In this study,we conducted an experiment to construct multi-model ensemble(MME)predictions for the El Niño-Southern Oscillation(ENSO)using a neural network,based on hindcast data released from five coupled oceana...In this study,we conducted an experiment to construct multi-model ensemble(MME)predictions for the El Niño-Southern Oscillation(ENSO)using a neural network,based on hindcast data released from five coupled oceanatmosphere models,which exhibit varying levels of complexity.This nonlinear approach demonstrated extraordinary superiority and effectiveness in constructing ENSO MME.Subsequently,we employed the leave-one-out crossvalidation and the moving base methods to further validate the robustness of the neural network model in the formulation of ENSO MME.In conclusion,the neural network algorithm outperforms the conventional approach of assigning a uniform weight to all models.This is evidenced by an enhancement in correlation coefficients and reduction in prediction errors,which have the potential to provide a more accurate ENSO forecast.展开更多
Given the extremely high inter-patient heterogeneity of acute myeloid leukemia(AML),the identification of biomarkers for prognostic assessment and therapeutic guidance is critical.Cell surface markers(CSMs)have been s...Given the extremely high inter-patient heterogeneity of acute myeloid leukemia(AML),the identification of biomarkers for prognostic assessment and therapeutic guidance is critical.Cell surface markers(CSMs)have been shown to play an important role in AML leukemogenesis and progression.In the current study,we evaluated the prognostic potential of all human CSMs in 130 AML patients from The Cancer Genome Atlas(TCGA)based on differential gene expression analysis and univariable Cox proportional hazards regression analysis.By using multi-model analysis,including Adaptive LASSO regression,LASSO regression,and Elastic Net,we constructed a 9-CSMs prognostic model for risk stratification of the AML patients.The predictive value of the 9-CSMs risk score was further validated at the transcriptome and proteome levels.Multivariable Cox regression analysis showed that the risk score was an independent prognostic factor for the AML patients.The AML patients with high 9-CSMs risk scores had a shorter overall and event-free survival time than those with low scores.Notably,single-cell RNA-sequencing analysis indicated that patients with high 9-CSMs risk scores exhibited chemotherapy resistance.Furthermore,PI3K inhibitors were identified as potential treatments for these high-risk patients.In conclusion,we constructed a 9-CSMs prognostic model that served as an independent prognostic factor for the survival of AML patients and held the potential for guiding drug therapy.展开更多
Traditional global sensitivity analysis(GSA)neglects the epistemic uncertainties associated with the probabilistic characteristics(i.e.type of distribution type and its parameters)of input rock properties emanating du...Traditional global sensitivity analysis(GSA)neglects the epistemic uncertainties associated with the probabilistic characteristics(i.e.type of distribution type and its parameters)of input rock properties emanating due to the small size of datasets while mapping the relative importance of properties to the model response.This paper proposes an augmented Bayesian multi-model inference(BMMI)coupled with GSA methodology(BMMI-GSA)to address this issue by estimating the imprecision in the momentindependent sensitivity indices of rock structures arising from the small size of input data.The methodology employs BMMI to quantify the epistemic uncertainties associated with model type and parameters of input properties.The estimated uncertainties are propagated in estimating imprecision in moment-independent Borgonovo’s indices by employing a reweighting approach on candidate probabilistic models.The proposed methodology is showcased for a rock slope prone to stress-controlled failure in the Himalayan region of India.The proposed methodology was superior to the conventional GSA(neglects all epistemic uncertainties)and Bayesian coupled GSA(B-GSA)(neglects model uncertainty)due to its capability to incorporate the uncertainties in both model type and parameters of properties.Imprecise Borgonovo’s indices estimated via proposed methodology provide the confidence intervals of the sensitivity indices instead of their fixed-point estimates,which makes the user more informed in the data collection efforts.Analyses performed with the varying sample sizes suggested that the uncertainties in sensitivity indices reduce significantly with the increasing sample sizes.The accurate importance ranking of properties was only possible via samples of large sizes.Further,the impact of the prior knowledge in terms of prior ranges and distributions was significant;hence,any related assumption should be made carefully.展开更多
