NCSI: Growing Artificial Tissues using Artificial Intelligence-based Controls

Status	Completed
Mentor Name	Roman Voronov
Mentor's XSEDE Affiliation	Campus Champion
Mentor Has Been in XSEDE Community	4-5 years
Project Title	Growing Artificial Tissues using Artificial Intelligence-based Controls
Summary	In this project we are developing a technology for controlling cell behavior in living cultures based on real time images acquired from high resolution microscopy. We are currently focusing on developing parallelized image processing and controls algorithms for directing cell behavior in real time based on the microscopy observations.
Job Description	-Debug and develop MPI code -Process images obtained from Lattice Light Sheet microscopy using HPC resources -Develop and Train a Reccurent Neural Network (RNN) algorithm on the microsopy images of cell behavior, for implementation in a distributed netwrok of a Model Predictive Controllre (MPC) -Implement the MPC network to direct artificial tissue growth experiments in real time
Computational Resources	The project will use Texas Advanced Computing Center resources via a New Jersey Institute of Technology Campus Champion allocation as follows: -Long term tape storage for large data from Lattice Light Sheet Microscopy -Image processing of the 3D Lattice Light Sheet Microscopy data, and Visualization using Visit and Paraview packages -Training of the Recurrent Neural Network (RNN) on experimental microscopy and chemical assaying data for implementation in the Model Predictive Controller (MPC).
Contribution to Community
Position Type	Apprentice
Training Plan	Over the Summer of 2020 students have been trained in the fundamentals of HPC, Fortran, working with clusters (connecting, compiling, scheduling jobs, etc), MPI and Open MP. During the Fall of 2020 they will begin to apply their knowledge to debugging and developing research codes independently. They will continue their training in advanced MPI and OpenMP, as well as the hybrid implementations of the two. This material will be deployed via weekly meetings with the PI, in order to get advice/directions regarding the plan and progress of the research. Additionally, they will perform literature reviews and take courses relevant to the research direction. Finally, the students will also be trained in parallel I/O, which is also important for achieving computational efficiency.
Student Prerequisites/Conditions/Qualifications	Must be an undergraduate student at NJIT with experience in Matlab and Lattice Light Sheet Microscopy. Additionally, interest in the following is highly desired: -Image Processing -Machine Learning -Controls Theory -Supercomputing
Duration	Semester
Start Date	09/01/2020
End Date	12/01/2020