Prediction and scheduling of multi-energy microgrid based on BiGRU self-attention mechanism and LQPSO

To predict renewable energy sources such as solar power in microgrids more accurately,a hybrid power prediction method is presented in this paper.First,the self-attention mechanism is introduced based on a bidirectional gated recurrent neural network(BiGRU)to explore the time-series characteristics of solar power output and consider the influence of different time nodes on the prediction results.Subsequently,an improved quantum particle swarm optimization(QPSO)algorithm is proposed to optimize the hyperparameters of the combined prediction model.The final proposed LQPSO-BiGRU-self-attention hybrid model can predict solar power more effectively.In addition,considering the coordinated utilization of various energy sources such as electricity,hydrogen,and renewable energy,a multi-objective optimization model that considers both economic and environmental costs was constructed.A two-stage adaptive multi-objective quantum particle swarm optimization algorithm aided by a Lévy flight,named MO-LQPSO,was proposed for the comprehensive optimal scheduling of a multi-energy microgrid system.This algorithm effectively balances the global and local search capabilities and enhances the solution of complex nonlinear problems.The effectiveness and superiority of the proposed scheme are verified through comparative simulations.

Aerial target threat assessment based on gated recurrent unit and self-attention mechanism

Aerial threat assessment is a crucial link in modern air combat, whose result counts a great deal for commanders to make decisions. With the consideration that the existing threat assessment methods have difficulties in dealing with high dimensional time series target data, a threat assessment method based on self-attention mechanism and gated recurrent unit(SAGRU) is proposed. Firstly, a threat feature system including air combat situations and capability features is established. Moreover, a data augmentation process based on fractional Fourier transform(FRFT) is applied to extract more valuable information from time series situation features. Furthermore, aiming to capture key characteristics of battlefield evolution, a bidirectional GRU and SA mechanisms are designed for enhanced features.Subsequently, after the concatenation of the processed air combat situation and capability features, the target threat level will be predicted by fully connected neural layers and the softmax classifier. Finally, in order to validate this model, an air combat dataset generated by a combat simulation system is introduced for model training and testing. The comparison experiments show the proposed model has structural rationality and can perform threat assessment faster and more accurately than the other existing models based on deep learning.

Hierarchical multihead self-attention for time-series-based fault diagnosis

Fault diagnosis is important for maintaining the safety and effectiveness of chemical process.Considering the multivariate,nonlinear,and dynamic characteristic of chemical process,many time-series-based data-driven fault diagnosis methods have been developed in recent years.However,the existing methods have the problem of long-term dependency and are difficult to train due to the sequential way of training.To overcome these problems,a novel fault diagnosis method based on time-series and the hierarchical multihead self-attention(HMSAN)is proposed for chemical process.First,a sliding window strategy is adopted to construct the normalized time-series dataset.Second,the HMSAN is developed to extract the time-relevant features from the time-series process data.It improves the basic self-attention model in both width and depth.With the multihead structure,the HMSAN can pay attention to different aspects of the complicated chemical process and obtain the global dynamic features.However,the multiple heads in parallel lead to redundant information,which cannot improve the diagnosis performance.With the hierarchical structure,the redundant information is reduced and the deep local time-related features are further extracted.Besides,a novel many-to-one training strategy is introduced for HMSAN to simplify the training procedure and capture the long-term dependency.Finally,the effectiveness of the proposed method is demonstrated by two chemical cases.The experimental results show that the proposed method achieves a great performance on time-series industrial data and outperforms the state-of-the-art approaches.

Overview of the immunological mechanisms in hepatitis B virus reactivation:Implications for disease progression and management strategies

Hepatitis B virus(HBV)reactivation is a clinically significant challenge in disease management.This review explores the immunological mechanisms underlying HBV reactivation,emphasizing disease progression and management.It delves into host immune responses and reactivation’s delicate balance,spanning innate and adaptive immunity.Viral factors’disruption of this balance,as are interac-tions between viral antigens,immune cells,cytokine networks,and immune checkpoint pathways,are examined.Notably,the roles of T cells,natural killer cells,and antigen-presenting cells are discussed,highlighting their influence on disease progression.HBV reactivation’s impact on disease severity,hepatic flares,liver fibrosis progression,and hepatocellular carcinoma is detailed.Management strategies,including anti-viral and immunomodulatory approaches,are critically analyzed.The role of prophylactic anti-viral therapy during immunosuppressive treatments is explored alongside novel immunotherapeutic interventions to restore immune control and prevent reactivation.In conclusion,this compre-hensive review furnishes a holistic view of the immunological mechanisms that propel HBV reactivation.With a dedicated focus on understanding its implic-ations for disease progression and the prospects of efficient management stra-tegies,this article contributes significantly to the knowledge base.The more profound insights into the intricate interactions between viral elements and the immune system will inform evidence-based approaches,ultimately enhancing disease management and elevating patient outcomes.The dynamic landscape of management strategies is critically scrutinized,spanning anti-viral and immunomodulatory approaches.The role of prophylactic anti-viral therapy in preventing reactivation during immunosuppressive treatments and the potential of innovative immunotherapeutic interventions to restore immune control and proactively deter reactivation.

