AIM:To build a functional generalized estimating equation(GEE)model to detect glaucomatous visual field progression and compare the performance of the proposed method with that of commonly employed algorithms.METHODS:...AIM:To build a functional generalized estimating equation(GEE)model to detect glaucomatous visual field progression and compare the performance of the proposed method with that of commonly employed algorithms.METHODS:Totally 716 eyes of 716 patients with primary open angle glaucoma(POAG)with at least 5 reliable 24-2 test results and 2y of follow-up were selected.The functional GEE model was used to detect perimetric progression in the training dataset(501 eyes).In the testing dataset(215 eyes),progression was evaluated the functional GEE model,mean deviation(MD)and visual field index(VFI)rates of change,Advanced Glaucoma Intervention Study(AGIS)and Collaborative Initial Glaucoma Treatment Study(CIGTS)scores,and pointwise linear regression(PLR).RESULTS:The proposed method showed the highest proportion of eyes detected as progression(54.4%),followed by the VFI rate(34.4%),PLR(23.3%),and MD rate(21.4%).The CIGTS and AGIS scores had a lower proportion of eyes detected as progression(7.9%and 5.1%,respectively).The time to detection of progression was significantly shorter for the proposed method than that of other algorithms(adjusted P≤0.019).The VFI rate displayed moderate pairwise agreement with the proposed method(k=0.47).CONCLUSION:The functional GEE model shows the highest proportion of eyes detected as perimetric progression and the shortest time to detect perimetric progression in patients with POAG.展开更多
This study explores a novel educational model of generative AI-empowered interdisciplinary project-based learning(PBL).By analyzing the current applications of generative AI technology in information technology curric...This study explores a novel educational model of generative AI-empowered interdisciplinary project-based learning(PBL).By analyzing the current applications of generative AI technology in information technology curricula,it elucidates its advantages and operational mechanisms in interdisciplinary PBL.Combining case studies and empirical research,the investigation proposes implementation pathways and strategies for the generative AI-enhanced interdisciplinary PBL model,detailing specific applications across three phases:project preparation,implementation,and evaluation.The research demonstrates that generative AI-enabled interdisciplinary project-based learning can effectively enhance students’learning motivation,interdisciplinary thinking capabilities,and innovative competencies,providing new conceptual frameworks and practical approaches for educational model innovation.展开更多
Over the past century,advancements in chemistry have significantly propelled human innovation,enhancing both industrial and consumer products.However,this rapid progression has resulted in chemical pollution increasin...Over the past century,advancements in chemistry have significantly propelled human innovation,enhancing both industrial and consumer products.However,this rapid progression has resulted in chemical pollution increasingly surpassing planetary boundaries,as production and release rates have outpaced our monitoring capabilities.To catalyze more impactful efforts,this study transitions from traditional chemical assessment to inverse chemical design,introducing a generative graph latent diffusion model aimed at discovering safer alternatives.In a case study on the design of green solvents for cyclohexane/benzene extraction distillation,we constructed a design database encompassing functional,environmental hazards,and process constraints.Virtual screening of previous design dataset revealed distinct trade-off trends between these design requirements.Based on the screening outcomes,an unconstrained generative model was developed,which covered a broader chemical space and demonstrated superior capabilities for structural interpolation and extrapolation.To further optimize molecular generation towards desired properties,a multi-objective latent diffusion method was applied,yielding 19 candidate molecules.Of these,7 were identified in PubChem as the most viable green solvent candidates,while the remaining 12 as potential novel candidates.Overall,this study effectively designed green solvent candidates for safer and more sustainable industrial production,setting a promising precedent for the development of environmentally friendly alternatives in other areas of chemical research.展开更多
The growing demand for wireless connectivity has made massive multiple-input multiple-output(MIMO)a cornerstone of modern communication systems.To optimize network performance and resource allocation,an efficient and ...The growing demand for wireless connectivity has made massive multiple-input multiple-output(MIMO)a cornerstone of modern communication systems.To optimize network performance and resource allocation,an efficient and robust approach is joint device activity detection and channel estimation.In this paper,we present an approach utilizing score-based generative models to address the underdetermined nature of channel estimation,which is data-driven and well-suited for the complex and dynamic environment of massive MIMO systems.Our experimental results,based on a comprehensive dataset generated through Monte-Carlo sampling,demonstrate the high precision of our channel estimation approach,with errors reduced to as low as-45 d B,and exceptional accuracy in detecting active devices.展开更多
This study focuses on the construction and application of intelligent financial decision-making models driven by generative artificial intelligence(AI).It analyzes the mechanisms by which generative AI empowers financ...This study focuses on the construction and application of intelligent financial decision-making models driven by generative artificial intelligence(AI).It analyzes the mechanisms by which generative AI empowers financial decision-making within a dual framework of dynamic knowledge evolution and risk control.The research reveals that generative AI,with its superior data processing,pattern recognition,and autonomous learning capabilities,can transcend the limitations of traditional decision-making models,facilitating a significant shift from causal inference to probabilistic creation in decision-making paradigms.By systematically constructing an intelligent financial decision-making model that includes data governance,core engine,and decision output layers,the study clarifies the functional roles and collaborative mechanisms of each layer.Additionally,it addresses key challenges in technology application,institutional adaptation,and organizational transformation by proposing systematic strategies for technical risk management,institutional innovation,and organizational capability enhancement,aiming to provide robust theoretical support and practical guidance for the intelligent transformation of corporate financial decision-making.展开更多
