Intelligent Adaptive Information Agents

Adaptation in open, multi-agent information gathering systems isimportant for several reasons. These reasons include the inability toaccurately predict future problem-solving workloads, future changes inexisting information requests, future failures and additions of agents anddata supply resources, and other future task environment characteristicchanges that require system reorganization. We have developed a multi-agentdistributed system infrastructure, RETSINA (REusable Task Structure-based Intelligent Network Agents) that handles adaptation in an open Internetenvironment. Adaptation occurs both at the individual agent level as well asat the overall agent organization level. The RETSINA system has three typesof agents. Interface agents interact with the userreceiving user specifications and delivering results. They acquire, model,and utilize user preferences to guide system coordination in support of theusers tasks. Task agents help users perform tasks byformulating problem solving plans and carrying out these plans throughquerying and exchanging information with other software agents. Information agents provide intelligent access to a heterogeneouscollection of information sources. In this paper, we concentrate on theadaptive architecture of the information agents. We use as the domain ofapplication WARREN, a multi-agent financial portfolio management system thatwe have implemented within the RETSINA framework.     

Structured development of problem solving methods

Problem solving methods (PSMs) describe the reasoning components of knowledge-based systems as patterns of behavior that can be reused across applications. While the availability of extensive problem solving method libraries and the emerging consensus on problem solving method specification languages indicate the maturity of the field, a number of important research issues are still open. In particular, very little progress has been achieved on foundational and methodological issues. Hence, despite the number of libraries which have been developed, it is still not clear what organization principles should be adopted to construct truly comprehensive libraries, covering large numbers of applications and encompassing both task-specific and task-independent problem solving methods. In this paper, we address these "fundamental" issues and present a comprehensive and detailed framework for characterizing problem solving methods and their development process. In particular, we suggest that PSM development consists of introducing assumptions and commitments along a three-dimensional space defined in terms of problem-solving strategy, task commitments, and domain (knowledge) assumptions. Individual moves through this space can be formally described by means of adapters. In the paper, we illustrate our approach and argue that our architecture provides answers to three fundamental problems related to research in problem solving methods: 1) what is the epistemological structure and what are the modeling primitives of PSMs? 2) how can we model the PSM development process? and 3) how can we develop and organize truly comprehensive and manageable libraries of problem solving methods?     

The role of explanations in an intelligent assistant system

This paper sets out to illustrate the importance of transparency within software support systems and in particular for those intelligent assistant systems performing complex industrial design tasks. Such transparency (with the meaning ‘clear’ or ‘easy to understand’) can be achieved by two distinct strategies that complement each other:

• 1.(i) The design of intelligible systems that would avoid the need for in depth explanation.
• 2.(ii) The flexible generation of those definitions or aspects of the system or domain that remain ambiguous.

The paper illustrates that for the generation of useful explanations going beyond a simple justification of a problem solving trace, specific explanatory knowledge must be acquired. By itself the problem solving techniques are not sufficient. A new approach to acquire and model explanatory knowledge for software systems is presented. The new four-layer explanatory model can be used to determine the range of explanation suitable for a given systems domain. This model has been successfully used for the development of an explanation component for the design assistant system ASSIST that supports factory layout planning, in itself a complex design task.     

A multiagent architecture for fuzzy modeling

In this paper a hybrid learning system that combines different fuzzy modeling techniques is being investigated. In order to implement the different methods, we propose the use of intelligent agents, which collaborate by means of a multiagent architecture. This approach, involving agents which embody the different problem solving methods, is a potentially useful strategy for enhancing the power of fuzzy modeling systems. ©1999 John Wiley & Sons, Inc.     

