This paper focuses on an important type of black-box attacks,i.e.,transfer-based adversarial attacks,where the adversary generates adversarial examples using a substitute(source)model and utilizes them to attack an un...This paper focuses on an important type of black-box attacks,i.e.,transfer-based adversarial attacks,where the adversary generates adversarial examples using a substitute(source)model and utilizes them to attack an unseen target model,without knowing its information.Existing methods tend to give unsatisfactory adversarial transferability when the source and target models are from different types of DNN architectures(e.g.,ResNet-18 and Swin Transformer).In this paper,we observe that the above phenomenon is induced by the output inconsistency problem.To alleviate this problem while effectively utilizing the existing DNN models,we propose a common knowledge learning(CKL)framework to learn better network weights to generate adversarial examples with better transferability,under fixed network architectures.Specifically,to reduce the model-specific features and obtain better output distributions,we construct a multi-teacher framework,where the knowledge is distilled from different teacher architectures into one student network.By considering that the gradient of input is usually utilized to generate adversarial examples,we impose constraints on the gradients between the student and teacher models,to further alleviate the output inconsistency problem and enhance the adversarial transferability.Extensive experiments demonstrate that our proposed work can significantly improve the adversarial transferability.展开更多
Knowledge distillation(KD) enhances student network generalization by transferring dark knowledge from a complex teacher network. To optimize computational expenditure and memory utilization, self-knowledge distillati...Knowledge distillation(KD) enhances student network generalization by transferring dark knowledge from a complex teacher network. To optimize computational expenditure and memory utilization, self-knowledge distillation(SKD) extracts dark knowledge from the model itself rather than an external teacher network. However, previous SKD methods performed distillation indiscriminately on full datasets, overlooking the analysis of representative samples. In this work, we present a novel two-stage approach to providing targeted knowledge on specific samples, named two-stage approach self-knowledge distillation(TOAST). We first soften the hard targets using class medoids generated based on logit vectors per class. Then, we iteratively distill the under-trained data with past predictions of half the batch size. The two-stage knowledge is linearly combined, efficiently enhancing model performance. Extensive experiments conducted on five backbone architectures show our method is model-agnostic and achieves the best generalization performance.Besides, TOAST is strongly compatible with existing augmentation-based regularization methods. Our method also obtains a speedup of up to 2.95x compared with a recent state-of-the-art method.展开更多
In recent years,with the continuous development of deep learning and knowledge graph reasoning methods,more and more researchers have shown great interest in improving knowledge graph reasoning methods by inferring mi...In recent years,with the continuous development of deep learning and knowledge graph reasoning methods,more and more researchers have shown great interest in improving knowledge graph reasoning methods by inferring missing facts through reasoning.By searching paths on the knowledge graph and making fact and link predictions based on these paths,deep learning-based Reinforcement Learning(RL)agents can demonstrate good performance and interpretability.Therefore,deep reinforcement learning-based knowledge reasoning methods have rapidly emerged in recent years and have become a hot research topic.However,even in a small and fixed knowledge graph reasoning action space,there are still a large number of invalid actions.It often leads to the interruption of RL agents’wandering due to the selection of invalid actions,resulting in a significant decrease in the success rate of path mining.In order to improve the success rate of RL agents in the early stages of path search,this article proposes a knowledge reasoning method based on Deep Transfer Reinforcement Learning path(DTRLpath).Before supervised pre-training and retraining,a pre-task of searching for effective actions in a single step is added.The RL agent is first trained in the pre-task to improve its ability to search for effective actions.Then,the trained agent is transferred to the target reasoning task for path search training,which improves its success rate in searching for target task paths.Finally,based on the comparative experimental results on the FB15K-237 and NELL-995 datasets,it can be concluded that the proposed method significantly improves the success rate of path search and outperforms similar methods in most reasoning tasks.展开更多
Concomitant with the advancement of contemporary medical technology,the significance of perioperative nursing has been increasingly accentuated,necessitating elevated standards for the pedagogy of perioperative nursin...Concomitant with the advancement of contemporary medical technology,the significance of perioperative nursing has been increasingly accentuated,necessitating elevated standards for the pedagogy of perioperative nursing.Presently,the PBL(problem-based learning)pedagogical approach,when integrated with CBL(case-based learning),has garnered considerable interest.An extensive literature review has been conducted to analyze the application of the PBL-CBL fusion in the education of perioperative nursing.Findings indicate that this integrative teaching methodology not only enhances students’theoretical knowledge,practical competencies,and collaborative skills but also contributes to the elevation of teaching quality.In conclusion,the PBL-CBL teaching approach holds immense potential for broader application in perioperative nursing education.Nevertheless,it is imperative to continually refine this combined pedagogical strategy to further enhance the caliber of perioperative nursing instruction and to cultivate a greater number of exceptional nursing professionals in the operating room setting.展开更多
Leveraging big data analytics and advanced algorithms to accelerate and optimize the process of molecular and materials design, synthesis, and application has revolutionized the field of molecular and materials scienc...Leveraging big data analytics and advanced algorithms to accelerate and optimize the process of molecular and materials design, synthesis, and application has revolutionized the field of molecular and materials science, allowing researchers to gain a deeper understanding of material properties and behaviors,leading to the development of new materials that are more efficient and reliable. However, the difficulty in constructing large-scale datasets of new molecules/materials due to the high cost of data acquisition and annotation limits the development of conventional machine learning(ML) approaches. Knowledgereused transfer learning(TL) methods are expected to break this dilemma. The application of TL lowers the data requirements for model training, which makes TL stand out in researches addressing data quality issues. In this review, we summarize recent progress in TL related to molecular and materials. We focus on the application of TL methods for the discovery of advanced molecules/materials, particularly, the construction of TL frameworks for different systems, and how TL can enhance the performance of models. In addition, the challenges of TL are also discussed.展开更多
In the face of intelligent manufacturing(or smart manufacturing)human resource shortage,the training of industrial engineers in the field of intelligent manufacturing is of great significance.In academia,the positive ...In the face of intelligent manufacturing(or smart manufacturing)human resource shortage,the training of industrial engineers in the field of intelligent manufacturing is of great significance.In academia,the positive link between learning transfer and knowledge innovation is recognized by most scholars,while the learner’s attitude toward big data decision-making,as a cognitive perception,affects learning transfer from the learner’s experienced engineering paradigm to the intelligent manufacturing paradigm.Thus,learning transfer can be regarded as a result of the learner’s attitude,and it becomes the intermediary state between their attitude and knowledge innovation.This paper reviews prior research on knowledge transfer and develops hypotheses on the relationships between learner acceptance attitude,knowledge transfer,and knowledge innovation.展开更多
