With the continuous expansion of the field of natural language processing, researchers have found that there is a phenomenon of imbalanced data distribution in some practical problems, and the ...excellent performance of most methods is based on the assumption that the samples in the dataset are data balanced. Therefore, the imbalanced data classification problem has gradually become a problem that needs to be studied. Aiming at the sentiment information mining of an imbalanced short text review dataset, this paper proposed a fusion multi-channel BLTCN-BLSTM self-attention sentiment classification method. By building a multi-channel BLTCN-BLSTM self-attention network model, the sample after word embedding processing is used as the input of the multi-channel, and after fully extracting features, the self-attention mechanism is fused to strengthen the sentiment to further fully extract text features. At the same time, focus loss rebalancing and classifier enhancement are combined to realize text sentiment predictions. The experimental results show that the optimal F1 value is up to 0.893 on the Chnsenticorp-HPL-10,000 corpus. The comparison and ablation of experimental results, including accuracy, recall, and F1-measure, show that the proposed model can fully integrate the weight of emotional feature words. It effectively improves the sentiment classification performance of imbalanced short-text review data.
Automatic character recognition is being gradually adopted in several everyday applications. In industrial settings, it can free up manpower required for reading and tracking product information. ...However, character recognition in industrial environments is particularly challenging. The main challenges are as follows: (1) There are no publicly available datasets that would aid the development of robust industrial character recognition methods; (2) Industrial characters may be printed in complex and uneven shapes on the surface of various materials, resulting in blurred characters, low contrast and distortion; (3) Industrial character recognition in complex industrial environments can suffers from various difficulties, such as uneven lighting conditions, oxidation of characters caused by long-term storage, etc. To address these challenges, we propose a convolutional recurrent neural network based on a residual structure and a “Squeeze-and-Excitation” block, namely RS-CRNN. The feature extraction of this method is inspired by ResNet and SEnet, and the method uses gate recurrent units for sequence label prediction. The model was trained and tested on constructed real and synthetic datasets, and experimental results show that the method has better performance than state-of-the-art character recognition models.
•we constructed a dataset specifically intended for industrial character recognition.•an industrial character recognition model combines the advantages of ResNet and SENet.•the residual structure is easier to train than the original structure.•Establish the interdependence between feature channels.
Nitrogen doping was widely used to increase the electronic density of carbon materials and to enhance the adsorption of the supported metal catalysts. However, the exact interaction between various ...doped nitrogen species and palladium (Pd) have rarely been reported for formic acid electrooxidation (FAO). In this study, the effect of the doped pyridinic-N and pyrrolic-N on the electronic structure and the electrochemical activity of Pd toward FAO are investigated. The oxidation state of Pd is reduced and more metallic Pd is formed when Pd nanoparticles supported on pyridinic-N and pyrrolic-N doped carbon materials. Density functional theory (DFT) calculations simulate that the adsorption energy of HCOO* and *COOH on Pd/pyrrolic-N are lower than those on Pd/pyridinic-N. Both DFT and electrochemical measurements suggest that the FAO activity of Pd is more correlated with the pyrrolic-N than pyridinic-N. The catalyst contains more pyrrolic-N species exhibits higher electrochemical activity and faster kinetics for FAO reaction. Moreover, Pd2+-N complexes are formed in all the nitrogen doped catalysts and display good activity for FAO. In this study, Pd supported on urea treated carbon (Pd/UR) owns the highest content of pyrrolic-N and exhibits the best activity for FAO.
•Pyrrolic-N and pyridinic-N doped carbon are synthesized to support Pd catalysts.•XPS shows that the oxidation state of Pd is reduced and more metallic Pd is formed.•DFT simulates Pd/pyrrolic-N owns the lowest adsorption energy of HCOO* and *COOH.•Pd2+-N complexes have electrochemical activity toward formic acid oxidation.•Pd/UR catalysts perform the best activity toward formic acid oxidation.
