Distributed blackboard decision-making framework for collaborative planning based on nested genetic algorithm

A distributed blackboard decision-making framework for collaborative planning based on nested genetic algorithm （NGA） is proposed. By using blackboard-based communication paradigm and shared data structure, multiple decision-makers （DMs） can collaboratively solve the tasks-platforms allocation scheduling problems dynamically through the coordinator. This methodo- logy combined with NGA maximizes tasks execution accuracy, also minimizes the weighted total workload of the DM which is measured in terms of intra-DM and inter-DM coordination. The intra-DM employs an optimization-based scheduling algorithm to match the tasks-platforms assignment request with its own platforms. The inter-DM coordinates the exchange of collaborative request information and platforms among DMs using the blackboard architecture. The numerical result shows that the proposed black- board DM framework based on NGA can obtain a near-optimal solution for the tasks-platforms collaborative planning problem. The assignment of platforms-tasks and the patterns of coordination can achieve a nice trade-off between intra-DM and inter-DM coordination workload.

Multi-target Collaborative Combat Decision-Making by Improved Particle Swarm Optimizer

A decision-making problem of missile-target assignment with a novel particle swarm optimization algorithm is proposed when it comes to a multiple target collaborative combat situation.The threat function is established to describe air combat situation.Optimization function is used to find an optimal missile-target assignment.An improved particle swarm optimization algorithm is utilized to figure out the optimization function with less parameters,which is based on the adaptive random learning approach.According to the coordinated attack tactics,there are some adjustments to the assignment.Simulation example results show that it is an effective algorithm to handle with the decision-making problem of the missile-target assignment(MTA)in air combat.

Study on Multi-enterprise Collaborative Resource Planning Based Process-oriented Decision Model

Aiming to share the information,knowledge and optimizing resource via collaborating with multiple external partners across their supply chains,the concept model and system framework of multi-enterprises collaborative resource planning (MECORP) are put forward.While there is Considerable pressure to improve the operation of MECORP system,their inherent complexity can make modelling a MECORP system a difficult task.Yet there could be considerable benefits in designing MECORP taking into account the operation of the system.In order to address the central research issue of developing of a methodology that can assist a manager in making decisions by modelling the operation of MECORP system.The methodology called process-oriented deci- sion model (PODM) is presented in the paper.This uses an abstracted network to model MECORP system.The MECORP system supported by PODM,can effective optimize the manifold resource,coordinate the relationship of multiple partners and assist deci- sion.Finally,an industry excample of MECORP system is described to illustrate the application of PODM.

Research on Collaboration Decision Design of Complex C2 System

The design of collaboration decision of C2 system is one of the puzzles which dicision science studies in complex system. To solve the contravention between the theory of collaboration decision design and development requirement in distributed C2 system,three-stage design approach is proposed to research coherence and optimization by which decision-maker carries out decision regulations. First,getting information and decision process are described; decision indexes and regulation models of collaboration are established. And then,a test circumstance is designed and established for measuring various decision-maker’s capabilities of carrying out decision regulation by simulation and getting their load capability parameters. Finally,the obtained parameters from the experiment are disposed and substituted into the original models for proving the coherence of decision regulations. As a result,it is feasible for three-stage approach to design collaboration decision,and decision regulations can satisfy various decision-maker requirements.

Perceptions of Collaboration and Satisfaction with Collaboration Regarding Care Decision-Making in Intensive Care Units in Japan: A National Survey

Multi-professional collaboration is being promoted worldwide as a response to the need for sophisticated medical care and for catering to patients’ diverse needs. Patients in Intensive Care Units (ICUs) are seriously ill, and their families may be at risk depending on the patient’s situation. Considering these characteristics of patients and families, there is a strong need for multi-professional collaboration within ICUs. The purpose of this descriptive study was to examine recognition and other factors related to collaboration and satisfaction involving care decisions in Japanese ICUs. A mail survey about collaboration of activities and systems was sent to physicians, clinical engineers, and nurses working in ICUs in Japan, 387 consented to participate in this study. Results showed that satisfaction scores were generally high among the three aforementioned professions, but collaboration scores on deciding care for patients showed significant differences (p < 0.05). The total collaboration score was the highest among physicians (36.7 ± 6.7 points), followed by nurses (32.8 ± 7.4 points), and CEs (32.8 ± 7.4 points). The factors that commonly affected collaboration scores were the satisfaction score and the ability to collaborate with other professionals and set team medical care as a goal. Moreover, it is worth noting that the degree of difficulty in collaboration negatively affected this factor. On the other hand, other factors differed among the three professions, suggesting that the purpose and need for collaboration differ depending on the profession.

