Taxi demand prediction is a crucial component of intelligent transportation system research.Compared to region-based demand prediction,origin-destination(OD)demand prediction has a wide range of potential applications...Taxi demand prediction is a crucial component of intelligent transportation system research.Compared to region-based demand prediction,origin-destination(OD)demand prediction has a wide range of potential applications,including real-time matching,idle vehicle allocation,ridesharing services,and dynamic pricing,among others.However,because OD demand involves complex spatiotemporal dependence,research in this area has been limited thus far.In this paper,we first review existing research from four perspectives:topology construction,temporal and spatial feature processing,and other relevant factors.We then elaborate on the advantages and limitations of OD prediction methods based on deep learning architecture theory.Next,we discuss ongoing challenges in OD prediction,such as dynamics,spatiotemporal dependence,semantic differentiation,time window selection,and data sparsity problems,and summarize and compare potential solutions to each challenge.These findings offer valuable insights for model selection in OD demand prediction.Finally,we provide public datasets and open-source code,along with suggestions for future research directions.展开更多
Urban construction land has relatively high human activity and high carbon emissions.Research on urban construction land prediction under carbon peak and neutrality goals(hereafter“dual carbon”goals)is important for...Urban construction land has relatively high human activity and high carbon emissions.Research on urban construction land prediction under carbon peak and neutrality goals(hereafter“dual carbon”goals)is important for territorial spatial planning.This study analyzed quantitative relationships between carbon emissions and urban construction land,and then modified the construction land demand prediction model.Thereafter,an integrated model for urban construction land demand prediction and spatial pattern simulation under“dual carbon”goals was developed,where urban construction land suitability was modified based on carbon source and sink capacity of different land-use types.Using Guangzhou as a case study,the integrated model was validated and applied to simulate the spatiotemporal dynamics of its urban construction land during 2030–2060 under baseline development and“dual carbon”goals scenarios.The simulation results showed that Guangzhou’s urban construction land expanded rapidly until 2030,with the spatial pattern not showing an intensive development trend.Guangzhou’s urban construction land expansion slowed during 2030–2060,with an average annual growth rate of 0.2%,and a centralized spatial pattern trend.Under the“dual carbon”goal scenario,Guangzhou’s urban construction land evolved into a polycentric development pattern in 2030.Compared with the baseline development scenario,urban construction land expansion in Guangzhou during 2030–2060 is slower,with an average annual growth rate of only 0.1%,and the polycentric development pattern of urban construction land was more prominent.Furthermore,land maintenance and growth,that is,a carbon sink,is more obvious under the“dual carbon”goals scenario,with the forest land area nearly 10.6%higher than that under the baseline development scenario.The study of urban construction land demand prediction and spatial pattern simulation under“dual carbon”goals provides a scientific decision-making support tool for territorial spatial planning,aiding in quantifying territorial spatial planning.展开更多
Accurate origin–destination(OD)demand prediction is crucial for the efficient operation and management of urban rail transit(URT)systems,particularly during a pandemic.However,this task faces several limitations,incl...Accurate origin–destination(OD)demand prediction is crucial for the efficient operation and management of urban rail transit(URT)systems,particularly during a pandemic.However,this task faces several limitations,including real-time availability,sparsity,and high-dimensionality issues,and the impact of the pandemic.Consequently,this study proposes a unified framework called the physics-guided adaptive graph spatial–temporal attention network(PAG-STAN)for metro OD demand prediction under pandemic conditions.Specifically,PAG-STAN introduces a real-time OD estimation module to estimate real-time complete OD demand matrices.Subsequently,a novel dynamic OD demand matrix compression module is proposed to generate dense real-time OD demand matrices.Thereafter,PAG-STAN leverages various heterogeneous data to learn the evolutionary trend of future OD ridership during the pandemic.Finally,a masked physics-guided loss function(MPG-loss function)incorporates the physical quantity information between the OD demand and inbound flow into the loss function to enhance model interpretability.PAG-STAN demonstrated favorable performance on two real-world metro OD demand datasets under the pandemic and conventional scenarios,highlighting its robustness and sensitivity for metro OD demand prediction.A series of ablation studies were conducted to verify the indispensability of each module in PAG-STAN.展开更多
The increasing penetration rate of electric kickboard vehicles has been popularized and promoted primarily because of its clean and efficient features.Electric kickboards are gradually growing in popularity in tourist...The increasing penetration rate of electric kickboard vehicles has been popularized and promoted primarily because of its clean and efficient features.Electric kickboards are gradually growing in popularity in tourist and education-centric localities.In the upcoming arrival of electric kickboard vehicles,deploying a customer rental service is essential.Due to its freefloating nature,the shared electric kickboard is a common and practical means of transportation.Relocation plans for shared electric kickboards are required to increase the quality of service,and forecasting demand for their use in a specific region is crucial.Predicting demand accurately with small data is troublesome.Extensive data is necessary for training machine learning algorithms for effective prediction.Data generation is a method for expanding the amount of data that will be further accessible for training.In this work,we proposed a model that takes time-series customers’electric kickboard demand data as input,pre-processes it,and generates synthetic data according to the original data distribution using generative adversarial networks(GAN).The electric kickboard mobility demand prediction error was reduced when we combined synthetic data with the original data.We proposed Tabular-GAN-Modified-WGAN-GP for generating synthetic data for better prediction results.We modified The Wasserstein GAN-gradient penalty(GP)with the RMSprop optimizer and then employed Spectral Normalization(SN)to improve training stability and faster convergence.Finally,we applied a regression-based blending ensemble technique that can help us to improve performance of demand prediction.We used various evaluation criteria and visual representations to compare our proposed model’s performance.Synthetic data generated by our suggested GAN model is also evaluated.The TGAN-Modified-WGAN-GP model mitigates the overfitting and mode collapse problem,and it also converges faster than previous GAN models for synthetic data creation.The presented model’s performance is compared to existing ensemble and baseline models.The experimental findings imply that combining synthetic and actual data can significantly reduce prediction error rates in the mean absolute percentage error(MAPE)of 4.476 and increase prediction accuracy.展开更多
In this study,related models of alloy purchasing decision system in the Baoshan base of Baosteel are discussed.First,the corresponding relationship between steel grades and alloy consumption is established through met...In this study,related models of alloy purchasing decision system in the Baoshan base of Baosteel are discussed.First,the corresponding relationship between steel grades and alloy consumption is established through metallurgical-mechanism modeling and statistical analysis.Then,the alloy-demand prediction model based on alloy unit consumption and time series analysis is developed by combining sales plans and historical data.Finally,the alloy purchasing and inventory optimization model is developed to minimize the total cost of purchase and storage by combining inventory optimization theories.展开更多
This study addresses a new charging station network planning problem for smart connected electric vehicles.We embed a charging station choice model into a charging network planning model that explicitly considers the ...This study addresses a new charging station network planning problem for smart connected electric vehicles.We embed a charging station choice model into a charging network planning model that explicitly considers the heterogeneity of the charging behavior in a data-driven manner.To cope with the deficiencies from a small size and sparse behavioral data,we propose a robust charging demand prediction method that can significantly reduce the impact of sample errors and missing data.On the basis of these two building blocks,we form and solve a new optimal charging station location and capacity problem by minimizing the construction and charging costs while considering the charging service level,construction budget,and limit to the number of chargers.We use a case study of planning charging stations in Shanghai to validate our contributions and provide managerial insight in this area.展开更多
