<div class="alert alert-note">
 <div class="flex">
 
 <div class="flex-shrink-0 mr-3">
 <img src="/assets/images/icon-information-circle-solid.svg" class="icon" aria-hidden="true" />
 </div>
 
 Note: This Guided Project is combined from parts of our <a target="_blank" href="https://stackabuse.com/courses/data-visualization-in-python/">Data Visualization in Python</a> and <a target="_blank" href="https://stackabuse.com/courses/data-visualization-in-python-with-matplotlib-and-pandas/">Data Visualization in Python with Matplotlib and Pandas</a> courses, and additionally made available as a standalone project. For the full experience, please enroll into the respective course(s).

 </div>
 </div>
 <h2 id="visualizingeegdatawithpythonmatplotlibandseaborn">Visualizing EEG Data with Python - Matplotlib and Seaborn</h2>
In this Guided Project, we'll be building a project based on EEG scans. Remember - when doing data visualization, you have to get familiar with the domain you're working with at least superficially. This will allow you to understand the format of the data you're working with and to interpret the visualizations you're making. We'll be diving into a topic that not everyone has been acquainted with, and it's an extensive topic in and of itself.
We'll be scratching the surface of what EEG is to gain a basic intuition on how it works and how we can interpret the data, before performing any visualizations.
More specifically - we'll be working with two datasets:
<ul>
<li><a target="_blank" href="https://www.kaggle.com/nnair25/Alcoholics">The EEG-Alcohol Dataset</a></li>
<li><a target="_blank" href="https://www.kaggle.com/wanghaohan/confused-eeg">The Confused Student Dataset</a></li>
</ul>
The first dataset was created in a study trying to figure out whether EEG correlates with genetic predisposition to alcoholism, while the second was created to figure out whether EEG correlates with the level of confusion of a student while watching MOOC clips of differing complexity.
<blockquote>
Both of these tasks are best done with machine learning algorithms, which are great making inference from data. However, the first step in any such project would be to properly explore the data visually, through data visualization techniques.
</blockquote>
<h3 id="whatiseeg">What is EEG?</h3>
Electroencephalography (EEG) is the process of recording an individuals brain activity - from a macroscopic scale. It's a non-invasive (external) procedure and collects aggregate, not individual neuronal data. This by all means doesn't mean the procedure is of low quality or inaccurate. What this means is that we see activation data of huge clumps of neurons, corresponding to a singular electrode placed in a certain area. To collect data on individual neurons, we'd need an invasive technology, which inserts channels directly into the brain, which are in physical contact with the neurons themselves. By using EEG and collecting data from a bunch of neurons that fire together - we've got a fairly effective way to correlate neuron activation to certain stimuli without having to perform invasive surgery on a patient.
These electrical signals are strong enough to actually travel through the skull, in a small range. By placing many electrodes on the human scalp - we can capture these signals. EEG allows us to also correlate these signals through time, which allows us to directly correlate certain stimuli with activations of groups of neurons.
There are various EEG electrode configurations - and each channel stems from one or more electrodes. The more channels we have, the more data points we can acquire and analyze. 64-channel EEG headsets aren't cheap and are mainly found in funded labs, however, 1-5 channel headsets can be found commercially and purchased for under $300 dollars, at the time of writing.
While not cheap by most standards - the technology is getting more refined and cheaper year-by-year, and at the very least, it's getting more accessible to the average consumer who'd like to play around with the data they can extract from themselves.
A 64-channel headset typically has an electrode placement of that looks like this:
<img src="https://s3.amazonaws.com/s3.stackabuse.com/media/ebooks/data-visualization-in-python-with-pandas-and-matplotlib/mpl-chapter-7-101.png" alt="Brylie Christopher Oxley, CC0, via Wikimedia Commons">
Brylie Christopher Oxley, CC0, via Wikimedia Commons
The first dataset we'll be working with was made with a device of 64 electrodes, while the second dataset will be a much more &quot;home-like&quot; device with a single channel that measured the activity over the frontal lobe, which stems from voltage differences between three electrodes - one on the forehead and two on the ears. The frontal lobe is very important for voluntary (planned) movement, expressive language, memory, emotions, problem solving and social interaction. In short - it plays a big role in higher order functions that are at play in the human body.
<blockquote>
Note: Keep in mind - we're here for Data Visualization. Our task is to visualize the signals provided in the dataset, and analyze it. Our task isn't to check the validity of the experiment's hypothesis - whatever it may be. Sometimes, these datasets are released without an accompanying &quot;goal&quot;. For instance, a dataset might be created as part of a research endeavor, or it might be created to democratize data and allow others to attempt finding correlations and relationships in it.
</blockquote>
That being said - let's hop in!

David Landup

Domain Research

In this lesson - we'll be using several plot types to explore EEG data, provided to us by the <a href="https://archive.ics.uci.edu/ml/index.php">University of California, Irvine</a>. They host the Machine Learning Repository, which has various datasets collected from and for academic research. All of the datasets they host are public and can be accessed and downloaded by anyone with an internet connection. Certain datasets have a citation policy - so make sure to read the policy before publishing the findings found by exploring a dataset.
We'll be using the <a href="https://archive.ics.uci.edu/ml/datasets/eeg+database">EEG Database Data Set</a>. It was formed during a large-scale study of 122 individuals, and the aim of the study was to examine EEG correlates of genetic predisposition to alcoholism.
<blockquote>
The dataset is attributable to Henri Begleiter at the Neurodynamics Laboratory at the State University of New York Health Center at Brooklyn.
</blockquote>
The individuals were separated into an alcoholic group and control group. To properly visualize data - we have to understand its domain. In this case, knowing the basics of EEG scanning will get us far - we can hardly work with an EEG dataset if we don't know what EEG scanning is, nor what the features are.
Each subject in the trial was shown either one or two stimuli - named S1 and S2. These stimuli were sampled from the <a href="http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.294.1979&amp;rep=rep1&amp;type=pdf">1980 Snodgrass and Vanderwart picture set</a>. When two stimuli were shown - they could be matching or not (S1 = S2), and this feature was also written down in the dataset.

