Baosteel＇s 60000 m^3/h air separation unit （ASU） is the largest oxygen generating system in China. The operational cost of such a giant system is very high. How to reduce the operational cost is a critical issue. T...Baosteel＇s 60000 m^3/h air separation unit （ASU） is the largest oxygen generating system in China. The operational cost of such a giant system is very high. How to reduce the operational cost is a critical issue. This paper discusses the system＇s characteristics,the current operational status and the difficulties in reducing the cost,and analyzes relevant indicators, such as the technical and economical indicators of individual units and systems as well as the indicators concerning the costs. The relationship between the cost and each economical indicator and measures to optimize an economical operation of the oxygen generating system are also discussed in this paper.展开更多
Nowadays,there are some problems in the area of distributed operating system(DOS)and its research methods.To solve these problems,we have provided a Distributed Operat-ing System Auto-generating System(DOSAGS)model,wh...Nowadays,there are some problems in the area of distributed operating system(DOS)and its research methods.To solve these problems,we have provided a Distributed Operat-ing System Auto-generating System(DOSAGS)model,which is characterized by intelli-gence,integration and moldability.DOSAGS’ system structure,functions,work principlesand key problems in its implementation are presented.It is obvious that the DOS generatedby DOSAGS is a real new generation distributed OS.展开更多
Distributed Operating System Formalization Generating System(DOSFGS)consists of agrammar subsystem DOSFSG and a semantics subsystem DOSFSS.DOSFSG is a kind ofContext-free grammar.DOSFSS is a semantics system with an o...Distributed Operating System Formalization Generating System(DOSFGS)consists of agrammar subsystem DOSFSG and a semantics subsystem DOSFSS.DOSFSG is a kind ofContext-free grammar.DOSFSS is a semantics system with an operating set.DOSFGS gen-erates a distributed operating system automatically according to the process of abstraction,description,and refinement.This paper discusses data structures,operating set and defini-tion of DOSFSS.展开更多
Neuroinflammation is associated with Parkinson’s disease:Reactive gliosis and neuroinflammation are hallmarks of Parkinson’s disease(PD),a multisystem neurodegenerative disorder characterized by a progressive loss o...Neuroinflammation is associated with Parkinson’s disease:Reactive gliosis and neuroinflammation are hallmarks of Parkinson’s disease(PD),a multisystem neurodegenerative disorder characterized by a progressive loss of dopaminergic neurons.Neuroinflammation has long been considered a mere consequence of neuronal loss,but whether it promotes PD or is a key player in disease progression remains to be determined.Human leukocyte antigen.展开更多
In the scenario of a steam generator tube rupture accident in a lead-cooled fast reactor,secondary circuit subcooled water under high pressure is injected into an ordinary-pressure primary vessel,where a molten lead-b...In the scenario of a steam generator tube rupture accident in a lead-cooled fast reactor,secondary circuit subcooled water under high pressure is injected into an ordinary-pressure primary vessel,where a molten lead-based alloy(typically pure lead or lead-bismuth eutectic(LBE))is used as the coolant.To clarify the pressure build-up characteristics under water-jet injection,this study conducted several experiments by injecting pressurized water into a molten LBE pool at Sun Yat-sen University.To obtain a further understanding,several new experimental parameters were adopted,including the melt temperature,water subcooling,injection pressure,injection duration,and nozzle diameter.Through detailed analyses,it was found that the pressure and temperature during the water-melt interaction exhibited a consistent variation trend with our previous water-droplet injection mode LBE experiment.Similarly,the existence of a steam explosion was confirmed,which typically results in a much stronger pressure build-up.For the non-explosion cases,increasing the injection pressure,melt-pool temperature,nozzle diameter,and water subcooling promoted pressure build-up in the melt pool.However,a limited enhancement effect was observed when increasing the injection duration,which may be owing to the continually rising pressure in the interaction vessel or the isolation effect of the generated steam cavity.Regardless of whether a steam explosion occurred,the calculated mechanical and kinetic energy conversion efficiencies of the melt were relatively small(not exceeding 4.1%and 0.7%,respectively).Moreover,the range of the conversion efficiency was similar to that of previous water-droplet experiments,although the upper limit of the jet mode was slightly lower.展开更多
The Internet of Things(IoT)is integral to modern infrastructure,enabling connectivity among a wide range of devices from home automation to industrial control systems.With the exponential increase in data generated by...The Internet of Things(IoT)is integral to modern infrastructure,enabling connectivity among a wide range of devices from home automation to industrial control systems.With the exponential increase in data generated by these interconnected devices,robust anomaly detection mechanisms are essential.Anomaly detection in this dynamic environment necessitates methods that can accurately distinguish between normal and anomalous behavior by learning intricate patterns.This paper presents a novel approach utilizing generative adversarial networks(GANs)for anomaly detection in IoT systems.However,optimizing GANs involves tuning hyper-parameters such as learning rate,batch size,and optimization algorithms,which can be challenging due to the non-convex nature of GAN loss functions.To address this,we propose a five-dimensional Gray wolf optimizer(5DGWO)to optimize GAN hyper-parameters.The 5DGWO introduces two new types of wolves:gamma(γ)for improved exploitation and convergence,and theta(θ)for enhanced exploration and escaping local minima.The proposed system framework comprises four key stages:1)preprocessing,2)generative model training,3)autoencoder(AE)training,and 4)predictive model training.The generative models are utilized to assist the AE training,and the final predictive models(including convolutional neural