In the international shipping industry, digital intelligence transformation has become essential, with both governments and enterprises actively working to integrate diverse datasets. The domain of maritime and shippi...In the international shipping industry, digital intelligence transformation has become essential, with both governments and enterprises actively working to integrate diverse datasets. The domain of maritime and shipping is characterized by a vast array of document types, filled with complex, large-scale, and often chaotic knowledge and relationships. Effectively managing these documents is crucial for developing a Large Language Model (LLM) in the maritime domain, enabling practitioners to access and leverage valuable information. A Knowledge Graph (KG) offers a state-of-the-art solution for enhancing knowledge retrieval, providing more accurate responses and enabling context-aware reasoning. This paper presents a framework for utilizing maritime and shipping documents to construct a knowledge graph using GraphRAG, a hybrid tool combining graph-based retrieval and generation capabilities. The extraction of entities and relationships from these documents and the KG construction process are detailed. Furthermore, the KG is integrated with an LLM to develop a Q&A system, demonstrating that the system significantly improves answer accuracy compared to traditional LLMs. Additionally, the KG construction process is up to 50% faster than conventional LLM-based approaches, underscoring the efficiency of our method. This study provides a promising approach to digital intelligence in shipping, advancing knowledge accessibility and decision-making.展开更多
Artificial intelligence has potential for forecasting reactor conditions in the nuclear industry.Owing to economic and security concerns,a common method is to train data generated by simulators.However,achieving a sat...Artificial intelligence has potential for forecasting reactor conditions in the nuclear industry.Owing to economic and security concerns,a common method is to train data generated by simulators.However,achieving a satisfactory performance in practical applications is difficult because simulators imperfectly emulate reality.To bridge this gap,we propose a novel framework called simulation-to-reality domain adaptation(SRDA)for forecasting the operating parameters of nuclear reactors.The SRDA model employs a transformer-based feature extractor to capture dynamic characteristics and temporal dependencies.A parameter predictor with an improved logarithmic loss function is specifically designed to adapt to varying reactor powers.To fuse prior reactor knowledge from simulations with reality,the domain discriminator utilizes an adversarial strategy to ensure the learning of deep domain-invariant features,and the multiple kernel maximum mean discrepancy minimizes their discrepancies.Experiments on neutron fluxes and temperatures from a pressurized water reactor illustrate that the SRDA model surpasses various advanced methods in terms of predictive performance.This study is the first to use domain adaptation for real-world reactor prediction and presents a feasible solution for enhancing the transferability and generalizability of simulated data.展开更多
BACKGROUND Breast cancer is one of the most prevalent causes of morbidity and mortality worldwide,presenting an increasing public health challenge,particularly in lowincome and middle-income countries.However,data on ...BACKGROUND Breast cancer is one of the most prevalent causes of morbidity and mortality worldwide,presenting an increasing public health challenge,particularly in lowincome and middle-income countries.However,data on the knowledge,attitudes,and preventive practices regarding breast cancer and the associated factors among females in Wollo,Ethiopia,remain limited.AIM To assess the impact of family history(FH)of breast disease on knowledge,attitudes,and breast cancer preventive practices among reproductive-age females.METHODS A community-based cross-sectional study was conducted in May and June 2022 in Northeast Ethiopia and involved 143 reproductive-age females with FH of breast diseases and 209 without such a history.We selected participants using the systematic random sampling technique.We analyzed the data using Statistical Package for Social Science version 25 software,and logistic regression analysis was employed to determine odds ratios for variable associations,with statistical significance set at P<0.05.RESULTS Among participants with FH of breast diseases,the levels of knowledge,attitudes,and preventive practices were found to be 83.9%[95%confidence interval(CI):77.9-89.9],49.0%(95%CI:40.8-57.1),and 74.1%(95%CI:66.9-81.3),respectively.In contrast,among those without FH of breast diseases,these levels were significantly decreased to 10.5%(95%CI:6.4-14.7),32.1%(95%CI:25.7-38.4),and 16.7%(95%CI:11.7-21.8),respectively.This study also indicated that knowledge,attitudes,and preventive practices related to breast cancer are significantly higher among participants with FH of breast diseases compared to those without HF breast diseases.CONCLUSION Educational status,monthly income,and community health insurance were identified as significant factors associated with the levels of knowledge,attitudes,and preventive practices regarding breast cancer among reproductive-age females.展开更多
Traditional Chinese medicine(TCM)serves as a treasure trove of ancient knowledge,holding a crucial position in the medical field.However,the exploration of TCM's extensive information has been hindered by challeng...Traditional Chinese medicine(TCM)serves as a treasure trove of ancient knowledge,holding a crucial position in the medical field.However,the exploration of TCM's extensive information has been hindered by challenges related to data standardization,completeness,and accuracy,primarily due to the decen-tralized distribution of TCM resources.To address these issues,we developed a platform for TCM knowledge discovery(TCMKD,https://cbcb.cdutcm.edu.cn/TCMKD/).Seven types of data,including syndromes,formulas,Chinese patent drugs(CPDs),Chinese medicinal materials(CMMs),ingredients,targets,and diseases,were manually proofread and consolidated within TCMKD.To strengthen the integration of TCM with modern medicine,TCMKD employs analytical methods such as TCM data mining,enrichment analysis,and network localization and separation.These tools help elucidate the molecular-level commonalities between TCM and contemporary scientific insights.In addition to its analytical capabilities,a quick question and answer(Q&A)system is also embedded within TCMKD to query the database efficiently,thereby improving the interactivity of the platform.The platform also provides a TCM text annotation tool,offering a simple and efficient method for TCM text mining.Overall,TCMKD not only has the potential to become a pivotal repository for TCM,delving into the pharmaco-logical foundations of TCM treatments,but its flexible embedded tools and algorithms can also be applied to the study of other traditional medical systems,extending beyond just TCM.展开更多
