations of urban transportation systems. Most of the previous energy management strategies have sought to achieve system optimisation at a single-vehicle or multi-vehicles level, and failed to consider the vehicle-to-vehicle and vehicle-to-infrastructure effects in a global optimisation manner. Furthermore, as a typical human-in-the-loop cyber–physical system, the mobility behaviours of road users undoubtedly play a vital role in the cooperative and green operations of urban transportation systems. Yet little research has dedicated to develop means to incentivise energy-saving behaviours in transportation systems. Hence, in this paper, we propose a unifying queueing and neural network model to calculate the time and energy efficient course of actions and routes for different types of road users within an urban road network in a real time manner. The lower-level queueing model captures the interactive dynamics of road users and solves the optimal flow ratio at each intersection while the upper-level neural network model further customises desired routes for different types of road users. In addition, an incentive mechanism is proposed to encourage road users to follow the optimal actions via publishing various types of reward-gaining tasks. A case study in a designated area of Beijing shows that the use of the bi-level optimisation algorithm can reduce the average travel time by approximately 20% and decrease the energy consumption by 10% in comparison with the realistic trip data. • An overall energy management framework for urban road networks is built in detail. • A heterogeneous queueing network model is utilised to derive eco-driving strategies. • Random Neural Network is applied to search desired routes for heterogeneous users. • SUMO-based simulation experiment is conducted to validate the performance. • The framework improves time and energy efficiency at the cost of monetary incentives. [ABSTRACT FROM AUTHOR]

Vegetable price predictions are of great significance to vegetable growers, particularly regarding production and management to ensure a balance in the regional supply and demand of vegetables. In the current paper, in order to improve the accuracy and efficiency of vegetable price forecasting, we propose an optimized neural network combined model based on the induced ordered weighted averaging operator. Our frameworks integrate the fruit fly algorithm (FOA) with the induced ordered weighted averaging (IWOA) operator for an enhanced performance. In particular, the FOA is employed for the parameter optimization of the generalized regression neural network (GRNN) and radial basis function neural network (RBFNN), reducing the adverse influence of man-induced factors in the model construction process and improving the learning ability of both GRNN and RBFNN. The IWOA operator calculates the weights of the single GRNN and RBFNN to address the problem of fixed weights in combination forecasting models. Monthly vegetable price data in Beijing was used to compare our method with nine single forecasting models, revealing that the optimization of the GRNN and RBFNN parameters by the FOA, the prediction accuracy of the FOA-GRNN model and FOA-RBFNN model surpass those of GRNN and RBFNN, respectively. Furthermore, results from four evaluation indexes reveal that the IOWA-based optimized neural network model exhibited a stronger predictive ability than the other nine prediction models. Results demonstrate the effectiveness of our framework for the prediction of vegetable price series, with potential applications in agricultural products of similar characteristics. • The parameter optimization of neural networks by the fruit fly algorithm. • Solving a problem of fixed weights by induced ordered weighted averaging operator. • Our model exhibiting a stronger predictive for the prediction of vegetable price series. • The vegetable price with a clear growth approaching the end of 2020. [ABSTRACT FROM AUTHOR]

We propose an autoregressive integrated moving average convolutional neural network (ARIMA-CNN) to address the problems of the large amount of computation required for typical networks, the low effectiveness of traditional machine learning in traffic index prediction, and the weak recognition ability of traditional methods based on distance and features to improve the traffic index in traffic scheduling. The ARIMA-CNN can accurately predict the traffic index and distinguish its model categories. The model includes two steps: traffic index prediction and prediction index classification. The first step uses the augmented Dickey-Fuller (ADF) test to determine the type of traffic index series and then converts a nonstationary series to a stationary series by the difference operation. The ARIMA is fitted with the Bayesian information criterion (BIC) matrix, and the traffic index is predicted by the ARIMA. The second step obtains the best CNN model based on the traffic index feature information extracted from the training time series, integrates the feature information into a one-dimensional feature vector, determines the feature vector pattern category according to the Softmax classifier, and decides the category of the predicted traffic index. We used the traffic index data of Beijing for three consecutive years (from 2016 to 2018) as an example. The time series of the traffic index in the experimental data was accurately predicted, the prediction results were consistent with the variation characteristics of the real series data, and the prediction mode of recognition was the Monday mode. Our results were consistent with the actual situation and prove the validity of the model. On the basis of the identification results and the corresponding threshold curve of this category, we were able to find abnormal points, supervise the traffic status, and obtain early warnings about possible abnormal traffic patterns. This research has important practical significance for helping traffic management departments to make traffic control decisions in advance. [ABSTRACT FROM AUTHOR]

The state of charge (SOC) is a crucial parameter of a battery management system for Li-ion batteries. The SOC indicates the amount of charge left in the battery of electric vehicles—akin to the fuel gauge in combustion vehicles. An accurate SOC knowledge contributes largely to the longevity, performance, and reliability of the battery. However, the SOC of Li-ion batteries cannot be easily measured by any apparatus. Furthermore, the SOC can also be influenced by numerous incalculable factors such as battery chemistry, ambient environment, aging factor, etc. In this article, we propose an SOC estimation model for a Li-ion battery using an improved deep neural network (DNN) approach for electric vehicle applications. We found that a DNN with a sufficient number of hidden layers is capable of predicting the SOC of the unseen drive cycles during training. We developed a series of DNN models with a varying number of hidden layers, and its training algorithm was to investigate their respective performance when evaluated on different drive cycles. We observe that the increasing number of hidden layers in the DNN (up to four hidden layers) decreases the error rate and improves SOC estimation. An additional increase in the number of hidden layers beyond that increases the error rate. In this study, we show that a four-hidden-layer DNN trained on Dynamic Stress Test drive cycle is capable of predicting SOC values unexpectedly well of other unseen drive cycles such as Federal Urban Driving Schedule, Beijing Dynamic Stress Test, and Supplemental Federal Test Procedure, respectively. [ABSTRACT FROM AUTHOR]