network(CNN),deep belief network(DBN),recurrent neural network(RNN),random forest(RF),and extreme gradient boosting(XGBoost))are trained using the generated data and AE-encoded features.We evaluated the system on three benchmark datasets:NSL-KDD,UNSW-NB15,and IoT-23.Experiments conducted on diverse IoT datasets show that our method outperforms existing anomaly detection strategies and significantly reduces false positives.The 5DGWO-GAN-CNNAE exhibits superior performance in various metrics,including accuracy,recall,precision,root mean square error(RMSE),and convergence trend.The proposed 5DGWO-GAN-CNNAE achieved the lowest RMSE values across the NSL-KDD,UNSW-NB15,and IoT-23 datasets,with values of 0.24,1.10,and 0.09,respectively.Additionally,it attained the highest accuracy,ranging from 94%to 100%.These results suggest a promising direction for future IoT security frameworks,offering a scalable and efficient solution to safeguard against evolving cyber threats.展开更多
We give a new result on the construction of K-frame generators for unitary systems by using the pseudo-inverses of involved operators,which provides an improvement to one known result on this topic.We also introduce t...We give a new result on the construction of K-frame generators for unitary systems by using the pseudo-inverses of involved operators,which provides an improvement to one known result on this topic.We also introduce the concept of K-woven generators for unitary systems,by means of which we investigate the weaving properties of K-frame generators for unitary systems.展开更多
New renewable energy exploitation technologies in offshore structures are vital for future energy production systems.Offshore hybrid wind-wave power generation(HWWPG)systems face increased component failure rates beca...New renewable energy exploitation technologies in offshore structures are vital for future energy production systems.Offshore hybrid wind-wave power generation(HWWPG)systems face increased component failure rates because of harsh weather,significantly affecting the maintenance procedures and reliability.Different types of failure rates of the wind turbine(WT)and wave energy converter(WEC),e.g.,the degradation and failure rates during regular wind speed fluctuation,the degradation and failure rates during intense wind speed fluctuation are considered.By incorporating both WT and WEC,the HWWPG system is designed to enhance the overall amount of electrical energy produced by the system over a given period under varying weather conditions.The universal generating function technique is used to calculate the HWWPG system dependability measures in a structured and efficient manner.This research highlights that intense weather conditions increase the failure rates of both WT and WEC,resulting in higher maintenance costs and more frequent downtimes,thus impacting the HWWPG system’s reliability.Although the HWWPG system can meet the energy demands in the presence of high failure rates,the reliance of the hybrid system on both WT and WEC helps maintain a relatively stable demand satisfaction during periods of high energy demand despite adverse weather conditions.To confirm the added value and applicability of the developed model,a case study of an offshore hybrid platform is conducted.The findings underscore the system’s robustness in maintaining energy production under varied weather conditions,though higher failure rates and maintenance costs arise in intense scenarios.展开更多
1 Introduction In recent years,the rapid development of industrial big data and artificial intelligence(AI)technologies has revolutionized the industrial landscape.Industrial systems,such as manufacturing,energy,trans...1 Introduction In recent years,the rapid development of industrial big data and artificial intelligence(AI)technologies has revolutionized the industrial landscape.Industrial systems,such as manufacturing,energy,transportation,and logistics,have become increasingly complex,generating vast amounts of data[1–3].These big data encompass a wide range of data sources,including sensor data,production logs,and maintenance records,which hold valuable insights[4–6].Moreover,machine learning-based AI techniques can be applied to extract meaningful insights from this big data[7].展开更多
This study presents a comparative analysis of a complex SQL benchmark, TPC-DS, with two existing text-to-SQL benchmarks, BIRD and Spider. Our findings reveal that TPC-DS queries exhibit a significantly higher level of...This study presents a comparative analysis of a complex SQL benchmark, TPC-DS, with two existing text-to-SQL benchmarks, BIRD and Spider. Our findings reveal that TPC-DS queries exhibit a significantly higher level of structural complexity compared to the other two benchmarks. This underscores the need for more intricate benchmarks to simulate realistic scenarios effectively. To facilitate this comparison, we devised several measures of structural complexity and applied them across all three benchmarks. The results of this study can guide future research in the development of more sophisticated text-to-SQL benchmarks. We utilized 11 distinct Language Models (LLMs) to generate SQL queries based on the query descriptions provided by the TPC-DS benchmark. The prompt engineering process incorporated both the query description as outlined in the TPC-DS specification and the database schema of TPC-DS. Our findings indicate that the current state-of-the-art generative AI models fall short in generating accurate decision-making queries. We conducted a comparison of the generated queries with the TPC-DS gold standard queries using a series of fuzzy structure matching techniques based on query features. The results demonstrated that the accuracy of the generated queries is insufficient for practical real-world application.展开更多
