Decoding mental attention from EEG using deep neural networks
Decoding mental attention from electroencephalogram (EEG) via deep learning has gained popularity amongst Brain-Computer Intefaces (BCI) researches over recent years. Many are hoping to build a model that is reliable and accurate to be commercialized in the medical field and thus help many in their...
Saved in:
Main Author: | |
---|---|
Other Authors: | |
Format: | Final Year Project |
Language: | English |
Published: |
Nanyang Technological University
2023
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/165877 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-165877 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-1658772023-04-14T15:37:21Z Decoding mental attention from EEG using deep neural networks Phuah, Jethro An Ping Guan Cuntai School of Computer Science and Engineering CTGuan@ntu.edu.sg Engineering::Computer science and engineering Decoding mental attention from electroencephalogram (EEG) via deep learning has gained popularity amongst Brain-Computer Intefaces (BCI) researches over recent years. Many are hoping to build a model that is reliable and accurate to be commercialized in the medical field and thus help many in their struggle against Attention Deficit Hyperactivity Disorder (ADHD). To gain deeper insights into this field of specialization, this report scrutinized and explored various deep learning models before zooming into Deep Convolutional Neural Network (DeepConvNet) which currently boasts an accuracy of 77.9%. This report dug deeper and examine the factors that lead to its success in model’s performance when compared to its peers like EEGNet or TSception. This process is done through a series of experimentation and fine-tuning, to find the best optimal hyperparameters for the model and provide a detailed analysis for future BCI researchers so that future works can be more streamlined and focused. Our experiments indicate that Depth, Width and Activation Function of the model (in decreasing order) are a few factors that has the largest impact on DeepConvNet’s performance, with the highest absolute change in classification accuracy of 7.4753% against its default parameters. To benefit the potential online usage of the deep learning model, I further explored pruning technologies to compress the model. Bachelor of Engineering (Computer Science) 2023-04-14T01:47:24Z 2023-04-14T01:47:24Z 2023 Final Year Project (FYP) Phuah, J. A. P. (2023). Decoding mental attention from EEG using deep neural networks. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/165877 https://hdl.handle.net/10356/165877 en application/pdf Nanyang Technological University |
institution |
Nanyang Technological University |
building |
NTU Library |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
NTU Library |
collection |
DR-NTU |
language |
English |
topic |
Engineering::Computer science and engineering |
spellingShingle |
Engineering::Computer science and engineering Phuah, Jethro An Ping Decoding mental attention from EEG using deep neural networks |
description |
Decoding mental attention from electroencephalogram (EEG) via deep learning has gained popularity amongst Brain-Computer Intefaces (BCI) researches over recent years. Many are hoping to build a model that is reliable and accurate to be commercialized in the medical field and thus help many in their struggle against Attention Deficit Hyperactivity Disorder (ADHD). To gain deeper insights into this field of specialization, this report scrutinized and explored various deep learning models before zooming into Deep Convolutional Neural Network (DeepConvNet) which currently boasts an accuracy of 77.9%. This report dug deeper and examine the factors that lead to its success in model’s performance when compared to its peers like EEGNet or TSception. This process is done through a series of experimentation and fine-tuning, to find the best optimal hyperparameters for the model and provide a detailed analysis for future BCI researchers so that future works can be more streamlined and focused. Our experiments indicate that Depth, Width and Activation Function of the model (in decreasing order) are a few factors that has the largest impact on DeepConvNet’s performance, with the highest absolute change in classification accuracy of 7.4753% against its default parameters. To benefit the potential online usage of the deep learning model, I further explored pruning technologies to compress the model. |
author2 |
Guan Cuntai |
author_facet |
Guan Cuntai Phuah, Jethro An Ping |
format |
Final Year Project |
author |
Phuah, Jethro An Ping |
author_sort |
Phuah, Jethro An Ping |
title |
Decoding mental attention from EEG using deep neural networks |
title_short |
Decoding mental attention from EEG using deep neural networks |
title_full |
Decoding mental attention from EEG using deep neural networks |
title_fullStr |
Decoding mental attention from EEG using deep neural networks |
title_full_unstemmed |
Decoding mental attention from EEG using deep neural networks |
title_sort |
decoding mental attention from eeg using deep neural networks |
publisher |
Nanyang Technological University |
publishDate |
2023 |
url |
https://hdl.handle.net/10356/165877 |
_version_ |
1764208153010896896 |