What's Elodie Been Tinkering With?

Portfolio

Seeking a Co-op/Internship for May 2022 in Ottawa, Toronto, or Waterloo.

I am at university in the hope of working in the field of Artificial Intelligence. I find the workings of the mind fascinating, and believe attempting to recreate the human mind is a great way to learn more about how we think.

**Some of my technical skills include:**

    👩‍💻 Well-practiced with a variety of languages such as Java, C/C++ and Python  
    👩‍💻 Exposure to AI development using tools such as TensorFlow, Jupyter, and scikit-learn  
    👩‍💻 Experience in web development, familiar with JavaScript, HTML and CSS
    👩‍💻 Previous work with Node.js servers and MongoDB databases  
    👩‍💻 On-going practice with 3D simulation software using Java and Webots  
    👩‍💻 Thorough understanding of Linux and Windows environments  

***

**Some of my soft skills include:**

    🧠 Great analytical skills and attention to detail, especially with data and code  
    🧠 Fast and willing learner; can learn platforms and frameworks quickly  
    🧠 Strong communication, advanced fluency in English  
    🧠 Great leadership skills, honed through previous supervisory roles  
    🧠 Excellent time management  


Enthusiastic about Cognition and AI

About Elodie

###
##### Email: <elodie.kane@carleton.ca>
##### LinkedIn: [elodie-kane](https://www.linkedin.com/in/elodie-kane/)
##### GitHub: [elodiekane](https://github.com/elodiekane)


Contact Me

🧠 Enthusiastic about Cognition and AI


Hi, I'm Elodie Kane

Recent Projects

Home

This partnered project involved designing and implementing a 5-layer Convolutional Neural Network (CNN) for translating audio data into visual spectrograms.

Being able to identify sounds could be very useful in technology for those that are hearing impaired. This real-world application was a key motivator for creating and training a network that could correctly classify a range of urban sound audio clips.

Dataset: [urbansound8k](https://urbansounddataset.weebly.com/urbansound8k.html)

There were 10 classes within this audio dataset. The distribution can be seen below:

![](/images/classesNN.PNG)

We formatted the data by translating the audio waves into spectrograms and then inputting the spectrogram images into the CNN model. Below is an example audio wave of a dog barking, and its accompanying spectrogram:

![](/images/NN_AudioWave-e8c473ed.PNG)![](/images/NN_Spectrogram-922e481c.PNG)

Next, we trained and evaluated using 10-fold cross validation, and the best accuracy was saved for any future testing.


Written in a Jupyter Notebook using Google Colab and Tensorflow

Sound Classifier Neural Network

Movie Database is an IMDb-inspired web application created using a node.js server that allows users to browse and contribute information on various movies, actors and other users.

*   This application was developed in the context of Carleton's computer science course: Fundamentals of Web Applications.

*   Built using Express for the backend and MongoDB as a NoSQL database program.

*   Utilized Pug to make it easier to write re-usable dynamic code for HTML, and easily render information pulled from the database.


RESTful design utilizing a Node.js server and MongoDB database

Movie Database Web Application

Created a simulation where a Roomba-like robot identifies its environment through the use of cameras, proximity sensors, and accelerometers.

The image below shows the robot in its environment, and the top left square shows the robot's camera view when attempting to identify the red balls.

![](/images/weBots-0c989424.JPG)

Once a red ball is identified, the robot navigates its environment with left and right motors to push the balls off the edge of the map.


Written in Java, using Webots - 3D robotics simulation software

Robot Homing & Tracking Simulation

Designed and implemented a Convolutional Neural Network to identify and classify 60,000 32x32 images.

**Dataset:** [CIFAR-10](https://www.cs.toronto.edu/~kriz/cifar.html)

Below is an image demonstrating the 10 different classes that the network was able to identify:

![](/images/CIFAR.JPG)

We achieved accuracy scores of 91% for the training data and an 80% overall testing accuracy.

After creating an accurate model, we then implemented an interactive app that allowed users to classify their own images.