Role of methoxy and C_(α)-based substituents in electrochemical oxidation mechanisms and bond cleavage selectivity of β-O-4 lignin model compounds

In order to better understand the specific substituent effects on the electrochemical oxidation process of β-O-4 bond, a series of methoxyphenyl type β-O-4 dimer model compounds with different localized methoxyl groups, including 2-(2-methoxyphenoxy)-1-phenylethanone, 2-(2-methoxyphenoxy)-1-phenylethanol, 2-(2-methoxyphenoxy)-1-(4-methoxyphenyl)ethanone, 2-(2-methoxyphenoxy)-1-(4-methoxyphenyl)ethanol, 2-(2,6-dimethoxyphenoxy)-1-(4-methoxyphenyl)ethanone, 2-(2,6-dimethoxyphenoxy)-1-(4-methoxyphenyl)ethanol have been selected and their electrochemical properties have been studied experimentally by cyclic voltammetry, and FT-IR spectroelectrochemistry. Combining with electrolysis products distribution analysis and density functional theory calculations, oxidation mechanisms of all six model dimers have been explored. In particular, a total effect from substituents of both para-methoxy(on the aryl ring closing to Cα) and Cα-OH on the oxidation mechanisms has been clearly observed, showing a significant selectivity on the Cα-Cβbond cleavage induced by electrochemical oxidations.

SMSTracker:A Self-Calibration Multi-Head Self-Attention Transformer for Visual Object Tracking

Visual object tracking plays a crucial role in computer vision.In recent years,researchers have proposed various methods to achieve high-performance object tracking.Among these,methods based on Transformers have become a research hotspot due to their ability to globally model and contextualize information.However,current Transformer-based object tracking methods still face challenges such as low tracking accuracy and the presence of redundant feature information.In this paper,we introduce self-calibration multi-head self-attention Transformer(SMSTracker)as a solution to these challenges.It employs a hybrid tensor decomposition self-organizing multihead self-attention transformermechanism,which not only compresses and accelerates Transformer operations but also significantly reduces redundant data,thereby enhancing the accuracy and efficiency of tracking.Additionally,we introduce a self-calibration attention fusion block to resolve common issues of attention ambiguities and inconsistencies found in traditional trackingmethods,ensuring the stability and reliability of tracking performance across various scenarios.By integrating a hybrid tensor decomposition approach with a self-organizingmulti-head self-attentive transformer mechanism,SMSTracker enhances the efficiency and accuracy of the tracking process.Experimental results show that SMSTracker achieves competitive performance in visual object tracking,promising more robust and efficient tracking systems,demonstrating its potential to providemore robust and efficient tracking solutions in real-world applications.

A Self-Attention Based Dynamic Resource Management for Satellite-Terrestrial Networks

The satellite-terrestrial networks possess the ability to transcend geographical constraints inherent in traditional communication networks,enabling global coverage and offering users ubiquitous computing power support,which is an important development direction of future communications.In this paper,we take into account a multi-scenario network model under the coverage of low earth orbit(LEO)satellite,which can provide computing resources to users in faraway areas to improve task processing efficiency.However,LEO satellites experience limitations in computing and communication resources and the channels are time-varying and complex,which makes the extraction of state information a daunting task.Therefore,we explore the dynamic resource management issue pertaining to joint computing,communication resource allocation and power control for multi-access edge computing(MEC).In order to tackle this formidable issue,we undertake the task of transforming the issue into a Markov decision process(MDP)problem and propose the self-attention based dynamic resource management(SABDRM)algorithm,which effectively extracts state information features to enhance the training process.Simulation results show that the proposed algorithm is capable of effectively reducing the long-term average delay and energy consumption of the tasks.

