首页 > 最新文献

Cognitive Neurodynamics最新文献

英文 中文
Decoded EEG neurofeedback-guided cognitive reappraisal training for emotion regulation 解码脑电图神经反馈引导的情绪调节认知重评训练
IF 3.7 3区 工程技术 Q2 NEUROSCIENCES Pub Date : 2024-05-03 DOI: 10.1007/s11571-024-10108-x
Linling Li, Xueying Gui, Gan Huang, Li Zhang, Feng Wan, Xue Han, Jianhong Wang, Dong Ni, Zhen Liang, Zhiguo Zhang

Neurofeedback, when combined with cognitive reappraisal, offers promising potential for emotion regulation training. However, prior studies have predominantly relied on functional magnetic resonance imaging, which could impede its clinical feasibility. Furthermore, these studies have primarily focused on reducing negative emotions while overlooking the importance of enhancing positive emotions. In our current study, we developed a novel electroencephalogram (EEG) neurofeedback-guided cognitive reappraisal training protocol for emotion regulation. We recruited forty-two healthy subjects (20 females; 22.4 ± 2.2 years old) who were randomly assigned to either the neurofeedback group or the control group. We evaluated the efficacy of this newly proposed neurofeedback training approach in regulating emotions evoked by pictures with different valence levels (low positive and high negative). Initially, we trained an EEG-based emotion decoding model for each individual using offline data. During the training process, we calculated the subjects’ real-time self-regulation performance based on the decoded emotional states and fed it back to the subjects as feedback signals. Our results indicate that the proposed decoded EEG neurofeedback-guided cognitive reappraisal training protocol significantly enhanced emotion regulation performance for stimuli with low positive valence. Additionally, wavelet energy and differential entropy features in the high-frequency band played a crucial role in emotion classification and were associated with neural plasticity changes induced by emotion regulation. These findings validate the beneficial effects of the proposed EEG neurofeedback protocol and offer insights into the neural mechanisms underlying its training effects. This novel decoded neurofeedback training protocol presents a promising cost-effective and non-invasive treatment technique for emotion-related mental disorders.

神经反馈与认知再评价相结合,为情绪调节训练提供了广阔的前景。然而,之前的研究主要依赖于功能性磁共振成像,这可能会阻碍其临床可行性。此外,这些研究主要侧重于减少负面情绪,而忽视了增强正面情绪的重要性。在目前的研究中,我们开发了一种新型脑电图(EEG)神经反馈引导的情绪调节认知再评价训练方案。我们招募了 42 名健康受试者(20 名女性;22.4 ± 2.2 岁),将他们随机分配到神经反馈组或对照组。我们评估了这种新提出的神经反馈训练方法在调节由不同价位(低正面和高负面)图片诱发的情绪方面的效果。最初,我们利用离线数据为每个人训练了一个基于脑电图的情绪解码模型。在训练过程中,我们根据解码的情绪状态计算受试者的实时自我调节表现,并将其作为反馈信号反馈给受试者。我们的研究结果表明,所提出的解码脑电图神经反馈指导认知再评价训练方案能显著提高受试者对低正价刺激的情绪调节能力。此外,高频段的小波能量和差分熵特征在情绪分类中发挥了关键作用,并与情绪调节引起的神经可塑性变化有关。这些发现验证了所提出的脑电图神经反馈方案的有益效果,并为了解其训练效果背后的神经机制提供了见解。这种新颖的解码神经反馈训练方案为治疗情绪相关精神障碍提供了一种经济有效的非侵入性治疗技术。
{"title":"Decoded EEG neurofeedback-guided cognitive reappraisal training for emotion regulation","authors":"Linling Li, Xueying Gui, Gan Huang, Li Zhang, Feng Wan, Xue Han, Jianhong Wang, Dong Ni, Zhen Liang, Zhiguo Zhang","doi":"10.1007/s11571-024-10108-x","DOIUrl":"https://doi.org/10.1007/s11571-024-10108-x","url":null,"abstract":"<p>Neurofeedback, when combined with cognitive reappraisal, offers promising potential for emotion regulation training. However, prior studies have predominantly relied on functional magnetic resonance imaging, which could impede its clinical feasibility. Furthermore, these studies have primarily focused on reducing negative emotions while overlooking the importance of enhancing positive emotions. In our current study, we developed a novel electroencephalogram (EEG) neurofeedback-guided cognitive reappraisal training protocol for emotion regulation. We recruited forty-two healthy subjects (20 females; 22.4 ± 2.2 years old) who were randomly assigned to either the neurofeedback group or the control group. We evaluated the efficacy of this newly proposed neurofeedback training approach in regulating emotions evoked by pictures with different valence levels (low positive and high negative). Initially, we trained an EEG-based emotion decoding model for each individual using offline data. During the training process, we calculated the subjects’ real-time self-regulation performance based on the decoded emotional states and fed it back to the subjects as feedback signals. Our results indicate that the proposed decoded EEG neurofeedback-guided cognitive reappraisal training protocol significantly enhanced emotion regulation performance for stimuli with low positive valence. Additionally, wavelet energy and differential entropy features in the high-frequency band played a crucial role in emotion classification and were associated with neural plasticity changes induced by emotion regulation. These findings validate the beneficial effects of the proposed EEG neurofeedback protocol and offer insights into the neural mechanisms underlying its training effects. This novel decoded neurofeedback training protocol presents a promising cost-effective and non-invasive treatment technique for emotion-related mental disorders.</p>","PeriodicalId":10500,"journal":{"name":"Cognitive Neurodynamics","volume":"114 1","pages":""},"PeriodicalIF":3.7,"publicationDate":"2024-05-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140884596","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Involvement of prelimbic cortex neurons and related circuits in the acquisition of a cooperative learning by pairs of rats 前边缘皮层神经元及相关回路参与成对大鼠合作学习的习得
IF 3.7 3区 工程技术 Q2 NEUROSCIENCES Pub Date : 2024-05-03 DOI: 10.1007/s11571-024-10107-y
A. R. Conde-Moro, F. Rocha-Almeida, E. Gebara, J. M. Delgado-García, C. Sandi, A. Gruart

Social behaviors such as cooperation are crucial for mammals. A deeper knowledge of the neuronal mechanisms underlying cooperation can be beneficial for people suffering from pathologies with impaired social behavior. Our aim was to study the brain activity when two animals synchronize their behavior to obtain a mutual reinforcement. In a previous work, we showed that the activity of the prelimbic cortex (PrL) was enhanced during cooperation in rats, especially in the ones leading most cooperative trials (leader rats). In this study, we investigated the specific cells in the PrL contributing to cooperative behaviors. To this end, we collected rats’ brains at key moments of the learning process to analyze the levels of c-FOS expression in the main cellular groups of the PrL. Leader rats showed increased c-FOS activity in cells expressing D1 receptors during cooperation. Besides, we analyzed the levels of anxiety, dominance, and locomotor behavior, finding that leader rats are in general less anxious and less dominant than followers. We also recorded local field potentials (LFPs) from the PrL, the nucleus accumbens septi (NAc), and the basolateral amygdala (BLA). A spectral analysis showed that delta activity in PrL and NAc increased when rats cooperated, while BLA activity in delta and theta bands decreased considerably during cooperation. The PrL and NAc also increased their connectivity in the high theta band during cooperation. Thus, the present work identifies the specific PrL cell types engaged in this behavior, as well as the way this information is propagated to selected downstream brain regions (BLA, NAc).

