29 May - skipped

Meetings

Link to page

29 May - Meeting

Test maximum bandwidth:

Before starting expremeient:

----------------------------------------------------------- Server listening on 5201 ----------------------------------------------------------- Accepted connection from 192.168.0.45, port 60386 [ 5] local 192.168.0.143 port 5201 connected to 192.168.0.45 port 60400 [ ID] Interval Transfer Bitrate [ 5] 0.00-1.00 sec 33.5 MBytes 281 Mbits/sec [ 5] 1.00-2.00 sec 36.1 MBytes 303 Mbits/sec [ 5] 2.00-3.00 sec 36.5 MBytes 306 Mbits/sec [ 5] 3.00-4.00 sec 36.7 MBytes 307 Mbits/sec [ 5] 4.00-5.00 sec 36.4 MBytes 305 Mbits/sec [ 5] 5.00-6.00 sec 36.5 MBytes 306 Mbits/sec [ 5] 6.00-7.00 sec 36.5 MBytes 307 Mbits/sec [ 5] 7.00-8.00 sec 36.0 MBytes 302 Mbits/sec [ 5] 8.00-9.00 sec 35.9 MBytes 301 Mbits/sec [ 5] 9.00-10.00 sec 36.5 MBytes 306 Mbits/sec [ 5] 10.00-10.12 sec 4.25 MBytes 307 Mbits/sec - - - - - - - - - - - - - - - - - - - - - - - - - [ ID] Interval Transfer Bitrate [ 5] 0.00-10.12 sec 365 MBytes 303 Mbits/sec re

During expremeient:

----------------------------------------------------------- Server listening on 5201 ----------------------------------------------------------- Accepted connection from 192.168.0.45, port 42284 [ 5] local 192.168.0.143 port 5201 connected to 192.168.0.45 port 42290 [ ID] Interval Transfer Bitrate [ 5] 0.00-1.00 sec 22.0 MBytes 184 Mbits/sec [ 5] 1.00-2.00 sec 23.8 MBytes 200 Mbits/sec [ 5] 2.00-3.00 sec 22.6 MBytes 190 Mbits/sec [ 5] 3.00-4.00 sec 22.4 MBytes 188 Mbits/sec [ 5] 4.00-5.00 sec 23.9 MBytes 200 Mbits/sec [ 5] 5.00-6.00 sec 21.0 MBytes 176 Mbits/sec [ 5] 6.00-7.00 sec 22.8 MBytes 191 Mbits/sec [ 5] 7.00-8.00 sec 23.6 MBytes 198 Mbits/sec [ 5] 8.00-9.00 sec 23.9 MBytes 200 Mbits/sec [ 5] 9.00-10.00 sec 24.1 MBytes 202 Mbits/sec [ 5] 10.00-10.17 sec 3.57 MBytes 177 Mbits/sec - - - - - - - - - - - - - - - - - - - - - - - - - [ ID] Interval Transfer Bitrate [ 5] 0.00-10.17 sec 234 MBytes 193 Mbits/sec receiver

After finishing expremeient:

----------------------------------------------------------- Server listening on 5201 ----------------------------------------------------------- Accepted connection from 192.168.0.45, port 43062 [ 5] local 192.168.0.143 port 5201 connected to 192.168.0.45 port 43072 [ ID] Interval Transfer Bitrate [ 5] 0.00-1.00 sec 2.60 MBytes 21.8 Mbits/sec [ 5] 1.00-2.00 sec 6.82 MBytes 57.2 Mbits/sec [ 5] 2.00-3.00 sec 12.4 MBytes 104 Mbits/sec [ 5] 3.00-4.00 sec 17.0 MBytes 143 Mbits/sec [ 5] 4.00-5.00 sec 18.1 MBytes 152 Mbits/sec [ 5] 5.00-6.00 sec 19.5 MBytes 164 Mbits/sec [ 5] 6.00-7.00 sec 20.1 MBytes 169 Mbits/sec [ 5] 7.00-8.00 sec 22.2 MBytes 186 Mbits/sec [ 5] 8.00-9.00 sec 21.7 MBytes 182 Mbits/sec [ 5] 9.00-10.00 sec 21.0 MBytes 176 Mbits/sec [ 5] 10.00-10.10 sec 2.24 MBytes 182 Mbits/sec - - - - - - - - - - - - - - - - - - - - - - - - - [ ID] Interval Transfer Bitrate [ 5] 0.00-10.10 sec 164 MBytes 136 Mbits/sec receiver

⁠

EEGNet

Description: EEGNet is a compact convolutional neural network designed for EEG-based brain-computer interface applications. It effectively captures spatial and temporal features of EEG signals.

