Project AI-24: Smart outdoor sports equipment tracker
Project Client: CabinPals
Project Description: For owners who share real estates such as summer houses and cabins in ski resorts, keeping track of their loaned equipment (skis, surfboards, bikes, etc) during guests’ stay can sometimes be a problem. We have designed a smart equipment tracker that can be easily attached to these items, helping homeowners and those using the equipment keep track of the location of their equipment.
The key features of such a tracker device is: Wireless technology, long communication range, compactness and power efficiency. The realization of one feature typically implies the trade-off of compromising the other ones. To effectively communicate its current location with the user end, the product utilizes wireless technologies including LoRaWAN and GPS. To minimize the size of the device, the wireless chips are integrated with super compact antennas, with optimal wiring on the self-designed PCB. The team has been dedicated to implementing ultra low-power firmware to maximize its battery life up to 6 months. As an extra feature, low-power motion sensing is also implemented to enable anti-theft modes.
Project CG-71: Wine health monitor
Project Client: Rampart Detection Systems Ltd
Project Description: 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.
Project CG-77: Waste & Recycling Sensor Pickup Simulator
This team will not have a booth at the Design & Innovation Day due to confidentiality agreements.
Project Client: RecycleSmart (Pello Project)
Project Description: Waste & Recycling Sensor Pickup Simulator project is designed to refine and advance the testing process and experience of the Pello Sensor for our client, Recycle Smart. The Pello Sensor, a versatile device situated in large trash receptacles, undergoes continuous optimization and adaptation to accommodate new pick-up movements. However, the client requires a consistent and measurable testing platform to support the precision improvement of the Pello sensor’s pick-up detection algorithm.
The primary technical challenge of the project involves constructing a mechanical platform capable of delivering accurate measurements and enabling the client to replicate specific test scenarios for algorithm debugging purposes. The sensor’s characteristics prompted the team to develop a suitable mechanical gimbal and a tailored control system, complete with a graphic user interface (GUI), to ensure that the platform can be operated by testers without an engineering background. Additionally, the prototype must incorporate appropriate components to facilitate potential mass production by the client.
Project HA-43: Energy management system for Harbour Air electric aircraft fleet
Project Client: Harbour Air Aerospace Services
Project Description: The product we have created is an application for Harbour Air which will serve as a tool to model the energy consumption of their electric aircraft fleet for commercial flights. The tool will aid the flight operations crew in scheduling flights by utilizing a multi-input, multi-output simulation model that represents Harbour Air’s ePlane battery array and has been modelled and tested on the appropriate battery cells.
Project HA-79: Transmission Line Ultimate Stage Fault Level Calculation Tool
Project Client: BC Hydro
Project Description: Our group (HA-079) designed and created a user-friendly Excel tool for engineers at BC Hydro to calculate the ultimate stage fault levels on high-voltage transmission lines. “Ultimate stage” refers to the power system with all foreseeable expansions to the network considered. Faults can be caused by various factors such as severe weather, equipment failure, or human error, and can disrupt operations or even pose safety risks. Therefore, understanding ultimate stage fault levels is critical for engineers to plan and design the power grid to be more resilient against faults.
The tool focuses on the two most common types of faults; three-phase faults and single-line-to-ground (SLG) faults. Once the user has input essential data, the tool then provides accurate calculations of the fault current at a specified location as well as a graphical representation of fault levels along the entire transmission line.
By offering a comprehensive yet straightforward solution, this tool will assist engineers at BC Hydro in ensuring the reliable and safe operation of their transmission lines. For further collaboration opportunities, please contact Megan: migiyang@student.ubc.ca ; Daivik: santoshd@student.ubc.ca ; Amaya: amayaw@student.ubc.ca ; Nick: nickvo@student.ubc.ca ; Hazel: chongoti@student.ubc.ca
Project JY-41: Modular Phone App for Cardiac Arrest Detection
Project Client: Canadians Saving Cardiac Arrest Victims Everywhere (CANSAVE)
Project Description: CodeBlue is a mobile application that aims to help the issue of unwitnessed Sudden Cardiac Arrests (SCA), which have a survival rate of nearly 0%. It does this by receiving data from wearable devices that collect cardiac data, analyzes that data, and monitors the user for cardiac events. If an event is detected, then EMS is alerted in order to provide life-saving care.
CodeBlue is geared towards high-risk individuals, such as the elderly, or those with cardiac conditions.
The major technical challenge that we resolved is the receiving and processing of data through cloud-based servers, even when the application is not open or the phone is closed.
Project PB-17: Logic Model to Drive Patient Treatment
Project Client: Human Motion Biomechanics Laboratory
Project Description: Children across the province currently wait months to years for appointments with specialist physicians. For children, these long wait times can prolong pain, contribute to worsening health outcomes, and negatively impact mental health. The triage of patients is a crucial tool in managing long waitlists, though the triage process is often complex and time consuming.
We worked with the Sleep Clinic within the Respiratory Division at BC Children’s Hospital to create a visualization tool that improves the efficiency and accuracy of the triage process. Our visualization tool is a desktop application that allows clinicians to clearly visualize population-level data and patient specific data with filtering and analytics capabilities. This supports clinicians to more easily understand the characteristics and needs of their patient population.
