Biography

Martha Asare, a PhD student in Computer Science at the University of Texas Rio Grande Valley, possesses a robust background in statistics and data science. Her research endeavors encompass machine learning, computer vision, and intelligent systems, with a specific focus on additive manufacturing and extensive data analytics. She develops machine vision systems for real-time quality control in 3D metal printing, employing deep learning methodologies such as YOLO, NLP and CNNs to identify anomalies and enhance operational efficiency. During the summer of 2024, Martha served as a Research Data Scientist at Lawrence Berkeley National Laboratory. In this capacity, she constructed Python-based pipelines to analyze over 6,000 NERSC support tickets and usage logs, resulting in a 25% reduction in resolution time and a 15% increase in team productivity. Her contributions have been recognized through publications in the FAIM 2025 Springer LNME series on AI-enhanced defect detection in manufacturing and the accepted lecture at IEEE Sensors 2025 on digital twin-driven multi-camera edge computing sensing for additive manufacturing. Martha is dedicated to harnessing the potential of AI for sustainable innovation and fostering equitable participation in STEM fields.

Academic Status

PhD Student - 2nd

Research Area/Department

Applied Mathematics; Computer Science; Data Science; Engineering; Machine Learning/AI

Major/Specialty

- Computer Science (PhD) – Specialization in Computer Vision, Artificial Intelligence, and Additive Manufacturing. - Applied Statistics and Data Science (Master’s) – Specialization in Machine Learning, Big Data Analytics, and Predictive Modeling. - Statistics (Bachelor’s) – Focus on Biostatistics, Probability Theory, and Statistical Modeling.

Degrees Earned or in Progress

• PhD in Computer Science (Interdisciplinary Applications) – University of Texas Rio Grande Valley, Aug 2024 – Present (in progress) • MS in Applied Statistics and Data Science – University of Texas Rio Grande Valley, Aug 2022 – Aug 2024 • BS in Statistics – Kwame Nkrumah University of Science and Technology, Ghana, Sep 2013 – Jun 2017

Academic Preparation

I have completed a comprehensive range of advanced coursework in both computer science and statistics, which directly equip me for research internships. These include: • Computer Science/Engineering: Machine Learning, Image Processing, Smart Sensors, Swarm Robotics, Computer Vision, Big Data Analytics. • Statistics/Data Science: Probability Theory, Biostatistics, Logistic Regression, Structural Equation Modeling, Advanced Data Analysis. Combined with my national lab experience at Lawrence Berkeley Lab and ongoing PhD research in additive manufacturing anomaly detection, these courses provide me with strong computational, analytical, and applied research skills.

Research/Publications

• FAIM 2025 (Springer LNME) – “AI-Enhanced Real-Time Additive Manufacturing Defect Detection” (Asare, Garcia, & Yang). Published. • FAIM 2025 (Springer LNME) – “AI-Enhanced Real-Time AM Defect Detection Method Using Large Language Models (LLM)” (Garcia, Asare, & Yang). Published. • IEEE Sensors 2025 (Vancouver) – “Digital Twin Driven Multi-Camera Edge Computing Sensing System for AM.” Accepted Lecture. • Asare, M. (2024). Evaluating Feature Selection Methods in Machine Learning With Class Imbalance (Master's thesis, The University of Texas Rio Grande Valley). • Fernandez, L. M., Villalobos, C., Ortiz, M. L., & Asare, M. Preliminary Results of Specificationis Grading in Calculus 1. In 2024 Fall Central Sectional Meeting. AMS. • Villalobos, C., Fernandez, L. M., Ortiz, M. L., & Asare, M. Student Attitudes in Specifications Grading Calculus 1 classes. In 2024 Joint Mathematics Meetings (JMM 2024). AMS. • Bilingual Research Journal – “Intersecting Beliefs on Mathematics and Emergent Bilingual Mathematics Education” (Ortiz Galarza, Nguyen, & Asare). Under review. • Research conducted at Lawrence Berkeley National Laboratory (NERSC data pipeline, 2024). • Ongoing PhD research at the IMVSS Laboratory, UTRGV (real-time defect detection in 3D printing).

Research/Academic Interests

My research interests lie at the intersection of artificial intelligence, computer vision, and intelligent sensing systems. I focus on developing AI-driven methods for real-time quality control in additive manufacturing, including anomaly detection, digital twins, and trustworthy AI approaches that improve efficiency and sustainability in production systems. I am also interested in advancing applied machine learning for science and engineering, including large-scale data analytics, predictive modeling, and AI-enabled automation. My work bridges theory and practice, combining deep learning (NLP, YOLO, CNNs), stereo vision, and 3D reconstruction to tackle real-world problems in manufacturing and beyond. More broadly, I am motivated by how AI for science and society can be applied to address challenges in sustainability, healthcare, and equitable education. I aim to continue building research that contributes not only to technical innovation but also to societal impact.

Computational and Data Science Areas

Applied Computer Science; Artificial Intelligence and Intelligent Systems; Computer Science; Educational Sciences; Electrical, Electronic, and Information Engineering; Informatics, Analytics and Information Science; Materials Engineering; Mechanical Engineering; Performance Evaluation and Benchmarking; Statistics and Probability; Visualization and Human-Computer Systems

Motivation

I want to participate in this program because it aligns closely with both my academic journey and long-term goals. As someone who was part of SRP 2023, I experienced firsthand how the program creates meaningful collaborations and mentorship opportunities. Returning now as a PhD student, I am eager to deepen that experience and contribute more strongly to the community. My current research focuses on using artificial intelligence and computer vision for real-time quality control in additive manufacturing. Through this work, I have developed deep learning pipelines and digital twin systems using machine learning models like YOLO, CNNs, with publications in FAIM 2025 and an accepted lecture at IEEE Sensors 2025. I also gained experience at Lawrence Berkeley Lab, where I built large-scale data pipelines using NLP that improved efficiency at NERSC by 15%. I believe these skills prepare me to contribute to NAIRR-supported projects that advance AI for science and engineering. Through SRP–NAIRR, I hope to expand my technical expertise by working with projects that use NAIRR resources to address real-world challenges. Just as important, I want to be part of a community where I can both learn from mentors and peers and also share my own perspective as someone committed to applying AI for sustainability, trustworthy automation, and equitable access to technology. I see this fellowship as a pathway not only to strengthen my research but also to prepare me to mentor others and to build long-term collaborations that extend beyond my PhD.

Lightning Talk Title

AI-Driven Computer Vision for Smart Manufacturing Systems

Keywords (Maximum 20 words)

Artificial Intelligence; Machine Learning; Computer Vision; Additive Manufacturing; Deep Learning; Defect Detection; 3D Reconstruction; Robotics; Smart Manufacturing; Digital Twin