The charging behaviors of electric vehicle(EV)users exhibit high randomness and individual heterogeneity,with the key parameters such as the charging duration and charged energy levels displaying significant fluctuati...The charging behaviors of electric vehicle(EV)users exhibit high randomness and individual heterogeneity,with the key parameters such as the charging duration and charged energy levels displaying significant fluctuations.Compared with EV cluster-layer prediction,predicting the charging demands of individual users requires not only the analysis of more complex charging behaviors but also the establishment of a coupling model between exogenous variables(e.g.,weather and holidays)and prediction accuracy,thereby imposing higher robustness requirements on prediction algorithms.An individual-user EV charging demand prediction method that in-tegrates multisource data with a dual-layer clustering approach and a light gradient boosting machine(LightGBM)is proposed in this study to address these technical challenges.First,a multisource dataset that incorporates user charging behavior data and exogenous variables(meteorological factors and date types)is constructed.A dual-layer feature extraction mechanism consisting of data-layer clustering for charging type identification and user-layer clustering for user group classification is employed,thereby establishing a classi-fication feature space that characterizes different charging types and user groups.A predictive model is subse-quently developed using the LightGBM algorithm,which directly incorporates classification features as its inputs,effectively mitigating the information loss associated with the traditional categorical variable encoding process.Finally,employing EV users from a typical residential community in northern China as an empirical case,comparative experiments are performed to validate the proposed method,demonstrating its effectiveness at improving prediction accuracy.展开更多
This study proposes a prediction model considering external weather and holiday factors to address the issue of accurately predicting urban taxi travel demand caused by complex data and numerous influencing factors.Th...This study proposes a prediction model considering external weather and holiday factors to address the issue of accurately predicting urban taxi travel demand caused by complex data and numerous influencing factors.The model integrates the Complete Ensemble Empirical Mode Decomposition with Adaptive Noise(CEEMDAN)and Convolutional Long Short Term Memory Neural Network(ConvLSTM)to predict short-term taxi travel demand.The CEEMDAN decomposition method effectively decomposes time series data into a set of modal components,capturing sequence characteristics at different time scales and frequencies.Based on the sample entropy value of components,secondary processing of more complex sequence components after decomposition is employed to reduce the cumulative prediction error of component sequences and improve prediction efficiency.On this basis,considering the correlation between the spatiotemporal trends of short-term taxi traffic,a ConvLSTM neural network model with Long Short Term Memory(LSTM)time series processing ability and Convolutional Neural Networks(CNN)spatial feature processing ability is constructed to predict the travel demand for urban taxis.The combined prediction model is tested on a taxi travel demand dataset in a certain area of Beijing.The results show that the CEEMDAN-ConvLSTM prediction model outperforms the LSTM,Autoregressive Integrated Moving Average model(ARIMA),CNN,and ConvLSTM benchmark models in terms of Symmetric Mean Absolute Percentage Error(SMAPE),Root Mean Square Error(RMSE),Mean Absolute Error(MAE),and R2 metrics.Notably,the SMAPE metric exhibits a remarkable decline of 21.03%with the utilization of our proposed model.These results confirm that our study provides a highly accurate and valid model for taxi travel demand forecasting.展开更多
Artificial neural network(ANN)has become an important method to model the nonlinear relationships between weather conditions,building characteristics and its heat demand.Due to the large amount of training data re-qui...Artificial neural network(ANN)has become an important method to model the nonlinear relationships between weather conditions,building characteristics and its heat demand.Due to the large amount of training data re-quired for ANN training,data reduction and feature selection are important to simplify the training.However,in building heat demand prediction,many weather-related input variables contain duplicated features.This paper develops a sensitivity analysis approach to analyse the correlation between input variables and to detect the variables that have high importance but contain duplicated features.The proposed approach is validated in a case study that predicts the heat demand of a district heating network containing tens of buildings at a university campus.The results show that the proposed approach detected and removed several unnecessary input variables and helped the ANN model to reduce approximately 20%training time compared with the traditional methods while maintaining the prediction accuracy.It indicates that the approach can be applied for analysing large num-ber of input variables to help improving the training efficiency of ANN in district heat demand prediction and other applications.展开更多
Accurate demand forecasting for online ride-hailing contributes to balancing traffic supply and demand,and improving the service level of ride-hailing platforms.In contrast to previous studies,which have primarily foc...Accurate demand forecasting for online ride-hailing contributes to balancing traffic supply and demand,and improving the service level of ride-hailing platforms.In contrast to previous studies,which have primarily focused on the inflow or outflow demands of each zone,this study proposes a conditional generative adversarial network with a Wasserstein divergence objective(CWGAN-div)to predict ride-hailing origin-destination(OD)demand matrices.Residual blocks and refined loss functions help to enhance the stability of model training.Interpretable conditional information is employed to capture external spatiotemporal dependencies and guide the model towards generating more precise results.Empirical analysis using ride-hailing data from Manhattan,New York City,demon-strates that our proposed CWGAN-div model can effectively predict the network-wide OD matrix and exhibits strong convergence performance.Comparative experiments also show that the CWGAN-div outperforms other benchmarking methods.Consequently,the proposed model displays potential for network-wide ride-hailing OD demand prediction.展开更多
Accurate and robust range estimation algorithms for battery electric vehicles have the potential to reduce range anxiety,increase the acceptance of lower-range vehicles,and improve the overall driving experience.Howev...Accurate and robust range estimation algorithms for battery electric vehicles have the potential to reduce range anxiety,increase the acceptance of lower-range vehicles,and improve the overall driving experience.However,developing such algorithms faces challenges due to the complexity of the driver-vehicle-environment system and the multitude of factors influencing a vehicle's energy demand.To address these challenges,this paper introduces a sensitivity analysis focused on driver-and environment-related factors,which are notably difficult to predict.Employing a global sensitivity analysis for factor prioritization,this study delineates and assesses the parameters and their value distributions using a validated vehicle simulation model.The co-simulation of a powertrain and an auxiliaries model enables the parameter-specific investigation of parameters related to the thermal system.The results are scenario-individual parameter rankings that show the importance of the considered factors in prediction algorithms and guide the strategy for the development of these algorithms.The acceleration behavior of the driver,often emphasized in literature,is shown to be of secondary importance to energy consumption.Moreover,factors such as air density and wind speed are identified as crucial in highway driving scenarios,whereas outside temperature and the probability of stopping at traffic lights are critical in urban settings.For validation purposes,the resulting rankings of the sensitivity study are validated by means of a convergence analysis.展开更多
