A neural-recording, headstage device wirelessly communicates signals from the brain of an animal subject to a data receiver using a bidirectional Bluetooth Low Energy (BLE) link. The headstage device can record either electrical or electrochemical signals and provides user-controlled optical stimuli to help probe brain tissues. The data receiver incorporates a graphical user interface (GUI) that can process and display data in real-time. The GUI also provides controls to configure the optical stimuli and to start/stop neural recording.

Team Members

Distributed networks address the issue of insufficient cellular coverage with individually owned and operated hotspots that together provide the coverage of a large network. Owners of these hotspots earn cryptocurrency proportional to the amount of data transmitted and received. This project consists of a web app user interface that allows hotspot owners to track their cryptocurrency earnings from multiple networks and a hotspot that operates within a distributed network to demonstrate a cheaper, entry-level alternative to existing products.

Team Members

MRI is short for magnetic resonance imaging, which uses a strong magnetic field and radio waves in order to non-invasively create detailed images of organs and tissues inside the body. The problem is that MRI scans are notoriously slow, and a single scan can take up to an hour to complete. Our project aims to address this by building a web application for hosting federated learning for reconstructing MRI scans from undersampled data. Federated learning refers to the process of aggregating many locally trained models into a single global model that can be shared with everyone.

UT TrustLab is an extensible, user-friendly, and interactive web application that provides users with trustworthy sources of information in a world full of misinformation. More specifically, we aim to provide users the ability to filter through Twitter accounts and see collected trust filter data for these accounts; this collection is out-of-scope for our project, but the data consists of a set of filters that determine the overall trustworthiness of an account. The application is organized into four pages: topics, sources, home, and about.

Over the past year, our team worked to upgrade Privacy Check, a browser extension created by UT Center for Identity. This extension utilizes machine learning to analyze a website's privacy policy and provide the user with easy-to-understand scores. Our update includes four new features which aim to empower Privacy Check's users. Our cache continuously updates the top 100 most visited websites' scores bi-weekly to reduce latency with our other features.

Our team has worked to deliver a new update to PrivacyCheck, a data mining tool developed by the UT Center for Identity that analyzes the text of privacy policies and provides digestible summaries on information collected and stored. PrivacyCheck provides consumers with an overview of the ways in which companies use their personal data in a graphical, ‘at-a-glance’ format. Our team aimed to provide support for additional browsers with significant market share besides Chrome including Firefox, Edge, Opera, and Safari.