This study systematically reviews the applications of generative artificial intelligence(GAI)in breast cancer research,focusing on its role in diagnosis and therapeutic development.While GAI has gained significant att...This study systematically reviews the applications of generative artificial intelligence(GAI)in breast cancer research,focusing on its role in diagnosis and therapeutic development.While GAI has gained significant attention across various domains,its utility in breast cancer research has yet to be comprehensively reviewed.This study aims to fill that gap by synthesizing existing research into a unified document.A comprehensive search was conducted following Preferred Reporting Items for Systematic Reviews and Meta-Analyses(PRISMA)guidelines,resulting in the retrieval of 3827 articles,of which 31 were deemed eligible for analysis.The included studies were categorized based on key criteria,such as application types,geographical distribution,contributing organizations,leading journals,publishers,and temporal trends.Keyword co-occurrence mapping and subject profiling further highlighted the major research themes in this field.The findings reveal that GAI models have been applied to improve breast cancer diagnosis,treatment planning,and outcome predictions.Geographical and network analyses showed that most contributions come from a few leading institutions,with limited global collaboration.The review also identifies key challenges in implementing GAI in clinical practice,such as data availability,ethical concerns,and model validation.Despite these challenges,the study highlights GAI’s potential to enhance breast cancer research,particularly in generating synthetic data,improving diagnostic accuracy,and personalizing treatment approaches.This review serves as a valuable resource for researchers and stakeholders,providing insights into current research trends,major contributors,and collaborative networks in GAI-based breast cancer studies.By offering a holistic overview,it aims to support future research directions and encourage broader adoption of GAI technologies in healthcare.Additionally,the study emphasizes the importance of overcoming implementation barriers to fully realizeGAI’s potential in transforming breast cancer management.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
Fractional calculus is widely used to deal with nonconservative dynamics because of its memorability and non-local properties.In this paper,the Herglotz principle with generalized operators is discussed,and the Herglo...Fractional calculus is widely used to deal with nonconservative dynamics because of its memorability and non-local properties.In this paper,the Herglotz principle with generalized operators is discussed,and the Herglotz type equations for nonholonomic systems are established.Then,the Noether symmetries are studied,and the conserved quantities are obtained.The results are extended to nonholonomic canonical systems,and the Herglotz type canonical equations and the Noether theorems are obtained.Two examples are provided to demonstrate the validity of the methods and results.展开更多
With the rapid development of generative artificial intelligence(AI)technology in the field of education,global educational systems are facing unprecedented opportunities and challenges,urgently requiring the establis...With the rapid development of generative artificial intelligence(AI)technology in the field of education,global educational systems are facing unprecedented opportunities and challenges,urgently requiring the establishment of comprehensive,flexible,and forward-looking governance solutions.The“Australian Framework for Generative AI in Schools”builds a multi-dimensional governance system covering aspects such as teaching and humanistic care,fairness and transparency,and accountability and security.Based on 22 specific principles and six core elements,it emphasizes a human-centered design concept,adopts a principle-based flexible structure,focuses on fairness and transparency,and stresses accountability and security.The framework provides valuable references for the use of generative AI in China’s education system and holds significant importance for promoting educational modernization and cultivating innovative talents adapted to the era of artificial intelligence.展开更多
The exponential growth of over-the-top(OTT)entertainment has fueled a surge in content consumption across diverse formats,especially in regional Indian languages.With the Indian film industry producing over 1500 films...The exponential growth of over-the-top(OTT)entertainment has fueled a surge in content consumption across diverse formats,especially in regional Indian languages.With the Indian film industry producing over 1500 films annually in more than 20 languages,personalized recommendations are essential to highlight relevant content.To overcome the limitations of traditional recommender systems-such as static latent vectors,poor handling of cold-start scenarios,and the absence of uncertainty modeling-we propose a deep Collaborative Neural Generative Embedding(C-NGE)model.C-NGE dynamically learns user and item representations by integrating rating information and metadata features in a unified neural framework.It uses metadata as sampled noise and applies the reparameterization trick to capture latent patterns better and support predictions for new users or items without retraining.We evaluate CNGE on the Indian Regional Movies(IRM)dataset,along with MovieLens 100 K and 1 M.Results show that our model consistently outperforms several existing methods,and its extensibility allows for incorporating additional signals like user reviews and multimodal data to enhance recommendation quality.展开更多
Concentrated solar thermal power generation has been experimentally tested in advanced countries for a period of time.This paper demonstrates how this technology can be improved by using water molecules as a medium to...Concentrated solar thermal power generation has been experimentally tested in advanced countries for a period of time.This paper demonstrates how this technology can be improved by using water molecules as a medium to drive traditional generator sets for energy conversion,thereby simultaneously improving the energy conversion rate.Additionally,a novel contribution is made by incorporating a magic number 4 to enhance the focusing efficiency of Fresnel lenses,which drives improvements in power generation output and QE(Quantum Efficiency).展开更多