Accurate prediction of nurse demand plays a crucial role in efficiently planning the healthcare workforce,ensuring appropriate staffing levels,and providing high-quality care to patients.The intricacy and variety of c...Accurate prediction of nurse demand plays a crucial role in efficiently planning the healthcare workforce,ensuring appropriate staffing levels,and providing high-quality care to patients.The intricacy and variety of contemporary healthcare systems and a growing patient populace call for advanced forecasting models.Factors like technological advancements,novel treatment protocols,and the increasing prevalence of chronic illnesses have diminished the efficacy of traditional estimation approaches.Novel forecasting methodologies,including time-series analysis,machine learning,and simulation-based techniques,have been developed to tackle these challenges.Time-series analysis recognizes patterns from past data,whereas machine learning uses extensive datasets to uncover concealed trends.Simulation models are employed to assess diverse scenarios,assisting in proactive adjustments to staffing.These techniques offer distinct advantages,such as the identification of seasonal patterns,the management of large datasets,and the ability to test various assumptions.By integrating these sophisticated models into workforce planning,organizations can optimize staffing,reduce financial waste,and elevate the standard of patient care.As the healthcare field progresses,the utilization of these predictive models will be pivotal for fostering adaptable and resilient workforce management.展开更多
In the context of the energy and climate crises,it is crucial for organizations to utilize advanced methods to reduce energy consumption and energy costs.This study explores the application of deep learning models for...In the context of the energy and climate crises,it is crucial for organizations to utilize advanced methods to reduce energy consumption and energy costs.This study explores the application of deep learning models for predicting energy demands in retail stores,which can enhance market efficiency and contribute to grid stability.We analyze a detailed electricity consumption dataset from a hypermarket in Hungary,focusing on 48-hour forecasts at 15-minute intervals.Our methodology includes the implementation of classical models such as ARIMA and linear regression,as well as state-of-the-art deep learning models like TiDE and foundational models such as Lag-Llama in a“zero shot prediction”as well as a“finetuning”scenario.展开更多
The development of vehicle-to-everything and cloud computing has brought new opportunities and challenges to the automobile industry.In this paper,a commuter vehicle demand torque prediction method based on historical...The development of vehicle-to-everything and cloud computing has brought new opportunities and challenges to the automobile industry.In this paper,a commuter vehicle demand torque prediction method based on historical vehicle speed information is proposed,which uses machine learning to predict and analyze vehicle demand torque.Firstly,the big data of vehicle driving is collected,and the driving data is cleaned and features extracted based on road information.Then,the vehicle longitudinal driving dynamics model is established.Next,the vehicle simulation simulator is established based on the longitudinal driving dynamics model of the vehicle,and the driving torque of the vehicle is obtained.Finally,the travel is divided into several accelerationcruise-deceleration road pairs for analysis,and the vehicle demand torque is predicted by BP neural network and Gaussian process regression.展开更多
Bulk mineral resources of iron ores, copper ores, bauxite, lead ores, zinc ores and potassium salt play a pivotal role on the world＇s and China＇s economic development. This study analyzed and predicted their resourc...Bulk mineral resources of iron ores, copper ores, bauxite, lead ores, zinc ores and potassium salt play a pivotal role on the world＇s and China＇s economic development. This study analyzed and predicted their resources base and potential, development and utilization and their world＇s and China＇s supply and demand situation in the future 20 years. The supply and demand of these six bulk mineral products are generally balanced, with a slight surplus, which will guarantee the stability of the international mineral commodity market supply. The six mineral resources （especially iron ores and copper ores） are abundant and have a great potential, and their development and utilization scale will gradually increase. Till the end of 2014, the reserve- production ratio of iron, copper, bauxite, lead, zinc ores and potassium salt was 95 years, 42 years, 100 years, 17 years, 37 years and 170 years, respectively. Except lead ores, the other five types all have reserve-production ratio exceeding 20 years, indicative of a high resources guarantee degree. If the utilization of recycled metals is counted in, the supply of the world＇s six mineral products will exceed the demand in the future twenty years. In 2015-2035, the supply of iron ores, refined copper, primary aluminum, refined lead, zinc and potassium salt will exceed their demand by 0.4-0.7 billion tons （Gt）, 5.0-6.0 million tons （Mt）, 1.1-8.9 Mt, 1.0-2.0 Mt, 1.2-2.0 Mt and 4.8-5.6 Mt, respectively. It is predicted that there is no problem with the supply side of bulk mineral products such as iron ores, but local or structural shortage may occur because of geopolitics, monopoly control, resources nationalism and trade friction. Affected by China＇s compressed industrialized development model, the demand of iron ores （crude steel）, potassium salt, refined lead, refined copper, bauxite （primary aluminum） and zinc will gradually reach their peak in advance. The demand peak of iron ores （crude steel） will reach around 2015, 2016 for potassium salt, 2020 for refined lead, 2021 for bauxite （primary aluminum）, 2022 for refined copper and 2023 for zinc. China＇s demand for iron ores （crude steel）, bauxite （primary aluminum） and zinc in the future 20 years will decline among the world＇s demand, while that for refined copper, refined lead and potassium salt will slightly increase. The demand for bulk mineral products still remains high. In 2015-2035, China＇s accumulative demand for iron ores （crude steel） will be 20.313 Gt （13.429 Gt）, 0.304 Gt for refined copper, 2.466 Gt （0.616 Gt） of bauxite （primary aluminum）, 0.102 Gt of refined lead, 0.138 Gt of zinc and 0.157 Gt of potassium salt, and they account for the world＇s YOY （YOY） accumulative demand of 35.17%, 51.09%, 48.47%, 46.62%, 43.95% and 21.84%, respectively. This proportion is 49.40%, 102.52%, 87.44%, 105.65%, 93.62% and 106.49% of that in 2014, respectively. From the supply side of China＇s bulk mineral resources, it is forecasted that the accumulative supply of primary （mine） mineral products in 2015-2035 is 4.046 Gt of iron ores, 0.591 Gt of copper, 1.129 Gt of bauxite, 63.661 Mt of （mine） lead, 0.109 Gt of （mine） zinc and 0.128 Gt of potassium salt, which accounts for 8.82%, 13.92%, 26.67%, 47.09%, 33.04% and 15.56% of the world＇s predicted YOY production, respectively. With the rapid increase in the smelting capacity of iron and steel and alumina, the rate of capacity utilization for crude steel, refined copper, alumina, primary aluminum and refined lead in 2014 was 72.13%, 83.63%, 74.45%, 70.76% and 72.22%, respectively. During 2000-2014, the rate of capacity utilization for China＇s crude steel and refined copper showed a generally fluctuating decrease, which leads to an insufficient supply of primary mineral products. It is forecasted that the supply insufficiency of iron ores in 2015-2035 is 17.44 Gt, 0.245 Gt of copper in copper concentrates, 1.337 Gt of bauxite, 38.44 Mt of lead in lead concentrates and 29.19 Mt of zinc in zinc concentrates. China has gradually raised the utilization of recycled metals, which has mitigated the insufficient supply of primary metal products to some extent. It is forecasted that in 2015-2035 the accumulative utilization amount of steel scrap （iron ores） is 3.27 Gt （5.08 Gt）, 70.312 Mt of recycled copper, 0.2 Gt of recycled aluminum, 48 Mt of recycled lead and 7.7 Mt of recycled zinc. The analysis on the supply and demand situation of China＇s bulk mineral resources in 2015-2035 suggests that the supply-demand contradiction for these six types of mineral products will decrease, indicative of a generally declining external dependency. If the use of recycled metal amount is counted in, the external dependency of China＇s iron, copper, bauxite, lead, zinc and potassium salt will be 79%, 65%, 26%, 8%, 16% and 18% in 2014, respectively. It is predicted that this external dependency will decrease to 62%, 64%, 20%, -0.93%, 16% and 14% in 2020, respectively, showing an overall decreasing trend. We propose the following suggestions correspondingly. （1） The demand peak of China＇s crude steel and potassium salt will reach during 2015-2023 in succession. Mining transformation should be planned and deployed in advance to deal with the arrival of this demand peak. （2） The supply-demand contradiction of China＇s bulk mineral resources will mitigate in the future 20 years, and the external dependency will decrease accordingly. It is suggested to adjust the mineral resources management policies according to different minerals and regions, and regulate the exploration and development activities. （3） China should further establish and improve the forced mechanism of resolving the smelting overcapacity of steel, refined copper, primary aluminum, lead and zinc to really achieve the goal of ＂reducing excess production capacity＂. （4） In accordance with the national strategic deployment of ＂One Belt One Road＂, China should encourage the excess capacity of steel, copper, alumina and primary aluminum enterprises to transfer to those countries or areas with abundant resources, high energy matching degree and relatively excellent infrastructure. Based on the national conditions, mining condition and geopolitics of the resources countries, we will gradually build steel, copper, aluminum and lead-zinc smelting bases, and potash processing and production bases, which will promote the excess capacity to transfer to the overseas orderly. （5） It is proposed to strengthen the planning and management of renewable resources recycling and to construct industrial base of renewable metal recycling. （6） China should promote the comprehensive development and utilization of paragenetic and associated mineral species to further improve the comprehensive utilization of bulk mineral resources.展开更多