Project PB-19: UBC Parking – Data Visualization and Dashboard Development
Project Client: UBC Parking Services
Project Description: Have you ever played a game of whack-a-mole? That’s what our client feels like when trying to access their parking data! They have to jump from website to website, trying to keep up with all the different pieces of information. It’s a headache and a half! But fear not, we’re here to streamline and consolidate all that data into one easy-to-access place. No more whack-a-mole, just smooth sailing.
Project PL-55: VR/AR interface for Delta Controls multi-sensor O3 Edge device
Project Client: Delta Controls Inc.
Project Description: The purpose of the project is to improve remote real time building inspections efficiency for maintenance staff through the usage of a VR user interface.
The major technical challenge involved is creating a communication bridge that is scalable between the building sensors and the users, as well as creating easily identifiable visualizations of the building sensor data.
Project PL-66: Testbed Management Centre for the AURORA Smart Transportation Testbed
Project Client: University of British Columbia
Project Description: This project supports the University of British Columbia’s (UBC) Automotive Testbed for Reconfigurable and Optimized Radio Access (AURORA) project. The project focuses on creating infrastructure to allow researchers to understand traffic patterns better. Traffic data from different intersections across UBC will be collected by different device sensors and monitors and sent to the Testbed Management Centre (TMC).
The main deliverable for this project is a functional AURORA Testbed Management Centre (TMC), i.e., a set of servers and monitors that receives data from the smart intersection and visualizes it with the help of Web Interface.
Project PL-68: Designing Window Sensors to Advance Bird- Friendly and Energy Saving Building Design Strategies on UBC Vancouver Campus
Project Client: UBC, Campus and Community Planning
Project Description: Bird collisions with windows are one of the top sources of human-caused bird mortality. Birds cannot see the transparent windows and attempt to fly through them.
The primary goal of our project is to develop an Internet-of-Things (IoT) device automating the detection of bird collisions with windows, while also gathering relevant environmental data, such as air temperatures, enabling researchers to better understand the conditions of bird-window collisions.
Additionally, our secondary goal is to measure the heat flow rate of windows, providing researchers with a tool to gauge the thermal performance of windows.
One of the challenges with detecting bird collisions is reading sensor data and processing it at near-real-time without one task interfering with the other. This challenge of real-time processing is resolved by developing an efficient algorithm while simultaneously taking advantage of Real-Time Operating System.
Moreover, measuring the heat flow rate typically requires an expensive heat flux sensor setup. Our device is able to measure the heat flow rate of windows using data from two temperature sensors.
Finally, our system is able to execute all of these functionalities without intervention for a maximum of 30 days, operate on a battery, and send data to a customizable user interface for monitoring and further analysis.
Contact information: For further inquiries, please contact us at ryotaroh@student.ubc.ca
Project SF-78: Towards Security Analysis in Microservice-Based Spring Applications
Project Client: The ReSeSS Research Lab, UBC. PI: Prof. Julia Rubin.
Project Description: Security vulnerabilities are flaws in computer systems that weaken the overall security of the system. An example of a recently widespread vulnerability is Log4J, which enables an attacker to execute malicious code on the host machine where the vulnerable application is running. Several tools have been proposed to detect security vulnerabilities. However, existing tools only work for monolithic applications, not microservice-based applications – applications that consist of numerous services communicating with each over the network.
InterSoot is a static analysis tool that constructs a holistic dataflow graph which models the entirety of a given Java Spring microservice-based application. This output dataflow graph can be used in conjunction with existing analysis tools by researchers and security analysts to identify security vulnerabilities and the propagation of taints within distributed microservice applications.
InterSoot’s novel design contribution is that it provides the ability to perform inter-service dataflow analysis for microservice-based applications, whereas existing tools can only analyze monolithic applications. The technical challenges involved in analyzing these microservice-based applications stem from identifying the various forms of obfuscated inter-service communication in Java bytecode, which are the key elements in the propagation of data between microservices.
Project TL-34: Monitoring Nature with LiDAR Software Platform
Project Client: Korotu Technology Inc.
Project Description: Korotu Technology needs a cross-platform desktop application that can rapidly process drone-captured LiDAR data into forest metrics and 3D visuals, and determine the feasibility and limitations of the processes and technologies required to extract forest metrics via digital photogrammetry.
Providing a well-organized code base that will allow our client to produce a viable commercial product that will make forest metrics easily obtainable to conservation groups and communities.
Project TL-63: Noise Detector and Classifier
Project Client: Breeze Labs Inc.
Project Description: The objective of this Capstone project is to employ Machine Learning to detect and categorize various audio sources at road intersections in Vancouver. The end goal of the project is to create a system that can assist the government in reducing CO2 emissions by identifying and monitoring emissions from vehicles. Traffic light cameras are equipped with microphones to capture audio, which is analyzed in real-time to identify sounds such as car horns and sirens. The identified audio is subsequently stored in a database, and sound metrics are computed and presented on a dashboard for easy visualization.