您的检索：
学者姓名：李明爱
精炼检索结果：
年份
成果类型
收录类型
来源
综合
合作者
语言
清除所有精炼条件
摘要 ：
Motor imagery electroencephalogram (MI-EEG) plays an important role in the brain computer interface-based neuro-rehabilitation, and it is challenging to make the recognition model have the self-learning and updating ability with the recovery process. Broad learning system (BLS) may be perfect duo to the incremental learning and dynamic broad expansion. However, its natural shallow network and simple mappings in generating feature nodes and enhancement nodes limit the feature mapping capacity and yield performance degradation for new data. In this paper, we develop a session-incremental broad learning system (SIBLS) to adaptively recognize the incremental sessions of MI-EEG with changing probability distributions. A multiscale feature mapping block (MFMB) is designed to extract the global and local features for reinforcing feature mapping. Then, the multiple key feature distillation blocks (KFDB), which are constructed by manifold learning embedded sparse autoencoders, are further employed to extract compact and highly geometrically relevant features for producing enhancement nodes. For the incremental sessions, Pearson's correlation coefficient constraints (PCCs) and taskdependent correlation constraints (TCs) are added to KFDB and output layer respectively to make the same category closer between adjacent sessions. The experiments are conducted on two public datasets, which include two and five sessions respectively, the time-frequency spectrum of each electrode is simultaneously input to SIBLS, separately achieving the average accuracies of all sessions 79.62% and 87.59%. Experiment results show that the perfect plasticity of SIBLS derives in the main from the strong feature mapping of MFMB and KFDB, and the forgetting is effectively inhibited by introducing constraints as well.
关键词 ：
Incremental learning Incremental learning Key features distillation Key features distillation Motor imagery EEG Motor imagery EEG Multiscale features mapping Multiscale features mapping Broad learning system Broad learning system
引用：
复制并粘贴一种已设定好的引用格式，或利用其中一个链接导入到文献管理软件中。
| GB/T 7714 | Yang, Yufei , Li, Mingai , Liu, Hanlin et al. A session-incremental broad learning system for motor imagery EEG classification [J]. | BIOMEDICAL SIGNAL PROCESSING AND CONTROL , 2024 , 97 . |
| MLA | Yang, Yufei et al. "A session-incremental broad learning system for motor imagery EEG classification" . | BIOMEDICAL SIGNAL PROCESSING AND CONTROL 97 (2024) . |
| APA | Yang, Yufei , Li, Mingai , Liu, Hanlin , Li, Zhi . A session-incremental broad learning system for motor imagery EEG classification . | BIOMEDICAL SIGNAL PROCESSING AND CONTROL , 2024 , 97 . |
| 导入链接 | NoteExpress RIS BibTex |
摘要 ：
本发明公开了基于通道优选和动态卷积神经网络的癫痫检测方法, 本发明利用癫痫发作时脑电图的高频振荡特征初步定位癫痫发作起始区域，并经统计计算确定发作起始区域的中心导联；进而，计算中心导联与其他导联间的互信息与基尼指数，获得中心导联的动态相关性指数；接着，设计一种具有通道注意力机制的动态卷积神经网络模型，并结合导联的动态相关性指数实现癫痫检测。该模型具有根据输入通道特征动态改变卷积层参数的能力，增强了癫痫检测过程中的自适应性和鲁棒性。本发明方法能够获取源于发作起始区域的最优导联排序，且在不同受试者身上有良好的癫痫检测效果。
引用：
复制并粘贴一种已设定好的引用格式，或利用其中一个链接导入到文献管理软件中。
| GB/T 7714 | 李明爱 , 张紫钺 , 孙炎珺 . 基于通道优选和动态卷积神经网络的癫痫检测方法 : CN202310045589.6[P]. | 2023-01-30 . |
| MLA | 李明爱 et al. "基于通道优选和动态卷积神经网络的癫痫检测方法" : CN202310045589.6. | 2023-01-30 . |
| APA | 李明爱 , 张紫钺 , 孙炎珺 . 基于通道优选和动态卷积神经网络的癫痫检测方法 : CN202310045589.6. | 2023-01-30 . |
| 导入链接 | NoteExpress RIS BibTex |
摘要 ：
本发明公开了基于3D插值和3DCNN的运动想象任务分类方法，首先，对运动想象脑电信号进行带通滤波处理；然后，利用快速傅里叶变换(FFT)对每个电极的EEG信号进行频域变换，并求取功率值；接着，将头皮电极的3D坐标投影到3D空间中，并使用3D插值算法对功率值进行插值，生成包含电极的3D真实空间位置信息的3D插值特征图像；最后，设计了一个3D卷积神经网络(3DCNN)来匹配3D插值特征图像的特点进行特征提取和分类。本发明体现了运动想象激活的深度信息，将电极的精确三维空间信息编码到3D插值成像图中，较好地匹配了3DCNN的空间卷积能力。
引用：
复制并粘贴一种已设定好的引用格式，或利用其中一个链接导入到文献管理软件中。
| GB/T 7714 | 李明爱 , 张京 , 孙炎珺 . 基于3D插值和3DCNN的运动想象任务分类方法 : CN202310010193.8[P]. | 2023-01-04 . |
| MLA | 李明爱 et al. "基于3D插值和3DCNN的运动想象任务分类方法" : CN202310010193.8. | 2023-01-04 . |
| APA | 李明爱 , 张京 , 孙炎珺 . 基于3D插值和3DCNN的运动想象任务分类方法 : CN202310010193.8. | 2023-01-04 . |
| 导入链接 | NoteExpress RIS BibTex |
摘要 ：
