Electroencephalographic Signal Data Augmentation Based on Improved Generative Adversarial Network.

EEG signals combined with deep learning play an important role in the study of human-computer interaction. However, the limited dataset makes it challenging to study EEG signals using deep learning methods. Inspired by the GAN network in image generation, this paper presents an improved generative adversarial network model L-C-WGAN-GP to generate artificial EEG data to augment training sets and improve the application of BCI in various fields. The generator consists of a long short-term memory (LSTM) network and the discriminator consists of a convolutional neural network (CNN) which uses the gradient penalty-based Wasserstein distance as the loss function in model training. The model can learn the statistical features of EEG signals and generate EEG data that approximate real samples. In addition, the performance of the compressed sensing reconstruction model can be improved by using augmented datasets. Experiments show that, compared with the existing advanced data amplification techniques, the proposed model produces EEG signals closer to the real EEG signals as measured by RMSE, FD and WTD indicators. In addition, in the compressed reconstruction of EEG signals, adding the new data reduces the loss by about 15% compared with the original data, which greatly improves the reconstruction accuracy of the EEG signals' compressed sensing.

A Data Augmentation Method for Motor Imagery EEG Signals Based on DCGAN-GP Network.

Motor imagery electroencephalography (EEG) signals have garnered attention in brain-computer interface (BCI) research due to their potential in promoting motor rehabilitation and control. However, the limited availability of labeled data poses challenges for training robust classifiers. In this study, we propose a novel data augmentation method utilizing an improved Deep Convolutional Generative Adversarial Network with Gradient Penalty (DCGAN-GP) to address this issue. We transformed raw EEG signals into two-dimensional time-frequency maps and employed a DCGAN-GP network to generate synthetic time-frequency representations resembling real data. Validation experiments were conducted on the BCI IV 2b dataset, comparing the performance of classifiers trained with augmented and unaugmented data. Results demonstrated that classifiers trained with synthetic data exhibit enhanced robustness across multiple subjects and achieve higher classification accuracy. Our findings highlight the effectiveness of utilizing a DCGAN-GP-generated synthetic EEG data to improve classifier performance in distinguishing different motor imagery tasks. Thus, the proposed data augmentation method based on a DCGAN-GP offers a promising avenue for enhancing BCI system performance, overcoming data scarcity challenges, and bolstering classifier robustness, thereby providing substantial support for the broader adoption of BCI technology in real-world applications.

Fast reconstruction of EEG signal compression sensing based on deep learning.

When traditional EEG signals are collected based on the Nyquist theorem, long-time recordings of EEG signals will produce a large amount of data. At the same time, limited bandwidth, end-to-end delay, and memory space will bring great pressure on the effective transmission of data. The birth of compressed sensing alleviates this transmission pressure. However, using an iterative compressed sensing reconstruction algorithm for EEG signal reconstruction faces complex calculation problems and slow data processing speed, limiting the application of compressed sensing in EEG signal rapid monitoring systems. As such, this paper presents a non-iterative and fast algorithm for reconstructing EEG signals using compressed sensing and deep learning techniques. This algorithm uses the improved residual network model, extracts the feature information of the EEG signal by one-dimensional dilated convolution, directly learns the nonlinear mapping relationship between the measured value and the original signal, and can quickly and accurately reconstruct the EEG signal. The method proposed in this paper has been verified by simulation on the open BCI contest dataset. Overall, it is proved that the proposed method has higher reconstruction accuracy and faster reconstruction speed than the traditional CS reconstruction algorithm and the existing deep learning reconstruction algorithm. In addition, it can realize the rapid reconstruction of EEG signals.

EEG Emotion Recognition by Fusion of Multi-Scale Features.

Electroencephalogram (EEG) signals exhibit low amplitude, complex background noise, randomness, and significant inter-individual differences, which pose challenges in extracting sufficient features and can lead to information loss during the mapping process from low-dimensional feature matrices to high-dimensional ones in emotion recognition algorithms. In this paper, we propose a Multi-scale Deformable Convolutional Interacting Attention Network based on Residual Network (MDCNAResnet) for EEG-based emotion recognition. Firstly, we extract differential entropy features from different channels of EEG signals and construct a three-dimensional feature matrix based on the relative positions of electrode channels. Secondly, we utilize deformable convolution (DCN) to extract high-level abstract features by replacing standard convolution with deformable convolution, enhancing the modeling capability of the convolutional neural network for irregular targets. Then, we develop the Bottom-Up Feature Pyramid Network (BU-FPN) to extract multi-scale data features, enabling complementary information from different levels in the neural network, while optimizing the feature extraction process using Efficient Channel Attention (ECANet). Finally, we combine the MDCNAResnet with a Bidirectional Gated Recurrent Unit (BiGRU) to further capture the contextual semantic information of EEG signals. Experimental results on the DEAP dataset demonstrate the effectiveness of our approach, achieving accuracies of 98.63% and 98.89% for Valence and Arousal dimensions, respectively.

Network Security Situation Prediction Based on Optimized Clock-Cycle Recurrent Neural Network for Sensor-Enabled Networks.