SVM-DT-Based Adaptive and Collaborative Intrusion Detection

As a primary defense technique, intrusion detection becomes more and more significant since the security of the networks is one of the most critical issues in the world. We present an adaptive collaboration intrusion detection method to improve the safety of a network. A self-adaptive and collaborative intrusion detection model is built by applying the Environmentsclasses, agents, roles, groups, and objects(E-CARGO) model. The objects, roles, agents, and groups are designed by using decision trees(DTs) and support vector machines(SVMs), and adaptive scheduling mechanisms are set up. The KDD CUP 1999 data set is used to verify the effectiveness of the method. The experimental results demonstrate the feasibility and efficiency of the proposed collaborative and adaptive intrusion detection method. Also, the proposed method is shown to be more predominant than the methods that use a set of single type support vector machine(SVM) in terms of detection precision rate and recall rate.

数智时代人机协同的研究现状与未来方向

数智时代因人机协同情境的普遍存在而出现新的决策范式。本专栏旨在促进学者研究与人机协同中的管理决策与组织行为有关的重要问题。尽管在20世纪人工智能的起始阶段学者注意到人与机器共同决策的重要问题,但因人工智能技术在很长时间内没有取得重要突破而没有被继续关注。伴随着人工智能的广泛应用以及认知科学在过去几十年取得的长足进步,学界研究人机协同中的决策和行为问题有了丰富的数据、场景、理论和方法。同时,实践界对于人机协同的新现象还存在认识上的不足和适应性困难,阻碍了企业和组织成员借助数智技术实现智能增强。本文总结了在商业与管理、计算机和心理学领域的学者所从事的有关人们对于机器算法的信任或依赖的研究,特别介绍了在企业情境下开展的人机协同研究。在简要介绍本专栏收录的七篇文章的主要研究发现后,我们指出了未来人机协同研究的重要方向,旨在倡导学界同行开展深入的研究,既能够建立数智化情境下的人机协同理论,又为中国企业顺利实现数智化转型提供参考。

A NEW APPROACH TO THE DESIGN OF A SYSTEM FOR FEATURE EXTRACTION BASED ON HUMAN-COMPUTER COLLABORATIVE TACTIC

We are involved in an embarrassing situation that the limited capability of automated feature extraction in digital photogrammetric systems cannot satisfy the increasing needs for rapid acquisition of semantic information for applications. Facing this challenge, a new tactic, Human-Computer Collaborative (HCC) tactic, and a corresponding new method, Operator-Object Directed (OOD) method, are proposed for the design of a system for feature extraction from large scale aerial images. We hold that in almost all technical complex systems, full automation will be neither technically feasible nor socially acceptable. The system should be designed to optimize through the cooperative operation with two agents in the system: the hurtan and the computer.

基于柔性演员-评论家算法的决策规划协同研究

为了解决基于常规深度强化学习(Deep Reinforcement Learning, DRL)的自动驾驶决策存在学习速度慢、安全性及合理性较差的问题,本文提出一种基于柔性演员-评论家(Soft Actor-Critic,SAC)算法的自动驾驶决策规划协同方法,并将SAC算法与基于规则的决策规划方法相结合设计自动驾驶决策规划协同智能体。结合自注意力机制(Self Attention Mechanism, SAM)和门控循环单元(Gate Recurrent Unit, GRU)构建预处理网络;根据规划模块的具体实现方式设计动作空间;运用信息反馈思想设计奖励函数,给智能体添加车辆行驶条件约束,并将轨迹信息传递给决策模块,实现决策规划的信息协同。在CARLA自动驾驶仿真平台中搭建交通场景对智能体进行训练,并在不同场景中将所提出的决策规划协同方法与常规的基于SAC算法的决策规划方法进行比较,结果表明,本文所设计的自动驾驶决策规划协同智能体学习速度提高了25.10%,由其决策结果生成的平均车速更高,车速变化率更小,更接近道路期望车速,路径长度与曲率变化率更小。

