MS Thesis

Thesis Manuscript
Abstract
Image-based deep learning (DL) models are employed to enable the detection of critical heat flux (CHF) based on pool boiling experimental images. Most machine learning approaches for pool boiling to date focus on a single dataset under a certain heater surface, working fluid, and operating conditions. For new datasets collected under different conditions, a significant effort in re-training the model or developing a new model is required under the assumption that the new dataset has a sufficient amount of labeled data.
This research explores supervised, semi-supervised, and unsupervised machine learning strategies that are formulated to adapt to different scenarios. The project consists mainly of two phases:
Phase I: studies the scenario of when the new dataset has limited labeled data available. This scenario was addressed by employing Convolutional Neural Networks (CNNs) and Transfer learning (TL) to tackle such situations.
Phase II: studies the scenario of when the new dataset has no labeled data available at all. In such cases, this research presents a generalized framework where any Unsupervised Image-to-Image (UI2I) translation model could be deployed to generalize a pre-existing classification model by adapting the new dataset to look like it came from a domain similar to the one that the classification model is familiar with.
The approaches presented are the first of their kind to utilize TL and UI2I to solve the boiling heat transfer problem within the heat transfer community and are a step forward towards obtaining a one-for-all general model.









Graduation Project:
In this project, we used a structured Data Envelopment Analysis (DEA) approach in the selection and ranking of the best Six Sigma project among several different projects, the approach starts with the application of simple DEA and then discusses the shortcomings of this DEA formulation. Hence, points out the need for the Aggressive and Benevolent formulations that tend to constrain the linear programming problem to obtain more reliable results; Aggressive and Benevolent formulations are then compared to the Super Efficiency model and discusses the differences of the results generated by these models.









Purchasing System for SATS Lounge:
I have developed a purchasing system consisting of an Android App that is used to record every transaction happening in the SATS Lounge. The system was also used to store the amounts requested by every member and the total amounts they consumed of each product. The system used a number of google sheets for data storage and the information was retrieved by the google sheets query (very similar to SQL).
Proctoring App Project (Staff's version):
I have developed a mobile application dedicated for proctoring to assist the lecturers and TAs when looking up information about their exams, such as proctors assigned, exam rooms, date and time , .. ,etc. The app is a continue of the proctoring system in our school that I have implemented using google sheets and google forms. The app basically feeds from a google sheet that I use as a data base to retrieve the information required.
Proctoring App Project (student's version):
Similar to the Staff's version, but dedicated for students.
Automated Measurements Report (Excel Sheet Based using VBA):
I have Automated one of the reports used in the Engineering Workshop course using Excel Visual Basic for Applications (VBA) to ease the grading procedure by making it automated and accurate. The application allow students to submit their readings into a form, then grades them according to an answer embedded in excel. The application takes a snapshot of each student submission to save it as evidence and saves their grades as well.