In order to improve the effect of electrical automation control, this paper combines the intelligent computer technology to construct the electrical automation control system, explores the principle ...of the active disturbance rejection controller, and applies it to the induction motor vector control system. The active disturbance rejection controller estimates the state variables of the system and their changing trends in real time through the extended state observer, compensates them by nonlinear feedback method, and provides appropriate control signals. In addition, this paper builds the induction motor active disturbance rejection control system based on ant colony algorithm and conducts a lot of simulation analysis. The research shows that the electrical automatic control system based on the intelligent computer algorithm proposed in this paper has a good electrical automatic control effect.
Traditional machine learning methods suffer from severe overfitting in EEG-based emotion reading. In this paper, we use hierarchical convolutional neural network (HCNN) to classify the positive, ...neutral, and negative emotion states. We organize differential entropy features from different channels as two-dimensional maps to train the HCNNs. This approach maintains information in the spatial topology of electrodes. We use stacked autoencoder (SAE), SVM, and KNN as competing methods. HCNN yields the highest accuracy, and SAE is slightly inferior. Both of them show absolute advantage over traditional shallow models including SVM and KNN. We confirm that the high-frequency wave bands Beta and Gamma are the most suitable bands for emotion reading. We visualize the hidden layers of HCNNs to investigate the feature transformation flow along the hierarchical structure. Benefiting from the strong representational learning capacity in the two-dimensional space, HCNN is efficient in emotion recognition especially on Beta and Gamma waves.
•A novel Contrastive Multi-Task Convolutional Neural Network (CMT-CNN) is proposed for automatic COVID-19 diagnosis.•The main task is to diagnose COVID-19 from other pneumonia and normal controls. ...The auxiliary task is self-supervised contrastive learning to acquire transformation-invariant representations.•A series of interpretable transformations are defined for medical image augmentation.•Extensive experiments demonstrate that the auxiliary task can significantly improve the generalization of CNN on both CT and X-ray datasets.
Computed tomography (CT) and X-ray are effective methods for diagnosing COVID-19. Although several studies have demonstrated the potential of deep learning in the automatic diagnosis of COVID-19 using CT and X-ray, the generalization on unseen samples needs to be improved. To tackle this problem, we present the contrastive multi-task convolutional neural network (CMT-CNN), which is composed of two tasks. The main task is to diagnose COVID-19 from other pneumonia and normal control. The auxiliary task is to encourage local aggregation though a contrastive loss: first, each image is transformed by a series of augmentations (Poisson noise, rotation, etc.). Then, the model is optimized to embed representations of a same image similar while different images dissimilar in a latent space. In this way, CMT-CNN is capable of making transformation-invariant predictions and the spread-out properties of data are preserved. We demonstrate that the apparently simple auxiliary task provides powerful supervisions to enhance generalization. We conduct experiments on a CT dataset (4,758 samples) and an X-ray dataset (5,821 samples) assembled by open datasets and data collected in our hospital. Experimental results demonstrate that contrastive learning (as plugin module) brings solid accuracy improvement for deep learning models on both CT (5.49%-6.45%) and X-ray (0.96%-2.42%) without requiring additional annotations. Our codes are accessible online.
Electroencephalogram (EEG) has been widely used in emotion recognition due to its high temporal resolution and reliability. Since the individual differences of EEG are large, the emotion recognition ...models could not be shared across persons, and we need to collect new labeled data to train personal models for new users. In some applications, we hope to acquire models for new persons as fast as possible, and reduce the demand for the labeled data amount. To achieve this goal, we propose a multisource transfer learning method, where existing persons are sources, and the new person is the target. The target data are divided into calibration sessions for training and subsequent sessions for test. The first stage of the method is source selection aimed at locating appropriate sources. The second is style transfer mapping, which reduces the EEG differences between the target and each source. We use few labeled data in the calibration sessions to conduct source selection and style transfer. Finally, we integrate the source models to recognize emotions in the subsequent sessions. The experimental results show that the three-category classification accuracy on benchmark SEED improves by 12.72% comparing with the nontransfer method. Our method facilitates the fast deployment of emotion recognition models by reducing the reliance on the labeled data amount, which has practical significance especially in fast-deployment scenarios.
► Soybean processing wastewater (SPW) as a culture medium for C. pyrenoidosa. ► High concentrations of organic wastewater promote the growth of C. pyrenoidosa. ► Cultivation of C. pyrenoidosa in SPW ...could yield cleaner water and useful biomass.
Chlorella pyrenoidosa was cultivated in soybean processing wastewater (SPW) in batch and fed-batch cultures without a supply of additional nutrients. The alga was able to remove 77.8±5.7%, 88.8±1.0%, 89.1±0.6% and 70.3±11.4% of soluble chemical oxygen demand (SCODCr), total nitrogen (TN), NH4+-N and total phosphate (TP), respectively, after 120h in fed-batch culture. C. pyrenoidosa attained an average biomass productivity of 0.64gL−1d−1, an average lipid content of 37.00±9.34%, and a high lipid productivity of 0.40gL−1d−1. Therefore, cultivation of C. pyrenoidosa in SPW could yield cleaner water and useful biomass.
