Distributed learning and cooperative control for multi-agent systems

This paper presents an algorithm and analysis of distributed learning and cooperative control for a multi-agent system so that a global goal of the overall system can be achieved by locally acting agents. We consider a resource-constrained multi-agent system, in which each agent has limited capabilities in terms of sensing, computation, and communication. The proposed algorithm is executed by each agent independently to estimate an unknown field of interest from noisy measurements and to coordinate multiple agents in a distributed manner to discover peaks of the unknown field. Each mobile agent maintains its own local estimate of the field and updates the estimate using collective measurements from itself and nearby agents. Each agent then moves towards peaks of the field using the gradient of its estimated field while avoiding collision and maintaining communication connectivity. The proposed algorithm is based on a recursive spatial estimation of an unknown field. We show that the closed-loop dynamics of the proposed multi-agent system can be transformed into a form of a stochastic approximation algorithm and prove its convergence using Ljung’s ordinary differential equation (ODE) approach. We also present extensive simulation results supporting our theoretical results.     

A knowledge centric methodology for dental implant technology assessment using ontology based patent analysis and clinical meta-analysis

The medical equipment industry has been one of the fastest growing sectors of the decade with predicted global sales reaching US$ 430 billion in 2017 [22]. During the period from 1995 to 2008, the patent applications in medical technology increased rapidly worldwide (World Intellectual Property Organization, 2012). Patent analysis, although useful in forecasting technology development trends, has posed a challenging analysis task since the volume and diversity of new patent applications has surpassed the ability of regular firms and research teams to process and identify relevant information. Further, medical related technologies rely on clinical trials to validate and gain regulatory approval for patient treatment even though patents, protecting the intellectual property rights of inventors, have been granted. This research focuses on developing a knowledge centric methodology and system to analyze and assess viable medical technology innovations and trends considering both patents and clinical reports. Specifically, the design innovations of dental implant connections are used as a case study. A novel and generic methodology combining ontology based patent analysis and clinical meta-analysis is developed to analyze and identify the most effective patented techniques in the dental implant field. The research establishes and verifies a computer supported analytical approach and system for the strategic prediction of medical technology development trends.     

Agent negotiation based ontology refinement process and mechanisms for service applications

Nowadays organisations are willing to outsource their business processes as services and make them accessible via the Web. In doing so, they can dynamically combine individual services to their service applications. However, unless the data on the Web can be meaningfully shared and is interpretable, this objective cannot be realised. In this paper, a new agent-based approach for managing ontology evolution in a Web services environment is exploited. The proposed approach has several key characteristics such as flexibility and extensibility that differentiate this research from others. The refinement mechanisms which cope with an evolving ontology are carefully examined. The novelty of our work is that inter-processes between different ontologies are studied from the agent’s perspective. Based on this perspective, an agent negotiation model is applied to reach an agreement regarding ontology discrepancy in an application. The efficiency and effectiveness of reaching an agreement over an ontology dispute is leveraged by the private negotiation strategy applied in the argumentation approach. An extended negotiation strategy is discussed to enable sufficient information in decision making at each negotiation round. A case study is presented to demonstrate ontology refinement in a Web services environment.     

Development of a patent document classification and search platform using a back-propagation network

In order to process large numbers of explicit knowledge documents such as patents in an organized manner, automatic document categorization and search are required. In this paper, we develop a document classification and search methodology based on neural network technology that helps companies manage patent documents more effectively. The classification process begins by extracting key phrases from the document set by means of automatic text processing and determining the significance of key phrases according to their frequency in text. In order to maintain a manageable number of independent key phrases, correlation analysis is applied to compute the similarities between key phrases. Phrases with higher correlations are synthesized into a smaller set of phrases. Finally, the back-propagation network model is adopted as a classifier. The target output identifies a patent document’s category based on a hierarchical classification scheme, in this case, the international patent classification (IPC) standard. The methodology is tested using patents related to the design of power hand-tools. Related patents are automatically classified using pre-trained neural network models. In the prototype system, two modules are used for patent document management. The automatic classification module helps the user classify patent documents and the search module helps users find relevant and related patent documents. The result shows an improvement in document classification and identification over previously published methods of patent document management.     