Deep learning has been applied to the recognition of motor imagery electroencephalograms (MI-EEG) in brain-computer interface, and the performance results depend on data representation as well as neural network structure. Especially, MI-EEG is so complex with the characteristics of non-stationarity, specific rhythms, and uneven distribution; however, its multidimensional feature information is difficult to be fused and enhanced simultaneously in the existing recognition methods. In this paper, a novel channel importance (NCI) based on time-frequency analysis is proposed to develop an image sequence generation method (NCI-ISG) for enhancing the integrity of data representation and highlighting the contribution inequalities of different channels as well. Each electrode of MI-EEG is converted to a time-frequency spectrum by utilizing short-time Fourier transform; the corresponding part to 8-30 Hz is combined with random forest algorithm for computing NCI; and it is further divided into three sub-images covered by alpha (8-13 Hz), beta(1) (13-21 Hz), and beta(2) (21-30 Hz) bands; their spectral powers are further weighted by NCI and interpolated to 2-dimensional electrode coordinates, producing three main sub-band image sequences. Then, a parallel multi-branch convolutional neural network and gate recurrent unit (PMBCG) is designed to successively extract and identify the spatial-spectral and temporal features from the image sequences. Two public four-class MI-EEG datasets are adopted; the proposed classification method respectively achieves the average accuracies of 98.26% and 80.62% by 10-fold cross-validation experiment; and its statistical performance is also evaluated by multi-indexes, such as Kappa value, confusion matrix, and ROC curve. Extensive experiment results show that NCI-ISG + PMBCG can yield great performance on MI-EEG classification compared to state-of-the-art methods. The proposed NCI-ISG can enhance the feature representation of time-frequency-space domains and match well with PMBCG, which improves the recognition accuracies of MI tasks and demonstrates the preferable reliability and distinguishable ability.
关键词 ：
Gate recurrent unit Gate recurrent unit Convolutional neural network Convolutional neural network Novel channel importance Novel channel importance Brain computer interface Brain computer interface Motor imagery electroencephalogram Motor imagery electroencephalogram
引用：
复制并粘贴一种已设定好的引用格式，或利用其中一个链接导入到文献管理软件中。
| GB/T 7714 | Wang, Linlin , Li, Mingai , Zhang, Liyuan . Recognize enhanced temporal-spatial-spectral features with a parallel multi-branch CNN and GRU [J]. | MEDICAL & BIOLOGICAL ENGINEERING & COMPUTING , 2023 , 61 (8) : 2013-2032 . |
| MLA | Wang, Linlin et al. "Recognize enhanced temporal-spatial-spectral features with a parallel multi-branch CNN and GRU" . | MEDICAL & BIOLOGICAL ENGINEERING & COMPUTING 61 . 8 (2023) : 2013-2032 . |
| APA | Wang, Linlin , Li, Mingai , Zhang, Liyuan . Recognize enhanced temporal-spatial-spectral features with a parallel multi-branch CNN and GRU . | MEDICAL & BIOLOGICAL ENGINEERING & COMPUTING , 2023 , 61 (8) , 2013-2032 . |
| 导入链接 | NoteExpress RIS BibTex |
摘要 ：
Motor imagery (MI) decoding is the core of an intelligent rehabilitation system in brain computer interface, and it has a potential advantage by using source signals, which have higher spatial resolution and the same time resolution compared to scalp electroencephalography (EEG). However, how to delve and utilize the personalized frequency characteristic of dipoles for improving decoding performance has not been paid sufficient attention. In this paper, a novel dipole feature imaging (DFI) and a hybrid convolutional neural network (HCNN) with an embedded squeeze-and-excitation block (SEB), denoted as DFI-HCNN, are proposed for decoding MI tasks. EEG source imaging technique is used for brain source estimation, and each sub-band spectrum powers of all dipoles are calculated through frequency analysis and band division. Then, the 3D space information of dipoles is retrieved, and by using azimuthal equidistant projection algorithm it is transformed to a 2D plane, which is combined with nearest neighbor interpolation to generate multi sub-band dipole feature images. Furthermore, a HCNN is designed and applied to the ensemble of sub-band dipole feature images, from which the importance of sub-bands is acquired to adjust the corresponding attentions adaptively by SEB. Ten-fold cross-validation experiments on two public datasets achieve the comparatively higher decoding accuracies of 84.23% and 92.62%, respectively. The experiment results show that DFI is an effective feature representation, and HCNN with an embedded SEB can enhance the useful frequency information of dipoles for improving MI decoding.
