Driving behavior modeling is very important in the research area of road traffic systems safety analysis. The characteristics of action of recovering from erroneous driving condition underlying road traffic accident o...Driving behavior modeling is very important in the research area of road traffic systems safety analysis. The characteristics of action of recovering from erroneous driving condition underlying road traffic accident or incident scenarios is quantitatively analyzed, the model of action of recovering from erroneous driving condition is set up according to the identification of erroneous driving condition and the measurement of correction from erroneous driving condition. And then, the probability of action of recovering from erroneous driving condition has been measured based on a revised decision tree. The measure process uses a combination of test data and subjective judgments of driving behavior. It can provide a very helpful theoretical basis for the further analysis of driving behavior in road traffic system.展开更多
Symbolic execution is an effective way of systematically exploring the search space of a program,and is often used for automatic software testing and bug finding.The program to be analyzed is usually compiled into a b...Symbolic execution is an effective way of systematically exploring the search space of a program,and is often used for automatic software testing and bug finding.The program to be analyzed is usually compiled into a binary or an intermediate representation,on which symbolic execution is carried out.During this process,compiler optimizations influence the effectiveness and efficiency of symbolic execution.However,to the best of our knowledge,there exists no work on compiler optimization recommendation for symbolic execution with respect to(w.r.t.)modified condition/decision coverage(MC/DC),which is an important testing coverage criterion widely used for mission-critical software.This study describes our use of a state-of-the-art symbolic execution tool to carry out extensive experiments to study the impact of compiler optimizations on symbolic execution w.r.t.MC/DC.The results indicate that instruction combining(IC)optimization is the important and dominant optimization for symbolic execution w.r.t.MC/DC.We designed and implemented a support vector machine based optimization recommendation method w.r.t.IC(denoted as auto).The experiments on two standard benchmarks(Coreutils and NECLA)showed that auto achieves the best MC/DC on 67.47%of Coreutils programs and 78.26%of NECLA programs.展开更多
Evaluating Unmanned Aerial Vehicle(UAV)systems within a System-of-Systems(SoS)environment helps clarify their contribution to the overall combat capability and supports effectiveness-oriented system optimization.When ...Evaluating Unmanned Aerial Vehicle(UAV)systems within a System-of-Systems(SoS)environment helps clarify their contribution to the overall combat capability and supports effectiveness-oriented system optimization.When assessing decision systems in such an environment,cross-level modeling and simulation are required,which often face a trade-off between low modeling cost and high simulation accuracy,while the credibility of results remains challenging to ensure.To address these issues,this study proposes a hybrid-granularity Hardware-In-the-Loop(HIL)SoS environment construction method based on Graphical Evaluation and Review Technique(GERT).The method employs GERT to analyze the relationships between simulation systems,the System Under Test(SUT),and mission outcomes,thereby determining the required model precision for different systems.A dynamic resource allocation algorithm is applied to adjust model granularity on demand,ensuring high-fidelity simulation under constrained total cost.Additionally,GERT estimates the computational frequency and communication bandwidth requirements of the SUT,guiding hardware selection to enhance simulation credibility.A UAV maritime combat case study was conducted for validation.The results demonstrate that,compared to the flat modeling approach,the hybrid-granularity scenario based on GERT analysis achieves higher simulation accuracy with lower overall model complexity.The coefficient of variation in evaluation results significantly decreases in HIL simulations compared to virtual simulations,confirming improved credibility.Under the hybrid-granularity HIL scenario,the decision system was evaluated from an effectiveness perspective,identifying the most sensitive performance parameter.Subsequent targeted optimization led to an 11.90%improvement in effectiveness,validating the method's practical utility.展开更多
Eco-driving behaviors have been recommended around the world because the transport is a key factor of energy use and pollution emissions.Therefore,based on the driving decision model,this paper introduces three aspect...Eco-driving behaviors have been recommended around the world because the transport is a key factor of energy use and pollution emissions.Therefore,based on the driving decision model,this paper introduces three aspects of the driving decisions(strategic decision,tactical decision and operation decision)to analyze the economy of vehicle energy.The analytic hierarchy process(AHP)is used to assign the weight of the internal evaluation indexes,so as to form a complete assessment for drivers'eco-driving behaviors.The research result can not only quantitatively describe the energy-saving effect of drivers'decisions,but also put forward targeted driving suggestions to optimize drivers'eco-driving behaviors.This assessment model helps to clarify the potential of eco-driving on energy economy of transportation in a hierarchical way,and provides a valuable theoretical basis for the further promotion and application of eco-driving education.展开更多
The global shift towards sustainable energy has intensified research into renewable sources,particularly wave energy.Pakistan,with its long coastline,holds significant potential for wave energy development.However,ide...The global shift towards sustainable energy has intensified research into renewable sources,particularly wave energy.Pakistan,with its long coastline,holds significant potential for wave energy development.However,identifying optimal locations for wave energy plants involves evaluating complex,multi-faceted criteria.This study employs a multi-criteria group decisionmaking(MCGDM)approach using single-valued neutrosophic numbers(SVNNs)to address both qualitative and quantitative uncertainties inherent in real-world scenarios.To enhance decision quality,we introduce two novel operators:the singlevalued neutrosophic prioritised averaging(SVNPAd)operator and the single-valued neutrosophic prioritised geometric(SVNPGd)operator,both incorporating priority degrees.These tools allow decision-makers to express preferences better and handle ambiguous data.The proposed model is validated through comparative analysis with prior studies and demonstrates improved robustness in site selection.Furthermore,we analyse how variations in priority degrees influence decision outcomes,enabling a more dynamic and tailored decision-making process.Our method contributes a more holistic and adaptive framework for selecting locations for wave energy projects,ultimately supporting informed investments in renewable energy infrastructure and improving energy access in underserved coastal regions.展开更多
The complex aerodynamic interaction between tandem tilt-wing and multi-rotor directly affects the wing surface flow and rotor thrust,making it a critical factor during the tilt transition process of this configuration...The complex aerodynamic interaction between tandem tilt-wing and multi-rotor directly affects the wing surface flow and rotor thrust,making it a critical factor during the tilt transition process of this configuration of rotorcraft.The aerodynamic interaction of tandem tilt-wing and multi-rotor is investigated based on the CFD method.The aerodynamic effect of multi tilt-rotor is simulated as virtual disk modeling by adding source terms to the Navier-Stokes equations,effectively reducing the calculation time while maintaining the accuracy of aerodynamic interaction calculations.Aerodynamic forces and flow field characteristics of the tandem tilt-wing and multi-rotor under different tilt angles are compared between cases with and without aerodynamic interaction.Furthermore,the differences in aerodynamic forces between dynamic tilt transition and fixed-angle conditions were compared.The results show that the aerodynamic interaction of multi-rotor obviously increases the lift of front tilt-wing at different tilt angles,the wing lift under interaction is increased by more than 40%compared with isolated wing at tilt angle of 15°for the computation in this paper,which is related to the increase of wing flow velocity and the suppression of flow separation caused by multi-rotor;the wing blocking effect will increase rotor thrust,especially near the tilt angles of 30°and 45°;the increases of rear wing lift and rear rotor thrust under aerodynamic interaction are not significant because of suppression by the front wing’s downwash;the unsteady effects during dynamic tilting have a relatively minor impact on aerodynamic interaction,with the aerodynamic forces on the rotors and wings during the dynamic tilting process showing little difference from those under corresponding fixed tilt angles.展开更多
