Improved Latin hypercube sampling initialization-based whale optimization algorithm for COVID-19 X-ray multi-threshold image segmentation.

Image segmentation techniques play a vital role in aiding COVID-19 diagnosis. Multi-threshold image segmentation methods are favored for their computational simplicity and operational efficiency. Existing threshold selection techniques in multi-threshold image segmentation, such as Kapur based on exhaustive enumeration, often hamper efficiency and accuracy. The whale optimization algorithm (WOA) has shown promise in addressing this challenge, but issues persist, including poor stability, low efficiency, and accuracy in COVID-19 threshold image segmentation. To tackle these issues, we introduce a Latin hypercube sampling initialization-based multi-strategy enhanced WOA (CAGWOA). It incorporates a COS sampling initialization strategy (COSI), an adaptive global search approach (GS), and an all-dimensional neighborhood mechanism (ADN). COSI leverages probability density functions created from Latin hypercube sampling, ensuring even solution space coverage to improve the stability of the segmentation model. GS widens the exploration scope to combat stagnation during iterations and improve segmentation efficiency. ADN refines convergence accuracy around optimal individuals to improve segmentation accuracy. CAGWOA's performance is validated through experiments on various benchmark function test sets. Furthermore, we apply CAGWOA alongside similar methods in a multi-threshold image segmentation model for comparative experiments on lung X-ray images of infected patients. The results demonstrate CAGWOA's superiority, including better image detail preservation, clear segmentation boundaries, and adaptability across different threshold levels.

The Impact of the COVID-19 Pandemic on Orthodontic Adult Patients' Characteristics and Decision on Orthodontic Appliance.

Purpose: There is an overall paucity of data examining the specific details of orthodontic patients' patterns or orthodontic service disruptions possibly influenced by COVID-19 pandemic. Therefore, this study aimed to explore the impact of the COVID-19 pandemic on orthodontic clinic disruption regarding the change in adult patients' characteristics and decisions of orthodontic treatment devices. Patients and Methods: A retrospective sample of 311 patients receiving orthodontic treatment from 2018 to 2022 were collected and divided into two groups: before (n = 167) and during (n = 144) the COVID-19 pandemic. Demographics, dental indices, the index of complexity outcome and need (ICON), and the degree of treatment difficulty were analyzed. Results: There were fewer students among patients during the COVID-19 pandemic than before (24.5% versus 35.9%, P = 0.036). Compared with patients before the pandemic, more patients selected ceramic brackets or Invisalign during the pandemic (P = 0.022). There were higher percentage of class I dental malocclusions among patients during than before the COVID-19 pandemic (P = 0.044). Moreover, the ICON score and the score of the degree of treatment difficulty were both significantly lower for patients during than before the COVID-19 pandemic (63.9±14.0 versus 58.3±15.3, P=0.001 and 7.4±2.6 versus 6.8±2.6, P=0.049, respectively). Conclusion: The COVID-19 pandemic influenced the characteristics and decisions of orthodontic patients. Those who still came to the orthodontic clinic despite the COVID-19 outbreak may have been those with less malocclusion severity and treatment difficulty. Besides, during the time of covid-19 pandemic, more patients chose ceramic bracket and Invisalign as their orthodontic treatment device rather than conventional or self-ligating metal brackets.

Analyzing greenhouse gas emissions and influencing factors of 247 actual wastewater treatment plants in China using emission factor and operational data integrated methods (ODIM).

In response to China's policies on pollution control and carbon emission (CE) reductions, more stringent regulations have been implemented to evaluate CE in wastewater treatment facilities. In this study, we have analyzed CE from China's wastewater treatment plants (WWTPs) and influencing factor. Emission factor (EF) and operational data integrated methods (ODIM) were utilized to measure emissions, using data collected from 247 WWTPs over a 1-year period across seven regions in China. The average CE intensity was 0.45 kgCO2-eq/m3, affected by region, season, influent water quality, treatment processes, effluent discharge standards, and facilities. The scale effect was obvious only in the range of 2 × 105 m3/day. Underground WWTPs exhibited significantly higher CE compared to aboveground WWTPs. In summary, the assessment of CE in 247 actual WWTPs not only identifies emission reduction potential but also provides a scientific basis for formulating targeted emission reduction measures.

Porous gradient hydrogel promotes skin regeneration by angiogenesis.

