Research

Research of Interest:

My research of interest is Cognitive Computing for Semantic Computing. Meaning, investigating and developing the theoretical and computational cognitive models involved in cognitive-based processes of semantic learning, representation and growth from sources of natural language . This direction of research is mainly based on the fundamental hypothesis of as the semantic tasks performed by/for the semantic memory are not disjoint from our cognition. In fact, strong claims have been made about cognitive semantics, such as: “to study semantics of natural language is to study cognitive psychology (Jackendoff, 1983).”​ 

This way to mimic the human cognition for semantic learning , representation  and growth and reduce it into process-based algorithmic models for building more intelligent computer agents, which to be capable of understanding then  consuming the sources of human natural language, such as text corpora and texts from social media platforms. 

I am also interested in modeling the natural and bio-inspired phenomena (computational intelligence) for applications of information security / network intrusion detection. That is to build realtime computer security agents simulating our natural human immune system.

Finally, and most recently I am having a shifting toward Computational Neurosciences (CNS) and Cognitive Robotics (CR), where I can integrate my cognitive computing background into what is being developed in the fields of CNS and CR. Therefore, I am highly looking for research collaborations from the CNS and CR societies, to help them adding more cognitive capabilities to their models of CNS and CR.


Publications:

  • CLEVis: A Semantic Driven Visual Analytics System for Community Level Events, IEEE Journal of Computer Graphics and Applications, 2020. [PDF][PPT][Poster]​
  • Computational Cognitive-Semantic Based Semantic Learning, Representation and Growth: A Perspective, 18th IEEE International Conference on COGNITIVE INFORMATICS & COGNITIVE COMPUTING, ICCI*CC 2019. [PDF][PPT][Poster]​
  • Graph-Based Semantic Learning, Representation and Growth from Text: A Systematic Review, 13th IEEE International Conference on Semantic Computing, ICSC-2019. [PDF][PPT][Poster]​
  • Semantic-Based Text Document Clustering Using Cognitive Semantic Learning and Graph Theory, ICSC-2018. [PDF][PPT][Poster]​
  • Using Text Comprehension Model for Learning Concepts, Context, and Topic of Web Content, ICSC-2017.  [PDF][PPT][Poster]​
  • Design and Implementation of Artificial Immune System for Detecting Flooding Attacks, International Conference on High Performance Computing & SimulationHPCS-2011. [PDF][PPT][Poster]​

Clustered corpus graph for the classic300 text-corpus, 300 documents and 5,129 terms. Every node is a text doc in corpus.
300 documents and 5,129 terms | 300 nodes, 12,635 edges
Avrg-node-degree of 84 and density of 0.282
3 topic-clusters: (1) Cranfield: from aeronautical system papers, in blue, (2) Medline: from medical journals, in red, (3) Cisi: from information retrieval papers, in yellow. 
 (Ismael Ali, ICSC-2018)


Semantic-Based Text Document Clustering Using Cognitive Semantic Learning and Graph Theory, ICSC-2018

Using Text Comprehension Model for Learning Concepts, Context, and Topic of Web Content, ICSC-2017

😉