当前位置:
X-MOL 学术
›
Front Hum Neurosci
›
论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Decoding multiple sound categories in the auditory cortex using recurrent neural networks: A functional near-infrared spectroscopy study
Frontiers in Human Neuroscience ( IF 2.9 ) Pub Date : 2021-03-31 , DOI: 10.3389/fnhum.2021.636191 So-Hyeon Yoo , Hendrik Santosa , Chang-Seok Kim , Keum-Shik Hong
Frontiers in Human Neuroscience ( IF 2.9 ) Pub Date : 2021-03-31 , DOI: 10.3389/fnhum.2021.636191 So-Hyeon Yoo , Hendrik Santosa , Chang-Seok Kim , Keum-Shik Hong
This study aims to decode the hemodynamic responses (HRs) evoked by multiple sound-categories using functional near-infrared spectroscopy (fNIRS). The six different sounds were given as stimuli (English, non-English, annoying, nature, music, and gunshot). The oxy-hemoglobin (HbO) concentration changes are measured in both hemispheres of the auditory cortex while 18 healthy subjects listen to 10-sec blocks of six sound-categories. Long-short term memory (LSTM) networks were used as a classifier. The classification accuracy was 20.38 ± 4.63% with six classes classification. Though LSTM networks’ performance was a little higher than chance levels, it is noteworthy that we could classify the data subject-wisely without feature selections.
中文翻译:
使用递归神经网络解码听觉皮层中的多个声音类别:功能性近红外光谱研究
这项研究旨在使用功能性近红外光谱(fNIRS)解码由多个声音类别引起的血液动力学反应(HRs)。六个不同的声音作为刺激(英语,非英语,烦人,自然,音乐和枪声)发出。在听觉皮层的两个半球中测量氧合血红蛋白(HbO)的浓度变化,而18位健康的受试者会聆听10秒的六个声音类别的声音。长期短期记忆(LSTM)网络用作分类器。六类分类的分类准确度为20.38±4.63%。尽管LSTM网络的性能略高于机会级别,但值得注意的是,我们可以按主题对数据进行分类,而无需选择特征。
更新日期:2021-03-31
中文翻译:
使用递归神经网络解码听觉皮层中的多个声音类别:功能性近红外光谱研究
这项研究旨在使用功能性近红外光谱(fNIRS)解码由多个声音类别引起的血液动力学反应(HRs)。六个不同的声音作为刺激(英语,非英语,烦人,自然,音乐和枪声)发出。在听觉皮层的两个半球中测量氧合血红蛋白(HbO)的浓度变化,而18位健康的受试者会聆听10秒的六个声音类别的声音。长期短期记忆(LSTM)网络用作分类器。六类分类的分类准确度为20.38±4.63%。尽管LSTM网络的性能略高于机会级别,但值得注意的是,我们可以按主题对数据进行分类,而无需选择特征。