As the proportion of natural gas consumption in the energy market gradually increases,optimizing the design of gas storage surface system(GSSS)has become a current research focus.Existing studies on the two independen...As the proportion of natural gas consumption in the energy market gradually increases,optimizing the design of gas storage surface system(GSSS)has become a current research focus.Existing studies on the two independent injection pipeline network(InNET)and production pipeline network(ProNET)for underground natural gas storage(UNGS)are scarce,and no optimization methods have been proposed yet.Therefore,this paper focuses on the flow and pressure boundary characteristics of the GSSS.It constructs systematic models,including the injection multi-condition coupled model(INM model),production multi-condition coupled model(PRM model),injection single condition model(INS model)and production single condition model(PRS model)to optimize the design parameters.Additionally,this paper proposes a hybrid genetic algorithm based on generalized reduced gradient(HGA-GRG)for solving the models.The models and algorithm are applied to a case study with the objective of minimizing the cost of the pipeline network.For the GSSS,nine different condition scenarios are considered,and iterative process analysis and sensitivity analysis of these scenarios are conducted.Moreover,simulation scenarios are set up to verify the applicability of different scenarios to the boundaries.The research results show that the cost of the InNET considering the coupled pressure boundary is 64.4890×10^(4) CNY,and the cost of the ProNET considering coupled flow and pressure boundaries is 87.7655×10^(4) CNY,demonstrating greater applicability and economy than those considering only one or two types of conditions.The algorithms and models proposed in this paper provide an effective means for the design of parameters for GSSS.展开更多
Symmetric encryption algorithms learned by the previous proposed end-to-end adversarial network encryption communication systems are deterministic.With the same key and same plaintext,the deterministic algorithm will ...Symmetric encryption algorithms learned by the previous proposed end-to-end adversarial network encryption communication systems are deterministic.With the same key and same plaintext,the deterministic algorithm will lead to the same ciphertext.This means that the key in the deterministic encryption algorithm can only be used once,thus the encryption is not practical.To solve this problem,a nondeterministic symmetric encryption end-to-end communication system based on generative adversarial networks is proposed.We design a nonce-based adversarial neural network model,where a“nonce”standing for“number used only once”is passed to communication participants,and does not need to be secret.Moreover,we optimize the network structure through adding Batch Normalization(BN)to the CNNs(Convolutional Neural Networks),selecting the appropriate activation functions,and setting appropriate CNNs parameters.Results of experiments and analysis show that our system can achieve non-deterministic symmetric encryption,where Alice encrypting the same plaintext with the key twice will generate different ciphertexts,and Bob can decrypt all these different ciphertexts of the same plaintext to the correct plaintext.And our proposed system has fast convergence and the correct rate of decryption when the plaintext length is 256 or even longer.展开更多
Objective:Generative artificial intelligence(AI)technology,represented by large language models(LLMs),has gradually been developed for traditional Chinese medicine(TCM);however,challenges remain in effectively enhanci...Objective:Generative artificial intelligence(AI)technology,represented by large language models(LLMs),has gradually been developed for traditional Chinese medicine(TCM);however,challenges remain in effectively enhancing AI applications for TCM.Therefore,this study is the first systematic review to analyze LLMs in TCM retrospectively,focusing on and summarizing the evidence of their performance in generative tasks.Methods:We extensively searched electronic databases for articles published until June 2024 to identify publicly available studies on LLMs in TCM.Two investigators independently selected and extracted the related information and evaluation metrics.Based on the available data,this study used descriptive analysis for a comprehensive systematic review of LLM technology related to TCM.Results:Ten studies published between 2023 and 2024 met our eligibility criteria and were included in this review,including 40%LLMs in the TCM vertical domain,40%containing TCM data,and 20%honoring the TCM contribution,with a foundational model parameter range from 1.8 to 33 billion.All included studies used manual or automatic evaluation metrics to evaluate model performance and fully discussed the challenges and contributions through an overview of LLMs in TCM.Conclusions:LLMs have achieved significant advantages in TCM applications and can effectively address intelligent TCM tasks.Further in-depth development of LLMs is needed in various vertical TCM fields,including clinical and fundamental research.Focusing on the functional segmentation development direction of generative AI technologies in TCM application scenarios to meet the practical needs-oriented demands of TCM digitalization is essential.展开更多
This paper introduces a novel chattering-free terminal sliding mode control(SMC)strategy to address chaotic behavior in permanent magnet synchronous generators(PMSG)for offshore wind turbine systems.By integrating an ...This paper introduces a novel chattering-free terminal sliding mode control(SMC)strategy to address chaotic behavior in permanent magnet synchronous generators(PMSG)for offshore wind turbine systems.By integrating an adaptive exponential reaching law with a continuous barrier function,the proposed approach eliminates chattering and ensures robust performance under model uncertainties.The methodology combines adaptive SMC with dynamic switching to estimate and compensates for unknown uncertainties,providing smooth and stable control.Finally,the performance and effectiveness of the proposed approach are compared with those of a previous study.展开更多
文摘Baosteel＇s 60000 m^3/h air separation unit （ASU） is the largest oxygen generating system in China. The operational cost of such a giant system is very high. How to reduce the operational cost is a critical issue. This paper discusses the system＇s characteristics,the current operational status and the difficulties in reducing the cost,and analyzes relevant indicators, such as the technical and economical indicators of individual units and systems as well as the indicators concerning the costs. The relationship between the cost and each economical indicator and measures to optimize an economical operation of the oxygen generating system are also discussed in this paper.