基于绿电减排量互认的建筑虚拟电厂电-碳双层协同决策机制

在“双碳”背景下,电-碳多政策并举和多市场并存局面带来了电能环境权益重复奖惩的问题。针对该问题,提出了基于减排量等效的绿色电力-国家核证自愿减排量(CCER)互认方法,将绿色电力的环境权益统一归属至用户侧,并以建筑主体为研究对象对互认方法进行验证。首先,依据减排特性差异,将建筑分为强制性建筑、减排性建筑、零碳建筑3类,以建筑虚拟电厂为CCER互认的代理。其次,针对建筑虚拟电厂内部CCER分配问题,提出了基于Shapley值法的分配方法,以保证分配的公平和合理性。然后,针对建筑主体面临的电-碳协同决策问题,提出了基于能源共享原则的电-碳双层协同交易机制,并基于主从博弈理论构建双层决策模型,结合供需比概念对模型进行凸化。最后,通过算例仿真验证了互认方法的可行性及电-碳双层协同决策机制的有效性。

Challenges of human-machine collaboration in risky decision-making

The purpose of this paper is to delineate the research challenges of human-machine collaboration in risky decision-making.Technological advances in machine intelligence have enabled a growing number of applications in human-machine collaborative decisionmaking.Therefore,it is desirable to achieve superior performance by folly leveraging human and machine capabilities.In risky decision-making,a human decisionmaker is vulnerable to cognitive biases when judging the possible outcomes of a risky event,whereas a machine decision-maker cannot handle new and dynamic contexts with incomplete information well.We first summarize features of risky decision-making and possible biases of human decision-makers therein.Then,we argue the necessity and urgency of advancing human-machine collaboration in risky decision-making.Afterward,we review the literature on human-machine collaboration in a general decision context,from the perspectives of human-machine organization,relationship,and collaboration.Lastly,we propose challenges of enhancing human-machine communication and teamwork in risky decisionmaking,followed by future research avenues.

基于决策导向评价的多学科协作团队教学模式在肠造口护理教学中的应用

探讨基于决策导向评价的多学科协作团队教学模式在肠造口护理教学中的应用效果,为提高外科造口护理教学质量提供参考。研究结果表明,该模式有助于提升护生实习成绩、造口护理核心能力、共情能力和教学满意度,值得进一步推广应用。

人机协同决策:文献综述

人工智能在决策领域得到越来越多的应用,使得组织决策变得更加高效。然而,人工智能存在各种局限性、例如依靠以往的数据获得洞见,必须结合人类决策者的知识、经验,实现人机协同决策。因此,人机协同决策快速成为一个研究领域。在利用VOSviewer软件对文献进行关键词共现分析的基础上,按照人机协同决策的必要性、概念与组织方式、影响因素与结果效应、理论视角与研究方法、应用场景这一架构对人机协同决策进行文献综述,以揭示人机协同决策研究现状,有助于学者和实践者洞察人机协同决策过去和现在的研究,同时为未来研究寻找新的线索提供坚实的基础。

基于改进SPRINT分类算法的数据挖掘模型

为解决目前数据挖掘模型分类时间长、挖掘准确率不高的问题,提出基于改进决策树分类算法(SPRINT)的数据挖掘模型。先采用最大-最小规范化公式完成原始数据线性变换,利用改进后的SPRINT分类算法按照输入数据特性进行分类,使用协同过滤技术生成与数据相近的属性集,计算数据属性相似度,生成语义规则集,为用户提供更优的数据服务。选取某公司营销数据集作为样本进行对比实验,结果表明,与对比模型相比,所提出的数据挖掘模型分类时间更短,挖掘准确率更高,能为用户提供更优质的数据服务。

基于EDAS的高端装备制造业协同创新伙伴选择

伴随市场环境的复杂多变,高端装备制造业必须通过协同创新来增强技术实力及提高创新成效,其中伙伴选择是其实现创新的关键一步。首先,分析总结伙伴选择评价指标相关文献,并结合高端装备制造业协同创新发展需求,从互补性、兼容性、创新资源、创新能力、创新环境、声誉与信任及技术水平这7个维度,建立了高端装备制造业协同创新伙伴选择指标体系;然后,考虑到高端装备制造业的复杂性及专家评价的模糊性,在概率犹豫模糊环境下,构建基于可能度的平均解距离法(evaluation based on distance from average solution,EDAS)群决策评价模型,并将其应用到该指标体系下的协同创新伙伴选择中;最后,通过一个算例,对该研究方法加以验证,为高端装备制造业进行协同创新伙伴选择提供一定的参考。

