Machine learning for vessel trajectories using compression,alignments and domain knowledge

In this paper we present a machine learning framework to analyze moving object trajectories from maritime vessels. Within this framework we perform the tasks of clustering, classification and outlier detection with vessel trajectory data. First, we apply a piecewise linear segmentation method to the trajectories to compress them. We adapt an existing technique to better retain stop and move information and show the better performance of our method with experimental results. Second, we use a similarity based approach to perform the clustering, classification and outlier detection tasks using kernel methods. We present experiments that investigate different alignment kernels and the effect of piecewise linear segmentation in the three different tasks. The experimental results show that compression does not negatively impact task performance and greatly reduces computation time for the alignment kernels. Finally, the alignment kernels allow for easy integration of geographical domain knowledge. In experiments we show that this added domain knowledge enhances performance in the clustering and classification tasks.     

Kave: a tool for knowledge acquisition to support artificial ventilation

A decision support system for artificial ventilation is being developed. One of the fundamental goals for this system is the application of the system when a domain expert is not present. Such a system requires a rich knowledge base. The knowledge acquisition process is often considered to be the bottleneck in acquiring such a complete knowledge base. Since no single available method, for example interviewing domain experts, is sufficient for removing this bottleneck, we have chosen a combination of different methods. The different backgrounds of knowledge engineers and domain experts could cause communication restrictions and difficulties between them, e.g. they might not understand each others knowledge domain and this will affect formulation of the knowledge. To solve this problem we needed a tool which supports both the knowledge engineer and the domain expert already from the initial phase of developing the knowledge base. We have developed a knowledge acquisition system called KAVE to elicit knowledge from domain experts and storing it in the knowledge base. KAVE is based on a domain specific conceptual model which is a result of cooperation between knowledge engineers and domain experts during identification, design and structuring of knowledge for this domain. KAVE includes a patient simulator to help validate knowledge in the knowledge base and a knowledge editor to facilitate refinement and maintenance of the knowledge base.     

Evolutionary patterns of agent organizations

Problems approached by multi-agent systems are typically complex. It is usually difficult to know at system design stage how many agents need to be in the system, what each agent's role is, and how the agents should interact to get optimal performance out of the group. The aim of the testbed presented here is to investigate which kinds of multi-agent systems could be developed to solve ranges of problems, avoiding the need to reorganize the agents from scratch for each task. The agent organization process explored here is based on the agents' knowledge, and not on their tasks. This opens up a new approach for distributed artificial intelligence designers to have their domain organized before the allocation of tasks among agents. These kinds of organizations should be more robust for solving different problems related to the same knowledge. We define information oriented domains for that purpose. An evolutionary approach to the design of a multi-agent system is suggested. Our model is based on a cellular automaton whose rules of dynamics induce the formation of an organization of agents. Patterns of organization obtained empirically are presented. Our knowledge-based organization approach is analyzed both from theoretical and practical perspectives     

支持多领域动态功能集成的网格GIS系统*

Grid_GIS是一个采用SOA（serviceoriented architecture）思想,支持多应用领域功能集成的网格GIS系统。系统采用一种超级P2P的网格体系结构,实现数据和功能资源的分布式存储、查询处理和动态数据集成;根据领域本体知识和推理机制,实现基于语义的智能查询;基于标准的Web服务,应用推模式,实现资源的有效监视;根据系统的状态和任务之间的通信关系,采用成本约束的自适应调度算法,实现系统的动态调度和负载平衡;采用WSSecurity扩展实现网格的安全,既可以保证网格的安全性又可以     

A study on the collaborative management method of product design cycle knowledge

Because of the ever-increasing market competition and rapidly changing of customers’ requirements, the innovation quality and design efficiency of knowledge-intensive product has become the key factors in business success. The traditional knowledge management method which is based on design reuse and the single categories of design knowledge cannot satisfy these demands any more. Therefore, in order to effectively support the innovative design process of enterprises, a design knowledge collaborative management method based on multi-knowledge migration is proposed. According to the characteristics and functions during the product design process, the design knowledge is divided into three categories, design principle knowledge, design domain knowledge and design object knowledge. By extracting the operation attributes, relation attributes and physical attributes of the design knowledge, a unified knowledge representation model is established for different design participants. The ontology concept and knowledge matrix are used to establish the association between various categories of design knowledge. Multifarious knowledge search methods include keyword, function, principle and natural semantics are proposed for different design participants in different design stages. They can not only realize the knowledge reuse in the same domain but also support the cross-domain knowledge migration among different domain. Finally, based on the system analysis modelling, a design knowledge collaborative platform is established for the design process of mechanical products. A case study is also presented to illustrate the implementation of the platform.     

