Research software · applied ML · technical notes

Research software and applied machine-learning studies.

A compact record of projects, notebooks, screenshots, and notes. The emphasis is on what was built, what problem it addressed, and what evidence or artifact remains available to inspect.

Work Notes Records Resume

Work

Projects

Two primary artifacts anchor the site: a research workspace and a notebook-based medical imaging study.

Research Platform · Ongoing

Refract

A research workspace for reading papers, saving evidence, comparing sources, and running analysis without losing the working context that connects those steps.

Problem

Research work often breaks across PDFs, notes, comparison tables, datasets, and analysis notebooks. Once those pieces separate, conclusions become difficult to trace back to source material.

Approach

Refract treats the session as the main object. Papers, saved passages, comparison outputs, uploaded files, and analysis runs all belong to the same working frame.

Output

A Next.js and FastAPI application with reader, compare, and statistics surfaces backed by persistent project/session state.

I designed and built the session model, reader flow, evidence storage, comparison surfaces, and analysis structure.

Next.jsFastAPIPostgreSQLPythonChromaDBLLM systems

Open Project Repository Research workspace article

Medical imaging study

Notebook-driven experimentation, staged image labels, and model comparison.

Medical Imaging Research · Notebook-based study

Alzheimer’s Disease MRI Research

A Google Colab MRI classification study that keeps image inspection, preprocessing, staged labels, CNN training, and comparison visible in the notebook record.

Problem

Medical imaging experiments can become difficult to judge when the final score is separated from the images, preprocessing choices, label structure, and evaluation path.

Approach

The notebook keeps the study sequence visible: MRI inspection, image resizing, augmentation, four-class labeling, CNN training, and ensemble-oriented comparison.

Output

A repository-backed Colab notebook and supporting image outputs that show the experiment as a reproducible sequence rather than a polished clinical claim.

I built the data preparation, augmentation, training, and evaluation flow and preserved the notebook as the visible record of the experiment.

TensorFlowKerasGoogle ColabMRI imaging

Open project

Writing

Project notes and essays that explain decisions, constraints, and evaluation concerns in plain language.

Research systems

Designing a session-centered research workspace

Research software becomes more reliable when the context of reading, evidence, and analysis persists across the life of the work. Refract treats the session as that continuity layer.

Read Article

What reliable should mean for LLMs in life sciences

In scientific and regulated settings, reliability is less about polished prose and more about whether claims remain traceable to evidence, scope, and method.

Essay

Notebook-first medical ML is still serious research

A notebook can be the most faithful record of a machine-learning study when it preserves data inspection, preprocessing, training, and evaluation in the same visible sequence.

Research note

Notes from a battery RUL project

In battery remaining-useful-life work, a strong score only matters if the feature story, time structure, and evaluation protocol remain believable under scrutiny.

Project writeup

Working principles

Common thread

The projects differ in format, but they share a concern with traceability. Refract asks how research software can keep reading, evidence, comparison, and analysis from breaking into disconnected tools. The Alzheimer MRI study asks how a notebook can preserve the experimental sequence of a medical imaging workflow. The writing records the design and evaluation questions behind those artifacts.

Suggested paths through the site

RefractStart here for the main software system and its session-centered workflow.Alzheimer's disease MRI researchUse this for the notebook-based machine-learning study and supporting image outputs.ResumeOpen the conventional PDF summary if you need a compact professional overview.