Visualizing "EEG-Alcohol" Data with Matplotlib

The dataset we'll be working with in this lesson is dubbed the <a href="https://www.kaggle.com/wanghaohan/confused-eeg">Confused student EEG brainwave data</a> and is available on Kaggle. It was uploaded by Haohan Wang and used within the <a href="http://www.cs.cmu.edu/~kkchang/paper/WangEtAl.2013.AIED.EEG-MOOC.pdf">Using EEG to Improve Massive Open Online Courses Feedback Interaction</a> research paper by Haohan Wang et al. at Carnegie Mellon University. The aim of their study was to see if we can detect confusion from EEG data or not. If yes - this could mean that MOOC platforms could start supplying students with home EEG devices to wear during lectures. The teachers would then have solid feedback on whether their lectures are confusing or not! Teaching online, teachers have significantly less feedback on the state of the classroom, which can lead to a worse lecturing experience. If nothing else - we can test whether we can figure out if students are confused or not as reliably as with eyesight.
Naturally, pattern-recognition approaches are used to come up with the conclusion - most notably, Machine Learning algorithms are used to find intricate relationships between the data. Also naturally, exploratory data analysis is the first step in this! It's worth noting that Haohan Wang clearly states that binary classification on this dataset &quot;extremely challenging&quot;. In essence, this means that it's extremely challenging to really predict the state of confusion based on the EEG data. This doesn't need to mean that EEG itself is not the technology to use - the equipment and processing algorithms play a huge role in this too! A major thing to note is that this was, after all, a single-channel EEG device, which limits the accuracy of the results. Because of this, we probably won't be able to see high correlation between features and the state of student confusion. If there were high, clear cut correlation, it wouldn't be very challenging to perform binary classification on the dataset.

Visualizing Confused Student EEG Brainwave Data with Seaborn

That concludes this Guided Project - &quot;Data Visualization in Python: Visualizing EEG Brainwave Data&quot;. Thank you for taking a ride with us!
<blockquote>
Online education is spreading through the world, and is becoming an increasingly important part of many lives. We believe that accessible, high-quality resources can help empower people that build tomorrow, and remain guided by that goal.
</blockquote>
At StackAbuse, we believe that learning is not a one-stop time investment. It's life-long. Especially in the volatile and rapidly changing world of Computer Science and Software Engineering. So, we've pledged to update our courses, guides, and other upcoming material to keep the pace of progress in the field. Software is updating - it's only fitting that learning resources are updating as well.
Thank you for purchasing &quot;Data Visualization in Python: Visualizing EEG Brainwave Data&quot;! We hope that it has brought a ton of value to you so far, and know that it will continue to do so as you dive further in to this topic.
<blockquote>
Now, we'd like to ask you to get involved in improving the next version our material.
</blockquote>
We believe that high-quality resources and education is community-driven and that minor (or major) contributions from each member results in a wonderful learning oasis. For this, feedback is crucial.

Thank You for Supporting Online Education

Jovana Ninkovic

Electroencephalography (EEG) is the process of recording an individual's brain activity - from a macroscopic scale. It's a non-invasive (external) procedure and collects aggregate, not individual neuronal data. This by all means doesn't mean the procedure is of low quality or inaccurate. What this means is that we see activation data of huge clumps of neurons, corresponding to a singular electrode placed in a certain area.
To collect data on individual neurons, we'd need an invasive technology, which inserts channels directly into the brain, which are in physical contact with the neurons themselves. By using EEG and collecting data from a bunch of neurons that fire together - we've got a fairly effective way to correlate neuron activation to certain stimuli without having to perform invasive surgery on a patient.
We'll be scratching the surface of what EEG is to gain a basic intuition on how it works and how we can interpret the data, before performing any visualizations.
More specifically - we'll be working with two datasets:
<ul>
<li><a target="_blank" href="https://www.kaggle.com/nnair25/Alcoholics">The EEG-Alcohol Dataset</a></li>
<li><a target="_blank" href="https://www.kaggle.com/wanghaohan/confused-eeg">The Confused Student Dataset</a></li>
</ul>
The first dataset was created in a study trying to figure out whether EEG correlates with genetic predisposition to alcoholism, while the second was created to figure out whether EEG correlates with the level of confusion of a student while watching MOOC clips of differing complexity.
<blockquote>
Both of these tasks are best done with machine learning algorithms, which are great making inference from data. However, the first step in any such project would be to properly explore the data visually, through data visualization techniques.
</blockquote>

 <div class="alert alert-note">
 <div class="flex">
 
 <div class="flex-shrink-0 mr-3">
 <img src="/assets/images/icon-information-circle-solid.svg" class="icon" aria-hidden="true" />
 </div>
 
 Note: This Guided Project is combined from parts of our <a target="_blank" href="https://stackabuse.com/courses/data-visualization-in-python/">Data Visualization in Python</a> and <a target="_blank" href="https://stackabuse.com/courses/data-visualization-in-python-with-matplotlib-and-pandas/">Data Visualization in Python with Matplotlib and Pandas</a> courses, and additionally made available as a standalone project. For the full experience, please enroll into the respective course(s).

 </div>
 </div>