Earthquakes are highly destructive spatio-temporal phenomena whose analysis is essential for disaster preparedness and risk mitigation.Modern seismological research produces vast volumes of heterogeneous data from sei...Earthquakes are highly destructive spatio-temporal phenomena whose analysis is essential for disaster preparedness and risk mitigation.Modern seismological research produces vast volumes of heterogeneous data from seismic networks,satellite observations,and geospatial repositories,creating the need for scalable infrastructures capable of integrating and analyzing such data to support intelligent decision-making.Data warehousing technologies provide a robust foundation for this purpose;however,existing earthquake-oriented data warehouses remain limited,often relying on simplified schemas,domain-specific analytics,or cataloguing efforts.This paper presents the design and implementation of a spatio-temporal data warehouse for seismic activity.The framework integrates spatial and temporal dimensions in a unified schema and introduces a novel array-based approach for managing many-to-many relationships between facts and dimensions without intermediate bridge tables.A comparative evaluation against a conventional bridge-table schema demonstrates that the array-based design improves fact-centric query performance,while the bridge-table schema remains advantageous for dimension-centric queries.To reconcile these trade-offs,a hybrid schema is proposed that retains both representations,ensuring balanced efficiency across heterogeneous workloads.The proposed framework demonstrates how spatio-temporal data warehousing can address schema complexity,improve query performance,and support multidimensional visualization.In doing so,it provides a foundation for integrating seismic analysis into broader big data-driven intelligent decision systems for disaster resilience,risk mitigation,and emergency management.展开更多
Background:The golden Syrian hamster is a valuable animal model for studying carcinogenesis,metabolic disorders,cardiovascular diseases,and viral infections due to its biological and pathological similarities to human...Background:The golden Syrian hamster is a valuable animal model for studying carcinogenesis,metabolic disorders,cardiovascular diseases,and viral infections due to its biological and pathological similarities to humans.However,the development of genetically engineered hamsters has lagged behind that of mice and rats,largely because of an embryonic development block at the two-cell stage in vitro.Although CRISPR/Cas9-mediated gene knockout has been achieved in hamsters,precise DNA fragment insertion or conditional knockout(cKO)models have not previously been reported,likely due to technical limitations in embryo manipulation and insufficient efficiency of homology-directed repair(HDR).Methods:In this study,we generated conditional alleles of the ApoF gene in golden Syrian hamsters.A two-cut strategy was applied using Cas9 protein,two sgRNAs,and a single donor plasmid containing exon 2 flanked by loxP sites and two~0.8 kb homology arms.A mixture of Cas9 protein,sgRNAs,and the donor plasmid was microinjected into the pronuclei of one-cell stage hamster embryos.Results:The efficiency of CRISPR/Cas9-mediated loxP knock-in reached up to 27%,and the genetically modified floxed alleles were successfully transmitted through the germline.The functionality of the inserted loxP sites was validated by in vivo Cremediated recombination following local administration of AAV vectors,including AAV-cTnT-Cre in the heart and AAV-CMV-Cre in the brain.Conclusions:To our knowledge,this work represents the first successful establishment of a conditional knockout model in the golden Syrian hamster,providing a valuable tool for mechanistic studies of gene function and disease modeling.展开更多
Cooperative multi-UAV search requires jointly optimizing wide-area coverage,rapid target discovery,and endurance under sensing and motion constraints.Resolving this coupling enables scalable coordination with high dat...Cooperative multi-UAV search requires jointly optimizing wide-area coverage,rapid target discovery,and endurance under sensing and motion constraints.Resolving this coupling enables scalable coordination with high data efficiency and mission reliability.We formulate this problem as a discounted Markov decision process on an occupancy grid with a cellwise Bayesian belief update,yielding a Markov state that couples agent poses with a probabilistic target field.On this belief–MDP we introduce a segment-conditioned latent-intent framework,in which a discrete intent head selects a latent skill every K steps and an intra-segment GRU policy generates per-step control conditioned on the fixed intent;both components are trained end-to-end with proximal updates under a centralized critic.On the 50×50 grid,coverage and discovery convergence times are reduced by up to 48%and 40%relative to a flat actor-critic benchmark,and the aggregated convergence metric improves by about 12%compared with a stateof-the-art hierarchical method.Qualitative analyses further reveal stable spatial sectorization,low path overlap,and fuel-aware patrolling,indicating that segment-conditioned latent intents provide an effective and scalable mechanism for coordinated multi-UAV search.展开更多
Estuarine and bay ecosystems serve as crucial transitional zones for land-based pollutants entering the ocean.However,there is a critical gap in understanding the behavior of emerging pollutants in the numerous small ...Estuarine and bay ecosystems serve as crucial transitional zones for land-based pollutants entering the ocean.However,there is a critical gap in understanding the behavior of emerging pollutants in the numerous small estuaries and bays located in undeveloped coastal areas.This study provides insights into the fate of antibiotics in these small and scattered estuaries and bays in Shantou's coast,driven by land use types and hydrodynamic conditions.The findings indicated that estuaries were more heavily polluted with antibiotics than the bays(P<0.05),with tetracyclines and fluoroquinolones as the primary antibiotics.Antibiotic pollution levels were more severe in October than in June(P<0.01).Rainfall runoff,aquaculture tailwater,and river discharge were identified as the main sources of antibiotic pollution.Build-up land and aquaculture ponds were the primary land use types contributing to antibiotic pollution.The total antibiotic concentrations in June were positively correlated with the proportion of aquaculture ponds(P<0.05)and negatively correlated with the proportions of cropland and grassland(P<0.05).The concentrations of lomefloxacin and ofloxacin were positively correlated with build-up land.The antibiotic concentrations exhibited strong spatial heterogeneity within both bay and estuarine ecosystems driven by different hydrodynamic conditions.A comparative analysis of global estuaries and bays revealed that specific land-use types and hydrodynamic conditions produced similar trends in antibiotic fate.These insights offered new perspectives to safeguard the health of estuarine and bay ecosystems,such as altering landscape patterns and regulating aquaculture activities.展开更多
In this article,we show the existence,uniqueness and stability of bounded solutions to the following quasilinear problems with mean curvature operator(φ'(x′(t)))′=f(t,x),t≥t_(0),lim_(t→∞)x(t)=ψ_(0),lim_(t→...In this article,we show the existence,uniqueness and stability of bounded solutions to the following quasilinear problems with mean curvature operator(φ'(x′(t)))′=f(t,x),t≥t_(0),lim_(t→∞)x(t)=ψ_(0),lim_(t→∞)x′(t)e^(t)=0,where t_(0) and ψ_(0) are real constants,φ(s)=s/√1−s^(2),s∈R with s∈(−1,1),f:[t_(0),∞)×R→R satisfies the Lipschitz or Osgood-type conditions.展开更多