合作等社会行为对哺乳动物至关重要。深入了解合作背后的神经元机制,对患有社会行为受损病症的人来说是有益的。我们的目的是研究当两只动物同步其行为以获得相互强化时的大脑活动。在之前的研究中,我们发现大鼠在合作过程中前缘皮层(PrL)的活动会增强,尤其是在领导合作试验最多的大鼠(领导鼠)中。在这项研究中,我们调查了 PrL 中促成合作行为的特定细胞。为此,我们在学习过程的关键时刻采集了大鼠的大脑,分析了 PrL 主要细胞群中 c-FOS 的表达水平。在合作过程中,领头鼠表现出表达 D1 受体的细胞中 c-FOS 活性增加。此外,我们还分析了大鼠的焦虑程度、支配性和运动行为,发现领导者大鼠的焦虑程度和支配性普遍低于跟随者大鼠。我们还记录了PrL、隔核(NAc)和杏仁基底外侧(BLA)的局部场电位(LFPs)。频谱分析表明,当大鼠合作时,PrL和NAc的δ活动增加,而BLA的δ和θ波段活动在合作过程中大幅减少。在合作过程中,PrL和NAc在高θ波段的连接性也有所增加。因此,本研究确定了参与这种行为的特定 PrL 细胞类型,以及这种信息传播到选定下游脑区(BLA、NAc)的方式。
{"title":"Involvement of prelimbic cortex neurons and related circuits in the acquisition of a cooperative learning by pairs of rats","authors":"A. R. Conde-Moro, F. Rocha-Almeida, E. Gebara, J. M. Delgado-García, C. Sandi, A. Gruart","doi":"10.1007/s11571-024-10107-y","DOIUrl":"https://doi.org/10.1007/s11571-024-10107-y","url":null,"abstract":"<p>Social behaviors such as cooperation are crucial for mammals. A deeper knowledge of the neuronal mechanisms underlying cooperation can be beneficial for people suffering from pathologies with impaired social behavior. Our aim was to study the brain activity when two animals synchronize their behavior to obtain a mutual reinforcement. In a previous work, we showed that the activity of the prelimbic cortex (PrL) was enhanced during cooperation in rats, especially in the ones leading most cooperative trials (<i>leader</i> rats). In this study, we investigated the specific cells in the PrL contributing to cooperative behaviors. To this end, we collected rats’ brains at key moments of the learning process to analyze the levels of c-FOS expression in the main cellular groups of the PrL. <i>Leader</i> rats showed increased c-FOS activity in cells expressing D1 receptors during cooperation. Besides, we analyzed the levels of anxiety, dominance, and locomotor behavior, finding that <i>leader</i> rats are in general less anxious and less dominant than <i>followers</i>. We also recorded local field potentials (LFPs) from the PrL, the nucleus accumbens septi (NAc), and the basolateral amygdala (BLA). A spectral analysis showed that delta activity in PrL and NAc increased when rats cooperated, while BLA activity in delta and theta bands decreased considerably during cooperation. The PrL and NAc also increased their connectivity in the high theta band during cooperation. Thus, the present work identifies the specific PrL cell types engaged in this behavior, as well as the way this information is propagated to selected downstream brain regions (BLA, NAc).</p>","PeriodicalId":10500,"journal":{"name":"Cognitive Neurodynamics","volume":"17 1","pages":""},"PeriodicalIF":3.7,"publicationDate":"2024-05-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140884745","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
An effective classification approach for EEG-based motor imagery tasks combined with attention mechanisms 基于脑电图的运动想象任务与注意力机制相结合的有效分类方法
IF 3.7 3区 工程技术 Q2 NEUROSCIENCES Pub Date : 2024-05-03 DOI: 10.1007/s11571-024-10115-y
Jixiang Li, Wuxiang Shi, Yurong Li

Currently, electroencephalogram (EEG)-based motor imagery (MI) signals have been received extensive attention, which can assist disabled subjects to control wheelchair, automatic driving and other activities. However, EEG signals are easily affected by some factors, such as muscle movements, wireless devices, power line, etc., resulting in the low signal-to-noise ratios and the worse recognition results on EEG decoding. Therefore, it is crucial to develop a stable model for decoding MI-EEG signals. To address this issue and further improve the decoding performance for MI tasks, a hybrid structure combining convolutional neural networks and bidirectional long short-term memory (BLSTM) model, namely CBLSTM, is developed in this study to handle the various EEG-based MI tasks. Besides, the attention mechanism (AM) model is further adopted to adaptively assign the weight of EEG vital features and enhance the expression which beneficial to classification for MI tasks. First of all, the spatial features and the time series features are extracted by CBLSTM from preprocessed MI-EEG data, respectively. Meanwhile, more effective features information can be mined by the AM model, and the softmax function is utilized to recognize intention categories. Ultimately, the numerical results illustrate that the model presented achieves an average accuracy of 98.40% on the public physioNet dataset and faster training process for decoding MI tasks, which is superior to some other advanced models. Ablation experiment performed also verifies the effectiveness and feasibility of the developed model. Moreover, the established network model provides a good basis for the application of brain-computer interface in rehabilitation medicine.

