Data Augmentation for Motor Imagery Signal Classification Based on a Hybrid Neural Network.

As an important paradigm of spontaneous brain-computer interfaces (BCIs), motor imagery (MI) has been widely used in the fields of neurological rehabilitation and robot control. Recently, researchers have proposed various methods for feature extraction and classification based on MI signals. The decoding model based on deep neural networks (DNNs) has attracted significant attention in the field of MI signal processing. Due to the strict requirements for subjects and experimental environments, it is difficult to collect large-scale and high-quality electroencephalogram (EEG) data. However, the performance of a deep learning model depends directly on the size of the datasets. Therefore, the decoding of MI-EEG signals based on a DNN has proven highly challenging in practice. Based on this, we investigated the performance of different data augmentation (DA) methods for the classification of MI data using a DNN. First, we transformed the time series signals into spectrogram images using a short-time Fourier transform (STFT). Then, we evaluated and compared the performance of different DA methods for this spectrogram data. Next, we developed a convolutional neural network (CNN) to classify the MI signals and compared the classification performance of after DA. The Fréchet inception distance (FID) was used to evaluate the quality of the generated data (GD) and the classification accuracy, and mean kappa values were used to explore the best CNN-DA method. In addition, analysis of variance (ANOVA) and paired t-tests were used to assess the significance of the results. The results showed that the deep convolutional generative adversarial network (DCGAN) provided better augmentation performance than traditional DA methods: geometric transformation (GT), autoencoder (AE), and variational autoencoder (VAE) (p < 0.01). Public datasets of the BCI competition IV (datasets 1 and 2b) were used to verify the classification performance. Improvements in the classification accuracies of 17% and 21% (p < 0.01) were observed after DA for the two datasets. In addition, the hybrid network CNN-DCGAN outperformed the other classification methods, with average kappa values of 0.564 and 0.677 for the two datasets.

Associations of Homocysteine, Folate, and Vitamin B12 with Osteoarthritis: A Mendelian Randomization Study.

Homocysteine, inversely related to folate and vitamin B12, is an independent risk factor for several age-related disorders. However, little is known about the association of homocysteine and related vitamins with osteoarthritis (OA). This study aimed to elucidate the potential causal effects of homocysteine, folate, and vitamin B12 on site- and gender-specific OA by applying the two-sample Mendelian randomization (MR) approach. Genetically predicted homocysteine showed adverse effects on overall OA (95% confidence interval (CI): 1.044-1.155), knee OA (95% CI: 1.000-1.167), hip OA (95% CI: 1.057-1.297), and spine OA (95% CI: 1.017-1.216). Genetically predicted folate showed protective effects on overall OA (95% CI: 0.783-0.961) and spine OA (95% CI: 0.609-0.954). Folate (95% CI: 0.887-1.004) and vitamin B12 (95% CI: 0.886-1.009) showed a protective trend against knee OA. The patterns of associations were site and gender specific. In conclusion, homocysteine had adverse effects on OA, especially on OA at weight-bearing joints and in females. Folate and vitamin B12 had protective effects on OA. Homocysteine-lowering interventions may be a potential option in the treatment and prevention of OA.

Enhancement of motor imagery training efficiency by an online adaptive training paradigm integrated with error related potential.

Objective. Motor imagery (MI) is a process of autonomously modulating the motor area to rehearse action mentally without actual execution. Based on the neuroplasticity of the cerebral cortex, MI can promote the functional rehabilitation of the injured cerebral cortex motor area. However, it usually takes several days to a few months to train individuals to acquire the necessary MI ability to control rehabilitation equipment in current studies, which greatly limits the clinical application of rehabilitation training systems based on the MI brain-computer interface (BCI).Approach. A novel MI training paradigm combined with the error related potential (ErrP) is proposed, and online adaptive training of the MI classifier was performed using ErrP. ErrP is used to correct the output of the MI classification to obtain a higher accuracy of kinesthetic feedback based on the imagination intention of subjects while generating simulated labels for MI online adaptive training. In this way, we improved the MI training efficiency. Thirteen subjects were randomly divided into an experimental group using the proposed paradigm and a control group using the traditional MI training paradigm to participate in six MI training experiments.Main results. The proposed paradigm enabled the experimental group to obtain a higher event-related desynchronization modulation level in the contralateral brain region compared with the control group and 69.76% online classification accuracy of MI after three MI training experiments. The online classification accuracy reached 72.76% and the whole system recognized the MI intention of the subjects with an online accuracy of 82.61% after six experiments.Significance. Compared with the conventional unimodal MI training strategy, the proposed approach enables subjects to use the MI-BCI based system directly and achieve a better performance after only three training experiments with training left and right hands simultaneously. This greatly improves the usability of the MI-BCI-based rehabilitation system and makes it more convenient for clinical use.