Aiming at the problem that the consumption data of new ammunition is less and the demand is difficult to predict,combined with the law of ammunition consumption under different damage grades,a Bayesian inference metho...Aiming at the problem that the consumption data of new ammunition is less and the demand is difficult to predict,combined with the law of ammunition consumption under different damage grades,a Bayesian inference method for ammunition demand based on Gompertz distribution is proposed.The Bayesian inference model based on Gompertz distribution is constructed,and the system contribution degree is introduced to determine the weight of the multi-source information.In the case where the prior distribution is known and the distribution of the field data is unknown,the consistency test is performed on the prior information,and the consistency test problem is transformed into the goodness of the fit test problem.Then the Bayesian inference is solved by the Markov chain-Monte Carlo(MCMC)method,and the ammunition demand under different damage grades is gained.The example verifies the accuracy of this method and solves the problem of ammunition demand prediction in the case of insufficient samples.展开更多
Mobile bike-sharing services have been prevalently used in many cities as an important urban commuting service and a promising way to build smart cities,especially in the new era of 5G and Internet-of-Things(IoT)envir...Mobile bike-sharing services have been prevalently used in many cities as an important urban commuting service and a promising way to build smart cities,especially in the new era of 5G and Internet-of-Things(IoT)environments.A mobile bike-sharing service makes commuting convenient for people and imparts new vitality to urban transportation systems.In the real world,the problems of no docks or no bikes at bike-sharing stations often arise because of several inevitable reasons such as the uncertainty of bike usage.In addition to pure manual rebalancing,in several works,attempts were made to predict the demand for bikes.In this paper,we devised a bike-sharing service with highly accurate demand prediction using collaborative computing and information fusion.We combined the information of bike demands at different time periods and the locations between stations and proposed a dynamical clustering algorithm for station clustering.We carefully analyzed and discovered the group of features that impact the demand of bikes,from historical bike-sharing records and 5G IoT environment data.We combined the discovered information and proposed an XGBoost-based regression model to predict the rental and return demand.We performed sufficient experiments on two real-world datasets.The results confirm that compared to some existing methods,our method produces superior prediction results and performance and improves the availability of bike-sharing service in 5G IoT environments.展开更多
This paper discusses how ML can be leveraged to enhance supply chain forecasting through demand prediction,risk mitigation and demand-supply match optimization.Even deterministic and time-series supply chain approache...This paper discusses how ML can be leveraged to enhance supply chain forecasting through demand prediction,risk mitigation and demand-supply match optimization.Even deterministic and time-series supply chain approaches don’t have an edge over volatile and challenging data environments,making them imprecise and inflexible.Through the use of ML models,such as recurrent neural networks(RNNs),support vector machines(SVMs),and reinforcement learning(RL)agents,this study shows the accuracy in demand prediction,risk detection,and supply-demand match.The primary findings include:the RNN decreases the mean squared error by 15%over traditional approaches and the RL agent minimizes inventory turnover and lead times to enhance supply chain efficiencies.These results highlight the potential of ML to react rapidly to real-time shifts and drive better decisions.The report provides a comprehensive approach to data-driven predictive models,and useful advice for companies looking to improve supply chain resilience and profitability.展开更多
Online demand prediction plays an important role in transport network services from operations,controls to management,and information provision.However,the online prediction models are impacted by streaming data quali...Online demand prediction plays an important role in transport network services from operations,controls to management,and information provision.However,the online prediction models are impacted by streaming data quality issues with noise measurements and missing data.To address these,we develop a robust prediction method for online network-level demand prediction in public transport.It consists of a PCA method to extract eigen demand images and an optimization-based pattern recognition model to predict the weights of eigen demand images by making use of the partially observed real-time data up to the prediction time in a day.The prediction model is robust to data quality issues given that the eigen demand images are stable and the predicted weights of them are optimized using the network level data(less impacted by local data quality issues).In the case study,we validate the accuracy and transferability of the model by comparing it with benchmark models and evaluate the robustness in tolerating data quality issues of the proposed model.The experimental results demonstrate that the proposed Pattern Recognition Prediction based on PCA(PRP-PCA)consistently outperforms other benchmark models in accuracy and transferability.Moreover,the model shows high robustness in accommodating data quality issues.For example,the PRP-PCA model is robust to missing data up to 50%regardless of the noise level.We also discuss the hidden patterns behind the network level demand.The visualization analysis shows that eigen demand images are significantly connected to the network structure and station activity variabilities.Though the demand changes dramatically before and after the pandemic,the eigen demand images are consistent over time in Stockholm.展开更多
Due to the impact of occupants’activities in buildings,the relationship between electricity demand and ambient temperature will show different trends in the long-term and short-term,which show seasonal variation and ...Due to the impact of occupants’activities in buildings,the relationship between electricity demand and ambient temperature will show different trends in the long-term and short-term,which show seasonal variation and hourly variation,respectively.This makes it difficult for conventional data fitting methods to accurately predict the long-term and short-term power demand of buildings at the same time.In order to solve this problem,this paper proposes two approaches for fitting and predicting the electricity demand of office buildings.The first proposed approach splits the electricity demand data into fixed time periods,containing working hours and non-working hours,to reduce the impact of occupants’activities.After finding the most sensitive weather variable to non-working hour electricity demand,the building baseload and occupant activities can be predicted separately.The second proposed approach uses the artificial neural network(ANN)and fuzzy logic techniques to fit the building baseload,peak load,and occupancy rate with multi-variables of weather variables.In this approach,the power demand data is split into a narrower time range as no-occupancy hours,full-occupancy hours,and fuzzy hours between them,in which the occupancy rate is varying depending on the time and weather variables.The proposed approaches are verified by the real data from the University of Glasgow as a case study.The simulation results show that,compared with the traditional ANN method,both proposed approaches have less root-mean-square-error(RMSE)in predicting electricity demand.In addition,the proposed working and non-working hour based regression approach reduces the average RMSE by 35%,while the ANN with fuzzy hours based approach reduces the average RMSE by 42%,comparing with the traditional power demand prediction method.In addition,the second proposed approach can provide more information for building energy management,including the predicted baseload,peak load,and occupancy rate,without requiring additional building parameters.展开更多
基金supported by 2022 Shenyang Philosophy and Social Science Planning under grant SY202201Z,Liaoning Provincial Department of Education Project under grant LJKZ0588.
