Projects will be performed in groups - of at most 3 students per group. Please organize yourselves into groups as appropriate. You need to pick a topic by Apr 03. There will be an interim review, and the final review in finals week. Please see the main page for deliverables on the project.
Example Projects (from previous years)
1. Healthcare
Covid 19 Predictions with Various Methods
Heartbeat data analysis
States Coronavirus Sentiment Analysis based on Tweets
2. Spatio-temporal Analysis
Spatio-temporal localized analysis of twitter content
Route optimization and visualization for NYC data
A real-time people counting application based on streaming data
Citi Bike Demand Prediction with Weather Information
3. Social Media Analysis
Youtube video recommendation based on twitter
Sentiment analysis based on youtube
Dynamic Word Cloud Generator on Twitter
Real-time hotspot issue detection
Real-time twitter hot topic mining
Wikistats
4. Financial Data Analysis
Stock/Bitcoin price prediction
Predicting stock prices with multi-dimensional data
Sentiment based stock price prediction
Evaluating the Correlation of Streamed Sentiments with Multiple Cryptocurrencies
5. Deep Learning and Stream Processing
Real-time facial recognition
Deep learning model based speech to text
6. Generative AI and Stream Processing
Real-time translation of live speech
Datasets
Physionet: http://www.physionet.org/
NOAA: http://w1.weather.gov/xml/current_obs/
Youtube API
RSS News Feeds (e.g. BBC)
Other Public Streaming Datasets
Final Project Reviews: May 08/May 15
Location: TBD
Final Project Report and Source Code (due May 9)
Please submit a 5 page report that summarizes your project, its goals, results, and a description of how it could be further improved.
Please also package up your source code, including visualization interfaces, makefiles, etc