HTRA1 from OVX rat osteoclasts causes detrimental effects on endplate chondrocytes through NF-κB.

Endplate osteochondritis is considered one of the major causes of intervertebral disc degeneration (IVDD) and low back pain. Menopausal women have a higher rate of endplate cartilage degeneration than similarly aged men, but the related mechanisms are still unclear. Subchondral bone changes, mainly mediated by osteoblasts and osteoclasts, are considered an important reason for the degeneration of cartilage. This work explored the role of osteoclasts in endplate cartilage degeneration, as well as its underlying mechanisms. A rat ovariectomy (OVX) model was used to induce estrogen deficiency. Our experiments indicated that OVX significantly promoted osteoclastogenesis and anabolism and catabolism changes in endplate chondrocytes. OVX osteoclasts cause an imbalance between anabolism and catabolism in endplate chondrocytes, as shown by a decrease in anabolic markers such as Aggrecan and Collagen II, and an increase in catabolic markers such as a disintegrin and metalloproteinase with thrombospondin motifs 5 (ADAMTS5) and matrix metalloproteinases (MMP13). Osteoclasts were also confirmed in this study to be able to secrete HtrA serine peptidase 1 (HTRA1), which resulted in increased catabolism in endplate chondrocytes through the NF-κB pathway under estrogen deficiency. This study demonstrated the involvement and mechanism of osteoclasts in the anabolism and catabolism changes of endplate cartilage under estrogen deficiency, and proposed a new strategy for the treatment of endplate osteochondritis and IVDD by targeting HTRA1.

Steady-State Motion Visual Evoked Potential (SSMVEP) Enhancement Method Based on Time-Frequency Image Fusion.

The steady-state motion visual evoked potential (SSMVEP) collected from the scalp suffers from strong noise and is contaminated by artifacts such as the electrooculogram (EOG) and the electromyogram (EMG). Spatial filtering methods can fuse the information of different brain regions, which is beneficial for the enhancement of the active components of the SSMVEP. Traditional spatial filtering methods fuse electroencephalogram (EEG) in the time domain. Based on the idea of image fusion, this study proposed an SSMVEP enhancement method based on time-frequency (T-F) image fusion. The purpose is to fuse SSMVEP in the T-F domain and improve the enhancement effect of the traditional spatial filtering method on SSMVEP active components. Firstly, two electrode signals were transformed from the time domain to the T-F domain via short-time Fourier transform (STFT). The transformed T-F signals can be regarded as T-F images. Then, two T-F images were decomposed via two-dimensional multiscale wavelet decomposition, and both the high-frequency coefficients and low-frequency coefficients of the wavelet were fused by specific fusion rules. The two images were fused into one image via two-dimensional wavelet reconstruction. The fused image was subjected to mean filtering, and finally, the fused time-domain signal was obtained by inverse STFT (ISTFT). The experimental results show that the proposed method has better enhancement effect on SSMVEP active components than the traditional spatial filtering methods. This study indicates that it is feasible to fuse SSMVEP in the T-F domain, which provides a new idea for SSMVEP analysis.

Human action recognition based on kinematic similarity in real time.

Human action recognition using 3D pose data has gained a growing interest in the field of computer robotic interfaces and pattern recognition since the availability of hardware to capture human pose. In this paper, we propose a fast, simple, and powerful method of human action recognition based on human kinematic similarity. The key to this method is that the action descriptor consists of joints position, angular velocity and angular acceleration, which can meet the different individual sizes and eliminate the complex normalization. The angular parameters of joints within a short sliding time window (approximately 5 frames) around the current frame are used to express each pose frame of human action sequence. Moreover, three modified KNN (k-nearest-neighbors algorithm) classifiers are employed in our method: one for achieving the confidence of every frame in the training step, one for estimating the frame label of each descriptor, and one for classifying actions. Additional estimating of the frame's time label makes it possible to address single input frames. This approach can be used on difficult, unsegmented sequences. The proposed method is efficient and can be run in real time. The research shows that many public datasets are irregularly segmented, and a simple method is provided to regularize the datasets. The approach is tested on some challenging datasets such as MSR-Action3D, MSRDailyActivity3D, and UTD-MHAD. The results indicate our method achieves a higher accuracy.