Traditional Chinese medicine(TCM)exerts integrative effects on complex diseases owing to the characteristics of multiple components with multiple targets.However,the syndrome-based system of diagnosis and treatment in...Traditional Chinese medicine(TCM)exerts integrative effects on complex diseases owing to the characteristics of multiple components with multiple targets.However,the syndrome-based system of diagnosis and treatment in TCM can easily lead to bias because of varying medication preferences among physicians,which has been a major challenge in the global acceptance and application of TCM.Therefore,a standardized TCM prescription system needs to be explored to promote its clinical application.In this study,we first developed a gradient weighted disease-target-herbal ingredient-herb network to aid TCM formulation.We tested its efficacy against intracerebral hemorrhage(ICH).First,the top 100 ICH targets in the GeneCards database were screened according to their relevance scores.Then,SymMap and Traditional Chinese Medicine Systems Pharmacology(TCMSP)databases were applied to find out the target-related ingredients and ingredient-containing herbs,respectively.The relevance of the resulting ingredients and herbs to ICH was determined by adding the relevance scores of the corresponding targets.The top five ICH therapeutic herbs were combined to form a tailored TCM prescriptions.The absorbed components in the serum were detected.In a mouse model of ICH,the new prescription exerted multifaceted effects,including improved neurological function,as well as attenuated neuronal damage,cell apoptosis,vascular leakage,and neuroinflammation.These effects matched well with the core pathological changes in ICH.The multi-targets-directed gradient-weighting strategy presents a promising avenue for tailoring precise,multipronged,unbiased,and standardized TCM prescriptions for complex diseases.This study provides a paradigm for advanced achievements-driven modern innovation in TCM concepts.展开更多
Privacy-sensitive data encounter immense security and usability challenges in processing,analyzing,and sharing.Meanwhile,traditional privacy data desensitization methods suffer from issues such as poor quality and low...Privacy-sensitive data encounter immense security and usability challenges in processing,analyzing,and sharing.Meanwhile,traditional privacy data desensitization methods suffer from issues such as poor quality and low usability after desensitization.Therefore,a text data desensitization model that combines Transformer and Wasserstein Text convolutional Generative Adversarial Network(Trans-WTGAN)is proposed.Transformer as the generator and its self-attention mechanism can handle long-range dependencies,enabling the generated of higher-quality text;Text Convolutional Neural Network(TextCNN)integrates the idea of Wasserstein as the discriminator to enhance the stability of model training;and the strategy gradient scheme of reinforcement learning is employed.Reinforcement learning utilizes the policy gradient scheme as the updating method of generator parameters,ensuring the generated data retains the original key features and maintains a certain level of usability.The experimental results indicate that the proposed model scheme holds a greater advantage over existing methods in terms of text quality and structural consistency,can guarantee the desensitization effect,and ensures the usability of the privacy-sensitive data to a certain extent after desensitization,facilitates the simulation of the development environment for the use of real data and the analysis and sharing of data.展开更多
The limited energy density of lithium-ion capacitors poses a significant obstacle to their widespread application,primarily stemming from the inability of the electrodes to simultaneously fulfill both high energy dens...The limited energy density of lithium-ion capacitors poses a significant obstacle to their widespread application,primarily stemming from the inability of the electrodes to simultaneously fulfill both high energy density and rapid charging requirements.Experimental data demonstrate that a directional particle configuration can enhance charging speed while maintaining high-capacity density,but it is rarely discussed.Here,we have developed a particle-level electrochemical model capable of reconstructing an electrode with a directional particle configuration.By employing this method,an investigation was conducted to explore how the spatial morphology characteristics of particle configuration impact the energy storage characteristics of electrodes.Results demonstrate that rational particle configuration can effectively enhance the transport of lithium ions and create additional space for lithium-ion storage.With the same particle size distribution,the best electrode can increase the discharge capacity by up to132.4% and increase the charging SOC by 11.3% compared to the ordinary electrode under the condition of 6 C.These findings provide a further understanding of the energy storage mechanism inside the anisotropic particle distribution electrode,which is important for developing high-performance lithium-ion capacitors.展开更多