The skin has a multilayered structure, and deep-seated injuries are exposed to external microbial invasion and in vivo microenvironmental destabilization. Here, a bilayer bionic skin scaffold (Bilayer SF) was developed based on methacrylated sericin protein to mimic the skin's multilayered structure and corresponding functions. The outer layer (SF@TA), which mimics the epidermal layer, was endowed with the function of resisting external bacterial and microbial invasion using a small pore structure and bio-crosslinking with tannic acid (TA). The inner layer (SF@DA@Gel), which mimics the dermal layer, was used to promote cellular growth using a large pore structure and introducing dopamine (DA) to regulate the wound microenvironment. This Bilayer SF showed good mechanical properties and structural stability, satisfactory antioxidant and promote cell proliferation and migration abilities. In vitro studies confirmed the antimicrobial properties of the outer layer and the pro-angiogenic ability of the inner layer. In vivo animal studies demonstrated that the bilayer scaffolds promoted collagen deposition, neovascularization, and marginal hair follicle formation, which might be a promising new bionic skin scaffold.

Photocatalytic toluene oxidation with nickel-mediated cascaded active units over Ni/Bi2WO6 monolayers.

Adsorption and activation of C-H bonds by photocatalysts are crucial for the efficient conversion of C-H bonds to produce high-value chemicals. Nevertheless, the delivery of surface-active oxygen species for C-H bond oxygenation inevitably needs to overcome obstacles due to the separated active centers, which suppresses the catalytic efficiency. Herein, Ni dopants are introduced into a monolayer Bi2WO6 to create cascaded active units consisting of unsaturated W atoms and Bi/O frustrated Lewis pairs. Experimental characterizations and density functional theory calculations reveal that these special sites can establish an efficient and controllable C-H bond oxidation process. The activated oxygen species on unsaturated W are readily transferred to the Bi/O sites for C-H bond oxygenation. The catalyst with a Ni mass fraction of 1.8% exhibits excellent toluene conversion rates and high selectivity towards benzaldehyde. This study presents a fascinating strategy for toluene oxidation through the design of efficient cascaded active units.

Enhanced differential evolution algorithm for feature selection in tuberculous pleural effusion clinical characteristics analysis.

Tuberculous pleural effusion poses a significant threat to human health due to its potential for severe disease and mortality. Without timely treatment, it may lead to fatal consequences. Therefore, early identification and prompt treatment are crucial for preventing problems such as chronic lung disease, respiratory failure, and death. This study proposes an enhanced differential evolution algorithm based on colony predation and dispersed foraging strategies. A series of experiments conducted on the IEEE CEC 2017 competition dataset validated the global optimization capability of the method. Additionally, a binary version of the algorithm is introduced to assess the algorithm's ability to address feature selection problems. Comprehensive comparisons of the effectiveness of the proposed algorithm with 8 similar algorithms were conducted using public datasets with feature sizes ranging from 10 to 10,000. Experimental results demonstrate that the proposed method is an effective feature selection approach. Furthermore, a predictive model for tuberculous pleural effusion is established by integrating the proposed algorithm with support vector machines. The performance of the proposed model is validated using clinical records collected from 140 tuberculous pleural effusion patients, totaling 10,780 instances. Experimental results indicate that the proposed model can identify key correlated indicators such as pleural effusion adenosine deaminase, temperature, white blood cell count, and pleural effusion color, aiding in the clinical feature analysis of tuberculous pleural effusion and providing early warning for its treatment and prediction.

A global dataset of terrestrial evapotranspiration and soil moisture dynamics from 1982 to 2020.

Quantifying terrestrial evapotranspiration (ET) and soil moisture dynamics accurately is crucial for understanding the global water cycle and surface energy balance. We present a novel, long-term dataset of global ET and soil moisture derived from the newly developed Simple Terrestrial Hydrosphere model, version 2 (SiTHv2). This ecohydrological model, driven by multi-source satellite observations and hydrometeorological variables from reanalysis data, provides daily global ET-related estimates (e.g., total ET, plant transpiration, soil evaporation, intercepted evaporation) and three-layer soil moisture dynamics at a 0.1° spatial resolution. Validation with in-situ measurements and comparisons with mainstream global ET and soil moisture products demonstrate robust performance of SiTHv2 in both magnitude and temporal dynamics of ET and soil moisture at multiple scales. The comprehensive water path characterization in the SiTHv2 model makes this seamless dataset particularly valuable for studies requiring synchronized water budget and vegetation response to water constraints. With its long-term coverage and high spatiotemporal resolution, the SiTHv2-derived ET and soil moisture product will be suitable to support analyses related to the hydrologic cycle, drought assessment, and ecosystem health.

