BlockBot


Title: BlockBot
Group: Anne Liu, Anjali Thatte, Kevin Feng, Daniel Martin
Course: exchange course equivalent to CISC 425

Description:
BlockBot is a educational learning application that leverages Augmented Reality to teach children (or even adults) how to program in an interactive and user friendly manner. Students place colored puzzle blocks of code segments together with the goal of generating robot movements. They can then easily simulate their programmed robot in their own rooms through the mixed reality AR camera, where the robot interacts with real world items captured in the camera frame. For instance, you can validate if your code correctly allows the robot to avoid falling off a desk or bump into walls in your room. This application enriches the remote learning experience as it allows students to learn robotics and coding from the comfort of their own homes without any robotics equipment!

 

Intention Prediction in Vehicular Environments


Title: Intention Prediction in Vehicular Environments
Author: Mitch Mathieu
Course: CISC 499

Description: Teaching machines to drive on their own is an ever-evolving task that requires computer algorithms to understand increasingly complex driving situations. Specifically, the ability to predict the near-future actions of other drivers on the road would help prevent our robotic drivers from unnecessary accidents and create a safer driving environment.

For this research project, I used LiDAR and camera data from autonomous vehicles to detect other cars in three-dimensional space and then predict their future positions. The object detection was done using a convolutional neural network trained to detect cars from 3D LiDAR point clouds which produced a 3D bounding box for each car. The future position of each car was predicted by applying a regression model to the current and previous positions of each bounding box.

View Poster (PDF)

Cycle AI: Using Artificial Intelligence to Classify Recyclables


Title: Cycle AI: Using Artificial Intelligence to Classify Recyclables
Group: Michael Fourie, James Gleave, Luis Mangubat, Jean Yaacoub
Course: This project was for QHacks and The Mayor’s Innovation Challenge

Description: Cycle AI is a mobile application that utilizes the power of artificial intelligence to classify recyclables, organics, hazardous waste, as well as regular waste allowing users to properly dispose of their waste. The original model built during QHacks utilized a standard convolutional neural network that could classify only one piece of waste in an image. After receiving some constructive feedback from the City of Kingston judges, the team created an entirely new more advanced convolutional neural network that has the ability to isolate and mask images. This means that users can now take a photo of as much waste as they would like, and Cycle would be able to classify each piece of waste in that photo. This entire project was written in Python, using Kivy for the front-end, and TensorFlow, Keras, and OpenCV for the back-end. Cycle has a built-in achievement system, granting users rewards such as using the app consistently, scanning every category of recyclables, and reaching 100 total scans. This is to incentivize users to use the app more often, furthering their knowledge of proper recycling habits.

Watch the group’s pitch for the Mayor’s Innovation Challenge (starts at 9:50).

More information can be found on the Cycle AI Devpost page.

 

 

Application of Linear Genetic Programming and Metabolomics in Alzheimer’s Disease


Title: Application of Linear Genetic Programming and Metabolomics in Alzheimer’s Disease
Group: Chengyuan Sha
Course: CISC 499

Description:Alzheimer’s disease (AD) is a progressive neurodegenerative disease. There are many people in Canada with this disease because it cannot be diagnosed effectively in the early stage. Metabolomics is the study of low-molecular-weight molecules. These metabolites are a result of complex biological processes, and thus are potential candidates to reflect disease.

Linear Genetic Programming (LGP) is a paradigm of genetic programming that uses a representation of linearly sequenced instructions in automatically generated programs. The term “linear” refers specifically to the structure of the program and does not limit the type of problems that LGP can be used to solve. In this project, I developed a python implementation of LGP with scikit-learn compatible API. I applied this evolutionary learning approach on plasma metabolites data and discovered five key metabolic biomarkers and their interactions. The results demonstrate a disturbance in fatty acid and amino acid metabolism, and the glutamate-glutamine cycle.