Below is a screenshot of the network correctly classifying my team member's dog:

![](/images/AI_Dog-67270b0f.PNG)


Written in Python

Image Classifier Neural Network

**This is a paragraph**. Pellentesque habitant morbi *tristique senectus et netus et malesuada* fames ac turpis egestas. Vestibulum [tortor quam](https://www.google.com), feugiat vitae, ultricies eget, tempor sit amet, ante. Donec eu libero sit amet quam egestas semper. Aenean ultricies mi vitae est. Mauris placerat eleifend leo. Quisque sit <mark>amet est et sapien ullamcorper</mark> pharetra. Vestibulum erat wisi, condimentum sed, commodo vitae, ornare sit amet, wisi.

# This is an H1

Quisque facilisis erat a dui. Nam malesuada ornare dolor. Cras gravida, this is marked text ornare, erat elit consectetuer erat, id egestas pede nibh eget odio. Proin tincidunt, velit vel porta elementum, magna diam molestie sapien, non aliquet massa pede eu diam. Aliquam iaculis. Fusce et ipsum et nulla tristique facilisis.

## This is an H2

Lorem ipsum dolor sit amet, consectetuer adipiscing elit. Morbi commodo, ipsum sed pharetra gravida, orci magna rhoncus neque, id pulvinar odio lorem non turpis. Nullam sit amet enim. Suspendisse id velit vitae ligula volutpat condimentum. Aliquam erat volutpat. Sed quis velit. Nulla facilisi. Nulla libero.

### This is an H3

Lorem ipsum dolor sit amet, consectetuer adipiscing elit. Morbi commodo, ipsum sed pharetra gravida, orci magna rhoncus neque, id pulvinar odio lorem non turpis. Nullam sit amet enim. Suspendisse id velit vitae ligula volutpat condimentum. Aliquam erat volutpat. Sed quis velit. Nulla facilisi. Nulla libero.

#### This is an H4

Quisque facilisis erat a dui. Nam malesuada ornare dolor. Cras gravida, diam sit amet rhoncus ornare, erat elit consectetuer erat, id egestas pede nibh eget odio. Proin tincidunt, velit vel porta elementum, magna diam molestie sapien, non aliquet massa pede eu diam. Aliquam iaculis.

## Quoting

Lorem ipsum dolor sit amet, consectetuer adipiscing elit.

>Creativity is allowing yourself to make mistakes. Design is knowing which ones to keep. <cite>Scott Adams</cite>

Morbi commodo, ipsum sed pharetra gravida, orci magna rhoncus neque, id pulvinar odio lorem non turpis. Nullam sit amet enim. Suspendisse id velit vitae ligula volutpat condimentum. Aliquam erat volutpat. Sed quis velit. Nulla facilisi. Nulla libero.

***

## Unordered Lists

+ Donec non tortor in arcu mollis feugiat
+ Lorem ipsum dolor sit amet, consectetuer adipiscing elit
+ Donec id eros eget quam aliquam gravida
+ Vivamus convallis urna id felis
+ Nulla porta tempus sapien

## Ordered Lists

1. Donec non tortor in arcu mollis feugiat
2. Lorem ipsum dolor sit amet, consectetuer adipiscing elit
3. Donec id eros eget quam aliquam gravida
4. Vivamus convallis urna id felis
5. Nulla porta tempus sapien

## Video Embeds

<iframe width="640" height="360" src="https://www.youtube.com/embed/wEG7x7jRhNQ" title="YouTube video player" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture" allowfullscreen></iframe>

## Code Blocks

Blocks of code are either fenced by lines with three back-ticks, or are indented with four spaces.

```

body {
  color:red;
}
```

## Tables

<table>
    <caption>Table with thead, tfoot, and tbody</caption>
  <thead>
    <tr>
      <th>Header content 1</th>
      <th>Header content 2</th>
    </tr>
  </thead>
  <tbody>
    <tr>
      <td>Body content 1</td>
      <td>Body content 2</td>
    </tr>
  </tbody>
  <tfoot>
    <tr>
      <td>Footer content 1</td>
      <td>Footer content 2</td>
    </tr>
  </tfoot>
</table>

The style guide provides you with a blueprint of default post and page styles. The style guide is also a great reference for suggested typographic treatment and styles for your content.

Style Guide

Thank you for contacting me! I will get back in touch with you soon.

**Have a great day!**
