About Me

Wojciech Prazuch

I am a PhD Candidate at Silesian University of Technology, Poland. My main area of research is Machine Learning for Healthcare, and I am active participant in many projects related to that (DM me for more details). However, I am trying to be involved in many other areas as well, as I personally find many wonderful ideas applied elsewhere to be applicable to other domains as well. I have 3 years of professional experience in Software Engineering, however, I found Machine Learning to bring me much more enjoyment. I applied for PhD studies to dwelve deep into Machine Learning (Deep Learning in particular), as my thesis is closely related to that topic. Currently, I work full time on research, and this gives a lot of possibilities to improve every day!

My Career

Medical University of Technology

I took a 3-month internship in Medical University of Gdansk to gather data and develop a Deep Learning model for early lung tumour detection from low-dose Computed Tomography imaging.

February, 2020
Intern

Silesian University of Technology

I am working at Silesian University of Technology on my PhD thesis, which is related to AI in Medicine.

October, 2019
PhD Candidate

Silesian University of Technology

I started my Master studies on Silesian University of Technologies on the same course as on my Bahcelor studies. Since the beginning of the studies, I focused on studying Machine Learning.

March, 2017

Diebold-Nixdorf

I worked at Diebold-Nixdorf for 3 years during my Bachelor and MSc studies. I was involved in developing solutions for retail, worked in large scale project, got familiar with major development tools and practices.

October, 2016
Software Developer

Silesian University of Technology

I started my Bachelor studies on Silesian University of Technologies on interdiscplinary course, called Control, Electronic and Information Technology. The studies were held in English and during that time I developed many crucial skills I use today.

October, 2013

My Skills

My Projects

Mail & SMS Spam Detection

In this project I built a deep learning model to detect spam from sms and e-mail messages. Additionally, I provided some EDA for the data. I have also created a simple endpoint in Flask to communicate with the model.

Face Mask Detection

In this project, I created a face mask detection system that checks, whether a person wears a face mask or not. Again, you can communicate with the model using REST API written in Flask - an example client is shown in the repo.

Automatic Stack Exchange Tagging

The intention of the project was to create an automated way of tagging questions raised by users on Stack Exchange.

Face Recognition

The goal of the project was to recognize faces given in the photo. A pretrained face recognition model was used to generate embeddings for each face provided.

IMDb Movie Reviews

This project showed how to build a model for a simple Sentiment Analysis task for IMDb Movie Reviews data.

Deep Learning from Scratch

In this project, I started from scratch in coding some simple neural networks and applying backpropagation to train them.

Stock Price Prediction

Common deep learning architectures to predict stock price from real-world data.

Music Genre Classification

Predicting music genre using ML algorithms. Some EDA was provied as well.

Twitter Sentiment Analysis

Classification of Tweet sentiments together with EDA.


Projects in progress

Netflix Movie Recommendation

Using data provided by Netflix, the goal is to give recommendations of the movies for the user of specific track of movies and ratings.

Handwriting Recognition

The goal was to automatically translate from written text to electronic text, based on CV techniques and Deep Learning.

Human Activity Recognition

Detect activities from videos or images.

Image Caption Generator

Automatically describe the content of the image using CNN & LSTM.

Lung Segmentation from X-rays

Segmentation of lung from X-ray imaging.

Chatbot

A simple chatbot based on Feed-forward network.

RSNA Pneumonia Detection Challenge

The goal is to tell apart pneumonia (viral or bacterial) from healthy patients, based on Chest X-Rays from NIH database. I applied various methods and tools to select the best model for that job.

Dog Breed Classification

This project involved building a classification model that would enable to classify dogs in terms of breeds. Stanford dogs dataset was used in the project.