Proposal submission for the 2024/2025 cohort is OPEN
Please contact Paul Lusina (capstones@ece.ubc.ca) if you have questions about our next Capstone cohort, or check out our Capstone Client FAQ Page.
What should a project look like?
Open-ended: Students must be able to exercise a fair amount of choice in the design and implementation strategies. You may impose reasonable constraints on the design and implementation, such as conformance to tools and strategies; however, this is not a case in which students will simply execute a given design.
Feasible: The project should be able to be completed by a group of four to six students within the timing and effort allocated to the project course: part-time for 26 weeks (1000 to 1300 person-hours). There must be enough work to engage the team from September until April.
Backburner project: No critical business outcome should rely on the success of the project. It should be something that you thought “if some day we have some spare time, wouldn’t it be nice to try to … [fill in the blank].”
Relevant: The topic has focuses on computer engineering, electrical engineering, or biomedical engineering technologies.
Work environment: Most of the work will be done at UBC and does not require students to be constantly present at your location.
Client Expectations
Clients are expected to dedicate time to explain the problem to the student team, and to help evaluate progress. There may be opportunities along the way if you wish to mentor the team without unduly restricting their freedom of action, as indicated above.
The first page provides information to help students decide whether to bid for your project. The second page provides more detail about the people with whom they would be working.
Background: Briefly explain the domain and the context in which you are trying to solve an engineering problem. (2-3 sentences)
Objectives: Briefly explain what problem you would like the student to solve, and what constraints and non-functional requirements they should be aware of. Note that detailed functional requirements will be jointly defined between you and the student team early in the project and do not need to be detailed here.
Major Deliverables: Explain what you would need to see to declare success in April: a prototype, a model, a computer simulation, validated design solution, a set of blueprints, etc.
You may want to include descriptions of the following special considerations:
- Special equipment and tools needed
- Required interfaces to already existing elements you have
- The need for a formal Intellectual Property agreement with UBC and the students
Submission Review Process
Before August 15: proposals will be reviewed and feedback given to authors. Feedback focuses on project scope and how to make the project attractive to students.
Before September 3: proposals will be reviewed but only limited feedback will be possible before the course starts.
After September 3: will be considered for the next year’s capstone cohort.
Due to the large volume of proposals we usually receive, our proposal review process can take up to two months. We suggest you submit your proposal as soon as practicable. Our review team will perform a static review, and if your proposal appears appropriate for the Capstone Program, the team will contact you for further clarifying discussions. We will not require face-to-face meetings, and we expect to complete the proposal review process by September 3, at which time you will be notified of our results. If selected, you will have the opportunity to pitch your project to the full Capstone student body and in an audio-visual presentation event scheduled for a date TBD in the first two weeks of September.
Feedback will typically be given within two weeks, but no later than September 3.
You may find some inspiration in the following examples:
1) Background information:
Image-related tasks such as object recognition and tracking have been a very popular
application of Machine Learning (ML). Most of this has been done either off-line using powerful
GPUs, or (to a limited extent) using specialized accelerators built for specific devices (e.g.,
smartphones). In this project, we would like to explore the possibilities for using low-power
reprogrammable computing (FPGAs) in independent mobile deployments (drones). We envision
eventual applications to disaster response (e.g., looking for survivors), wildlife management
(e.g., tracking wildlife), farming (e.g., tracking farm animals’ populations), etc.
2) Main Objectives:
The overall objective is to assess the viability, and determine the constraints, of airborne
autonomous object tracking applications by developing a proof-of-concept drone-hosted FPGAbased
video processing platform (see Deliverables). The project should promote knowledge and
expertise in the design of FPGAs for object tracking in particular and machine learning
applications in general. To this end, all code and designs produced during the project will be
released using the open source MIT license.
3) Main Deliverables:
The project will be expected to deliver a remotely-controlled flying drone that hosts a small
video camera and an FPGA (as powerful as feasible given the power constraints), plus any
software / hardware source code / scripts required to program / use the drone.
Within the drone, the video stream should be fed to the FPGA, which should host a deep
learning model (likely a CNN) to identify and track objects in the camera's field of view, and
both the video stream and the FPGA output (bounding boxes, classification results, etc.) should
be transmitted to a ground-based host (e.g., laptop or phone) and displayed to the user (as, e.g.
bounding boxes superimposed on the image)
1) Background information:
Current patient monitoring technology is costly and inconvenient for both the patients and the
caretakers. Typically, patients are connected, via sensors and wires, to a large patient monitor.