MAGAD-BFS: A learning method for Beta fuzzy systems based on a multi-agent genetic algorithm

This paper proposes a learning method for Beta fuzzy systems (BFS) based on a multiagent genetic algorithm. This method, called Multi-Agent Genetic Algorithm for the Design of BFS has two advantages. First, thanks to genetic algorithms (GA) efficiency, it allows to design a suitable and precise model for BFS. Second, it improves the GA convergence by reducing rule complexity thanks to the distributed implementation by multi-agent approach. Dynamic agents interact to provide an optimal solution in order to obtain the best BFS reaching the balance interpretability-precision. The performance of the method is tested on a simulated example.     

A patent quality analysis for innovative technology and product development

Enterprises evaluate intellectual property rights and the quality of patent documents in order to develop innovative products and discover state-of-the-art technology trends. The product technologies covered by patent claims are protected by law, and the quality of the patent insures against infringement by competitors while increasing the worth of the invention. Thus, patent quality analysis provides a means by which companies determine whether or not to customize and manufacture innovative products. Since patents provide significant financial protection for businesses, the number of patents filed is increasing at a fast pace. Companies which cannot process patent information or fail to protect their innovations by filing patents lose market competitiveness. Current patent research is needed to estimate the quality of patent documents. The purpose of this research is to improve the analysis and ranking of patent quality. The first step of the proposed methodology is to collect technology specific patents and to extract relevant patent quality performance indicators. The second step is to identify the key impact factors using principal component analysis. These factors are then used as the input parameters for a back-propagation neural network model. Patent transactions help judge patent quality and patents which are licensed or sold with intellectual property usage rights are considered high quality patents. This research collected 283 patents sold or licensed from the news of patent transactions and 116 patents which were unsold but belong to the technology specific domains of interest. After training the patent quality model, 36 historical patents are used to verify the performance of the trained model. The match between the analytical results and the actual trading status reached an 85% level of accuracy. Thus, the proposed patent quality methodology evaluates the quality of patents automatically and effectively as a preliminary screening solution. The approach saves domain experts valuable time targeting high value patents for R&D commercialization and mass customization of products.     

An appraisal and design of a multi-agent system based cooperative wireless intrusion detection computational intelligence technique

The deployment of wireless sensor networks and mobile ad-hoc networks in applications such as emergency services, warfare and health monitoring poses the threat of various cyber hazards, intrusions and attacks as a consequence of these networks’ openness. Among the most significant research difficulties in such networks safety is intrusion detection, whose target is to distinguish between misuse and abnormal behavior so as to ensure secure, reliable network operations and services. Intrusion detection is best delivered by multi-agent system technologies and advanced computing techniques. To date, diverse soft computing and machine learning techniques in terms of computational intelligence have been utilized to create Intrusion Detection and Prevention Systems (IDPS), yet the literature does not report any state-of-the-art reviews investigating the performance and consequences of such techniques solving wireless environment intrusion recognition issues as they gain entry into cloud computing. The principal contribution of this paper is a review and categorization of existing IDPS schemes in terms of traditional artificial computational intelligence with a multi-agent support. The significance of the techniques and methodologies and their performance and limitations are additionally analyzed in this study, and the limitations are addressed as challenges to obtain a set of requirements for IDPS in establishing a collaborative-based wireless IDPS (Co-WIDPS) architectural design. It amalgamates a fuzzy reinforcement learning knowledge management by creating a far superior technological platform that is far more accurate in detecting attacks. In conclusion, we elaborate on several key future research topics with the potential to accelerate the progress and deployment of computational intelligence based Co-WIDPSs.     