Anti-inflammatory and immunoregulatory effects of colistin sulphate on human PBMCs.

In previous studies, CST has been identified as having an immunostimulatory effect on Caenorhabditis elegans and macrophage of rats. Here, we further investigated its immunomodulatory effects on human peripheral blood mononuclear cells (PBMCs). LPS-stimulated PBMCs inflammatory model was established. Flow cytometry was applied to measure phagocytosis of PBMCs. Cytokine mRNA and protein expression levels of LPS-stimulated PBMCs with or without CST were measured by qRT-PCR and ELISA. The transcriptomic profile of CST-treated PBMCs was investigated by RNA-sequencing. Gene Ontology (GO) and Kyoto Encylopedia of Genes and Genomes (KEGG) were applied to find potential signalling pathways. PBMCs showed a significant increase in phagocytic activity at 6 h after being incubated with CST at the concentration of 10 µg/mL. In the presence of LPS, CST maintained and promoted the expression of TNF-α and chemokine CCL24. The content of pro-inflammatory cytokines, such as IL-1ß, IL-6 and IFN-γ, which were released from LPS-stimulated PBMCs, was reduced by CST at 6 h. Anti-inflammatory cytokines, such as IL-4, IL-13 and TGF-ß1, were significantly increased by CST at 24 h. A total of 277 differentially expressed immune-related genes (DEIRGs) were detected and cytokine-cytokine receptor interaction was highly enriched. CST presented obvious anti-inflammatory and immunoregulatory effects in LPS-induced PBMCs inflammatory model not only by improving the ability of PBMCs to clear pathogens but also by decreasing pro-inflammatory cytokines and increasing anti-inflammatory cytokines. And the mechanism may be related to cytokine-cytokine receptor interaction.

Utilize multi-metabolic parameters as determinants for prediction of skeletal muscle mass quality in elderly type2 diabetic Chinese patients.

BACKGROUND: Sarcopenia, an age-related disorder characterized by loss of skeletal muscle mass and function, is recently recognized as a complication in elderly patients with type 2 diabetes mellitus (T2DM). Skeletal muscles play a crucial role in glycemic metabolism, utilizing around 80% of blood glucose. Accordingly, we aimed to explore the relationship between glucose metabolism and muscle mass in T2DM. METHODS: We employed the AWGS 2019 criteria for diagnosing low muscle mass and 1999 World Health Organization (WHO) diabetes diagnostic standards. This study included data of 191 individuals aged 60 and above with T2DM of Shanghai Pudong Hospital from November 2021 to November 2022. Fasting C-peptide (FPCP), fasting plasma glucose (FPG), 2-hour postprandial plasma glucose (PPG) and postprandial 2-hour C-peptide (PPCP), glycated hemoglobin A1c (HbA1c), glycated albumin (GA), serum lipids spectrum, renal and hepatic function, hemoglobin, and hormone were measured. Based on the findings of univariate analysis, logistic regression and receiver operating characteristic (ROC) curves were established. RESULTS: Participants with low muscle mass had significantly lower alanine and aspartate aminotransferase, and both FPCP and PPCP levels (P < 0.05). Compared with those without low muscle mass, low muscle mass group had significantly higher FPG, HbA1c, GA levels (P < 0.05). Body fat (BF, OR = 1.181) was an independent risk factor for low muscle mass. PPCP (OR = 0.497), BMI (OR = 0.548), and female (OR = 0.050) were identified as protective factors for low skeletal muscle. The AUC of BMI was the highest, followed by the PPCP, gender and BF (0.810, 0.675, 0.647, and 0.639, respectively), and the AUC of the combination of the above four parameters reached 0.895. CONCLUSIONS: In this cross-sectional study, BMI, Female, and PPCP associated with T2DM were protective factors for low muscle mass. BF was associated with T2DM and risk factor for low muscle mass.

Dual roles of dopaminergic pathways in olfactory learning and memory in the oriental fruit fly, Bactrocera dorsalis.