Inverse design has long been an efficient and powerful design tool in the aircraft industry.In this paper,a novel inverse design method for supercritical airfoils is proposed based on generative models in deep learnin...Inverse design has long been an efficient and powerful design tool in the aircraft industry.In this paper,a novel inverse design method for supercritical airfoils is proposed based on generative models in deep learning.A Conditional Variational Auto Encoder(CVAE)and an integrated generative network CVAE-GAN that combines the CVAE with the Wasserstein Generative Adversarial Networks(WGAN),are conducted as generative models.They are used to generate target wall Mach distributions for the inverse design that matches specified features,such as locations of suction peak,shock and aft loading.Qualitative and quantitative results show that both adopted generative models can generate diverse and realistic wall Mach number distributions satisfying the given features.The CVAE-GAN model outperforms the CVAE model and achieves better reconstruction accuracies for all the samples in the dataset.Furthermore,a deep neural network for nonlinear mapping is adopted to obtain the airfoil shape corresponding to the target wall Mach number distribution.The performances of the designed deep neural network are fully demonstrated and a smoothness measurement is proposed to quantify small oscillations in the airfoil surface,proving the authenticity and accuracy of the generated airfoil shapes.展开更多
Recently,diffusion models have emerged as a promising paradigm for molecular design and optimization.However,most diffusion-based molecular generative models focus on modeling 2D graphs or 3D geom-etries,with limited ...Recently,diffusion models have emerged as a promising paradigm for molecular design and optimization.However,most diffusion-based molecular generative models focus on modeling 2D graphs or 3D geom-etries,with limited research on molecular sequence diffusion models.The International Union of Pure and Applied Chemistry(IUPAC)names are more akin to chemical natural language than the simplified molecular input line entry system(SMILES)for organic compounds.In this work,we apply an IUPAC-guided conditional diffusion model to facilitate molecular editing from chemical natural language to chemical language(SMILES)and explore whether the pre-trained generative performance of diffusion models can be transferred to chemical natural language.We propose DiffIUPAC,a controllable molecular editing diffusion model that converts IUPAC names to SMILES strings.Evaluation results demonstrate that our model out-performs existing methods and successfully captures the semantic rules of both chemical languages.Chemical space and scaffold analysis show that the model can generate similar compounds with diverse scaffolds within the specified constraints.Additionally,to illustrate the model’s applicability in drug design,we conducted case studies in functional group editing,analogue design and linker design.展开更多
Integration of digital twin(DT)and wireless channel provides new solution of channel modeling and simulation,and can assist to design,optimize and evaluate intelligent wireless communication system and networks.With D...Integration of digital twin(DT)and wireless channel provides new solution of channel modeling and simulation,and can assist to design,optimize and evaluate intelligent wireless communication system and networks.With DT channel modeling,the generated channel data can be closer to realistic channel measurements without requiring a prior channel model,and amount of channel data can be significantly increased.Artificial intelligence(AI)based modeling approach shows outstanding performance to solve such problems.In this work,a channel modeling method based on generative adversarial networks is proposed for DT channel,which can generate identical statistical distribution with measured channel.Model validation is conducted by comparing DT channel characteristics with measurements,and results show that DT channel leads to fairly good agreement with measured channel.Finally,a link-layer simulation is implemented based on DT channel.It is found that the proposed DT channel model can be well used to conduct link-layer simulation and its performance is comparable to using measurement data.The observations and results can facilitate the development of DT channel modeling and provide new thoughts for DT channel applications,as well as improving the performance and reliability of intelligent communication networking.展开更多
For reservoirs with complex non-Gaussian geological characteristics,such as carbonate reservoirs or reservoirs with sedimentary facies distribution,it is difficult to implement history matching directly,especially for...For reservoirs with complex non-Gaussian geological characteristics,such as carbonate reservoirs or reservoirs with sedimentary facies distribution,it is difficult to implement history matching directly,especially for the ensemble-based data assimilation methods.In this paper,we propose a multi-source information fused generative adversarial network(MSIGAN)model,which is used for parameterization of the complex geologies.In MSIGAN,various information such as facies distribution,microseismic,and inter-well connectivity,can be integrated to learn the geological features.And two major generative models in deep learning,variational autoencoder(VAE)and generative adversarial network(GAN)are combined in our model.Then the proposed MSIGAN model is integrated into the ensemble smoother with multiple data assimilation(ESMDA)method to conduct history matching.We tested the proposed method on two reservoir models with fluvial facies.The experimental results show that the proposed MSIGAN model can effectively learn the complex geological features,which can promote the accuracy of history matching.展开更多
In this paper,we propose a novel coverless image steganographic scheme based on a generative model.In our scheme,the secret image is first fed to the generative model database,to generate a meaning-normal and independ...In this paper,we propose a novel coverless image steganographic scheme based on a generative model.In our scheme,the secret image is first fed to the generative model database,to generate a meaning-normal and independent image different from the secret image.The generated image is then transmitted to the receiver and fed to the generative model database to generate another image visually the same as the secret image.Thus,we only need to transmit the meaning-normal image which is not related to the secret image,and we can achieve the same effect as the transmission of the secret image.This is the first time to propose the coverless image information steganographic scheme based on generative model,compared with the traditional image steganography.The transmitted image is not embedded with any information of the secret image in this method,therefore,can effectively resist steganalysis tools.Experimental results show that our scheme has high capacity,security and reliability.展开更多
Brain encoding and decoding via functional magnetic resonance imaging(fMRI)are two important aspects of visual perception neuroscience.Although previous researchers have made significant advances in brain encoding and...Brain encoding and decoding via functional magnetic resonance imaging(fMRI)are two important aspects of visual perception neuroscience.Although previous researchers have made significant advances in brain encoding and decoding models,existing methods still require improvement using advanced machine learning techniques.For example,traditional methods usually build the encoding and decoding models separately,and are prone to overfitting on a small dataset.In fact,effectively unifying the encoding and decoding procedures may allow for more accurate predictions.In this paper,we first review the existing encoding and decoding methods and discuss the potential advantages of a“bidirectional”modeling strategy.Next,we show that there are correspondences between deep neural networks and human visual streams in terms of the architecture and computational rules.Furthermore,deep generative models(e.g.,variational autoencoders(VAEs)and generative adversarial networks(GANs))have produced promising results in studies on brain encoding and decoding.Finally,we propose that the dual learning method,which was originally designed for machine translation tasks,could help to improve the performance of encoding and decoding models by leveraging large-scale unpaired data.展开更多
