Individual Class Projects
Perspectives of Modeling and Simulation
(Fall 2018)
Professor: Dr. Bockelman, Ph.D.
Project: Modeling the biological effects of ionizing radiation exposure
Project Aim: To summarize the history of radiobiology, current state of knowledge, and future challenges to studying the biological effects of radiation on humans
Reflection: The project made me conduct a literature review on the topic of my research interest and show how modeling and simulation could be used to address the limitations of existing solutions. The project was also my first experience of writing a paper and presenting ideas to others in English
The effects of exposure.pdfThe effects of exposure Poster.pdfAnimal-Vehicle Collisions Report.pdfAdvanced Computer Processing of Statistical Data
(Fall 2019)
Professor: Dr. Mantzaris, Ph.D.
Project: Animal-Vehicle Collisions
Project Aim: To answer a set of questions on animal-vehicle collisions by analyzing an appropriate dataset using SAS
Reflection: It was my first individual project on SAS data analysis which also made me practice technical writing and oral presentation skills
Research Design for Modeling and Simulation
(Fall 2019)
Professor: Dr. Amon, Ph.D.
Project: Reducing road crashes among novice drivers
Project Aim: To examine whether the assessment of a broader range of driving skills during the behind-the-wheel test reduces the crash rate in newly qualified drivers significantly
Reflection: It was my first experience of working on a human subject project. I learned to design an experiment for human participants, think about their recruitment, study materials and procedure. Even though I did not perform the experiment in the real life and only make up the numbers for the class assignment, I believe that the thinking experience could be helpful in studying the effects of radiation exposure one day as well. In addition, the project was a good opportunity to practice turning ideas into writing and presenting them to others
Reducing road crashes.pdfReducing road crashes Presentation.pdfSurvival of glioma patients.pdfMachine Learning
(Spring 2020)
Professor: Dr. Fu, Ph.D.
Project: Predicting survival in glioma patients
Project Aim: To develop a machine learning system allowing to predict the survival of glioma patients following diagnosis using clinical data and magnetic resonance imaging radiomic features
Reflection: The project provided me with a hands-on experience on the development of a machine learning system using Python. I learned about different machine learning algorithms and synthetic data generation as well as practiced writing a report and presenting the results to others
Data Visualization Midterm Project.pdfData Visualization
(Summer 2020)
Professor: Dr. Wiegand, Ph.D.
Project: Creating effective data visualizations
Project Aim: To improve the visualizations of CBTRUS Statistical Report on brain tumors published in Neuro-Oncology (2018)
Reflection: I learned to identify drawbacks in visualizations made by others and create my own alternative / improved versions using R
Project: Storytelling with data
Project Aim: To tell about cancer burden in the United States using data visualizations
Reflection: I learned to visualize data in a way that would support my story objective while preserving the accuracy of the information and delivering it in a clear way
Data Visualization Final Project.pdfThe class inspired me to learn more about data visualization and data storytelling. Thus, I started to read the books by Cole Nussbaumer Knaflic, Steve Wexler, Jeffrey Shaffer and Andy Cotgreave. One day, I hope to apply the acquired knowledge to the creation of powerful visualizations of radiation effects on humans.
Survival in oropharyngeal cancer patients.pdfData Mining
(Spring 2021)
Professor: Dr. Hill, Ph.D.
Project: Predicting survival in oropharyngeal cancer patients
Project Aim: To identify variables most responsible for oropharyngeal cancer patient survival and develop an effective survival predictive model
Reflection: Using R, I learned to explore and prepare a dataset for the analysis, perform variable selection, build various predictive models, and select the most efficient one. I also got a chance to practice interpreting the Logistic Regression model coefficient estimates using the knowledge obtained in Logistic Regression class previously.