Topographic maps,as essential tools and sources of information for geographic research,contain precise spatial locations and rich map features,and they illustrate spatio-temporal information on the distribution and di...Topographic maps,as essential tools and sources of information for geographic research,contain precise spatial locations and rich map features,and they illustrate spatio-temporal information on the distribution and differences of various surface features.Currently,topographic maps are mainly stored in raster and vector formats.Extraction of the spatio-temporal knowledge in the maps—such as spatial distribution patterns,feature relationships,and dynamic evolution—still primarily relies on manual interpretation.However,manual interpretation is time-consuming and laborious,especially for large-scale,long-term map knowledge extraction and application.With the development of artificial intelligence technology,it is possible to improve the automation level of map knowledge interpretation.Therefore,the present study proposes an automatic interpretation method for raster topographic map knowledge based on deep learning.To address the limitations of current data-driven intelligent technology in learning map spatial relations and cognitive logic,we establish a formal description of map knowledge by mapping the relationship between map knowledge and features,thereby ensuring interpretation accuracy.Subsequently,deep learning techniques are employed to extract map features automatically,and the spatio-temporal knowledge is constructed by combining formal descriptions of geographic feature knowledge.Validation experiments demonstrate that the proposed method effectively achieves automatic interpretation of spatio-temporal knowledge of geographic features in maps,with an accuracy exceeding 80%.The findings of the present study contribute to machine understanding of spatio-temporal differences in map knowledge and advances the intelligent interpretation and utilization of cartographic information.展开更多
In the field of intelligent education,the integration of artificial intelligence,especially deep learning technologies,has garnered significant attention.Knowledge tracing(KT)plays a pivotal role in this field by pred...In the field of intelligent education,the integration of artificial intelligence,especially deep learning technologies,has garnered significant attention.Knowledge tracing(KT)plays a pivotal role in this field by predicting students’future performance through the analysis of historical interaction data,thereby assisting educators in evaluating knowledgemastery and tailoring instructional strategies.Traditional knowledge tracingmethods,largely based on Recurrent Neural Networks(RNNs)and Transformer models,primarily focus on capturing long-term interaction patterns in sequential data.However,these models may neglect crucial short-term dynamics and other relevant features.This paper introduces a novel approach to knowledge tracing by leveraging a pure Multilayer Perceptron(MLP)architecture.We proposeMixerKT,a knowledge tracing model based on theHyperMixer framework,which uniquely integrates global and localMixer feature extractors.This architecture enables more effective extraction of both long-terminteraction trends and recent learning behaviors,addressing limitations in currentmodels thatmay overlook these key aspects.Empirical evaluations on twowidely-used datasets,ASSIS Tments2009 and Algebra2005,demonstrate that MixerKT consistently outperforms several state-of-the-art models,including DKT,SAKT,and Separated Self-Attentive Neural Knowledge Tracing(SAINT).Specifically,MixerKT achieves higher prediction accuracy,highlighting its effectiveness in capturing the nuances of learners’knowledge states.These results indicate that our model provides a more comprehensive representation of student learning patterns,enhancing the ability to predict future performance with greater precision.展开更多
Mitochondria play a crucial role as organelles,managing several physiological processes such as redox balance,cell metabolism,and energy synthesis.Initially,the assumption was that mitochondria primarily resided in th...Mitochondria play a crucial role as organelles,managing several physiological processes such as redox balance,cell metabolism,and energy synthesis.Initially,the assumption was that mitochondria primarily resided in the host cells and could exclusively transmit from oocytes to offspring by a mechanism known as vertical inheritance of mitochondria.Recent scholarly works,however,suggest that certain cell types transmit their mitochondria to other developmental cell types via a mechanism referred to as intercellular or horizontal mitochondrial transfer.This review details the process of which mitochondria are transferred across cells and explains the impact of mitochondrial transfer between cells on the efficacy and functionality of cancer cells in various cancer forms.Specifically,we review the role of mitochondria transfer in regulating cellular metabolism restoration,excess reactive oxygen species(ROS)generation,proliferation,invasion,metastasis,mitophagy activation,mitochondrial DNA(mtDNA)inheritance,immune system modulation and therapeutic resistance in cancer.Additionally,we highlight the possibility of using intercellular mitochondria transfer as a therapeutic approach to treat cancer and enhance the efficacy of cancer treatments.展开更多
Accurate prediction of drug-target interactions(DTIs)plays a pivotal role in drug discovery,facilitating optimization of lead compounds,drug repurposing and elucidation of drug side effects.However,traditional DTI pre...Accurate prediction of drug-target interactions(DTIs)plays a pivotal role in drug discovery,facilitating optimization of lead compounds,drug repurposing and elucidation of drug side effects.However,traditional DTI prediction methods are often limited by incomplete biological data and insufficient representation of protein features.In this study,we proposed KG-CNNDTI,a novel knowledge graph-enhanced framework for DTI prediction,which integrates heterogeneous biological information to improve model generalizability and predictive performance.The proposed model utilized protein embeddings derived from a biomedical knowledge graph via the Node2Vec algorithm,which were further enriched with contextualized sequence representations obtained from ProteinBERT.For compound representation,multiple molecular fingerprint schemes alongside the Uni-Mol pre-trained model were evaluated.The fused representations served as inputs to both classical machine learning models and a convolutional neural network-based predictor.Experimental evaluations across benchmark datasets demonstrated that KG-CNNDTI achieved superior performance compared to state-of-the-art methods,particularly in terms of Precision,Recall,F1-Score and area under the precision-recall curve(AUPR).Ablation analysis highlighted the substantial contribution of knowledge graph-derived features.Moreover,KG-CNNDTI was employed for virtual screening of natural products against Alzheimer's disease,resulting in 40 candidate compounds.5 were supported by literature evidence,among which 3 were further validated in vitro assays.展开更多
In scenarios such as vehicle radiation monitoring and unmanned aerial vehicle radiation detection,rapid measurements using a NaI(Tl)detector often result in low photon counts,weak characteristic peaks,and significant ...In scenarios such as vehicle radiation monitoring and unmanned aerial vehicle radiation detection,rapid measurements using a NaI(Tl)detector often result in low photon counts,weak characteristic peaks,and significant statistical fluctuations.These issues can lead to potential failures in peak-searching-based identification methods.To address the low precision associated with short-duration measurements of radionuclides,this paper proposes an identification algorithm that leverages heterogeneous spectral transfer to develop a low-count energy spectral identification model.Comparative experiments demonstrated that transferring samples from 26 classes of simulated heterogeneous gamma spectra aids in creating a reliable model for measured gamma spectra.With only 10%of target domain samples used for training,the accuracy on real low-count spectral samples was 95.56%.This performance shows a significant improvement over widely employed full-spectrum analysis methods trained on target domain samples.The proposed method also exhibits strong generalization capabilities,effectively mitigating overfitting issues in low-count energy spectral classification under short-duration measurements.展开更多
