A convolutional neural network with sparse representation

Suppressing of Power Line Artifact From Electroencephalogram Measurements Using Sparsity in Frequency Domain

Electroencephalogram (EEG) plays an important role in brain disease diagnosis and research of brain-computer interface (BCI). However, the measurements of EEG are often exposed to strong interference of power line artifact (PLA). Digital notch filters (DNFs) can be applied to remove the PLA effectively, but it also results in severe signal distortions in the time domain. To address this problem, spectrum correction (SC) based methods can be utilized. These methods estimate harmonic parameters of the PLA such that compensation signals are produced to remove the noise. In order to ensure high accuracy during harmonic parameter estimations, a novel approach is proposed in this paper. This novel approach is based on the combination of sparse representation (SR) and SC. It can deeply mine the information of PLA in the frequency domain. Firstly, a ratio-based spectrum correction (RBSC) using rectangular window is employed to make rough estimation of the harmonic parameters of PLA. Secondly, the two spectral line closest to the estimated frequency are calculated. Thirdly, the two spectral lines with high amplitudes can be utilized as input of RBSC to make finer estimations of the harmonic parameters. Finally, a compensation signal, based on the extracted harmonic parameters, is generated to suppress PLA. Numerical simulations and actual EEG signals with PLA were used to evaluate the effectiveness of the improved approach. It is verified that this approach can effectively suppress the PLA without distorting the time-domain waveform of the EEG signal.

Improving the Classification Rate of Insulation Defects in Power Cables by Automatic Features Extraction and Sample Augmentation of Partial Discharge Signal

Conventional pattern recognition methods employed for differentiating the types of insulation defects in power cables usually rely on the manual extraction of partial discharge features, which is inefficient and easily affected by subjective uncertainty. This work addresses this problem by proposing a new framework based on the automatic features extraction of partial discharge signal. The method first applies a sliding time window to convert partial discharge signals in the time domain into two-dimensional images that serve directly as the input to the convolutional neural networks (CNNs). Then a nonlinear encoder is employed to automatically extract the features of the partial discharge image data as the input of CNNs for classification. In addition, we address the overfitting problem associated with the few-shot by applying a deep convolutional generative adversarial network (DCGAN) to augment the original training dataset. Experimental results demonstrate the validity of the proposed algorithm; it increases the classification accuracy by 4.18% relative to that achieved with manually extracted features; the overall accuracy of the proposed algorithm training with the augmented dataset is 3.175% higher than that with the original experimental dataset.

Learning Hierarchical Representations with Spike-and-Slab Inception Network

Recently, deep convolutional neural networks (CNN) with inception modules have attracted much attention due to their excellent performances on diverse domains. Nevertheless, the basic CNN can only capture a univariate feature, which is essentially linear. It leads to a weak ability in feature expression, further resulting in insufficient feature mining. In view of this issue, researchers incessantly deepened the network, bringing parameter redundancy and model over-fitting. Hence, whether we can employ this efficient deep neural network architecture to improve CNN and enhance the capacity of image recognition task still remains unknown. In this paper, we introduce spike-and-slab units to the modified inception module, enabling our model to capture dual latent variables and the average and covariance information. This operation further enhances the robustness of our model to variations of image intensity without increasing the model parameters. The results of several tasks demonstrated that dual variable operations can be well-integrated into inception modules, and excellent results have been achieved.

18F-FDG-PET/CT Whole-Body Imaging Lung Tumor Diagnostic Model: An Ensemble E-ResNet-NRC with Divided Sample Space

Under the background of ¹⁸F-FDG-PET/CT multimodal whole-body imaging for lung tumor diagnosis, for the problems of network degradation and high dimension features during convolutional neural network (CNN) training, beginning with the perspective of dividing sample space, an E-ResNet-NRC (ensemble ResNet nonnegative representation classifier) model is proposed in this paper. The model includes the following steps: (1) Parameters of a pretrained ResNet model are initialized using transfer learning. (2) Samples are divided into three different sample spaces (CT, PET, and PET/CT) based on the differences in multimodal medical images PET/CT, and ROI of the lesion was extracted. (3) The ResNet neural network was used to extract ROI features and obtain feature vectors. (4) Individual classifier ResNet-NRC was constructed with nonnegative representation NRC at a fully connected layer. (5) Ensemble classifier E-ResNet-NRC was constructed using the “relative majority voting method.” Finally, two network models, AlexNet and ResNet-50, and three classification algorithms, nearest neighbor classification algorithm (NNC), softmax, and nonnegative representation classification algorithm (NRC), were combined to compare with the E-ResNet-NRC model in this paper. The experimental results show that the overall classification performance of the Ensemble E-ResNet-NRC model is better than the individual ResNet-NRC, and specificity and sensitivity are more higher; the E-ResNet-NRC has better robustness and generalization ability.