CODE & AI PORTFOLIO
My projects in computer science: web dev, artificial intelligence, app dev, games!
CrashMap
Web App
An interactive traffic incidents map for new drivers. The night before I drove to school for the first time, I went online to find the safest route to school. There was nowhere to find where accidents were most common, which is shocking. I was unfamiliar with the traffic patterns, and I did not know what to look out for. At the PHS hackathon, my teamdecided to solve this problem. We created a comprehensive accident map, with data straight from the Princeton Police Department. You and your parents can use our interactive map to see hotspots for accidents and potential areas to avoid, and learn the traffic pattern to get a good sense of the roads in the area.
Decoding Emotions from Brain Signals
Artificial Intelligence
Despite playing a large role in human interactions and decisions, emotions are not well understood. Mediums such as music videos, which are mentally stimulating, often elicit a wide range of emotions from receivers. These emotions can appear as electrical signals through electroencephalography (EEG). Being able to classify and quantify an individual’s emotions has useful applications in many fields. This paper uses data from the Dataset of Emotional Analysis Using Physiological Signals (DEAP) dataset, which recorded the EEG signals of participants as they watched videos that were specifically chosen to elicit strong emotions and rated their emotions on quantitative scales. A Long Short-Term Memory (LSTM) recurrent neural network was trained to find correlations between EEG data and self reported emotional scores. The purpose of this study was to create an accurate and efficient method of decoding electrical activity into quantitative emotional values. It was found that valence scores, measures of the degree of happiness, predicted by the neural network matched somewhat closely with the actual valence scores given by the participants. It was concluded that the trained LSTM neural network achieved a reasonable accuracy in predicting valence scores given EEG signals.
Farmeet
Web App / AI
Built during the Databricks Datathon. Farmeet is a Farmers Market smart recommendation app to help shoppers discover fresh food markets in their area based on preferences and support local vendors during the pandemic and beyond. This app would not only help the farmer’s sell their produce more efficiently, but would also help the people have a better access to nutritious produce. During a pandemic, it can be helpful for people to be able to see what farmer’s markets available to them if they are not comfortable in commuting to a particular location which has recently seen a spike in cases. From a technical perspective, developing this app gave me a better understanding of a lot of open source technologies like Flask, React.JS, Leaflet, Heroku etc. I got experience in developing the front and back end of the app and combining them seamlessly.
Classifying Stocks by Return Fingerprints
Artificial Intelligence
In the stock market, the returns (% change in price of the stock between days) of any particular stock create a fingerprint unique to that stock. For example, the returns of Tesla and Johnson & Johnson are very different, since they are shaped by variable factors such as industry, size, and volatility. In this project, I used machine learning to analyze the "return fingerprint" of stocks in the S&P 500. Would the computer tell me that Facebook and Twitter are similar, if I gave it no context? To isolate the return fingerprint from the rest of the variable factors, I trained the computer on Date Plots. I aimed to correctly group stocks by fingerprint (within the time frame of a year). Dots of the same color cluster together into smaller subgroups, confirming that industry has a big influence on the similarity between stocks. While not all stocks in a sector clustered in one big group, most tended to cluster near at least two others of the same sector.
life.
Web Game
Every day, everywhere, we are surrounded by people from all walks of life. Some have a vast amount of resources available to them, others have close to nothing. During ByteHacks 2018, Team Organic Forto Coffee created this game to raise awareness on the wide variety of lifestyles in our own neighborhoods. By understanding how gender, financial status, education, and hobbies shape our lives and social pyramid standings, we hope to create a more inclusive and open minded community. Our game also shows how different choices and events will impact one's social status. Built with HMTL, CSS, and JS.
Predicting Unemployment in the USA
Artificial Intelligence
Have you ever thought about why the unemployment rates in certain regions always remain low while other regions show consistent high unemployment? Do you want to know what contributes to unemployment, and if analyzing unemployment rates to reveal hidden patterns or correlations in society? In 2019, my team of AI researchers crunched data from the Bureau of Labor Statistics to analyze unemployment rates of various demographics, and we used this data to create and test an unemployment rate predictor. We created algorithms to predict unemployment by region, race, and industry.
Day in Princeton
Web App
If you’ve ever been to Princeton for a day in town, you know that it is hard to decide where to go when. There are so numerous restaurants, shops, and entertainment venues to choose from, and the variety can be overwhelming for visitors. For my first ever web project, I built a quiz to plan a personalized itinerary for users based on their interests and tastes. Simply enter your food, shopping, and entertainment preferences to get your Day in Princeton. Built in HTML, CSS, JS.
GSalud: Create a Plan for Health Reform in Guatemala
Web App
Built for my Advanced Latin American Identities project, site is entirely in spanish. Do you want to learn more about public health and the health system in Guatemala? Right now, Guatemala is doing a reform in the health sector. It is important that we all understand those reforms and how they will affect our lives. So, we put you in the shoes of the Guatemalan legislators. If you were a Guatemalan legislator, what health areas would you focus on, and why? We have compiled a list of current health initiatives actually in Congress, along with some of our own policies that we would like to see implemented. Your job is to choose ten policies that are important to you. In this way you will learn how to envision the possible future of the Guatemalan health system.