We propose an optimized Clockwork Recurrent Neural Network (CW-RNN) based approach to address temporal dynamics and nonlinearity in network security situations, improving prediction accuracy and real-time performance. By leveraging the clock-cycle RNN, we enable the model to capture both short-term and long-term temporal features of network security situations. Additionally, we utilize the Grey Wolf Optimization (GWO) algorithm to optimize the hyperparameters of the network, thus constructing an enhanced network security situation prediction model. The introduction of a clock-cycle for hidden units allows the model to learn short-term information from high-frequency update modules while retaining long-term memory from low-frequency update modules, thereby enhancing the model's ability to capture data patterns. Experimental results demonstrate that the optimized clock-cycle RNN outperforms other network models in extracting the temporal and nonlinear features of network security situations, leading to improved prediction accuracy. Furthermore, our approach has low time complexity and excellent real-time performance, ideal for monitoring large-scale network traffic in sensor networks.

Multinomial Logistic Factor Regression for Multi-source Functional Block-wise Missing Data.

Multi-source functional block-wise missing data arise more commonly in medical care recently with the rapid development of big data and medical technology, hence there is an urgent need to develop efficient dimension reduction to extract important information for classification under such data. However, most existing methods for classification problems consider high-dimensional data as covariates. In the paper, we propose a novel multinomial imputed-factor Logistic regression model with multi-source functional block-wise missing data as covariates. Our main contribution is to establishing two multinomial factor regression models by using the imputed multi-source functional principal component scores and imputed canonical scores as covariates, respectively, where the missing factors are imputed by both the conditional mean imputation and the multiple block-wise imputation approaches. Specifically, the univariate FPCA is carried out for the observable data of each data source firstly to obtain the univariate principal component scores and the eigenfunctions. Then, the block-wise missing univariate principal component scores instead of the block-wise missing functional data are imputed by the conditional mean imputation method and the multiple block-wise imputation method, respectively. After that, based on the imputed univariate factors, the multi-source principal component scores are constructed by using the relationship between the multi-source principal component scores and the univariate principal component scores; and at the same time, the canonical scores are obtained by the multiple-set canonial correlation analysis. Finally, the multinomial imputed-factor Logistic regression model is established with the multi-source principal component scores or the canonical scores as factors. Numerical simulations and real data analysis on ADNI data show the proposed method works well.

Sustainable Operation and Maintenance Modeling and Application of Building Infrastructures Combined with Digital Twin Framework.

Sustainable management is a challenging task for large building infrastructures due to the uncertainties associated with daily events as well as the vast yet isolated functionalities. To improve the situation, a sustainable digital twin (DT) model of operation and maintenance for building infrastructures, termed SDTOM-BI, is proposed in this paper. The proposed approach is able to identify critical factors during the in-service phase and achieve sustainable operation and maintenance for building infrastructures: (1) by expanding the traditional 'factor-energy consumption' to three parts of 'factor-event-energy consumption', which enables the model to backtrack the energy consumption-related factors based on the relevance of the impact of random events; (2) by combining with the Bayesian network (BN) and random forest (RF) in order to make the correlation between factors and results more clear and forecasts more accurate. Finally, the application is illustrated and verified by the application in a real-world gymnasium.

Membrane behavior of clay considering the effect of fixed charges.

Membrane efficiency coefficient of clay is evaluated with considering the effect of fixed charges adsorbed on clay mineral surfaces. By virtue of the concept of chemical potential, the ionic concentration of pore water is calculated. An equation is first proposed to calculate the Donnan osmotic pressure based on the activity of water (H2O), and then a new method is developed to determine the membrane efficiency coefficient, based on the theoretical chemo-osmotic pressure difference. The proposed method is used to calculate the membrane efficiency coefficients of geosynthetic clay liners (GCLs) with different bentonite contents and porosities under different KCl concentrations. The calculated results are compared to those of van't Hoff equation, showing that if skeletal deformation is excluded, the proposed model and van't Hoff equation with average ion concentration difference yield practically the same results; if the deformation is considered, however, van't Hoff equation yields smaller membrane coefficients.

The Dynamic Relationship among Bank Credit, House Prices and Carbon Dioxide Emissions in China.

This paper explores the dynamic relationship among bank credit, house prices and carbon dioxide emissions in China by systematically analyzing related data from January 2000 to December 2019 with the help of the time-varying parameter vector autoregression with stochastic volatility (TVP-SV-VAR) model and the Bayesian DCC-GARCH model. Empirical results show the expansion of bank credit significantly drives up house prices and increases carbon dioxide emissions in mosttimes. The rise in house prices inhibits the expansion of bank credit but increases carbon dioxide emissions and aggravates environment pollution, and that the increase in carbon dioxide is helpful to stimulate bank credit expansion and house price rise. In addition, bank credit and house prices are most relevant, followed by bank credit and carbon dioxide emissions, then by house prices and carbon dioxide emissions. Therefore, we believe that in order to stabilize skyrocketing house prices, restrain carbon dioxide emissions, and secure a stable and healthy macro-economy, the government should strengthen management of bank credit, and effectively control its total volume.