Climate models are vital for understanding and projecting global climate change and its associated impacts.However,these models suffer from biases that limit their accuracy in historical simulations and the trustworth...Climate models are vital for understanding and projecting global climate change and its associated impacts.However,these models suffer from biases that limit their accuracy in historical simulations and the trustworthiness of future projections.Addressing these challenges requires addressing internal variability,hindering the direct alignment between model simulations and observations,and thwarting conventional supervised learning methods.Here,we employ an unsupervised Cycle-consistent Generative Adversarial Network(CycleGAN),to correct daily Sea Surface Temperature(SST)simulations from the Community Earth System Model 2(CESM2).Our results reveal that the CycleGAN not only corrects climatological biases but also improves the simulation of major dynamic modes including the El Niño-Southern Oscillation(ENSO)and the Indian Ocean Dipole mode,as well as SST extremes.Notably,it substantially corrects climatological SST biases,decreasing the globally averaged Root-Mean-Square Error(RMSE)by 58%.Intriguingly,the CycleGAN effectively addresses the well-known excessive westward bias in ENSO SST anomalies,a common issue in climate models that traditional methods,like quantile mapping,struggle to rectify.Additionally,it substantially improves the simulation of SST extremes,raising the pattern correlation coefficient(PCC)from 0.56 to 0.88 and lowering the RMSE from 0.5 to 0.32.This enhancement is attributed to better representations of interannual,intraseasonal,and synoptic scales variabilities.Our study offers a novel approach to correct global SST simulations and underscores its effectiveness across different time scales and primary dynamical modes.展开更多
Natural products（NPs） have long been recognized as a valuable resource for drug discovery, and bringing NP-related features to virtual libraries is believed to be an effective way to increase the coverage of druggab...Natural products（NPs） have long been recognized as a valuable resource for drug discovery, and bringing NP-related features to virtual libraries is believed to be an effective way to increase the coverage of druggable chemical space. Here, deep learning-based molecule generative model, which is a recent technique in de novo molecule design, was applied to generate virtual libraries with NP-like properties. Results demonstrated that the model was effective in generating molecules that highly resemble NPs. Moreover, the model was also found to be capable of generating NP-like molecules that were also easy to synthesize, significantly increasing the practical value of the compound library.展开更多
Objective This study aimed to evaluate and compare the effectiveness of knowledge base-optimized and unoptimized large language models(LLMs)in the field of orthopedics to explore optimization strategies for the applic...Objective This study aimed to evaluate and compare the effectiveness of knowledge base-optimized and unoptimized large language models(LLMs)in the field of orthopedics to explore optimization strategies for the application of LLMs in specific fields.Methods This research constructed a specialized knowledge base using clinical guidelines from the American Academy of Orthopaedic Surgeons(AAOS)and authoritative orthopedic publications.A total of 30 orthopedic-related questions covering aspects such as anatomical knowledge,disease diagnosis,fracture classification,treatment options,and surgical techniques were input into both the knowledge base-optimized and unoptimized versions of the GPT-4,ChatGLM,and Spark LLM,with their generated responses recorded.The overall quality,accuracy,and comprehensiveness of these responses were evaluated by 3 experienced orthopedic surgeons.Results Compared with their unoptimized LLMs,the optimized version of GPT-4 showed improvements of 15.3%in overall quality,12.5%in accuracy,and 12.8%in comprehensiveness;ChatGLM showed improvements of 24.8%,16.1%,and 19.6%,respectively;and Spark LLM showed improvements of 6.5%,14.5%,and 24.7%,respectively.Conclusion The optimization of knowledge bases significantly enhances the quality,accuracy,and comprehensiveness of the responses provided by the 3 models in the orthopedic field.Therefore,knowledge base optimization is an effective method for improving the performance of LLMs in specific fields.展开更多
Intelligent sorting is an important prerequisite for the full quantitative consumption and harmless disposal of kitchen waste.The existing object detection method based on an ImageNet pre-trained model is an effective...Intelligent sorting is an important prerequisite for the full quantitative consumption and harmless disposal of kitchen waste.The existing object detection method based on an ImageNet pre-trained model is an effective way of sorting.Owing to significant domain gaps between natural images and kitchen waste images,it is difficult to reflect the characteristics of diverse scales and dense distribution in kitchen waste based on an ImageNet pre-trained model,leading to poor generalisation.In this article,the authors propose the first pre-trained model for kitchen waste sorting called KitWaSor,which combines both contrastive learning(CL)and masked image modelling(MIM)through self-supervised learning(SSL).First,to address the issue of diverse scales,the authors propose a mixed masking strategy by introducing an incomplete masking branch based on the original random masking branch.It prevents the complete loss of small-scale objects while avoiding excessive leakage of large-scale object pixels.Second,to address the issue of dense distribution,the authors introduce semantic consistency constraints on the basis of the mixed masking strategy.That is,object semantic reasoning is performed through semantic consistency constraints to compensate for the lack of contextual information.To train KitWaSor,the authors construct the first million-level kitchen waste dataset across seasonal and regional distributions,named KWD-Million.Extensive experiments show that KitWaSor achieves state-of-the-art(SOTA)performance on the two most relevant downstream tasks for kitchen waste sorting(i.e.image classification and object detection),demonstrating the effectiveness of the proposed KitWaSor.展开更多
Predicting cross-immunity between viral strains is vital for public health surveillance and vaccine development.Traditional neural network methods,such as BiLSTM,could be ineffective due to the lack of lab data for mo...Predicting cross-immunity between viral strains is vital for public health surveillance and vaccine development.Traditional neural network methods,such as BiLSTM,could be ineffective due to the lack of lab data for model training and the overshadowing of crucial features within sequence concatenation.The current work proposes a less data-consuming model incorporating a pre-trained gene sequence model and a mutual information inference operator.Our methodology utilizes gene alignment and deduplication algorithms to preprocess gene sequences,enhancing the model’s capacity to discern and focus on distinctions among input gene pairs.The model,i.e.,DNA Pretrained Cross-Immunity Protection Inference model(DPCIPI),outperforms state-of-theart(SOTA)models in predicting hemagglutination inhibition titer from influenza viral gene sequences only.Improvement in binary cross-immunity prediction is 1.58%in F1,2.34%in precision,1.57%in recall,and 1.57%in Accuracy.For multilevel cross-immunity improvements,the improvement is 2.12%in F1,3.50%in precision,2.19%in recall,and 2.19%in Accuracy.Our study showcases the potential of pre-trained gene models to improve predictions of antigenic variation and cross-immunity.With expanding gene data and advancements in pre-trained models,this approach promises significant impacts on vaccine development and public health.展开更多
