Tilmann Steinberg

Learn More
We perform discriminative analysis of brain structures using morphometric information. Spherical harmonics technique and point distribution model are used for shape description. Classification is performed using linear discriminants and support vector machines with several feature selection approaches. We consider both inclusion and exclusion of volume(More)
Web access patterns can provide valuable information for website designers in making website-based communication more efficient. To extract interesting or useful web access patterns, we use data mining techniques which analyze historical web access logs. In this paper, we present an efficient approach to mine the most interesting web access associations,(More)
This paper introduces SCENS, a Secure Content Exchange Negotiation System suitable for the exchange of private digital data that reside in distributed digital repositories. SCENS is an open negotiation system with flexibility, security and scalability. SCENS is currently being designed to support data sharing in scientific research, by providing incentives(More)
Traditional digital library systems have difficulties when managing heterogeneous datasets that have limitations on their distribution. Collections of digital libraries have to be accessed individually and through non-uniform interfaces. By introducing a level of abstraction, a Meta-Digital Library or MetaDL, users gain a central access portal that allows(More)
This paper describes data collection interfaces for research collaboration in biomedical applications where there is need for secure sharing of sensitive data. These interfaces are multi-functional because they (a) are structured templates for entering experiments and tools within a given domain ; (b) provide hierarchical entry/presentation of data; (c)(More)
Trust in cross-media applications is essential to successful collaboration. Cross media service delivery encompasses different types of security incidents and assumes a level of trust on the part of the participants of any one transaction. As enterprises and participants of cross media transactions become more susceptible to security risks facilitated by(More)
We describe the development of a system that automates data collection, metadata extraction and analysis of spatio-temporal multi-modal data, combining data management and data analysis to provide an efficient resource for clinicians. Though the system is extensible to many applications, the current focus is on managing Multiple Sclerosis (MS) lesion data,(More)
Correlating event streams or development paths of observed behavior that involves disparate types of data is a common problem in many applications including biomedical and clinical diagnosis systems. We present a new formulation of the following dual problem: (a) given multiple event streams for which we have prior knowledge, specify a feature space with(More)
Quantitative measurements of changes in evolving brain pathology, such as multiple sclerosis lesions and brain tumors, are important for clinicians to perform pertinent diagnoses and to help in patient follow-up. Lesions or tumors can vary over time in size, shape, location and composition because of natural pathological processes or the effect of a drug(More)