目前,基于脑电图(EEG)的运动图像(MI)信号受到广泛关注,它可以帮助残疾人士控制轮椅、自动驾驶等活动。然而,脑电信号容易受到肌肉运动、无线设备、电源线等因素的影响,导致信噪比低,脑电解码的识别效果较差。因此,建立一个稳定的 MI-EEG 信号解码模型至关重要。为解决这一问题并进一步提高 MI 任务的解码性能,本研究开发了一种结合卷积神经网络和双向长短期记忆(BLSTM)模型的混合结构,即 CBLSTM,以处理各种基于脑电图的 MI 任务。此外,本研究还进一步采用了注意力机制(AM)模型来自适应地分配脑电图重要特征的权重,并增强有利于 MI 任务分类的表达。首先,利用 CBLSTM 分别从预处理后的 MI-EEG 数据中提取空间特征和时间序列特征。同时,AM 模型可以挖掘出更多有效的特征信息,并利用 softmax 函数识别意向类别。最终,数值结果表明,该模型在公共physioNet数据集上实现了98.40%的平均准确率,并且在解码MI任务时训练过程更快,优于其他一些先进模型。所进行的消融实验也验证了所开发模型的有效性和可行性。此外,所建立的网络模型还为脑机接口在康复医学中的应用提供了良好的基础。
{"title":"An effective classification approach for EEG-based motor imagery tasks combined with attention mechanisms","authors":"Jixiang Li, Wuxiang Shi, Yurong Li","doi":"10.1007/s11571-024-10115-y","DOIUrl":"https://doi.org/10.1007/s11571-024-10115-y","url":null,"abstract":"<p>Currently, electroencephalogram (EEG)-based motor imagery (MI) signals have been received extensive attention, which can assist disabled subjects to control wheelchair, automatic driving and other activities. However, EEG signals are easily affected by some factors, such as muscle movements, wireless devices, power line, etc., resulting in the low signal-to-noise ratios and the worse recognition results on EEG decoding. Therefore, it is crucial to develop a stable model for decoding MI-EEG signals. To address this issue and further improve the decoding performance for MI tasks, a hybrid structure combining convolutional neural networks and bidirectional long short-term memory (BLSTM) model, namely CBLSTM, is developed in this study to handle the various EEG-based MI tasks. Besides, the attention mechanism (AM) model is further adopted to adaptively assign the weight of EEG vital features and enhance the expression which beneficial to classification for MI tasks. First of all, the spatial features and the time series features are extracted by CBLSTM from preprocessed MI-EEG data, respectively. Meanwhile, more effective features information can be mined by the AM model, and the softmax function is utilized to recognize intention categories. Ultimately, the numerical results illustrate that the model presented achieves an average accuracy of 98.40% on the public physioNet dataset and faster training process for decoding MI tasks, which is superior to some other advanced models. Ablation experiment performed also verifies the effectiveness and feasibility of the developed model. Moreover, the established network model provides a good basis for the application of brain-computer interface in rehabilitation medicine.</p>","PeriodicalId":10500,"journal":{"name":"Cognitive Neurodynamics","volume":"14 1","pages":""},"PeriodicalIF":3.7,"publicationDate":"2024-05-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140884540","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
SST-CRAM: spatial-spectral-temporal based convolutional recurrent neural network with lightweight attention mechanism for EEG emotion recognition SST-CRAM:基于空间-光谱-时间的卷积递归神经网络与轻量级注意力机制,用于脑电图情感识别
IF 3.7 3区 工程技术 Q2 NEUROSCIENCES Pub Date : 2024-04-30 DOI: 10.1007/s11571-024-10114-z
Yingxiao Qiao, Qian Zhao

Through emotion recognition with EEG signals, brain responses can be analyzed to monitor and identify individual emotional states. The success of emotion recognition relies on comprehensive emotion information extracted from EEG signals and the constructed emotion identification model. In this work, we proposed an innovative approach, called spatial-spectral-temporal-based convolutional recurrent neural network (CRNN) with lightweight attention mechanism (SST-CRAM). Firstly, we combined power spectral density (PSD) with differential entropy (DE) features to construct four-dimensional (4D) EEG feature maps and obtain more spatial, spectral, and temporal information. Additional, with a spatial interpolation algorithm, the utilization of the obtained valuable information was enhanced. Next, the constructed 4D EEG feature map was input into the convolutional neural network (CNN) integrated with convolutional block attention module (CBAM) and efficient channel attention module (ECA-Net) for extracting spatial and spectral features. CNN was used to learn spatial and spectral information and CBAM was employed to prioritize global information and obtain detailed and accurate features. ECA-Net was also used to further highlight key brain regions and frequency bands. Finally, a bidirectional long short-term memory (LSTM) network was used to explore the temporal correlation of EEG feature maps for comprehensive feature extraction. To assess the performance of our model, we tested it on the publicly available DEAP dataset. Our model demonstrated excellent performance and achieved high accuracy (98.63% for arousal classification and 98.66% for valence classification). These results indicated that SST-CRAM could fully utilize spatial, spectral, and temporal information to improve the emotion recognition performance.

通过脑电信号进行情绪识别,可以分析大脑反应,监测和识别个人情绪状态。情绪识别的成功依赖于从脑电信号中提取的综合情绪信息和构建的情绪识别模型。在这项工作中,我们提出了一种创新方法,即基于空间-频谱-时间的卷积递归神经网络(CRNN)与轻量级注意机制(SST-CRAM)。首先,我们将功率谱密度(PSD)与微分熵(DE)特征相结合,构建了四维(4D)脑电图特征图,获得了更多的空间、频谱和时间信息。此外,通过空间插值算法,还提高了对所获有价值信息的利用率。接着,将构建的四维脑电图特征图输入到卷积神经网络(CNN)中,该网络集成了卷积块注意模块(CBAM)和高效通道注意模块(ECA-Net),用于提取空间和频谱特征。CNN 用于学习空间和频谱信息,而 CBAM 则用于优先处理全局信息并获得详细而准确的特征。ECA-Net 还用于进一步突出关键脑区和频带。最后,双向长短期记忆(LSTM)网络用于探索脑电图特征图的时间相关性,以实现全面的特征提取。为了评估模型的性能,我们在公开的 DEAP 数据集上进行了测试。我们的模型表现出色,达到了很高的准确率(唤醒分类为 98.63%,情绪分类为 98.66%)。这些结果表明,SST-CRAM 可以充分利用空间、频谱和时间信息来提高情绪识别性能。
{"title":"SST-CRAM: spatial-spectral-temporal based convolutional recurrent neural network with lightweight attention mechanism for EEG emotion recognition","authors":"Yingxiao Qiao, Qian Zhao","doi":"10.1007/s11571-024-10114-z","DOIUrl":"https://doi.org/10.1007/s11571-024-10114-z","url":null,"abstract":"<p>Through emotion recognition with EEG signals, brain responses can be analyzed to monitor and identify individual emotional states. The success of emotion recognition relies on comprehensive emotion information extracted from EEG signals and the constructed emotion identification model. In this work, we proposed an innovative approach, called spatial-spectral-temporal-based convolutional recurrent neural network (CRNN) with lightweight attention mechanism (SST-CRAM). Firstly, we combined power spectral density (PSD) with differential entropy (DE) features to construct four-dimensional (4D) EEG feature maps and obtain more spatial, spectral, and temporal information. Additional, with a spatial interpolation algorithm, the utilization of the obtained valuable information was enhanced. Next, the constructed 4D EEG feature map was input into the convolutional neural network (CNN) integrated with convolutional block attention module (CBAM) and efficient channel attention module (ECA-Net) for extracting spatial and spectral features. CNN was used to learn spatial and spectral information and CBAM was employed to prioritize global information and obtain detailed and accurate features. ECA-Net was also used to further highlight key brain regions and frequency bands. Finally, a bidirectional long short-term memory (LSTM) network was used to explore the temporal correlation of EEG feature maps for comprehensive feature extraction. To assess the performance of our model, we tested it on the publicly available DEAP dataset. Our model demonstrated excellent performance and achieved high accuracy (98.63% for arousal classification and 98.66% for valence classification). These results indicated that SST-CRAM could fully utilize spatial, spectral, and temporal information to improve the emotion recognition performance.</p>","PeriodicalId":10500,"journal":{"name":"Cognitive Neurodynamics","volume":"6 1","pages":""},"PeriodicalIF":3.7,"publicationDate":"2024-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140829622","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Time-varying EEG networks of major depressive disorder during facial emotion tasks 面部情绪任务中重度抑郁障碍的时变脑电图网络
IF 3.7 3区 工程技术 Q2 NEUROSCIENCES Pub Date : 2024-04-20 DOI: 10.1007/s11571-024-10111-2
Jingru Yang, Bowen Li, Wanqing Dong, Xiaorong Gao, Yanfei Lin

