Generating Molecular Communication Water Channel Images via GAN

In this project, the aim is to generate an open-source simulator for our water channel testbed using generative adversarial networks (GAN). The water channel testbed basically consists of a transparent water channel, water tanks, adjustable circulation pump, information molecules, molecule emitter, molecule filters, laser, high-resolution programmable cameras, chemical sensors, synchronization unit between camera and laser, and a computer.

During the experiments, we changed the emission point and obtained 2-3 minute videos of different propagation results of the molecules. The intended output of this dissertation is to generate artificial videos when the emission point is given as an input. It is aimed to turn this study into a simulator using GAN or any other method you suggest. The distance of the emission point will be given to the simulator as an input, and it will be expected to generate a video. The videos we obtained earlier with different emission points will be used as a training set for the GAN. You can see the example of 3 frames extracted from the video in Figure.

Duration: 2 semesters