View Poster (PDF)

Predicting Tomorrow’s COPD and Asthma ER Visits from Historical Visits and Weather Data


Title: Predicting Tomorrow’s COPD and Asthma ER Visits from Historical Visits and Weather Data
Author: Lixuan Liu
Course: CISC 499

Description: COPD and asthma are respiratory diseases that make breathing difficult and limit the activity levels of individuals. Some of these conditions are made worse by the prevailing weather. Hence, this project aims to investigate the temporal pattern of presentation at ER by patients classified with syndromes asthma and COPD, and to predict tomorrow’s ER visits from previous ER visits data and weather factors for hospitals in Kingston and Windsor. Moreover, ER overcrowding has been seen as a frequent and significant problem. The ability to predict ER visits from prevailing weather factors may provide an opportunity for hospitals to arrange medical resources in advance to ensure that patients will have access to treatments on time and potentially alleviate overcrowding.

View Poster (PDF)

Application of Machine Learning and Metabolomics in Alzheimer’s Disease


Title: Application of machine learning and Metabolomics in Alzheimer’s Disease
Author: Jiaao Chen
Course: CISC 499

Description: Alzheimer’s disease is a neurodegenerative disorder that currently affects half a million Canadians and over 35 million people worldwide. Metabolomic is the study of an entire set of metabolites in a tissue or body fluids like blood or CSF (cerebrospinal fluid) and provides the complete overview of the status of the tissue. Metabolomic is the perfect tool to understand the complex biochemical and biological mechanism of the disease pathology with biomarkers in this case Alzheimer’s disease.

View Poster (PDF)

 

Electric Sheep


Title: Electric Sheep
Group: Amos Cohoe, Aleks Jugovic, Ryan Protheroe
Course: CISC 226

Description: Electric Sheep is a procedurally generated cyberpunk 2D action adventure where the player traverses a maze-like cyberspace, attempting to locate and shut down the corrupted mind of the Artificial Intelligence MainFrame. The player’s charge level is both a measure of health and your number of attacks, so the player must choose their actions wisely. Moving from room to room you encounter a variety of enemies maintained by MainFrame’s central processing unit. Whether you choose to fight or dodge past them, you eventually come to the brain of the computer, and face down against MainFrame itself. Whether you triumph or are defeated depends on your reflexes, but more importantly the choices you made while playing.

Play Electric Sheep Now

WaveNotes


Title: WaveNotes
Group: Rithik Bhatia, Berge Yaacoubian, Sammy Moss, Spencer Neal, Daniel Pang
Course: CISC 325

Description: WaveNotes is a note taking application that lets the user record the audio as well as type their notes. When a class is over, they can use the app to review the notes by previewing the audio of their notes and see what they typed at what time using a timeline. They can then find out when they did not type anything and fill up missing sections of notes.

Download WaveNotes (Mac OS X only)

Artistic Line Rendering of 3D Models


Title: Artistic Line Rendering of 3D Models
Author: Lauren D. Bhagwandat
Course: CISC 499

Description: Non-photorealistic rendering (NPR) generates stylized images that attempt to imitate traditional 2D artistry. A particularly challenging area in NPR is producing line rendering of 3D models in order to effectively portray feature contours in a visually appealing manner. This project presents an efficient algorithm for real-time line rendering of 3D models that programmatically achieves varying thickness based on artistic rules often used in illustration.

Educ[alcul]ate – iOS Academics Tracker


Title: Educ[alcul]ate – iOS Academics Tracker
Author: Jordan Belinsky

Description: Educ[alcul]ate is an iOS app I created following a Python-based proof of concept. The app is designed to help students, of all education levels, keep track of their courses and assignment marks. Included in the app are two calculators and a class tracker.

The weighted average calculator allows for calculating marks based on individual weightings or section weights. The final exam calculator allows for calculating what exam mark is needed for a desired final mark, and what final mark will come from a desired exam mark.

The classes section allows students to create, edit and organize their individual classes. Within each class, students are able to add the titles and corresponding marks of assignments, and keep track of them throughout the term. This can be incredibly useful for schools or classes which don’t use an online grading system.

Throughout this school year, I have been working on a complete rewrite using Apple’s new SwiftUI framework. Support for native dark mode, GPA calculation, and cloud saving are going to be included with the new update, along with a completely reworked user interface. Version 1.1 is available on the App Store as of now, with Version 2.0 likely releasing Summer 2020.

I encourage you to give the app a try if you want to have an easy method of tracking your success through school, or check out the source code if you wish to learn more about how the app works.

Download on the App Store Fork on GitHub