We have developed an algorithm called Q5 for probabilistic classiŽ cation of healthy versus disease whole serum samples using mass spectrometry. The algorithm employs principal components analysis (PCA) followed by linear discriminant analysis (LDA) on whole spectrum surface-enhanced laser desorption/ionization time of  ight (SELDI-TOF) mass spectrometry (MS) data and is demonstrated on four r...

Probabilistic databases store, query and manage large amounts of uncertain information in an efficient way. This paper summarizes my thesis which advances the state-of-the-art in probabilistic databases in three different ways: First, we present a closed and complete data model for temporal probabilistic databases. Queries are posed via temporal deduction rules which induce lineage formulas cap...

The precise probability of a compound event (e.g. e1 _ e2; e1 ^ e2) depends upon the known relationships (e.g. independence, mutual exclusion, ignorance of any relationship, etc.) between the primitive events that constitute the compound event. To date, most research on probabilistic logic programming 20, 19, 22, 23, 24] has assumed that we are ignorant of the relationship between primitive eve...

We present the description logic PN-ALCK NF for reasoning about actions with sensing under qualitative and probabilistic uncertainty, which is an extension of the description logic ALCK NF by actions with nondeterministic and probabilistic effects. We define a formal semantics of PN-ALCK NF in terms of deterministic, nondeterministic, and probabilistic transitions between epistemic states, whic...

Traditionally, probabilistic reasoning has been plagued by its computational intractability in real sitiiations. Complete joint probabilistic specificat.ions are not possible in most situations and very simplistic probabilistic models which are compiitationally inexpensive do not capture the complexities of a real life problem. With the advent of Bayesian networks, we have seen a renewed intere...

The most slow and tedious job in genealogical research is searching civil or church records for information about an individual. But, this is an essential step in research. By searching multiple sources such as census records, wills, deeds, birth and death records we can compile a more complete set of information, and potentially the pedigree of an individual. When records are stored electronic...

Activity networks model the time to project completion based on the times to complete various subtasks, some of which can proceed concurrently and others of which are prerequisite to others. Uncertainty in the times to complete subtasks implies uncertainty in the overall time to complete the project. When the information about the times to complete subtasks is insufficient to fully specify a pr...

We introduce probabilistic many-valued logic programs in which the implication connective is interpreted as material implication. We show that probabilistic many-valued logic programming is computationally more complex than classical logic programming. More precisely, some deduction problems that are P-complete for classical logic programs are shown to be co-NP-complete for probabilistic many-v...

Queries over probabilistic databases are either safe, in which case they can be evaluated entirely in a relational database engine, or unsafe, in which case they need to be evaluated with a general-purpose inference engine at a high cost. We propose a new approach by which every query is evaluated inside the database engine, by using a new method called dissociation. A dissociated query is obta...

Key Violations often occur in real-life datasets, especially in those integrated from different sources. Enforcing constraints strictly on these datasets is not feasible. In this paper we formalize the notion of soft-key constraints on probabilistic databases, which allow for violation of key constraint by penalizing every violating world by a quantity proportional to the violation. To represen...