文摘Taxi demand prediction is a crucial component of intelligent transportation system research.Compared to region-based demand prediction,origin-destination(OD)demand prediction has a wide range of potential applications,including real-time matching,idle vehicle allocation,ridesharing services,and dynamic pricing,among others.However,because OD demand involves complex spatiotemporal dependence,research in this area has been limited thus far.In this paper,we first review existing research from four perspectives:topology construction,temporal and spatial feature processing,and other relevant factors.We then elaborate on the advantages and limitations of OD prediction methods based on deep learning architecture theory.Next,we discuss ongoing challenges in OD prediction,such as dynamics,spatiotemporal dependence,semantic differentiation,time window selection,and data sparsity problems,and summarize and compare potential solutions to each challenge.These findings offer valuable insights for model selection in OD demand prediction.Finally,we provide public datasets and open-source code,along with suggestions for future research directions.
基金National Natural Science Foundation of China,No.41971233。
文摘Urban construction land has relatively high human activity and high carbon emissions.Research on urban construction land prediction under carbon peak and neutrality goals(hereafter“dual carbon”goals)is important for territorial spatial planning.This study analyzed quantitative relationships between carbon emissions and urban construction land,and then modified the construction land demand prediction model.Thereafter,an integrated model for urban construction land demand prediction and spatial pattern simulation under“dual carbon”goals was developed,where urban construction land suitability was modified based on carbon source and sink capacity of different land-use types.Using Guangzhou as a case study,the integrated model was validated and applied to simulate the spatiotemporal dynamics of its urban construction land during 2030–2060 under baseline development and“dual carbon”goals scenarios.The simulation results showed that Guangzhou’s urban construction land expanded rapidly until 2030,with the spatial pattern not showing an intensive development trend.Guangzhou’s urban construction land expansion slowed during 2030–2060,with an average annual growth rate of 0.2%,and a centralized spatial pattern trend.Under the“dual carbon”goal scenario,Guangzhou’s urban construction land evolved into a polycentric development pattern in 2030.Compared with the baseline development scenario,urban construction land expansion in Guangzhou during 2030–2060 is slower,with an average annual growth rate of only 0.1%,and the polycentric development pattern of urban construction land was more prominent.Furthermore,land maintenance and growth,that is,a carbon sink,is more obvious under the“dual carbon”goals scenario,with the forest land area nearly 10.6%higher than that under the baseline development scenario.The study of urban construction land demand prediction and spatial pattern simulation under“dual carbon”goals provides a scientific decision-making support tool for territorial spatial planning,aiding in quantifying territorial spatial planning.
基金supported by the National Natural Science Foundation of China(72288101,72201029,and 72322022).
文摘Accurate origin–destination(OD)demand prediction is crucial for the efficient operation and management of urban rail transit(URT)systems,particularly during a pandemic.However,this task faces several limitations,including real-time availability,sparsity,and high-dimensionality issues,and the impact of the pandemic.Consequently,this study proposes a unified framework called the physics-guided adaptive graph spatial–temporal attention network(PAG-STAN)for metro OD demand prediction under pandemic conditions.Specifically,PAG-STAN introduces a real-time OD estimation module to estimate real-time complete OD demand matrices.Subsequently,a novel dynamic OD demand matrix compression module is proposed to generate dense real-time OD demand matrices.Thereafter,PAG-STAN leverages various heterogeneous data to learn the evolutionary trend of future OD ridership during the pandemic.Finally,a masked physics-guided loss function(MPG-loss function)incorporates the physical quantity information between the OD demand and inbound flow into the loss function to enhance model interpretability.PAG-STAN demonstrated favorable performance on two real-world metro OD demand datasets under the pandemic and conventional scenarios,highlighting its robustness and sensitivity for metro OD demand prediction.A series of ablation studies were conducted to verify the indispensability of each module in PAG-STAN.
基金This work was supported by Korea Institute for Advancement of Technology(KIAT)grant funded by the Korea Government(MOTIE)(P0016977,The Establishment Project of Industry-University Fusion District).
文摘The increasing penetration rate of electric kickboard vehicles has been popularized and promoted primarily because of its clean and efficient features.Electric kickboards are gradually growing in popularity in tourist and education-centric localities.In the upcoming arrival of electric kickboard vehicles,deploying a customer rental service is essential.Due to its freefloating nature,the shared electric kickboard is a common and practical means of transportation.Relocation plans for shared electric kickboards are required to increase the quality of service,and forecasting demand for their use in a specific region is crucial.Predicting demand accurately with small data is troublesome.Extensive data is necessary for training machine learning algorithms for effective prediction.Data generation is a method for expanding the amount of data that will be further accessible for training.In this work,we proposed a model that takes time-series customers’electric kickboard demand data as input,pre-processes it,and generates synthetic data according to the original data distribution using generative adversarial networks(GAN).The electric kickboard mobility demand prediction error was reduced when we combined synthetic data with the original data.We proposed Tabular-GAN-Modified-WGAN-GP for generating synthetic data for better prediction results.We modified The Wasserstein GAN-gradient penalty(GP)with the RMSprop optimizer and then employed Spectral Normalization(SN)to improve training stability and faster convergence.Finally,we applied a regression-based blending ensemble technique that can help us to improve performance of demand prediction.We used various evaluation criteria and visual representations to compare our proposed model’s performance.Synthetic data generated by our suggested GAN model is also evaluated.The TGAN-Modified-WGAN-GP model mitigates the overfitting and mode collapse problem,and it also converges faster than previous GAN models for synthetic data creation.The presented model’s performance is compared to existing ensemble and baseline models.The experimental findings imply that combining synthetic and actual data can significantly reduce prediction error rates in the mean absolute percentage error(MAPE)of 4.476 and increase prediction accuracy.
基金sponsored by National Key Research and Development Program of China(No.2017YFB0304100)。
文摘In this study,related models of alloy purchasing decision system in the Baoshan base of Baosteel are discussed.First,the corresponding relationship between steel grades and alloy consumption is established through metallurgical-mechanism modeling and statistical analysis.Then,the alloy-demand prediction model based on alloy unit consumption and time series analysis is developed by combining sales plans and historical data.Finally,the alloy purchasing and inventory optimization model is developed to minimize the total cost of purchase and storage by combining inventory optimization theories.