关键词 ：
EEG source imaging EEG source imaging Squeeze-and-excitation block Squeeze-and-excitation block Brain computer interface Brain computer interface Hybrid convolutional neural network Hybrid convolutional neural network Motor imagery Motor imagery
引用：
复制并粘贴一种已设定好的引用格式，或利用其中一个链接导入到文献管理软件中。
| GB/T 7714 | Wang, Linlin , Li, Mingai . Decoding motor imagery based on dipole feature imaging and a hybrid CNN with embedded squeeze-and-excitation block [J]. | BIOCYBERNETICS AND BIOMEDICAL ENGINEERING , 2023 , 43 (4) : 751-762 . |
| MLA | Wang, Linlin et al. "Decoding motor imagery based on dipole feature imaging and a hybrid CNN with embedded squeeze-and-excitation block" . | BIOCYBERNETICS AND BIOMEDICAL ENGINEERING 43 . 4 (2023) : 751-762 . |
| APA | Wang, Linlin , Li, Mingai . Decoding motor imagery based on dipole feature imaging and a hybrid CNN with embedded squeeze-and-excitation block . | BIOCYBERNETICS AND BIOMEDICAL ENGINEERING , 2023 , 43 (4) , 751-762 . |
| 导入链接 | NoteExpress RIS BibTex |
摘要 ：
Electroencephalography (EEG) contains rich information about brain activity. Classification based on motor imagery EEG (MI-EEG) is essential for active intelligent rehabilitation using brain-computer interface technology. However, most of the current MI-EEG decoding methods are dedicated to the study of efficient time-frequency feature extraction from the raw EEG, ignoring the spatial features associated with electrode distribution. Therefore, this paper proposed an MI-EEG classification method using a combination of three dimensional (3D) spatial interpolation and 3D convolutional neural network (3DCNN) to fully utilize the 3D spatial features of electrodes. First, the frequency transformation was applied to the EEG signal at each electrode using the fast Fourier transform and the energy value was obtained. Then, the 3D coordinates of the scalp electrodes were projected into the 3D space and the energy values were interpolated using the 3D interpolation method to generate a 3D feature image containing the 3D real spatial location information of the electrodes. Finally, a 3DCNN was designed to match the 3D feature image for feature extraction and recognition. The proposed method obtained 77.19% accuracy in the BCI Competition IV 2a dataset, which is higher than the existing decoding methods. Results from experiments validate the effectiveness of the proposed MI-EEG classification method.
关键词 ：
3D Interpolation 3D Interpolation EEG EEG Motor imagery Motor imagery 3DCNN 3DCNN Fast Fourier Transformation Fast Fourier Transformation
引用：
复制并粘贴一种已设定好的引用格式，或利用其中一个链接导入到文献管理软件中。
| GB/T 7714 | Li, Ming-ai , Zhang, Jing . A Novel Approach to MI-EEG Classification via 3D Interpolation and 3DCNN [J]. | 2023 35TH CHINESE CONTROL AND DECISION CONFERENCE, CCDC , 2023 : 3062-3066 . |
| MLA | Li, Ming-ai et al. "A Novel Approach to MI-EEG Classification via 3D Interpolation and 3DCNN" . | 2023 35TH CHINESE CONTROL AND DECISION CONFERENCE, CCDC (2023) : 3062-3066 . |
| APA | Li, Ming-ai , Zhang, Jing . A Novel Approach to MI-EEG Classification via 3D Interpolation and 3DCNN . | 2023 35TH CHINESE CONTROL AND DECISION CONFERENCE, CCDC , 2023 , 3062-3066 . |
| 导入链接 | NoteExpress RIS BibTex |
摘要 ：
At present, how to efficiently and effectively identify motor imagery tasks is still a huge challenge for the development of the Brain Computer Interface (BCI) systems in the field of human rehabilitation. Therefore, this paper proposes an optimized recognition method based on temporal features and spatial features re-representation. The Local Mean Decomposition (LMD) algorithm is used to extract the Product Functions (PFs) of the Motor Imagery Electroencephalogram (MI-EEG) signals and the Common Spatial Pattern (CSP) algorithm is applied to reconstruct the spatial distribution of each PF, then the MI-EEG signals are re-represented as features with temporal and spatial characteristics. The Probabilistic Neural Network (PNN) is constructed, in which the smoothing factor is optimized by the Particle Swarm Optimization (PSO). By introducing the PSO algorithm, the PNN can be adaptively determined according to the respective conditions of different subjects or datasets. The experimental results show, compared with the Support Vector Machine (SVM) based on feature re-representation and other state-of-the-art machine learning methods, the proposed method in this paper has both high recognition accuracy and adaptability. This optimized PNN with PSO method establishes a theoretical foundation and methodological guidance for the decoding of motor imagery recognition.
