About Projects Research Writing Artwork & Music
JOCELYN SHEN

About

Hi! I'm Jocelyn, a sophomore at MIT pursuing a major in Electrical Engineering and Computer Science alongisde a minor in Economics. I'm passionate about technology, behavioral science, and AI policy and ethics. The driving questions behind my research and my projects are: how can we quantify behavioral characteristics such as emotion and creativity, how can we connect people, and how can we provide equitable technology? In the past, I've worked at Facebook as a Software Engineering Intern and Affectiva as a Data Science Intern. I hope to use my knowledge in CS and machine learning to better understand human behavior and contribute to causes related to mental disability, education, and assistive technology, as well as drive research behind policy decisions regarding artificial intelligence. Aside from my work, I'm a Chinese American author and digital artist based in Los Angeles.

Projects

pop'nWeblab 2020 Semifinalist

Online polling game for people around the world to ask questions about certain regions and see how much they know about people around the world

footprntFacebook, 2019

Travel the world virtually through footprnt. Explore user-created travel logs from all around the world

Eye in the SkyHackMIT Winner 2019 (Health Tech)

Mobile application for crowd-sourced natural disaster relief

In-Vehicle Object DetectionAffectiva, Emotion AI Summit 2018

Object detection using Retinanet to help drivers on the road

Research

Evolutionary Convergence in Vascular Branching

Branching in vascular networks and in overall organismic form is one of the most common and ancient features of multicellular plants, fungi and animals. These networks deliver resources and eliminate wastes from early development onward, and even play a vital role in the growth, prognosis, and treatment of tumors and stroke recovery. Because of these basic and applied reasons there is immense interest in identifying key features of vascular branching and their connection to biological function. Here we classify diverse branching networks-mouse lung, human head and torso, angiosperm plants, and gymnosperm plants-by harnessing recent advances in medical imaging, algorithms and software for extracting vascular data, theory for resource-distribution networks, and machine-learning. Specifically, we apply standard machine-learning techniques to a variety of feature spaces. Our results show that our theoretically-informed feature spaces-especially those that determine blood flow rate-combined with Kernel Density Estimation are best at distinguishing networks. Our categorization of networks enhances the mapping between biologic function-such as the dependence of metabolic rate on body mass-to vascular branching traits among organisms and organs. We accomplish this by analyzing how variation in metabolic scaling exponents-around the canonical value of 3/4-arises despite differences in vascular traits. Our results reveal how network categorization and variation in metabolic scaling are both heavily determined by scaling ratios of vessel radii-changes and asymmetries across branching generations-that strongly constrain rates of fluid flow. These linkages will improve understanding of evolutionary convergence across plants and animals while also potentially aiding prognosis and treatment of vascular pathologies and other diseased states.

Source code available herePaper available here

Writing

ON TECH

Machines and MedicineThe Tech (MIT Newspaper)

Artificial intelligence is beginning to cement itself as a useful tool for researchers and engineers alike, and it has the potential to become a new addition to the health professional’s toolkit...
READ MORE

Mental Health and the BrainThe Tech (MIT Newspaper)

Research into the human brain has rapidly grown in the past few decades, and scientists and patients alike are beginning to understand the importance of mental health awareness...
READ MORE

Open Source and Diversity

Open source still has a long way to go before software, and software development alike, becomes more equitable...
READ MORE

NOVELS

Time Zone 1st prize, MIT Boit Manuscript Prize

Juneau is a mess. From the outside, she has it all together: she is smart, warm, and well-liked. But behind closed doors, she lets all the pent-up emotions flood out. Haiden is her best friend. He’s her rock, but he’s also absolutely off-limits. Caught in the midst of turbulence back home and at school, Juneau struggles to uncover her own identity as the voices around her are so disharmonious. The only thing that helps her drown out the noise is Haiden. There’s just one problem: he’s moving to the other side of the world in three months.
But with a heart full of hope, she wonders if perhaps their love can perservere across every time zone.
Coming soon...

ESSAYS & POETRY

Between Barbed Wire: A Visual Analysis of TIME's Welcome to America1st prize, MIT List Vera Prize for Writing on the Visual Arts

A series of rafts float closer to shore, near the Rio Grande on United States territory. The riders’ faces are beaten and their hair mangled and sweaty...
READ MORE

Rotten to the Core

Every parent has a pet peeve. My mother’s is dishonesty. In her house, even the little white lies never went unnoticed...
READ MORE

Sugar Glass Cage1st prize, Helen Creeley Poetry Prize

Walking through streets of Nanjing
Lanterns speckled by the carbon dust and debris...
READ MORE

A Needle in Time1st prize, Helen Creeley Poetry Prize

The needle is a fine strand of hair plucked from an aging scalp.
It is intentional in physiology...
READ MORE

Artwork & Music

DIGITAL ART

Portrait of Pebble
Portrait of Jeffrey
Portrait of Julia
Sample from my comic
Sample from my comic
Sample from my comic

PAINTINGS

Acadia in Acrylic
The Pool
Bokehs in Black

MUSIC