Organic nanophotocatalysts are promising candidates for solar fuels production,but they still face the challenge of unfavorable geminate recombination due to the limited exciton diffusion lengths.Here,we introduce a b...Organic nanophotocatalysts are promising candidates for solar fuels production,but they still face the challenge of unfavorable geminate recombination due to the limited exciton diffusion lengths.Here,we introduce a binary nanophotocatalyst fabricated by blending two polymers,PS-PEG5(PS)and PBT-PEG5(PBT),with matched absorption and emission spectra,enabling a Forster resonance energy transfer(FRET)process for enhanced photocatalysis.These heterostructure nanophotocatalysts are processed using a facile and scalable flash nanoprecipitation(FNP)technique with precious kinetic control over binary nanoparticle formation.The resulting nanoparticles exhibit an exceptional photocatalytic hydrogen evolution rate up to 65 mmol g^(-1) h^(-1),2.5 times higher than that single component nanoparticles.Characterizations through fluorescence spectra and transient absorption spectra confirm the hetero-energy transfer within the binary nanoparticles,which prolongs the excited-state lifetime and extends the namely“effective exciton diffusion length”.Our finding opens new avenues for designing efficient organic photocatalysts by improving exciton migration.展开更多
Catalytic oxidation of organic pollutants is a well-known and effective technique for pollutant abatement.Unfortunately,this method is significantly hindered in practical applications by the lowefficiency and difficul...Catalytic oxidation of organic pollutants is a well-known and effective technique for pollutant abatement.Unfortunately,this method is significantly hindered in practical applications by the lowefficiency and difficult recovery of the catalysts in a powdery form.Herein,a three-dimensional(3D)framework of Fe-incorporated Ni_(3)S_(2)nanosheets in-situ grown on Ni foam(Fe-Ni_(3)S_(2)@NF)was fabricated by a facile two-step hydrothermal process and applied to trigger peroxymonosulfate(PMS)oxidation of organic compounds inwater.A homogeneous growth environment enabled the uniform and scalable growth of Fe-Ni_(3)S_(2)nanosheets on the Ni foam.Fe-Ni_(3)S_(2)@NF possessed outstanding activity and durability in activating PMS,as it effectively facilitated electron transfer from organic pollutants to PMS.Fe-Ni_(3)S_(2)@NF initially supplied electrons to PMS,causing the catalyst to undergo oxidation,and subsequently accepted electrons from organic compounds,returning to its initial state.The introduction of Fe into the Ni_(3)S_(2)lattice enhanced electrical conductivity,promoting mediated electron transfer between PMS and organic compounds.The 3D conductive Ni foam provided an ideal platform for the nucleation and growth of Fe-Ni_(3)S_(2),accelerating pollutant abatement due to its porous structure and high conductivity.Furthermore,its monolithic nature simplified the catalyst recycling process.A continuous flow packed-bed reactor by encapsulating Fe-Ni_(3)S_(2)@NF catalyst achieved complete pollutant abatement with continuous operation for 240 h,highlighting its immense potential for practical environmental remediation.This study presents a facile synthesis method for creating a novel type of monolithic catalyst with high activity and durability for decontamination through Fenton-like processes.展开更多
Deep-time Earth research plays a pivotal role in deciphering the rates,patterns,and mechanisms of Earth's evolutionary processes throughout geological history,providing essential scientific foundations for climate...Deep-time Earth research plays a pivotal role in deciphering the rates,patterns,and mechanisms of Earth's evolutionary processes throughout geological history,providing essential scientific foundations for climate prediction,natural resource exploration,and sustainable planetary stewardship.To advance Deep-time Earth research in the era of big data and artificial intelligence,the International Union of Geological Sciences initiated the“Deeptime Digital Earth International Big Science Program”(DDE)in 2019.At the core of this ambitious program lies the development of geoscience knowledge graphs,serving as a transformative knowledge infrastructure that enables the integration,sharing,mining,and analysis of heterogeneous geoscience big data.The DDE knowledge graph initiative has made significant strides in three critical dimensions:(1)establishing a unified knowledge structure across geoscience disciplines that ensures consistent representation of geological entities and their interrelationships through standardized ontologies and semantic frameworks;(2)developing a robust and scalable software infrastructure capable of supporting both expert-driven and machine-assisted knowledge engineering for large-scale graph construction and management;(3)implementing a comprehensive three-tiered architecture encompassing basic,discipline-specific,and application-oriented knowledge graphs,spanning approximately 20 geoscience disciplines.Through its open knowledge framework and international collaborative network,this initiative has fostered multinational research collaborations,establishing a robust foundation for next-generation geoscience research while propelling the discipline toward FAIR(Findable,Accessible,Interoperable,Reusable)data practices in deep-time Earth systems research.展开更多
Layered double hydroxide(LDH)based heterogonous peroxymonosulfate(PMS)activation degradation of pollutants has attracted extensive attention.The challenge is to selectively regulate the traditional free radical domina...Layered double hydroxide(LDH)based heterogonous peroxymonosulfate(PMS)activation degradation of pollutants has attracted extensive attention.The challenge is to selectively regulate the traditional free radical dominant degradation pathway into a nonradical degradation pathway.Herein,an interface ar-chitecture of Ti_(3) C_(2) T_(x)-MXene(MXene)loading on the Fe-Al LDH scaffold was developed,which showed excellent stability and robust resistance against harsh conditions.Significantly,the rate constant for tetra-cycline hydrochloride(TC)degradation in the MXene-LDH/PMS process was 0.421 min^(-1),which was ten times faster than the rate constant for pure Fe-Al LDH(0.042 min^(-1)).Specifically,more reactive Fe with the closer d-band center to the Fermi level results in higher electron transfer efficiency.The occupa-tions of Fe-3d orbitals in Mxene/Fe-Al LDH are pushed above the Fermi level to generate,which results in higher PMS adsorption and inhibition of the release of oxygen-containing active species intermedi-ates,leading to the enhanced^(1)O_(2) generation.Additionally,the built-in electric field in the heterojunc-tion was driven by the charge redistribution between MXene and Fe-Al LDH,resulting in a mediated-electron transfer mechanism,differentiating it from the Fe-Al LDH/PMS system.It was fascinating that MXene/Fe-Al LDH achieved satisfactory treatment efficiency in continuous column reactor and real landfill leachate.展开更多
The current deep learning models for braced excavation cannot predict deformation from the beginning of excavation due to the need for a substantial corpus of sufficient historical data for training purposes.To addres...The current deep learning models for braced excavation cannot predict deformation from the beginning of excavation due to the need for a substantial corpus of sufficient historical data for training purposes.To address this issue,this study proposes a transfer learning model based on a sequence-to-sequence twodimensional(2D)convolutional long short-term memory neural network(S2SCL2D).The model can use the existing data from other adjacent similar excavations to achieve wall deflection prediction once a limited amount of monitoring data from the target excavation has been recorded.In the absence of adjacent excavation data,numerical simulation data from the target project can be employed instead.A weight update strategy is proposed to improve the prediction accuracy by integrating the stochastic gradient masking with an early stopping mechanism.To illustrate the proposed methodology,an excavation project in Hangzhou,China is adopted.The proposed deep transfer learning model,which uses either adjacent excavation data or numerical simulation data as the source domain,shows a significant improvement in performance when compared to the non-transfer learning model.Using the simulation data from the target project even leads to better prediction performance than using the actual monitoring data from other adjacent excavations.The results demonstrate that the proposed model can reasonably predict the deformation with limited data from the target project.展开更多
基金supported in part by the National Natural Science Foundation of China(Grant Nos.62272020 and U20B2069)in part by the State Key Laboratory of Complex&Critical Software Environment(SKLSDE2023ZX-16)in part by the Fundamental Research Funds for Central Universities.