Cloud data sharing is an important issue in modern times.To maintain the privacy and confidentiality of data stored in the cloud,encryption is an inevitable process before uploading the data.However,the centralized ma...Cloud data sharing is an important issue in modern times.To maintain the privacy and confidentiality of data stored in the cloud,encryption is an inevitable process before uploading the data.However,the centralized management and transmission latency of the cloud makes it difficult to support real-time processing and distributed access structures.As a result,fog computing and the Internet of Things(IoT)have emerged as crucial applications.Fog-assisted proxy re-encryption is a commonly adopted technique for sharing cloud ciphertexts.It allows a semitrusted proxy to transforma data owner’s ciphertext into another re-encrypted ciphertext intended for a data requester,without compromising any information about the original ciphertext.Yet,the user revocation and cloud ciphertext renewal problems still lack effective and secure mechanisms.Motivated by it,we propose a revocable conditional proxy re-encryption scheme offering ciphertext evolution(R-CPRE-CE).In particular,a periodically updated time key is used to revoke the user’s access privileges while an access condition prevents a malicious proxy from reencrypting unauthorized ciphertext.We also demonstrate that our scheme is provably secure under the notion of indistinguishability against adaptively chosen identity and chosen ciphertext attacks in the random oracle model.Performance analysis shows that our scheme reduces the computation time for a complete data access cycle from an initial query to the final decryption by approximately 47.05%compared to related schemes.展开更多
The carbonylation of amines offers a promising route for synthesizing N-substituted carbamates with high atom economy.However,conventional catalysts exhibit limited catalytic efficiency,and the underlying proton trans...The carbonylation of amines offers a promising route for synthesizing N-substituted carbamates with high atom economy.However,conventional catalysts exhibit limited catalytic efficiency,and the underlying proton transfer mechanism remains elusive.Herein,we reported a metal-free,room-temperature strategy utilizing 1,5,7-triazabicyclo[4.4.0]dec-5-ene(TBD)as a dual hydrogen bond catalyst to synergistically activate propylamine(PA)and dimethyl carbonate(DMC).This green catalytic system achieves a 10-fold acceleration in reaction rate compared to other hydrogen bonding catalysts under mild conditions.This is enabled by dual hydrogen bonding of TBD with PA and DMC,which facilitates rapid proton transfer and stabilizes tetrahedral intermediates.Theoretical calculations confirm that the dual hydrogen bond system significantly lowers activation energy compared to single hydrogen bond analogs.Furthermore,it was revealed that the hydrogen bonding network within the product is the primary factor responsible for the sluggish reaction rate.This study demonstrates the effectiveness of a dual hydrogen bond system in accelerating the carbonylation of amines and provides a green route to access carbamates.展开更多
The dynamic characteristics of the track system can directly affect its service performance and failure process.To explore the load characteristics and dynamic response of the track system under the dynamic loads from...The dynamic characteristics of the track system can directly affect its service performance and failure process.To explore the load characteristics and dynamic response of the track system under the dynamic loads from the rack vehicle in traction conditions,a systematic test of the track subsystem was carried out on a large-slope test line.In the test,the bending stress of the rack teeth,the wheel-rail forces,and the acceleration of crucial components in the track system were measured.Subsequently,a detailed analysis was conducted on the tested signals of the rack railway track system in the time domain and the time-frequency domains.The test results indicate that the traction force significantly affects the rack tooth bending stress and the wheel-rail forces.The vibrations of the track system under the traction conditions are mainly caused by the impacts generated from the gear-rack engagement,which are then transferred to the sleepers,the rails,and the ballast beds.Furthermore,both the maximum stress on the racks and the wheel-rail forces measured on the rails remain below their allowable values.This experimental study evaluates the load characteristics and reveals the vibration characteristics of the rack railway track system under the vehicle’s ultimate load,which is very important for the load-strengthening design of the key components such as racks and the vibration and noise reduction of the track system.展开更多
Intervention strategies to control non-point source nitrogen(N)and phosphorus(P)pollution in agriculture are expensive and there is a trade-off between engineering cost and treatment effectiveness.Implementing strateg...Intervention strategies to control non-point source nitrogen(N)and phosphorus(P)pollution in agriculture are expensive and there is a trade-off between engineering cost and treatment effectiveness.Implementing strategies often result in unsatisfactory outcomes and massive engineering costs when managing diffusive pollution in agricultural catchments.To address this issue,this paper proposes a robust,handy,catchment N&P decision support system(CNPDSS),an Android-based smartphone system integrated with a web-based geographic information system(GIS).The CNPDSS aims to provide artificial intelligence-driven decisions that minimize N&P loadings and engineering costs for mitigating pollution in agricultural catchments.It consists of four components:a general user interface(GUI),GIS,N&P pollution modeling(NPPM),and a DSS.The CNPDSS simplifies the GUI and integrates GIS modules to create a user-friendly interface,enabling non-professional users to operate the system easily through intuitive actions.The NPPM uses straightforward empirical models to predict N&P loadings,enhancing efficiency by avoiding excessive parameters.Taking into account the N&P movement pathway in the catchment,the DSS incorporates three control measures:source reduction in farmland(before migration stage),process retention by ecological ditch(midway transport stage),and down-end purification by constructed wetland(waterbody discharge stage),to formulate a comprehensive ternary controlling strategy.To optimize the cost-effectiveness of any proposed N&P control strategies for sub-catchments,a differential evolution algorithm(DEA)is employed in CNPDSS to carry out a dual-objective decision-making optimization computation.In this study,the CNPDSS is applied to a case study in an agricultural catchment in Central China to develop the most cost-effective ternary N&P control strategies that ensure the catchment water quality within Criterion Ⅲ of the Chinese Surface Water Quality Standard GB3838-2002 is met(total N concentration≤1.0 mg L^(-1)and total P concentration≤0.2 mg L^(-1)).Our results demonstrate that the CNPDSS is feasible and also possesses an adaptive design and flexible architecture to enable its generalization and extension to support strong hands-on applications in other catchments.展开更多
In this paper,we study the asymptotic behavior of the micropolar fluid flow through a thin domain,assuming zero Dirichlet boundary condition on the top boundary,which is rapidly oscillating,and non-standard boundary c...In this paper,we study the asymptotic behavior of the micropolar fluid flow through a thin domain,assuming zero Dirichlet boundary condition on the top boundary,which is rapidly oscillating,and non-standard boundary conditions on the flat bottom.Assuming“Reynolds roughness regime”,in which the thickness of the domain is very small compared to the wavelength of the roughness(i.e.a very slight roughness),we rigorously derive a generalized Reynolds equation for pressure,clearly showing the roughness-induced effects.Moreover,we give expressions for the average velocity and microrotation.展开更多
