16-Node Raspberry Pi 4 Cluster
Currently working on designing and constructing a 16-node (64 core) Raspberry Pi 4 cluster in order to have dedicated hardware at home for my personal pursuits in computational science and HPC.
Currently working on designing and constructing a 16-node (64 core) Raspberry Pi 4 cluster in order to have dedicated hardware at home for my personal pursuits in computational science and HPC.
As an optional personal project that aligned with my course study, I investigated the capabilities of human location tracking via network monitoring and utilizing computer vision in a home surveillance application. On a single host system, computer vision algorithms were used to analyze doorknobs and deadbolts in order to synthesize their locked/unlocked state while home network traffic was constantly analyzed to deduce what residents are currently home and the times that residents come/leave home. This collective information allows the owner of the system to know if there house was left unlocked and unattended in addition to which resident left the home in that state.
A final project where the fundamentals of stochastic system processing were addressed. The fundamentals covered in this project include Control Data Generation, Synthesis, and Detection/Discrimination using the Fisher Discriminant.
A write-up on the attack and defense strategy that I used to win the UKY Spring 2019 EE 576 Cybersecurity Capture-the-Flag Challenge.
WRITE UP COMING SOON.
In this project, I recreated a K-Means Image Segmentation approach in CUDA. The kernel scheme for this approach was inspired by similar work from a research group from the University of Split, Croatia.
This compiler take a C-like language, performs code motion, code straightening, loop unrolling, constant/variable propagation, and even generates a combinatorial circuit equivalent to the given code.
Swapped my server to an Unraid setup. This allows me to more easily host VMs, dockers, cloud host files, and host network-based backup locations. More information coming soon.
Designed and implemented the verification (using Verilog) of a general purpose processor that uses log number system (LNS) arithmetic rather than today’s standard of floating point arithmetic. The log number system arithmetic is much more efficient at multiplies than floating point arithmetic; while floating point is much more efficient at addition than LNS. This full post is coming soon to discuss more LNS, its use cases, and why it is important to investigate other forms of arithmetic.
Currently developing a camera system that uses an LED matrix for light sensing and light emitting. That’s right… if you are unaware, LEDs can be used as light sensing devices. This is possible by two physics concepts present in semiconducting devices: the photoelectric effect and depletion layer capacitance build up. This full post will be coming soon, so stay tuned to learn more.
Still working on populating my website with posts. I hope to put up two blog posts very soon. Once those are finished, I will advertise the website on social media. So, keep your eyes on my social media to catch the website unveiling announcement.