With the miniaturization of devices and the development of modern heating technologies,the generalization of heat conduction and thermoelastic coupling has become crucial,effectively emulating the thermodynamic behavi...With the miniaturization of devices and the development of modern heating technologies,the generalization of heat conduction and thermoelastic coupling has become crucial,effectively emulating the thermodynamic behavior of materials in ultrashort time scales.Theoretically,generalized heat conductive models are considered in this work.By analogy with mechanical viscoelastic models,this paper further enriches the heat conduction models and gives their one-dimensional physical expression.Numerically,the transient thermoelastic response of the slim strip material under thermal shock is investigated by applying the proposed models.First,the analytical solution in the Laplace domain is obtained by the Laplace transform.Then,the numerical results of the transient responses are obtained by the numerical inverse Laplace transform.Finally,the transient responses of different models are analyzed and compared,and the effects of material parameters are discussed.This work not only opens up new research perspectives on generalized heat conductive and thermoelastic coupling theories,but also is expected to be beneficial for the deeper understanding of the heat wave theory.展开更多
We analyze the suitability of existing pre-trained transformer-based language models(PLMs)for abstractive text summarization on German technical healthcare texts.The study focuses on the multilingual capabilities of t...We analyze the suitability of existing pre-trained transformer-based language models(PLMs)for abstractive text summarization on German technical healthcare texts.The study focuses on the multilingual capabilities of these models and their ability to perform the task of abstractive text summarization in the healthcare field.The research hypothesis was that large language models could perform high-quality abstractive text summarization on German technical healthcare texts,even if the model is not specifically trained in that language.Through experiments,the research questions explore the performance of transformer language models in dealing with complex syntax constructs,the difference in performance between models trained in English and German,and the impact of translating the source text to English before conducting the summarization.We conducted an evaluation of four PLMs(GPT-3,a translation-based approach also utilizing GPT-3,a German language Model,and a domain-specific bio-medical model approach).The evaluation considered the informativeness using 3 types of metrics based on Recall-Oriented Understudy for Gisting Evaluation(ROUGE)and the quality of results which is manually evaluated considering 5 aspects.The results show that text summarization models could be used in the German healthcare domain and that domain-independent language models achieved the best results.The study proves that text summarization models can simplify the search for pre-existing German knowledge in various domains.展开更多
Two dimensional(2D) materials based on boron and carbon have attracted wide attention due to their unique properties. BC compounds have rich active sites and diverse chemical coordination, showing great potential in o...Two dimensional(2D) materials based on boron and carbon have attracted wide attention due to their unique properties. BC compounds have rich active sites and diverse chemical coordination, showing great potential in optoelectronic applications. However, due to the limitation of calculation and experimental conditions, it is still a challenging task to predict new 2D BC monolayer materials. Specifically, we utilized Crystal Diffusion Variational Autoencoder(CDVAE) and pre-trained Materials Graph Neural Network with 3-Body Interactions(M3GNet) model to generate novel and stable BCP materials. Each crystal structure was treated as a high-dimensional vector, where the encoder extracted lattice information and element coordinates, mapping the high-dimensional data into a low-dimensional latent space. The decoder then reconstructed the latent representation back into the original data space. Additionally, our designed attribute predictor network combined the advantages of dilated convolutions and residual connections,effectively increasing the model's receptive field and learning capacity while maintaining relatively low parameter count and computational complexity. By progressively increasing the dilation rate, the model can capture features at different scales. We used the DFT data set of about 1600 BCP monolayer materials to train the diffusion model, and combined with the pre-trained M3GNet model to screen the best candidate structure. Finally, we used DFT calculations to confirm the stability of the candidate structure.The results show that the combination of generative deep learning model and attribute prediction model can help accelerate the discovery and research of new 2D materials, and provide effective methods for exploring the inverse design of new two-dimensional materials.展开更多
With the rapid development of generative artificial intelligence technology,the traditional cloud-based centralized model training and inference face significant limitations due to high transmission latency and costs,...With the rapid development of generative artificial intelligence technology,the traditional cloud-based centralized model training and inference face significant limitations due to high transmission latency and costs,which restrict user-side in-situ Artificial Intelligence Generated Content(AIGC)service requests.To this end,we propose the Edge Artificial Intelligence Generated Content(Edge AIGC)framework,which can effectively address the challenges of cloud computing by implementing in-situ processing of services close to the data source through edge computing.However,AIGC models usually have a large parameter scale and complex computing requirements,which poses a huge challenge to the storage and computing resources of edge devices.This paper focuses on the edge intelligence model caching and resource allocation problems in the Edge AIGC framework,aiming to improve the cache hit rate and resource utilization of edge devices for models by optimizing the model caching strategy and resource allocation scheme,and realize in-situ AIGC service processing.With the optimization objectives of minimizing service request response time and execution cost in resource-constrained environments,we employ the Twin Delayed Deep Deterministic Policy Gradient algorithm for optimization.Experimental results show that,compared with other methods,our model caching and resource allocation strategies can effectively improve the cache hit rate by at least 41.06%and reduce the response cost as well.展开更多
基金Supported by the Korea Health Technology R&D Project through the Korea Health Industry Development Institute(KHIDI),funded by the Ministry of Health&Welfare,Republic of Korea(No.HR20C0026)the National Research Foundation of Korea(NRF)(No.RS-2023-00247504)the Patient-Centered Clinical Research Coordinating Center,funded by the Ministry of Health&Welfare,Republic of Korea(No.HC19C0276).
