Santiago Posso-Murillo
Lexington,KY
Summary
I am a PhD student with 6 years of experience applying deep learning to real-world problems. I specialize in data processing for brain-computer interfaces and computer vision, with hands-on expertise in EEG, fNIRS, and medical imaging. I thrive on tackling complex challenges and quickly mastering new techniques.
Overview
6
6
years of professional experience
Work History
Research Assistant
University Of Kentucky College Of Engineering
01.2021 - Current
PROJECTS
- EEG-based Premovement Decoding with Reinforcement Learning: Application of Deep Q-Learning using CNNs for decoding premovement intention using Freewill EEG data.
- Brain Encoding using LLMs : Prediction of fMRI brain responses to visual stimuli using V-JEPA features and Linear regression.
- Spatial and Temporal analysis of the fNIRS-based decoding models for speech: Achieved up to 98% accuracy; SHAP analysis localized key features to left rostral and right caudal cortical regions.
- Semantic Reconstruction From fNIRS Using Recurrent Neural Networks: Improved brain decoding performance by up to 33% compared to a linear model.
- Nonuniform Sampling-based Breast Cancer Classification: Using high-resolution saliency regions improved performance by up to 21% on low-resolution images and enabled generalization across datasets without pixel-level annotations.
Junior Researcher
Ministry of Science and Technology
07.2019 - 06.2020
Preprocessed mammograms and extracted statistical and morphological features for ML-based breast cancer classification using SVM, logistic regression, and Random Forest.
Education
Ph.D. - Electrical Engineering
12.2026
- Awarded Elise Boyd Graduate Teaching Fellow for the Spring 2025 Semester.
- Relevant Courses: Information theory for Machine Learning, Matrix Theory, Brain Decoding using Deep Learning.
- GPA: 3.8/4.0
- Advisor: Dr. Jihye Bae and Dr. Luis G. Sanchez
Master of Science - Electrical Engineering
12.2023
- Thesis: Nonuniform Sampling-based Breast Cancer Classification
- Relevant Courses: Machine Learning, Medical Image Processing, Bayesian Learning.
- GPA: 3.7/4.0
- Advisor: Dr. Luis G. Sanchez.
Bachelor of Engineering - Engineering Physics
07.2020
- Young Researcher and Innovator Scholarship Recipient, MinCiencias.
- Study Abroad: University of Kentucky, Breast Cancer Classification Project.
- Relevant Courses: Signal Processing, Big Data, Numerical methods.
- GPA: 4.3/5.0
Skills
- PyTorch
- Machine learning
- Computer Vision
- Brain Machine Interfaces
- Signal Processing
- Transfer Learning
LANGUAGES
Spanish - Native or Bilingual
English - Professional
Timeline
Research Assistant - University Of Kentucky College Of Engineering
01.2021 - Current
Junior Researcher - Ministry of Science and Technology
07.2019 - 06.2020
University of Kentucky, College of Engineering - Ph.D., Electrical Engineering
University of Kentucky, College of Engineering - Master of Science, Electrical Engineering
Technological University of Pereira - Bachelor of Engineering, Engineering Physics
PUBLICATIONS
- Posso-Murillo, S., Sanchez-Giraldo, L.G. and Bae, J., 2025, April. Semantic Reconstruction from Fnirs Using Recurrent Neural Networks. In 2025 IEEE 22nd International Symposium on Biomedical Imaging (ISBI) (pp. 1-5). IEEE.
- Posso, Santiago, "Nonuniform Sampling-based Breast Cancer Classification" (2024). Theses and DissertationsElectrical and Computer Engineering. 198. https://uknowledge.uky.edu/ece_etds/198
- Non-uniform Sampling-Based Breast Cancer Classification, Posso Murillo, S., Skean, O., Sanchez Giraldo, L.G., 2024, Machine Learning in Medical Imaging. MLMI 2023. Lecture Notes in Computer Science, vol 14349. Springer, Cham., https://doi.org/10.1007/978-3-031-45676-3_34
- The Representation Jensen-Shannon Divergence, Hoyos-Osorio, Posso-Murillo, S, Et al., 2023, Under review, arXiv preprint arXiv:2305.16446