System upgrades in unmanned systems have made Unmanned Aerial Vehicle(UAV)-based patrolling and monitoring a preferred solution for ocean surveillance.However,dynamic environments and large-scale deployments pose sign...System upgrades in unmanned systems have made Unmanned Aerial Vehicle(UAV)-based patrolling and monitoring a preferred solution for ocean surveillance.However,dynamic environments and large-scale deployments pose significant challenges for efficient decision-making,necessitating a modular multiagent control system.Deep Reinforcement Learning(DRL)and Decision Tree(DT)have been utilized for these complex decision-making tasks,but each has its limitations:DRL is highly adaptive but lacks interpretability,while DT is inherently interpretable but has limited adaptability.To overcome these challenges,we propose the Adaptive Interpretable Decision Tree(AIDT),an evolutionary-based algorithm that is both adaptable to diverse environmental settings and highly interpretable in its decision-making processes.We first construct a Markov decision process(MDP)-based simulation environment using the Cooperative Submarine Search task as a representative scenario for training and testing the proposed method.Specifically,we use the heat map as a state variable to address the issue of multi-agent input state proliferation.Next,we introduce the curiosity-guiding intrinsic reward to encourage comprehensive exploration and enhance algorithm performance.Additionally,we incorporate decision tree size as an influence factor in the adaptation process to balance task completion with computational efficiency.To further improve the generalization capability of the decision tree,we apply a normalization method to ensure consistent processing of input states.Finally,we validate the proposed algorithm in different environmental settings,and the results demonstrate both its adaptability and interpretability.展开更多
The belief rule-based(BRB)system has been popular in complexity system modeling due to its good interpretability.However,the current mainstream optimization methods of the BRB systems only focus on modeling accuracy b...The belief rule-based(BRB)system has been popular in complexity system modeling due to its good interpretability.However,the current mainstream optimization methods of the BRB systems only focus on modeling accuracy but ignore the interpretability.The single-objective optimization strategy has been applied in the interpretability-accuracy trade-off by inte-grating accuracy and interpretability into an optimization objec-tive.But the integration has a greater impact on optimization results with strong subjectivity.Thus,a multi-objective optimiza-tion framework in the modeling of BRB systems with inter-pretability-accuracy trade-off is proposed in this paper.Firstly,complexity and accuracy are taken as two independent opti-mization goals,and uniformity as a constraint to give the mathe-matical description.Secondly,a classical multi-objective opti-mization algorithm,nondominated sorting genetic algorithm II(NSGA-II),is utilized as an optimization tool to give a set of BRB systems with different accuracy and complexity.Finally,a pipeline leakage detection case is studied to verify the feasibility and effectiveness of the developed multi-objective optimization.The comparison illustrates that the proposed multi-objective optimization framework can effectively avoid the subjectivity of single-objective optimization,and has capability of joint optimiz-ing the structure and parameters of BRB systems with inter-pretability-accuracy trade-off.展开更多
A new approach is proposed in this study for accountable capability improvement based on interpretable capability evaluation using the belief rule base(BRB).Firstly,a capability evaluation model is constructed and opt...A new approach is proposed in this study for accountable capability improvement based on interpretable capability evaluation using the belief rule base(BRB).Firstly,a capability evaluation model is constructed and optimized.Then,the key sub-capabilities are identified by quantitatively calculating the contributions made by each sub-capability to the overall capability.Finally,the overall capability is improved by optimizing the identified key sub-capabilities.The theoretical contributions of the proposed approach are as follows.(i)An interpretable capability evaluation model is constructed by employing BRB which can provide complete access to decision-makers.(ii)Key sub-capabilities are identified according to the quantitative contribution analysis results.(iii)Accountable capability improvement is carried out by only optimizing the identified key sub-capabilities.Case study results show that“Surveillance”,“Positioning”,and“Identification”are identified as key sub-capabilities with a summed contribution of 75.55%in an analytical and deducible fashion based on the interpretable capability evaluation model.As a result,the overall capability is improved by optimizing only the identified key sub-capabilities.The overall capability can be greatly improved from 59.20%to 81.80%with a minimum cost of 397.Furthermore,this paper also investigates how optimizing the BRB with more collected data would affect the evaluation results:only optimizing“Surveillance”and“Positioning”can also improve the overall capability to 81.34%with a cost of 370,which thus validates the efficiency of the proposed approach.展开更多
以基因、转录、蛋白质等生命组学为主体的生物大数据快速积累和以深度学习为代表的人工智能技术迅猛发展,催生出各种类别的生物大模型(biological large models)。复杂的深度学习架构、巨大的参数量和算力需求、以及海量的预训练数据等...以基因、转录、蛋白质等生命组学为主体的生物大数据快速积累和以深度学习为代表的人工智能技术迅猛发展,催生出各种类别的生物大模型(biological large models)。复杂的深度学习架构、巨大的参数量和算力需求、以及海量的预训练数据等是大模型技术的主要特征。预训练数据类别及参数量一定程度上决定了大模型所具备的能力强弱,而不同的模型架构则可支撑不同类别的下游任务。近两年,围绕DNA/RNA/蛋白质等生物序列与单细胞表达图谱等组学数据分析挖掘、大分子结构预测、新型药物设计和功能机制解析等多种应用场景,涌现了多种通用或专用大模型,展示出其在生物医学研究及转化应用等领域的巨大潜力。本文旨在结合不同类别的生物数据特点和研究应用需求,概述生物数据特征及其用于生物大模型训练的技术方法,并进一步综述现有大模型在生物医学研究及疾病诊疗中的应用进展,为提升生物大模型能力、拓展应用范围提供新的思路。展开更多
文摘System upgrades in unmanned systems have made Unmanned Aerial Vehicle(UAV)-based patrolling and monitoring a preferred solution for ocean surveillance.However,dynamic environments and large-scale deployments pose significant challenges for efficient decision-making,necessitating a modular multiagent control system.Deep Reinforcement Learning(DRL)and Decision Tree(DT)have been utilized for these complex decision-making tasks,but each has its limitations:DRL is highly adaptive but lacks interpretability,while DT is inherently interpretable but has limited adaptability.To overcome these challenges,we propose the Adaptive Interpretable Decision Tree(AIDT),an evolutionary-based algorithm that is both adaptable to diverse environmental settings and highly interpretable in its decision-making processes.We first construct a Markov decision process(MDP)-based simulation environment using the Cooperative Submarine Search task as a representative scenario for training and testing the proposed method.Specifically,we use the heat map as a state variable to address the issue of multi-agent input state proliferation.Next,we introduce the curiosity-guiding intrinsic reward to encourage comprehensive exploration and enhance algorithm performance.Additionally,we incorporate decision tree size as an influence factor in the adaptation process to balance task completion with computational efficiency.To further improve the generalization capability of the decision tree,we apply a normalization method to ensure consistent processing of input states.Finally,we validate the proposed algorithm in different environmental settings,and the results demonstrate both its adaptability and interpretability.
