
Ian F. Blake Lecture

Join ECE for this year’s Ian F. Blake Lectureship speaker, Professor Vahid Tarokh from Duke University, on Wednesday, May 10th at 11am PDT, online.
Tarokh’s lecture “Hypothesis Testing and Quickest Change Detection for Unnormalized Models” presents a fresh take on likelihood-based hypothesis testing, reflecting on first experiences with this topic from his graduate Digital Communications course taught by Ian Blake.
The celebrated Neyman-Pearson Lemma proves that this test is Universally Most Powerful for testing a null hypothesis versus an alternative one. Similarly, the CUSUM change detection is based on log-likelihood ratio and its optimality has been proved by Moustakides. In order to apply these optimal tests, we need to know the exact pdfs for both null and alternative (respectively pre and post change) distributions. These pdfs are not unfortunately easy to obtain in high dimensional data-driven scenarios. Recent research has demonstrated that energy, score-based and diffusion methods produce state of the art models in high-dimensional setting. Additionally, these models are extremely robust to potential noises in the collected data. Unfortunately, these models are unnormalized. Calculating the partition functions required for their normalization is a notoriously difficult problem. This limits their applicability to log-likelihood based tests.
This motivates our work where we have developed Fisher-inspired methods for hypothesis testing, quickest change detection, and their robust versions (when the hypotheses or pre- and post-change distributions may not be exactly known) for unnormalized models. We will discuss our results and demonstrate their applications to various scenarios including out of distribution detection.
About the speaker:
Vahid Tarokh received the PhD degree from the University of Waterloo in 1995 under the supervision of Ian F. Blake. He worked at AT&T Labs-Research until 2000. From 2000-2002, he was an Associate Professor at Massachusetts Institute of Technology (MIT). In 2002, he joined Harvard University as a Hammond Vinton Hayes Senior Fellow of Electrical Engineering and Perkins Professor of Applied Mathematics. He joined Duke University in Jan 2018, as the Rhodes Family Professor of Electrical and Computer Engineering. He was also a Gordon Moore Distinguished Research Fellow at CALTECH in 2018. Between Jan 2019-Dec 2021, he was also a Microsoft Data Science Investigator at Duke University.
Please RSVP to attend and receive the Zoom link: https://ubc.ca1.qualtrics.com/jfe/form/SV_b3m9cLPhD7Pdbgi
Design and Innovation Day 2023: Winners, Projects, and Photos
Thank you to everyone who attended Design and Innovation Day! Congratulations to all of the groups on your hardwork and effort for this year’s capstone projects!
The capstone design project is a major component of the ECE engineering curriculum where students work in teams of four to six students to design a product/service of significance and to solve an open-ended problem in electrical and computer engineering.
Best Video Winners
The best video awards recognize our teams’ exceptional ability to communicate their technical design challenge and project’s impact to a general audience. A short list of videos is selected by the Capstone students with the final winners selected by a panel of judges representing diverse perspectives.
First Prize: Industrial IoT RF Proximity Detection System for Underground Mining Application
Project Client: Minto Metals
Our client is a mining company that needs to prevent vehicle-to-person collisions inside tunnels by letting vehicle drivers know how many people are around them within a 15-meter radius.
For this purpose, we created wireless devices that could determine the distance between people and vehicles and count the number of people nearby. We also made it possible for these devices to alert drivers when people are within a 15-meter range. Additionally, we made sure that the devices were simple to set up and operate for the convenience of the client.
If you’re interested in our team or have any questions, please don’t hesitate to reach out to us. We’d be happy to hear from you!