基金Software-Engineering National Key Laboratory of Wuhan University.
文摘Nowadays,there are some problems in the area of distributed operating system(DOS)and its research methods.To solve these problems,we have provided a Distributed Operat-ing System Auto-generating System(DOSAGS)model,which is characterized by intelli-gence,integration and moldability.DOSAGS’ system structure,functions,work principlesand key problems in its implementation are presented.It is obvious that the DOS generatedby DOSAGS is a real new generation distributed OS.
基金Supported by the High Technology Research and Development Programme of China.
文摘Distributed Operating System Formalization Generating System(DOSFGS)consists of agrammar subsystem DOSFSG and a semantics subsystem DOSFSS.DOSFSG is a kind ofContext-free grammar.DOSFSS is a semantics system with an operating set.DOSFGS gen-erates a distributed operating system automatically according to the process of abstraction,description,and refinement.This paper discusses data structures,operating set and defini-tion of DOSFSS.
基金supported by the Spanish Government(ISCIII-FEDER)PI20/01063by Navarra Government(PC 060-061 and PC 192-193)Fundación Gangoiti(to MSA).LA was funded by FPU19/03255.
文摘Neuroinflammation is associated with Parkinson’s disease:Reactive gliosis and neuroinflammation are hallmarks of Parkinson’s disease(PD),a multisystem neurodegenerative disorder characterized by a progressive loss of dopaminergic neurons.Neuroinflammation has long been considered a mere consequence of neuronal loss,but whether it promotes PD or is a key player in disease progression remains to be determined.Human leukocyte antigen.
基金supported by Basic and Applied Basic research foundation of Guangdong province(Nos.2021A1515010343 and 2022A1515011582)the Science and Technology Program of Guangdong Province(Nos.2021A0505030026 and 2022A0505050029).
文摘In the scenario of a steam generator tube rupture accident in a lead-cooled fast reactor,secondary circuit subcooled water under high pressure is injected into an ordinary-pressure primary vessel,where a molten lead-based alloy(typically pure lead or lead-bismuth eutectic(LBE))is used as the coolant.To clarify the pressure build-up characteristics under water-jet injection,this study conducted several experiments by injecting pressurized water into a molten LBE pool at Sun Yat-sen University.To obtain a further understanding,several new experimental parameters were adopted,including the melt temperature,water subcooling,injection pressure,injection duration,and nozzle diameter.Through detailed analyses,it was found that the pressure and temperature during the water-melt interaction exhibited a consistent variation trend with our previous water-droplet injection mode LBE experiment.Similarly,the existence of a steam explosion was confirmed,which typically results in a much stronger pressure build-up.For the non-explosion cases,increasing the injection pressure,melt-pool temperature,nozzle diameter,and water subcooling promoted pressure build-up in the melt pool.However,a limited enhancement effect was observed when increasing the injection duration,which may be owing to the continually rising pressure in the interaction vessel or the isolation effect of the generated steam cavity.Regardless of whether a steam explosion occurred,the calculated mechanical and kinetic energy conversion efficiencies of the melt were relatively small(not exceeding 4.1%and 0.7%,respectively).Moreover,the range of the conversion efficiency was similar to that of previous water-droplet experiments,although the upper limit of the jet mode was slightly lower.
