In response to the pressing need for accessible learning tools for Sub-Saharan African Languages, our project, Dele aims to provide an engaging iOS application. Starting with Yoruba, a language spoken by millions in Nigeria and West Africa. Recognizing the challenge of effectively teaching a language, our solution integrates gamification elements and an AI model, aiming at keeping users motivated and engaged. The app offers interactive lessons, progress tracking, and a rewards system to enhance engagement.

Formula SAE is a student design competition for universities to design, build, and race formula-style cars. As one of the founding universities, UT Austin has expanded its team to include solar-powered and electric vehicles (EV), alongside its traditional internal combustion car. In recent years in the EV division, there has been a shift away from a single inboard-mounted motor to multiple outboard, wheel hub-mounted setups. Outboard motors widen the performance envelope of the car to include traction control, torque vectoring, and energy regeneration.

Introducing FridgeMate: Transform your standard refrigerator into a smart appliance effortlessly. As you stock your fridge, FridgeMate swiftly scans items, seamlessly integrating them into a virtual inventory. Access your complete grocery list anytime, anywhere with the FridgeMate mobile app, placing convenience at your fingertips. Beyond inventory management, FridgeMate monitors fridge conditions, alerting you to temperature fluctuations and open-door instances. Embrace hassle-free grocery tracking with FridgeMate – let your fridge take the reins.

Team Members:

This project combines digital signal processing and machine learning to separate human speakers using a custom 16-channel uniform circular array. First, a beamforming operation is applied to the recorded audio. Then, the transformed data is sent to a convolutional neural network (CNN) which predicts the ideal ratio mask (IRM) that filters out the unwanted source. The IRM is applied to the spectrograms with the largest signal power of the target speaker, which is found using a direction-of-arrival (DOA) calculation.

The ARMM (Assistive Robotic Modular Manipulator) is a robotic arm that can be controlled by a user's arm movements and gestures. Various industrial robotic arms have come before the ARMM to automate laborious tasks, such as palletizing, welding, and various pick-and-place manufacturing jobs. In manufacturing, research, and the general field of robotics, robotic armatures are some of the most common types of robots used today. However, these are often preprogrammed with set routines and are usually not controlled in real time by a user.

"KickOff Connect: Play Nearby" is an innovative software application designed to bridge the gap between sports enthusiasts and local sports communities. Our app allows users to organize events, find nearby activities, and connect with like-minded individuals. With features like event creation, GPS-based activity search, and interactive discussion boards, KickOff Connect revolutionizes the way people engage with sports.

This capstone project introduces an open-source software package dedicated to the modeling of incoherent quantum systems and nanoelectronic devices utilizing emerging quantum materials. The package is designed to advance the simulation of complex electron physics in novel nanotechnologies such as 2D transistors and graphene, optionally with applied magnetic or exchange fields, using the Non-equilibrium Green's function methodology for calculating conductances and self-interaction effects.

The aim of this project is to simulate the hardware of an integrated photonic circuit to be used as a machine learning accelerator. The design consists of a programmable mesh of Mach-Zehnder Interferometers that can be tuned under an applied voltage to perform matrix-vector multiplication on optically encoded data. Such optical computation is extremely fast, being limited only by the speed of light in the integrated waveguides and the bandwidth of the internal phase-shifters.

Neuromorphic computing is an exciting new area of computer architecture that takes inspiration from the brain to achieve huge improvements in power efficiency. Applications are often described in the form of Spiking Neural Networks (SNNs), which are similar to conventional neural networks, but where information is encoded in time and communicated as sparse time-varying “spikes”. SNNs have been applied efficiently to a range of applications, such as machine-learning and robotic control. Hardware architectures have been proposed that execute SNNs far more efficiently than CPUs or GPUs.

The goal of our project was to create an accurate experimental procedure to perform comparison verification recordings with a state-of-the-art brain activity recording device, EEG, and a headrest embedded sensor.

Team Members:

Jonah Cadena-Perena
Robert Carney
Brian Chu
Ella Harper
Carson Nguyen
Jason Zubia