Yuqi Fu
Lena Kim
Justin Chang
Nestor Brito Naveda
Daniel Nadeem
Second Prize: Building Secret Support Services for UBC Library
Project Client: UBC Library – Chapman Learning Commons
Our team has collaborated with UBC’s own CLC (Chapman Learning Commons) from the Iriving K. Barber to develop a device for librarians and student staff to feel safer whilst on shift. Our project is described as a “secret support service” to allow for discreet communication to a supervisor or other staff in situations that may be stressful or overwhelming to a student staff member. In times that a staff member may land themselves in an encounter or confrontation with a difficult customer in the library, and require extra support from another person. To achieve this we created a portable and rechargeable device that can attach to a lanyard or be stored in a pocket capable of communicating to the necessary personnel at the push of a button. Throughout anywhere in the library, a staff member can use the device to contact a supervisor, a staff member, or if the situation calls for it, UBC security, informing them of their situation, all whilst maintaining their attention towards the customer. The recipients, contents of the phone call/text, or contact schedule are all configurable through the device using computer peripherals, and once set it will use the information to notify the respective personnel. The corresponding recipient will receive a phone call or text describing that a staff member from the CLC is in need of aid, and the recipient can now respond accordingly.

Ross Mojgani
Victor Parangue
Azwad Sadman
Daniel Lee
Jordan Lee
Third Prize: Wine health monitor
Project Client: Rampart Detection Systems Ltd
Approximately 31.7 billion bottles of wine are produced around the world each year. In BC alone this contributes $3.75 billion annually to BC’s economy. Of all that, roughly 1% percent of it spoils and will be wasted. In BC, this contributes to nearly $30 million dollars lost annually for one of our premier industries. If these bottles could be found to be spoiled before the bottle was opened/contaminated, then that would save a lot of hassle on the point of restaurants and would allow it to be put to other use such as making vinegar or dyes and would save product and money.
Our client, Rampart Detection Systems is a company that specializes in non-contact electrometers. In the past they have used their technology for IED detection and analyzing mining conveyor belts for microcracks or other wear before they are visible to the eye. We, in cooperation with Rampart, are applying their technology to creating a device that will detect if wine has spoiled without opening the bottle. The audience for this device includes but is not limited to: Wineries, Restaurants, Bars, Liquor Stores, Wine Merchants, Bottle Distribution Centers, Distilleries, and Importers.
Detecting if wine has spoiled involves detecting very trace amounts of chemicals. The chemicals in question are acetic acid and 2,4,6-trichloroanisole (TCA). In order to detect these trace chemicals we needed out sensor to be as close to an ideal electrometer as possible. We needed to have a sensor that would be incredibly sensitive. We used our own implementation of Rampart’s floating electric potential sensor (FEPS) to get the sensitivity we were looking for. Another challenge is eliminating electrical noise, keeping the quality of the signal as high as possible. We’ve designed the enclosure for the device to minimize noise and we’ve added a control loop to keep the signal within desired parameters. Finally, there is the issue of interpreting the data to tell if the wine is spoiled. The relationship between whether the wine is spoiled and the data gained may not be obvious to the human eye. We’ve implemented machine learning to interpret the data and give a result of the wine being spoiled or not.

Madison Maurice
James Pan
John Forssander-Song
Sanid Singhal
Jasmine Radu
Explore the 2023 Capstone Projects
Facilitate Our Personal and Community Connection
Enhance How We Do Things
Improve How We Make Things
Leverage Data to Help Us Make Decisions
Design and Innovation Day Photo Gallery















2023 Capstone Design & Innovation Day

Welcome to Electrical and Computer Engineering Design and Innovation Day!
We are excited to share the projects our students have worked on over the final year of their undergraduate program! The capstone design project is a major component of the ECE engineering curriculum where students work in teams of four to six to design a product/service of significance and to solve an open-ended problem in electrical and computer engineering.
April 11th, 2:00-5:00pm
Fred Kaiser Building – 2332 Main Mall, UBC Campus – Atrium and Kaiser 2020/2030
https://design-innovation.apsc.ubc.ca/
Browse through our ECE projects and abstracts featured at Design + Innovation Day!
Facilitate Our Personal and Community Connection
Enhance How We Do Things
Improve How We Make Things
Leverage Data to Help Us Make Decisions
Map