Dopamine (DA) is a key regulator of associative learning and memory in both vertebrates and invertebrates, and it is widely believed that DA plays a key role in aversive conditioning in invertebrates. However, the idea that DA is involved only in aversive conditioning has been challenged in recent studies on the fruit fly (Drosophila melanogaster), ants and crabs, suggesting diverse functions of DA modulation on associative plasticity. Here, we present the results of DA modulation in aversive olfactory conditioning with DEET punishment and appetitive olfactory conditioning with sucrose reward in the oriental fruit fly, Bactrocera dorsalis. Injection of DA receptor antagonist fluphenazine or chlorpromazine into these flies led to impaired aversive learning, but had no effect on the appetitive learning. DA receptor antagonists impaired both aversive and appetitive long-term memory retention. Interestingly, the impairment on appetitive memory was rescued not only by DA but also by octopamine (OA). Blocking the OA receptors also impaired the appetitive memory retention, but this impairment could only be rescued by OA, not by DA. Thus, we conclude that in B. dorsalis, OA and DA pathways mediate independently the appetitive and aversive learning, respectively. These two pathways, however, are organized in series in mediating appetitive memory retrieval with DA pathway being at upstream. Thus, OA and DA play dual roles in associative learning and memory retrieval, but their pathways are organized differently in these two cognitive processes - parallel organization for learning acquisition and serial organization for memory retrieval.

Advancing forensic-based investigation incorporating slime mould search for gene selection of high-dimensional genetic data.

Modern medicine has produced large genetic datasets of high dimensions through advanced gene sequencing technology, and processing these data is of great significance for clinical decision-making. Gene selection (GS) is an important data preprocessing technique that aims to select a subset of feature information to improve performance and reduce data dimensionality. This study proposes an improved wrapper GS method based on forensic-based investigation (FBI). The method introduces the search mechanism of the slime mould algorithm in the FBI to improve the original FBI; the newly proposed algorithm is named SMA_FBI; then GS is performed by converting the continuous optimizer to a binary version of the optimizer through a transfer function. In order to verify the superiority of SMA_FBI, experiments are first executed on the 30-function test set of CEC2017 and compared with 10 original algorithms and 10 state-of-the-art algorithms. The experimental results show that SMA_FBI is better than other algorithms in terms of finding the optimal solution, convergence speed, and robustness. In addition, BSMA_FBI (binary version of SMA_FBI) is compared with 8 binary algorithms on 18 high-dimensional genetic data from the UCI repository. The results indicate that BSMA_FBI is able to obtain high classification accuracy with fewer features selected in GS applications. Therefore, SMA_FBI is considered an optimization tool with great potential for dealing with global optimization problems, and its binary version, BSMA_FBI, can be used for GS tasks.

[Influencing mechanism of stand age to the accumulation of microbial residue carbon in the Pinus masso-niana plantations]. / 林龄对马尾松人工林微生物残体碳积累的影响机制.

Clarifying the accumulation pattern of soil microbial residue carbon and its contribution to soil organic carbon (SOC) across stand age is helpful to understand the mechanism underlying soil carbon cycling. In this study, we analyzed the differences of amino sugar content, physicochemical properties and microbial composition in surface soil (0-10 cm) in young (6 a), middle-aged (13 a), near-mature (29 a), mature (38 a) and over-mature (57 a) Pinus massoniana plantations of subtropical China, quantified the microbial residue carbon content and its contribution to SOC, and discussed the mechanism. The results showed that SOC, total nitrogen, amorphous iron oxide and leucine aminopeptidase contents in the middle-aged plantation were significantly lower than those in the mature plantation. Soil pH and fungal/bacteria in young plantation were significantly higher than those in other age groups. Across the stand age gradient, the ranges of microbial, fungal and bacterial residue carbon were 7.52-14.63, 4.03-8.00 and 3.48-6.63 g·kg-1, respectively. The contents of all the residue carbon were significantly higher in the mature plantation than that of the middle-aged plantation, which were positively affected by soil total nitrogen content. The contribution of microbial, fungal, and bacterial residue carbon to SOC was 59.7%-72.3%, 33.4%-45.6%, and 24.3%-30.8%, respectively. The contribution of fungal residue carbon to SOC in young plantation was significantly higher than that in other age groups, and the contribution of bacterial residue carbon to SOC in middle-aged plantation was significantly higher than that in young and near-mature plantations, both of which were affected by soil inorganic nitrogen. Fungal residue carbon content was 1.2-1.7 times as that of bacterial residue carbon content, and dominated for the accumulation of microbial residue carbon. Results of the partial least squares model showed that stand age, soil environmental factors (such as leucine aminopeptidase, amorphous iron oxide, pH, and total nitrogen), bacterial residue carbon, fungal residue carbon and the contribution of bacterial residue carbon to SOC had total effects on the contribution of fungal residue carbon to SOC (-0.37, -1.16, 0.90, 1.09, and 0.83, respectively). In conclusion, stand age promoted the accumulation of microbial residue carbon but did not increase its contribution to SOC.