单幅图像去雨数据集和深度学习算法的联合评估与展望

雨天会影响室外图像捕捉的质量,进而引起户外视觉任务性能下降。基于深度学习的单幅图像去雨研究因算法性能优越而引起了大家的关注,并且聚焦点集中在数据集的质量、图像去雨方法、单幅图像去雨后续高层任务的研究和性能评价指标等方面。为了方便研究者快速全面了解该领域,本文从上述4个方面综述了基于深度学习的单幅图像去雨的主流文献。依据数据集的构建方式将雨图数据集分为4类：基于背景雨层简单加和、背景雨层复杂融合、生成对抗网络 (generative adversarial network,GAN)数据驱动合成的数据集,以及半自动化采集的真实数据集。依据任务场景、采取的学习机制以及网络设计对主流算法分类总结。综述了面向单任务和联合任务的去雨算法,单任务即雨滴、雨纹、雨雾和暴雨的去除;联合任务即雨滴和雨纹、所有噪声去除。综述了学习机制和网络构建方式(比如:卷积神经网络 (convolutional neural network,CNN)结构多分支组合,GAN的生成结构,循环和多阶段结构,多尺度结构,编解码结构,基于注意力,基于Transformer)以及数据模型双驱动的构建方式。综述了单幅图像去雨后续高层任务的研究文献和图像去雨算法性能的评价指标。通过合成数据集和真实数据集上的综合实验对比,证实了领域知识隐式引导网络构建可以有效提升算法性能,领域知识显式引导正则化网络的学习有潜力进一步提升算法的泛化性。最后,指出单幅图像去雨工作目前面临的挑战和未来的研究方向。     

LUIS—A logic for task-oriented user interface specification

The complexity of user interface design is still steadily increasing because of an increasing variety of innovative interaction styles (e.g., pen-based interaction) and because of an increasing orientation towards tasks as they are actually accomplished in work environments. In order to handle the resulting variety of knowledge that has to be taken into account for design, specification techniques have to rely on representation schemes for end user tasks and their organization, problem domain data, and interaction styles. Declarative knowledge representation techniques provide the capabilities to handle heterogeneous categories of knowledge as well as their integration. This article describes not only a conceptual but also a formal framework for task-oriented, declarative user interface specification. the conceptual framework is based on a semantic network. It is formalized comprehensively through LUIS (Logical User Interface Specification). LUIS is a novel many-sorted temporal specification logic. Using LUIS all static and dynamic relations between (1) end user tasks and problem domain data, (2) end user tasks and interaction styles (media and modalities), and (3) problem domain data and interaction styles, according to different levels of refinement can be captured. In particular, LUIS supports to stepwise refinement of knowledge to elementary data structures and basic functions. Moreover, in LUIS organizational constraints concerning the accomplishment of end user tasks can be represented by postulating axioms applying the modalities “First,” “Sometime in the future,” “Next,” and “More recently than.” Since each knowledge category corresponds to a particular sort of the specification logic, the designer can be provided with modular knowledge sources. They can be extended or modified for further developments in a flexible way. © 1995 John Wiley & Sons, Inc.     