Over the past few years, deep learning has been introduced to tackle hyperspectral image (HSI) classification and demonstrated good performance. In particular, the convolutional neural network (CNN) ...based methods have progressed. However, due to the high dimensionality of HSI and equal treatment of all bands, the performances of CNN based methods are hampered. The labels of land-covers often differ between edge and the center pixels in pixel-centered spatial information. These edge pixels may weaken the discrimination of spatial features and reduce classification accuracy. Motivated by the attention mechanism of the human visual system, the spatial proximity feature selection with residual spatial-spectral attention network is proposed in this article. It contains a residual spatial attention module, a residual spectral attention module, and a spatial proximity feature selection module. The residual spatial attention module aims to select the crucial spatial information, which assigns weights to different features by measuring the similarity between the surrounding elements and their central ones. The residual spectral attention module is designed for spectral bands which are selected from raw input data by emphasizing the valuable bands and suppressing the valueless. According to the spatial distribution of features, the spatial proximity feature selection module is used to filter features effectively. Experiments on three public data sets demonstrate that the proposed network outperforms the state-of-the-art methods in comparison.
In response to problems during the startup of coal-fired generating units, including intricate equipment operation, an excess of control parameters, limited optimization techniques, and protracted ...startup time, an object-oriented dynamic learning method for whole-process fuel control within coal-fired generating units is introduced. This method entails the segmentation and objectification of the entire fuel control process, allowing for the dynamic acquisition of the current operational status of each system at every stage. Consequently, adaptive fuel intelligent control directives are generated, facilitating the realization of intelligent fuel control throughout the entire sequence, from unit ignition to coordinated operation. Functional validation has been performed on a 1,050 MW unit, and practical implementation confirms the method’s capacity for efficient and intelligent operation throughout the entire process, significantly reducing unit startup duration, and elevating the unit’s overall level of automa
As reported previously by our group, medium-chain triglycerides can ameliorate atherosclerosis. Given that TLR4 is closely related to atherosclerosis, we hypothesized herein that caprylic acid (C8:0) ...would suppress inflammation via TLR4/NF-κB signaling and further promote the amelioration of atherosclerosis in apoE- deficient (apoE
) mice.
Fifty 6-week male apoE
mice were randomly allocated into five diet groups: a high-fat diet (HFD) without or with 2% caprylic acid (C8:0), capric acid (C10:0), stearic acid (C18:0), or linolenic acid (C18:3). RAW246.7 cells were treated with caprylic acid (C8:0), docosahexenoic acid (DHA), palmitic acid (C16:0), and lipopolysaccharide (LPS) with or without TLR4 knock-down (TLR4-KD). The serum lipid profiles, inflammatory biomolecules, and mRNA and protein expression levels were measured. Atherosclerotic lesions that occurred in the aorta and aortic sinuses were evaluated and quantified.
Our results indicated that C8:0 reduced body fat, improved the lipid profiles, suppressed inflammatory cytokine production, downregulated aortic TLR4, MyD88, NF-κB, TNF-α, IKKα, and IKKβ mRNA expression, and alleviated atherosclerosis in the apoE
mice (
< 0.05). In RAW 264.7 cells, C8:0 diminished the inflammatory response and both mRNA and protein expression of TLR4, MyD88, NF-κB, and TNF-α compared to those in the LPS and C16:0 groups (
< 0.05). However, in the TLR4-KD RAW 264.7 cells, C8:0 significantly upregulated NF-κB mRNA and protein expression compared to those in the C16:0 and DHA groups.
These results suggest that C8:0 functions via TLR4/NF-κB signaling to improve the outcomes of apoE
mice through suppressing inflammation and ameliorating atherosclerosis. Thus, C8:0 may represent as a promising nutrient against chronic inflammatory diseases.
Celotno besedilo
Dostopno za:
DOBA, IZUM, KILJ, NUK, PILJ, PNG, SAZU, SIK, UILJ, UKNU, UL, UM, UPUK, VSZLJ
Universal stress proteins (USPs) play essential roles in plant development, hormonal regulation, and abiotic stress responses. However, the characteristics and functional divergence of USP family ...members have not been studied in blueberry (
). In this study, we identified 72
genes from the Genome Database for
. These
could be divided into five groups based on their phylogenetic relationships. VcUSPs from groups Ⅰ, Ⅳ, and Ⅴ each possess one UspA domain; group Ⅰ proteins also contain an ATP-binding site that is not present in group Ⅳ and Ⅴ proteins. Groups Ⅱ and Ⅲ include more complex proteins possessing one to three UspA domains and UspE or UspF domains. Prediction of cis-regulatory elements in the upstream sequences of
genes indicated that their protein products are likely involved in phytohormone signaling pathways and abiotic stress responses. Analysis of RNA deep sequencing data showed that 21 and 7
genes were differentially expressed in response to UV-B radiation and exogenous abscisic acid (ABA) treatments, respectively.