基金described in this paper has been developed with in the project PRESECREL(PID2021-124502OB-C43)。
文摘The Internet of Things(IoT)is integral to modern infrastructure,enabling connectivity among a wide range of devices from home automation to industrial control systems.With the exponential increase in data generated by these interconnected devices,robust anomaly detection mechanisms are essential.Anomaly detection in this dynamic environment necessitates methods that can accurately distinguish between normal and anomalous behavior by learning intricate patterns.This paper presents a novel approach utilizing generative adversarial networks(GANs)for anomaly detection in IoT systems.However,optimizing GANs involves tuning hyper-parameters such as learning rate,batch size,and optimization algorithms,which can be challenging due to the non-convex nature of GAN loss functions.To address this,we propose a five-dimensional Gray wolf optimizer(5DGWO)to optimize GAN hyper-parameters.The 5DGWO introduces two new types of wolves:gamma(γ)for improved exploitation and convergence,and theta(θ)for enhanced exploration and escaping local minima.The proposed system framework comprises four key stages:1)preprocessing,2)generative model training,3)autoencoder(AE)training,and 4)predictive model training.The generative models are utilized to assist the AE training,and the final predictive models(including convolutional neural network(CNN),deep belief network(DBN),recurrent neural network(RNN),random forest(RF),and extreme gradient boosting(XGBoost))are trained using the generated data and AE-encoded features.We evaluated the system on three benchmark datasets:NSL-KDD,UNSW-NB15,and IoT-23.Experiments conducted on diverse IoT datasets show that our method outperforms existing anomaly detection strategies and significantly reduces false positives.The 5DGWO-GAN-CNNAE exhibits superior performance in various metrics,including accuracy,recall,precision,root mean square error(RMSE),and convergence trend.The proposed 5DGWO-GAN-CNNAE achieved the lowest RMSE values across the NSL-KDD,UNSW-NB15,and IoT-23 datasets,with values of 0.24,1.10,and 0.09,respectively.Additionally,it attained the highest accuracy,ranging from 94%to 100%.These results suggest a promising direction for future IoT security frameworks,offering a scalable and efficient solution to safeguard against evolving cyber threats.
基金Supported by NSFC(Nos.12361028,11761057)Science Foundation of Jiangxi Education Department(Nos.GJJ202302,GJJ202303,GJJ202319).
文摘We give a new result on the construction of K-frame generators for unitary systems by using the pseudo-inverses of involved operators,which provides an improvement to one known result on this topic.We also introduce the concept of K-woven generators for unitary systems,by means of which we investigate the weaving properties of K-frame generators for unitary systems.
文摘New renewable energy exploitation technologies in offshore structures are vital for future energy production systems.Offshore hybrid wind-wave power generation(HWWPG)systems face increased component failure rates because of harsh weather,significantly affecting the maintenance procedures and reliability.Different types of failure rates of the wind turbine(WT)and wave energy converter(WEC),e.g.,the degradation and failure rates during regular wind speed fluctuation,the degradation and failure rates during intense wind speed fluctuation are considered.By incorporating both WT and WEC,the HWWPG system is designed to enhance the overall amount of electrical energy produced by the system over a given period under varying weather conditions.The universal generating function technique is used to calculate the HWWPG system dependability measures in a structured and efficient manner.This research highlights that intense weather conditions increase the failure rates of both WT and WEC,resulting in higher maintenance costs and more frequent downtimes,thus impacting the HWWPG system’s reliability.Although the HWWPG system can meet the energy demands in the presence of high failure rates,the reliance of the hybrid system on both WT and WEC helps maintain a relatively stable demand satisfaction during periods of high energy demand despite adverse weather conditions.To confirm the added value and applicability of the developed model,a case study of an offshore hybrid platform is conducted.The findings underscore the system’s robustness in maintaining energy production under varied weather conditions,though higher failure rates and maintenance costs arise in intense scenarios.
基金supported by the Science and Technology Innovation Program of Hunan Province(No.2023RC3097)in part the National Natural Science Foundation of China(No.52105108)in part Young Elite Scientists Sponsorship Program by CAST(No.2023QNRC001).
文摘1 Introduction In recent years,the rapid development of industrial big data and artificial intelligence(AI)technologies has revolutionized the industrial landscape.Industrial systems,such as manufacturing,energy,transportation,and logistics,have become increasingly complex,generating vast amounts of data[1–3].These big data encompass a wide range of data sources,including sensor data,production logs,and maintenance records,which hold valuable insights[4–6].Moreover,machine learning-based AI techniques can be applied to extract meaningful insights from this big data[7].
文摘This study presents a comparative analysis of a complex SQL benchmark, TPC-DS, with two existing text-to-SQL benchmarks, BIRD and Spider. Our findings reveal that TPC-DS queries exhibit a significantly higher level of structural complexity compared to the other two benchmarks. This underscores the need for more intricate benchmarks to simulate realistic scenarios effectively. To facilitate this comparison, we devised several measures of structural complexity and applied them across all three benchmarks. The results of this study can guide future research in the development of more sophisticated text-to-SQL benchmarks. We utilized 11 distinct Language Models (LLMs) to generate SQL queries based on the query descriptions provided by the TPC-DS benchmark. The prompt engineering process incorporated both the query description as outlined in the TPC-DS specification and the database schema of TPC-DS. Our findings indicate that the current state-of-the-art generative AI models fall short in generating accurate decision-making queries. We conducted a comparison of the generated queries with the TPC-DS gold standard queries using a series of fuzzy structure matching techniques based on query features. The results demonstrated that the accuracy of the generated queries is insufficient for practical real-world application.