To achieve effective intraday dispatch of photovoltaic(PV)power generation systems,a reliable ultra-shortterm power generation forecasting model is required.Based on a gradient boosting strategy and a dendritic networ...To achieve effective intraday dispatch of photovoltaic(PV)power generation systems,a reliable ultra-shortterm power generation forecasting model is required.Based on a gradient boosting strategy and a dendritic network,this paper proposes a novel ensemble prediction model,named gradient boosting dendritic network(GBDD)model which can reduce the forecast error by learning the relationship between forecast residuals and meteorological factors during the training of sub-models by means of a greedy function approximation.Unlike other machine learning models,the GBDD proposed is able to make fuller use of all meteorological factor data and has a good model interpretation.In addition,based on the structure of GBDD,this paper proposes a strategy that can improve the prediction performance of other types of prediction models.The GBDD is trained by analyzing the relationship between prediction errors and meteorological factors for compensating the prediction results of other prediction models.The experimental results show that the GBDD proposed has the benefit of achieving a higher PV power prediction accuracy for PV power generation and can be used to improve the prediction performance of other prediction models.展开更多
Although Chinese-English machine translation is a resource-rich language pair,the problem of data sparsity still exists.For example,for the translation of some specific domains or low-frequency words,the amount of par...Although Chinese-English machine translation is a resource-rich language pair,the problem of data sparsity still exists.For example,for the translation of some specific domains or low-frequency words,the amount of parallel corpus is limited,which makes it difficult to improve the translation quality of the model in these scenarios.Neural machine translation models usually need a large amount of alignment data to train,otherwise they are prone to over-fitting.Neural machine translation models are slow to train and decode,especially when dealing with long sentences or complex structures,which limits their efficiency in real-time application scenarios.Chinese-English machine translation can help people overcome the language barrier and promote the communication and cooperation between people with different language backgrounds,which is of great significance for international business,academic exchanges and cultural exchanges.This paper proposes a Chinese-English neural machine translation model based on generative adversarial network.This model applies the generative adversarial network to neural machine translation,and further optimizes the adversarial learning based neural machine translation model by improving the monotone decoding sequence from left to right or from right to left in the original machine translation model.At the same time,unlike previous generative adversarial networks,neural machine translation models are actually a sequence of discrete symbols that map source language sentences to target language sentences,both in discontinuous spaces.In this case,the generative adversarial network fails to transmit the gradient properly,causing the generator to lose its update direction.By introducing the strategy gradient algorithm in reinforcement learning,the generator optimization problem in adversarial learning is solved,and the translation performance of the model is improved.Finally,experiments on public data sets show that the proposed model can effectively improve translation quality compared with other advanced models.展开更多
基金supported by the National Natural Science Foundation of China(Grant Nos.:82174259 and 82304997)China Postdoctoral Followship Program of CPSF(Grant No.:GZC20233202)+4 种基金China Postdoctoral Science Foundation(Grant No.:2024M753698)the Key Research and Development Program of Hunan Province of China(Grant Nos.:2023SK2021 and 2022SK2015)the Natural Science Foundation of Hunan Province,China(Grant Nos.:2024JJ6632,2022JJ40853,and 2021JJ31117)the Hunan Traditional Chinese Medicine Scientific Research Program,China(Grant Nos.:B2024113,B2024114,and 2021032)the Fundamental Research Funds for the Central Universities of Central South University,China(Grant No.:1053320232786).
文摘Traditional Chinese medicine(TCM)exerts integrative effects on complex diseases owing to the characteristics of multiple components with multiple targets.However,the syndrome-based system of diagnosis and treatment in TCM can easily lead to bias because of varying medication preferences among physicians,which has been a major challenge in the global acceptance and application of TCM.Therefore,a standardized TCM prescription system needs to be explored to promote its clinical application.In this study,we first developed a gradient weighted disease-target-herbal ingredient-herb network to aid TCM formulation.We tested its efficacy against intracerebral hemorrhage(ICH).First,the top 100 ICH targets in the GeneCards database were screened according to their relevance scores.Then,SymMap and Traditional Chinese Medicine Systems Pharmacology(TCMSP)databases were applied to find out the target-related ingredients and ingredient-containing herbs,respectively.The relevance of the resulting ingredients and herbs to ICH was determined by adding the relevance scores of the corresponding targets.The top five ICH therapeutic herbs were combined to form a tailored TCM prescriptions.The absorbed components in the serum were detected.In a mouse model of ICH,the new prescription exerted multifaceted effects,including improved neurological function,as well as attenuated neuronal damage,cell apoptosis,vascular leakage,and neuroinflammation.These effects matched well with the core pathological changes in ICH.The multi-targets-directed gradient-weighting strategy presents a promising avenue for tailoring precise,multipronged,unbiased,and standardized TCM prescriptions for complex diseases.This study provides a paradigm for advanced achievements-driven modern innovation in TCM concepts.
基金supported by the National Natural Science Foundation of China(No.62262013).