关键词 ：
particle swarm optimization particle swarm optimization feature re-representation feature re-representation motor imagery recognition motor imagery recognition probabilistic neural network probabilistic neural network optimization algorithm optimization algorithm
引用：
复制并粘贴一种已设定好的引用格式，或利用其中一个链接导入到文献管理软件中。
| GB/T 7714 | Yang, Yufei , Li, Mingai . Motor Imagery Recognition Based on an Optimized Probabilistic Neural Network with the Particle Swarm Optimization [J]. | 2023 35TH CHINESE CONTROL AND DECISION CONFERENCE, CCDC , 2023 : 4743-4748 . |
| MLA | Yang, Yufei et al. "Motor Imagery Recognition Based on an Optimized Probabilistic Neural Network with the Particle Swarm Optimization" . | 2023 35TH CHINESE CONTROL AND DECISION CONFERENCE, CCDC (2023) : 4743-4748 . |
| APA | Yang, Yufei , Li, Mingai . Motor Imagery Recognition Based on an Optimized Probabilistic Neural Network with the Particle Swarm Optimization . | 2023 35TH CHINESE CONTROL AND DECISION CONFERENCE, CCDC , 2023 , 4743-4748 . |
| 导入链接 | NoteExpress RIS BibTex |
摘要 ：
Because of insufficient data, cross-class transfer learning has potential prospects in motor imagery electroencephalogram (MI-EEG) based rehabilitation engineering, and it has not been effectively addressed to reduce cross-class variability between source and target domains and find the best class-to-class transitive correspondence (CCTC). In this paper, we propose an adaptive cross-class transfer learning (ACTL) framework with twolevel alignment (TLA) for MI decoding. By using the fast partitioning around medoids method, the central samples of each class are acquired from the source domain and target domain respectively. Then, they are applied to construct the central alignment matrix to realize the 1st-level domain alignment for any possible CCTC case. The 2nd-level subject alignment is performed by Euclidean alignment for each class of aligned source domain. Furthermore, the central samples of the target domain together with the two-level aligned source domain are mapped into tangent space, the resulting features are fed to a teacher convolutional neural network (TCNN), it and the transferred student CNN (SCNN) are trained successively, and their parameters of distillation loss are optimized automatically by a scaling-based grid search method. Experiments are conducted on a public MI-EEG dataset with multiple subjects and MI-tasks, the proposed framework can find the optimal SCNN associated with the best CCTC, which achieves a statistically significant average classification accuracy of 86.37%. The results suggest that TLA is helpful for increasing the distribution similarity between different domains, and the knowledge distillation embedded in ACTL framework greatly simplifies the SCNN and outperforms the complicated TCNN.