基金financial support from the Fundamental Research Grant Scheme(FRGS)under grant number:FRGS/1/2024/ICT02/TARUMT/02/1from the Ministry of Higher Education Malaysiafunded in part by the internal grant from the Tunku Abdul Rahman University of Management and Technology(TAR UMT)with grant number:UC/I/G2024-00129.
文摘This study systematically reviews the applications of generative artificial intelligence(GAI)in breast cancer research,focusing on its role in diagnosis and therapeutic development.While GAI has gained significant attention across various domains,its utility in breast cancer research has yet to be comprehensively reviewed.This study aims to fill that gap by synthesizing existing research into a unified document.A comprehensive search was conducted following Preferred Reporting Items for Systematic Reviews and Meta-Analyses(PRISMA)guidelines,resulting in the retrieval of 3827 articles,of which 31 were deemed eligible for analysis.The included studies were categorized based on key criteria,such as application types,geographical distribution,contributing organizations,leading journals,publishers,and temporal trends.Keyword co-occurrence mapping and subject profiling further highlighted the major research themes in this field.The findings reveal that GAI models have been applied to improve breast cancer diagnosis,treatment planning,and outcome predictions.Geographical and network analyses showed that most contributions come from a few leading institutions,with limited global collaboration.The review also identifies key challenges in implementing GAI in clinical practice,such as data availability,ethical concerns,and model validation.Despite these challenges,the study highlights GAI’s potential to enhance breast cancer research,particularly in generating synthetic data,improving diagnostic accuracy,and personalizing treatment approaches.This review serves as a valuable resource for researchers and stakeholders,providing insights into current research trends,major contributors,and collaborative networks in GAI-based breast cancer studies.By offering a holistic overview,it aims to support future research directions and encourage broader adoption of GAI technologies in healthcare.Additionally,the study emphasizes the importance of overcoming implementation barriers to fully realizeGAI’s potential in transforming breast cancer management.
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 by the National Natural Science Foundation of China(Grant No.12272248)the Postgraduate Research and Practice Innovation Program of Jiangsu Province of China(Grant No.KYCX23_3296).
文摘Fractional calculus is widely used to deal with nonconservative dynamics because of its memorability and non-local properties.In this paper,the Herglotz principle with generalized operators is discussed,and the Herglotz type equations for nonholonomic systems are established.Then,the Noether symmetries are studied,and the conserved quantities are obtained.The results are extended to nonholonomic canonical systems,and the Herglotz type canonical equations and the Noether theorems are obtained.Two examples are provided to demonstrate the validity of the methods and results.
基金2024 Undergraduate Innovation Training Program Project“Research on the Current Situation,Impact and Management Countermeasures of Generative AI in College Students’Learning”(202410065153)。
文摘With the rapid development of generative artificial intelligence(AI)technology in the field of education,global educational systems are facing unprecedented opportunities and challenges,urgently requiring the establishment of comprehensive,flexible,and forward-looking governance solutions.The“Australian Framework for Generative AI in Schools”builds a multi-dimensional governance system covering aspects such as teaching and humanistic care,fairness and transparency,and accountability and security.Based on 22 specific principles and six core elements,it emphasizes a human-centered design concept,adopts a principle-based flexible structure,focuses on fairness and transparency,and stresses accountability and security.The framework provides valuable references for the use of generative AI in China’s education system and holds significant importance for promoting educational modernization and cultivating innovative talents adapted to the era of artificial intelligence.
文摘The exponential growth of over-the-top(OTT)entertainment has fueled a surge in content consumption across diverse formats,especially in regional Indian languages.With the Indian film industry producing over 1500 films annually in more than 20 languages,personalized recommendations are essential to highlight relevant content.To overcome the limitations of traditional recommender systems-such as static latent vectors,poor handling of cold-start scenarios,and the absence of uncertainty modeling-we propose a deep Collaborative Neural Generative Embedding(C-NGE)model.C-NGE dynamically learns user and item representations by integrating rating information and metadata features in a unified neural framework.It uses metadata as sampled noise and applies the reparameterization trick to capture latent patterns better and support predictions for new users or items without retraining.We evaluate CNGE on the Indian Regional Movies(IRM)dataset,along with MovieLens 100 K and 1 M.Results show that our model consistently outperforms several existing methods,and its extensibility allows for incorporating additional signals like user reviews and multimodal data to enhance recommendation quality.
文摘Concentrated solar thermal power generation has been experimentally tested in advanced countries for a period of time.This paper demonstrates how this technology can be improved by using water molecules as a medium to drive traditional generator sets for energy conversion,thereby simultaneously improving the energy conversion rate.Additionally,a novel contribution is made by incorporating a magic number 4 to enhance the focusing efficiency of Fresnel lenses,which drives improvements in power generation output and QE(Quantum Efficiency).
