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.

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.

Sentiment classification model for bullet screen based on self-attention mechanism

With the development of short video industry,video and bullet screen have become important ways to spread public opinions.Public attitudes can be timely obtained through emotional analysis on bullet screen,which can also reduce difficulties in management of online public opinions.A convolutional neural network model based on multi-head attention is proposed to solve the problem of how to effectively model relations among words and identify key words in emotion classification tasks with short text contents and lack of complete context information.Firstly,encode word positions so that order information of input sequences can be used by the model.Secondly,use a multi-head attention mechanism to obtain semantic expressions in different subspaces,effectively capture internal relevance and enhance dependent relationships among words,as well as highlight emotional weights of key emotional words.Then a dilated convolution is used to increase the receptive field and extract more features.On this basis,the above multi-attention mechanism is combined with a convolutional neural network to model and analyze the seven emotional categories of bullet screens.Testing from perspectives of model and dataset,experimental results can validate effectiveness of our approach.Finally,emotions of bullet screens are visualized to provide data supports for hot event controls and other fields.

Keyphrase Generation Based on Self-Attention Mechanism

Keyphrase greatly provides summarized and valuable information.This information can help us not only understand text semantics,but also organize and retrieve text content effectively.The task of automatically generating it has received considerable attention in recent decades.From the previous studies,we can see many workable solutions for obtaining keyphrases.One method is to divide the content to be summarized into multiple blocks of text,then we rank and select the most important content.The disadvantage of this method is that it cannot identify keyphrase that does not include in the text,let alone get the real semantic meaning hidden in the text.Another approach uses recurrent neural networks to generate keyphrases from the semantic aspects of the text,but the inherently sequential nature precludes parallelization within training examples,and distances have limitations on context dependencies.Previous works have demonstrated the benefits of the self-attention mechanism,which can learn global text dependency features and can be parallelized.Inspired by the above observation,we propose a keyphrase generation model,which is based entirely on the self-attention mechanism.It is an encoder-decoder model that can make up the above disadvantage effectively.In addition,we also consider the semantic similarity between keyphrases,and add semantic similarity processing module into the model.This proposed model,which is demonstrated by empirical analysis on five datasets,can achieve competitive performance compared to baseline methods.

QAR Data Imputation Using Generative Adversarial Network with Self-Attention Mechanism

Quick Access Recorder(QAR),an important device for storing data from various flight parameters,contains a large amount of valuable data and comprehensively records the real state of the airline flight.However,the recorded data have certain missing values due to factors,such as weather and equipment anomalies.These missing values seriously affect the analysis of QAR data by aeronautical engineers,such as airline flight scenario reproduction and airline flight safety status assessment.Therefore,imputing missing values in the QAR data,which can further guarantee the flight safety of airlines,is crucial.QAR data also have multivariate,multiprocess,and temporal features.Therefore,we innovatively propose the imputation models A-AEGAN("A"denotes attention mechanism,"AE"denotes autoencoder,and"GAN"denotes generative adversarial network)and SA-AEGAN("SA"denotes self-attentive mechanism)for missing values of QAR data,which can be effectively applied to QAR data.Specifically,we apply an innovative generative adversarial network to impute missing values from QAR data.The improved gated recurrent unit is then introduced as the neural unit of GAN,which can successfully capture the temporal relationships in QAR data.In addition,we modify the basic structure of GAN by using an autoencoder as the generator and a recurrent neural network as the discriminator.The missing values in the QAR data are imputed by using the adversarial relationship between generator and discriminator.We introduce an attention mechanism in the autoencoder to further improve the capability of the proposed model to capture the features of QAR data.Attention mechanisms can maintain the correlation among QAR data and improve the capability of the model to impute missing data.Furthermore,we improve the proposed model by integrating a self-attention mechanism to further capture the relationship between different parameters within the QAR data.Experimental results on real datasets demonstrate that the model can reasonably impute the missing values in QAR data with excellent results.

