Xiaohe(Joyce) Yin
Data Scientist, Software Developer,
and Urban Technologist
New York, NY
Find me at LinkedIn and GitHub
Data-driven solutions make life better!
Ongoing Research and Previous Projects
EV Adoption and Infrastructure Location Equity
The transportation sector is the largest source of greenhouse gas (GHG) emissions, accounting for 28% of all GHG emissions in the U.S. The transition from Internal Combustion Engine (ICE) to Electric Vehicle (EV) is highly valued by the federal government, which has implemented diverse policies and incentives. Under these circumstances, this project will provide an insight of how transportation electrification is performing in NYC.
Ongoing...
#GHG #ElectricVehicle #ChargingInfra #EquityConsideration
DocHub: A Full-stack Web App with Django and LlamaIndex
This web application aims to manage the documents and extract the information efficiently by using Large Language Models (LLM). By uploading your resource/document, you are able to ask anything on the chatbox that combines uploaded data. In the meantime, LLM enables us to summarize each document to grab its main idea.
#FullStackWeb #LLamaIndex #Django
More DetailsNYC Subway Station Noise Analysis
NYC Subway is NOISY! But where does the noise come from? This project aims to gain a basic understanding by analyzing multiple subway videos. We use an innovative movement detection to extract informative clips and apply computer vision techniques such as DETIC to track noise sources. Combining audio analysis, we delivered a dashboard to visualize analysis spatially and temporally.
#ComputerVision #DETIC #GeoAnalytics #JavaScript
More Details
NYU Restaurant Inspection Grading Prediction
We noticed that every restaurant in New York City post their inspection grade at the entrance (it could be A, B, C, or pending). Diving into NYC Open Data, we utilized the inspection data as a main dataset and connect it with other socio-economic factors (i.e. Food Drop-off Location, Rodent Inspect). With 50,000+ records in the dataset, we managed to run baseline machine Learning to predict grades in the following year.
#MachineLearning #ComplexDatasets #GeoAnalytics #PolicyAnalysis
More DetailsChinaVis2021: Air Pollutions Analysis
I know AIR QUALITY is a critial problem. How can we live with a good air quality in China? First thing we need to know is what kind of air pollutants matter most? So check out this air pollutants analysis dashboard :)
#ClimateTech #DataProcessing #Visualization #JavaScript
More Details