Objective To develop a clinical decision and prescription generation system(CDPGS)specifically for diarrhea in traditional Chinese medicine(TCM),utilizing a specialized large language model(LLM),Qwen-TCM-Dia,to standa...Objective To develop a clinical decision and prescription generation system(CDPGS)specifically for diarrhea in traditional Chinese medicine(TCM),utilizing a specialized large language model(LLM),Qwen-TCM-Dia,to standardize diagnostic processes and prescription generation.Methods Two primary datasets were constructed:an evaluation benchmark and a fine-tuning dataset consisting of fundamental diarrhea knowledge,medical records,and chain-ofthought(CoT)reasoning datasets.After an initial evaluation of 16 open-source LLMs across inference time,accuracy,and output quality,Qwen2.5 was selected as the base model due to its superior overall performance.We then employed a two-stage low-rank adaptation(LoRA)fine-tuning strategy,integrating continued pre-training on domain-specific knowledge with instruction fine-tuning using CoT-enriched medical records.This approach was designed to embed the clinical logic(symptoms→pathogenesis→therapeutic principles→prescriptions)into the model’s reasoning capabilities.The resulting fine-tuned model,specialized for TCM diarrhea,was designated as Qwen-TCM-Dia.Model performance was evaluated for disease diagnosis and syndrome type differentiation using accuracy,precision,recall,and F1-score.Furthermore,the quality of the generated prescriptions was compared with that of established open-source TCM LLMs.Results Qwen-TCM-Dia achieved peak performance compared to both the base Qwen2.5 model and five other open-source TCM LLMs.It achieved 97.05%accuracy and 91.48%F1-score in disease diagnosis,and 74.54%accuracy and 74.21%F1-score in syndrome type differentiation.Compared with existing open-source TCM LLMs(BianCang,HuangDi,LingDan,TCMLLM-PR,and ZhongJing),Qwen-TCM-Dia exhibited higher fidelity in reconstructing the“symptoms→pathogenesis→therapeutic principles→prescriptions”logic chain.It provided complete prescriptions,whereas other models often omitted dosages or generated mismatched prescriptions.Conclusion By integrating continued pre-training,CoT reasoning,and a two-stage fine-tuning strategy,this study establishes a CDPGS for diarrhea in TCM.The results demonstrate the synergistic effect of strengthening domain representation through pre-training and activating logical reasoning via CoT.This research not only provides critical technical support for the standardized diagnosis and treatment of diarrhea but also offers a scalable paradigm for the digital inheritance of expert TCM experience and the intelligent transformation of TCM.展开更多
The main purpose of using geothermal energy piles(GEPs)is to enable the exploitation of geothermal energy for meeting the heating/cooling demands of buildings efficiently.However,the installation process of convention...The main purpose of using geothermal energy piles(GEPs)is to enable the exploitation of geothermal energy for meeting the heating/cooling demands of buildings efficiently.However,the installation process of conventional GEPs is inconvenient compared with that of traditional foundation piles.The pre-bored grouted planted geothermal energy pile(PGP GEP)is an innovative technology to simplify the installation process.Most investigations of in-situ experiments for conventional GEPs have focused on summer conditions.An in-situ test for a PGP GEP was conducted to analyze the temperature changes and thermo-mechanical characteristics under winter conditions.The results show that the average temperature of the pile decreased by 5.1℃,and the pile exhibited a general trend of high temperatures at both ends and low temperatures in the middle.In mechanics,strong pile end restraints resulted in smaller observed axial strain and higher axial thermal-induced force in the pile ends than at the middle of the pile.展开更多
To address the issue of scarce labeled samples and operational condition variations that degrade the accuracy of fault diagnosis models in variable-condition gearbox fault diagnosis,this paper proposes a semi-supervis...To address the issue of scarce labeled samples and operational condition variations that degrade the accuracy of fault diagnosis models in variable-condition gearbox fault diagnosis,this paper proposes a semi-supervised masked contrastive learning and domain adaptation(SSMCL-DA)method for gearbox fault diagnosis under variable conditions.Initially,during the unsupervised pre-training phase,a dual signal augmentation strategy is devised,which simultaneously applies random masking in the time domain and random scaling in the frequency domain to unlabeled samples,thereby constructing more challenging positive sample pairs to guide the encoder in learning intrinsic features robust to condition variations.Subsequently,a ConvNeXt-Transformer hybrid architecture is employed,integrating the superior local detail modeling capacity of ConvNeXt with the robust global perception capability of Transformer to enhance feature extraction in complex scenarios.Thereafter,a contrastive learning model is constructed with the optimization objective of maximizing feature similarity across different masked instances of the same sample,enabling the extraction of consistent features from multiple masked perspectives and reducing reliance on labeled data.In the final supervised fine-tuning phase,a multi-scale attention mechanism is incorporated for feature rectification,and a domain adaptation module combining Local Maximum Mean Discrepancy(LMMD)with adversarial learning is proposed.This module embodies a dual mechanism:LMMD facilitates fine-grained class-conditional alignment,compelling features of identical fault classes to converge across varying conditions,while the domain discriminator utilizes adversarial training to guide the feature extractor toward learning domain-invariant features.Working in concert,they markedly diminish feature distribution discrepancies induced by changes in load,rotational speed,and other factors,thereby boosting the model’s adaptability to cross-condition scenarios.Experimental evaluations on the WT planetary gearbox dataset and the Case Western Reserve University(CWRU)bearing dataset demonstrate that the SSMCL-DA model effectively identifies multiple fault classes in gearboxes,with diagnostic performance substantially surpassing that of conventional methods.Under cross-condition scenarios,the model attains fault diagnosis accuracies of 99.21%for the WT planetary gearbox and 99.86%for the bearings,respectively.Furthermore,the model exhibits stable generalization capability in cross-device settings.展开更多
Recommending personalized travel routes from sparse,implicit feedback poses a significant challenge,as conventional systems often struggle with information overload and fail to capture the complex,sequential nature of...Recommending personalized travel routes from sparse,implicit feedback poses a significant challenge,as conventional systems often struggle with information overload and fail to capture the complex,sequential nature of user preferences.To address this,we propose a Conditional Generative Adversarial Network(CGAN)that generates diverse and highly relevant itineraries.Our approach begins by constructing a conditional vector that encapsulates a user’s profile.This vector uniquely fuses embeddings from a Heterogeneous Information Network(HIN)to model complex user-place-route relationships,a Recurrent Neural Network(RNN)to capture sequential path dynamics,and Neural Collaborative Filtering(NCF)to incorporate collaborative signals from the wider user base.This comprehensive condition,further enhanced with features representing user interaction confidence and uncertainty,steers a CGAN stabilized by spectral normalization to generate high-fidelity latent route representations,effectively mitigating the data sparsity problem.Recommendations are then formulated using an Anchor-and-Expand algorithm,which selects relevant starting Points of Interest(POI)based on user history,then expands routes through latent similarity matching and geographic coherence optimization,culminating in Traveling Salesman Problem(TSP)-based route optimization for practical travel distances.Experiments on a real-world check-in dataset validate our model’s unique generative capability,achieving F1 scores ranging from 0.163 to 0.305,and near-zero pairs−F1 scores between 0.002 and 0.022.These results confirm the model’s success in generating novel travel routes by recommending new locations and sequences rather than replicating users’past itineraries.This work provides a robust solution for personalized travel planning,capable of generating novel and compelling routes for both new and existing users by learning from collective travel intelligence.展开更多
文摘Driving behavior modeling is very important in the research area of road traffic systems safety analysis. The characteristics of action of recovering from erroneous driving condition underlying road traffic accident or incident scenarios is quantitatively analyzed, the model of action of recovering from erroneous driving condition is set up according to the identification of erroneous driving condition and the measurement of correction from erroneous driving condition. And then, the probability of action of recovering from erroneous driving condition has been measured based on a revised decision tree. The measure process uses a combination of test data and subjective judgments of driving behavior. It can provide a very helpful theoretical basis for the further analysis of driving behavior in road traffic system.