文摘AIM:To build a functional generalized estimating equation(GEE)model to detect glaucomatous visual field progression and compare the performance of the proposed method with that of commonly employed algorithms.METHODS:Totally 716 eyes of 716 patients with primary open angle glaucoma(POAG)with at least 5 reliable 24-2 test results and 2y of follow-up were selected.The functional GEE model was used to detect perimetric progression in the training dataset(501 eyes).In the testing dataset(215 eyes),progression was evaluated the functional GEE model,mean deviation(MD)and visual field index(VFI)rates of change,Advanced Glaucoma Intervention Study(AGIS)and Collaborative Initial Glaucoma Treatment Study(CIGTS)scores,and pointwise linear regression(PLR).RESULTS:The proposed method showed the highest proportion of eyes detected as progression(54.4%),followed by the VFI rate(34.4%),PLR(23.3%),and MD rate(21.4%).The CIGTS and AGIS scores had a lower proportion of eyes detected as progression(7.9%and 5.1%,respectively).The time to detection of progression was significantly shorter for the proposed method than that of other algorithms(adjusted P≤0.019).The VFI rate displayed moderate pairwise agreement with the proposed method(k=0.47).CONCLUSION:The functional GEE model shows the highest proportion of eyes detected as perimetric progression and the shortest time to detect perimetric progression in patients with POAG.
文摘This study explores a novel educational model of generative AI-empowered interdisciplinary project-based learning(PBL).By analyzing the current applications of generative AI technology in information technology curricula,it elucidates its advantages and operational mechanisms in interdisciplinary PBL.Combining case studies and empirical research,the investigation proposes implementation pathways and strategies for the generative AI-enhanced interdisciplinary PBL model,detailing specific applications across three phases:project preparation,implementation,and evaluation.The research demonstrates that generative AI-enabled interdisciplinary project-based learning can effectively enhance students’learning motivation,interdisciplinary thinking capabilities,and innovative competencies,providing new conceptual frameworks and practical approaches for educational model innovation.
基金supported by Shanghai Science and Technology Commission Project(No.21DZ1201502)Shanghai Municipal Bureau of Ecology and Environment(Shanghai Environ-mental Science[2023]No.40)+1 种基金the Interdisciplinary Joint Research Project of Tongji University(No.2022-4-YB-12)Shanghai Science and Technology Commission Project(No.22DZ2200200).
文摘Over the past century,advancements in chemistry have significantly propelled human innovation,enhancing both industrial and consumer products.However,this rapid progression has resulted in chemical pollution increasingly surpassing planetary boundaries,as production and release rates have outpaced our monitoring capabilities.To catalyze more impactful efforts,this study transitions from traditional chemical assessment to inverse chemical design,introducing a generative graph latent diffusion model aimed at discovering safer alternatives.In a case study on the design of green solvents for cyclohexane/benzene extraction distillation,we constructed a design database encompassing functional,environmental hazards,and process constraints.Virtual screening of previous design dataset revealed distinct trade-off trends between these design requirements.Based on the screening outcomes,an unconstrained generative model was developed,which covered a broader chemical space and demonstrated superior capabilities for structural interpolation and extrapolation.To further optimize molecular generation towards desired properties,a multi-objective latent diffusion method was applied,yielding 19 candidate molecules.Of these,7 were identified in PubChem as the most viable green solvent candidates,while the remaining 12 as potential novel candidates.Overall,this study effectively designed green solvent candidates for safer and more sustainable industrial production,setting a promising precedent for the development of environmentally friendly alternatives in other areas of chemical research.
文摘The growing demand for wireless connectivity has made massive multiple-input multiple-output(MIMO)a cornerstone of modern communication systems.To optimize network performance and resource allocation,an efficient and robust approach is joint device activity detection and channel estimation.In this paper,we present an approach utilizing score-based generative models to address the underdetermined nature of channel estimation,which is data-driven and well-suited for the complex and dynamic environment of massive MIMO systems.Our experimental results,based on a comprehensive dataset generated through Monte-Carlo sampling,demonstrate the high precision of our channel estimation approach,with errors reduced to as low as-45 d B,and exceptional accuracy in detecting active devices.
文摘This study focuses on the construction and application of intelligent financial decision-making models driven by generative artificial intelligence(AI).It analyzes the mechanisms by which generative AI empowers financial decision-making within a dual framework of dynamic knowledge evolution and risk control.The research reveals that generative AI,with its superior data processing,pattern recognition,and autonomous learning capabilities,can transcend the limitations of traditional decision-making models,facilitating a significant shift from causal inference to probabilistic creation in decision-making paradigms.By systematically constructing an intelligent financial decision-making model that includes data governance,core engine,and decision output layers,the study clarifies the functional roles and collaborative mechanisms of each layer.Additionally,it addresses key challenges in technology application,institutional adaptation,and organizational transformation by proposing systematic strategies for technical risk management,institutional innovation,and organizational capability enhancement,aiming to provide robust theoretical support and practical guidance for the intelligent transformation of corporate financial decision-making.
基金co-supported by the National Key Project of China(No.GJXM92579)the National Natural Science Foundation of China(Nos.92052203,61903178 and61906081)。
文摘Inverse design has long been an efficient and powerful design tool in the aircraft industry.In this paper,a novel inverse design method for supercritical airfoils is proposed based on generative models in deep learning.A Conditional Variational Auto Encoder(CVAE)and an integrated generative network CVAE-GAN that combines the CVAE with the Wasserstein Generative Adversarial Networks(WGAN),are conducted as generative models.They are used to generate target wall Mach distributions for the inverse design that matches specified features,such as locations of suction peak,shock and aft loading.Qualitative and quantitative results show that both adopted generative models can generate diverse and realistic wall Mach number distributions satisfying the given features.The CVAE-GAN model outperforms the CVAE model and achieves better reconstruction accuracies for all the samples in the dataset.Furthermore,a deep neural network for nonlinear mapping is adopted to obtain the airfoil shape corresponding to the target wall Mach number distribution.The performances of the designed deep neural network are fully demonstrated and a smoothness measurement is proposed to quantify small oscillations in the airfoil surface,proving the authenticity and accuracy of the generated airfoil shapes.
基金supported by the Yonsei University graduate school Department of Integrative Biotechnology.