文摘This paper focuses on an important type of black-box attacks,i.e.,transfer-based adversarial attacks,where the adversary generates adversarial examples using a substitute(source)model and utilizes them to attack an unseen target model,without knowing its information.Existing methods tend to give unsatisfactory adversarial transferability when the source and target models are from different types of DNN architectures(e.g.,ResNet-18 and Swin Transformer).In this paper,we observe that the above phenomenon is induced by the output inconsistency problem.To alleviate this problem while effectively utilizing the existing DNN models,we propose a common knowledge learning(CKL)framework to learn better network weights to generate adversarial examples with better transferability,under fixed network architectures.Specifically,to reduce the model-specific features and obtain better output distributions,we construct a multi-teacher framework,where the knowledge is distilled from different teacher architectures into one student network.By considering that the gradient of input is usually utilized to generate adversarial examples,we impose constraints on the gradients between the student and teacher models,to further alleviate the output inconsistency problem and enhance the adversarial transferability.Extensive experiments demonstrate that our proposed work can significantly improve the adversarial transferability.
基金supported by the National Natural Science Foundation of China (62176061)。
文摘Knowledge distillation(KD) enhances student network generalization by transferring dark knowledge from a complex teacher network. To optimize computational expenditure and memory utilization, self-knowledge distillation(SKD) extracts dark knowledge from the model itself rather than an external teacher network. However, previous SKD methods performed distillation indiscriminately on full datasets, overlooking the analysis of representative samples. In this work, we present a novel two-stage approach to providing targeted knowledge on specific samples, named two-stage approach self-knowledge distillation(TOAST). We first soften the hard targets using class medoids generated based on logit vectors per class. Then, we iteratively distill the under-trained data with past predictions of half the batch size. The two-stage knowledge is linearly combined, efficiently enhancing model performance. Extensive experiments conducted on five backbone architectures show our method is model-agnostic and achieves the best generalization performance.Besides, TOAST is strongly compatible with existing augmentation-based regularization methods. Our method also obtains a speedup of up to 2.95x compared with a recent state-of-the-art method.
基金supported by Key Laboratory of Information System Requirement,No.LHZZ202202Natural Science Foundation of Xinjiang Uyghur Autonomous Region(2023D01C55)Scientific Research Program of the Higher Education Institution of Xinjiang(XJEDU2023P127).
文摘In recent years,with the continuous development of deep learning and knowledge graph reasoning methods,more and more researchers have shown great interest in improving knowledge graph reasoning methods by inferring missing facts through reasoning.By searching paths on the knowledge graph and making fact and link predictions based on these paths,deep learning-based Reinforcement Learning(RL)agents can demonstrate good performance and interpretability.Therefore,deep reinforcement learning-based knowledge reasoning methods have rapidly emerged in recent years and have become a hot research topic.However,even in a small and fixed knowledge graph reasoning action space,there are still a large number of invalid actions.It often leads to the interruption of RL agents’wandering due to the selection of invalid actions,resulting in a significant decrease in the success rate of path mining.In order to improve the success rate of RL agents in the early stages of path search,this article proposes a knowledge reasoning method based on Deep Transfer Reinforcement Learning path(DTRLpath).Before supervised pre-training and retraining,a pre-task of searching for effective actions in a single step is added.The RL agent is first trained in the pre-task to improve its ability to search for effective actions.Then,the trained agent is transferred to the target reasoning task for path search training,which improves its success rate in searching for target task paths.Finally,based on the comparative experimental results on the FB15K-237 and NELL-995 datasets,it can be concluded that the proposed method significantly improves the success rate of path search and outperforms similar methods in most reasoning tasks.
文摘Concomitant with the advancement of contemporary medical technology,the significance of perioperative nursing has been increasingly accentuated,necessitating elevated standards for the pedagogy of perioperative nursing.Presently,the PBL(problem-based learning)pedagogical approach,when integrated with CBL(case-based learning),has garnered considerable interest.An extensive literature review has been conducted to analyze the application of the PBL-CBL fusion in the education of perioperative nursing.Findings indicate that this integrative teaching methodology not only enhances students’theoretical knowledge,practical competencies,and collaborative skills but also contributes to the elevation of teaching quality.In conclusion,the PBL-CBL teaching approach holds immense potential for broader application in perioperative nursing education.Nevertheless,it is imperative to continually refine this combined pedagogical strategy to further enhance the caliber of perioperative nursing instruction and to cultivate a greater number of exceptional nursing professionals in the operating room setting.
基金National Key R&D Program of China (No. 2021YFC2100100)Shanghai Science and Technology Project (No. 21JC1403400, 23JC1402300)。
文摘Leveraging big data analytics and advanced algorithms to accelerate and optimize the process of molecular and materials design, synthesis, and application has revolutionized the field of molecular and materials science, allowing researchers to gain a deeper understanding of material properties and behaviors,leading to the development of new materials that are more efficient and reliable. However, the difficulty in constructing large-scale datasets of new molecules/materials due to the high cost of data acquisition and annotation limits the development of conventional machine learning(ML) approaches. Knowledgereused transfer learning(TL) methods are expected to break this dilemma. The application of TL lowers the data requirements for model training, which makes TL stand out in researches addressing data quality issues. In this review, we summarize recent progress in TL related to molecular and materials. We focus on the application of TL methods for the discovery of advanced molecules/materials, particularly, the construction of TL frameworks for different systems, and how TL can enhance the performance of models. In addition, the challenges of TL are also discussed.
基金Natural Science Foundation of Inner Mongolia(Project No.2023LHMS07016)the Fundamental Research Fund for the directly affiliated university of Inner Mongolia(Project No.2022 JBQN056)。
文摘In the face of intelligent manufacturing(or smart manufacturing)human resource shortage,the training of industrial engineers in the field of intelligent manufacturing is of great significance.In academia,the positive link between learning transfer and knowledge innovation is recognized by most scholars,while the learner’s attitude toward big data decision-making,as a cognitive perception,affects learning transfer from the learner’s experienced engineering paradigm to the intelligent manufacturing paradigm.Thus,learning transfer can be regarded as a result of the learner’s attitude,and it becomes the intermediary state between their attitude and knowledge innovation.This paper reviews prior research on knowledge transfer and develops hypotheses on the relationships between learner acceptance attitude,knowledge transfer,and knowledge innovation.