Missing Value Imputation for Radar-Derived Time-Series Tracks of Aerial Targets Based on Improved Self-Attention-Based Network

The frequent missing values in radar-derived time-series tracks of aerial targets(RTT-AT)lead to significant challenges in subsequent data-driven tasks.However,the majority of imputation research focuses on random missing(RM)that differs significantly from common missing patterns of RTT-AT.The method for solving the RM may experience performance degradation or failure when applied to RTT-AT imputation.Conventional autoregressive deep learning methods are prone to error accumulation and long-term dependency loss.In this paper,a non-autoregressive imputation model that addresses the issue of missing value imputation for two common missing patterns in RTT-AT is proposed.Our model consists of two probabilistic sparse diagonal masking self-attention(PSDMSA)units and a weight fusion unit.It learns missing values by combining the representations outputted by the two units,aiming to minimize the difference between the missing values and their actual values.The PSDMSA units effectively capture temporal dependencies and attribute correlations between time steps,improving imputation quality.The weight fusion unit automatically updates the weights of the output representations from the two units to obtain a more accurate final representation.The experimental results indicate that,despite varying missing rates in the two missing patterns,our model consistently outperforms other methods in imputation performance and exhibits a low frequency of deviations in estimates for specific missing entries.Compared to the state-of-the-art autoregressive deep learning imputation model Bidirectional Recurrent Imputation for Time Series(BRITS),our proposed model reduces mean absolute error(MAE)by 31%~50%.Additionally,the model attains a training speed that is 4 to 8 times faster when compared to both BRITS and a standard Transformer model when trained on the same dataset.Finally,the findings from the ablation experiments demonstrate that the PSDMSA,the weight fusion unit,cascade network design,and imputation loss enhance imputation performance and confirm the efficacy of our design.

Activity-dependent mechanisms of neuroprotection:promising avenues against dementia

The study of the brain and its complex functions is highly fascinating and,at the same time,extremely important.Indeed,furthering our understanding of the biology of neurons and synapses is a prerequisite to uncover the mechanisms involved in memory formation and the coordination of movement as well as their alterations occurring in several neurological disorders.

Obituary:Prof.Yun Zhang(1963-2023)-A scientist focused on toxins and their underlying mechanisms to decipher human diseases

Prof.Yun Zhang was born on 9 July 1963 in Kunming,Yunnan,China,during a tumultuous period which he often referenced.Throughout his life,he harbored a steadfast belief in using knowledge to unravel the mysteries of human diseases.His educational journey was marked by frequent changes in schools due to his parents’occupational relocations.However,despite these challenges,he consistently displayed diligence and was admitted to the East China University of Science and Technology,Shanghai,after completing high school in 1980.He remained an active and loyal member of the School of Biotechnology at the university.

Chlorfenapyr poisoning:mechanisms,clinical presentations,and treatment strategies

BACKGROUND:Chlorfenapyr is used to kill insects that are resistant to organophosphorus insecticides.Chlorfenapyr poisoning has a high mortality rate and is difficult to treat.This article aims to review the mechanisms,clinical presentations,and treatment strategies for chlorfenapyr poisoning.DATA RESOURCES:We conducted a review of the literature using PubMed,Web of Science,and SpringerLink from their beginnings to the end of October 2023.The inclusion criteria were systematic reviews,clinical guidelines,retrospective studies,and case reports on chlorfenapyr poisoning that focused on its mechanisms,clinical presentations,and treatment strategies.The references in the included studies were also examined to identify additional sources.RESULTS:We included 57 studies in this review.Chlorfenapyr can be degraded into tralopyril,which is more toxic and reduces energy production by inhibiting the conversion of adenosine diphosphate to adenosine triphosphate.High fever and altered mental status are characteristic clinical presentations of chlorfenapyr poisoning.Once it occurs,respiratory failure occurs immediately,ultimately leading to cardiac arrest and death.Chlorfenapyr poisoning is diflcult to treat,and there is no specific antidote.CONCLUSION:Chlorfenapyr is a new pyrrole pesticide.Although it has been identified as a moderately toxic pesticide by the World Health Organization(WHO),the mortality rate of poisoned patients is extremely high.There is no specific antidote for chlorfenapyr poisoning.Therefore,based on the literature review,future efforts to explore rapid and effective detoxification methods,reconstitute intracellular oxidative phosphorylation couplings,identify early biomarkers of chlorfenapyr poisoning,and block the conversion of chlorfenapyr to tralopyril may be helpful for emergency physicians in the diagnosis and treatment of this disease.

