Structured Regression in Complex Networks by Fusion of Qualitative Knowledge and Big Data

Jun 1, 2015 · 1 min read
projects

Integrating context, domain knowledge, and data-driven modeling of complex phenomena based on observations that are highly structured and interdependent is a very challenging task. In this project we address this problem by using the structured predictive modeling framework based on a probabilistic exponential graphical model instead of relying on traditional statistical approaches that assume independent and identically distributed random variables. Current state-of-the-art predictive modeling techniques usually cannot deal with such large and complex networks; thus we provide knowledge-based compression techniques for complexity reduction. We use multiple kinds of domain knowledge and context to capture additional information that might be missing from the observed data. We also directly constrain the model optimization based on domain constraints and embed other problem-specific qualitative knowledge directly into the framework. The main innovation of this project is extending our structured learning models to explore in detail the hypothesis that a unified approach of integrating big data with sources of high-level knowledge (ontologies, domain-based constraints etc.) is beneficial for predictive modeling of complex phenomena.
Role I have developed predictive models for BIG temporal graphs, which resulted in publications in IEEE Big Data conference.
Temple University. ONR (N00014-15-1-2729). Jun 2015 - May 2016 .

Temple AI Research AIML
Mohamed Ghalwash
Authors
Mohamed Ghalwash
Associate Professor
Mohamed Ghalwash is an Associate Professor of Artificial Intelligence at Ain Shams University / Zewail City of Science, Technology, and Innovation. Ghalwash is interested in developing machine learning and AI models for discovery of interpretable spatio-temporal patterns from complex events and exploiting their utilities in practical high impact real-world applications, focusing on analytics for healthcare, health behavior, decision support, and to support the generation of real world evidence from medical data, wearable devices and instrumented environments. He also has more than ten years of expertise in the software engineering industry, developing software that are currently being deployed, where he engaged in all phases of the project life cycle for the development of large business applications. My long-term goal is to put my footprints in the field of pattern recognition through contribution of original ideas and translating those ideas to end applications and products.