Table form document analysis based on the document structure grammar

Structure analysis of table form documents is an important issue because a printed document and even an electronic document do not provide logical structural information but merely geometrical layout and lexical information. To handle these documents automatically, logical structure information is necessary. In this paper, we first analyze the elements of the form documents from a communication point of view and retrieve the grammatical elements that appear in them. Then, we present a document structure grammar which governs the logical structure of the form documents. Finally, we propose a structure analysis system of the table form documents based on the grammar. By using grammar notation, we can easily modify and keep it consistent, as the rules are relatively simple. Another advantage of using grammar notation is that it can be used for generating documents only from logical structure. In our system, documents are assumed to be composed of a set of boxes and they are classified as seven box types. Then the box relations between the indication box and its associated entry box are analyzed based on the semantic and geometric knowledge defined in the document structure grammar. Experimental results have shown that the system successfully analyzed several kinds of table forms.     

基于文档结构与深度学习的金融公告信息抽取

针对金融类公告中的结构化数据难以被高效快速提取的问题,提出一种基于文档结构与Bi-LSTM-CRF网络模型的信息抽取方法。自定义一种文档结构树生成算法,利用规则从文档结构树中抽取所需节点信息;构建基于信息句触发词的局部句子规则,抽取包含结构化字段信息的信息句;将字段的结构化信息抽取看作序列标注问题,分词时加入领域知识词典,构建基于Bi-LSTM-CRF的神经网络模型进行字段信息识别。实验结果表明,该信息抽取方法可以满足多类型公告的结构化信息提取,最终的信息句与字段信息抽取的平均F1值均可达到91%以上,验证了该方法在产品业务中的可行性和实用性。     

A Semantic-based Intellectual Property Management System (SIPMS) for supporting patent analysis

Patent databases provide valuable information for technology management. However, the rapid growth of patent documents, the lengthy text and the rich of content in technical terminology, and the complicated relationships among the patents, make it taking a lot of human effort for conducting analyses. As a result, an automated system for assisting the inventors in patent analysis as well as providing support in technological innovation is in great demand. In this paper, a Semantic-based Intellectual Property Management System (SIPMS) has been developed for supporting the management of intellectual properties (IP). It incorporates semantic analysis and text mining techniques for processing and analyzing the patent documents. The method differentiates itself from the traditional technological management tools in its knowledge base. Instead of eliciting knowledge from domain experts, the proposed method adopts global patent databases as sources of knowledge. The system enables users to search for existing patent documents or relevant IP documents which are related to a potential new invention and to support invention by providing the relationships and patterns among a group of IP documents. The method has been evaluated by benchmarking with the performance against traditional text mining technique and has successfully been implemented at a selected reference site.     

A knowledge-based system for extracting text-lines from mixed and overlapping text/graphics compound document images

This paper presents a new knowledge-based system for extracting and identifying text-lines from various real-life mixed text/graphics compound document images. The proposed system first decomposes the document image into distinct object planes to separate homogeneous objects, including textual regions of interest, non-text objects such as graphics and pictures, and background textures. A knowledge-based text extraction and identification method obtains the text-lines with different characteristics in each plane. The proposed system offers high flexibility and expandability by merely updating new rules to cope with various types of real-life complex document images. Experimental and comparative results prove the effectiveness of the proposed knowledge-based system and its advantages in extracting text-lines with a large variety of illumination levels, sizes, and font styles from various types of mixed and overlapping text/graphics complex compound document images.     

Cooperative control for target-capturing task based on a cyclic pursuit strategy

This paper studies a methodology for group coordination and cooperative control of n agents to achieve a target-capturing task in 3D space. The proposed approach is based on a cyclic pursuit strategy, where agent i simply pursues agent i+1 modulo n. The distinctive features of the proposed method are as follows. First, no communication mechanism between agents is necessary and thus it is inherently a distributed control strategy. Also, it is a simple robust memoryless control scheme which has self-stability property. Finally, it guarantees a global convergence of all agents to the desired formation. Further, it is also guaranteed that no collision occurs. Simulation examples are given to illustrate the efficacy of the proposed method and the achievement of a desired pursuit pattern in 3D space.     