Depression is a mental disease involved in emotional and cognitive impairments. Neuroimaging studies have found abnormalities in the structure and functional network of brain for major depressive disorder (MDD).However, neural mechanism of the dynamic connectivity for emotional attention of MDD is currently insufficient. In this study, event-related potentials (ERP) and time-varying network were analyzed to investigate attention bias and corresponding neural mechanisms induced by emotional facial stimuli. In the ERP results, N100 components in MDD had shorter latencies and smaller amplitudes than those in healthy controls (HC) for sad and fear faces. The P200 amplitudes induced by sad faces in MDD were significantly higher than those induced by happy and fear faces in MDD, and those induced by sad faces in HC. It was indicated that MDD patients had attention bias towards sad faces. For the time-varying network analysis, adaptive directed transfer function was explored to construct dynamic network connectivity. MDD patients had stronger information outflow from the right frontal region and weaker information outflow from parieto-occipital regions for sad faces. In addition, the network properties of sad faces were significantly correlated with PHQ-9 scores for MDD group. These findings may provide further explanation for understanding the MDD’s neural mechanism of attention bias during facial emotional tasks.

抑郁症是一种涉及情感和认知障碍的精神疾病。神经影像学研究发现,重度抑郁症(MDD)患者的大脑结构和功能网络存在异常,但目前对MDD患者情绪注意动态连接的神经机制研究尚不充分。本研究分析了事件相关电位(ERP)和时变网络,以探讨情绪性面部刺激诱发的注意偏差及相应的神经机制。在ERP结果中,与健康对照组(HC)相比,MDD患者对悲伤和恐惧面孔的N100分量具有更短的潜伏期和更小的振幅。MDD患者由悲伤面孔诱发的P200振幅明显高于MDD患者由快乐和恐惧面孔诱发的振幅,也高于HC患者由悲伤面孔诱发的振幅。这表明 MDD 患者对悲伤面孔存在注意偏差。在时变网络分析中,探索了自适应定向传递函数来构建动态网络连接。对于悲伤面孔,MDD 患者从右侧额叶区流出的信息更多,而从顶枕区流出的信息较少。此外,悲伤面孔的网络特性与 MDD 组的 PHQ-9 评分有显著相关性。这些发现可能为理解 MDD 在面部情绪任务中注意力偏差的神经机制提供了进一步的解释。
{"title":"Time-varying EEG networks of major depressive disorder during facial emotion tasks","authors":"Jingru Yang, Bowen Li, Wanqing Dong, Xiaorong Gao, Yanfei Lin","doi":"10.1007/s11571-024-10111-2","DOIUrl":"https://doi.org/10.1007/s11571-024-10111-2","url":null,"abstract":"<p>Depression is a mental disease involved in emotional and cognitive impairments. Neuroimaging studies have found abnormalities in the structure and functional network of brain for major depressive disorder (MDD).However, neural mechanism of the dynamic connectivity for emotional attention of MDD is currently insufficient. In this study, event-related potentials (ERP) and time-varying network were analyzed to investigate attention bias and corresponding neural mechanisms induced by emotional facial stimuli. In the ERP results, N100 components in MDD had shorter latencies and smaller amplitudes than those in healthy controls (HC) for sad and fear faces. The P200 amplitudes induced by sad faces in MDD were significantly higher than those induced by happy and fear faces in MDD, and those induced by sad faces in HC. It was indicated that MDD patients had attention bias towards sad faces. For the time-varying network analysis, adaptive directed transfer function was explored to construct dynamic network connectivity. MDD patients had stronger information outflow from the right frontal region and weaker information outflow from parieto-occipital regions for sad faces. In addition, the network properties of sad faces were significantly correlated with PHQ-9 scores for MDD group. These findings may provide further explanation for understanding the MDD’s neural mechanism of attention bias during facial emotional tasks.</p>","PeriodicalId":10500,"journal":{"name":"Cognitive Neurodynamics","volume":"13 1","pages":""},"PeriodicalIF":3.7,"publicationDate":"2024-04-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140628639","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Deep-learning-optimized microstate network analysis for early Parkinson’s disease with mild cognitive impairment 针对伴有轻度认知障碍的早期帕金森病的深度学习优化微状态网络分析
IF 3.7 3区 工程技术 Q2 NEUROSCIENCES Pub Date : 2024-04-18 DOI: 10.1007/s11571-023-10016-6
Luxiao Zhang, Xiao Shen, Chunguang Chu, Shang Liu, Jiang Wang, Yanlin Wang, Jinghui Zhang, Tingyu Cao, Fei Wang, Xiaodong Zhu, Chen Liu

