RECORD
EnK: Encoding time-information in convolution
Machine Learning · Submitted 7 Jun 2020
abstract compiled · 2026-09-23 · no language-model review
The authors' main claim These results support our methodology and show high potential to improve CNN performance in the context of time-series data in general.
The compiled record
The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. Numbers in the tables are the authors', checked by code. No sentence in this record was written by a model.
Open the compiled record
The abstract, sentence by sentence
Recent development in deep learning techniques has attracted attention in decoding and classification in EEG signals. Despite several efforts utilizing different features of EEG signals, a significant research challenge is to use time-dependent features in combination with local and global features. There have been several efforts to remodel the deep learning convolution neural networks (CNNs) to capture time-dependency information by incorporating hand-crafted features, slicing the input data in a smaller time-windows, and recurrent convolution. However, these approaches partially solve the problem, but simultaneously hinder the CNN's capability to learn from unknown information that might be present in the data. To solve this, we have proposed a novel time encoding kernel (EnK) approach, which introduces the increasing time information during convolution operation in CNN. The encoded information by EnK lets CNN learn time-dependent features in-addition to local and global features. We performed extensive experiments on several EEG datasets: cognitive conflict (CC), physical-human robot collaboration (pHRC), P300 visual-evoked potentials, movement-related cortical potentials (MRCP). EnK outperforms the state-of-art by 12\% (F1 score). Moreover, the EnK approach required only one additional parameter to learn and can be applied to a virtually any CNN architectures with minimal efforts. These results support our methodology and show high potential to improve CNN performance in the context of time-series data in general.
background contribution method result interpretation main claim
| # | sentence | role | the authors' own work | states the main conclusion | strength |
|---|---|---|---|---|---|
| s0 | Recent development in deep learning techniques has attracted attention in decoding and classification in EEG signals. | background 1.00 | 0.04 | 0.01 | asserted 0.99 |
| s1 | Despite several efforts utilizing different features of EEG signals, a significant research challenge is to use time-dependent features in combination with local and global features. | gap 0.89 | 0.06 | 0.02 | asserted 1.00 |
| s2 | There have been several efforts to remodel the deep learning convolution neural networks (CNNs) to capture time-dependency information by incorporating hand-crafted features, slicing the input data in a smaller time-windows, and recurrent convolution. | background 1.00 | 0.05 | 0.02 | asserted 1.00 |
| s3 | However, these approaches partially solve the problem, but simultaneously hinder the CNN's capability to learn from unknown information that might be present in the data. | gap 0.79 | 0.10 | 0.03 | asserted 0.99 |
| s4 | To solve this, we have proposed a novel time encoding kernel (EnK) approach, which introduces the increasing time information during convolution operation in CNN. | contribution 0.97 | 0.92 | 0.12 | asserted 1.00 |
| s5 | The encoded information by EnK lets CNN learn time-dependent features in-addition to local and global features. | contribution 0.33 | 0.60 | 0.16 | asserted 1.00 |
| s6 | We performed extensive experiments on several EEG datasets: cognitive conflict (CC), physical-human robot collaboration (pHRC), P300 visual-evoked potentials, movement-related cortical potentials (MRCP). | method 0.93 | 0.96 | 0.03 | asserted 0.98 |
| s7 | EnK outperforms the state-of-art by 12\% (F1 score). | result 1.00 | 0.94 | 0.60 | asserted 1.00 |
| s8 | Moreover, the EnK approach required only one additional parameter to learn and can be applied to a virtually any CNN architectures with minimal efforts. | result 0.84 | 0.90 | 0.10 | asserted 0.98 |
| s9 | These results support our methodology and show high potential to improve CNN performance in the context of time-series data in general. | interpretation 1.00 | 0.68 | 0.49 | asserted 0.73 |
What was examined, and what was not
- arXiv listing abstract v1
- full text
- figures and tables
- references and citing sentences
- relations to other papers
- P abstract
- S sections
- T body sentences
- C citations
- R cross-paper relations
The paper
Original abstract
Recent development in deep learning techniques has attracted attention in decoding and classification in EEG signals. Despite several efforts utilizing different features of EEG signals, a significant research challenge is to use time-dependent features in combination with local and global features. There have been several efforts to remodel the deep learning convolution neural networks (CNNs) to capture time-dependency information by incorporating hand-crafted features, slicing the input data in a smaller time-windows, and recurrent convolution. However, these approaches partially solve the problem, but simultaneously hinder the CNN's capability to learn from unknown information that might be present in the data. To solve this, we have proposed a novel time encoding kernel (EnK) approach, which introduces the increasing time information during convolution operation in CNN. The encoded information by EnK lets CNN learn time-dependent features in-addition to local and global features. We performed extensive experiments on several EEG datasets: cognitive conflict (CC), physical-human robot collaboration (pHRC), P300 visual-evoked potentials, movement-related cortical potentials (MRCP). EnK outperforms the state-of-art by 12\% (F1 score). Moreover, the EnK approach required only one additional parameter to learn and can be applied to a virtually any CNN architectures with minimal efforts. These results support our methodology and show high potential to improve CNN performance in the context of time-series data in general.
Human review
How the literature uses it
What this paper does with the arXiv papers it cites
What it cites · 4 sentences without a confident label
Cites as background 2 papers
-
Inspired by several CNN models, the author [ref] proposed a very deep convolution neural network model called DeepConvNet inspired from VGG [ref] for EEG signals.
Very Deep Convolutional Networks for Large-Scale Image Recognition · Related work · 0.81
-
Deep learning has already shown a high number of successful applications in the field of natural language processing and computer vision, text classification, and action recognition [ref] [ref] (review: [ref] ).
An Analysis of Deep Neural Network Models for Practical Applications · Related work · 0.90
Discussion
Know something about this paper? Leave a comment, or highlight any passage above to comment on it.