基金Project supported by the National Key R&D Program of China(No.2017YFB1001802)the National Natural Science Foundation of China(Nos.61472440,61632015,61690203,and 61532007)。
文摘Symbolic execution is an effective way of systematically exploring the search space of a program,and is often used for automatic software testing and bug finding.The program to be analyzed is usually compiled into a binary or an intermediate representation,on which symbolic execution is carried out.During this process,compiler optimizations influence the effectiveness and efficiency of symbolic execution.However,to the best of our knowledge,there exists no work on compiler optimization recommendation for symbolic execution with respect to(w.r.t.)modified condition/decision coverage(MC/DC),which is an important testing coverage criterion widely used for mission-critical software.This study describes our use of a state-of-the-art symbolic execution tool to carry out extensive experiments to study the impact of compiler optimizations on symbolic execution w.r.t.MC/DC.The results indicate that instruction combining(IC)optimization is the important and dominant optimization for symbolic execution w.r.t.MC/DC.We designed and implemented a support vector machine based optimization recommendation method w.r.t.IC(denoted as auto).The experiments on two standard benchmarks(Coreutils and NECLA)showed that auto achieves the best MC/DC on 67.47%of Coreutils programs and 78.26%of NECLA programs.
基金funded by Henan Key Laboratory of General Aviation Technology,grant number ZHKF-240202。
文摘Evaluating Unmanned Aerial Vehicle(UAV)systems within a System-of-Systems(SoS)environment helps clarify their contribution to the overall combat capability and supports effectiveness-oriented system optimization.When assessing decision systems in such an environment,cross-level modeling and simulation are required,which often face a trade-off between low modeling cost and high simulation accuracy,while the credibility of results remains challenging to ensure.To address these issues,this study proposes a hybrid-granularity Hardware-In-the-Loop(HIL)SoS environment construction method based on Graphical Evaluation and Review Technique(GERT).The method employs GERT to analyze the relationships between simulation systems,the System Under Test(SUT),and mission outcomes,thereby determining the required model precision for different systems.A dynamic resource allocation algorithm is applied to adjust model granularity on demand,ensuring high-fidelity simulation under constrained total cost.Additionally,GERT estimates the computational frequency and communication bandwidth requirements of the SUT,guiding hardware selection to enhance simulation credibility.A UAV maritime combat case study was conducted for validation.The results demonstrate that,compared to the flat modeling approach,the hybrid-granularity scenario based on GERT analysis achieves higher simulation accuracy with lower overall model complexity.The coefficient of variation in evaluation results significantly decreases in HIL simulations compared to virtual simulations,confirming improved credibility.Under the hybrid-granularity HIL scenario,the decision system was evaluated from an effectiveness perspective,identifying the most sensitive performance parameter.Subsequent targeted optimization led to an 11.90%improvement in effectiveness,validating the method's practical utility.
文摘Eco-driving behaviors have been recommended around the world because the transport is a key factor of energy use and pollution emissions.Therefore,based on the driving decision model,this paper introduces three aspects of the driving decisions(strategic decision,tactical decision and operation decision)to analyze the economy of vehicle energy.The analytic hierarchy process(AHP)is used to assign the weight of the internal evaluation indexes,so as to form a complete assessment for drivers'eco-driving behaviors.The research result can not only quantitatively describe the energy-saving effect of drivers'decisions,but also put forward targeted driving suggestions to optimize drivers'eco-driving behaviors.This assessment model helps to clarify the potential of eco-driving on energy economy of transportation in a hierarchical way,and provides a valuable theoretical basis for the further promotion and application of eco-driving education.
基金supported by Science foundation Ireland(22/NCF/DR/11309).
文摘The global shift towards sustainable energy has intensified research into renewable sources,particularly wave energy.Pakistan,with its long coastline,holds significant potential for wave energy development.However,identifying optimal locations for wave energy plants involves evaluating complex,multi-faceted criteria.This study employs a multi-criteria group decisionmaking(MCGDM)approach using single-valued neutrosophic numbers(SVNNs)to address both qualitative and quantitative uncertainties inherent in real-world scenarios.To enhance decision quality,we introduce two novel operators:the singlevalued neutrosophic prioritised averaging(SVNPAd)operator and the single-valued neutrosophic prioritised geometric(SVNPGd)operator,both incorporating priority degrees.These tools allow decision-makers to express preferences better and handle ambiguous data.The proposed model is validated through comparative analysis with prior studies and demonstrates improved robustness in site selection.Furthermore,we analyse how variations in priority degrees influence decision outcomes,enabling a more dynamic and tailored decision-making process.Our method contributes a more holistic and adaptive framework for selecting locations for wave energy projects,ultimately supporting informed investments in renewable energy infrastructure and improving energy access in underserved coastal regions.
基金supported by the National Key Laboratory of Helicopter Aeromechanics Fund(No.2024-CXPT-GF-JJ-093-05).
文摘The complex aerodynamic interaction between tandem tilt-wing and multi-rotor directly affects the wing surface flow and rotor thrust,making it a critical factor during the tilt transition process of this configuration of rotorcraft.The aerodynamic interaction of tandem tilt-wing and multi-rotor is investigated based on the CFD method.The aerodynamic effect of multi tilt-rotor is simulated as virtual disk modeling by adding source terms to the Navier-Stokes equations,effectively reducing the calculation time while maintaining the accuracy of aerodynamic interaction calculations.Aerodynamic forces and flow field characteristics of the tandem tilt-wing and multi-rotor under different tilt angles are compared between cases with and without aerodynamic interaction.Furthermore,the differences in aerodynamic forces between dynamic tilt transition and fixed-angle conditions were compared.The results show that the aerodynamic interaction of multi-rotor obviously increases the lift of front tilt-wing at different tilt angles,the wing lift under interaction is increased by more than 40%compared with isolated wing at tilt angle of 15°for the computation in this paper,which is related to the increase of wing flow velocity and the suppression of flow separation caused by multi-rotor;the wing blocking effect will increase rotor thrust,especially near the tilt angles of 30°and 45°;the increases of rear wing lift and rear rotor thrust under aerodynamic interaction are not significant because of suppression by the front wing’s downwash;the unsteady effects during dynamic tilting have a relatively minor impact on aerodynamic interaction,with the aerodynamic forces on the rotors and wings during the dynamic tilting process showing little difference from those under corresponding fixed tilt angles.
