shivasuri Goto Github PK

auto-captioning

Caption an English video of a single person speaking face-front to a camera, integrating visual and audio features into our model.

boggle

Final Project--Boggle from scratch (Java)

classifying_depression

Objective: Given a set of a person’s tweets (and their associated metadata), predict whether that person suffers from depression, PTSD, or neither of these (control). Specifically, I create three models – one for each pairwise distinction: PTSD vs. control, depression vs. control, and PTSD vs. depression

computer-systems-cis-240

Computer Systems

dicomparser

JavaScript parser for DICOM Part 10 data

dwv-react

Medical viewer using DWV (DICOM Web Viewer) and React.

embedded-systems-ese-350

eslint-plugin-react

React specific linting rules for ESLint

google-landmark-recognition

kaggle competition: https://www.kaggle.com/c/landmark-recognition-2019/

penncloud

PennCloud - A distributed cloud platform with a highly scalable, fault-tolerant key-value datastore at the backend that supports strong consistency and efficient replication, checkpointing and recovery.

ra

A simple native WebRTC demo iOS app using swift

semantic_textual_similarity

Objective: find semantic [i.e. meaning-based] similarity measures across pairs of sentences. Uses word2vec and WordNet.

sound

Using Sallen-Key filter topology, I assembled low-pass and high-pass filters for treble and bass components followed by respective amplifiers (using MOSFET transistors). Furthermore, I powered the audio docking station by building my own AC/DC power supply by implementing a transformer, full-wave rectifier, smoothing filter, and voltage regulator.

stat571-ncaa-predictions

textsummarization

Extractive Text Summarization. Trained on 200k+ CNN and Daily Mail News Articles. Outputs ~3 sentence summaries to match the provided gold summaries, necessary for testing. Uses SpaCy for NER/POS tagging, and implements QR Matrix Decomposition, a semi-supervised model, and word-frequency calculator to determine summary sentences.