Perceptual control architecture for cyber–physical systems in traffic incident management

Based on Perceptual Control Theory, we study the problem of unified modeling for incompatible approaches of Cyber–Physical Systems (CPSs). Inspired by the effective organization of living systems structure accommodating heterogeneous information processing and environmental interaction, we propose Perceptual Control Architecture of CPSs, and take Traffic Incident Management systems as the modeling research carrier. Throughout the structure of Traffic Incident Management systems, the hierarchical negative feedback is constituted by perceptual and behavioral loops to ensure a mechanism of intelligence behavior. The internal representation is categorized into two intelligent spaces: physical-reflex space and cyber-virtual space. In physical-reflex space, the sensing-actuation mapping of objective world is built, through four levels of distributed traffic infrastructure. In cyber-virtual space, subjective decision using Bayesian reasoning network is defined by three levels: principles, interrelated factors and situation assessment. Through evaluation of field operation in Dalian, the Traffic Incident Management under the developed architecture shows a considerable reduction in response time as well as assessment inaccuracy. The test results explicated the effectiveness of the architecture on integrating complex Cyber–Physical functions. Besides transportation systems, the modeling approach could be a well-defined unified architecture applied to other CPSs.     

Soft computing in engineering design: a hybrid dual cross-mapping neural network model

Contemporary design process requires the development of a new computational intelligence or soft computing methodology that involves intelligence integration and hybrid intelligent systems for design, analysis and evaluation, and optimization. This paper first presents a discussion of the need to incorporate intelligence into an automated design process and the various constraints that designers face when embarking on industrial design projects. Then, it presents the design problem as optimizing the design output against constraints and the use of soft computing and hybrid intelligent systems techniques. In this paper, a soft-computing-integrated intelligent design framework is developed. A hybrid dual cross-mapping neural network (HDCMNN) model is proposed using the hybrid soft computing technique based on cross-mapping between a back-propagation network (BPNN) and a recurrent Hopfield network (HNN) for supporting modeling, analysis and evaluation, and optimization tasks in the design process. The two networks perform different but complementary tasks—the BPNN decides if the design problem is a type 0 (rational) or type 1 (non-rational) problem, and the output layer weights are then used as the energy function for the HNN. The BPNN is used for representing design patterns, training classification boundaries, and outputting network weight values to the HNN, and then the HNN uses the calculated network weight values to evaluate and modify or re-design the design patterns. The developed system provides a unified soft-computing-integrated intelligent design framework with both symbolic and computational intelligence. The system has self-modifying and self-learning functions. Within the system, only one network training is needed for accomplishing the evaluation, rectification/modification, and optimization tasks in the design process. Finally, two case studies are provided to illustrate and validate the developed model and system.     

Evolving Soccer Keepaway Players Through Task Decomposition

Complex control tasks can often be solved by decomposing them into hierarchies of manageable subtasks. Such decompositions require designers to decide how much human knowledge should be used to help learn the resulting components. On one hand, encoding human knowledge requires manual effort and may incorrectly constrain the learners hypothesis space or guide it away from the best solutions. On the other hand, it may make learning easier and enable the learner to tackle more complex tasks. This article examines the impact of this trade-off in tasks of varying difficulty. A space laid out by two dimensions is explored: (1) how much human assistance is given and (2) how difficult the task is. In particular, the neuroevolution learning algorithm is enhanced with three different methods for learning the components that result from a task decomposition. The first method, coevolution, is mostly unassisted by human knowledge. The second method, layered learning, is highly assisted. The third method, concurrent layered learning, is a novel combination of the first two that attempts to exploit human knowledge while retaining some of coevolutions flexibility. Detailed empirical results are presented comparing and contrasting these three approaches on two versions of a complex task, namely robot soccer keepaway, that differ in difficulty of learning. These results confirm that, given a suitable task decomposition, neuroevolution can master difficult tasks. Furthermore, they demonstrate that the appropriate level of human assistance depends critically on the difficulty of the problem.Editor Robert Holte     

基于统一建模语言的智能交通系统工程设计研究

以统一建模语言设计智能交通的工程系统为研究,结合统一建模语言的特点,详细讨论了统一建模语言设计智能交通系统的总体结构、硬件体系及软件部分的方法,提出了信息系统的设计规划结合统一建模语言的流程、模式和方法。     