基金the National Natural Science Founda-tion of China(Nos.72171175,and 72021102)。
文摘This study addresses a new charging station network planning problem for smart connected electric vehicles.We embed a charging station choice model into a charging network planning model that explicitly considers the heterogeneity of the charging behavior in a data-driven manner.To cope with the deficiencies from a small size and sparse behavioral data,we propose a robust charging demand prediction method that can significantly reduce the impact of sample errors and missing data.On the basis of these two building blocks,we form and solve a new optimal charging station location and capacity problem by minimizing the construction and charging costs while considering the charging service level,construction budget,and limit to the number of chargers.We use a case study of planning charging stations in Shanghai to validate our contributions and provide managerial insight in this area.
基金supported in part by the National Key Research and Development Program of China under Grant 2022YFB2403900.
文摘The charging behaviors of electric vehicle(EV)users exhibit high randomness and individual heterogeneity,with the key parameters such as the charging duration and charged energy levels displaying significant fluctuations.Compared with EV cluster-layer prediction,predicting the charging demands of individual users requires not only the analysis of more complex charging behaviors but also the establishment of a coupling model between exogenous variables(e.g.,weather and holidays)and prediction accuracy,thereby imposing higher robustness requirements on prediction algorithms.An individual-user EV charging demand prediction method that in-tegrates multisource data with a dual-layer clustering approach and a light gradient boosting machine(LightGBM)is proposed in this study to address these technical challenges.First,a multisource dataset that incorporates user charging behavior data and exogenous variables(meteorological factors and date types)is constructed.A dual-layer feature extraction mechanism consisting of data-layer clustering for charging type identification and user-layer clustering for user group classification is employed,thereby establishing a classi-fication feature space that characterizes different charging types and user groups.A predictive model is subse-quently developed using the LightGBM algorithm,which directly incorporates classification features as its inputs,effectively mitigating the information loss associated with the traditional categorical variable encoding process.Finally,employing EV users from a typical residential community in northern China as an empirical case,comparative experiments are performed to validate the proposed method,demonstrating its effectiveness at improving prediction accuracy.
基金supported by the Surface Project of the National Natural Science Foundation of China(No.71273024)the Fundamental Research Funds for the Central Universities of China(2021YJS080).
文摘This study proposes a prediction model considering external weather and holiday factors to address the issue of accurately predicting urban taxi travel demand caused by complex data and numerous influencing factors.The model integrates the Complete Ensemble Empirical Mode Decomposition with Adaptive Noise(CEEMDAN)and Convolutional Long Short Term Memory Neural Network(ConvLSTM)to predict short-term taxi travel demand.The CEEMDAN decomposition method effectively decomposes time series data into a set of modal components,capturing sequence characteristics at different time scales and frequencies.Based on the sample entropy value of components,secondary processing of more complex sequence components after decomposition is employed to reduce the cumulative prediction error of component sequences and improve prediction efficiency.On this basis,considering the correlation between the spatiotemporal trends of short-term taxi traffic,a ConvLSTM neural network model with Long Short Term Memory(LSTM)time series processing ability and Convolutional Neural Networks(CNN)spatial feature processing ability is constructed to predict the travel demand for urban taxis.The combined prediction model is tested on a taxi travel demand dataset in a certain area of Beijing.The results show that the CEEMDAN-ConvLSTM prediction model outperforms the LSTM,Autoregressive Integrated Moving Average model(ARIMA),CNN,and ConvLSTM benchmark models in terms of Symmetric Mean Absolute Percentage Error(SMAPE),Root Mean Square Error(RMSE),Mean Absolute Error(MAE),and R2 metrics.Notably,the SMAPE metric exhibits a remarkable decline of 21.03%with the utilization of our proposed model.These results confirm that our study provides a highly accurate and valid model for taxi travel demand forecasting.
文摘Artificial neural network(ANN)has become an important method to model the nonlinear relationships between weather conditions,building characteristics and its heat demand.Due to the large amount of training data re-quired for ANN training,data reduction and feature selection are important to simplify the training.However,in building heat demand prediction,many weather-related input variables contain duplicated features.This paper develops a sensitivity analysis approach to analyse the correlation between input variables and to detect the variables that have high importance but contain duplicated features.The proposed approach is validated in a case study that predicts the heat demand of a district heating network containing tens of buildings at a university campus.The results show that the proposed approach detected and removed several unnecessary input variables and helped the ANN model to reduce approximately 20%training time compared with the traditional methods while maintaining the prediction accuracy.It indicates that the approach can be applied for analysing large num-ber of input variables to help improving the training efficiency of ANN in district heat demand prediction and other applications.
基金supported by the National Natural Science Foundation of China(Grant No.72371251)the National Science Foundation for Distinguished Young Scholars of Hunan Province(Grant No.2024JJ2080)+1 种基金the Excellent Youth Foundation of Hunan Education Department(Grant No.21B0015)the State Key Lab-oratory of Rail Traffic Control and Safety of Beijing Jiaotong Uni-v ersity,China(Gr ant No.RCS2022K004).
文摘Accurate demand forecasting for online ride-hailing contributes to balancing traffic supply and demand,and improving the service level of ride-hailing platforms.In contrast to previous studies,which have primarily focused on the inflow or outflow demands of each zone,this study proposes a conditional generative adversarial network with a Wasserstein divergence objective(CWGAN-div)to predict ride-hailing origin-destination(OD)demand matrices.Residual blocks and refined loss functions help to enhance the stability of model training.Interpretable conditional information is employed to capture external spatiotemporal dependencies and guide the model towards generating more precise results.Empirical analysis using ride-hailing data from Manhattan,New York City,demon-strates that our proposed CWGAN-div model can effectively predict the network-wide OD matrix and exhibits strong convergence performance.Comparative experiments also show that the CWGAN-div outperforms other benchmarking methods.Consequently,the proposed model displays potential for network-wide ride-hailing OD demand prediction.
基金Open Access funding enabled and organized by Projekt DEAL.
文摘Accurate and robust range estimation algorithms for battery electric vehicles have the potential to reduce range anxiety,increase the acceptance of lower-range vehicles,and improve the overall driving experience.However,developing such algorithms faces challenges due to the complexity of the driver-vehicle-environment system and the multitude of factors influencing a vehicle's energy demand.To address these challenges,this paper introduces a sensitivity analysis focused on driver-and environment-related factors,which are notably difficult to predict.Employing a global sensitivity analysis for factor prioritization,this study delineates and assesses the parameters and their value distributions using a validated vehicle simulation model.The co-simulation of a powertrain and an auxiliaries model enables the parameter-specific investigation of parameters related to the thermal system.The results are scenario-individual parameter rankings that show the importance of the considered factors in prediction algorithms and guide the strategy for the development of these algorithms.The acceleration behavior of the driver,often emphasized in literature,is shown to be of secondary importance to energy consumption.Moreover,factors such as air density and wind speed are identified as crucial in highway driving scenarios,whereas outside temperature and the probability of stopping at traffic lights are critical in urban settings.For validation purposes,the resulting rankings of the sensitivity study are validated by means of a convergence analysis.