A note on connectivity of multi-agent systems with proximity graphs and linear feedback protocol

In this note, we investigate the possibility of simplifying the connectivity verification for multi-agent systems with proximity graphs and the linear feedback protocol. A Lyapunov-like approach is developed for analyzing the monotonicity of the largest edge length in the network. Based on this approach, we provide an initial-connectivity-based sufficient condition for dynamic connectivity. In particular, when each initial node degree is not less than three fourth of the graph order, initial network connectivity implies dynamic connectivity.     

基于Q/A与文档库的智能课程答疑系统

评价智能答疑系统优劣的重要指标是准确率和召回率.系统结合Q/A库和文档库搜索技术的优势实现,利用成熟的Q/A技术回答常见问题,保证了系统的准确率和高效率.利用智能文档搜索技术解答非常见问题,提高了系统的召回率,又因为事先对文档作了预处理,使搜索效率明显提高.同时系统基于课程开发,关键词的词汇量少而精确,使得语义理解的处理得以简化.     

Stability analysis for multi-agent systems using the incidence matrix: Quantized communication and formation control

The spectral properties of the incidence matrix of the communication graph are exploited to provide solutions to two multi-agent control problems. In particular, we consider the problem of state agreement with quantized communication and the problem of distance-based formation control. In both cases, stabilizing control laws are provided when the communication graph is a tree. It is shown how the relation between tree graphs and the null space of the corresponding incidence matrix encode fundamental properties for these two multi-agent control problems.     

A linear discriminant analysis method based on mutual information maximization

We present a new linear discriminant analysis method based on information theory, where the mutual information between linearly transformed input data and the class labels is maximized. First, we introduce a kernel-based estimate of mutual information with a variable kernel size. Furthermore, we devise a learning algorithm that maximizes the mutual information w.r.t. the linear transformation. Two experiments are conducted: the first one uses a toy problem to visualize and compare the transformation vectors in the original input space; the second one evaluates the performance of the method for classification by employing cross-validation tests on four datasets from the UCI repository. Various classifiers are investigated. Our results show that this method can significantly boost class separability over conventional methods, especially for nonlinear classification.     

MASCF: A generic process-centered methodological framework for analysis and design of multi-agent supply chain systems

Multi-agent systems (MAS) are becoming popular for modeling complex systems such as supply chains. However, development of multi-agent systems remain quite involved and extremely time consuming. Currently, there exist no generic methodologies for modeling supply chains using multi-agent systems. In this research, we propose a generic process-centered methodological framework, Multi-Agent Supply Chain Framework (MASCF), to simplify MAS development for supply chain (SC) applications. MASCF introduces the notion of process-centered organization metaphor, and creatively adopts Supply Chain Operations Reference (SCOR) model to a well-structured generic MAS analysis and design methodology, Gaia, for multi-agent supply chain system (MASCS) development. The popular Tamagotchi case was designed and analyzed using MASCF. The validity of the framework was established by implementing MASCF output of Tamagotchi SC using the Java Agent DEvelopment Framework (JADE).     

A robust approach for multi-agent natural resource allocation based on stochastic optimization algorithms

Natural resource allocation is a complex problem that entails difficulties related to the nature of real world problems and to the constraints related to the socio-economical aspects of the problem. In more detail, as the resource becomes scarce relations of trust or communication channels that may exist between the users of a resource become unreliable and should be ignored. In this sense, it is argued that in multi-agent natural resource allocation settings agents are not considered to observe or communicate with each other. The aim of this paper is to study multi-agent learning within this constrained framework. Two novel learning methods are introduced that operate in conjunction with any decentralized multi-agent learning algorithm to provide efficient resource allocations. The proposed methods were applied on a multi-agent simulation model that replicates a natural resource allocation procedure, and extensive experiments were conducted using popular decentralized multi-agent learning algorithms. Experimental results employed statistical figures of merit for assessing the performance of the algorithms with respect to the preservation of the resource and to the utilities of the users. It was revealed that the proposed learning methods improved the performance of all policies under study and provided allocation schemes that both preserved the resource and ensured the survival of the agents, simultaneously. It is thus demonstrated that the proposed learning methods are a substantial improvement, when compared to the direct application of typical learning algorithms to natural resource sharing, and are a viable means of achieving efficient resource allocations.