文摘Earthquakes are highly destructive spatio-temporal phenomena whose analysis is essential for disaster preparedness and risk mitigation.Modern seismological research produces vast volumes of heterogeneous data from seismic networks,satellite observations,and geospatial repositories,creating the need for scalable infrastructures capable of integrating and analyzing such data to support intelligent decision-making.Data warehousing technologies provide a robust foundation for this purpose;however,existing earthquake-oriented data warehouses remain limited,often relying on simplified schemas,domain-specific analytics,or cataloguing efforts.This paper presents the design and implementation of a spatio-temporal data warehouse for seismic activity.The framework integrates spatial and temporal dimensions in a unified schema and introduces a novel array-based approach for managing many-to-many relationships between facts and dimensions without intermediate bridge tables.A comparative evaluation against a conventional bridge-table schema demonstrates that the array-based design improves fact-centric query performance,while the bridge-table schema remains advantageous for dimension-centric queries.To reconcile these trade-offs,a hybrid schema is proposed that retains both representations,ensuring balanced efficiency across heterogeneous workloads.The proposed framework demonstrates how spatio-temporal data warehousing can address schema complexity,improve query performance,and support multidimensional visualization.In doing so,it provides a foundation for integrating seismic analysis into broader big data-driven intelligent decision systems for disaster resilience,risk mitigation,and emergency management.
基金State Key Laboratory Special Fund,Grant/Award Number:2060204Open Research Project in State Key Laboratory of Vascular Homeostasis and Remodeling,Grant/Award Number:Peking University,202411+3 种基金The Non-profit Central Research Institute Fund of the Chinese Academy of Medical Sciences,Grant/Award Number:2023-PT180-01Haihe Laboratory of Cell Ecosystem Innovation Fund,Grant/Award Number:HH24KYZX0007CAMS Innovation Fund for Medical Sciences,Grant/Award Number:2021-I2M-1-024,2022-I2M-1-020 and 2023-I2M-2-001the National Key Research and Development Program of China from the Ministry of Science and Technology,Grant/Award Number:2021YFF0702802。
文摘Background:The golden Syrian hamster is a valuable animal model for studying carcinogenesis,metabolic disorders,cardiovascular diseases,and viral infections due to its biological and pathological similarities to humans.However,the development of genetically engineered hamsters has lagged behind that of mice and rats,largely because of an embryonic development block at the two-cell stage in vitro.Although CRISPR/Cas9-mediated gene knockout has been achieved in hamsters,precise DNA fragment insertion or conditional knockout(cKO)models have not previously been reported,likely due to technical limitations in embryo manipulation and insufficient efficiency of homology-directed repair(HDR).Methods:In this study,we generated conditional alleles of the ApoF gene in golden Syrian hamsters.A two-cut strategy was applied using Cas9 protein,two sgRNAs,and a single donor plasmid containing exon 2 flanked by loxP sites and two~0.8 kb homology arms.A mixture of Cas9 protein,sgRNAs,and the donor plasmid was microinjected into the pronuclei of one-cell stage hamster embryos.Results:The efficiency of CRISPR/Cas9-mediated loxP knock-in reached up to 27%,and the genetically modified floxed alleles were successfully transmitted through the germline.The functionality of the inserted loxP sites was validated by in vivo Cremediated recombination following local administration of AAV vectors,including AAV-cTnT-Cre in the heart and AAV-CMV-Cre in the brain.Conclusions:To our knowledge,this work represents the first successful establishment of a conditional knockout model in the golden Syrian hamster,providing a valuable tool for mechanistic studies of gene function and disease modeling.
文摘Cooperative multi-UAV search requires jointly optimizing wide-area coverage,rapid target discovery,and endurance under sensing and motion constraints.Resolving this coupling enables scalable coordination with high data efficiency and mission reliability.We formulate this problem as a discounted Markov decision process on an occupancy grid with a cellwise Bayesian belief update,yielding a Markov state that couples agent poses with a probabilistic target field.On this belief–MDP we introduce a segment-conditioned latent-intent framework,in which a discrete intent head selects a latent skill every K steps and an intra-segment GRU policy generates per-step control conditioned on the fixed intent;both components are trained end-to-end with proximal updates under a centralized critic.On the 50×50 grid,coverage and discovery convergence times are reduced by up to 48%and 40%relative to a flat actor-critic benchmark,and the aggregated convergence metric improves by about 12%compared with a stateof-the-art hierarchical method.Qualitative analyses further reveal stable spatial sectorization,low path overlap,and fuel-aware patrolling,indicating that segment-conditioned latent intents provide an effective and scalable mechanism for coordinated multi-UAV search.
基金supported by the National Key Research and Development Program of China(Nos.2022YFF0801104 and 2021YFD1700600)the National Natural Science Foundation of China(No.51809177)the Science Foundation of Nanjing Institute of Geography and Limnology,Chinese Academy of Sciences(No.NIGLAS2022GS08).
文摘Estuarine and bay ecosystems serve as crucial transitional zones for land-based pollutants entering the ocean.However,there is a critical gap in understanding the behavior of emerging pollutants in the numerous small estuaries and bays located in undeveloped coastal areas.This study provides insights into the fate of antibiotics in these small and scattered estuaries and bays in Shantou's coast,driven by land use types and hydrodynamic conditions.The findings indicated that estuaries were more heavily polluted with antibiotics than the bays(P<0.05),with tetracyclines and fluoroquinolones as the primary antibiotics.Antibiotic pollution levels were more severe in October than in June(P<0.01).Rainfall runoff,aquaculture tailwater,and river discharge were identified as the main sources of antibiotic pollution.Build-up land and aquaculture ponds were the primary land use types contributing to antibiotic pollution.The total antibiotic concentrations in June were positively correlated with the proportion of aquaculture ponds(P<0.05)and negatively correlated with the proportions of cropland and grassland(P<0.05).The concentrations of lomefloxacin and ofloxacin were positively correlated with build-up land.The antibiotic concentrations exhibited strong spatial heterogeneity within both bay and estuarine ecosystems driven by different hydrodynamic conditions.A comparative analysis of global estuaries and bays revealed that specific land-use types and hydrodynamic conditions produced similar trends in antibiotic fate.These insights offered new perspectives to safeguard the health of estuarine and bay ecosystems,such as altering landscape patterns and regulating aquaculture activities.
基金Supported by the National Natural Science Foundation of China(Grant Nos.12361040,12061064)the National Science Foundation of Gansu Province(Grant No.22JR5RA264)State Scholarship Fund(Grant No.20230862021).
文摘In this article,we show the existence,uniqueness and stability of bounded solutions to the following quasilinear problems with mean curvature operator(φ'(x′(t)))′=f(t,x),t≥t_(0),lim_(t→∞)x(t)=ψ_(0),lim_(t→∞)x′(t)e^(t)=0,where t_(0) and ψ_(0) are real constants,φ(s)=s/√1−s^(2),s∈R with s∈(−1,1),f:[t_(0),∞)×R→R satisfies the Lipschitz or Osgood-type conditions.
基金supported in part by the National Science and Technology Council of Republic of China under the contract numbers NSTC 114-2221-E-019-055-MY2NSTC 114-2221-E-019-069.