基金funded by the National Natural Science Foun-dation of China,grant number 51704253 and 52474084。
文摘As the proportion of natural gas consumption in the energy market gradually increases,optimizing the design of gas storage surface system(GSSS)has become a current research focus.Existing studies on the two independent injection pipeline network(InNET)and production pipeline network(ProNET)for underground natural gas storage(UNGS)are scarce,and no optimization methods have been proposed yet.Therefore,this paper focuses on the flow and pressure boundary characteristics of the GSSS.It constructs systematic models,including the injection multi-condition coupled model(INM model),production multi-condition coupled model(PRM model),injection single condition model(INS model)and production single condition model(PRS model)to optimize the design parameters.Additionally,this paper proposes a hybrid genetic algorithm based on generalized reduced gradient(HGA-GRG)for solving the models.The models and algorithm are applied to a case study with the objective of minimizing the cost of the pipeline network.For the GSSS,nine different condition scenarios are considered,and iterative process analysis and sensitivity analysis of these scenarios are conducted.Moreover,simulation scenarios are set up to verify the applicability of different scenarios to the boundaries.The research results show that the cost of the InNET considering the coupled pressure boundary is 64.4890×10^(4) CNY,and the cost of the ProNET considering coupled flow and pressure boundaries is 87.7655×10^(4) CNY,demonstrating greater applicability and economy than those considering only one or two types of conditions.The algorithms and models proposed in this paper provide an effective means for the design of parameters for GSSS.
基金supported by The National Defense Innovation Project(No.ZZKY20222411)Natural Science Basic Research Plan in Shaanxi Province of China(No.2024JC-YBMS-546).
文摘Symmetric encryption algorithms learned by the previous proposed end-to-end adversarial network encryption communication systems are deterministic.With the same key and same plaintext,the deterministic algorithm will lead to the same ciphertext.This means that the key in the deterministic encryption algorithm can only be used once,thus the encryption is not practical.To solve this problem,a nondeterministic symmetric encryption end-to-end communication system based on generative adversarial networks is proposed.We design a nonce-based adversarial neural network model,where a“nonce”standing for“number used only once”is passed to communication participants,and does not need to be secret.Moreover,we optimize the network structure through adding Batch Normalization(BN)to the CNNs(Convolutional Neural Networks),selecting the appropriate activation functions,and setting appropriate CNNs parameters.Results of experiments and analysis show that our system can achieve non-deterministic symmetric encryption,where Alice encrypting the same plaintext with the key twice will generate different ciphertexts,and Bob can decrypt all these different ciphertexts of the same plaintext to the correct plaintext.And our proposed system has fast convergence and the correct rate of decryption when the plaintext length is 256 or even longer.
基金supported by the National Multidisciplinary Innovation Team of Traditional Chinese Medicine(ZYYCXTD-D-202204)China Postdoctoral Science Foundation(2023M742627)+1 种基金Postdoctoral Fellowship Program of CPSF(GZC20231928)Foundation of State Key Laboratory of Component-based Chinese Medicine(CBCM2023201).
文摘Objective:Generative artificial intelligence(AI)technology,represented by large language models(LLMs),has gradually been developed for traditional Chinese medicine(TCM);however,challenges remain in effectively enhancing AI applications for TCM.Therefore,this study is the first systematic review to analyze LLMs in TCM retrospectively,focusing on and summarizing the evidence of their performance in generative tasks.Methods:We extensively searched electronic databases for articles published until June 2024 to identify publicly available studies on LLMs in TCM.Two investigators independently selected and extracted the related information and evaluation metrics.Based on the available data,this study used descriptive analysis for a comprehensive systematic review of LLM technology related to TCM.Results:Ten studies published between 2023 and 2024 met our eligibility criteria and were included in this review,including 40%LLMs in the TCM vertical domain,40%containing TCM data,and 20%honoring the TCM contribution,with a foundational model parameter range from 1.8 to 33 billion.All included studies used manual or automatic evaluation metrics to evaluate model performance and fully discussed the challenges and contributions through an overview of LLMs in TCM.Conclusions:LLMs have achieved significant advantages in TCM applications and can effectively address intelligent TCM tasks.Further in-depth development of LLMs is needed in various vertical TCM fields,including clinical and fundamental research.Focusing on the functional segmentation development direction of generative AI technologies in TCM application scenarios to meet the practical needs-oriented demands of TCM digitalization is essential.
文摘This paper introduces a novel chattering-free terminal sliding mode control(SMC)strategy to address chaotic behavior in permanent magnet synchronous generators(PMSG)for offshore wind turbine systems.By integrating an adaptive exponential reaching law with a continuous barrier function,the proposed approach eliminates chattering and ensures robust performance under model uncertainties.The methodology combines adaptive SMC with dynamic switching to estimate and compensates for unknown uncertainties,providing smooth and stable control.Finally,the performance and effectiveness of the proposed approach are compared with those of a previous study.