Structural Diversity in Oxadiazole-Containing Silver Complexes Dependent on the Anions.

Two coordination polymers, namely [Ag2(L)(SO3CF3)(H2O)](SO3CF3)•CH2Cl2 (1) and [Ag5(L)4(H2O)2](SbF6)5•5THF (2), were obtained by reacting oxadiazole-containing tri-armed ligand 1,3,5-tri(2-methylthio-1,3,4-oxadiazole-5yl) ben-zene (L) and silver salts in CH2Cl2/THF medium. The two complexes crystallized in the tetragonal space group I41/a and orthorhombic space group Fdd2, respectively. The Single-crystal X-ray diffraction revealed that the two complexes ex-hibit strikingly different 3D polymeric structures, which can be ascribed to the different counter anions. L in compound 1 acted as a hexa-dentate ligand, binding to two types of Ag+ atoms to form a 3D polymeric structure. L in compound 2acted as a hexa- and penta-dentate ligand, binding to three types of Ag+ atoms to form the 3D polymeric structure. The antibacterial activity of the complexes was also investigated.

Synthesis and in vivo Anti-inflammatory Evaluation of Piperazine Derivatives Containing 1,4-Benzodioxan Moiety.

Six piperazine derivatives 6a-f containing 1,4-benzodioxan moiety have been synthesized and characterized by 1H NMR, ESI-MS and elemental analysis. The structure of 6d was further confirmed by single crystal X-ray diffraction. All these novel compounds were screened for their in vivo anti-inflammatory activity employing classical para-xylene-induced mice ear-swelling model. The results revealed that most of the target compounds showed significant anti-inflammatory activities, especially compound 6a with ortho-substituted methoxy group on the phenylpiperazine ring exhibited the best activity among the designed compounds.

Seismic stability of subsea tunnels subjected to seepage.

Strength reduction method and ADINA software are adopted to study the stability of submarine tunnel structures subjected to seepage and earthquake under different seawater depths and overlying rock strata thicknesses. First, the excess pore water pressure in the rock mass is eliminated through consolidation calculation. Second, dynamic time-history analysis is performed by inputting the seismic wave to obtain the maximum horizontal displacement at the model top. Finally, static analysis is conducted by inputting the gravity and the lateral border node horizontal displacement when the horizontal displacement is the largest on the top border. The safety factor of a subsea tunnel structure subjected to seepage and earthquake is obtained by continuously reducing the shear strength parameters until the calculation is not convergent. The results show that the plastic zone initially appears at a small scope on the arch feet close to the lining structure and at both sides of the vault. Moreover, the safety factor decreases with increasing seawater depth and overlying rock strata thickness. With increasing seawater depth and overlying rock strata thickness, maximum main stress, effective stress, and maximum displacement increase, whereas displacement amplitude slightly decreases.

[Finite element analysis of total hip replacement].

Total hip replacement is a very effective method to cure many kinds of hip joint illnesses. About a century ago, it was first used in clinic. Since then, total hip replacement has been well developed. Hip joints sustain the most load of body, so people pay great attention to the hip prothesis' mechanics property. Especially after the finite element analysis was widely used in biomechanics investigation, the stress distribution of different designs can be easily compared with each other, and the relatively better parameters of the design could be decided. The stress distribution of different materials with the same design also can be valued. However, studies have indicated that total hip joint replacement still has some disadvantages. Loosening of the hip prothesis is still the most likely cause of the failure of surgery, and generally this is believed to stem from either mechanical failure of the fixation in response to over high density stresses, or osteolysis of the surrounding bone stock responsing to particular wear debris. Many researchers on computational studies have considered the potential for the former one, but only a few have attempted to tackle the latter. The process of osteolysis of the bone is not yet completely known. Nowadays, in order to solve the problems of loosening, investigators are trying to find different methods. Some of them are working on improving the geometry parameters and the shape of the hip prothesises, some are trying to find new suitable biomaterials, and, at the same time, the fixation methods are under deliberation.

Highly selective biotransformation of ginsenoside Rb1 to Rd by the phytopathogenic fungus Cladosporium fulvum (syn. Fulvia fulva).

Fourteen phytopathogenic fungi were tested for their ability to transform the major ginsenosides to the active minor ginsenoside Rd. The transformation products were identified by TLC and HPLC, and their structures were assigned by NMR analysis. Cladosporium fulvum, a tomato pathogen, was found to transform major ginsenoside Rb(1) to Rd as the sole product. The following optimum conditions for transforming Rd by C. fulvum were determined: the time of substrate addition, 24 h; substrate concentration, 0.25 mg ml(-1); temperature, 37 degrees C; pH 5.0; and biotransformation period, 8 days. At these optimum conditions, the maximum yield was 86% (molar ratio). Further, a preparative scale transformation with C. fulvum was performed at a dose of 100 mg of Rb(1) by a yield of 80%. This fungus has potential to be applied on the preparation for Rd in pharmaceutical industry.