基金supported by the National Natural Science Foundation of China(71901212)the Science and Technology Innovation Program of Hunan Province(2020RC4046).
文摘The belief rule-based(BRB)system has been popular in complexity system modeling due to its good interpretability.However,the current mainstream optimization methods of the BRB systems only focus on modeling accuracy but ignore the interpretability.The single-objective optimization strategy has been applied in the interpretability-accuracy trade-off by inte-grating accuracy and interpretability into an optimization objec-tive.But the integration has a greater impact on optimization results with strong subjectivity.Thus,a multi-objective optimiza-tion framework in the modeling of BRB systems with inter-pretability-accuracy trade-off is proposed in this paper.Firstly,complexity and accuracy are taken as two independent opti-mization goals,and uniformity as a constraint to give the mathe-matical description.Secondly,a classical multi-objective opti-mization algorithm,nondominated sorting genetic algorithm II(NSGA-II),is utilized as an optimization tool to give a set of BRB systems with different accuracy and complexity.Finally,a pipeline leakage detection case is studied to verify the feasibility and effectiveness of the developed multi-objective optimization.The comparison illustrates that the proposed multi-objective optimization framework can effectively avoid the subjectivity of single-objective optimization,and has capability of joint optimiz-ing the structure and parameters of BRB systems with inter-pretability-accuracy trade-off.
基金supported by the National Natural Science Foundation of China(72471067,72431011,72471238,72231011,62303474,72301286)the Fundamental Research Funds for the Provincial Universities of Zhejiang(GK239909299001-010).
文摘A new approach is proposed in this study for accountable capability improvement based on interpretable capability evaluation using the belief rule base(BRB).Firstly,a capability evaluation model is constructed and optimized.Then,the key sub-capabilities are identified by quantitatively calculating the contributions made by each sub-capability to the overall capability.Finally,the overall capability is improved by optimizing the identified key sub-capabilities.The theoretical contributions of the proposed approach are as follows.(i)An interpretable capability evaluation model is constructed by employing BRB which can provide complete access to decision-makers.(ii)Key sub-capabilities are identified according to the quantitative contribution analysis results.(iii)Accountable capability improvement is carried out by only optimizing the identified key sub-capabilities.Case study results show that“Surveillance”,“Positioning”,and“Identification”are identified as key sub-capabilities with a summed contribution of 75.55%in an analytical and deducible fashion based on the interpretable capability evaluation model.As a result,the overall capability is improved by optimizing only the identified key sub-capabilities.The overall capability can be greatly improved from 59.20%to 81.80%with a minimum cost of 397.Furthermore,this paper also investigates how optimizing the BRB with more collected data would affect the evaluation results:only optimizing“Surveillance”and“Positioning”can also improve the overall capability to 81.34%with a cost of 370,which thus validates the efficiency of the proposed approach.
文摘以基因、转录、蛋白质等生命组学为主体的生物大数据快速积累和以深度学习为代表的人工智能技术迅猛发展,催生出各种类别的生物大模型(biological large models)。复杂的深度学习架构、巨大的参数量和算力需求、以及海量的预训练数据等是大模型技术的主要特征。预训练数据类别及参数量一定程度上决定了大模型所具备的能力强弱,而不同的模型架构则可支撑不同类别的下游任务。近两年,围绕DNA/RNA/蛋白质等生物序列与单细胞表达图谱等组学数据分析挖掘、大分子结构预测、新型药物设计和功能机制解析等多种应用场景,涌现了多种通用或专用大模型,展示出其在生物医学研究及转化应用等领域的巨大潜力。本文旨在结合不同类别的生物数据特点和研究应用需求,概述生物数据特征及其用于生物大模型训练的技术方法,并进一步综述现有大模型在生物医学研究及疾病诊疗中的应用进展,为提升生物大模型能力、拓展应用范围提供新的思路。
