Knowledge Extraction

An approach to the online learning of Takagi-Sugeno (TS) type models is proposed in the paper. It is based on a novel learning algorithm that recursively updates TS model structure and parameters by combining supervised and unsupervised learning. The rule-base and parameters of the TS model continually evolve by adding new rules with more summarization power and by modifying existing rules and parameters. In this way, the rule-base structure is inherited and up-dated when new data become available. By applying this learning concept to the TS model we arrive at a new type adaptive model called the Evolving Takagi-Sugeno model (ETS). The adaptive nature of these evolving TS models in combination with the highly transparent and compact form of fuzzy rules makes them a promising candidate for online modeling and control of complex processes, competitive to neural networks. The approach has been tested on data from an air-conditioning installation serving a real building. The results illustrate the viability and efficiency of the approach. The proposed concept, however, has significantly wider implications in a number of fields, including adaptive nonlinear control, fault detection and diagnostics, performance analysis, forecasting, knowledge extraction, robotics, behavior modeling.

Understanding complex systems often requires a bottom-up analysis towards a systems biology approach. The need to investigate a system, not only as individual components but as a whole, emerges. This can be done by examining the elementary constituents individually and then how these are connected. The myriad components of a system and their interactions are best characterized as networks and they are mainly represented as graphs where thousands of nodes are connected with thousands of vertices. In this article we demonstrate approaches, models and methods from the graph theory universe and we discuss ways in which they can be used to reveal hidden properties and features of a network. This network profiling combined with knowledge extraction will help us to better understand the biological significance of the system.

This review paper focuses on modelling of wastewater treatment plants (WWTP). White-box modelling is widely applied in this field, with learning, design and process optimisation as the main applications. The introduction of the ASM model family by the IWA task group was of great importance, providing researchers and practitioners with a standardised set of basis models. This paper introduces the nowadays most frequently used white-box models for description of biological nitrogen and phosphorus removal activated sludge processes. These models are mainly applicable to municipal wastewater systems, but can be adapted easily to specific situations such as the presence of industrial wastewater. Some of the main model assumptions are highlighted, and their implications for practical model application are discussed. A step-wise procedure leads from the model purpose definition to a calibrated WWTP model. Important steps in the procedure are: model purpose definition, model selection, data collection, data reconciliation, calibration of the model parameters and model unfalsification. The model purpose, defined at the beginning of the procedure, influences the model selection, the data collection and the model calibration. In the model calibration a process engineering approach, i.e. based on understanding of the process and the model structure, is needed. A calibrated WWTP model, the result of an iterative procedure, can usually be obtained by only modifying few model parameters, using the default parameter sets as a starting point. Black-box, stochastic grey-box and hybrid models are useful in WWTP applications for prediction of the influent load, for estimation of biomass activities and effluent quality parameters. These modelling methodologies thus complement the process knowledge included in white-box models with predictions based on data in areas where the white-box model assumptions are not valid or where white-box models do not provide accurate predictions. Artificial intelligence (AI) covers a large spectrum of methods, and many of them have been applied in applications related to WWTPs. AI methodologies and white-box models can interact in many ways; supervisory control systems for WWTPs are one evident application. Modular agent-based systems combining several AI and modelling methods provide a great potential. In these systems, AI methods on one hand can maximise the knowledge extracted from data and operator experience, and subsequently apply this knowledge to improve WWTP control. White-box models on the other hand allow evaluating scenarios based on the available process knowledge about the WWTP. A white-box model calibration tool, an AI based WWTP design tool and a knowledge representation tool in the WWTP domain are other potential applications where fruitful interactions between AI methods and white-box models could be developed. 

The increasing availability of large-scale location traces creates unprecedent opportunities to change the paradigm for knowledge discovery in transportation systems. A particularly promising area is to extract energy-efficient transportation patterns (green knowledge), which can be used as guidance for reducing inefficiencies in energy consumption of transportation sectors. However, extracting green knowledge from location traces is not a trivial task. Conventional data analysis tools are usually not customized for handling the massive quantity, complex, dynamic, and distributed nature of location traces. To that end, in this paper, we provide a focused study of extracting energy-efficient transportation patterns from location traces. Specifically, we have the initial focus on a sequence of mobile recommendations. As a case study, we develop a mobile recommender system which has the ability in recommending a sequence of pick-up points for taxi drivers or a sequence of potential parking positions. The goal of this mobile recommendation system is to maximize the probability of business success. Along this line, we provide a Potential Travel Distance (PTD) function for evaluating each candidate sequence. This PTD function possesses a monotone property which can be used to effectively prune the search space. Based on this PTD function, we develop two algorithms, LCP and SkyRoute, for finding the recommended routes. Finally, experimental results show that the proposed system can provide effective mobile sequential recommendation and the knowledge extracted from location traces can be used for coaching drivers and leading to the efficient use of energy.

The paper describes the development and application of several techniques for knowledge extraction from trained ANN models, such as the identification of redundant inputs and hidden neurons, deriving of causal relationships between inputs and outputs, and analysis of the hidden neuron behavior in classification ANN. Example of the application of these techniques is given of the faulty LED display benchmark. References of the application of these techniques are given of diverse large scale ANN models of industrial processes.