Integration and control of intelligence in distributed manufacturing

The area of intelligent systems has generated a considerable amount of interest—occasionally verging on controversy—within both the research community and the industrial sector. This paper aims to present a unified framework for integrating the methods and techniques related to intelligent systems in the context of design and control of modern manufacturing systems. Particular emphasis is placed on the methodologies relevant to distributed processing over the Internet. Following presentation of a spectrum of intelligent techniques, a framework for integrated analysis of these techniques at different levels in the context of intelligent manufacturing systems is discussed. Integration of methods of artificial intelligence is investigated primarily along two dimensions: the manufacturing product life-cycle dimension, and the organizational complexity dimension. It is shown that at different stages of the product life-cycle, different intelligent and knowledge-oriented techniques are used, mainly because of the varied levels of complexity associated with those stages. Distribution of the system architecture or system control is the most important factor in terms of demanding the use of the most up-to-date distributed intelligence technologies. A tool set for web-enabled design of distributed intelligent systems is presented. Finally, the issue of intelligence control is addressed. It is argued that the dominant criterion according to which the level of intelligence is selected in technological tasks is the required precision of the resulting operation, related to the degree of generalization required by the particular task. The control of knowledge in higher-level tasks has to be executed with a strong involvement of the human component in the feedback loop. In order to facilitate the human intervention, there is a need for readily available, user-transparent computing and telecommunications infrastructure. In its final part, the paper discusses currently emerging ubiquitous systems, which combine this type of infrastructure with new intelligent control systems based on a multi-sensory perception of the state of the controlled process and its environment to give us tools to manage information in a way that would be most natural and easy for the human operator.     

Shop-floor scheduling at shipbuilding yards using the multiple intelligent agent system

The intelligent agent system has become a typical approach to research distributed artificial intelligence and distributed problem solving. However, despite its various technical advantages, the distribution and expansion of the intelligent agent system approach has been limited because existing methodologies rely on specialized applications and therefore require intensive investment to develop new systems. In an attempt to conquer these difficulties, a standardized methodology to construct intelligent agent systems is proposed. This approach deviates from current agent system approaches of repeatedly constructing new and customized expert systems. Specifically, it provides an economical method for developing intelligent agent systems by investigating the possibility of standardizing message communication protocols in linguistics speech-act theory and by supplementing traditional algorithmic systems with intelligent segments using, among others, expert system tools. To verify effectiveness, the shop-floor scheduling system of a large-scale shipbuilding yard has been redesigned, developed, and tested using this approach. This shop-floor scheduling system requires the scheduling of when and where to process block construction under various constraints. It is a difficult four-dimensional time and space allocation problem involving traditional NP-complete search spaces. The tested intelligent agent system proposes an innovative method for reducing the search space into three levels: the algorithm level, the agent intelligence level, and the level of cooperation among agents. It also provides methods for solving deadlock occurrence and non-uniformity problems resulting from parallel processing. Test results demonstrate applicability and economy, among other technical advantages.     

Inventive machine: Second generation

Inventive Machine project is the matter of discussion. The project aims to develop a family of AI systems for intelligent support of all stages of engineering design. Peculiarities of the IM project:

1. deep and comprehensive knowledge base — the theory of inventive problem solving (TIPS)
2. solving complex problems at the level of inventions
3. application in any area of engineering
4. structural prediction of engineering system development

The systems of the second generation are described in detail     

Validation method for intelligent systems

Knowledge incorporated intelligent solving methods are prevailing in practical planning and scheduling systems because of the large problem size and complex constraints. However, when intelligent methods are used in real applications, it is an important problem to validate that both optimality and response time are at expert-level. Turing Test approaches are useful in validating intelligent systems. Nevertheless, validation burdens experts with heavy tasks. In distribution route scheduling, for instance, validation load is considerable since patterns of distribution spots are numerous. A bi-directional, many-sided explanation typed multi-step validation method, which enables to share validation tasks among experts, KEs (Knowledge Engineers) and computers, is proposed to diminish the load for busy experts, in validating intelligent systems. Furthermore, an additional validation tool based on the above method is also proposed. This method ensures efficient validation due to the decrease of load for experts by means of sharing validation tasks through multi-step validation with experts, KEs and computers. From this viewpoint, the proposed method can be used in validating general intelligent solving methods and intelligent systems, as well as intelligent scheduling systems.     