文摘Recently,diffusion models have emerged as a promising paradigm for molecular design and optimization.However,most diffusion-based molecular generative models focus on modeling 2D graphs or 3D geom-etries,with limited research on molecular sequence diffusion models.The International Union of Pure and Applied Chemistry(IUPAC)names are more akin to chemical natural language than the simplified molecular input line entry system(SMILES)for organic compounds.In this work,we apply an IUPAC-guided conditional diffusion model to facilitate molecular editing from chemical natural language to chemical language(SMILES)and explore whether the pre-trained generative performance of diffusion models can be transferred to chemical natural language.We propose DiffIUPAC,a controllable molecular editing diffusion model that converts IUPAC names to SMILES strings.Evaluation results demonstrate that our model out-performs existing methods and successfully captures the semantic rules of both chemical languages.Chemical space and scaffold analysis show that the model can generate similar compounds with diverse scaffolds within the specified constraints.Additionally,to illustrate the model’s applicability in drug design,we conducted case studies in functional group editing,analogue design and linker design.
基金supported by National Key R&D Program of China under Grant 2021YFB3901302 and 2021YFB2900301the National Natural Science Foundation of China under Grant 62271037,62001519,62221001,and U21A20445+1 种基金the State Key Laboratory of Advanced Rail Autonomous Operation under Grant RCS2022ZZ004the Fundamental Research Funds for the Central Universities under Grant 2022JBQY004.
文摘Integration of digital twin(DT)and wireless channel provides new solution of channel modeling and simulation,and can assist to design,optimize and evaluate intelligent wireless communication system and networks.With DT channel modeling,the generated channel data can be closer to realistic channel measurements without requiring a prior channel model,and amount of channel data can be significantly increased.Artificial intelligence(AI)based modeling approach shows outstanding performance to solve such problems.In this work,a channel modeling method based on generative adversarial networks is proposed for DT channel,which can generate identical statistical distribution with measured channel.Model validation is conducted by comparing DT channel characteristics with measurements,and results show that DT channel leads to fairly good agreement with measured channel.Finally,a link-layer simulation is implemented based on DT channel.It is found that the proposed DT channel model can be well used to conduct link-layer simulation and its performance is comparable to using measurement data.The observations and results can facilitate the development of DT channel modeling and provide new thoughts for DT channel applications,as well as improving the performance and reliability of intelligent communication networking.
基金supported by the National Natural Science Foundation of China under Grant 51722406,52074340,and 51874335the Shandong Provincial Natural Science Foundation under Grant JQ201808+5 种基金The Fundamental Research Funds for the Central Universities under Grant 18CX02097Athe Major Scientific and Technological Projects of CNPC under Grant ZD2019-183-008the Science and Technology Support Plan for Youth Innovation of University in Shandong Province under Grant 2019KJH002the National Research Council of Science and Technology Major Project of China under Grant 2016ZX05025001-006111 Project under Grant B08028Sinopec Science and Technology Project under Grant P20050-1
文摘For reservoirs with complex non-Gaussian geological characteristics,such as carbonate reservoirs or reservoirs with sedimentary facies distribution,it is difficult to implement history matching directly,especially for the ensemble-based data assimilation methods.In this paper,we propose a multi-source information fused generative adversarial network(MSIGAN)model,which is used for parameterization of the complex geologies.In MSIGAN,various information such as facies distribution,microseismic,and inter-well connectivity,can be integrated to learn the geological features.And two major generative models in deep learning,variational autoencoder(VAE)and generative adversarial network(GAN)are combined in our model.Then the proposed MSIGAN model is integrated into the ensemble smoother with multiple data assimilation(ESMDA)method to conduct history matching.We tested the proposed method on two reservoir models with fluvial facies.The experimental results show that the proposed MSIGAN model can effectively learn the complex geological features,which can promote the accuracy of history matching.
基金This paper was supported by the National Natural Science Foundation of China(No.U1204606)the Key Programs for Science and Technology Development of Henan Province(No.172102210335)Key Scientific Research Projects in Henan Universities(No.16A520058).
文摘In this paper,we propose a novel coverless image steganographic scheme based on a generative model.In our scheme,the secret image is first fed to the generative model database,to generate a meaning-normal and independent image different from the secret image.The generated image is then transmitted to the receiver and fed to the generative model database to generate another image visually the same as the secret image.Thus,we only need to transmit the meaning-normal image which is not related to the secret image,and we can achieve the same effect as the transmission of the secret image.This is the first time to propose the coverless image information steganographic scheme based on generative model,compared with the traditional image steganography.The transmitted image is not embedded with any information of the secret image in this method,therefore,can effectively resist steganalysis tools.Experimental results show that our scheme has high capacity,security and reliability.
基金This work was supported by the National Key Research and Development Program of China(2018YFC2001302)National Natural Science Foundation of China(91520202)+2 种基金Chinese Academy of Sciences Scientific Equipment Development Project(YJKYYQ20170050)Beijing Municipal Science and Technology Commission(Z181100008918010)Youth Innovation Promotion Association of Chinese Academy of Sciences,and Strategic Priority Research Program of Chinese Academy of Sciences(XDB32040200).
文摘Brain encoding and decoding via functional magnetic resonance imaging(fMRI)are two important aspects of visual perception neuroscience.Although previous researchers have made significant advances in brain encoding and decoding models,existing methods still require improvement using advanced machine learning techniques.For example,traditional methods usually build the encoding and decoding models separately,and are prone to overfitting on a small dataset.In fact,effectively unifying the encoding and decoding procedures may allow for more accurate predictions.In this paper,we first review the existing encoding and decoding methods and discuss the potential advantages of a“bidirectional”modeling strategy.Next,we show that there are correspondences between deep neural networks and human visual streams in terms of the architecture and computational rules.Furthermore,deep generative models(e.g.,variational autoencoders(VAEs)and generative adversarial networks(GANs))have produced promising results in studies on brain encoding and decoding.Finally,we propose that the dual learning method,which was originally designed for machine translation tasks,could help to improve the performance of encoding and decoding models by leveraging large-scale unpaired data.