This monitor alone can cost thousands of dollars. Also, because of the wires and bulk of the
monitoring systems, patients are restricted in their freedom. Hence, there is a need to improve
upon existing technology for patient monitoring, especially for “at home” use.
2) Main Objectives:
Our organization is planning to purchase new monitoring equipment for application in our
facilities and for at-home care of our patients. Our doctors and nurses currently have very little
experience with emerging technologies related to patient monitoring.
The aim of this project is to engage our medical staff in the design of a patient monitoring
solution in order to identify what is possible. At the end of the project, our staff should be able
to articulate the requirements they need for a patient monitoring system. In other words, our
staff should become ‘expert’ customers.
3) Main Deliverables:
The project should deliver a product that can test the following functionality:
• Monitoring of patient vital signs including alerts via wireless sensors
• Communication of the patient vital signs to the medical staff via a phone app
• Identification and testing of the limitations of the wireless sensing equipment such as
range, reliability, security
• Final report including an assessment of current patient monitoring solutions.
1) Background information:
This project solves a real problem in the industry and implements a real business case.
If you were an entrepreneur with a team of IoT experts, this is one project that could lead to a
very successful business. With this project, get ready to tackle a real industrial problem with the
help of the engineers from a global communications leader.
The monitoring of mobile assets everywhere on earth including in areas not covered by
cellular networks (like in the open sea) is a real problem in the industry with no satisfying
solution so far. This project aims at prototyping a mobile vehicle tracking & monitoring product
that can be used as an emergency alert system as well.
2) Main Objectives:
The successful completion of this project will enable our company to test the asset monitoring
features with potential users, and provide our company insight into the performance limits of
the product.
The resulting prototype will be part of our company’s assessment of the technical feasibility of
a mobile asset monitoring product. Lesson learned from the product design will be used to
inform further product design iterations in the event that our company chooses to pursue this
technology.
3) Main Deliverables:
Upon successful completion of this project our company expects a mobile asset tracking device
that integrates the following sub-systems:
• An array of sensors allowing for tracking and monitoring of the asset. The sensor suite
functionality is to be determined by the Capstone team through research of similar
products
• A microprocessor with associated firmware for recording, analyzing and communicating
the sensor information
• A cloud database for storing historical asset information. The Capstone team is
responsible for designing an appropriate database structure for collecting and
organizing the IoT information collected.
• A mobile app that will communicate the asset’s status and alert the user if there is an
emergency.
• All code developed during the project.
1) Background information:
Our organization produces furniture that customers can create online using an intuitive three -
dimensional modelling app. Users can define their furniture’s dimensions, colour and style.
They can even mix various styles or features from our extensive catalogue of products to make
an item as unique as their home. Our furniture modelling app is incredibly successful; however,
a certain portion of our customers are overwhelmed by the range of options available.
2) Main Objectives:
Our company wants to explore the application of chatbots to help certain customers that find
the furniture creation process complex or overwhelming. We currently do not know how our
customers would react to a chatbot, nor how well such a product could facilitate in the creation
of custom furniture designs. The project should provide our company insight to both our
customers’ preferences as well as an introduction to the design, capabilities and limitations of
chatbots to our company. Our IT department will use the project’s results to determine if this
technology is appropriate for our company.
3) Main Deliverables:
The primary deliverable of the project is a chatbot deployed in an SAAS module. The bot should
be able to guide a client in the task of designing a chesterfield (sofa) using an AI or ML module.
The bot should interact using human-like responses. By the end of the chatbot session the
client should have a sofa design that matches their taste and home environment.
The chatbot should also include metrics and questions to gauge the client’s satisfaction with:
• The chatbot guide
• The final sofa designs
The chatbot must integrate with our current furniture design app for example using API REST
calls. All code and testing results should be delivered to our company upon the project
completion.
Students are encouraged to develop the chatbot according to their own interests and expertise
by expanding support to different types of furniture.
Intellectual Property
The project is not strictly confidential. Although the resulting Intellectual Property will belong to you, the students need to be able to write reports and to make presentations to instructors and peers at UBC for grading.
You will find our standard IP transfer agreement and Non Disclosure agreement below. Note that only these text can be used for capstone projects. Due to volume, UBC will not negotiate specific texts for each project or client.
2022 NDA and IP Agreements:
Undergraduate Project NDA Agreement 2022.pdf | ||
Undergraduate Project NDA Agreement 2022.doc | ||
Undergraduate Project IP Agreement 2022.pdf | ||
Undergraduate Project IP Agreement 2022.doc |