文摘In the international shipping industry, digital intelligence transformation has become essential, with both governments and enterprises actively working to integrate diverse datasets. The domain of maritime and shipping is characterized by a vast array of document types, filled with complex, large-scale, and often chaotic knowledge and relationships. Effectively managing these documents is crucial for developing a Large Language Model (LLM) in the maritime domain, enabling practitioners to access and leverage valuable information. A Knowledge Graph (KG) offers a state-of-the-art solution for enhancing knowledge retrieval, providing more accurate responses and enabling context-aware reasoning. This paper presents a framework for utilizing maritime and shipping documents to construct a knowledge graph using GraphRAG, a hybrid tool combining graph-based retrieval and generation capabilities. The extraction of entities and relationships from these documents and the KG construction process are detailed. Furthermore, the KG is integrated with an LLM to develop a Q&A system, demonstrating that the system significantly improves answer accuracy compared to traditional LLMs. Additionally, the KG construction process is up to 50% faster than conventional LLM-based approaches, underscoring the efficiency of our method. This study provides a promising approach to digital intelligence in shipping, advancing knowledge accessibility and decision-making.
基金supported by the Industry-University Cooperation Project in Fujian Province University(No.2023H6006)the State Key Laboratory of Reliability and Intelligence of Electrical Equipment(No.EERI-KF20200005)。
文摘Artificial intelligence has potential for forecasting reactor conditions in the nuclear industry.Owing to economic and security concerns,a common method is to train data generated by simulators.However,achieving a satisfactory performance in practical applications is difficult because simulators imperfectly emulate reality.To bridge this gap,we propose a novel framework called simulation-to-reality domain adaptation(SRDA)for forecasting the operating parameters of nuclear reactors.The SRDA model employs a transformer-based feature extractor to capture dynamic characteristics and temporal dependencies.A parameter predictor with an improved logarithmic loss function is specifically designed to adapt to varying reactor powers.To fuse prior reactor knowledge from simulations with reality,the domain discriminator utilizes an adversarial strategy to ensure the learning of deep domain-invariant features,and the multiple kernel maximum mean discrepancy minimizes their discrepancies.Experiments on neutron fluxes and temperatures from a pressurized water reactor illustrate that the SRDA model surpasses various advanced methods in terms of predictive performance.This study is the first to use domain adaptation for real-world reactor prediction and presents a feasible solution for enhancing the transferability and generalizability of simulated data.
文摘BACKGROUND Breast cancer is one of the most prevalent causes of morbidity and mortality worldwide,presenting an increasing public health challenge,particularly in lowincome and middle-income countries.However,data on the knowledge,attitudes,and preventive practices regarding breast cancer and the associated factors among females in Wollo,Ethiopia,remain limited.AIM To assess the impact of family history(FH)of breast disease on knowledge,attitudes,and breast cancer preventive practices among reproductive-age females.METHODS A community-based cross-sectional study was conducted in May and June 2022 in Northeast Ethiopia and involved 143 reproductive-age females with FH of breast diseases and 209 without such a history.We selected participants using the systematic random sampling technique.We analyzed the data using Statistical Package for Social Science version 25 software,and logistic regression analysis was employed to determine odds ratios for variable associations,with statistical significance set at P<0.05.RESULTS Among participants with FH of breast diseases,the levels of knowledge,attitudes,and preventive practices were found to be 83.9%[95%confidence interval(CI):77.9-89.9],49.0%(95%CI:40.8-57.1),and 74.1%(95%CI:66.9-81.3),respectively.In contrast,among those without FH of breast diseases,these levels were significantly decreased to 10.5%(95%CI:6.4-14.7),32.1%(95%CI:25.7-38.4),and 16.7%(95%CI:11.7-21.8),respectively.This study also indicated that knowledge,attitudes,and preventive practices related to breast cancer are significantly higher among participants with FH of breast diseases compared to those without HF breast diseases.CONCLUSION Educational status,monthly income,and community health insurance were identified as significant factors associated with the levels of knowledge,attitudes,and preventive practices regarding breast cancer among reproductive-age females.
基金supported by Natural Science Foundation of Sichuan,China(Grant No.:2024ZDZX0019).
文摘Traditional Chinese medicine(TCM)serves as a treasure trove of ancient knowledge,holding a crucial position in the medical field.However,the exploration of TCM's extensive information has been hindered by challenges related to data standardization,completeness,and accuracy,primarily due to the decen-tralized distribution of TCM resources.To address these issues,we developed a platform for TCM knowledge discovery(TCMKD,https://cbcb.cdutcm.edu.cn/TCMKD/).Seven types of data,including syndromes,formulas,Chinese patent drugs(CPDs),Chinese medicinal materials(CMMs),ingredients,targets,and diseases,were manually proofread and consolidated within TCMKD.To strengthen the integration of TCM with modern medicine,TCMKD employs analytical methods such as TCM data mining,enrichment analysis,and network localization and separation.These tools help elucidate the molecular-level commonalities between TCM and contemporary scientific insights.In addition to its analytical capabilities,a quick question and answer(Q&A)system is also embedded within TCMKD to query the database efficiently,thereby improving the interactivity of the platform.The platform also provides a TCM text annotation tool,offering a simple and efficient method for TCM text mining.Overall,TCMKD not only has the potential to become a pivotal repository for TCM,delving into the pharmaco-logical foundations of TCM treatments,but its flexible embedded tools and algorithms can also be applied to the study of other traditional medical systems,extending beyond just TCM.
基金Deep-time Digital Earth(DDE)Big Science Program(No.GJ-C03-SGF-2025-004)National Natural Science Foundation of China(No.42394063)Sichuan Science and Technology Program(No.2025ZNSFSC0325).
文摘Topographic maps,as essential tools and sources of information for geographic research,contain precise spatial locations and rich map features,and they illustrate spatio-temporal information on the distribution and differences of various surface features.Currently,topographic maps are mainly stored in raster and vector formats.Extraction of the spatio-temporal knowledge in the maps—such as spatial distribution patterns,feature relationships,and dynamic evolution—still primarily relies on manual interpretation.However,manual interpretation is time-consuming and laborious,especially for large-scale,long-term map knowledge extraction and application.With the development of artificial intelligence technology,it is possible to improve the automation level of map knowledge interpretation.Therefore,the present study proposes an automatic interpretation method for raster topographic map knowledge based on deep learning.To address the limitations of current data-driven intelligent technology in learning map spatial relations and cognitive logic,we establish a formal description of map knowledge by mapping the relationship between map knowledge and features,thereby ensuring interpretation accuracy.Subsequently,deep learning techniques are employed to extract map features automatically,and the spatio-temporal knowledge is constructed by combining formal descriptions of geographic feature knowledge.Validation experiments demonstrate that the proposed method effectively achieves automatic interpretation of spatio-temporal knowledge of geographic features in maps,with an accuracy exceeding 80%.The findings of the present study contribute to machine understanding of spatio-temporal differences in map knowledge and advances the intelligent interpretation and utilization of cartographic information.
基金supported by National Natural Science Foundation of China(Nos.62266054 and 62166050)Key Program of Fundamental Research Project of Yunnan Science and Technology Plan(No.202201AS070021)+2 种基金Yunnan Fundamental Research Projects(No.202401AT070122)Yunnan International Joint Research and Development Center of China-Laos-Thailand Educational Digitalization(No.202203AP140006)Scientific Research Foundation of Yunnan Provincial Department of Education(No.2024Y159).