城市综合能源系统协同调控与互动交易研究综述

城市是工业、服务业的聚集地,是经济增长的主引擎,未来城市综合能源系统的发展目标将不仅仅局限于满足社会能源需求,还需要将视角提升到支撑城市全局发展层面。因此,城市综合能源系统协同调控与互动交易相关研究不仅是近年来研究的热点问题,也是促进人类和城市可持续发展的必要解决问题。该文首先分析了相关研究的发展趋势和发文热度。然后在模型层面,分别讨论了城市综合能源系统的基本协同调控模型以及满足零碳需求、韧性提升需求、互动交易场景下的协同调控模型;在决策框架和算法层面,就目前常用的双层优化、鲁棒优化、人工智能优化方法分别进行概括分析;对城市综合能源系统仿真软件的特点进行了归纳总结。最后,对城市综合能源系统中多能源协同运行灵活性潜力挖掘、全设备模型建模方法与信息交换技术、多元用户互动特性分析、信息-物理-社会深度融合的需求和挑战进行了展望。

人机协同调节:复合脑视角下自我调节学习的新路径

以ChatGPT为代表的生成式人工智能的出现,使人工智能与人类智能之间实现群智联结,形成人机协同的“复合脑”思维。研究在梳理自我调节学习内涵与过程的基础上,聚焦复合脑对自我调节学习的赋能作用,阐述了复合脑支撑自我调节学习的三个层次,即数据支持下协同记录的“数脑”、数据关联下协同分析的“汇脑”、数据赋能下协同决策的“智脑”;剖析了复合脑赋能自我调节学习的“协同判断—协同调整—协同决定”三个过程。最后,基于内外脑决策自主度的变化,提出了共同调节、共享调节、复合调节三种典型样态,支持学习者不断强化主体责任、构建适应未来的复合脑,形成面向未来的高质量学习力。

果蝇嗅视神经通路研究综述

果蝇嗅觉和视觉神经系统对于自然环境中嗅觉和视觉刺激具有高度的灵敏性,高灵敏的嗅视单模态感知决策和跨模态协同决策机制为仿生应用提供一定的启示作用。该文首先以果蝇嗅觉和视觉神经系统为基础,从嗅觉和视觉信号的捕获、加工、决策3个部分概述了果蝇嗅觉和视觉神经单模态感知决策生理机制与计算模型的研究现状,同时对果蝇嗅觉和视觉神经跨模态协同决策生理机制与计算模型进行阐述;然后对果蝇嗅觉和视觉的单模态感知和跨模态协同的典型仿生应用进行归纳;最后总结果蝇嗅视神经通路生理机制与计算建模当前面临的难题并展望未来发展趋势,为未来相关研究工作奠定了基础。

系统可信度和人格特质对人机协同决策的影响研究

随着人工智能技术的发展,人机协同决策工作模式愈发常见,人和机两方面对高效协同的影响都值得关注。本文基于实验探讨了系统可信度与决策者的人格特质对协同决策的影响。实验以模拟应急救援为任务场景,从系统信息提供的角度设置了3个系统可信度水平,采用大五人格问卷测量参试者人格特质。实验招募了54名志愿者,采集并分析了人机协同决策过程中的任务完成时间、决策时间和任务得分等绩效数据。结果显示,提高系统可信度显著提高了任务得分,但同时也导致了决策时间的增加;人机团队中决策者的神经质与开放性水平与系统可信度存在交互作用;高神经质显著增强了系统可信度对任务完成时间的影响,低开放性显著增强了系统可信度对决策时间的影响。

基于分层深度强化学习的分布式能源系统多能协同优化方法

分布式能源系统的多能协同运行对于促进新能源的消纳具有重要意义。然而,分布式能源系统中源荷的不确定性以及异质能源网络的时空差异性,给多能协同优化问题带来巨大挑战。针对这一问题,提出了一种面向分布式能源系统的两阶段多能协同优化模型,通过采用长时间尺度控制和短时间尺度控制两阶段解耦决策方式,实现了对不同时间响应特性的复合空间进行序贯决策。然后,面对高维复合搜索空间和源荷不确定性因素,采用了深度强化学习无模型解决方案,并提出一种全新的分层深度强化学习算法进行求解。通过算例仿真验证了所提模型和求解方法的有效性和优越性。