Paper:

EEGNet: A Compact Convolutional Neural Network for EEG-based Brain-Computer Interfaces⁠

⁠

GitHub:

EEGNet Repository⁠

⁠

Goal: To provide a lightweight yet efficient model for various BCI tasks.

Performance Metrics: Generally achieves around 60-70% accuracy on various EEG classification tasks, but this can vary significantly depending on the dataset.

Accuracy of the network on the test set: 57.52%

DeepConvNet

Description: DeepConvNet is a deep convolutional neural network tailored for EEG signal processing, emphasizing capturing more complex patterns through multiple convolutional layers.

Paper:

Deep learning with convolutional neural networks for EEG decoding and visualization⁠

⁠

GitHub:

DeepConvNet Example⁠

⁠

Goal: To improve the classification performance of EEG signals by using a deeper network architecture.

Performance Metrics: Typically achieves accuracy around 70-80% on BCI competition datasets.

Accuracy of the network on the test set: 82.58%

ShallowConvNet

Description: ShallowConvNet is a shallow convolutional neural network designed to serve as a benchmark for deep learning models on EEG data.

Paper:

Deep learning with convolutional neural networks for EEG decoding and visualization⁠

⁠

GitHub:

ShallowConvNet Example⁠

⁠

Goal: To provide a baseline performance to compare against deeper models like DeepConvNet.

Performance Metrrics: Generally achieves around 60-70% accuracy on various EEG classification tasks.

Accuracy of the network on the test set: 81.33%

EEGTransformer

Description: EEGTransformer leverages the power of transformer architectures to capture the temporal dependencies in EEG signals. This model is based on the Transformer architecture, which has shown significant success in various sequence-to-sequence tasks.

Paper: [Not directly available; inspired by the success of Transformer models in other domains]

GitHub:

A general transformer repository⁠

⁠

Goal: To utilize the attention mechanism for capturing long-range dependencies in EEG signals.

Performance Metrics: Generally achieves high accuracy in various EEG classification tasks, but specific performance will depend on the dataset.

Accuracy of the network on the test set: 72.37%

EEG-Transformer by eeyhsong

Description: This project applies a Transformer (ViT) model to 2-D physiological signal (EEG) classification tasks, which can be adapted for various tasks including driving intention prediction.

GitHub Repository:

https://github.com/eeyhsong/EEG-Transformer⁠

⁠

Key Features:

Utilizes the attention mechanism to enhance spatial and temporal features.

Applies common spatial pattern (CSP) for feature enhancement.

Performance: The repository mentions achieving state-of-the-art performance in multi-classification of EEG signals.

Driver Intention Prediction by yaorong0921

Description: This framework predicts driver’s maneuver behaviors using EEG and other sensor data. It includes a comprehensive approach for in-cabin and driving scene monitoring.

GitHub Repository:

Driver-Intention-Prediction⁠

⁠

Key Features:

Incorporates both in-cabin and external driving scene data.

Uses ConvLSTM and other models for prediction.

Performance: Specific performance metrics are not detailed in the repository, but the approach is robust and leverages multiple data sources for prediction.

Transformer for Single-Channel EEG by eason123789

Description: This project replaces a CompactCNN with a Transformer model for classifying 1D EEG signals, specifically targeting driver drowsiness recognition.

GitHub Repository:

Transformer-for-Single-Channel-EEG⁠

⁠

Key Features:

Focuses on single-channel EEG data.

Aims at driver drowsiness detection, which is closely related to predicting driving intention.

Performance: The repository indicates that the model performs well in classifying driver drowsiness but specific metrics are not provided.

Want to print your doc?
This is not the way.

Try clicking the ⋯ next to your doc name or using a keyboard shortcut (

CtrlP

) instead.