关键词 ：
Knowledge distillation Knowledge distillation Transfer learning Transfer learning Motor imagery Motor imagery Two-level alignment Two-level alignment Cross-class Cross-class
引用：
复制并粘贴一种已设定好的引用格式，或利用其中一个链接导入到文献管理软件中。
| GB/T 7714 | Xu, Dong-qin , Sun, Yan-jun , Li, Ming-ai . An adaptive cross-class transfer learning framework with two-level alignment [J]. | BIOMEDICAL SIGNAL PROCESSING AND CONTROL , 2023 , 86 . |
| MLA | Xu, Dong-qin et al. "An adaptive cross-class transfer learning framework with two-level alignment" . | BIOMEDICAL SIGNAL PROCESSING AND CONTROL 86 (2023) . |
| APA | Xu, Dong-qin , Sun, Yan-jun , Li, Ming-ai . An adaptive cross-class transfer learning framework with two-level alignment . | BIOMEDICAL SIGNAL PROCESSING AND CONTROL , 2023 , 86 . |
| 导入链接 | NoteExpress RIS BibTex |
摘要 ：
Domain adaptation, as an important branch of transfer learning, can be applied to cope with data insufficiency and high subject variabilities in motor imagery electroencephalogram (MI-EEG) based brain-computer interfaces. The existing methods generally focus on aligning data and feature distribution; however, aligning each source domain with the informative samples of the target domain and seeking the most appropriate source domains to enhance the classification effect has not been considered. In this paper, we propose a dual alignment-based multi-source domain adaptation framework, denoted DAMSDAF. Based on continuous wavelet transform, all channels of MI-EEG signals are converted respectively and the generated time-frequency spectrum images are stitched to construct multi-source domains and target domain. Then, the informative samples close to the decision boundary are found in the target domain by using entropy, and they are employed to align and reassign each source domain with normalized mutual information. Furthermore, a multi-branch deep network (MBDN) is designed, and the maximum mean discrepancy is embedded in each branch to realign the specific feature distribution. Each branch is separately trained by an aligned source domain, and all the single branch transfer accuracies are arranged in descending order and utilized for weighted prediction of MBDN. Therefore, the most suitable number of source domains with top weights can be automatically determined. Extensive experiments are conducted based on 3 public MI-EEG datasets. DAMSDAF achieves the classification accuracies of 92.56%, 69.45% and 89.57%, and the statistical analysis is performed by the kappa value and t-test. Experimental results show that DAMSDAF significantly improves the transfer effects compared to the present methods, indicating that dual alignment can sufficiently use the different weighted samples and even source domains at different levels as well as realizing optimal selection of multi-source domains.
关键词 ：
Transfer learning Transfer learning Weighted alignment Weighted alignment Maximum mean discrepancy Maximum mean discrepancy Motor imagery Motor imagery Domain adaptation Domain adaptation
引用：
复制并粘贴一种已设定好的引用格式，或利用其中一个链接导入到文献管理软件中。
| GB/T 7714 | Xu, Dong-qin , Li, Ming-ai . A dual alignment-based multi-source domain adaptation framework for motor imagery EEG classification [J]. | APPLIED INTELLIGENCE , 2022 , 53 (9) : 10766-10788 . |
| MLA | Xu, Dong-qin et al. "A dual alignment-based multi-source domain adaptation framework for motor imagery EEG classification" . | APPLIED INTELLIGENCE 53 . 9 (2022) : 10766-10788 . |
| APA | Xu, Dong-qin , Li, Ming-ai . A dual alignment-based multi-source domain adaptation framework for motor imagery EEG classification . | APPLIED INTELLIGENCE , 2022 , 53 (9) , 10766-10788 . |
| 导入链接 | NoteExpress RIS BibTex |
摘要 ：
本发明公开了基于D‑K分区的简化分布式偶极子模型建立与识别方法，具体包括：首先，利用不同的带通滤波器对原始MI‑EEG进行滤波，以挑选与运动想象活动相关的最优频带；然后，对挑选出的每个子带进行脑电逆变换，将头皮EEG转换为脑皮层中的偶极子；接着，获得基于神经解剖学D‑K分区的中心偶极子，以构建简化分布式偶极子模型，将大脑皮层中心偶极子的活动视为神经动力学系统，构建4D数据表达；最后，将多频带数据表达进行融合并输入至设计好的n分支并行的nB3DCNN中，从时‑频‑空三个维度进行综合特征提取与识别。本发明体现了不同频带下，偶极子在3D空间中幅值随着时间的变化，利用少量中心偶极子反映了整个大脑皮质层由运动想象引起的神经电活动。
引用：
复制并粘贴一种已设定好的引用格式，或利用其中一个链接导入到文献管理软件中。
| GB/T 7714 | 李明爱 , 阮秭威 , 孙炎珺 . 基于D-K分区的简化分布式偶极子模型建立与识别方法 : CN202210239817.9[P]. | 2022-03-12 . |
| MLA | 李明爱 et al. "基于D-K分区的简化分布式偶极子模型建立与识别方法" : CN202210239817.9. | 2022-03-12 . |
| APA | 李明爱 , 阮秭威 , 孙炎珺 . 基于D-K分区的简化分布式偶极子模型建立与识别方法 : CN202210239817.9. | 2022-03-12 . |
| 导入链接 | NoteExpress RIS BibTex |
导出
| 数据： |
选中 到 |
| 格式： |
