Lukas Justen's repositories
Lane-Marking-Detection
This is the final project for the Geospatial Vision and Visualization class at Northwestern University. The goal of the project is detecting the lane marking for a small LIDAR point cloud. Therefore, we cannot use a Deep Learning algorithm that learns to identify the lane markings by looking at a vast amount of data. Instead we will need to build a system that is able to identify the marking just by looking at the intensity value within the point cloud.
NLP-AllRecipes
This project aims to convert a recipe from AllRecipes.com into another recipe with a different style or cuisine. We parse the HTML code into an internal representation using semantic NLP techniques.
Law-OMNI-BERT-Project
Directly applying advancements in transfer learning from BERT results in poor accuracy in domain-specific areas like law because of a word distribution shift from general domain corpora to domain-specific corpora. In our project, we will demonstrate how the pre-trained language model BERT can be adapted to additional domains, such as contract law or court judgments.
Deep-Reinforcement-Learning
This repository contains the source code and documentation for the course project of the Deep Reinforcement Learning class at Northwestern University. The goal of the project was setting up an Open AI Gym and train different Deep Reinforcement Learning algorithms on the same environment to find out strengths and weaknesses for each algorithm. This will help us to get a better understanding of these algorithms and when it makes sense to use a particular algorithm or modification.
IT-Security-2BPR
This repository contains the material for one lecture about Two-Server Blind Password Registration based on the Paper "Blind Password Registration for Two-Server Password Authenticated Key Exchange and Secret Sharing Protocols" by Franziskus Kiefer and Mark Manulis.
Machine-Learning-Tutorials
A repository for machine learning problems and exploration of different ML libraries. The goal of this repository is to collect takeaways while developing ML models. This should improve my overall understanding of developing machine learning applications.
NLP-GoldenGlobes
This project NLP project uses Twitter tweets from the 2013 and 2015 Golden Globes ceremony in order to detect the hosts, winners, presenters, awards and nominees. We used a semantic approach instead of a machine learning approach in order to extract this kind of information. We build the model so that it will generalize to other award ceremonies like the Oscars or Grammys.
Airbnb-Price-Evaluator
Our goal in this project was to gain insight into the world of Airbnb market dynamics. There are several different ways to accomplish this goal, but more specifically, we attempted to predict the price for any Airbnb given standard measures such as the location of the listing, and the features that any particular Airbnb offers.
4-Gewinnt-Spezial
Diese App wird im Rahmen der Lehrveranstaltung MOVS (Mobile & Verteilte Systeme) programmiert. Es handelt sich um das klassische 4 Gewinnt mit einem Multiplayer Modus und einem kleinen Highscore, der auf einer Realm Datenbank realisiert ist.
Alexa-Norris
This Alexa Skill project has been developed throughout a Heckathon at Northwestern University for the Master's program for Artificial Intelligence. In a group of 4 developers we developed a Alexa skill that tells you Chuck Norris jokes.
Blackbox
Eine "crossplatform" App für Segelflieger und hobby Astronauten. Mit Hilfe der eingebauten Fluginstrumente für Geschwindigkeit und Orientierung kann man theoretisch sicher fliegen :D
Coding-Camp-2018
Dieses Repository enthält Code für das TH Bingen Coding Camp welches unter anderem im Jahr 2018 veranstaltet wurde. Bei diesem Projekt sollten Schüler Google Maps nutzen um geometrische Objekte auf einer Karte einzuzeichnen. Dadurch konnten die Schüler auch einen ersten Einblick in komplexe APIs wie Google Maps erhalten.
detekt
Static code analysis for Kotlin
Fuel-Price-Tracking
This repository aims to to keep track of fuel prices in my local area and build a history of fuel prices that could then be visualized for further analysis.
MOVS
Das Repository enthält alle relevanten Projektordner für einen Vortrag rund um NFC Tags and NFC Beam in der Android Entwicklung. Der Vortrag wurde im Rahmen der Vorlesung zum Thema Mobile & Verteilte Systeme an der TH Bingen vorbereitet.
Weinberg-iOS
Unsere Weinberg-App für Winzer zur Optimierung von Arbeitsvorgängen im Apple-Gewand. Wir haben diese App im Rahmen einer Vorlesung an der TH Bingen weiterentwickelt.