Dr. Faezeh Soleimani
<b>Department: </b>Mathematical Sciences<br><b>Research Area: </b>Machine Learning, Data Mining, Statistics
Department: Mathematical Sciences
Research Focus: Machine Learning, Data Mining, Statistics
Potential Student Project(s):
1. Data analysis and literature review The potential student projects will involve analyzing real-world datasets to uncover insights using statistical tools and techniques. Students would also conduct a comprehensive literature review to identify existing research trends and methodologies in the field. Projects may include areas such as data visualization, predictive modeling, or trend analysis, depending on student interest and available datasets.
2. Predicting the bridge surface temperature using machine learning methods Students will apply machine learning methods to real-world engineering data to predict bridge deck surface temperature. Using meteorological data from a bridge de-icing project in Texas, students will explore various machine learning techniques to build predictive models. Projects will focus on data preprocessing, model training and evaluation, and interpretation of results.
3. Women in Data Science Datathon Challenge (https://www.widsworldwide.org/learn/datathon/) Students will form teams (up to four people) and participate in the Women in Data Science (WiDS) Datathon, which involves solving a data science problem posed by WiDS in a competitive environment. Using real-world datasets, students will apply data wrangling, exploratory data analysis, and machine learning techniques to generate actionable insights or predictions. Students will work with provided datasets, often focused on social, environmental, or healthcare challenges. They will also have the opportunity to collaborate, share findings, and compete with other teams globally. This project offers valuable experience in tackling complex data science challenges while contributing to a global initiative that promotes women in the field of data science.
Attributes/skills/background sought in undergraduate:
Proficiency in R or other programming languages, strong coding skills, and a solid understanding of widely used machine learning algorithms, such as linear regression, support vector machines, random forests, etc.
Mentoring Plan: The student will work 5 hours per week on the project, including at least 1 hour of 1-on-1 interaction with me every other week. During our meetings, I will provide guidance on key concepts and tasks relevant to each project, whether it’s data analysis, machine learning, or collaborative challenges. We will focus on developing critical thinking, technical skills, and problem-solving abilities. I will offer regular feedback, encourage independent work, and help the student navigate challenges. Through consistent support and open communication, I aim to foster the student’s growth in both individual and team-based environments, ensuring they gain practical experience and confidence in their skills.
Contact: 765-285-8814 , RB 435