文摘In the field of intelligent education,the integration of artificial intelligence,especially deep learning technologies,has garnered significant attention.Knowledge tracing(KT)plays a pivotal role in this field by predicting students’future performance through the analysis of historical interaction data,thereby assisting educators in evaluating knowledgemastery and tailoring instructional strategies.Traditional knowledge tracingmethods,largely based on Recurrent Neural Networks(RNNs)and Transformer models,primarily focus on capturing long-term interaction patterns in sequential data.However,these models may neglect crucial short-term dynamics and other relevant features.This paper introduces a novel approach to knowledge tracing by leveraging a pure Multilayer Perceptron(MLP)architecture.We proposeMixerKT,a knowledge tracing model based on theHyperMixer framework,which uniquely integrates global and localMixer feature extractors.This architecture enables more effective extraction of both long-terminteraction trends and recent learning behaviors,addressing limitations in currentmodels thatmay overlook these key aspects.Empirical evaluations on twowidely-used datasets,ASSIS Tments2009 and Algebra2005,demonstrate that MixerKT consistently outperforms several state-of-the-art models,including DKT,SAKT,and Separated Self-Attentive Neural Knowledge Tracing(SAINT).Specifically,MixerKT achieves higher prediction accuracy,highlighting its effectiveness in capturing the nuances of learners’knowledge states.These results indicate that our model provides a more comprehensive representation of student learning patterns,enhancing the ability to predict future performance with greater precision.
基金supported by the National Natural Science Foundation of China(Grant No.:82272749)the Natural Science Foundation of Liaoning Province,China(Grant No.:2022-MS-190).
文摘Mitochondria play a crucial role as organelles,managing several physiological processes such as redox balance,cell metabolism,and energy synthesis.Initially,the assumption was that mitochondria primarily resided in the host cells and could exclusively transmit from oocytes to offspring by a mechanism known as vertical inheritance of mitochondria.Recent scholarly works,however,suggest that certain cell types transmit their mitochondria to other developmental cell types via a mechanism referred to as intercellular or horizontal mitochondrial transfer.This review details the process of which mitochondria are transferred across cells and explains the impact of mitochondrial transfer between cells on the efficacy and functionality of cancer cells in various cancer forms.Specifically,we review the role of mitochondria transfer in regulating cellular metabolism restoration,excess reactive oxygen species(ROS)generation,proliferation,invasion,metastasis,mitophagy activation,mitochondrial DNA(mtDNA)inheritance,immune system modulation and therapeutic resistance in cancer.Additionally,we highlight the possibility of using intercellular mitochondria transfer as a therapeutic approach to treat cancer and enhance the efficacy of cancer treatments.
基金supported by the National Natural Science Foundation of China(Nos.82173746 and U23A20530)Shanghai Frontiers Science Center of Optogenetic Techniques for Cell Metabolism(Shanghai Municipal Education Commission)。
文摘Accurate prediction of drug-target interactions(DTIs)plays a pivotal role in drug discovery,facilitating optimization of lead compounds,drug repurposing and elucidation of drug side effects.However,traditional DTI prediction methods are often limited by incomplete biological data and insufficient representation of protein features.In this study,we proposed KG-CNNDTI,a novel knowledge graph-enhanced framework for DTI prediction,which integrates heterogeneous biological information to improve model generalizability and predictive performance.The proposed model utilized protein embeddings derived from a biomedical knowledge graph via the Node2Vec algorithm,which were further enriched with contextualized sequence representations obtained from ProteinBERT.For compound representation,multiple molecular fingerprint schemes alongside the Uni-Mol pre-trained model were evaluated.The fused representations served as inputs to both classical machine learning models and a convolutional neural network-based predictor.Experimental evaluations across benchmark datasets demonstrated that KG-CNNDTI achieved superior performance compared to state-of-the-art methods,particularly in terms of Precision,Recall,F1-Score and area under the precision-recall curve(AUPR).Ablation analysis highlighted the substantial contribution of knowledge graph-derived features.Moreover,KG-CNNDTI was employed for virtual screening of natural products against Alzheimer's disease,resulting in 40 candidate compounds.5 were supported by literature evidence,among which 3 were further validated in vitro assays.
基金supported by the National Defense Fundamental Research Project(No.JCKY2022404C005)the Nuclear Energy Development Project(No.23ZG6106)+1 种基金the Sichuan Scientific and Technological Achievements Transfer and Transformation Demonstration Project(No.2023ZHCG0026)the Mianyang Applied Technology Research and Development Project(No.2021ZYZF1005)。
文摘In scenarios such as vehicle radiation monitoring and unmanned aerial vehicle radiation detection,rapid measurements using a NaI(Tl)detector often result in low photon counts,weak characteristic peaks,and significant statistical fluctuations.These issues can lead to potential failures in peak-searching-based identification methods.To address the low precision associated with short-duration measurements of radionuclides,this paper proposes an identification algorithm that leverages heterogeneous spectral transfer to develop a low-count energy spectral identification model.Comparative experiments demonstrated that transferring samples from 26 classes of simulated heterogeneous gamma spectra aids in creating a reliable model for measured gamma spectra.With only 10%of target domain samples used for training,the accuracy on real low-count spectral samples was 95.56%.This performance shows a significant improvement over widely employed full-spectrum analysis methods trained on target domain samples.The proposed method also exhibits strong generalization capabilities,effectively mitigating overfitting issues in low-count energy spectral classification under short-duration measurements.
基金supported by National Natural Science Foundation of China(NSFC,22338006,92356301,9235630033 and 22375062)Shanghai Municipal Science and Technology Major Project(21JC1401700)+4 种基金Shanghai Pilot Program for Basic Research(22TQ1400100-10)Fundamental Research Funds for the Central UniversitiesShanghai Pujiang Program(22PJ1402400)“Chenguang Program”supported by Shanghai Education Development Foundation and Shanghai Municipal Education Commission(22CGA32)the Young Elite Scientists Sponsorship Program by CAST(2023QNRC001).
文摘Organic nanophotocatalysts are promising candidates for solar fuels production,but they still face the challenge of unfavorable geminate recombination due to the limited exciton diffusion lengths.Here,we introduce a binary nanophotocatalyst fabricated by blending two polymers,PS-PEG5(PS)and PBT-PEG5(PBT),with matched absorption and emission spectra,enabling a Forster resonance energy transfer(FRET)process for enhanced photocatalysis.These heterostructure nanophotocatalysts are processed using a facile and scalable flash nanoprecipitation(FNP)technique with precious kinetic control over binary nanoparticle formation.The resulting nanoparticles exhibit an exceptional photocatalytic hydrogen evolution rate up to 65 mmol g^(-1) h^(-1),2.5 times higher than that single component nanoparticles.Characterizations through fluorescence spectra and transient absorption spectra confirm the hetero-energy transfer within the binary nanoparticles,which prolongs the excited-state lifetime and extends the namely“effective exciton diffusion length”.Our finding opens new avenues for designing efficient organic photocatalysts by improving exciton migration.