文摘Cloud data sharing is an important issue in modern times.To maintain the privacy and confidentiality of data stored in the cloud,encryption is an inevitable process before uploading the data.However,the centralized management and transmission latency of the cloud makes it difficult to support real-time processing and distributed access structures.As a result,fog computing and the Internet of Things(IoT)have emerged as crucial applications.Fog-assisted proxy re-encryption is a commonly adopted technique for sharing cloud ciphertexts.It allows a semitrusted proxy to transforma data owner’s ciphertext into another re-encrypted ciphertext intended for a data requester,without compromising any information about the original ciphertext.Yet,the user revocation and cloud ciphertext renewal problems still lack effective and secure mechanisms.Motivated by it,we propose a revocable conditional proxy re-encryption scheme offering ciphertext evolution(R-CPRE-CE).In particular,a periodically updated time key is used to revoke the user’s access privileges while an access condition prevents a malicious proxy from reencrypting unauthorized ciphertext.We also demonstrate that our scheme is provably secure under the notion of indistinguishability against adaptively chosen identity and chosen ciphertext attacks in the random oracle model.Performance analysis shows that our scheme reduces the computation time for a complete data access cycle from an initial query to the final decryption by approximately 47.05%compared to related schemes.
基金financially supported by the National Key R&D Program of China(2023YFC3905400)the Clean Combustion and Low-carbon Utilization of Coal,Strategic Priority Research Program of the Chinese Academy of Sciences,Grant No.XDA 29000000.
文摘The carbonylation of amines offers a promising route for synthesizing N-substituted carbamates with high atom economy.However,conventional catalysts exhibit limited catalytic efficiency,and the underlying proton transfer mechanism remains elusive.Herein,we reported a metal-free,room-temperature strategy utilizing 1,5,7-triazabicyclo[4.4.0]dec-5-ene(TBD)as a dual hydrogen bond catalyst to synergistically activate propylamine(PA)and dimethyl carbonate(DMC).This green catalytic system achieves a 10-fold acceleration in reaction rate compared to other hydrogen bonding catalysts under mild conditions.This is enabled by dual hydrogen bonding of TBD with PA and DMC,which facilitates rapid proton transfer and stabilizes tetrahedral intermediates.Theoretical calculations confirm that the dual hydrogen bond system significantly lowers activation energy compared to single hydrogen bond analogs.Furthermore,it was revealed that the hydrogen bonding network within the product is the primary factor responsible for the sluggish reaction rate.This study demonstrates the effectiveness of a dual hydrogen bond system in accelerating the carbonylation of amines and provides a green route to access carbamates.
基金supported by the National Natural Science Foundation of China(No.52388102)the Sichuan Science and Technology Program(No.2024NSFTD0011)the Fundamental Research Funds for the State Key Laboratory of Rail Transit Vehicle System of Southwest Jiaotong University(No.2023TPL-T11).
文摘The dynamic characteristics of the track system can directly affect its service performance and failure process.To explore the load characteristics and dynamic response of the track system under the dynamic loads from the rack vehicle in traction conditions,a systematic test of the track subsystem was carried out on a large-slope test line.In the test,the bending stress of the rack teeth,the wheel-rail forces,and the acceleration of crucial components in the track system were measured.Subsequently,a detailed analysis was conducted on the tested signals of the rack railway track system in the time domain and the time-frequency domains.The test results indicate that the traction force significantly affects the rack tooth bending stress and the wheel-rail forces.The vibrations of the track system under the traction conditions are mainly caused by the impacts generated from the gear-rack engagement,which are then transferred to the sleepers,the rails,and the ballast beds.Furthermore,both the maximum stress on the racks and the wheel-rail forces measured on the rails remain below their allowable values.This experimental study evaluates the load characteristics and reveals the vibration characteristics of the rack railway track system under the vehicle’s ultimate load,which is very important for the load-strengthening design of the key components such as racks and the vibration and noise reduction of the track system.
基金financially supported by the National Key Research and Development Program of China(2024YFD1700104 and 2022YFE0209200-03)the National Natural Science Foundation of China(42161144002 and 41977156)+3 种基金the Guangxi Natural Science Foundation,China(2022GXNSFBA035625)the Guangxi Technology Base and Talent Subject,China(Guike AD22035927)the Shandong Key Research and Development Project,China(2022TZXD0045)the State Key Laboratory of Earth System Numerical Modeling and Application,Institute of Atmospheric Physics,Chinese Academy of Sciences。
文摘Intervention strategies to control non-point source nitrogen(N)and phosphorus(P)pollution in agriculture are expensive and there is a trade-off between engineering cost and treatment effectiveness.Implementing strategies often result in unsatisfactory outcomes and massive engineering costs when managing diffusive pollution in agricultural catchments.To address this issue,this paper proposes a robust,handy,catchment N&P decision support system(CNPDSS),an Android-based smartphone system integrated with a web-based geographic information system(GIS).The CNPDSS aims to provide artificial intelligence-driven decisions that minimize N&P loadings and engineering costs for mitigating pollution in agricultural catchments.It consists of four components:a general user interface(GUI),GIS,N&P pollution modeling(NPPM),and a DSS.The CNPDSS simplifies the GUI and integrates GIS modules to create a user-friendly interface,enabling non-professional users to operate the system easily through intuitive actions.The NPPM uses straightforward empirical models to predict N&P loadings,enhancing efficiency by avoiding excessive parameters.Taking into account the N&P movement pathway in the catchment,the DSS incorporates three control measures:source reduction in farmland(before migration stage),process retention by ecological ditch(midway transport stage),and down-end purification by constructed wetland(waterbody discharge stage),to formulate a comprehensive ternary controlling strategy.To optimize the cost-effectiveness of any proposed N&P control strategies for sub-catchments,a differential evolution algorithm(DEA)is employed in CNPDSS to carry out a dual-objective decision-making optimization computation.In this study,the CNPDSS is applied to a case study in an agricultural catchment in Central China to develop the most cost-effective ternary N&P control strategies that ensure the catchment water quality within Criterion Ⅲ of the Chinese Surface Water Quality Standard GB3838-2002 is met(total N concentration≤1.0 mg L^(-1)and total P concentration≤0.2 mg L^(-1)).Our results demonstrate that the CNPDSS is feasible and also possesses an adaptive design and flexible architecture to enable its generalization and extension to support strong hands-on applications in other catchments.
文摘In this paper,we study the asymptotic behavior of the micropolar fluid flow through a thin domain,assuming zero Dirichlet boundary condition on the top boundary,which is rapidly oscillating,and non-standard boundary conditions on the flat bottom.Assuming“Reynolds roughness regime”,in which the thickness of the domain is very small compared to the wavelength of the roughness(i.e.a very slight roughness),we rigorously derive a generalized Reynolds equation for pressure,clearly showing the roughness-induced effects.Moreover,we give expressions for the average velocity and microrotation.
基金National Key Research and Development Program of China(2024YFC3505400)Capital Clinical Project of Beijing Municipal Science&Technology Commission(Z221100007422092)Capital’s Funds for Health Improvement and Research(2024-1-2231).
