A bit more about me.

RESEARCH

Robust Graph-Based Android Malware Classification Under Distribution Shift

San José State · Spring 2026

robustness gap 36.2 → 31.0

How far does a graph neural network's accuracy fall when Android malware stops looking like its training data, and does telling the model which features are missing close that gap? Training with simulated missing features cut the robustness gap from 36.2 to 31.0 points. The gating model I proposed did not beat that, most likely because the extra features were synthetic.

RESEARCH

Identifying Subgiant Stars and Binary Systems in Gaia DR3

UC San Diego Stellar Data Lab · advised by Prof. Chris Theissen

288,746 stars → 53,800 subgiant candidates

Queried Gaia DR3 and cleaned the sample to 288,746 stars, then used temperature, surface gravity and absolute magnitude to isolate about 53,800 subgiant candidates. Cross-matched them against the El-Badry wide-binary catalog to find subgiants with white dwarf and low-mass companions. Presented at a research symposium at UC Irvine in October 2025.

PEER-REVIEWED

S&P 500 Forecasting Using Generative AI

UC Merced Undergraduate Research Journal

A GPT-4-based model for short- and long-term S&P 500 forecasting, improved iteratively. GPT-4 was new at the time, and the question was what it could actually do.

RESEARCH

V-QUIP: Vision-Based Quick Impromptu Polling

Google exploreCSR

30% lower latency

Fine-tuned YOLO and optimized TensorFlow Lite models for real-time gesture recognition in classrooms, cutting latency by 30%.

APPLIED RESEARCH

Fall Detection for Rare Events and Changing Devices

Guardian AI

evaluated on unseen people · waist → wrist

Falls are rare, sensors differ from device to device, and a missed fall costs far more than a false alarm. I trained CatBoost on 3-second windows of SisFall accelerometer and gyroscope data, judged it only on people held out of training, and balanced the rare fall class with ADASYN and mixup augmentation. Temporal smoothing cuts false alarms, and a CORAL alignment step carries the model from waist-worn sensors toward wrist devices.

EARLY RESEARCH

Identifying Early-Stage Alzheimer's Disease from MRI

Early research, begun before ChatGPT existed: a TensorFlow/Keras convolutional network that sorts brain MRI scans into stages of Alzheimer's disease, trained with data augmentation, SGD and a learning-rate schedule.