Electrical and Computer Engineering ETDs

Publication Date

Summer 8-1-2022

Abstract

The study aims in applying combinatorial structures motivated from the basic CNN in various applications. Convolutional neural networks (CNNs) have grown to be very popular in the field of deep learning. The ability of such networks to learn both Spatial and temporal characteristics in the data have helped in deploying them in various fields. Through this research we explore different kinds of CNN-derived architectures and how these structures can be trained and setup in combinatorial environment to solve problems in deep learning applications. First, we introduce the basic idea of a deep learning meta-structures which is used in the application of facial expression recognition. Next, we investigate CNN meta-structures in detail in the application of Super-resolution. Further, the analysis of different combinatorial models containing CNN meta-structures and machine learning approaches are studied in detail for two different applications. The first application is a medical imaging application for detecting Malarial retinopathy with high specificity and second is for developing an adaptive protection scheme to detect faults and topology change in distribution systems. Overall, the proposed work investigates the analysis of meta-structures derived from basic CNNs arranged in different combinations.

Keywords

Deep learning, Machine learning, Computer vision, Engineering applications, Medical imaging, Convolutional Neural networks

Document Type

Dissertation

Language

English

Degree Name

Electrical Engineering

Level of Degree

Doctoral

Department Name

Electrical and Computer Engineering

First Committee Member (Chair)

Manel Martinez Ramon

Second Committee Member

Ali Bidram

Third Committee Member

Sandra Biedron

Fourth Committee Member

Abdullah Mueen

Download

Share

COinS