Adaptive long-term traffic state estimation with evolving spiking neural networks

Abstract

Road traffic management is a critical aspect for the design and planning of complex urban transport networks for which vehicle flow forecasting is an essential component. Due to the nature of traffic itself, specially in urban contexts, most predictive models reported in literature aim for short-term forecasts, and their performance degrades when the prediction horizon is increased. Long term forecasting strategies are more scarce, and commonly based on the detection and assignment to patterns. These approaches can perform reasonably well unless an unexpected event provokes non predictable changes, or if the allocation to a pattern is inaccurate. This work introduces a method to obtain long-term pattern forecasts and adapt them to real-time circumstances. The method takes advantage of the architecture of evolving Spiking Neural Networks (eSNN) to perform online adaptations without retraining the model. Its performance is assessed over a real scenario with 5 minute data of a 6 month span of traffic in the centre of Madrid (Spain). Significant accuracy gains are obtained when applying the proposed online adaptation mechanism on days with special, non-predictable events that degrade the quality of their long-term traffic forecasts.

From Data to Actions in Intelligent Transportation Systems: A Prescription of Functional Requirements for Model Actionability

“…However, when the goal is to model data interactions within complex systems such as transportation networks, it is often the case that the modeling choice resorts to ensembles of different learner types. For instance, when applying regression models for road traffic forecasting, a first clustering stage is often advisable to unveil typicalities in the historical traffic profiles and to feed them as priors for the subsequent predictive modeling [ 35 , 36 , 37 ]. However, when it comes to model actionability, a key feature of this stage is the generalization of the developed model to unseen data.…”

“…However, the adaptability of ITS models to evolving data is scarcely found in literature, and certainly, in many cases concept drift management is the scope of the work, and not a circumstance that is considered to achieve a greater goal [ 104 , 106 ]. There are though some online approaches to typical ITS problems that consider the effects of drift in data [ 36 , 107 , 108 ], and we consider this kind of initiatives should lead the way for an actionable ITS research. Robust : When an ITS system is deployed in a real-life environment, diverse kinds of setbacks can affect its normal operation, from power failures that preclude its functioning to the interruption of the input data flow.…”

Short‐term traffic flow prediction of road network based on deep learning

“…Compared with parametric methods, non‐parametric methods does not need to make any strict restrictions on the data, but relies on the existing data to determine the relationship between output and input. Examples of non‐parametric methods include support vector regression (SVR) [9, 10], Kalman flter [11], artificial neural network (ANN) [12–19] and k‐nearest neighbour [20, 21]. Note that ANNs have excellent memory and self‐learning ability, they are widely used for traffic flow prediction.…”

Hydrofluoroether Impurities—Chemical Detection Using a Deep Learning Laser Speckle Contrast Evolving Spiking Neural Network

“…This unique feature gives them the greatest benefit [62] . The above-mentioned developments in the use of large amounts of HFE data for online forecasts pose significant challenges linked to its stochastic character and its evolution over long periods [63], [64] . Without explicit specific plant models, ESNN's most obvious advantage is that its neural networks can learn to carry out satisfactory tasks.…”