Rule-based system validation through automatic identification ofequivalence classes

The proposed validation method identifies equivalence classes for fundamental tasks in a rule based system to help identify incorrect knowledge and rule inconsistencies. The proposed method validates the entire input domain of a pre existing rule based system by using symbolic execution to determine the conditions under which tasks may be instantiated     

公理化设计框架下产品设计知识重用的关键技术

针对具有层次性、多属性特点的复杂产品设计过程,对公理化设计框架下的产品设计重用技术进行了研究。通过建立公理化设计框架将复杂产品设计过程进行分解,形成产品设计的需求域、功能域、结构域与工艺域的Z形映射关系,提出一种基于实例的综合考虑设计域间和域内设计信息的知识重用方法,采用基于相似度的知识重用检索算法,获得符合设计要求的最佳重用对象,并以实例进行了验证。     

Heuristic, symbolic logic and knowledge-based approach to the design and construction of buildings

The emergence of knowledge-based expert systems provide means with which one can use the computer as an aid to the solution of an ill-structured problem. Expert systems are interactive computer programs based on heuristics, incorporating judgement, rules of thumb, intuition and expertise to provide knowledgeable advice about variety of tasks. Such specialized interactive computer programs can broadly be classified as (1) identifying the relevant design knowledge, (2) providing a formalism for representing and processing the knowledge and (3) implementing the formalism in a computer environment. While the first issue of identifying the relevant knowledge is through knowledge acquisition from various domain experts and verification of the same by other domain experts. The second issue is proper formalism for the varied knowledge requiring the use of logics (prepositional calculus) as a symbolic language; heuristics or rules of thumb wherever necessary and a suitable reasoning methodology, i.e. an inference technique. The third issue is the evaluation of a suitable strategy for successful computer implementation, i.e. the computer problem is subdivided into smaller tasks which have easy solutions; and the capability of interacting the solutions of the smaller tasks into a larger framework. Therefore, this will require theorem proving, search technique and a special purpose computer language such as PROLOG or readily available domain independent shells, i.e. expert system tools. The overall synthesis of all the above is termed as a knowledge-based expert system (KBES). In this paper a KBES is developed for a highly complex building element, ‘beam design’, as part of a larger model involving planning, analysis, design, optimization and cost forecasts along with other allied services such as plumbing and electrical services. In the development of KBES; the knowledge-base is purely heuristic and subjected to alteration by numerical calculations. For an effective search the modified depth technique is adopted. Heuristics are employed to further the search as and when required from the point of view of practical computer implementation. In the overall development, use is made of dependency diagrams, charts, tables and search trees. For computer implementation the necessary tool chosen was the M1 shell developed by Teknowledge Inc., U.S.A. This requires a PC-AT with 640 kB RAM and 40 MB hard disk. A brief overview of the expert system, followed by an example problem, is presented.     

PDViz: A Visual Analytics Approach for State Policy Data

Sub-national governments across the United States implement a variety of policies to address large societal problems and needs. Many policies are picked up or adopted in other states. This process is called policy diffusion and allows researchers to analyse and compare the social, political, and contextual characteristics that lead to adopting certain policies, as well as the efficacy of these policies once adopted. In this paper, we introduce PDViz, a visual analytics approach that allows social scientists to dynamically analyse the policy diffusion history and underlying patterns. It is designed for analysing and answering a list of research questions and tasks posed by social scientists in prior work. To evaluate our system, we present two usage scenarios and conduct interviews with domain experts in political science. The interviews highlight that PDViz provides the result of policy diffusion patterns that align with their domain knowledge as well as the potential to be a learning tool for students to understand the concept of policy diffusion.     

Web search behavior of Internet experts and newbies

Searching for relevant information on the World Wide Web is often a laborious and frustrating task for casual and experienced users. To help improve searching on the Web based on a better understanding of user characteristics, we investigate what types of knowledge are relevant for Web-based information seeking, and which knowledge structures and strategies are involved. Two experimental studies are presented, which address these questions from different angles and with different methodologies. In the first experiment, 12 established Internet experts are first interviewed about search strategies and then perform a series of realistic search tasks on the World Wide Web. From this study a model of information seeking on the World Wide Web is derived and then tested in a second study. In the second experiment two types of potentially relevant types of knowledge are compared directly. Effects of Web experience and domain-specific background knowledge are investigated with a series of search tasks in an economics-related domain (introduction of the Euro currency). We find differential and combined effects of both Web experience and domain knowledge: while successful search performance requires the combination of the two types of expertise, specific strategies directly related to Web experience or domain knowledge can be identified.     

