Project AI-18: Dynamic Parking Signage V3
Project Client: UBC Parking Services
Project Description: The Dynamic Parking Signage system is an innovative solution that can help UBC’s parking department manage their parking spaces more efficiently while reducing traffic congestion on campus. The system is designed to be versatile and adaptable, allowing it to display customized content based on the current needs of the parking lot, such as disability parking, reserved spots for specific individuals or events, and delivery zones.
The use of LED matrix displays ensures that the signage is clear and legible, providing drivers with clear instructions and information. The system also features LTE wireless capability, which means that the parking signs can be easily updated and customized through a web app, ensuring that the information displayed is always up-to-date and accurate.
Additionally, the signs are powered by batteries and solar panels, making them a sustainable and eco-friendly option. This also means that the signs are easy to install in any lot without the need for costly electrical infrastructure.
The system also includes a parking occupancy sensor, allowing the parking department to monitor the availability of parking spaces and make informed decisions about managing parking capacity.
Overall, the Dynamic Parking Signage system is a valuable tool that can help UBC’s parking department improve the usage of their parking spaces, reduce traffic congestion, and enhance the overall experience of drivers on campus. If you are interested in learning more about this project, please contact email@example.com.
Project AI-26: Avionics Integration Test Bench
Project Client: KF Aerospace
Project Description: The Avionics Integration Test Bench is a product that allows a user to communicate with avionics equipment using a computer. It is an adapter device with a software GUI that allows the user to emulate various aircraft parameters onto equipment under test and read from the equipment simultaneously. This allows our client, KF Aerospace, to emulate bi-directional data communication between avionics equipment and experiment with novel integration techniques prior to undertaking the expensive process of modifying an in-service aircraft. Codenamed AeroSim, this product helps speed up the time consuming and expensive process of testing avionics equipment integration.
Contact info: Anthony Wang: firstname.lastname@example.org ; Andrew Hanlon: email@example.com ; Isabelle André: firstname.lastname@example.org ; Patric McDonald: email@example.com ; Nursultan Tugolbaev: firstname.lastname@example.org
Project HA-58: Nimba IoT Platform
Project Client: Hedgehog Technologies Inc.
Project Description: The Nimba IoT Dashboard makes data from remote energy assets serviced by Hedgehog Technologies’ Nimba microgrid controllers securely accessible over the Internet.
Nimba microgrid controllers optimize renewable energy systems to extend their lifespans. The controller manages the microgrid’s energy consumption behavior by monitoring and controlling microgrid assets. As Nimba controllers are deployed in remote locations across Canada that experience harsh weather conditions year-round, Hedgehog Technologies currently uses a remote desktop to view Nimba controller data for troubleshooting. However, the growing body of stakeholders who need access to this data, including customers and clients, has motivated a more flexible and robust solution to distribute Nimba controller data.
This is where the Nimba IoT Dashboard comes in. The Nimba IoT Dashboard pulls data generated by a Nimba controller deployment and displays it on a website. Stakeholders can log into the website to view, analyze, visualize, and remotely monitor data over the Internet. The system is also designed to minimize the loss of Nimba controller data during Internet outages, which are common to locations where Nimba controllers are deployed. This ensures minimal data loss when troubleshooting Nimba controllers, increasing their reliability. By enabling more flexible and robust monitoring of Nimba microgrid controllers, the Nimba IoT Dashboard improves energy security for communities that rely on microgrids serviced by Nimba controllers.
Project HA-75: DC Non-Contact voltmeter
Project Client: Rampart Detection Systems Ltd
Project Description: Maintenance in aerospace and automotive industries relies on piercing probes to measure the voltages of an electrical system and inspect component functionality. However, this method can cause corrosion in the conductive core of the wire, and this can potentially affect the functionality of the vehicles. This project aims to solve this issue by inventing a design that allows inspection without damage to the wire insulation and is designed for engineers and technicians in those industries specified above.
As this is a R&D project, our main technical challenge was to come up with and understand a design that the prototype is able to measure the voltage without touching the conductor part of the wire and without getting affected by the thickness of the wire insulation. Also selecting the right components for the design such as a microcontroller, firmware, and other electrical components was challenging.
Contact Information: email@example.com
Project JY-07: ‘PhysViz’: Gamification of a mobile application for physiotherapy
Project Client: UBC Tendon Injury Prevention and Rehabilitation Research Group
Project Description: PhysViz is a project focusing on providing a non-invasive treatment option to patients suffering from Achilles tendinopathy, an injury stemming from the overuse of the Achilles tendon. With the usage of mobile (patient-facing) and web (clinician-facing) applications and a Bluetooth load-monitoring device, the project hopes to facilitate tendon recovery and strengthening through exercise therapy.
