Learn More
Few studies have properly compared predictive performance of different models using the same medical data set. We developed and compared 3 models (logistic regression, neural networks, and rough sets) in the in prediction of ambulation at hospital discharge following spinal cord injury. We used the multi-center Spinal Cord Injury Model System database. All(More)
An interesting aspect of techniques for data mining and knowledge discovery is their potential for generating hypotheses by discovering underlying relationships buried in the data. However, the set of possible hypotheses is often very large and the extracted models may become prohibitively complex. It is therefore typically desirable to only consider the(More)
Embryonic cleavage depends on the distribution in the cytosol of molecular signals that influence mitotic spindle positioning. By implementing the New Kind of Science (NKS) theory in which a simple rule can evolve with a complex overall behavior, here we propose a new theoretical approach that is capable of modeling the mechanisms of early embryonic(More)
The totalistic two-dimensional cellular automaton code 52 is capable of a wide variety of behavior. In this paper we look at its generic behavior, its complex behavior on simple backgrounds, its versatility in performing finite computations, and its block emulations of elementary cellular au-tomata (ECA). In all, we found 65 ECA which are emulated by code(More)
  • 1