Regeneration of the heart:f rom molecular mechanisms to clinical therapeutics

Heart injury such as myocardial infarction leads to cardiomyocyte loss,fibrotic tissue deposition,and scar formation.These changes reduce cardiac contractility,resulting in heart failure,which causes a huge public health burden.Military personnel,compared with civilians,is exposed to more stress,a risk factor for heart diseases,making cardiovascular health management and treatment innovation an important topic for military medicine.So far,medical intervention can slow down cardiovascular disease progression,but not yet induce heart regeneration.In the past decades,studies have focused on mechanisms underlying the regenerative capability of the heart and applicable approaches to reverse heart injury.Insights have emerged from studies in animal models and early clinical trials.Clinical interventions show the potential to reduce scar formation and enhance cardiomyocyte proliferation that counteracts the pathogenesis of heart disease.In this review,we discuss the signaling events controlling the regeneration of heart tissue and summarize current therapeutic approaches to promote heart regeneration after injury.

Controllable Condensation of Aromatics and Its Mechanisms in Carbonization

In order to obtain liquefied products with higher yields of aromatic molecules to produce mesophase pitch,a good understanding of the relevant reaction mechanisms is required.Reactive molecular dynamics simulations were used to study the thermal reactions of pyrene,1-methylpyrene,7,8,9,10-tetrahydrobenzopyrene,and mixtures of pyrene with 1-octene,cyclohexene,or styrene.The reactant conversion rates,reaction rates,and product distributions were calculated and compared,and the mechanisms were analyzed and discussed.The results demonstrated that methyl and naphthenic structures in aromatics might improve the conversion rates of reactants in hydrogen transfer processes,but their steric hindrances prohibited the generation of high polymers.The naphthenic structures could generate more free radicals and presented a more obvious inhibition effect on the condensation of polymers compared with the methyl side chains.It was discovered that when different olefins were mixed with pyrene,1-octene primarily underwent pyrolysis reactions,whereas cyclohexene mainly underwent hydrogen transfer reactions with pyrene and styrene,mostly producing superconjugated biradicals through condensation reactions with pyrene.In the mixture systems,the olefins scattered aromatic molecules,hindering the formation of pyrene trimers and higher polymers.According to the reactive molecular dynamics simulations,styrene may enhance the yield of dimer and enable the controlled polycondensation of pyrene.

Drug resistance mechanisms in cancers:Execution of prosurvival strategies

One of the quintessential challenges in cancer treatment is drug resistance.Several mechanisms of drug resistance have been described to date,and new modes of drug resistance continue to be discovered.The phenomenon of cancer drug resistance is now widespread,with approximately 90% of cancer-related deaths associated with drug resistance.Despite significant advances in the drug discovery process,the emergence of innate and acquired mechanisms of drug resistance has impeded the progress in cancer therapy.Therefore,understanding the mechanisms of drug resistance and the various pathways involved is integral to treatment modalities.In the present review,I discuss the different mechanisms of drug resistance in cancer cells,including DNA damage repair,epithelial to mesenchymal transition,inhibition of cell death,alteration of drug targets,inactivation of drugs,deregulation of cellular energetics,immune evasion,tumor-promoting inflammation,genome instability,and other contributing epigenetic factors.Furthermore,I highlight available treatment options and conclude with future directions.

Evolution model and failure mechanisms of rainfall-induced cracked red clay slopes:insights from Xinshao County,China

Red clay landslides are widely distributed worldwide,resulting in severe loss of life and property.Although rainfall-induced red clay slopes have received extensive attention,the role of cracks in the evolutionary process of red clay slopes and their connection to failure mechanisms is still poorly understood.A comprehensive approach integrating field investigation,laboratory tests,and numerical simulations was conducted to study the 168 red clay landslides in Xinshao County,China.The results show that red clay is prone to forming cracks at high moisture content due to its low swelling and high shrinkage properties.The failure mode of red clay slopes can be summarized in three stages:crack generation,slope excavation,and slope failure.Furthermore,the retrospective analysis and numerical simulations of the typical landslide in Guanchong indicated that intense rainfall primarily impacts the shallow layer of soil within approximately 0.5 m on the intact slope.However,cracks change the pattern of rainfall infiltration in the slope.Rainwater infiltrates rapidly through the preferential channels induced by the cracks rather than uniformly and slowly from the slope surface.This results in a significant increase in both the depth of infiltration and the saturated zone area of the cracked slope,reaching 3.8 m and 36.2 m^(2),respectively.Consequently,the factor of safety of the slope decreases by 13.4%compared to the intact slope,ultimately triggering landslides.This study can provide valuable insights into understanding the failure mechanisms of red clay slopes in China and other regions with similar geological settings.