Graph-theory-based topological impairment of the whole-brain network has been verified to be one of the characteristics of mild cognitive impairment (MCI). However, two major challenges impede the further understanding of topological features for the personalized functional connectivity network of early Parkinson’s disease (ePD) with MCI. The uncertain of characteristic frequency band reflecting the abnormality of ePD-MCI and the setting of fixed length of sliding window at a second level in the construction of conventional brain network both limit a deeper exploration of network characteristics for ePD-MCI. Thus, a convolutional neural network is constructed first and the gradient-weighted class activation mapping method is used to determine the characteristic frequency band of the ePD-MCI. It is found that 1–4 Hz is a characteristic frequency band for recognizing MCI in ePD. Then, we propose a microstate window construction method based on electroencephalography microstate sequences to build brain functional network. By exploring the graph-theory-based topological features and their clinical correlations with cognitive impairment, it is shown that the clustering coefficient, global efficiency, and local efficiency of the occipital lobe significantly decrease in ePD-MCI, which reflects the low degree of nodes interconnection, low efficiency of parallel information transmission and low communication efficiency among the nodes in the brain network of the occipital lobe may be the neural marker of ePD-MCI. The finding of personalized topological impairments of the brain network may be a potential characteristic of early PD-MCI.

基于图论的全脑网络拓扑损伤已被证实是轻度认知障碍(MCI)的特征之一。然而,两大挑战阻碍了对早期帕金森病(ePD)合并 MCI 的个性化功能连接网络拓扑特征的进一步了解。反映 ePD-MCI 异常的特征频段的不确定性,以及传统脑网络构建中二级滑动窗口固定长度的设置,都限制了对 ePD-MCI 网络特征的深入探索。因此,首先构建卷积神经网络,并采用梯度加权类激活映射法确定 ePD-MCI 的特征频段。结果发现,1-4 Hz 是识别 ePD MCI 的特征频段。然后,我们提出了一种基于脑电图微状态序列的微状态窗口构建方法,以构建大脑功能网络。通过探索基于图论的拓扑特征及其与认知障碍的临床相关性,结果表明枕叶的聚类系数、全局效率和局部效率在ePD-MCI中显著下降,这反映了枕叶脑网络中节点互联程度低、并行信息传输效率低、节点间通信效率低,可能是ePD-MCI的神经标志。脑网络个性化拓扑损伤的发现可能是早期 PD-MCI 的潜在特征。
{"title":"Deep-learning-optimized microstate network analysis for early Parkinson’s disease with mild cognitive impairment","authors":"Luxiao Zhang, Xiao Shen, Chunguang Chu, Shang Liu, Jiang Wang, Yanlin Wang, Jinghui Zhang, Tingyu Cao, Fei Wang, Xiaodong Zhu, Chen Liu","doi":"10.1007/s11571-023-10016-6","DOIUrl":"https://doi.org/10.1007/s11571-023-10016-6","url":null,"abstract":"<p>Graph-theory-based topological impairment of the whole-brain network has been verified to be one of the characteristics of mild cognitive impairment (MCI). However, two major challenges impede the further understanding of topological features for the personalized functional connectivity network of early Parkinson’s disease (ePD) with MCI. The uncertain of characteristic frequency band reflecting the abnormality of ePD-MCI and the setting of fixed length of sliding window at a second level in the construction of conventional brain network both limit a deeper exploration of network characteristics for ePD-MCI. Thus, a convolutional neural network is constructed first and the gradient-weighted class activation mapping method is used to determine the characteristic frequency band of the ePD-MCI. It is found that 1–4 Hz is a characteristic frequency band for recognizing MCI in ePD. Then, we propose a microstate window construction method based on electroencephalography microstate sequences to build brain functional network. By exploring the graph-theory-based topological features and their clinical correlations with cognitive impairment, it is shown that the clustering coefficient, global efficiency, and local efficiency of the occipital lobe significantly decrease in ePD-MCI, which reflects the low degree of nodes interconnection, low efficiency of parallel information transmission and low communication efficiency among the nodes in the brain network of the occipital lobe may be the neural marker of ePD-MCI. The finding of personalized topological impairments of the brain network may be a potential characteristic of early PD-MCI.</p>","PeriodicalId":10500,"journal":{"name":"Cognitive Neurodynamics","volume":"8 1","pages":""},"PeriodicalIF":3.7,"publicationDate":"2024-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140628684","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Emotional reactivity and its impact on neural circuitry for attention-emotion interaction through regression-based machine learning model 通过基于回归的机器学习模型研究情绪反应及其对注意力-情绪互动神经回路的影响
IF 3.7 3区 工程技术 Q2 NEUROSCIENCES Pub Date : 2024-04-16 DOI: 10.1007/s11571-024-10106-z
Raghavendra Prasad, Shashikanta Tarai, Arindam Bit

Attentional paradigm can have a significant influence on the processing and experience of positive and negative emotions. Attentional mechanism refers to the tendency to selectively attend to a particular stimulus while ignoring others. In the context of emotions, individuals may exhibit attentional biases towards either positive or negative emotional stimuli. By directing attention towards a specific stimulus, individuals can modulate their emotional responses. When attention is directed towards negative or threatening stimuli, it can intensify negative emotions such as fear, sadness, anger and anxiety. Conversely, directing attention away from negative stimuli can reduce emotional reactivity and promote emotional regulation. Similarly, paying attention to positive stimuli can amplify positive emotions and facilitate positive emotional experiences. Attentional paradigms are also responsible for cognitive appraisal of emotional stimuli. The allocation of attention can shape how emotional stimuli are evaluated and categorized, influencing the subsequent emotional response. Since the relationship between attention and emotions is complex and can vary across individuals and contexts, it is important to understand the underlying cognitive neural dynamics of the same. Custom rank allocation model (CRAM) was used to decode the underlying neural dynamics of cognitive and emotional resource sharing through the non-significant EEG channels. During the main effect of global–local (GL), CRAM ranks and scores indicated that the EEG channels C4, PZ, OZ, and P4 were found to be the most non-significant channels. Similarly, CRAM ranks and scores of the interaction effects between global–local and positive emotion-negative emotion and the interaction effects between global–local and frequent-deviant-equal indicated midline central EEG channels CZ, PZ, FZ and OZ to be the main contributor of the cognitive and emotional resources to others. Understanding the dynamics of attention-emotion conflicts with reference to significant and non-significant channels is important to gain insights into the complex computational interplay between attention and emotion, leading to a deeper understanding of human cognition and emotion regulation.