Projects
| Team Name | Title | Company |
| AI-15 | 2-D Vibration Detection of Guitar Strings Using Piezo Sensors | Yamaha Guitar Group, Inc |
| AI-18 | Dynamic Parking Signage V3 | UBC Parking Services |
| AI-24 | Smart outdoor sports equipment tracker | CabinPals |
| AI-26 | Avionics Integration Test Bench | KF Aerospace |
| CG-42 | 3D Mapping Smart Glasses for people with vision loss | Seleste Innovations Inc |
| CG-49 | Cost-Effective Control System and GUI for Portable All-in-one Automated Microfluidics | UBC SoC Lab and BioMEMS Lab |
| CG-65 | Cost-Effective Automated Testing System based on Modified 3D Printer for Optimizing Assistive Switch Designs | Neil Squire |
| CG-71 | Wine health monitor | Rampart Detection Systems Ltd |
| HA-33 | Battery Monitoring System for Small Drones | University of Victoria Centre for Aerospace Research |
| HA-43 | Energy management system for Harbour Air electric aircraft fleet | Harbour Air Aerospace Services |
| HA-58 | Nimba IoT Platform | Hedgehog Technologies Inc. |
| HA-75 | DC Non-Contact voltmeter | Rampart Detection Systems Ltd |
| HA-79 | Transmission Line Ultimate Stage Fault Level Calculation Tool | BC Hydro |
| JY-05 | 6-DOF Robotic Arm | Synovus Solutions |
| JY-07 | ‘PhysViz’: Gamification of a mobile application for physiotherapy | UBC Tendon Injury Prevention and Rehabilitation Research Group |
| JY-16 | Wearable Device for Automated Cardiac Arrest Detection | Canadians Saving Cardiac Arrest Victims Everywhere (CANSAVE) |
| JY-41 | Modular Phone App for Cardiac Arrest Detection | Canadians Saving Cardiac Arrest Victims Everywhere (CANSAVE) |
| PB-06 | Building Secret Support Services for UBC Library | UBC Library – Chapman Learning Commons |
| PB-17 | Logic Model to Drive Patient Treatment | Human Motion Biomechanics Laboratory |
| PB-19 | UBC Parking – Data Visualization and Dashboard Development | UBC Parking Services |
| PB-30 | Chat Bot & Recommendation Engine | UBC Cloud Innovation Centre |
| PB-57 | Trace-based Debugging for Java Development Environments | UBC ECE, ReSeSS Research Lab, PI: Prof. Julia Rubin. |
| PL-55 | VR/AR interface for Delta Controls multi-sensor O3 Edge device | Delta Controls Inc. |
| PL-66 | Testbed Management Centre for the AURORA Smart Transportation Testbed | University of British Columbia |
| PL-68 | Designing Window Sensors to Advance Bird- Friendly and Energy Saving Building Design Strategies on UBC Vancouver Campus | UBC, Campus and Community Planning |
| PN-13 | Gesture Controlled Drone Vlogging Assistant | Huawei Technologies Canada Inc. |
| PN-32 | Innovation Connections – Knowledge Graph | UBC Cloud Innovation Centre |
| PN-44 | Efficient HW Implementation of Super Resolution DNN for real time video scaling | NETINT Technologies |
| SF-39 | Software Platform for Surgical Dental Implants | Prisman Research Laboratory, Department of Surgery, UBC |
| SF-60 | Neesh-An LGBTQ2+ Community Mobile Application | Qrated Studio Inc. |
| SF-64 | Remote mobility monitoring system | UBC Cloud Innovation Centre |
| SF-70 | Machine learning models for protein design and drug discovery | Gandeeva Therapeutics |
| SF-78 | Towards Security Analysis in Microservice-Based Spring Applications | The ReSeSS Research Lab, UBC. PI: Prof. Julia Rubin. |
| TL-08 | Industrial IoT RF Proximity Detection System for Underground Mining Application | Minto Metals |
| TL-34 | Monitoring Nature with LiDAR Software Platform | Korotu Technology Inc. |
| TL-63 | Noise Detector and Classifier | Breeze Labs Inc. |