Exploring the ecological meanings of temperature sensitivity of ecosystem respiration from different methods.

Temperature sensitivity (Q10) of ecosystem respiration (Re) is a critical parameter for predicting global terrestrial carbon dynamics and its response to climate warming. However, the determination of Q10 has been controversial. In this study, we scrutinized the underpinnings of three mainstream methods to reveal their relationships in estimating Q10 for Re in the Heihe River Basin, northwest China. Specifically, these methods are Q10 estimated from the long-term method (Q10_long), short-term method (Q10_short), and the low-frequency (Q10_lf) and high-frequency (Q10_hf) signals decomposed by the singular spectrum analysis (SSA) method. We found that: 1) Q10_lf and Q10_long are affected by the confounding effects caused by non-temperature factors, and are 1.8 ± 0.3 and 1.7 ± 0.3, respectively. 2) The high-frequency signals of the SSA method and short-term method have consistent roles in removing the confounding effects. Both Q10_short and Q10_hf reflect the actual response of respiration to temperature. 3) Overall, Q10_long has a larger variability (1.7 ± 0.3) across different biomes, whereas Q10_short and Q10_hf show convergence (1.4 ± 0.2 and 1.3 ± 0.1, respectively). These results highlight the fact that Q10 can be overestimated by the long-term method, whereas the short-term method and high-frequency signals decomposed by the SSA method can obtain closer and convergent values after removing the confounding effects driven by non-temperature factors. Therefore, it is recommended to use the Q10 value estimated by the short-term method or high-frequency signals decomposed by the SSA method to predict carbon dynamics and its response to global warming in Earth system models.

Parrot optimizer: Algorithm and applications to medical problems.

Stochastic optimization methods have gained significant prominence as effective techniques in contemporary research, addressing complex optimization challenges efficiently. This paper introduces the Parrot Optimizer (PO), an efficient optimization method inspired by key behaviors observed in trained Pyrrhura Molinae parrots. The study features qualitative analysis and comprehensive experiments to showcase the distinct characteristics of the Parrot Optimizer in handling various optimization problems. Performance evaluation involves benchmarking the proposed PO on 35 functions, encompassing classical cases and problems from the IEEE CEC 2022 test sets, and comparing it with eight popular algorithms. The results vividly highlight the competitive advantages of the PO in terms of its exploratory and exploitative traits. Furthermore, parameter sensitivity experiments explore the adaptability of the proposed PO under varying configurations. The developed PO demonstrates effectiveness and superiority when applied to engineering design problems. To further extend the assessment to real-world applications, we included the application of PO to disease diagnosis and medical image segmentation problems, which are highly relevant and significant in the medical field. In conclusion, the findings substantiate that the PO is a promising and competitive algorithm, surpassing some existing algorithms in the literature. The supplementary files and open source codes of the proposed Parrot Optimizer (PO) is available at https://aliasgharheidari.com/PO.html and https://github.com/junbolian/PO.

Exploratory study on the metabolic similarity of denitrifying carbon sources.

Mixed carbon sources have been developed for denitrification to eliminate the "carbon dependency" problem of single carbon. The metabolic correlation between different carbon sources is significant as guidance for the development of novel mixed carbon sources. In this study, to explore the metabolic similarity of denitrifying carbon sources, we selected alcohols (methanol, ethanol, and glycerol) and saccharide carbon sources (glucose, sucrose, and starch). Batch denitrification experiments revealed that methanol-acclimated sludge improved the denitrification rate of both methanol (14.42 mg-N/gMLVSS*h) and ethanol (9.65 mg-N/gMLVSS*h), whereas ethanol-acclimated sludge improved the denitrification rate of both methanol (7.80 mg-N/gMLVSS*h) and ethanol (22.23 mg-N/gMLVSS*h). In addition, the glucose-acclimated sludge and sucrose-acclimated sludge possibly improved the denitrification rate of glucose and sucrose, and the glycerol-acclimated sludge improved the denitrification rate of volatile fatty acids (VFAs), alcohols, and saccharide carbon sources. Functional gene analysis revealed that methanol, ethanol, and glycerol exhibited active alcohol oxidation and glyoxylate metabolism, and glycerol, glucose, and sucrose exhibited active glycolysis metabolism. This indicated that the similarity in the denitrification metabolism of these carbon sources was based on functional gene similarity, and glycerol-acclimated sludge exhibited the most diverse metabolism, which ensured its good denitrification effect with other carbon sources.

