In light of growing urban traffic,car parking becomes increasingly critical for cities to manage.As a result,the prediction of parking occupancy has sparked significant research interest in recent years.While many ext...In light of growing urban traffic,car parking becomes increasingly critical for cities to manage.As a result,the prediction of parking occupancy has sparked significant research interest in recent years.While many external data sources have been considered in the prediction models,the underlying geographic context has mostly been ignored.Thus,in order to study the contribution of geospatial information to parking occupancy prediction models,road network centrality,land use,and Point of Interest(POI)data were incorporated in Random Forest(RF)and Artificial Neural Network(ANN,specifically Feedforward Neural Network FFNN)prediction models in this work.Model performances were compared to a baseline,which only considers historical and temporal input data.Moreover,the influence of the amount of training data,the prediction horizon,and the spatial variation of the prediction were explored.The results show that the inclusion of geospatial information led to a performance improvement of up to 25%compared to the baseline.Besides,as the prediction horizon expanded,predictions became less reliable,while the relevance of geospatial data increased.In general,land use and POI data proved to be more beneficial than road network centrality.The amount of training data did not have a significant influence on the performance of the RF model.The ANN model,conversely,achieved optimal results on a training input of 5 days.Likely attributable to varying occupancy patterns,prediction performance disparities could be identified for different parking districts and street segments.Generally,the RF model outperformed the ANN model on all predictions.展开更多
The loading and unloading operations carried out by transport and logistics operators have a strong impact on city mobility if they are not performed correctly.If loading/unloading bays,i.e.,delivery bays(DB),are not ...The loading and unloading operations carried out by transport and logistics operators have a strong impact on city mobility if they are not performed correctly.If loading/unloading bays,i.e.,delivery bays(DB),are not available for freight vehicle operations,operators may opt to double park or park on the sidewalk where there is no strong enforcement of these laws,with significant impact on congestion.This paper proposes a methodology for verifying and designing the number of delivery bays needed for freight vehicles for not interfere with cars or pedestrians.The methodology consists of two stages:in the first stage,an initial estimation is made using queueing theory.Subsequently,in the second stage,using such tentative scenario,in order to take into account the system stochasticity involving different entities,a discrete event simulation is performed to more realistically verify and upgrade(if necessary)the number of delivery bays to obtain the expected outcomes.The methodology was applied in the inner area of Santander(Spain).The study area was subdivided into 29 zones where the methodology was applied individually.The results indicated that none of these zones currently have an optimal number of delivery bays to satisfy demand.In some zones,there is an excess of delivery bays,although in most of them,there is a deficit which can cause significant impacts on traffic.The method proposed can be an effective tool to be used by city planners for improving freight operations in urban areas limiting the negative impacts produced in terms of internal and external costs.展开更多
文摘In light of growing urban traffic,car parking becomes increasingly critical for cities to manage.As a result,the prediction of parking occupancy has sparked significant research interest in recent years.While many external data sources have been considered in the prediction models,the underlying geographic context has mostly been ignored.Thus,in order to study the contribution of geospatial information to parking occupancy prediction models,road network centrality,land use,and Point of Interest(POI)data were incorporated in Random Forest(RF)and Artificial Neural Network(ANN,specifically Feedforward Neural Network FFNN)prediction models in this work.Model performances were compared to a baseline,which only considers historical and temporal input data.Moreover,the influence of the amount of training data,the prediction horizon,and the spatial variation of the prediction were explored.The results show that the inclusion of geospatial information led to a performance improvement of up to 25%compared to the baseline.Besides,as the prediction horizon expanded,predictions became less reliable,while the relevance of geospatial data increased.In general,land use and POI data proved to be more beneficial than road network centrality.The amount of training data did not have a significant influence on the performance of the RF model.The ANN model,conversely,achieved optimal results on a training input of 5 days.Likely attributable to varying occupancy patterns,prediction performance disparities could be identified for different parking districts and street segments.Generally,the RF model outperformed the ANN model on all predictions.
文摘The loading and unloading operations carried out by transport and logistics operators have a strong impact on city mobility if they are not performed correctly.If loading/unloading bays,i.e.,delivery bays(DB),are not available for freight vehicle operations,operators may opt to double park or park on the sidewalk where there is no strong enforcement of these laws,with significant impact on congestion.This paper proposes a methodology for verifying and designing the number of delivery bays needed for freight vehicles for not interfere with cars or pedestrians.The methodology consists of two stages:in the first stage,an initial estimation is made using queueing theory.Subsequently,in the second stage,using such tentative scenario,in order to take into account the system stochasticity involving different entities,a discrete event simulation is performed to more realistically verify and upgrade(if necessary)the number of delivery bays to obtain the expected outcomes.The methodology was applied in the inner area of Santander(Spain).The study area was subdivided into 29 zones where the methodology was applied individually.The results indicated that none of these zones currently have an optimal number of delivery bays to satisfy demand.In some zones,there is an excess of delivery bays,although in most of them,there is a deficit which can cause significant impacts on traffic.The method proposed can be an effective tool to be used by city planners for improving freight operations in urban areas limiting the negative impacts produced in terms of internal and external costs.