Sodium glucose cotransporter 2 (SGLT2) inhibitors are beneficial in halting diabetic kidney disease; however, the complete mechanisms have not yet been elucidated. The epithelial-mesenchymal ...transition (EMT) is associated with the suppression of sirtuin 3 (Sirt3) and aberrant glycolysis. Here, we hypothesized that the SGLT2 inhibitor empagliflozin restores normal kidney histology and function in association with the inhibition of aberrant glycolysis in diabetic kidneys. CD-1 mice with streptozotocin-induced diabetes displayed kidney fibrosis that was associated with the EMT at 4 months after diabetes induction. Empagliflozin intervention for 1 month restored all pathological changes; however, adjustment of blood glucose by insulin did not. Empagliflozin normalized the suppressed Sirt3 levels and aberrant glycolysis that was characterized by HIF-1α accumulation, hexokinase 2 induction, and pyruvate kinase isozyme M2 dimer formation in diabetic kidneys. Empagliflozin also suppressed the accumulation of glycolysis byproducts in diabetic kidneys. Another SGLT2 inhibitor, canagliflozin, demonstrated similar in vivo effects. High-glucose media induced the EMT, which was associated with Sirt3 suppression and aberrant glycolysis induction, in the HK2 proximal tubule cell line; SGLT2 knockdown suppressed the EMT, with restoration of all aberrant functions. SGLT2 suppression in tubular cells also inhibited the mesenchymal transition of neighboring endothelial cells. Taken together, SGLT2 inhibitors exhibit renoprotective potential that is partially dependent on the inhibition of glucose reabsorption and subsequent aberrant glycolysis in kidney tubules.
As a nanoscale renewable resource derived from lignocellulosic materials, cellulose nanocrystals (CNCs) have the features of high purity, high crystallinity, high aspect ratio, high Young's modulus, ...and large specific surface area. The most interesting trait is that they can form the entire films with bright structural colors through the evaporation‐induced self‐assembly (EISA) process under certain conditions. Structural color originates from micro‐nano structure of CNCs matrixes via the interaction of nanoparticles with light, rather than the absorption and reflection of light from the pigment. CNCs are the new generation of photonic liquid crystal materials of choice due to their simple and convenient preparation processes, environmentally friendly fabrication approaches, and intrinsic chiral nematic structure. Therefore, understanding the forming mechanism of CNCs in nanoarchitectonics is crucial to multiple fields of physics, chemistry, materials science, and engineering application. Herein, a timely summary of the chiral photonic liquid crystal films derived from CNCs is systematically presented. The relationship of CNC, structural color, chiral nematic structure, film performance, and applications of chiral photonic liquid crystal films is discussed. The review article also summarizes the most recent achievements in the field of CNCs‐based photonic functional materials along with the faced challenges.
This review introduces the relationship between structural color, photonic crystal, and CNC liquid crystal structure, and systematically summarizes the preparation methods, control principles, and application research of CNC chiral nematic liquid crystal films in different fields. Finally, the future research directions and challenges of CNC chiral nematic liquid crystal films are pointed out.
Necroptosis plays an important role in hepatocellular carcinoma (HCC) development, recurrence, and immunotherapy tolerance. We aimed to build a new prognostic necroptosis-related gene signature that ...could be used for survival and immunotherapy prediction in HCC patients.
We found that necroptosis was associated with HCC progression and survival outcomes and was involved in the immune infiltration of HCC. Multiple bioinformatics methods including WGCNA, LASSO-Cox regression, stepwise Cox regression, and Random Forest and Boruta model analysis, were used to establish a prognostic profile related to necroptosis. The necroptosis-related gene signature was validated in ICGC and GSE14520 datasets.
This five-gene signature showed excellent predictive performance and was an independent risk factor for patients' overall survival outcome in the three cohorts. Moreover, this signature was an exact predictor using fewer genes than previous gene signatures. Finally, qRT-PCR and immunohistochemical staining investigations were performed in previously collected fresh frozen tumor tissues from HCC patients and their paracancerous normal tissues, and the results were consistent with the bioinformatics results. We found that LGALS3 not only affected the proliferation and migration ability of HepG2 cells but also affected necroptosis and the expression of inflammatory cytokines.
In summary, we established and validated an individualized prognostic profile related to necroptosis to forecast the therapeutic response to immune therapy, which might offer a potential non-apoptotic therapeutic target for HCC patients.
As an essential element for the diagnosis and rehabilitation of psychiatric disorders, the electroencephalogram (EEG) based emotion recognition has achieved significant progress due to its high ...precision and reliability. However, one obstacle to practicality lies in the variability between subjects and sessions. Although several studies have adopted domain adaptation (DA) approaches to tackle this problem, most of them treat multiple EEG data from different subjects and sessions together as a single source domain for transfer, which either fails to satisfy the assumption of domain adaptation that the source has a certain marginal distribution, or increases the difficulty of adaptation. We therefore propose the multi-source marginal distribution adaptation (MS-MDA) for EEG emotion recognition, which takes both domain-invariant and domain-specific features into consideration. First, we assume that different EEG data share the same low-level features, then we construct independent branches for multiple EEG data source domains to adopt one-to-one domain adaptation and extract domain-specific features. Finally, the inference is made by multiple branches. We evaluate our method on SEED and SEED-IV for recognizing three and four emotions, respectively. Experimental results show that the MS-MDA outperforms the comparison methods and state-of-the-art models in cross-session and cross-subject transfer scenarios in our settings. Codes at https://github.com/VoiceBeer/MS-MDA.