注意范式会对积极和消极情绪的处理和体验产生重大影响。注意机制指的是有选择地注意某一特定刺激而忽略其他刺激的倾向。在情绪方面,个体可能会对积极或消极的情绪刺激表现出注意偏差。通过将注意力引向特定的刺激,个体可以调节自己的情绪反应。当注意力指向负面或威胁性刺激时,会加剧恐惧、悲伤、愤怒和焦虑等负面情绪。相反,将注意力从负面刺激上转移开,可以降低情绪反应,促进情绪调节。同样,注意积极的刺激可以放大积极情绪,促进积极的情绪体验。注意范式也负责对情绪刺激进行认知评估。注意力的分配会影响对情绪刺激的评价和分类,从而影响随后的情绪反应。由于注意力与情绪之间的关系很复杂,而且会因个体和情境的不同而有所差异,因此了解其背后的认知神经动态非常重要。研究人员使用自定义等级分配模型(CRAM),通过非显著脑电图通道解码认知和情绪资源共享的潜在神经动态。在全局-局部(GL)主效应期间,CRAM 的等级和得分表明,脑电图通道 C4、PZ、OZ 和 P4 是最不显著的通道。同样,全局-局部与积极情绪-消极情绪之间的交互效应以及全局-局部与频繁-偏差-平等之间的交互效应的 CRAM 等级和得分表明,中线中心脑电图通道 CZ、PZ、FZ 和 OZ 是认知和情绪资源对他人的主要贡献者。参照重要通道和非重要通道了解注意力-情绪冲突的动态,对于深入了解注意力和情绪之间复杂的计算相互作用非常重要,从而加深对人类认知和情绪调节的理解。
{"title":"Emotional reactivity and its impact on neural circuitry for attention-emotion interaction through regression-based machine learning model","authors":"Raghavendra Prasad, Shashikanta Tarai, Arindam Bit","doi":"10.1007/s11571-024-10106-z","DOIUrl":"https://doi.org/10.1007/s11571-024-10106-z","url":null,"abstract":"<p>Attentional paradigm can have a significant influence on the processing and experience of positive and negative emotions. Attentional mechanism refers to the tendency to selectively attend to a particular stimulus while ignoring others. In the context of emotions, individuals may exhibit attentional biases towards either positive or negative emotional stimuli. By directing attention towards a specific stimulus, individuals can modulate their emotional responses. When attention is directed towards negative or threatening stimuli, it can intensify negative emotions such as fear, sadness, anger and anxiety. Conversely, directing attention away from negative stimuli can reduce emotional reactivity and promote emotional regulation. Similarly, paying attention to positive stimuli can amplify positive emotions and facilitate positive emotional experiences. Attentional paradigms are also responsible for cognitive appraisal of emotional stimuli. The allocation of attention can shape how emotional stimuli are evaluated and categorized, influencing the subsequent emotional response. Since the relationship between attention and emotions is complex and can vary across individuals and contexts, it is important to understand the underlying cognitive neural dynamics of the same. Custom rank allocation model (CRAM) was used to decode the underlying neural dynamics of cognitive and emotional resource sharing through the non-significant EEG channels. During the main effect of global–local (GL), CRAM ranks and scores indicated that the EEG channels C4, PZ, OZ, and P4 were found to be the most non-significant channels. Similarly, CRAM ranks and scores of the interaction effects between global–local and positive emotion-negative emotion and the interaction effects between global–local and frequent-deviant-equal indicated midline central EEG channels CZ, PZ, FZ and OZ to be the main contributor of the cognitive and emotional resources to others. Understanding the dynamics of attention-emotion conflicts with reference to significant and non-significant channels is important to gain insights into the complex computational interplay between attention and emotion, leading to a deeper understanding of human cognition and emotion regulation.</p>","PeriodicalId":10500,"journal":{"name":"Cognitive Neurodynamics","volume":"251 1","pages":""},"PeriodicalIF":3.7,"publicationDate":"2024-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140615482","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Effect of adult hippocampal neurogenesis on pattern separation and its applications 成年海马神经发生对模式分离的影响及其应用
IF 3.7 3区 工程技术 Q2 NEUROSCIENCES Pub Date : 2024-04-16 DOI: 10.1007/s11571-024-10110-3
Zengbin Wang, Kai Yang, Xiaojuan Sun

Adult hippocampal neurogenesis (AHN) is considered essential in memory formation. The dentate gyrus neural network containing newborn dentate gyrus granule cells at the critical period (4–6 weeks) have been widely discussed in neurophysiological and behavioral experiments. However, how newborn dentate gyrus granule cells at this critical period influence pattern separation of dentate gyrus remains unclear. To address this issue, we propose a biologically related dentate gyrus neural network model with AHN. By Leveraging this model, we find pattern separation is enhanced at the medium level of neurogenesis (5% of mature granule cells). This is because the sparse firing of mature granule cells is increased. We can understand this change from the following two aspects. On one hand, newborn granule cells compete with mature granule cells for inputs from the entorhinal cortex, thereby weakening the firing of mature granule cells. On the other hand, newborn granule cells effectively enhance the feedback inhibition level of the network by promoting the firing of interneurons (Mossy cells and Basket cells) and then indirectly regulating the sparse firing of mature granule cells. To verify the validity of the model for pattern separation, we apply the proposed model to a similar concept separation task and reveal that our model outperforms the original model counterparts in this task.

