Patients’ EEG Data Analysis via Spectrogram Image with a Convolution Neural Network

Yuan, Linwang; Cao, Jianting

doi:10.1007/978-3-319-59421-7_2

Cited by 35 publications

(17 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Study on human brain intelligence has been researched across a number of areas, including neuroscience, brain science, and computer science, in which EEG-based interfacing with brains remains one of the most popular methods [10, 15, 66]. While artificial intelligence is becoming the most actively pursued topic in computer vision, exploitation of brain intelligence could provide enormous potential for further advancing AI techniques as well as their practical applications.…”

Section: Discussionmentioning

confidence: 99%

EEG-based image classification via a region-level stacked bi-directional deep learning framework

Fares

Zhong

Jiang

2019

BMC Med Inform Decis Mak

View full text Add to dashboard Cite

BackgroundAs a physiological signal, EEG data cannot be subjectively changed or hidden. Compared with other physiological signals, EEG signals are directly related to human cortical activities with excellent temporal resolution. After the rapid development of machine learning and artificial intelligence, the analysis and calculation of EEGs has made great progress, leading to a significant boost in performances for content understanding and pattern recognition of brain activities across the areas of both neural science and computer vision. While such an enormous advance has attracted wide range of interests among relevant research communities, EEG-based classification of brain activities evoked by images still demands efforts for further improvement with respect to its accuracy, generalization, and interpretation, yet some characters of human brains have been relatively unexplored.MethodsWe propose a region-level stacked bi-directional deep learning framework for EEG-based image classification. Inspired by the hemispheric lateralization of human brains, we propose to extract additional information at regional level to strengthen and emphasize the differences between two hemispheres. The stacked bi-directional long short-term memories are used to capture the dynamic correlations hidden from both the past and the future to the current state in EEG sequences.ResultsExtensive experiments are carried out and our results demonstrate the effectiveness of our proposed framework. Compared with the existing state-of-the-arts, our framework achieves outstanding performances in EEG-based classification of brain activities evoked by images. In addition, we find that the signals of Gamma band are not only useful for achieving good performances for EEG-based image classification, but also play a significant role in capturing relationships between the neural activations and the specific emotional states.ConclusionsOur proposed framework provides an improved solution for the problem that, given an image used to stimulate brain activities, we should be able to identify which class the stimuli image comes from by analyzing the EEG signals. The region-level information is extracted to preserve and emphasize the hemispheric lateralization for neural functions or cognitive processes of human brains. Further, stacked bi-directional LSTMs are used to capture the dynamic correlations hidden in EEG data. Extensive experiments on standard EEG-based image classification dataset validate that our framework outperforms the existing state-of-the-arts under various contexts and experimental setups.

show abstract

Section: Discussionmentioning

confidence: 99%

EEG-based image classification via a region-level stacked bi-directional deep learning framework

Fares

Zhong

Jiang

2019

BMC Med Inform Decis Mak

View full text Add to dashboard Cite

show abstract

“…Any load signal can be represented as image by transforming it into spectrogram image. References [ 24 , 25 , 26 ] used pixel from spectrogram image (transformed from a signal) as the feature of recognition task and then has performed promising result. Because colors distribution of spectrogram image is unique and can represent the feature of each recognition class.…”

Section: Proposed Methodsmentioning

confidence: 99%

Background Load Denoising across Complex Load Based on Generative Adversarial Network to Enhance Load Identification

Mukaroh

Kim

2020

Sensors

View full text Add to dashboard Cite

Non-Intrusive Load Monitoring (NILM) allows load identification of appliances through a single sensor. By using NILM, users can monitor their electricity consumption, which is beneficial for energy efficiency or energy saving. In advance NILM systems, identification of appliances on/off events should be processed instantly. Thus, it is necessary to use an extremely short period signal of appliances to shorten the time delay for users to acquire event information. However, acquiring event information from a short period signal raises another problem. The problem is target load feature to be easily mixed with background load. The more complex the background load has, the noisier the target load occurs. This issue certainly reduces the appliance identification performance. Therefore, we provide a novel methodology that leverages Generative Adversarial Network (GAN) to generate noise distribution of background load then use it to generate a clear target load. We also built a Convolutional Neural Network (CNN) model to identify load based on single load data. Then we use that CNN model to evaluate the target load generated by GAN. The result shows that GAN is powerful to denoise background load across the complex load. It yields a high accuracy of load identification which could reach 92.04%.

show abstract

“…Most current research has focused on the recognition of abnormality of EEG signals. On the other hand, (Yuan and Cao, 2017) attempted to apply a deep learning network to EEG signals to prove clinical brain death diagnosis. The Short Time Fourier Transform technique was used as a time frequency analysis technique.…”

Section: Application Of Cnn For Eeg Analysismentioning

confidence: 99%

“…The result was 99.8% accuracy. This approach can be used to evaluate the condition of brain-damaged patients as well as for quasi-brain death diagnosis (Yuan and Cao, 2017). Another study focused on to distinguish EEG pattern of three classes namely normal, preictal and seizure pattern.…”

Section: Application Of Cnn For Eeg Analysismentioning

confidence: 99%

Convolutional Neural Network Application in Biomedical Signals

Alaskar¹

2018

JCSIT

View full text Add to dashboard Cite

Recent improvements in big data and machine learning have enhanced the importance of biomedical signal and image-processing research. One part of machine learning evolution is deep learning networks. Deep learning networks are designed for the task of exploiting compositional structure in data. The golden age of the deep learning network in particular convolutional neural networks (CNNs) began in 2012. CNNs have rapidly become a methodology of optimal choice for analysing biomedical signals. CNNs have been successful in detecting and diagnosing an abnormality in biomedical signals. This paper has three distinct aims. The key primary aim is to provide state of the art knowledge about how deep learning evolved and revolutionized machine learning in the past few years. Second, to critically review the application of deep learning for different biomedical signals analysis and provide a holistic overview of current works of literature. Finally, to discuss the research opportunities with deep learning algorithms in the field of study that can serve as a starting point for new researchers to identify the future research direction in a concise manner.

show abstract

Patients’ EEG Data Analysis via Spectrogram Image with a Convolution Neural Network

Cited by 35 publications

References 16 publications

EEG-based image classification via a region-level stacked bi-directional deep learning framework

EEG-based image classification via a region-level stacked bi-directional deep learning framework

Background Load Denoising across Complex Load Based on Generative Adversarial Network to Enhance Load Identification

Convolutional Neural Network Application in Biomedical Signals

Contact Info

Product

Resources

About