基于本体的军事装备知识建模及分析

针对本体建模过程中不同受众具有不同应用需求的问题,结合本体建模七步法和软件开发螺旋模型提出基于需求的螺旋反馈法.首先,明确领域知识范畴和用户需求,进行本体总体设计;其次,领域专家依据本体构建原则评估知识体系;再次,组装知识体系模型,定义本体属性,创建实例,完成本体详细设计;最后,用户评估反馈,进行新一轮的增量迭代,直至...     

Automated knowledge acquisition for the surface-mount PWB assembly domain

The development of knowledge-based (or expert) systems for the surface-mount printed wiring board (PWB) assembly domain requires the understanding and regulation of several complex tasks. While the knowledge base in an expert system serves as a storehouse of knowledge primitives, its design and development is a bottleneck in the expert system development life-cycle. Therefore the development of an automated knowledge acquisition (KA) facility (or KA tool) would facilitate the implementation of expert systems for any domain. This paper describes an automated KA tool that helps to elicit and store information in domain-specific knowledge bases for surface-mount PWB assembly. A salient feature of this research is the acquisition of uncertain information.     

基于自监督知识的无监督新集域适应学习

无监督域适应(unsupervised domain adaptation,UDA)旨在利用带大量标注数据的源域帮助无任何标注信息的目标域学习.在UDA中,通常假设源域和目标域间的数据分布不同,但共享相同的类标签空间.但在真实开放学习场景中,域间的标签空间很可能存在差异.在极端情形下,域间的类别不存在交集,即目标域中类...     

Distributed conflict resolution among cooperating expert systems

Abstract: Cooperating experts approach attempts to integrate and coordinate the activities of multiple specialised problem solvers that come together to solve complex tasks such as design, medical diagnosis, business management and so on. Due to the different goals, knowledge and viewpoints of agents, conflicts may arise at any phase of the problem-solving process. Managing diverse expertise requires well-organised models of conflict resolution. In this paper, a model for cooperating experts is described which openly supports multi-agent conflict detection and resolution. The model is based on the idea that each agent has its own conflict knowledge which is separated from its domain level knowledge, and each agent has its own conflict resolution knowledge which is not accessible and known by others. Furthermore, there are no globally known conflict resolution strategies. Each agent involved in a conflict chooses a resolution scheme according to its self interest. The model is described by using an example in the domain of office design and it is compared with other systems.     

A mix method of knowledge capitalization in maintenance

This paper deals with knowledge capitalization in maintenance especially in diagnosis and repair of industrial equipments. The goal is to propose a method of knowledge capitalization in order to develop a decision support system for maintenance operators. The knowledge capitalization cycle was adopted as the underlying principle. It consists of four principal steps: detect, preserve, capitalize and actualize the strategic knowledge. Different knowledge management tools and methods that can be used in the cycle are reviewed. We propose a mix method of knowledge capitalization in maintenance. This method integrates a representation and a reasoning model both completing each other and suitable to represent and manipulate the domain knowledge. The knowledge representation model using unified modelling language (UML) diagram proposes different domain models based on maintenance analysis to guide the domain expertise. The reasoning model uses the case-based reasoning which allows the manipulation of represented domain knowledge. Finally, the method is implemented on the pallet transfer system Sormel in the context of Proteus e-maintenance platform.     

Knowledge map: An approach to knowledge acquisition in developing engineering expert systems

This paper addresses the critical issues of knowledge acquisition in developing knowledge-based expert systems for engineering tasks. First, it reviews the role of knowledge acquisition and its current practice in expert system development. Then, a new approach based on three stages of knowledge refinement is suggested to improve the process of knowledge acquisition. This approach, calledrule verification without rule construction, is proposed to allow knowledge engineers and domain experts to experience a more intimate and balanced role in developing intelligent systems. The communication tool developed for this concept is calledknowledge map, which provides a systematic way of indexing and quantifying a piece of knowledge in the problem space by defining important attributes as the axes of the map. This approach is demonstrated by constructing a twodimensional map for a knowledge-based engineering design system, IDRILL, which we are currently developing. Future expansions of this knowledge acquisition technique are summarized as the conclusions of this paper.This paper was presented in part at the 1986 ASME International Computers in Engineering Conference in Chicago, IL, and appeared in the proceedings of that conference.