It is widely acknowledged that traffic information has the potential of alleviating congestion in road networks and hence its negative environmental and societal side effects. The idea behind this notion is that when individuals are better informed, they make better decisions (for example in terms of route and departure time), which potentially yield better traffic conditions (less congestion) for every one. However, for these beneficial collective effects to occur reliable and accurate traffic information is a prerequisite. In his PhD research Hans van Lint developed a reliable framework for online travel time prediction for freeways. This framework can be applied for generating traffic information messages on so-called Dynamic Route Information Panels (DRIPs) on Freeways. Central in this framework is a so-called state-space neural network model, which learns to predict travel times directly from data obtained from real time traffic data collection systems. The framework is capable of dealing with corrupted and missing data and produces also a measure for the reliability of each prediction. This enables traffic managers to monitor the reliability of this system without actually measuring travel times.