Efficacy and safety of omadacycline for treating complicated skin and soft tissue infections: a meta-analysis of randomized controlled trials.

OBJECTIVE: In the present study, we aimed to compare the clinical efficacy and safety of omadacycline (OMC) with its comparators for the treatment of complicated skin and soft tissue infections (cSSTIs) in adult patients. METHODS: Randomized controlled trials (RCTs) evaluating OMC for cSSTIs were searched in databases of PubMed, Embase, Cochrane, Web of Science, and Clinical Trial, up to July 2022. The primary outcomes were clinical efficacy and microbiological response, with secondary outcome was safety. RESULTS: Four RCTs consisting of 1,757 patients were included, with linezolid (LZD) as a comparator drug. For clinical efficacy, OMC was not inferior to LZD in the modified intent-to-treat (MITT) (OR: 1.24, 95% Cl: [0.93, 1.66], P = 0.15) and clinically evaluable (CE) populations (OR: 1.92, 95% Cl: [0.94, 3.92], P = 0.07). For microbiological response, OMC was numerically higher than LZD in the microbiologically evaluable (ME) (OR: 1.74, 95% Cl: [0.81, 3.74], P = 0.16) and microbiological MITT (micro-MITT) populations (OR: 1.27, 95% Cl: [0.92, 1.76], P = 0.14). No significant difference was found in subpopulations of monomicrobial or polymicrobial mixed infection populations. The mortality and adverse event rates were similar between OMC and LZD. CONCLUSIONS: OMC was as good as LZD in terms of clinical efficacy and microbiological response, and has similar safety issues in treating cSSTIs. OMC might be a promising option for treating cSSTIs in adult patients.

Alkadiyne-Pyrene Conjugated Frameworks with Surface Exclusion Effect for Ultrafast Seawater Desalination.

Billions of populations are suffering from the supply-demand imbalance of clean water, resulting in a global sustainability crisis. Membrane desalination is a promising method to produce fresh water from saline waters. However, conventional membranes often encounter challenges related to low water permeation, negatively impacting energy efficiency and water productivity. Herein, we achieve ultrafast desalination over the newly developed alkadiyne-pyrene conjugated frameworks membrane supported on a porous copper hollow fiber. With membrane distillation, the membrane exhibits nearly complete NaCl rejection (>99.9%) and ultrahigh fluxes (∼500 L m-2 h-1) from the seawater salinity-level NaCl solutions, which surpass the commercial polymeric membranes with at least 1 order of magnitude higher permeability. Experimental and theoretical investigations suggest that the large aspect ratio of membrane pores and the high evaporation area contribute to the high flux, and the graphene-like hydrophobic surface of conjugated frameworks exhibits complete salt exclusion. The simulations also confirm that the intraplanar pores of frameworks are impermeable for water and ions.

A Cross-Scale Transformer and Triple-View Attention Based Domain-Rectified Transfer Learning for EEG Classification in RSVP Tasks.

Rapid serial visual presentation (RSVP)-based brain-computer interface (BCI) is a promising target detection technique by using electroencephalogram (EEG) signals. However, existing deep learning approaches seldom considered dependencies of multi-scale temporal features and discriminative multi-view spectral features simultaneously, which limits the representation learning ability of the model and undermine the EEG classification performance. In addition, recent transfer learning-based methods generally failed to obtain transferable cross-subject invariant representations and commonly ignore the individual-specific information, leading to the poor cross-subject transfer performance. In response to these limitations, we propose a cross-scale Transformer and triple-view attention based domain-rectified transfer learning (CST-TVA-DRTL) for the RSVP classification. Specially, we first develop a cross-scale Transformer (CST) to extract multi-scale temporal features and exploit the dependencies of different scales features. Then, a triple-view attention (TVA) is designed to capture spectral features from triple views of multi-channel time-frequency images. Finally, a domain-rectified transfer learning (DRTL) framework is proposed to simultaneously obtain transferable domain-invariant representations and untransferable domain-specific representations, then utilize domain-specific information to rectify domain-invariant representations to adapt to target data. Experimental results on two public RSVP datasets suggests that our CST-TVA-DRTL outperforms the state-of-the-art methods in the RSVP classification task. The source code of our model is publicly available in https://github.com/ljbuaa/CST_TVA_DRTL.