A Method for Extracting Electronic Medical Record Entities by Fusing Multichannel Self-Attention Mechanism with Location Relationship Features

With the implementation of the“Internet+”strategy,electronic medi-cal records are generally applied in the medicalfield.Deep mining of electronic medical record content data is an effective means to obtain medical knowledge and analyse patients’states,but the existing methods for extracting entities from electronic medical records have problems of redundant information,overlapping entities,and low accuracy rates.Therefore,this paper proposes an entity extrac-tion method for electronic medical records based on the network framework of BERT-BiLSTM,which incorporates a multichannel self-attention mechanism and location relationship features.First,the text input sequence was encoded using the BERT-BiLSTM network framework,and the global semantic information of the sentence was mined more deeply using the multichannel self-attention mech-anism.Then,the position relation characteristic was used to extract the local semantic message of the text,and the position relation characteristic of the word and the position embedding matrix of the whole sentence were obtained.Next,the extracted global semantic information was stitched with the positional embedding matrix of the sentence to obtain the current entity classification matrix.Finally,the proposed method was validated on the dataset of Chinese medical text entity relationship extraction and the 2010i2b2/VA relationship corpus,and the exper-imental results indicate that the proposed method surpasses existing methods in terms of precision,recall,F1 value and training time.

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.

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.

The underlying mechanism of variety–water–nitrogen–stubble damage interactions on yield formation in ratoon rice with low stubble height under mechanized harvesting

Agronomic measures are the key to promote the sustainable development of ratoon rice by reducing the damage from mechanical crushing to the residual stubble of the main crop, thereby mitigating the impact on axillary bud sprouting and yield formation in ratoon rice. This study used widely recommended conventional rice Jiafuzhan and hybrid rice Yongyou 2640 as the test materials to conduct a four-factor block design field experiment in a greenhouse of the experimental farm of Fujian Agricultural and Forestry University, China from 2018 to 2019.The treatments included fertilization and no fertilization, alternate wetting and drying irrigation and continuous water flooding irrigation, and plots with and without artificial crushing damage on the rice stubble. At the same time, a 13C stable isotope in-situ detection technology was used to fertilize the pot experiment. The results showed significant interactions among varieties, water management, nitrogen application and stubble status.Relative to the long-term water flooding treatment, the treatment with sequential application of nitrogen fertilizer coupled with moderate field drought for root-vigor and tiller promotion before and after harvesting of the main crop, significantly improved the effective tillers from low position nodes. This in turn increased the effective panicles per plant and grains per panicle by reducing the influence of artificial crushing damage on rice stubble and achieving a high yield of the regenerated rice. Furthermore, the partitioning of 13C assimilates to the residual stubble and its axillary buds were significantly improved at the mature stage of the main crop, while the translocation rate to roots and rhizosphere soil was reduced at the later growth stage of ratooning season rice. This was triggered by the metabolism of hormones and polyamines at the stem base regulated by the interaction of water and fertilizer at this time. We therefore suggest that to achieve a high yield of ratoon rice with low stubble height under mechanized harvesting, the timely application of nitrogen fertilizer is fundamental,coupled with moderate field drying for root-vigor preservation and tiller promotion before and after the mechanical harvesting of the main crop.

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.

To explore the mechanism of Yigong San anti-gastric cancer and immune regulation

BACKGROUND Yigong San(YGS)is a representative prescription for the treatment of digestive disorders,which has been used in clinic for more than 1000 years.However,the mechanism of its anti-gastric cancer and regulate immunity are still remains unclear.AIM To explore the mechanism of YGS anti-gastric cancer and immune regulation.METHODS Firstly,collect the active ingredients and targets of YGS,and the differentially expressed genes of gastric cancer.Secondly,constructed a protein-protein interaction network between the targets of drugs and diseases,and screened hub genes.Then the clinical relevance,mutation and repair,tumor microenvironment and drug sensitivity of the hub gene were analyzed.Finally,molecular docking was used to verify the binding ability of YGS active ingredient and hub genes.RESULTS Firstly,obtained 55 common targets of gastric cancer and YGS.The Kyoto Encyclopedia of Genes and Genomes screened the microtubule-associated protein kinase signaling axis as the key pathway and IL6,EGFR,MMP2,MMP9 and TGFB1 as the hub genes.The 5 hub genes were involved in gastric carcinogenesis,staging,typing and prognosis,and their mutations promote gastric cancer progression.Finally,molecular docking results confirmed that the components of YGS can effectively bind to therapeutic targets.CONCLUSION YGS has the effect of anti-gastric cancer and immune regulation.

