Multimodal deep learning approach for joint EEG-EMG data compression and classification

Multimodal deep learning approach for joint EEG-EMG data compression and classification. Said, A. B., Mohamed, A., Elfouly, T., Harras, K., & Wang, Z. J. March, 2017.

Paper abstract bibtex

In this paper, we present a joint compression and classification approach of EEG and EMG signals using a deep learning approach. Specifically, we build our system based on the deep autoencoder architecture which is designed not only to extract discriminant features in the multimodal data representation but also to reconstruct the data from the latent representation using encoder-decoder layers. Since autoencoder can be seen as a compression approach, we extend it to handle multimodal data at the encoder layer, reconstructed and retrieved at the decoder layer. We show through experimental results, that exploiting both multimodal data intercorellation and intracorellation 1) Significantly reduces signal distortion particularly for high compression levels 2) Achieves better accuracy in classifying EEG and EMG signals recorded and labeled according to the sentiments of the volunteer.

@article{said_multimodal_2017,
	title = {Multimodal deep learning approach for joint {EEG}-{EMG} data compression and classification},
	url = {https://arxiv.org/abs/1703.08970v1},
	abstract = {In this paper, we present a joint compression and classification approach of
EEG and EMG signals using a deep learning approach. Specifically, we build our
system based on the deep autoencoder architecture which is designed not only to
extract discriminant features in the multimodal data representation but also to
reconstruct the data from the latent representation using encoder-decoder
layers. Since autoencoder can be seen as a compression approach, we extend it
to handle multimodal data at the encoder layer, reconstructed and retrieved at
the decoder layer. We show through experimental results, that exploiting both
multimodal data intercorellation and intracorellation 1) Significantly reduces
signal distortion particularly for high compression levels 2) Achieves better
accuracy in classifying EEG and EMG signals recorded and labeled according to
the sentiments of the volunteer.},
	language = {en},
	urldate = {2020-04-05},
	author = {Said, Ahmed Ben and Mohamed, Amr and Elfouly, Tarek and Harras, Khaled and Wang, Z. Jane},
	month = mar,
	year = {2017},
}

Downloads: 0

{"_id":"nZeDP2qsjWS8SaaYh","bibbaseid":"said-mohamed-elfouly-harras-wang-multimodaldeeplearningapproachforjointeegemgdatacompressionandclassification-2017","authorIDs":[],"author_short":["Said, A. B.","Mohamed, A.","Elfouly, T.","Harras, K.","Wang, Z. J."],"bibdata":{"bibtype":"article","type":"article","title":"Multimodal deep learning approach for joint EEG-EMG data compression and classification","url":"https://arxiv.org/abs/1703.08970v1","abstract":"In this paper, we present a joint compression and classification approach of EEG and EMG signals using a deep learning approach. Specifically, we build our system based on the deep autoencoder architecture which is designed not only to extract discriminant features in the multimodal data representation but also to reconstruct the data from the latent representation using encoder-decoder layers. Since autoencoder can be seen as a compression approach, we extend it to handle multimodal data at the encoder layer, reconstructed and retrieved at the decoder layer. We show through experimental results, that exploiting both multimodal data intercorellation and intracorellation 1) Significantly reduces signal distortion particularly for high compression levels 2) Achieves better accuracy in classifying EEG and EMG signals recorded and labeled according to the sentiments of the volunteer.","language":"en","urldate":"2020-04-05","author":[{"propositions":[],"lastnames":["Said"],"firstnames":["Ahmed","Ben"],"suffixes":[]},{"propositions":[],"lastnames":["Mohamed"],"firstnames":["Amr"],"suffixes":[]},{"propositions":[],"lastnames":["Elfouly"],"firstnames":["Tarek"],"suffixes":[]},{"propositions":[],"lastnames":["Harras"],"firstnames":["Khaled"],"suffixes":[]},{"propositions":[],"lastnames":["Wang"],"firstnames":["Z.","Jane"],"suffixes":[]}],"month":"March","year":"2017","bibtex":"@article{said_multimodal_2017,\n\ttitle = {Multimodal deep learning approach for joint {EEG}-{EMG} data compression and classification},\n\turl = {https://arxiv.org/abs/1703.08970v1},\n\tabstract = {In this paper, we present a joint compression and classification approach of\nEEG and EMG signals using a deep learning approach. Specifically, we build our\nsystem based on the deep autoencoder architecture which is designed not only to\nextract discriminant features in the multimodal data representation but also to\nreconstruct the data from the latent representation using encoder-decoder\nlayers. Since autoencoder can be seen as a compression approach, we extend it\nto handle multimodal data at the encoder layer, reconstructed and retrieved at\nthe decoder layer. We show through experimental results, that exploiting both\nmultimodal data intercorellation and intracorellation 1) Significantly reduces\nsignal distortion particularly for high compression levels 2) Achieves better\naccuracy in classifying EEG and EMG signals recorded and labeled according to\nthe sentiments of the volunteer.},\n\tlanguage = {en},\n\turldate = {2020-04-05},\n\tauthor = {Said, Ahmed Ben and Mohamed, Amr and Elfouly, Tarek and Harras, Khaled and Wang, Z. Jane},\n\tmonth = mar,\n\tyear = {2017},\n}\n\n","author_short":["Said, A. B.","Mohamed, A.","Elfouly, T.","Harras, K.","Wang, Z. J."],"key":"said_multimodal_2017","id":"said_multimodal_2017","bibbaseid":"said-mohamed-elfouly-harras-wang-multimodaldeeplearningapproachforjointeegemgdatacompressionandclassification-2017","role":"author","urls":{"Paper":"https://arxiv.org/abs/1703.08970v1"},"metadata":{"authorlinks":{}}},"bibtype":"article","biburl":"https://bibbase.org/zotero/m.shamimkaiser","creationDate":"2021-02-19T18:04:09.065Z","downloads":0,"keywords":[],"search_terms":["multimodal","deep","learning","approach","joint","eeg","emg","data","compression","classification","said","mohamed","elfouly","harras","wang"],"title":"Multimodal deep learning approach for joint EEG-EMG data compression and classification","year":2017,"dataSources":["yda423vBhGBN7Q3WB"]}