Soil moisture is one of the main factors in agricultural production and hydrological cycles, and its precise prediction is important for the rational use and management of water resources. However, soil moisture involves complex structural characteristics and meteorological factors, and it is difficult to establish an ideal mathematical model for soil moisture prediction. Existing prediction models have problems such as prediction accuracy, generalization, and multi-feature processing capability, and prediction performance must improve. Based on this, taking the Beijing area as the research object, the deep learning regression network (DNNR) with big data fitting capability was proposed to construct a soil moisture prediction model. By integrating the dataset, analyzing the time series of the predictive variables, and clarifying the relationship between features and predictive variables through the Taylor diagram, selected meteorological parameters can provide effective weights for moisture prediction. Test results prove that the deep learning model is feasible and effective for soil moisture prediction. Its’ good data fitting and generalization capability can enrich the input characteristics while ensuring high accuracy in predicting the trends and values of soil moisture data and provides an effective theoretical basis for water-saving irrigation and drought control. [ABSTRACT FROM AUTHOR]

Satellite-based rapid sweeping screening of localized PM2.5 hotspots at fine-scale local neighborhood levels is highly desirable. This motivated us to develop a random forest–convolutional neural network–local contrast normalization (RF–CNN–LCN) pipeline that detects local PM2.5 hotspots at a 300 m resolution using satellite imagery and meteorological information. The RF–CNN joint model in the pipeline uses three meteorological variables and daily 3 m/pixel resolution PlanetScope satellite imagery to generate daily 300 m ground-level PM2.5 estimates. The downstream LCN processes the estimated PM2.5 maps to reveal local PM2.5 hotspots. The RF–CNN joint model achieved a low normalized root mean square error for PM2.5 of within ~31% and normalized mean absolute error of within ~19% on the holdout samples in both Delhi and Beijing. The RF–CNN–LCN pipeline reasonably predicts urban PM2.5 local hotspots and coolspots by capturing both the main intra-urban spatial trends in PM2.5 and the local variations in PM2.5 with urban landscape, with local hotspots relating to compact urban spatial structures and coolspots being open areas and green spaces. Based on 20 sampled representative neighborhoods in Delhi, our pipeline revealed an annual average 9.2 ± 4.0 μg m−3 difference in PM2.5 between the local hotspots and coolspots within the same community. In some cases, the differences were much larger; for example, at the Indian Gandhi International Airport, the increase was 20.3 μg m−3 from the coolest spot (the residential area immediately outside the airport) to the hottest spot (airport runway). This work provides a possible means of automatically identifying local PM2.5 hotspots at 300 m in heavily polluted megacities and highlights the potential existence of substantial health inequalities in long-term outdoor PM2.5 exposures even within the same local neighborhoods between local hotspots and coolspots. [ABSTRACT FROM AUTHOR]

Intersections are the bottlenecks of the road network. The capacity of signalized intersections restricts the operation of the road network. Dynamic estimation of capacity is necessary for signalized intersections refined management. With the development of technology, more and more detectors were installed near the intersection. It had been the information-rich environment, which provided support for dynamic estimation of capacity. A dynamic estimation method for a saturation flow rate based on a neural network was developed. It would grasp the dynamic change of saturation flow rates and influencing factors. The measure data at three scenarios (through lanes, shared right-turn and through lanes, shared left-turn and through lanes) of signalized intersections in Beijing were taken as examples to validate the proposed method. Firstly, the traffic flow characteristics of the three scenarios and factors affecting the saturation flow rate were analyzed. Secondly, neural network models of the three scenarios were established. Then the hyperparameters of neural network models were determined. After training, the neural network structure and parameters were saved. Lastly, the test set data was validated by the training model. At the same time, the proposed method was compared with the Highway Capacity Manual (HCM) method and the statistical regression method. The results show that both regression models and neural network models have better accuracy than HCM models. In a simple scenario, the neural network models are not much different from the regression models. With the increase of complexity of scenarios, the advantages of neural network models are highlighted. In through-left lane and through-right lane scenarios, the estimated saturation flow rates used by the proposed method were 7.02%, 4.70%, respectively. In the complexity of traffic scenarios, the proposed method can estimate the saturation flow rate accurately and timely. The results could be used for signal control schemes optimizing and operation managing at signalized intersections subtly. [ABSTRACT FROM AUTHOR]

The study investigates land use/cover classification and change detection of urban areas from very high resolution (VHR) remote sensing images using deep learning-based methods. Firstly, we introduce a fully Atrous convolutional neural network (FACNN) to learn the land cover classification. In the FACNN an encoder, consisting of full Atrous convolution layers, is proposed for extracting scale robust features from VHR images. Then, a pixel-based change map is produced based on the classification map of current images and an outdated land cover geographical information system (GIS) map. Both polygon-based and object-based change detection accuracy is investigated, where a polygon is the unit of the GIS map and an object consists of those adjacent changed pixels on the pixel-based change map. The test data covers a rapidly developing city of Wuhan (8000 km2), China, consisting of 0.5 m ground resolution aerial images acquired in 2014, and 1 m ground resolution Beijing-2 satellite images in 2017, and their land cover GIS maps. Testing results showed that our FACNN greatly exceeded several recent convolutional neural networks in land cover classification. Second, the object-based change detection could achieve much better results than a pixel-based method, and provide accurate change maps to facilitate manual urban land cover updating. [ABSTRACT FROM AUTHOR]