成人海马神经发生(AHN)被认为是记忆形成的关键。在神经生理学和行为学实验中,包含关键期(4-6 周)新生齿状回颗粒细胞的齿状回神经网络已被广泛讨论。然而,这一关键期的新生齿状回颗粒细胞如何影响齿状回的模式分离仍不清楚。为了解决这个问题,我们提出了一个与 AHN 生物学相关的齿状回神经网络模型。通过利用该模型,我们发现在中等神经发生水平(5% 的成熟颗粒细胞)时,模式分离会增强。这是因为成熟颗粒细胞的稀疏发射增加了。我们可以从以下两个方面来理解这种变化。一方面,新生颗粒细胞与成熟颗粒细胞竞争来自内皮层的输入,从而削弱了成熟颗粒细胞的发射。另一方面,新生颗粒细胞通过促进中间神经元(苔藓细胞和篮状细胞)的发射,进而间接调节成熟颗粒细胞的稀疏发射,从而有效提高网络的反馈抑制水平。为了验证该模型在模式分离方面的有效性,我们将所提出的模型应用于类似的概念分离任务,结果表明我们的模型在该任务中的表现优于原始模型。
{"title":"Effect of adult hippocampal neurogenesis on pattern separation and its applications","authors":"Zengbin Wang, Kai Yang, Xiaojuan Sun","doi":"10.1007/s11571-024-10110-3","DOIUrl":"https://doi.org/10.1007/s11571-024-10110-3","url":null,"abstract":"<p>Adult hippocampal neurogenesis (AHN) is considered essential in memory formation. The dentate gyrus neural network containing newborn dentate gyrus granule cells at the critical period (4–6 weeks) have been widely discussed in neurophysiological and behavioral experiments. However, how newborn dentate gyrus granule cells at this critical period influence pattern separation of dentate gyrus remains unclear. To address this issue, we propose a biologically related dentate gyrus neural network model with AHN. By Leveraging this model, we find pattern separation is enhanced at the medium level of neurogenesis (5% of mature granule cells). This is because the sparse firing of mature granule cells is increased. We can understand this change from the following two aspects. On one hand, newborn granule cells compete with mature granule cells for inputs from the entorhinal cortex, thereby weakening the firing of mature granule cells. On the other hand, newborn granule cells effectively enhance the feedback inhibition level of the network by promoting the firing of interneurons (Mossy cells and Basket cells) and then indirectly regulating the sparse firing of mature granule cells. To verify the validity of the model for pattern separation, we apply the proposed model to a similar concept separation task and reveal that our model outperforms the original model counterparts in this task.</p>","PeriodicalId":10500,"journal":{"name":"Cognitive Neurodynamics","volume":"16 1","pages":""},"PeriodicalIF":3.7,"publicationDate":"2024-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140615486","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Motor imagery decoding using source optimized transfer learning based on multi-loss fusion CNN 利用基于多损失融合 CNN 的源优化迁移学习进行运动图像解码
IF 3.7 3区 工程技术 Q2 NEUROSCIENCES Pub Date : 2024-04-10 DOI: 10.1007/s11571-024-10100-5
Jun Ma, Banghua Yang, Fenqi Rong, Shouwei Gao, Wen Wang

Transfer learning is increasingly used to decode multi-class motor imagery tasks. Previous transfer learning ignored the optimizability of the source model, weakened the adaptability to the target domain and limited the performance. This paper first proposes the multi-loss fusion convolutional neural network (MF-CNN) to make an optimizable source model. Then we propose a novel source optimized transfer learning (SOTL), which optimizes the source model to make it more in line with the target domain's features to improve the target model's performance. We transfer the model trained from 16 healthy subjects to 16 stroke patients. The average classification accuracy achieves 51.2 ± 0.17% in the four types of unilateral upper limb motor imagery tasks, which is significantly higher than the classification accuracy of deep learning (p < 0.001) and transfer learning (p < 0.05). In this paper, an MI model from the data of healthy subjects can be used for the classification of stroke patients and can demonstrate good classification results, which provides experiential support for the study of transfer learning and the modeling of stroke rehabilitation training.

迁移学习越来越多地用于解码多类运动图像任务。以往的迁移学习忽视了源模型的可优化性,削弱了对目标域的适应性,限制了迁移学习的性能。本文首先提出了多损失融合卷积神经网络(MF-CNN)来建立可优化的源模型。然后,我们提出了一种新颖的源优化迁移学习(SOTL),通过优化源模型使其更符合目标领域的特征,从而提高目标模型的性能。我们将从 16 名健康人身上训练出来的模型移植到 16 名中风患者身上。在四种类型的单侧上肢运动想象任务中,平均分类准确率达到 51.2 ± 0.17%,明显高于深度学习(p <0.001)和迁移学习(p <0.05)的分类准确率。本文将健康受试者数据中的运动学模型用于脑卒中患者的分类,并取得了良好的分类效果,为迁移学习的研究和脑卒中康复训练的建模提供了经验支持。
{"title":"Motor imagery decoding using source optimized transfer learning based on multi-loss fusion CNN","authors":"Jun Ma, Banghua Yang, Fenqi Rong, Shouwei Gao, Wen Wang","doi":"10.1007/s11571-024-10100-5","DOIUrl":"https://doi.org/10.1007/s11571-024-10100-5","url":null,"abstract":"<p>Transfer learning is increasingly used to decode multi-class motor imagery tasks. Previous transfer learning ignored the optimizability of the source model, weakened the adaptability to the target domain and limited the performance. This paper first proposes the multi-loss fusion convolutional neural network (MF-CNN) to make an optimizable source model. Then we propose a novel source optimized transfer learning (SOTL), which optimizes the source model to make it more in line with the target domain's features to improve the target model's performance. We transfer the model trained from 16 healthy subjects to 16 stroke patients. The average classification accuracy achieves 51.2 ± 0.17% in the four types of unilateral upper limb motor imagery tasks, which is significantly higher than the classification accuracy of deep learning (<i>p</i> &lt; 0.001) and transfer learning (<i>p</i> &lt; 0.05). In this paper, an MI model from the data of healthy subjects can be used for the classification of stroke patients and can demonstrate good classification results, which provides experiential support for the study of transfer learning and the modeling of stroke rehabilitation training.</p>","PeriodicalId":10500,"journal":{"name":"Cognitive Neurodynamics","volume":"234 1","pages":""},"PeriodicalIF":3.7,"publicationDate":"2024-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140561645","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
An improved CapsNet based on data augmentation for driver vigilance estimation with forehead single-channel EEG 基于数据增强的改进型 CapsNet,利用前额单通道脑电图估测驾驶员警觉性
IF 3.7 3区 工程技术 Q2 NEUROSCIENCES Pub Date : 2024-04-10 DOI: 10.1007/s11571-024-10105-0
Huizhou Yang, Jingwen Huang, Yifei Yu, Zhigang Sun, Shouyi Zhang, Yunfei Liu, Han Liu, Lijuan Xia

Various studies have shown that it is necessary to estimate the drivers’ vigilance to reduce the occurrence of traffic accidents. Most existing EEG-based vigilance estimation studies have been performed on intra-subject and multi-channel signals, and these methods are too costly and complicated to implement in practice. Hence, aiming at the problem of cross-subject vigilance estimation of single-channel EEG signals, an estimation algorithm based on capsule network (CapsNet) is proposed. Firstly, we propose a new construction method of the input feature maps to fit the characteristics of CapsNet to improve the algorithm accuracy. Meanwhile, the self-attention mechanism is incorporated in the algorithm to focus on the key information in feature maps. Secondly, we propose substituting the traditional multi-channel signals with the single-channel signals to improve the utility of algorithm. Thirdly, since the single-channel signals carry fewer dimensions of the information compared to the multi-channel signals, we use the conditional generative adversarial network to improve the accuracy of single-channel signals by increasing the amount of data. The proposed algorithm is verified on the SEED-VIG, and Root-mean-square-error (RMSE) and Pearson Correlation Coefficient (PCC) are used as the evaluation metrics. The results show that the proposed algorithm improves the computing speed while the RMSE is reduced by 3%, and the PCC is improved by 12% compared to the mainstream algorithm. Experiment results prove the feasibility of using forehead single-channel EEG signals for cross-subject vigilance estimation and offering the possibility of lightweight EEG vigilance estimation devices for practical applications.