基金supported by the National Natural Science Foundation of China(Grant Nos.42141019 and 42261144687)the Second Tibetan Plateau Scientific Expedition and Research(STEP)program(Grant No.2019QZKK0102)+4 种基金the Strategic Priority Research Program of the Chinese Academy of Sciences(Grant No.XDB42010404)the National Natural Science Foundation of China(Grant No.42175049)the Guangdong Meteorological Service Science and Technology Research Project(Grant No.GRMC2021M01)the National Key Scientific and Technological Infrastructure project“Earth System Science Numerical Simulator Facility”(EarthLab)for computational support and Prof.Shiming XIANG for many useful discussionsNiklas BOERS acknowledges funding from the Volkswagen foundation.
文摘Climate models are vital for understanding and projecting global climate change and its associated impacts.However,these models suffer from biases that limit their accuracy in historical simulations and the trustworthiness of future projections.Addressing these challenges requires addressing internal variability,hindering the direct alignment between model simulations and observations,and thwarting conventional supervised learning methods.Here,we employ an unsupervised Cycle-consistent Generative Adversarial Network(CycleGAN),to correct daily Sea Surface Temperature(SST)simulations from the Community Earth System Model 2(CESM2).Our results reveal that the CycleGAN not only corrects climatological biases but also improves the simulation of major dynamic modes including the El Niño-Southern Oscillation(ENSO)and the Indian Ocean Dipole mode,as well as SST extremes.Notably,it substantially corrects climatological SST biases,decreasing the globally averaged Root-Mean-Square Error(RMSE)by 58%.Intriguingly,the CycleGAN effectively addresses the well-known excessive westward bias in ENSO SST anomalies,a common issue in climate models that traditional methods,like quantile mapping,struggle to rectify.Additionally,it substantially improves the simulation of SST extremes,raising the pattern correlation coefficient(PCC)from 0.56 to 0.88 and lowering the RMSE from 0.5 to 0.32.This enhancement is attributed to better representations of interannual,intraseasonal,and synoptic scales variabilities.Our study offers a novel approach to correct global SST simulations and underscores its effectiveness across different time scales and primary dynamical modes.
基金The National Natural Science Foundation of China(Grant No.81573273,81673279,21572010 and 21772005)National Major Scientific and Technological Special Project for"Significant New Drugs Development"(Grant No.2018ZX09735001-003)
文摘Natural products（NPs） have long been recognized as a valuable resource for drug discovery, and bringing NP-related features to virtual libraries is believed to be an effective way to increase the coverage of druggable chemical space. Here, deep learning-based molecule generative model, which is a recent technique in de novo molecule design, was applied to generate virtual libraries with NP-like properties. Results demonstrated that the model was effective in generating molecules that highly resemble NPs. Moreover, the model was also found to be capable of generating NP-like molecules that were also easy to synthesize, significantly increasing the practical value of the compound library.
基金supported by the National Natural Science Foundation of China(Grant No.81974355 and No.82172524).
文摘Objective This study aimed to evaluate and compare the effectiveness of knowledge base-optimized and unoptimized large language models(LLMs)in the field of orthopedics to explore optimization strategies for the application of LLMs in specific fields.Methods This research constructed a specialized knowledge base using clinical guidelines from the American Academy of Orthopaedic Surgeons(AAOS)and authoritative orthopedic publications.A total of 30 orthopedic-related questions covering aspects such as anatomical knowledge,disease diagnosis,fracture classification,treatment options,and surgical techniques were input into both the knowledge base-optimized and unoptimized versions of the GPT-4,ChatGLM,and Spark LLM,with their generated responses recorded.The overall quality,accuracy,and comprehensiveness of these responses were evaluated by 3 experienced orthopedic surgeons.Results Compared with their unoptimized LLMs,the optimized version of GPT-4 showed improvements of 15.3%in overall quality,12.5%in accuracy,and 12.8%in comprehensiveness;ChatGLM showed improvements of 24.8%,16.1%,and 19.6%,respectively;and Spark LLM showed improvements of 6.5%,14.5%,and 24.7%,respectively.Conclusion The optimization of knowledge bases significantly enhances the quality,accuracy,and comprehensiveness of the responses provided by the 3 models in the orthopedic field.Therefore,knowledge base optimization is an effective method for improving the performance of LLMs in specific fields.
基金National Key Research and Development Program of China,Grant/Award Number:2021YFC1910402。
文摘Intelligent sorting is an important prerequisite for the full quantitative consumption and harmless disposal of kitchen waste.The existing object detection method based on an ImageNet pre-trained model is an effective way of sorting.Owing to significant domain gaps between natural images and kitchen waste images,it is difficult to reflect the characteristics of diverse scales and dense distribution in kitchen waste based on an ImageNet pre-trained model,leading to poor generalisation.In this article,the authors propose the first pre-trained model for kitchen waste sorting called KitWaSor,which combines both contrastive learning(CL)and masked image modelling(MIM)through self-supervised learning(SSL).First,to address the issue of diverse scales,the authors propose a mixed masking strategy by introducing an incomplete masking branch based on the original random masking branch.It prevents the complete loss of small-scale objects while avoiding excessive leakage of large-scale object pixels.Second,to address the issue of dense distribution,the authors introduce semantic consistency constraints on the basis of the mixed masking strategy.That is,object semantic reasoning is performed through semantic consistency constraints to compensate for the lack of contextual information.To train KitWaSor,the authors construct the first million-level kitchen waste dataset across seasonal and regional distributions,named KWD-Million.Extensive experiments show that KitWaSor achieves state-of-the-art(SOTA)performance on the two most relevant downstream tasks for kitchen waste sorting(i.e.image classification and object detection),demonstrating the effectiveness of the proposed KitWaSor.