In the continually evolving landscape of data-driven methodologies addressing car crash patterns,a holistic analysis remains critical to decode the complex nuances of this phenomenon.This study bridges this knowledge ...In the continually evolving landscape of data-driven methodologies addressing car crash patterns,a holistic analysis remains critical to decode the complex nuances of this phenomenon.This study bridges this knowledge gap with a robust examination of car crash occurrence dynamics and the influencing variables in the Greater Melbourne area,Australia.We employed a comprehensive multi-model machine learning and geospatial analytics approach,unveiling the complicated interactions intrinsic to vehicular incidents.By harnessing Random Forest with SHAP(Shapley Additive Explanations),GLR(Generalized Linear Regression),and GWR(Geographically Weighted Regression),our research not only highlighted pivotal contributing elements but also enriched our findings by capturing often overlooked complexities.Using the Random Forest model,essential factors were emphasized,and with the aid of SHAP,we accessed the interaction of these factors.To complement our methodology,we incorporated hexagonalized geographic units,refining the granularity of crash density evaluations.In our multi-model study of car crash dynamics in Greater Melbourne,road geometry emerged as a key factor,with intersections showing a significant positive correlation with crashes.The average land surface temperature had variable significance across scales.Socio-economically,regions with a higher proportion of childless populations were identified as more prone to accidents.Public transit usage displayed a strong positive association with crashes,especially in densely populated areas.The convergence of insights from both Generalized Linear Regression and Random Forest’s SHAP values offered a comprehensive understanding of underlying patterns,pinpointing high-risk zones and influential determinants.These findings offer pivotal insights for targeted safety interventions in Greater Melbourne,Australia.展开更多
随着深度学习技术的快速进步,大型语言模型(Large Language Models,LLM)在语言理解和生成方面展现出卓越的能力,其在医疗领域的应用也日益广泛。然而,这些模型在处理复杂医疗问题时仍面临诸多挑战。传统医疗对话系统在应对多轮对话的复...随着深度学习技术的快速进步,大型语言模型(Large Language Models,LLM)在语言理解和生成方面展现出卓越的能力,其在医疗领域的应用也日益广泛。然而,这些模型在处理复杂医疗问题时仍面临诸多挑战。传统医疗对话系统在应对多轮对话的复杂性和话题变化时存在局限性。此外,医学领域对错误决策的容忍度极低,因此系统生成回复的可靠性和可解释性显得尤为重要。为了解决这些问题,该文研究了多智能体协同医疗辅助决策对话机制,旨在通过多智能体协作来提升医疗系统生成辅助建议的合理性和准确性。选择了CMB数据集进行实验,重点关注三个医疗任务:规培结业、执业医师和医学考研。通过实验评估,对该方法的性能进行了分析,并与其他医疗大模型进行了对比。实验结果表明多智能体协作在辅助预测的性能方面显著优于单一医疗大模型。展开更多
基金The fund from Southern Marine Science and Engineering Guangdong Laboratory(Zhuhai)under contract No.SML2021SP310the National Natural Science Foundation of China under contract Nos 42227901 and 42475061the Key R&D Program of Zhejiang Province under contract No.2024C03257.
文摘In this study,we conducted an experiment to construct multi-model ensemble(MME)predictions for the El Niño-Southern Oscillation(ENSO)using a neural network,based on hindcast data released from five coupled oceanatmosphere models,which exhibit varying levels of complexity.This nonlinear approach demonstrated extraordinary superiority and effectiveness in constructing ENSO MME.Subsequently,we employed the leave-one-out crossvalidation and the moving base methods to further validate the robustness of the neural network model in the formulation of ENSO MME.In conclusion,the neural network algorithm outperforms the conventional approach of assigning a uniform weight to all models.This is evidenced by an enhancement in correlation coefficients and reduction in prediction errors,which have the potential to provide a more accurate ENSO forecast.
基金supported by the National Natural Science Foundation of China(Grant Nos.32200590 to K.L.,81972358 to Q.W.,91959113 to Q.W.,and 82372897 to Q.W.)the Natural Science Foundation of Jiangsu Province(Grant No.BK20210530 to K.L.).
文摘Given the extremely high inter-patient heterogeneity of acute myeloid leukemia(AML),the identification of biomarkers for prognostic assessment and therapeutic guidance is critical.Cell surface markers(CSMs)have been shown to play an important role in AML leukemogenesis and progression.In the current study,we evaluated the prognostic potential of all human CSMs in 130 AML patients from The Cancer Genome Atlas(TCGA)based on differential gene expression analysis and univariable Cox proportional hazards regression analysis.By using multi-model analysis,including Adaptive LASSO regression,LASSO regression,and Elastic Net,we constructed a 9-CSMs prognostic model for risk stratification of the AML patients.The predictive value of the 9-CSMs risk score was further validated at the transcriptome and proteome levels.Multivariable Cox regression analysis showed that the risk score was an independent prognostic factor for the AML patients.The AML patients with high 9-CSMs risk scores had a shorter overall and event-free survival time than those with low scores.Notably,single-cell RNA-sequencing analysis indicated that patients with high 9-CSMs risk scores exhibited chemotherapy resistance.Furthermore,PI3K inhibitors were identified as potential treatments for these high-risk patients.In conclusion,we constructed a 9-CSMs prognostic model that served as an independent prognostic factor for the survival of AML patients and held the potential for guiding drug therapy.
