AI-Based Automated Methodologies for Supply Chains: High Precision Tabular Detection and Semantic Modeling of Electronic Components from Datasheets

This project will develop a hybrid framework by integrating AI and machine learning methods with tabular information extraction and semantic modeling to improve the state-of-the-art precision and recall in tabular detection while maximizing the value of extracted information for industrial applications. Following a properly designed pre-processing stage to improve the outcomes of AI techniques, the research problem is three-fold: The first phase involves in improving the success of tabular detection as there is significant room for improvement in the recognition of e-Component tables under the billion+ components data. Next, semantic search will be applied on tabular information to extract specific data for electronic components in the second phase. In the first two phases, classification and self-organizing maps will be used as the AI techniques to meet the desired level of success. The design of an end-to-end holistic system will be accomplished in the third phase of the proposed project.

Intern: 
Inam Ul Haq;Johan Fernandes;Ahmed Omara;Ji Chu Jiang
Faculty Supervisor: 
Burak Kantarci
Province: 
Ontario
Partner: 
Partner University: 
Program: