Search

EEG-based emotion recognition through artificial intelligence is one of the major areas of biomedical and machine learning, which plays a key role in understanding brain activity and developing decision-making systems. However, the traditional EEG-based emotion recognition is a single feature input mode, which cannot obtain multiple feature information, and cannot meet the requirements of intelligent and high real-time brain computer interface. And because the EEG signal is nonlinear, the traditional methods of time domain or frequency domain are not suitable. In this paper, a CNN-DSC-Bi-LSTM-Attention (CDBA) model based on EEG signals for automatic emotion recognition is presented, which contains three feature-extracted channels. The normalized EEG signals are used as an input, the feature of which is extracted by multi-branching and then concatenated, and each channel feature weight is assigned through the attention mechanism layer. Finally, Softmax was used to classify EEG signals. To evaluate the performance of the proposed CDBA model, experiments were performed on SEED and DREAMER datasets, separately. The validation experimental results show that the proposed CDBA model is effective in classifying EEG emotions. For triple-category (positive, neutral and negative) and four-category (happiness, sadness, fear and neutrality), the classification accuracies were respectively 99.44% and 99.99% on SEED datasets. For five classification (Valence 1—Valence 5) on DREAMER datasets, the accuracy is 84.49%. To further verify and evaluate the model accuracy and credibility, the multi-classification experiments based on ten-fold cross-validation were conducted, the elevation indexes of which are all higher than other models. The results show that the multi-branch feature fusion deep learning model based on attention mechanism has strong fitting and generalization ability and can solve nonlinear modeling problems, so it is an effective emotion recognition method. Therefore, it is helpful to the diagnosis and treatment of nervous system diseases, and it is expected to be applied to emotion-based brain computer interface systems.

Epilepsy is the second most common disease of the nervous system. Because of its high disability rate and the long course of the disease, it is a worldwide medical problem and social public health problem. Therefore, the timely detection and treatment of epilepsy are very important. Currently, medical professionals use their own diagnostic experience to identify seizures by visual inspection of the electroencephalogram (EEG). Not only does it require a lot of time and effort, but the process is also very cumbersome. Machine learning-based methods have recently been proposed for epilepsy detection, which can help clinicians make rapid and correct diagnoses. However, these methods often require extracting the features of EEG signals before using the data. In addition, the selection of features often requires domain knowledge, and feature types also have a significant impact on the performance of the classifier. In this paper, a one-dimensional depthwise separable convolutional neural network and long short-term memory networks (1D DSCNN-LSTMs) model is proposed to identify epileptic seizures by autonomously extracting the features of raw EEG. On the UCI dataset, the performance of the proposed 1D DSCNN-LSTMs model is verified by cross-validation and time complexity comparison. Compared with other previous models, the experimental results show that the highest recognition rates of binary and quintuple classification are 99.57% and 81.30%, respectively. It can be concluded that the 1D DSCNN-LSTMs model proposed in this paper is an effective method to identify seizures based on EEG signals.

BackgroundThe protective role of IL-11, an IL-6 family cytokine, has been implicated in ischemia/reperfusion injury (IRI) in the heart and kidney, but its role has not been elucidated in liver IRI. This study was designed to evaluate the effects of IL-11 and its mechanism of action on liver IRI in a mouse model.MethodsA partial (70%) warm liver IRI was induced by interrupting the artery/portal vein blood supply to the left/middle liver lobes. IL-11 mRNA expression of ischemic liver after reperfusion was analyzed. Signal transducer and activator of transcription 3 (STAT3) was analyzed following IL-11 treatment in vivo and in vitro. Next, IL-11 was injected intraperitoneally (ip) 1 hour before ischemia. Liver injury was assessed based on serum alanine aminotransferase levels and histopathology. Apoptosis and inflammation were also determined in the ischemic liver. To analyze the role of STAT3 in IL-11 treatment, STAT3 siRNA or non-specific (NS) siRNA was used in vitro and in vivo.ResultsIL-11 mRNA expression was significantly increased after reperfusion in the ischemic liver. STAT3, as a target of IL-11, was activated in hepatocytes after IL-11 treatment in vivo and in vitro. Next, effects of IL-11/STAT3 signaling pathway were assessed in liver IRI, which showed IL-11 treatment significantly attenuated liver IRI, as evidenced by reduced hepatocellular function and hepatocellular necrosis/apoptosis. In addition, IL-11 treatment significantly inhibited the gene expressions of pro-inflammatory cytokines (TNF-α and IL-10) and chemokines (IP-10 and MCP-1). To determine the role of STAT3 in the hepatoprotective effects of IL-11, STAT3 siRNA or NS siRNA was used prior to IL-11 treatment. The results showed STAT3 knockdown abrogated the protective effects of IL-11 in vitro and in vivo.ConclusionsThis work provides first-time evidence for the protective effect of IL-11 treatment on hepatocyte in liver IRI, through the activation of the STAT3 pathway.

Colorectal cancer is the third most commonly diagnosed cancer worldwide. Although surgery remains the best treatment for this disease, adjuvant chemotherapy and radiotherapy are also very important in clinical practice. However, the notorious refractory lack of responses to radiochemotherapy greatly limits the application of radiochemotherapy in the context of colorectal cancer. There is a growing interest in the role that Aurora B may play in colorectal cancer cell survival as well as other cancer subtypes. In the current study, we sought to ascertain whether blocking of Aurora B signaling machinery by a small molecule inhibitor, CCT137690, could synergize radiation-induced colorectal cancer cell death. Results showed that CCT137690 increases the sensitivity of SW620 cells to radiation. Mechanistic studies revealed that Aurora B-Survivin pathway may be involved in this synergistic effect. Taken together, our results for the first time show that Aurora B inhibition and radiation exert a synergistic effect, resulting in enhanced colorectal cancer cell death. This synergistic effect is clinically relevant as lower doses of radiation could be used for cancer treatment, and could provide significant clinical benefits in terms of colorectal cancer management, while reducing unwanted side-effects. [ABSTRACT FROM AUTHOR]

Abstract Objective  The results of TIPS and the combined TIPS and portal-azygous disconnection for portal hypertension and variceal bleeding were evaluated. Methods  358 patients with portal hypertension were admitted to our clinical ward because of variceal bleeding. 263 patients underwent TIPS and 95 patients with combined TIPS and portal-azygous disconnection. Portal hemodynamics was evaluated by pressure measurements, venography and Doppler ultrasound before and 2 weeks after the procedure. The rates of shunt patency, rebleeding, encephalopathy and survival were observed during the follow-up period from 1 to 10 years. Results  The portal pressure and HVPG were decreased significantly after TIPS. TIPS procedure was successfully performed in 97.50% patients. During 1 month after treatment, acute shunt occlusion occurred in 3.42% patients with TIPS and there were no occluded shunts in patients with combined TIPS and portal-azygous disconnection. Encephalopathy was observed in 36.50% patients with TIPS and 18.95% with combined TIPS and portal-azygous disconnection. Recurrent variceal bleeding was documented in 6.46% patients with TIPS and none of patients with combined TIPS and azygous portal disconnection. Thirty-three patients with TIPS and two patients with combined TIPS and portal-azygous disconnection died. During follow-up periods, the patency of shunts in patients with TIPS and patients combined TIPS and azygous portal disconnection was 68.47, 43.84 and 87.06, 57.65% in 12 and 24 months after operation, respectively. The rates of rebleeding, and encephalopathy in patients with TIPS and patients with combined TIPS and azygous portal disconnection were 17.95, 31.79 and 7.04, 16.47%, respectively. The survival rate in 1, 5, 10 years in patients with TIPS and patients combined TIPS and azygous portal disconnection was 87.68, 51.23, 39.90 and 94.12, 81.18, 76.47%. Conclusion  Combined TIPS and portal-azygous disconnection can improve the effect of TIPS for portal hypertension. [ABSTRACT FROM AUTHOR]

Emotion analysis is the key technology in human–computer emotional interaction and has gradually become a research hotspot in the field of artificial intelligence. The key problems of emotion analysis based on EEG are feature extraction and classifier design. The existing methods of emotion analysis mainly use machine learning and rely on manually extracted features. As an end-to-end method, deep learning can automatically extract EEG features and classify them. However, most of the deep learning models of emotion recognition based on EEG still need manual screening and data pre-processing, and the accuracy and convenience are not high enough. Therefore, this paper proposes a CNN-Bi-LSTM-Attention model to automatically extract the features and classify emotions based on EEG signals. The original EEG data are used as input, a CNN and a Bi-LSTM network are used for feature extraction and fusion, and then the electrode channel weights are balanced through the attention mechanism layer. Finally, the EEG signals are classified to different kinds of emotions. An emotion classification experiment based on EEG is conducted on the SEED dataset to evaluate the performance of the proposed model. The experimental results show that the method proposed in this paper can effectively classify EEG emotions. The method was assessed on two distinctive classification tasks, one with three and one with four target classes. The average ten-fold cross-validation classification accuracy of this method is 99.55% and 99.79%, respectively, corresponding to three and four classification tasks, which is significantly better than the other methods. It can be concluded that our method is superior to the existing methods in emotion recognition, which can be widely used in many fields, including modern neuroscience, psychology, neural engineering, and computer science as well. [ABSTRACT FROM AUTHOR]

Epilepsy is the second most common disease of the nervous system. Because of its high disability rate and the long course of the disease, it is a worldwide medical problem and social public health problem. Therefore, the timely detection and treatment of epilepsy are very important. Currently, medical professionals use their own diagnostic experience to identify seizures by visual inspection of the electroencephalogram (EEG). Not only does it require a lot of time and effort, but the process is also very cumbersome. Machine learning-based methods have recently been proposed for epilepsy detection, which can help clinicians make rapid and correct diagnoses. However, these methods often require extracting the features of EEG signals before using the data. In addition, the selection of features often requires domain knowledge, and feature types also have a significant impact on the performance of the classifier. In this paper, a one-dimensional depthwise separable convolutional neural network and long short-term memory networks (1D DSCNN-LSTMs) model is proposed to identify epileptic seizures by autonomously extracting the features of raw EEG. On the UCI dataset, the performance of the proposed 1D DSCNN-LSTMs model is verified by cross-validation and time complexity comparison. Compared with other previous models, the experimental results show that the highest recognition rates of binary and quintuple classification are 99.57% and 81.30%, respectively. It can be concluded that the 1D DSCNN-LSTMs model proposed in this paper is an effective method to identify seizures based on EEG signals. [ABSTRACT FROM AUTHOR]

Copyright of Shipin Kexue/ Food Science is the property of Food Science Editorial Department and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)