基金supported by the National Natural Science Foundation of China(No.21876039)Y.Yao acknowledges the scholarship support from the China Scholarship Council(No.202106695010)Partial support from the Australian Research Council for DP230102406 is also acknowledged.
文摘Catalytic oxidation of organic pollutants is a well-known and effective technique for pollutant abatement.Unfortunately,this method is significantly hindered in practical applications by the lowefficiency and difficult recovery of the catalysts in a powdery form.Herein,a three-dimensional(3D)framework of Fe-incorporated Ni_(3)S_(2)nanosheets in-situ grown on Ni foam(Fe-Ni_(3)S_(2)@NF)was fabricated by a facile two-step hydrothermal process and applied to trigger peroxymonosulfate(PMS)oxidation of organic compounds inwater.A homogeneous growth environment enabled the uniform and scalable growth of Fe-Ni_(3)S_(2)nanosheets on the Ni foam.Fe-Ni_(3)S_(2)@NF possessed outstanding activity and durability in activating PMS,as it effectively facilitated electron transfer from organic pollutants to PMS.Fe-Ni_(3)S_(2)@NF initially supplied electrons to PMS,causing the catalyst to undergo oxidation,and subsequently accepted electrons from organic compounds,returning to its initial state.The introduction of Fe into the Ni_(3)S_(2)lattice enhanced electrical conductivity,promoting mediated electron transfer between PMS and organic compounds.The 3D conductive Ni foam provided an ideal platform for the nucleation and growth of Fe-Ni_(3)S_(2),accelerating pollutant abatement due to its porous structure and high conductivity.Furthermore,its monolithic nature simplified the catalyst recycling process.A continuous flow packed-bed reactor by encapsulating Fe-Ni_(3)S_(2)@NF catalyst achieved complete pollutant abatement with continuous operation for 240 h,highlighting its immense potential for practical environmental remediation.This study presents a facile synthesis method for creating a novel type of monolithic catalyst with high activity and durability for decontamination through Fenton-like processes.
基金Strategic Priority Research Program of the Chinese Academy of Sciences,No.XDB0740000National Key Research and Development Program of China,No.2022YFB3904200,No.2022YFF0711601+1 种基金Key Project of Innovation LREIS,No.PI009National Natural Science Foundation of China,No.42471503。
文摘Deep-time Earth research plays a pivotal role in deciphering the rates,patterns,and mechanisms of Earth's evolutionary processes throughout geological history,providing essential scientific foundations for climate prediction,natural resource exploration,and sustainable planetary stewardship.To advance Deep-time Earth research in the era of big data and artificial intelligence,the International Union of Geological Sciences initiated the“Deeptime Digital Earth International Big Science Program”(DDE)in 2019.At the core of this ambitious program lies the development of geoscience knowledge graphs,serving as a transformative knowledge infrastructure that enables the integration,sharing,mining,and analysis of heterogeneous geoscience big data.The DDE knowledge graph initiative has made significant strides in three critical dimensions:(1)establishing a unified knowledge structure across geoscience disciplines that ensures consistent representation of geological entities and their interrelationships through standardized ontologies and semantic frameworks;(2)developing a robust and scalable software infrastructure capable of supporting both expert-driven and machine-assisted knowledge engineering for large-scale graph construction and management;(3)implementing a comprehensive three-tiered architecture encompassing basic,discipline-specific,and application-oriented knowledge graphs,spanning approximately 20 geoscience disciplines.Through its open knowledge framework and international collaborative network,this initiative has fostered multinational research collaborations,establishing a robust foundation for next-generation geoscience research while propelling the discipline toward FAIR(Findable,Accessible,Interoperable,Reusable)data practices in deep-time Earth systems research.
基金financially supported by the Second Tibetan Plateau Scientific Expedition and Research Program(STEP)(No.2019QZKK1003)the Science and Technology Innovation Pro-gram of Hunan Province(No.2022RC1122)。
文摘Layered double hydroxide(LDH)based heterogonous peroxymonosulfate(PMS)activation degradation of pollutants has attracted extensive attention.The challenge is to selectively regulate the traditional free radical dominant degradation pathway into a nonradical degradation pathway.Herein,an interface ar-chitecture of Ti_(3) C_(2) T_(x)-MXene(MXene)loading on the Fe-Al LDH scaffold was developed,which showed excellent stability and robust resistance against harsh conditions.Significantly,the rate constant for tetra-cycline hydrochloride(TC)degradation in the MXene-LDH/PMS process was 0.421 min^(-1),which was ten times faster than the rate constant for pure Fe-Al LDH(0.042 min^(-1)).Specifically,more reactive Fe with the closer d-band center to the Fermi level results in higher electron transfer efficiency.The occupa-tions of Fe-3d orbitals in Mxene/Fe-Al LDH are pushed above the Fermi level to generate,which results in higher PMS adsorption and inhibition of the release of oxygen-containing active species intermedi-ates,leading to the enhanced^(1)O_(2) generation.Additionally,the built-in electric field in the heterojunc-tion was driven by the charge redistribution between MXene and Fe-Al LDH,resulting in a mediated-electron transfer mechanism,differentiating it from the Fe-Al LDH/PMS system.It was fascinating that MXene/Fe-Al LDH achieved satisfactory treatment efficiency in continuous column reactor and real landfill leachate.
基金supported by the National Key Research and Development Program of China(Grant No.2023YFC3009400)the National Natural Science Foundation of China(Grant Nos.42307218 and U2239251).
文摘The current deep learning models for braced excavation cannot predict deformation from the beginning of excavation due to the need for a substantial corpus of sufficient historical data for training purposes.To address this issue,this study proposes a transfer learning model based on a sequence-to-sequence twodimensional(2D)convolutional long short-term memory neural network(S2SCL2D).The model can use the existing data from other adjacent similar excavations to achieve wall deflection prediction once a limited amount of monitoring data from the target excavation has been recorded.In the absence of adjacent excavation data,numerical simulation data from the target project can be employed instead.A weight update strategy is proposed to improve the prediction accuracy by integrating the stochastic gradient masking with an early stopping mechanism.To illustrate the proposed methodology,an excavation project in Hangzhou,China is adopted.The proposed deep transfer learning model,which uses either adjacent excavation data or numerical simulation data as the source domain,shows a significant improvement in performance when compared to the non-transfer learning model.Using the simulation data from the target project even leads to better prediction performance than using the actual monitoring data from other adjacent excavations.The results demonstrate that the proposed model can reasonably predict the deformation with limited data from the target project.
