Category: Data Science
-
Regression Analysis for SARS-CoV-2 RNA Concentrations in NYC Wastewater
An analysis of the trends of SARS-CoV-2 RNA concentrations in NYC wastewater during the height of the COVID-19 pandemic that uses API Building, SQLite for database creation, manipulation, and storage, Pandas & Matplotlib for data visualization and analysis, and scikit-learn for Linear Regression.
-
Evaluating authenticity and quality of image captions via sentiment and semantic analyses
This study explores how sentiment and semantic variance analyses can be used to assess the quality of image captions in large datasets like COCO. By examining how human-generated captions reflect emotional tone and object context, the study reveals subtle biases and variations that influence model training outcomes in NLP and Computer Vision.
-
Student Adaptability Level Classifier in Online Education
An extensive Exploratory Data Analysis using Python, Pandas and matplotlib, explored Supervised Machine Learning Models using scikit-learn and binary classification methods to train, modify, and evaluate the ability for students of certain demographics to adapt to online education platforms, and compared the machine learning models to determine which model had the best predictions.
Dylan K. Picart 