OBJECTIVES (1) Estimate age, period and cohort effects for motorcyclist traffic casualties 1979-2008 in New Zealand and (2) forecast the incidence of New Zealand motorcycle traffic casualties for the period 2019-2023 assuming future age, cohort and period effects, and compare these with an estimate based on simple linear extrapolation. METHODS Age-period-cohort (APC) modelling was used to est...

Amajor problem in forecasting is estimating the time of some future event. Traditionally, forecasts are designed to minimize an error cost function that is evaluated once, possibly when the event occurs and forecast accuracy can be determined. However, in many applications forecast error costs accumulate over time, and the forecasts themselves may be updated with information that is collected a...

Future air traffic management (ATM) decision support systems (DSS) rely upon trajectory forecasting to adequately deliver benefits. These forecasts are subject to errors from a variety of sources. As the number and sophistication of ATM DSS capabilities grow, the interoperability between DSS will become more sensitive to the magnitude and variation in trajectory forecasting errors across DSS. T...

Traffic forecasting problem remains a challenging task in the intelligent transportation system due to its spatio-temporal complexity. Although temporal dependency has been well studied and discussed, spatial is relatively less explored large variations, especially urban environment. In this study, novel graph convolutional network model, Multi-Weight Graph Convolutional (MW-TGC) network, propo...

Urban traffic analysis is crucial for traffic forecasting systems, urban planning and, more recently, various mobile and network applications. In this paper, we analyse urban traffic with network and statistical methods. Our analysis is based on one big bus dataset containing 45 million bus arrival samples in Helsinki. We mainly address following questions: 1. How can we identify the areas that...

internet traffic has grown exponentially over last few years due to provision of multiple class services through internet backbone. with the explosive use of internet, contemporary internet routers are susceptible to overloads and their services deteriorate drastically and often cause denial of services. in this paper, an analysis is made how forecasting technique, routing algorithm and genetic...

An application of time series prediction, to traffic forecasting in ATM networks, using neural nets is described. One key issue, the number of data points needed to be included in the input representation to the net is discussed from a theoretical point of view, and the results are applied in the model under discussion. Experimental results are discussed and analysed.

The paper looks at the current state of development in transportation modelling and tries to identify future developments which are either likely or desirable. It discusses developments in the fields of data modelling, surveying techniques for supply and demand data, traffic assignment and travel forecasting models, microscopic modelling, and user interface.