A hybrid system applied to epidemic screening

Although many knowledge-based systems (KBSs) focus on single-paradigm approaches to encoding knowledge (such as production rules), human experts rarely use a single type of knowledge to solve a real-world problem. A human expert usually combines a number of reasoning mechanisms. In recent years, rule-based reasoning (RBR), case-based reasoning (CBR) and model-based reasoning (MBR) have emerged as important and complementary reasoning methodologies in the intelligent systems area. For complex problem solving, it is useful to integrate RBR, CBR and MBR. In this paper, a hybrid epidemic screening KBS which integrates a deductive RBR system, an inductive CBR system and a quantitative MBR system is proposed. The system has been tested using real epidemic screening variables and data.     

多Agent系统分布式问题求解的代数模型方法(Ⅱ): 群体智能和社会动力学

该文是组合论文中第二篇，讨论多Agent系统分布式问题求解的代数模型中的特性层和动力学层，即没粒度Agent群体的宏观群体智能的形式优化代数模型以及宏观社会智能与Agent个体间微观社会行为之间的社会动力学模型，提出了基于这种新的代数模型方法的超分布超并行社会智能问题求解算法，关于分布式多任务自组织规划和资源自组织分配的仿真实验以及与其它方法的比较分析，表明了该文提出了代数模型和问题求解方法的特点和有效性。     

Complementary case-based reasoning and competitive fuzzy cognitive maps for advanced medical decisions

This paper presents a new hybrid modeling methodology suitable for complex decision making processes. It extends previous work on competitive fuzzy cognitive maps for medical decision support systems by complementing them with case based reasoning methods. The synergy of these methodologies is accomplished by a new proposed algorithm that leads to more dependable advanced medical decision support systems that are suitable to handle situations where the decisions are not clearly distinct. The methodology developed here is applied successfully to model and test two decision support systems, one a differential diagnosis problem from the speech pathology area for the diagnosis of language impairments and the other for decision making choices in external beam radiation therapy.     

人机对话中自然语言任务命令的识别和计划

随着智能手机和智能系统的飞速发展, 使用自然语言对话的人机交互方式也成为了流行趋势. 但是如果该对话系统需要处理多功能任务类型, 那么将产生复杂的任务命令, 问题的维度也会增加. 尽管目前的NLP技术能提供一些解决方案, 但在动态范围内实现动态任务命令识别与处理的能力仍然有限, 解决复杂问题的效果还有待提高. 因此, 在本项工作中, 提供了一种结合NLP引擎和任务计划单元的方法, 根据自然语言的指令来设定任务计划, 以便对话系统能较准确地识别命令任务和相关参数, 并为任务生成相应的合理计划. 同时, 为解决自然语言对话中信息的歧义或遗漏, 还研究了一种对话策略, 在必要时能以最少的问答迭代收集对话信息.     

The role of prior experience and task characteristics in object-oriented modeling: an empirical study

The object-oriented methodology for systems analysis and design has generated considerable interest recently. Object-orientation represents a fundamental shift in focus from the traditional process-oriented approaches that have dominated software development for over two decades. Although there is anecdotal evidence to suggest that systems analysts experienced in process-oriented modeling approaches will find it difficult to apply objective-oriented methodologies, there is no empirical work investigating the relationship between a procedural mindset and an ability to learn and apply object-oriented concepts. Prior research in human problem solving, however, suggests that the efficacy of a systems analysis and design methodology should be judged in the context of the task to which it is applied. To explore the effects of prior experience and task characteristics on performance in systems analysis and design, we conducted an experiment in which two groups of subjects applied the object-oriented methodology to two types of tasks, one process-oriented and the other object-oriented. One group had significant prior experience in process-oriented methodologies, while the other group had no formal experience. Both groups were provided identical training in object-oriented analysis and design prior to the experiment. The results of the study suggest that both prior experience and task characteristics play a role in determining performance. The implications that follow for research and practice are discussed.