Nikolai Åkerholt's Portfolio
  • Posts
  • Introduction
  • Projects
    • Academic
      • Bachelor Thesis: Neodroid Playground
      • CSGO Round Win Predictor
      • VR Health and Wellness Hub
    • Gamejams
      • Super Awesome Game About Fear of Open Spaces: The Game
      • Game of Life
      • Twitch.tv Arena Battler
    • Other
      • Flight Sim - OpenGL Graphics Exam
      • Getting Air Android Game
      • Rogue Army
      • Mr. RogueBot
Bachelor Thesis: Neodroid Playground

Bachelor thesis (Programming Games & Applications at NTNU Gjøvik) done together with Aksel Hjerpbakk, Halvor Bakken Smedås and Jone Skaara. The thesis was part of a larger research project by Sintef Ocean called Neodroid. The main idea was to create a virtual environment in Unity where people could show a robot agent how a task should be done through VR. After having displayed the task the agent would train through machine-learning on how to solve this task in this virtual environment.

January 18, 2021 Read
VR Health and Wellness Hub

University project done in collaboration with Morten Omholt-Jensen. Main idea was to create a VR Game Hub that would consist of several types of minigames. The minigames would have some sort of serious goal other than purely entertainment, for the most part it was to induce some sort of physical exercise for people. Repository is private due to proprietary assets, however below are some images from the application and design:

January 18, 2021 Read
CSGO Round Win Predictor

Deeplearning project done in collaboration with Morten Omholt-Jensen. The project was done for a master degree course, IMT4392 Deep learning for visual computing, at NTNU Gjøvik. The main idea of the project was to see how well a neural network could predict the outcome of a round of CSGO solely based on what equipment each team brought into the round. The project includes three main parts: Datascraper and demo-info extractor to create dataset (Golang) OpenCV template matching to read equipment on teams from a CSGO match image (Python) Deep-learning neural network imlpementation with Keras and Tensorflow in Python to predict which team wins the round Our final trained model was able to predict outcome of rounds with an accuracy of ~68%.

January 18, 2021 Read
Navigation
  • About
  • Skills
  • Experience
  • Education
  • Projects
Contact me:
  • Email: nikolai_aakk@hotmail.com
  • Phone: +4799157507

Toha
© 2021 Nikolai Åkerholt
Powered by Hugo Logo