文摘Privacy-sensitive data encounter immense security and usability challenges in processing,analyzing,and sharing.Meanwhile,traditional privacy data desensitization methods suffer from issues such as poor quality and low usability after desensitization.Therefore,a text data desensitization model that combines Transformer and Wasserstein Text convolutional Generative Adversarial Network(Trans-WTGAN)is proposed.Transformer as the generator and its self-attention mechanism can handle long-range dependencies,enabling the generated of higher-quality text;Text Convolutional Neural Network(TextCNN)integrates the idea of Wasserstein as the discriminator to enhance the stability of model training;and the strategy gradient scheme of reinforcement learning is employed.Reinforcement learning utilizes the policy gradient scheme as the updating method of generator parameters,ensuring the generated data retains the original key features and maintains a certain level of usability.The experimental results indicate that the proposed model scheme holds a greater advantage over existing methods in terms of text quality and structural consistency,can guarantee the desensitization effect,and ensures the usability of the privacy-sensitive data to a certain extent after desensitization,facilitates the simulation of the development environment for the use of real data and the analysis and sharing of data.
基金This work is supported by the National Key R&D Program of China(2021YFB2400400).
文摘The limited energy density of lithium-ion capacitors poses a significant obstacle to their widespread application,primarily stemming from the inability of the electrodes to simultaneously fulfill both high energy density and rapid charging requirements.Experimental data demonstrate that a directional particle configuration can enhance charging speed while maintaining high-capacity density,but it is rarely discussed.Here,we have developed a particle-level electrochemical model capable of reconstructing an electrode with a directional particle configuration.By employing this method,an investigation was conducted to explore how the spatial morphology characteristics of particle configuration impact the energy storage characteristics of electrodes.Results demonstrate that rational particle configuration can effectively enhance the transport of lithium ions and create additional space for lithium-ion storage.With the same particle size distribution,the best electrode can increase the discharge capacity by up to132.4% and increase the charging SOC by 11.3% compared to the ordinary electrode under the condition of 6 C.These findings provide a further understanding of the energy storage mechanism inside the anisotropic particle distribution electrode,which is important for developing high-performance lithium-ion capacitors.
基金supported by the National Natural Science Foundation of China(Grant Nos.61973322 and 62103443)the Natural Science Foundation of Hunan Province,China(Grant No.2022JJ40630).
文摘To achieve effective intraday dispatch of photovoltaic(PV)power generation systems,a reliable ultra-shortterm power generation forecasting model is required.Based on a gradient boosting strategy and a dendritic network,this paper proposes a novel ensemble prediction model,named gradient boosting dendritic network(GBDD)model which can reduce the forecast error by learning the relationship between forecast residuals and meteorological factors during the training of sub-models by means of a greedy function approximation.Unlike other machine learning models,the GBDD proposed is able to make fuller use of all meteorological factor data and has a good model interpretation.In addition,based on the structure of GBDD,this paper proposes a strategy that can improve the prediction performance of other types of prediction models.The GBDD is trained by analyzing the relationship between prediction errors and meteorological factors for compensating the prediction results of other prediction models.The experimental results show that the GBDD proposed has the benefit of achieving a higher PV power prediction accuracy for PV power generation and can be used to improve the prediction performance of other prediction models.
文摘Although Chinese-English machine translation is a resource-rich language pair,the problem of data sparsity still exists.For example,for the translation of some specific domains or low-frequency words,the amount of parallel corpus is limited,which makes it difficult to improve the translation quality of the model in these scenarios.Neural machine translation models usually need a large amount of alignment data to train,otherwise they are prone to over-fitting.Neural machine translation models are slow to train and decode,especially when dealing with long sentences or complex structures,which limits their efficiency in real-time application scenarios.Chinese-English machine translation can help people overcome the language barrier and promote the communication and cooperation between people with different language backgrounds,which is of great significance for international business,academic exchanges and cultural exchanges.This paper proposes a Chinese-English neural machine translation model based on generative adversarial network.This model applies the generative adversarial network to neural machine translation,and further optimizes the adversarial learning based neural machine translation model by improving the monotone decoding sequence from left to right or from right to left in the original machine translation model.At the same time,unlike previous generative adversarial networks,neural machine translation models are actually a sequence of discrete symbols that map source language sentences to target language sentences,both in discontinuous spaces.In this case,the generative adversarial network fails to transmit the gradient properly,causing the generator to lose its update direction.By introducing the strategy gradient algorithm in reinforcement learning,the generator optimization problem in adversarial learning is solved,and the translation performance of the model is improved.Finally,experiments on public data sets show that the proposed model can effectively improve translation quality compared with other advanced models.