文摘Accurate prediction of nurse demand plays a crucial role in efficiently planning the healthcare workforce,ensuring appropriate staffing levels,and providing high-quality care to patients.The intricacy and variety of contemporary healthcare systems and a growing patient populace call for advanced forecasting models.Factors like technological advancements,novel treatment protocols,and the increasing prevalence of chronic illnesses have diminished the efficacy of traditional estimation approaches.Novel forecasting methodologies,including time-series analysis,machine learning,and simulation-based techniques,have been developed to tackle these challenges.Time-series analysis recognizes patterns from past data,whereas machine learning uses extensive datasets to uncover concealed trends.Simulation models are employed to assess diverse scenarios,assisting in proactive adjustments to staffing.These techniques offer distinct advantages,such as the identification of seasonal patterns,the management of large datasets,and the ability to test various assumptions.By integrating these sophisticated models into workforce planning,organizations can optimize staffing,reduce financial waste,and elevate the standard of patient care.As the healthcare field progresses,the utilization of these predictive models will be pivotal for fostering adaptable and resilient workforce management.
文摘In the context of the energy and climate crises,it is crucial for organizations to utilize advanced methods to reduce energy consumption and energy costs.This study explores the application of deep learning models for predicting energy demands in retail stores,which can enhance market efficiency and contribute to grid stability.We analyze a detailed electricity consumption dataset from a hypermarket in Hungary,focusing on 48-hour forecasts at 15-minute intervals.Our methodology includes the implementation of classical models such as ARIMA and linear regression,as well as state-of-the-art deep learning models like TiDE and foundational models such as Lag-Llama in a“zero shot prediction”as well as a“finetuning”scenario.
基金supported in part by National Natural Science Foundation(NNSF)of China(Nos.61803079,61890924,61991404)in part by Fundamental Research Funds for the Central Universities(No.N2108006)in part by Liaoning Revitalization Talents Program(No.XLYC1907087)。
文摘The development of vehicle-to-everything and cloud computing has brought new opportunities and challenges to the automobile industry.In this paper,a commuter vehicle demand torque prediction method based on historical vehicle speed information is proposed,which uses machine learning to predict and analyze vehicle demand torque.Firstly,the big data of vehicle driving is collected,and the driving data is cleaned and features extracted based on road information.Then,the vehicle longitudinal driving dynamics model is established.Next,the vehicle simulation simulator is established based on the longitudinal driving dynamics model of the vehicle,and the driving torque of the vehicle is obtained.Finally,the travel is divided into several accelerationcruise-deceleration road pairs for analysis,and the vehicle demand torque is predicted by BP neural network and Gaussian process regression.
基金supported by the China geological survey subproject of Dynamic Track and Evaluation of the Guarantee Degree of the Main Mineral Resources in China(No.121201103000150112,N1618-8)
文摘Bulk mineral resources of iron ores, copper ores, bauxite, lead ores, zinc ores and potassium salt play a pivotal role on the world＇s and China＇s economic development. This study analyzed and predicted their resources base and potential, development and utilization and their world＇s and China＇s supply and demand situation in the future 20 years. The supply and demand of these six bulk mineral products are generally balanced, with a slight surplus, which will guarantee the stability of the international mineral commodity market supply. The six mineral resources （especially iron ores and copper ores） are abundant and have a great potential, and their development and utilization scale will gradually increase. Till the end of 2014, the reserve- production ratio of iron, copper, bauxite, lead, zinc ores and potassium salt was 95 years, 42 years, 100 years, 17 years, 37 years and 170 years, respectively. Except lead ores, the other five types all have reserve-production ratio exceeding 20 years, indicative of a high resources guarantee degree. If the utilization of recycled metals is counted in, the supply of the world＇s six mineral products will exceed the demand in the future twenty years. In 2015-2035, the supply of iron ores, refined copper, primary aluminum, refined lead, zinc and potassium salt will exceed their demand by 0.4-0.7 billion tons （Gt）, 5.0-6.0 million tons （Mt）, 1.1-8.9 Mt, 1.0-2.0 Mt, 1.2-2.0 Mt and 4.8-5.6 Mt, respectively. It is predicted that there is no problem with the supply side of bulk mineral products such as iron ores, but local or structural shortage may occur because of geopolitics, monopoly control, resources nationalism and trade friction. Affected by China＇s compressed industrialized development model, the demand of iron ores （crude steel）, potassium salt, refined lead, refined copper, bauxite （primary aluminum） and zinc will gradually reach their peak in advance. The demand peak of iron ores （crude steel） will reach around 2015, 2016 for potassium salt, 2020 for refined lead, 2021 for bauxite （primary aluminum）, 2022 for refined copper and 2023 for zinc. China＇s demand for iron ores （crude steel）, bauxite （primary aluminum） and zinc in the future 20 years will decline among the world＇s demand, while that for refined copper, refined lead and potassium salt will slightly increase. The demand for bulk mineral products still remains high. In 2015-2035, China＇s accumulative demand for iron ores （crude steel） will be 20.313 Gt （13.429 Gt）, 0.304 Gt for refined copper, 2.466 Gt （0.616 Gt） of bauxite （primary aluminum）, 0.102 Gt of refined lead, 0.138 Gt of zinc and 0.157 Gt of potassium salt, and they account for the world＇s YOY （YOY） accumulative demand of 35.17%, 51.09%, 48.47%, 46.62%, 43.95% and 21.84%, respectively. This proportion is 49.40%, 102.52%, 87.44%, 105.65%, 93.62% and 106.49% of that in 2014, respectively. From the supply side of China＇s bulk mineral resources, it is forecasted that the accumulative supply of primary （mine） mineral products in 2015-2035 is 4.046 Gt of iron ores, 0.591 Gt of copper, 1.129 Gt of bauxite, 63.661 Mt of （mine） lead, 0.109 Gt of （mine） zinc and 0.128 Gt of potassium salt, which accounts for 8.82%, 13.92%, 26.67%, 47.09%, 33.04% and 15.56% of the world＇s predicted YOY production, respectively. With the rapid increase in the smelting capacity of iron and steel and alumina, the rate of capacity utilization for crude steel, refined copper, alumina, primary aluminum and refined lead in 2014 was 72.13%, 83.63%, 74.45%, 70.76% and 72.22%, respectively. During 2000-2014, the rate of capacity utilization for China＇s crude steel and refined copper showed a generally fluctuating decrease, which leads to an insufficient supply of primary mineral products. It is forecasted that the supply insufficiency of iron ores in 2015-2035 is 17.44 Gt, 0.245 Gt of copper in copper concentrates, 1.337 Gt of bauxite, 38.44 Mt of lead in lead concentrates and 29.19 Mt of zinc in zinc concentrates. China has gradually raised the utilization of recycled metals, which has mitigated the insufficient supply of primary metal products to some extent. It is forecasted that in 2015-2035 the accumulative utilization amount of steel scrap （iron ores） is 3.27 Gt （5.08 Gt）, 70.312 Mt of recycled copper, 0.2 Gt of recycled aluminum, 48 Mt of recycled lead and 7.7 Mt of recycled zinc. The analysis on the supply and demand situation of China＇s bulk mineral resources in 2015-2035 suggests that the supply-demand contradiction for these six types of mineral products will decrease, indicative of a generally declining external dependency. If the use of recycled metal amount is counted in, the external dependency of China＇s iron, copper, bauxite, lead, zinc and potassium salt will be 79%, 65%, 26%, 8%, 16% and 18% in 2014, respectively. It is predicted that this external dependency will decrease to 62%, 64%, 20%, -0.93%, 16% and 14% in 2020, respectively, showing an overall decreasing trend. We propose the following suggestions correspondingly. （1） The demand peak of China＇s crude steel and potassium salt will reach during 2015-2023 in succession. Mining transformation should be planned and deployed in advance to deal with the arrival of this demand peak. （2） The supply-demand contradiction of China＇s bulk mineral resources will mitigate in the future 20 years, and the external dependency will decrease accordingly. It is suggested to adjust the mineral resources management policies according to different minerals and regions, and regulate the exploration and development activities. （3） China should further establish and improve the forced mechanism of resolving the smelting overcapacity of steel, refined copper, primary aluminum, lead and zinc to really achieve the goal of ＂reducing excess production capacity＂. （4） In accordance with the national strategic deployment of ＂One Belt One Road＂, China should encourage the excess capacity of steel, copper, alumina and primary aluminum enterprises to transfer to those countries or areas with abundant resources, high energy matching degree and relatively excellent infrastructure. Based on the national conditions, mining condition and geopolitics of the resources countries, we will gradually build steel, copper, aluminum and lead-zinc smelting bases, and potash processing and production bases, which will promote the excess capacity to transfer to the overseas orderly. （5） It is proposed to strengthen the planning and management of renewable resources recycling and to construct industrial base of renewable metal recycling. （6） China should promote the comprehensive development and utilization of paragenetic and associated mineral species to further improve the comprehensive utilization of bulk mineral resources.
