We study the problem of predicting the viewer’s behavior in an Interactive TV application, using soccer matches as an example. Based on the information extracted from the video frames and the user’s Region of Interest (RoI) trajectory history, we make the prediction of the viewer’s RoI ahead of time. We start with a generic probabilistic model, make simplifications and develop a tractable syste...

Sequences of action potentials are the basis for our perception of the world. E.g., all information about the visual world is transmitted by action potentials of retinal ganglion cells from the eye to the brain. However, responses to identical stimulation can be very variable. Which features of the spike sequences of neuronal populations are most important to encode sensory information is still...

Event trees are a popular technique for modelling accidents in system safety analyses. Bayesian networks are a probabilistic modelling technique representing influences between uncertain variables. Although popular in expert systems, Bayesian networks are not used widely for safety. Using a train derailment case study, we show how an event tree can be viewed as a Bayesian network, making it cle...

Sustained implementation of health education interventions is important to optimize the impact of initial investments in program development and training. From 2002-2012, the Health Care Institute (HCI) at UCLA trained 192 Head Start grantees, serving low-income preschool children and families in the U.S., on how to implement lowliteracy health education programs, using a train-the-trainer (TTT...

Train control system is to control the velocity and the distance between trains in the railway and to protect the safe and high efficiency of train running. An ideal train control system testing and simulation platform should simulate the real railway operating environment and the train running. There are different requirements for the train visualization in the train control system testing and...

One of the most popular data mining areas, which estimate future trends of data, is classification. This research is dedicated to predict Iranian passenger train delay with high accuracy over Iranian railway network. A hybrid method based on neuro-fuzzy inference system and Two-step clustering is used for this purpose. The results indicate that the hybrid method is superior over the other commo...

Quantifying similarity and dissimilarity of spike trains is an important requisite for understanding neural codes. Spike metrics constitute a class of approaches to this problem. In contrast to most signal-processing methods, spike metrics operate on time series of all-or-none events, and are, thus, particularly appropriate for extracellularly recorded neural signals. The spike metric approach ...

At the occasion of ATMOS 2012, Tim Nonner and Alexander Souza defined a new train shunting problem that can roughly be described as follows. We are given a train visiting stations in a given order and cars located at some source stations. Each car has a target station. During the trip of the train, the cars are added to the train at their source stations and removed from it at their target stat...

AN Internet connection on the train offers a lot of perspectives for the passengers [1]. Within the train they can now enjoy leisure activities like infotainment, on line gaming, web surfing, Video on Demand etc. Business travelers have a virtual office during their journey with applications such as e-mail and video conferencing. But apart from gaining additional revenues due to both Internet a...