Deep Insight of Design,Mechanism,and Cancer Theranostic Strategy of Nanozymes

Since the discovery of enzyme-like activity of Fe3O4 nanoparticles in 2007,nanozymes are becoming the promising substitutes for natural enzymes due to their advantages of high catalytic activity,low cost,mild reaction conditions,good stability,and suitable for large-scale production.Recently,with the cross fusion of nanomedicine and nanocatalysis,nanozyme-based theranostic strategies attract great attention,since the enzymatic reactions can be triggered in the tumor microenvironment to achieve good curative effect with substrate specificity and low side effects.Thus,various nanozymes have been developed and used for tumor therapy.In this review,more than 270 research articles are discussed systematically to present progress in the past five years.First,the discovery and development of nanozymes are summarized.Second,classification and catalytic mechanism of nanozymes are discussed.Third,activity prediction and rational design of nanozymes are focused by highlighting the methods of density functional theory,machine learning,biomimetic and chemical design.Then,synergistic theranostic strategy of nanozymes are introduced.Finally,current challenges and future prospects of nanozymes used for tumor theranostic are outlined,including selectivity,biosafety,repeatability and stability,in-depth catalytic mechanism,predicting and evaluating activities.

Instability mechanism of mining roadway passing through fault at different angles in kilometre-deep mine and control measures of roof cutting and NPR cables

The angle α between the fault strike and the axial direction of the roadway produces different damage characteristics. In this paper, the research methodology includes theoretical analyses, numerical simulations and field experiments in the context of the Daqiang coal mine located in Shenyang, China. The stability control countermeasure of "pre-splitting cutting roof + NPR anchor cable"(PSCR-NPR) is simultaneously proposed. According to the different deformation characteristics of the roadway, the faults are innovatively classified into three types, with α of type I being 0°-30°, α of type II being 30°-60°, and α of type III being 60°-90°. The full-cycle stress evolution paths during mining roadway traverses across different types of faults are investigated by numerical simulation. Different pinch angles α lead to high stress concentration areas at different locations in the surrounding rock. The non-uniform stress field formed in the shallow surrounding rock is an important reason for the instability of the roadway. The pre-cracked cut top shifted the high stress region to the deep rock mass and formed a low stress region in the shallow rock mass. The high prestressing NPR anchor cable transforms the non-uniform stress field of the shallow surrounding rock into a uniform stress field. PSCR-NPR is applied in the fault-through roadway of Daqiang mine. The low stress area of the surrounding rock was enlarged by 3-7 times, and the cumulative convergence was reduced by 45%-50%. It provides a reference for the stability control of the deep fault-through mining roadway.

Molecular Mechanism and Molecular Design of Lubricating Oil Antioxidants

To overcome the limitations of traditional experimental“trial and error”methods in lubricant additive design,a new molecular design method based on molecular structure parameters is established here.The molecular mechanism of the antioxidant reaction of hindered phenol,diphenylamine,and alkyl sulfide are studied via molecular simulations.Calculation results show that the strong electron-donating ability and high hydrogen-donating activity of the antioxidant molecule and the low hydrogen-abstracting activity of free radicals formed after dehydrogenation are the internal molecular causes of the shielding of phenol and diphenylamine from scavenging peroxy free radicals,and the strong electron-donating ability is the internal molecular cause of the high activity of thioether in decomposing alkyl hydrogen peroxide.Based on this antioxidant molecular mechanism,a molecular design rule of antioxidant is proposed,namely“high EHOMO,large Q(S),low bond dissociation energy BDE(O—H)and BDE(N—H)”.Two new antioxidants,PAS-I and PAS-II,are designed and prepared by chemical bonding of hindered phenol,diphenylamine,and sulfur atoms.Experimental results show that these antioxidants both have excellent antioxidant effects in lubricating oil,and that PAS-II is the superior antioxidant,consistent with theoretical predictions.

Recent research progress in the mechanism and suppression of fusion welding-induced liquation cracking of nickel based superalloys

Nickel-based superalloys are extensively used in the crucial hot-section components of industrial gas turbines,aeronautics,and astronautics because of their excellent mechanical properties and corrosion resistance at high temperatures.Fusion welding serves as an effective means for joining and repairing these alloys;however,fusion welding-induced liquation cracking has been a challenging issue.This paper comprehensively reviewed recent liquation cracking,discussing the formation mechanisms,cracking criteria,and remedies.In recent investigations,regulating material composition,changing the preweld heat treatment of the base metal,optimizing the welding process parameters,and applying auxiliary control methods are effective strategies for mitigating cracks.To promote the application of nickel-based superalloys,further research on the combination impact of multiple elements on cracking prevention and specific quantitative criteria for liquation cracking is necessary.

