Tuesday, July 13, 2004
Inference
It enables to gain new information from several datasets. Is the process deterministic or stochastic? Inference is used in data mining, too. It has: inference reasoning, statistical / Bayesian inference, data visualization, process modeling, inference engines/ software, knowledge discovery in very large databases.
Over the years, inference has evolved from logical to statistical, graphical and very large data mining, with the help of distributed computing environments for structured/ nonstructured data processing.
The inference life cycle: analysis, reasoning, risk assessment, statistical/ Bayesian inference, data visualization, AI/ DSS, process modeling, inference engines/ software, knowledge discovery in very large databases. PhD dissertation and Nuclear Engineering MS thesis were on the stochastic processes optimization which required strong time-variant random process modeling/ simulation, with emphasis on Monte Carlo numerical methods/ distibution functions. Published over 70 technical papers on various aspect of computer-assisted inference modeling, visualization, decision support systems (DSS). Worked on full life cycle, national level technical projects, using data warehousing/ mart/ mining, inference-based decalssification, world nuclear/ chem-bio target dominant knowledge-base systems, graphical tools for mapping, security aspect of the content-sensitive enterprise IT architecture.
It enables to gain new information from several datasets. Is the process deterministic or stochastic? Inference is used in data mining, too. It has: inference reasoning, statistical / Bayesian inference, data visualization, process modeling, inference engines/ software, knowledge discovery in very large databases.
Over the years, inference has evolved from logical to statistical, graphical and very large data mining, with the help of distributed computing environments for structured/ nonstructured data processing.
The inference life cycle: analysis, reasoning, risk assessment, statistical/ Bayesian inference, data visualization, AI/ DSS, process modeling, inference engines/ software, knowledge discovery in very large databases. PhD dissertation and Nuclear Engineering MS thesis were on the stochastic processes optimization which required strong time-variant random process modeling/ simulation, with emphasis on Monte Carlo numerical methods/ distibution functions. Published over 70 technical papers on various aspect of computer-assisted inference modeling, visualization, decision support systems (DSS). Worked on full life cycle, national level technical projects, using data warehousing/ mart/ mining, inference-based decalssification, world nuclear/ chem-bio target dominant knowledge-base systems, graphical tools for mapping, security aspect of the content-sensitive enterprise IT architecture.