文摘Objective To develop a clinical decision and prescription generation system(CDPGS)specifically for diarrhea in traditional Chinese medicine(TCM),utilizing a specialized large language model(LLM),Qwen-TCM-Dia,to standardize diagnostic processes and prescription generation.Methods Two primary datasets were constructed:an evaluation benchmark and a fine-tuning dataset consisting of fundamental diarrhea knowledge,medical records,and chain-ofthought(CoT)reasoning datasets.After an initial evaluation of 16 open-source LLMs across inference time,accuracy,and output quality,Qwen2.5 was selected as the base model due to its superior overall performance.We then employed a two-stage low-rank adaptation(LoRA)fine-tuning strategy,integrating continued pre-training on domain-specific knowledge with instruction fine-tuning using CoT-enriched medical records.This approach was designed to embed the clinical logic(symptoms→pathogenesis→therapeutic principles→prescriptions)into the model’s reasoning capabilities.The resulting fine-tuned model,specialized for TCM diarrhea,was designated as Qwen-TCM-Dia.Model performance was evaluated for disease diagnosis and syndrome type differentiation using accuracy,precision,recall,and F1-score.Furthermore,the quality of the generated prescriptions was compared with that of established open-source TCM LLMs.Results Qwen-TCM-Dia achieved peak performance compared to both the base Qwen2.5 model and five other open-source TCM LLMs.It achieved 97.05%accuracy and 91.48%F1-score in disease diagnosis,and 74.54%accuracy and 74.21%F1-score in syndrome type differentiation.Compared with existing open-source TCM LLMs(BianCang,HuangDi,LingDan,TCMLLM-PR,and ZhongJing),Qwen-TCM-Dia exhibited higher fidelity in reconstructing the“symptoms→pathogenesis→therapeutic principles→prescriptions”logic chain.It provided complete prescriptions,whereas other models often omitted dosages or generated mismatched prescriptions.Conclusion By integrating continued pre-training,CoT reasoning,and a two-stage fine-tuning strategy,this study establishes a CDPGS for diarrhea in TCM.The results demonstrate the synergistic effect of strengthening domain representation through pre-training and activating logical reasoning via CoT.This research not only provides critical technical support for the standardized diagnosis and treatment of diarrhea but also offers a scalable paradigm for the digital inheritance of expert TCM experience and the intelligent transformation of TCM.
文摘The main purpose of using geothermal energy piles(GEPs)is to enable the exploitation of geothermal energy for meeting the heating/cooling demands of buildings efficiently.However,the installation process of conventional GEPs is inconvenient compared with that of traditional foundation piles.The pre-bored grouted planted geothermal energy pile(PGP GEP)is an innovative technology to simplify the installation process.Most investigations of in-situ experiments for conventional GEPs have focused on summer conditions.An in-situ test for a PGP GEP was conducted to analyze the temperature changes and thermo-mechanical characteristics under winter conditions.The results show that the average temperature of the pile decreased by 5.1℃,and the pile exhibited a general trend of high temperatures at both ends and low temperatures in the middle.In mechanics,strong pile end restraints resulted in smaller observed axial strain and higher axial thermal-induced force in the pile ends than at the middle of the pile.
基金supported by the National Natural Science Foundation of China Funded Project(Project Name:Research on Robust Adaptive Allocation Mechanism of Human Machine Co-Driving System Based on NMS Features,Project Approval Number:52172381).
文摘To address the issue of scarce labeled samples and operational condition variations that degrade the accuracy of fault diagnosis models in variable-condition gearbox fault diagnosis,this paper proposes a semi-supervised masked contrastive learning and domain adaptation(SSMCL-DA)method for gearbox fault diagnosis under variable conditions.Initially,during the unsupervised pre-training phase,a dual signal augmentation strategy is devised,which simultaneously applies random masking in the time domain and random scaling in the frequency domain to unlabeled samples,thereby constructing more challenging positive sample pairs to guide the encoder in learning intrinsic features robust to condition variations.Subsequently,a ConvNeXt-Transformer hybrid architecture is employed,integrating the superior local detail modeling capacity of ConvNeXt with the robust global perception capability of Transformer to enhance feature extraction in complex scenarios.Thereafter,a contrastive learning model is constructed with the optimization objective of maximizing feature similarity across different masked instances of the same sample,enabling the extraction of consistent features from multiple masked perspectives and reducing reliance on labeled data.In the final supervised fine-tuning phase,a multi-scale attention mechanism is incorporated for feature rectification,and a domain adaptation module combining Local Maximum Mean Discrepancy(LMMD)with adversarial learning is proposed.This module embodies a dual mechanism:LMMD facilitates fine-grained class-conditional alignment,compelling features of identical fault classes to converge across varying conditions,while the domain discriminator utilizes adversarial training to guide the feature extractor toward learning domain-invariant features.Working in concert,they markedly diminish feature distribution discrepancies induced by changes in load,rotational speed,and other factors,thereby boosting the model’s adaptability to cross-condition scenarios.Experimental evaluations on the WT planetary gearbox dataset and the Case Western Reserve University(CWRU)bearing dataset demonstrate that the SSMCL-DA model effectively identifies multiple fault classes in gearboxes,with diagnostic performance substantially surpassing that of conventional methods.Under cross-condition scenarios,the model attains fault diagnosis accuracies of 99.21%for the WT planetary gearbox and 99.86%for the bearings,respectively.Furthermore,the model exhibits stable generalization capability in cross-device settings.
基金supported by the Chung-Ang University Research Grants in 2023.Alsothe work is supported by the ELLIIT Excellence Center at Linköping–Lund in Information Technology in Sweden.
文摘Recommending personalized travel routes from sparse,implicit feedback poses a significant challenge,as conventional systems often struggle with information overload and fail to capture the complex,sequential nature of user preferences.To address this,we propose a Conditional Generative Adversarial Network(CGAN)that generates diverse and highly relevant itineraries.Our approach begins by constructing a conditional vector that encapsulates a user’s profile.This vector uniquely fuses embeddings from a Heterogeneous Information Network(HIN)to model complex user-place-route relationships,a Recurrent Neural Network(RNN)to capture sequential path dynamics,and Neural Collaborative Filtering(NCF)to incorporate collaborative signals from the wider user base.This comprehensive condition,further enhanced with features representing user interaction confidence and uncertainty,steers a CGAN stabilized by spectral normalization to generate high-fidelity latent route representations,effectively mitigating the data sparsity problem.Recommendations are then formulated using an Anchor-and-Expand algorithm,which selects relevant starting Points of Interest(POI)based on user history,then expands routes through latent similarity matching and geographic coherence optimization,culminating in Traveling Salesman Problem(TSP)-based route optimization for practical travel distances.Experiments on a real-world check-in dataset validate our model’s unique generative capability,achieving F1 scores ranging from 0.163 to 0.305,and near-zero pairs−F1 scores between 0.002 and 0.022.These results confirm the model’s success in generating novel travel routes by recommending new locations and sequences rather than replicating users’past itineraries.This work provides a robust solution for personalized travel planning,capable of generating novel and compelling routes for both new and existing users by learning from collective travel intelligence.