基金supported by the Bill & Melinda Gates Foundation and the Minderoo Foundation
文摘Predicting cross-immunity between viral strains is vital for public health surveillance and vaccine development.Traditional neural network methods,such as BiLSTM,could be ineffective due to the lack of lab data for model training and the overshadowing of crucial features within sequence concatenation.The current work proposes a less data-consuming model incorporating a pre-trained gene sequence model and a mutual information inference operator.Our methodology utilizes gene alignment and deduplication algorithms to preprocess gene sequences,enhancing the model’s capacity to discern and focus on distinctions among input gene pairs.The model,i.e.,DNA Pretrained Cross-Immunity Protection Inference model(DPCIPI),outperforms state-of-theart(SOTA)models in predicting hemagglutination inhibition titer from influenza viral gene sequences only.Improvement in binary cross-immunity prediction is 1.58%in F1,2.34%in precision,1.57%in recall,and 1.57%in Accuracy.For multilevel cross-immunity improvements,the improvement is 2.12%in F1,3.50%in precision,2.19%in recall,and 2.19%in Accuracy.Our study showcases the potential of pre-trained gene models to improve predictions of antigenic variation and cross-immunity.With expanding gene data and advancements in pre-trained models,this approach promises significant impacts on vaccine development and public health.
基金Project supported by the Guangdong Basic and Applied Basic Research Foundation of China(No.2023A1515012809)the Natural Science Foundation of Shaanxi Province of China(No.2023-JC-YB-073)the Fundamental Research Funds for the Central Universities of China(No.D5000230066)。
文摘With the miniaturization of devices and the development of modern heating technologies,the generalization of heat conduction and thermoelastic coupling has become crucial,effectively emulating the thermodynamic behavior of materials in ultrashort time scales.Theoretically,generalized heat conductive models are considered in this work.By analogy with mechanical viscoelastic models,this paper further enriches the heat conduction models and gives their one-dimensional physical expression.Numerically,the transient thermoelastic response of the slim strip material under thermal shock is investigated by applying the proposed models.First,the analytical solution in the Laplace domain is obtained by the Laplace transform.Then,the numerical results of the transient responses are obtained by the numerical inverse Laplace transform.Finally,the transient responses of different models are analyzed and compared,and the effects of material parameters are discussed.This work not only opens up new research perspectives on generalized heat conductive and thermoelastic coupling theories,but also is expected to be beneficial for the deeper understanding of the heat wave theory.
文摘We analyze the suitability of existing pre-trained transformer-based language models(PLMs)for abstractive text summarization on German technical healthcare texts.The study focuses on the multilingual capabilities of these models and their ability to perform the task of abstractive text summarization in the healthcare field.The research hypothesis was that large language models could perform high-quality abstractive text summarization on German technical healthcare texts,even if the model is not specifically trained in that language.Through experiments,the research questions explore the performance of transformer language models in dealing with complex syntax constructs,the difference in performance between models trained in English and German,and the impact of translating the source text to English before conducting the summarization.We conducted an evaluation of four PLMs(GPT-3,a translation-based approach also utilizing GPT-3,a German language Model,and a domain-specific bio-medical model approach).The evaluation considered the informativeness using 3 types of metrics based on Recall-Oriented Understudy for Gisting Evaluation(ROUGE)and the quality of results which is manually evaluated considering 5 aspects.The results show that text summarization models could be used in the German healthcare domain and that domain-independent language models achieved the best results.The study proves that text summarization models can simplify the search for pre-existing German knowledge in various domains.
基金supported by the National Nature Science Foundation of China (Nos. 61671362 and 62071366)。
文摘Two dimensional(2D) materials based on boron and carbon have attracted wide attention due to their unique properties. BC compounds have rich active sites and diverse chemical coordination, showing great potential in optoelectronic applications. However, due to the limitation of calculation and experimental conditions, it is still a challenging task to predict new 2D BC monolayer materials. Specifically, we utilized Crystal Diffusion Variational Autoencoder(CDVAE) and pre-trained Materials Graph Neural Network with 3-Body Interactions(M3GNet) model to generate novel and stable BCP materials. Each crystal structure was treated as a high-dimensional vector, where the encoder extracted lattice information and element coordinates, mapping the high-dimensional data into a low-dimensional latent space. The decoder then reconstructed the latent representation back into the original data space. Additionally, our designed attribute predictor network combined the advantages of dilated convolutions and residual connections,effectively increasing the model's receptive field and learning capacity while maintaining relatively low parameter count and computational complexity. By progressively increasing the dilation rate, the model can capture features at different scales. We used the DFT data set of about 1600 BCP monolayer materials to train the diffusion model, and combined with the pre-trained M3GNet model to screen the best candidate structure. Finally, we used DFT calculations to confirm the stability of the candidate structure.The results show that the combination of generative deep learning model and attribute prediction model can help accelerate the discovery and research of new 2D materials, and provide effective methods for exploring the inverse design of new two-dimensional materials.
基金supported in part by the Shandong Provincial Natural Science Foundation under Grants ZR2023LZH017,ZR2022LZH015 and ZR2024MF066the National Natural Science Foundation of China under Grant 62471493+1 种基金the Tertiary Education Scientific research project of Guangzhou Municipal Education Bureau under Grant 2024312246the Guangzhou Higher Education Teaching Quality and Teaching Reform Project under Grant 2023KCJJD002。
文摘With the rapid development of generative artificial intelligence technology,the traditional cloud-based centralized model training and inference face significant limitations due to high transmission latency and costs,which restrict user-side in-situ Artificial Intelligence Generated Content(AIGC)service requests.To this end,we propose the Edge Artificial Intelligence Generated Content(Edge AIGC)framework,which can effectively address the challenges of cloud computing by implementing in-situ processing of services close to the data source through edge computing.However,AIGC models usually have a large parameter scale and complex computing requirements,which poses a huge challenge to the storage and computing resources of edge devices.This paper focuses on the edge intelligence model caching and resource allocation problems in the Edge AIGC framework,aiming to improve the cache hit rate and resource utilization of edge devices for models by optimizing the model caching strategy and resource allocation scheme,and realize in-situ AIGC service processing.With the optimization objectives of minimizing service request response time and execution cost in resource-constrained environments,we employ the Twin Delayed Deep Deterministic Policy Gradient algorithm for optimization.Experimental results show that,compared with other methods,our model caching and resource allocation strategies can effectively improve the cache hit rate by at least 41.06%and reduce the response cost as well.