文摘Traditional global sensitivity analysis(GSA)neglects the epistemic uncertainties associated with the probabilistic characteristics(i.e.type of distribution type and its parameters)of input rock properties emanating due to the small size of datasets while mapping the relative importance of properties to the model response.This paper proposes an augmented Bayesian multi-model inference(BMMI)coupled with GSA methodology(BMMI-GSA)to address this issue by estimating the imprecision in the momentindependent sensitivity indices of rock structures arising from the small size of input data.The methodology employs BMMI to quantify the epistemic uncertainties associated with model type and parameters of input properties.The estimated uncertainties are propagated in estimating imprecision in moment-independent Borgonovo’s indices by employing a reweighting approach on candidate probabilistic models.The proposed methodology is showcased for a rock slope prone to stress-controlled failure in the Himalayan region of India.The proposed methodology was superior to the conventional GSA(neglects all epistemic uncertainties)and Bayesian coupled GSA(B-GSA)(neglects model uncertainty)due to its capability to incorporate the uncertainties in both model type and parameters of properties.Imprecise Borgonovo’s indices estimated via proposed methodology provide the confidence intervals of the sensitivity indices instead of their fixed-point estimates,which makes the user more informed in the data collection efforts.Analyses performed with the varying sample sizes suggested that the uncertainties in sensitivity indices reduce significantly with the increasing sample sizes.The accurate importance ranking of properties was only possible via samples of large sizes.Further,the impact of the prior knowledge in terms of prior ranges and distributions was significant;hence,any related assumption should be made carefully.
基金Linking Health,Place and Urban Planning through the Australian Urban Observatory by Ian Potter Foundation,Australia.
文摘In the continually evolving landscape of data-driven methodologies addressing car crash patterns,a holistic analysis remains critical to decode the complex nuances of this phenomenon.This study bridges this knowledge gap with a robust examination of car crash occurrence dynamics and the influencing variables in the Greater Melbourne area,Australia.We employed a comprehensive multi-model machine learning and geospatial analytics approach,unveiling the complicated interactions intrinsic to vehicular incidents.By harnessing Random Forest with SHAP(Shapley Additive Explanations),GLR(Generalized Linear Regression),and GWR(Geographically Weighted Regression),our research not only highlighted pivotal contributing elements but also enriched our findings by capturing often overlooked complexities.Using the Random Forest model,essential factors were emphasized,and with the aid of SHAP,we accessed the interaction of these factors.To complement our methodology,we incorporated hexagonalized geographic units,refining the granularity of crash density evaluations.In our multi-model study of car crash dynamics in Greater Melbourne,road geometry emerged as a key factor,with intersections showing a significant positive correlation with crashes.The average land surface temperature had variable significance across scales.Socio-economically,regions with a higher proportion of childless populations were identified as more prone to accidents.Public transit usage displayed a strong positive association with crashes,especially in densely populated areas.The convergence of insights from both Generalized Linear Regression and Random Forest’s SHAP values offered a comprehensive understanding of underlying patterns,pinpointing high-risk zones and influential determinants.These findings offer pivotal insights for targeted safety interventions in Greater Melbourne,Australia.
文摘随着深度学习技术的快速进步,大型语言模型(Large Language Models,LLM)在语言理解和生成方面展现出卓越的能力,其在医疗领域的应用也日益广泛。然而,这些模型在处理复杂医疗问题时仍面临诸多挑战。传统医疗对话系统在应对多轮对话的复杂性和话题变化时存在局限性。此外,医学领域对错误决策的容忍度极低,因此系统生成回复的可靠性和可解释性显得尤为重要。为了解决这些问题,该文研究了多智能体协同医疗辅助决策对话机制,旨在通过多智能体协作来提升医疗系统生成辅助建议的合理性和准确性。选择了CMB数据集进行实验,重点关注三个医疗任务:规培结业、执业医师和医学考研。通过实验评估,对该方法的性能进行了分析,并与其他医疗大模型进行了对比。实验结果表明多智能体协作在辅助预测的性能方面显著优于单一医疗大模型。