and
expressions responded to both treatments, and their encoded proteins may integrate the UV-B and ABA signaling pathways. Weighted gene co-expression network analysis revealed that
,
,
,
, and
were co-expressed with many transcription factor genes, most of which encode members of the MYB, WRKY, zinc finger, bHLH, and AP2 families, and may be involved in plant hormone signal transduction, circadian rhythms, the MAPK signaling pathway, and UV-B-induced flavonoid biosynthesis under UV-B and exogenous ABA treatments. Our study provides a useful reference for the further functional analysis of
genes and blueberry molecular breeding.
Display omitted
Efficiently and thoroughly degrading organic dyes in wastewater is of great importance and challenge. Herein, vertically oriented mesoporous α-Fe2O3 nanorods array (α-Fe2O3-NA) is ...directly grown on fluorine-doped tin oxide (FTO) glass and employed as the photoanode for photoelectrocatalytic degradation of methylene blue simulated dye wastewater. The Ov sites on the α-Fe2O3-NA surface are the active sites for methylene blue (MB) adsorption. Electrons transfer from the adsorbed MB to Fe-O is detected. Compared with electrocatalytic and photocatalytic degradation processes, the photoelectrocatalytic (PEC) process exhibited the best degrading performance and the largest kinetic constant. Hydroxyl, superoxide free radicals, and photo-generated holes play a jointly leading role in the PEC degradation. A possible degrading pathway is suggested by liquid chromatography-mass spectroscopy analysis. This work demonstrates that photoelectrocatalysis by α-Fe2O3-NA has a remarkable superiority over photocatalysis and electrocatalysis in MB degradation. The in-depth investigation of photoelectrocatalytic degradation mechanism in this study is meaningful for organic wastewater treatment.
B-box (BBX) proteins play important roles in regulating plant growth, development, and abiotic stress responses. BBX family genes have been identified and functionally characterized in many plant ...species, but little is known about the BBX family in blueberry (Vaccinium corymbosum). In this study, we identified 23 VcBBX genes from the Genome Database for Vaccinium (GDV). These VcBBXs can be divided into five clades based on gene structures and conserved domains in their encoded proteins. The prediction of cis-acting elements in the upstream sequences of VcBBX genes and protein-protein interactions indicated that VcBBX proteins are likely involved in phytohormone signaling pathways and abiotic stress responses. Analysis of transcriptome deep sequencing (RNA-seq) data showed that VcBBX genes exhibited organ-specific expression pattern and 11 VcBBX genes respond to ultraviolet B (UV-B) radiation. The co-expression analysis revealed that the encoded 11 VcBBX proteins act as bridges integrating UV-B and phytohormone signaling pathways in blueberry under UV-B radiation. Reverse-transcription quantitative PCR (RT-qPCR) analysis showed that most VcBBX genes respond to drought, salt, and cold stress. Among VcBBX proteins, VcBBX24 is highly expressed in all the organs, not only responds to abiotic stress, but it also interacts with proteins in UV-B and phytohormone signaling pathways, as revealed by computational analysis and co-expression analysis, and might be an important regulator integrating abiotic stress and phytohormone signaling networks. Twenty-three VcBBX genes were identified in blueberry, in which, 11 VcBBX genes respond to UV-B radiation, and act as bridges integrating UV-B and phytohormone signaling pathways according to RNA-seq data. The expression patterns under abiotic stress suggested that the functional roles of most VcBBX genes respose to drought, salt, and cold stress. Our study provides a useful reference for functional analysis of VcBBX genes and for improving abiotic stress tolerance in blueberry.
Celotno besedilo
Dostopno za:
DOBA, IZUM, KILJ, NUK, PILJ, PNG, SAZU, SIK, UILJ, UKNU, UL, UM, UPUK