Clothing Parsing Based on Multi-Scale Fusion and Improved Self-Attention Mechanism

Due to the lack of long-range association and spatial location information,fine details and accurate boundaries of complex clothing images cannot always be obtained by using the existing deep learning-based methods.This paper presents a convolutional structure with multi-scale fusion to optimize the step of clothing feature extraction and a self-attention module to capture long-range association information.The structure enables the self-attention mechanism to directly participate in the process of information exchange through the down-scaling projection operation of the multi-scale framework.In addition,the improved self-attention module introduces the extraction of 2-dimensional relative position information to make up for its lack of ability to extract spatial position features from clothing images.The experimental results based on the colorful fashion parsing dataset(CFPD)show that the proposed network structure achieves 53.68%mean intersection over union(mIoU)and has better performance on the clothing parsing task.

Seed Storability in Rice: Physiological Foundations, Molecular Mechanisms, and Applications in Breeding

Long-term storage of crop seeds is critical for the conservation of germplasm resources, ensuring food supply, and supporting sustainable production. Rice, as a major food staple, has a substantial stock for consumption and production worldwide. However, its food value and seed viability tend to decline during storage. Understanding the physiological responses and molecular mechanisms of aging tolerance forms the basis for enhancing seed storability in rice. This review outlines the latest progress in influential factors, evaluation methods, and identification indices of seed storability. It also discusses the physiological consequences, molecular mechanisms, and strategies for breeding aging-tolerant rice in detail. Finally, it highlights challenges in seed storability research that require future attention. This review offers a theoretical foundation and research direction for uncovering the mechanisms behind seed storability and breeding aging-tolerant rice.

Enhancing Image Description Generation through Deep Reinforcement Learning:Fusing Multiple Visual Features and Reward Mechanisms

Image description task is the intersection of computer vision and natural language processing,and it has important prospects,including helping computers understand images and obtaining information for the visually impaired.This study presents an innovative approach employing deep reinforcement learning to enhance the accuracy of natural language descriptions of images.Our method focuses on refining the reward function in deep reinforcement learning,facilitating the generation of precise descriptions by aligning visual and textual features more closely.Our approach comprises three key architectures.Firstly,it utilizes Residual Network 101(ResNet-101)and Faster Region-based Convolutional Neural Network(Faster R-CNN)to extract average and local image features,respectively,followed by the implementation of a dual attention mechanism for intricate feature fusion.Secondly,the Transformer model is engaged to derive contextual semantic features from textual data.Finally,the generation of descriptive text is executed through a two-layer long short-term memory network(LSTM),directed by the value and reward functions.Compared with the image description method that relies on deep learning,the score of Bilingual Evaluation Understudy(BLEU-1)is 0.762,which is 1.6%higher,and the score of BLEU-4 is 0.299.Consensus-based Image Description Evaluation(CIDEr)scored 0.998,Recall-Oriented Understudy for Gisting Evaluation(ROUGE)scored 0.552,the latter improved by 0.36%.These results not only attest to the viability of our approach but also highlight its superiority in the realm of image description.Future research can explore the integration of our method with other artificial intelligence(AI)domains,such as emotional AI,to create more nuanced and context-aware systems.

Mobile Crowdsourcing Task Allocation Based on Dynamic Self-Attention GANs

Crowdsourcing technology is widely recognized for its effectiveness in task scheduling and resource allocation.While traditional methods for task allocation can help reduce costs and improve efficiency,they may encounter challenges when dealing with abnormal data flow nodes,leading to decreased allocation accuracy and efficiency.To address these issues,this study proposes a novel two-part invalid detection task allocation framework.In the first step,an anomaly detection model is developed using a dynamic self-attentive GAN to identify anomalous data.Compared to the baseline method,the model achieves an approximately 4%increase in the F1 value on the public dataset.In the second step of the framework,task allocation modeling is performed using a twopart graph matching method.This phase introduces a P-queue KM algorithm that implements a more efficient optimization strategy.The allocation efficiency is improved by approximately 23.83%compared to the baseline method.Empirical results confirm the effectiveness of the proposed framework in detecting abnormal data nodes,enhancing allocation precision,and achieving efficient allocation.

A comparative study on kinetics and dynamics of two dump truck lifting mechanisms using MATLAB simscape

In this paper,two lifting mechanism models with opposing placements,which use the same hydraulic hoist model and have the same angle of 50°,have been developed.The mechanical and hydraulic simulation models are established using MATLAB Simscape to analyze their kinetics and dynamics in the lifting and holding stages.The simulation findings are compared to the analytical calculation results in the steady state,and both methods show good agreement.In the early lifting stage,Model 1 produces greater force and discharges goods in the container faster than Model 2.Meanwhile,Model 2 reaches a higher force and ejects goods from the container cleaner than its counterpart at the end lifting stage.The established simulation models can consider the effects of dynamic loads due to inertial moments and forces generated during the system operation.It is crucial in studying,designing,and optimizing the structure of hydraulic-mechanical systems.