This project, in collaboration with the UBC Tendon Research Group, is a continuation of previous capstone projects. The existing solution we received from previous teams was a working software system consisting of a web app, a mobile app, a backend, and hardware that passes data around with minimum efficiency, security, and user satisfaction.
Our main design contributions included strengthening the security of the system to guard against common attacks, improving user acceptance to boost user engagement, visualizing the data to help clinicians make faster diagnoses, re-architecting the software for faster performance and better reusability, fixing existing bugs, and adding some quality-of-life tools for future students/developers working on the project.
Contact information: firstname.lastname@example.org
Project PB-06: Building Secret Support Services for UBC Library
Project Client: UBC Library – Chapman Learning Commons
Project Description: 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.
Contact Information: Azwad Sadman: email@example.com ; Daniel Lee: firstname.lastname@example.org ; Jordan Lee: email@example.com ; Ross Mojgani: firstname.lastname@example.org ; VIctor Parangue: email@example.com
Project PB-57: Trace-based Debugging for Java Development Environments
Project Client: UBC ECE, ReSeSS Research Lab, PI: Prof. Julia Rubin.
Project Description: Studies show that programmers spend 35-50% of their time on validating and debugging their programs. Traditional debuggers require programmers to step through hundreds of lines of code, many of which may not be relevant to the bug. Our solution, Debugger++, is an IntelliJ Plugin which is an upgraded version of the traditional IntelliJ debugger, designed to help programmers debug faster and more accurately by using the power of dynamic slicing. During a debugging session, our tool allows the user to select the buggy line as the slicing criterion, and automatically grays out all lines that are irrelevant to the bug during program execution to bring focus to lines that have a real impact on the bug. Debugger actions such as Step Into and Step Over also automatically skip lines irrelevant to the bug, potentially saving hours on debugging. In addition, Debugger++ includes new tabs that show critical dynamic slicing information such as the control and data dependencies for each line in the slice, as well as a dependencies graph for better visualization. Our project is implemented by integrating Slicer4J, a dynamic slicing tool developed by our client, the ReSSeS Lab, into IntelliJ’s debugger.
Project SF-39: Software Platform for Surgical Dental Implants
Project Client: Prisman Research Laboratory, Department of Surgery, UBC
Project Description: Patients with bone cancer of the jaw often require surgery to remove the cancer and recreate the jaw to help restore the patient’s quality of life. Vancouver General Hospital currently uses a custom virtual surgical planning (VSP) software platform to pre-plan these surgeries, but it has limitations. The current model of VSP reconstructs the jaw using the outer contour, but it is suboptimal for dental implant placements, leading to poor chewing and eating function for patients. Additionally, the current VSP lacks measurement program support, necessitating the export of the model to a measurement platform, resulting in an inconsistent and error-prone workflow.
The two main objectives of our project were to 1) bridge the gap between jaw reconstruction surgery and dental implantation surgery and 2) remove unnecessary platform switching.
Through research and discussion with dental surgeons and a jaw reconstruction surgeon, our team updated the VSP to address dental-focused issues by reconstructing the jaw using the contour of the patient’s occlusion. We also integrated measurement tools into the reconstruction platform. The updated VSP is designed to be intuitive for technicians working on virtual jaw reconstruction surgery, and our implementation details can be found in our video.
Contact information: Han Cho: firstname.lastname@example.org ; Eric Liu: email@example.com ; Kingston Chen: firstname.lastname@example.org ; Vincent Cen: email@example.com ; Vincent Yan: firstname.lastname@example.org
Project SF-70: Machine learning models for protein design and drug discovery
Project Client: Gandeeva Therapeutics
Project Description: The purpose of our project is to deliver an adaptable framework to our client, Gandeeva Therapeutics, to allow them to expedite, automate, and increase the success rate of selecting resolvable protein fragments. Resolvable protein fragments are sub-sequences of a protein that can be successfully imaged, where the full length protein cannot be. This task is part of Gandeeva’s drug discovery pipeline, but is currently done manually by experts and is a slow process with a success rate of less than 50%. Our solution aims to alleviate this bottleneck and increase the cost-efficiency of the fragment-selection process.
- A graphical user interface used to quickly and easily visualize resolvable protein fragment candidates.
- A machine learning module to produce performance metrics and facilitate the evaluation of machine learning models specific to the task of predicting resolvable protein fragments. This set of metrics helps quickly compare different ML models when selecting an appropriate model for this task.
- A data curation process to create maintainable and clean datasets ready to be inputted into the machine learning workflow.