基金the Army Scientific Research(KYSZJWJK1744,012016012600B11403).
文摘Aiming at the problem that the consumption data of new ammunition is less and the demand is difficult to predict,combined with the law of ammunition consumption under different damage grades,a Bayesian inference method for ammunition demand based on Gompertz distribution is proposed.The Bayesian inference model based on Gompertz distribution is constructed,and the system contribution degree is introduced to determine the weight of the multi-source information.In the case where the prior distribution is known and the distribution of the field data is unknown,the consistency test is performed on the prior information,and the consistency test problem is transformed into the goodness of the fit test problem.Then the Bayesian inference is solved by the Markov chain-Monte Carlo(MCMC)method,and the ammunition demand under different damage grades is gained.The example verifies the accuracy of this method and solves the problem of ammunition demand prediction in the case of insufficient samples.
基金supported by the National Natural Science Foundation of China (No. 61902236)Fundamental Research Funds for the Central Universities (No. JB210311).
文摘Mobile bike-sharing services have been prevalently used in many cities as an important urban commuting service and a promising way to build smart cities,especially in the new era of 5G and Internet-of-Things(IoT)environments.A mobile bike-sharing service makes commuting convenient for people and imparts new vitality to urban transportation systems.In the real world,the problems of no docks or no bikes at bike-sharing stations often arise because of several inevitable reasons such as the uncertainty of bike usage.In addition to pure manual rebalancing,in several works,attempts were made to predict the demand for bikes.In this paper,we devised a bike-sharing service with highly accurate demand prediction using collaborative computing and information fusion.We combined the information of bike demands at different time periods and the locations between stations and proposed a dynamical clustering algorithm for station clustering.We carefully analyzed and discovered the group of features that impact the demand of bikes,from historical bike-sharing records and 5G IoT environment data.We combined the discovered information and proposed an XGBoost-based regression model to predict the rental and return demand.We performed sufficient experiments on two real-world datasets.The results confirm that compared to some existing methods,our method produces superior prediction results and performance and improves the availability of bike-sharing service in 5G IoT environments.
文摘This paper discusses how ML can be leveraged to enhance supply chain forecasting through demand prediction,risk mitigation and demand-supply match optimization.Even deterministic and time-series supply chain approaches don’t have an edge over volatile and challenging data environments,making them imprecise and inflexible.Through the use of ML models,such as recurrent neural networks(RNNs),support vector machines(SVMs),and reinforcement learning(RL)agents,this study shows the accuracy in demand prediction,risk detection,and supply-demand match.The primary findings include:the RNN decreases the mean squared error by 15%over traditional approaches and the RL agent minimizes inventory turnover and lead times to enhance supply chain efficiencies.These results highlight the potential of ML to react rapidly to real-time shifts and drive better decisions.The report provides a comprehensive approach to data-driven predictive models,and useful advice for companies looking to improve supply chain resilience and profitability.
文摘Online demand prediction plays an important role in transport network services from operations,controls to management,and information provision.However,the online prediction models are impacted by streaming data quality issues with noise measurements and missing data.To address these,we develop a robust prediction method for online network-level demand prediction in public transport.It consists of a PCA method to extract eigen demand images and an optimization-based pattern recognition model to predict the weights of eigen demand images by making use of the partially observed real-time data up to the prediction time in a day.The prediction model is robust to data quality issues given that the eigen demand images are stable and the predicted weights of them are optimized using the network level data(less impacted by local data quality issues).In the case study,we validate the accuracy and transferability of the model by comparing it with benchmark models and evaluate the robustness in tolerating data quality issues of the proposed model.The experimental results demonstrate that the proposed Pattern Recognition Prediction based on PCA(PRP-PCA)consistently outperforms other benchmark models in accuracy and transferability.Moreover,the model shows high robustness in accommodating data quality issues.For example,the PRP-PCA model is robust to missing data up to 50%regardless of the noise level.We also discuss the hidden patterns behind the network level demand.The visualization analysis shows that eigen demand images are significantly connected to the network structure and station activity variabilities.Though the demand changes dramatically before and after the pandemic,the eigen demand images are consistent over time in Stockholm.
文摘Due to the impact of occupants’activities in buildings,the relationship between electricity demand and ambient temperature will show different trends in the long-term and short-term,which show seasonal variation and hourly variation,respectively.This makes it difficult for conventional data fitting methods to accurately predict the long-term and short-term power demand of buildings at the same time.In order to solve this problem,this paper proposes two approaches for fitting and predicting the electricity demand of office buildings.The first proposed approach splits the electricity demand data into fixed time periods,containing working hours and non-working hours,to reduce the impact of occupants’activities.After finding the most sensitive weather variable to non-working hour electricity demand,the building baseload and occupant activities can be predicted separately.The second proposed approach uses the artificial neural network(ANN)and fuzzy logic techniques to fit the building baseload,peak load,and occupancy rate with multi-variables of weather variables.In this approach,the power demand data is split into a narrower time range as no-occupancy hours,full-occupancy hours,and fuzzy hours between them,in which the occupancy rate is varying depending on the time and weather variables.The proposed approaches are verified by the real data from the University of Glasgow as a case study.The simulation results show that,compared with the traditional ANN method,both proposed approaches have less root-mean-square-error(RMSE)in predicting electricity demand.In addition,the proposed working and non-working hour based regression approach reduces the average RMSE by 35%,while the ANN with fuzzy hours based approach reduces the average RMSE by 42%,comparing with the traditional power demand prediction method.In addition,the second proposed approach can provide more information for building energy management,including the predicted baseload,peak load,and occupancy rate,without requiring additional building parameters.