Preliminary discussion on the ignition mechanism of exploding foil initiators igniting boron potassium nitrate

Exploding foil initiator(EFI)is a kind of advanced device for initiating explosives,but its function is unstable when it comes to directly igniting pyrotechnics.To solve the problem,this research aims to reveal the ignition mechanism of EFIs directly igniting pyrotechnics.An oscilloscope,a photon Doppler velocimetry,and a plasma spectrum measurement system were employed to obtain information of electric characteristics,impact pressure,and plasma temperature.The results of the electric characteristics and the impact pressure were inconsistent with ignition results.The only thing that the ignition success tests had in common was that their plasma all had a relatively long period of high-temperature duration(HTD).It eventually concludes that the ignition mechanism in this research is the microconvection heat transfer rather than the shock initiation,which differs from that of exploding foil initiators detonating explosives.Furthermore,the methods for evaluating the ignition success of semiconductor bridge initiators are not entirely applicable to the tests mentioned in this paper.The HTD is the critical parameter for judging the ignition success,and it is influenced by two factors:the late time discharge and the energy of the electric explosion.The longer time of the late time discharge and the more energy of the electric explosion,the easier it is to expand the HTD,which improves the probability of the ignition success.

Unraveling the Fundamental Mechanism of Interface Conductive Network Influence on the Fast‑Charging Performance of SiO‑Based Anode for Lithium‑Ion Batteries

Progress in the fast charging of high-capacity silicon monoxide(SiO)-based anode is currently hindered by insufficient conductivity and notable volume expansion.The construction of an interface conductive network effectively addresses the aforementioned problems;however,the impact of its quality on lithium-ion transfer and structure durability is yet to be explored.Herein,the influence of an interface conductive network on ionic transport and mechanical stability under fast charging is explored for the first time.2D modeling simulation and Cryo-transmission electron microscopy precisely reveal the mitigation of interface polarization owing to a higher fraction of conductive inorganic species formation in bilayer solid electrolyte interphase is mainly responsible for a linear decrease in ionic diffusion energy barrier.Furthermore,atomic force microscopy and Raman shift exhibit substantial stress dissipation generated by a complete conductive network,which is critical to the linear reduction of electrode residual stress.This study provides insights into the rational design of optimized interface SiO-based anodes with reinforced fast-charging performance.

Efficient Unsupervised Image Stitching Using Attention Mechanism with Deep Homography Estimation

Traditional feature-based image stitching techniques often encounter obstacles when dealing with images lackingunique attributes or suffering from quality degradation. The scarcity of annotated datasets in real-life scenesseverely undermines the reliability of supervised learning methods in image stitching. Furthermore, existing deeplearning architectures designed for image stitching are often too bulky to be deployed on mobile and peripheralcomputing devices. To address these challenges, this study proposes a novel unsupervised image stitching methodbased on the YOLOv8 (You Only Look Once version 8) framework that introduces deep homography networksand attentionmechanisms. Themethodology is partitioned into three distinct stages. The initial stage combines theattention mechanism with a pooling pyramid model to enhance the detection and recognition of compact objectsin images, the task of the deep homography networks module is to estimate the global homography of the inputimages consideringmultiple viewpoints. The second stage involves preliminary stitching of the masks generated inthe initial stage and further enhancement through weighted computation to eliminate common stitching artifacts.The final stage is characterized by adaptive reconstruction and careful refinement of the initial stitching results.Comprehensive experiments acrossmultiple datasets are executed tometiculously assess the proposed model. Ourmethod’s Peak Signal-to-Noise Ratio (PSNR) and Structure Similarity Index Measure (SSIM) improved by 10.6%and 6%. These experimental results confirm the efficacy and utility of the presented model in this paper.

An Underwater Target Detection Algorithm Based on Attention Mechanism and Improved YOLOv7

For underwater robots in the process of performing target detection tasks,the color distortion and the uneven quality of underwater images lead to great difficulties in the feature extraction process of the model,which is prone to issues like error detection,omission detection,and poor accuracy.Therefore,this paper proposed the CER-YOLOv7(CBAM-EIOU-RepVGG-YOLOv7)underwater target detection algorithm.To improve the algorithm’s capability to retain valid features from both spatial and channel perspectives during the feature extraction phase,we have added a Convolutional Block Attention Module(CBAM)to the backbone network.The Reparameterization Visual Geometry Group(RepVGG)module is inserted into the backbone to improve the training and inference capabilities.The Efficient Intersection over Union(EIoU)loss is also used as the localization loss function,which reduces the error detection rate and missed detection rate of the algorithm.The experimental results of the CER-YOLOv7 algorithm on the UPRC(Underwater Robot Prototype Competition)dataset show that the mAP(mean Average Precision)score of the algorithm is 86.1%,which is a 2.2%improvement compared to the YOLOv7.The feasibility and validity of the CER-YOLOv7 are proved through ablation and comparison experiments,and it is more suitable for underwater target detection.