各种研究表明,有必要对驾驶员的警觉性进行估计,以减少交通事故的发生。现有的基于脑电图的警觉性估计研究大多是针对受试者内部和多通道信号进行的,这些方法在实际应用中成本过高且过于复杂。因此,针对单通道脑电信号的跨主体警觉性估计问题,提出了一种基于胶囊网络(CapsNet)的估计算法。首先,我们提出了一种新的输入特征图构建方法,以适应 CapsNet 的特点,从而提高算法的准确性。同时,在算法中加入自我关注机制,以关注特征图中的关键信息。其次,我们提出用单信道信号取代传统的多信道信号,以提高算法的实用性。第三,由于单通道信号比多通道信号携带的信息维度更少,我们使用条件生成对抗网络,通过增加数据量来提高单通道信号的准确性。我们在 SEED-VIG 上验证了所提出的算法,并将均方根误差(RMSE)和皮尔逊相关系数(PCC)作为评价指标。结果表明,与主流算法相比,拟议算法提高了计算速度,同时均方根误差降低了 3%,皮尔逊相关系数提高了 12%。实验结果证明了使用前额单通道脑电信号进行跨被试警觉性估计的可行性,并为实际应用中的轻量级脑电警觉性估计设备提供了可能。
{"title":"An improved CapsNet based on data augmentation for driver vigilance estimation with forehead single-channel EEG","authors":"Huizhou Yang, Jingwen Huang, Yifei Yu, Zhigang Sun, Shouyi Zhang, Yunfei Liu, Han Liu, Lijuan Xia","doi":"10.1007/s11571-024-10105-0","DOIUrl":"https://doi.org/10.1007/s11571-024-10105-0","url":null,"abstract":"<p>Various studies have shown that it is necessary to estimate the drivers’ vigilance to reduce the occurrence of traffic accidents. Most existing EEG-based vigilance estimation studies have been performed on intra-subject and multi-channel signals, and these methods are too costly and complicated to implement in practice. Hence, aiming at the problem of cross-subject vigilance estimation of single-channel EEG signals, an estimation algorithm based on capsule network (CapsNet) is proposed. Firstly, we propose a new construction method of the input feature maps to fit the characteristics of CapsNet to improve the algorithm accuracy. Meanwhile, the self-attention mechanism is incorporated in the algorithm to focus on the key information in feature maps. Secondly, we propose substituting the traditional multi-channel signals with the single-channel signals to improve the utility of algorithm. Thirdly, since the single-channel signals carry fewer dimensions of the information compared to the multi-channel signals, we use the conditional generative adversarial network to improve the accuracy of single-channel signals by increasing the amount of data. The proposed algorithm is verified on the SEED-VIG, and Root-mean-square-error (RMSE) and Pearson Correlation Coefficient (PCC) are used as the evaluation metrics. The results show that the proposed algorithm improves the computing speed while the RMSE is reduced by 3%, and the PCC is improved by 12% compared to the mainstream algorithm. Experiment results prove the feasibility of using forehead single-channel EEG signals for cross-subject vigilance estimation and offering the possibility of lightweight EEG vigilance estimation devices for practical applications.</p>","PeriodicalId":10500,"journal":{"name":"Cognitive Neurodynamics","volume":"148 1","pages":""},"PeriodicalIF":3.7,"publicationDate":"2024-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140561334","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
期刊
Cognitive Neurodynamics
全部 Acc. Chem. Res. ACS Applied Bio Materials ACS Appl. Electron. Mater. ACS Appl. Energy Mater. ACS Appl. Mater. Interfaces ACS Appl. Nano Mater. ACS Appl. Polym. Mater. ACS BIOMATER-SCI ENG ACS Catal. ACS Cent. Sci. ACS Chem. Biol. ACS Chemical Health & Safety ACS Chem. Neurosci. ACS Comb. Sci. ACS Earth Space Chem. ACS Energy Lett. ACS Infect. Dis. ACS Macro Lett. ACS Mater. Lett. ACS Med. Chem. Lett. ACS Nano ACS Omega ACS Photonics ACS Sens. ACS Sustainable Chem. Eng. ACS Synth. Biol. Anal. Chem. BIOCHEMISTRY-US Bioconjugate Chem. BIOMACROMOLECULES Chem. Res. Toxicol. Chem. Rev. Chem. Mater. CRYST GROWTH DES ENERG FUEL Environ. Sci. Technol. Environ. Sci. Technol. Lett. Eur. J. Inorg. Chem. IND ENG CHEM RES Inorg. Chem. J. Agric. Food. Chem. J. Chem. Eng. Data J. Chem. Educ. J. Chem. Inf. Model. J. Chem. Theory Comput. J. Med. Chem. J. Nat. Prod. J PROTEOME RES J. Am. Chem. Soc. LANGMUIR MACROMOLECULES Mol. Pharmaceutics Nano Lett. Org. Lett. ORG PROCESS RES DEV ORGANOMETALLICS J. Org. Chem. J. Phys. Chem. J. Phys. Chem. A J. Phys. Chem. B J. Phys. Chem. C J. Phys. Chem. Lett. Analyst Anal. Methods Biomater. Sci. Catal. Sci. Technol. Chem. Commun. Chem. Soc. Rev. CHEM EDUC RES PRACT CRYSTENGCOMM Dalton Trans. Energy Environ. Sci. ENVIRON SCI-NANO ENVIRON SCI-PROC IMP ENVIRON SCI-WAT RES Faraday Discuss. Food Funct. Green Chem. Inorg. Chem. Front. Integr. Biol. J. Anal. At. Spectrom. J. Mater. Chem. A J. Mater. Chem. B J. Mater. Chem. C Lab Chip Mater. Chem. Front. Mater. Horiz. MEDCHEMCOMM Metallomics Mol. Biosyst. Mol. Syst. Des. Eng. Nanoscale Nanoscale Horiz. Nat. Prod. Rep. New J. Chem. Org. Biomol. Chem. Org. Chem. Front. PHOTOCH PHOTOBIO SCI PCCP Polym. Chem.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1