In recent years, the interaction between evolution and learning has received much attention from the research commu-12 nity. Some recent studies on machine learning have shown that it can significantly improve the efficiency of problem solv-13 ing when using evolutionary algorithms. This paper proposes an architecture for learning and evolving of flexible job-shop 14 schedules called LEarnable genetic architecture (LEGA). LEGA provides an effective integration between evolution and 15 learning within a random search process. Unlike the canonical evolution algorithm, where random elitist selection and 16 mutational genetics are assumed; through LEGA, the knowledge extracted from previous generation by its schemata learn-17 ing module is used to influence the diversity and quality of offsprings. In addition, the architecture specifies a population 18 generator module that generates the initial population of schedules and also trains the schemata learning module. A large 19 range of benchmark data taken from literature and some generated by ourselves are used to analyze the efficacy of LEGA. 20 Experimental results indicate that an instantiation of LEGA called GENACE outperforms current approaches using 21 canonical EAs in computational time and quality of schedules. 22 43 involves n jobs and m machines. Each job is to 44 be processed on each machine in a pre-defined 45 sequence. Each operation of a job is to be processed 46 only on one machine at a time. In practice, the shop-47 floor setup typically consists of multiple copies of 48 the most critical machines so that bottlenecks due 49 to long operations or busy machines can be reduced. 50 Therefore, an operation may be processed on more 51 than one machine having the same function. This 52 leads to a more complex problem known as the flex-53 ible job-shop scheduling problem (FJSP). With the 54 new extension, two decisions have to be made: 55 assignment of an operation to an appropriate 56 machine and sequencing the operations on each 57 machine. In addition, for complex manufacturing 58 systems, a job can visit a machine more than once 59 (called recirculation). These three features of the 60 FJSP significantly increase the complexity of finding 61 even approximately optimal solutions [7]. 62

This paper reports the first part of a project that aims to develop a knowledge extraction and knowledge discovery system that extracts causal knowledge from textual databases. In this initial study, we develop a method to identify and extract cause-effect information that is explicitly expressed in medical abstracts in the Medline database. A set of graphical patterns were constructed that indicate the presence of a causal relation in sentences, and which part of the sentence represents the cause and which part represents the effect. The patterns are matched with the syntactic parse trees of sentences, and the parts of the parse tree that match with the slots in the patterns are extracted as the cause or the effect.

GPS devices allow recording the movement track of the moving object they are attached to. This data typically consists of a stream of spatio-temporal (x,y,t) points. For application purposes the stream is transformed into finite subsequences called trajectories. Existing knowledge extraction algorithms defined for trajectories mainly assume a specific context (e.g. vehicle movements) or analyze specific parts of a trajectory (e.g. stops), in association with data from chosen geographic sources (e.g. points-of-interest, road networks). We investigate a more comprehensive semantic annotation framework that allows enriching trajectories with any kind of semantic data provided by multiple 3rd party sources.

Community discovery in complex networks is an interesting problem with a number of applications, especially in the knowledge extraction task in social and information networks. However, many large networks often lack a particular community organization at a global level. In these cases, traditional graph partitioning algorithms fail to let the latent knowledge embedded in modular structure emerge, because they impose a top-down global view of a network. We propose here a simple local-first approach to community discovery, able to unveil the modular organization of real complex networks. This is achieved by democratically letting each node vote for the communities it sees surrounding it in its limited view of the global system, i.e. its ego neighborhood, using a label propagation algorithm; finally, the local communities are merged into a global collection. We tested this intuition against the state-of-the-art overlapping and non-overlapping community discovery methods, and found that our new method clearly outperforms the others in the quality of the obtained communities, evaluated by using the extracted communities to predict the metadata about the nodes of several real world networks. We also show how our method is deterministic, fully incremental, and has a limited time complexity, so that it can be used on web-scale real networks.

Although much research has been done over the decades on the formulation of statistical regression models for road traffic relationships, they have been largely unsuitable due to the complexity of traffic characteristics. Traffic engineers have resorted to alternative methods such as neural networks, but despite some promising results, the difficulties in their design and implementation remain unresolved. In addition, the opaqueness of trained networks prevents understanding the underlying models. Fuzzy neural networks, which combine the complementary capabilities of both neural networks and fuzzy logic, thus constitute a more promising technique for modeling traffic flow. This paper describes the application of a specific class of fuzzy neural network known as the pseudo outer-product fuzzy neural network using the truth-value-restriction method (POPFNN-TVR) for shortterm traffic flow prediction. The obtained results highlight the capability of POPFNN-TVR in fuzzy knowledge extraction and generalization from input data as well its high degree of prediction capability as compared to traditional feedforward neural networks using backpropagation learning.

Motor fault detection and diagnosis involves processing a large amount of information of the motor system. With the combined synergy of fuzzy logic and neural networks, a better understanding of the heuristics underlying the motor fault detection/diagnosis process and successful fault detection/diagnosis schemes can be achieved. This paper presents two neural fuzzy (NN/FZ) inference systems, namely, Fuzzy Adaptive Learning Control/Decision Network (FALCON) and Adaptive Network Based Fuzzy Inference System (ANFIS), with applications to induction motor fault detection/diagnosis problems. The general specifications of the NN/FZ systems are discussed. In addition, the fault detection/diagnosis structures are analyzed and compared with regard to their learning algorithms, initial knowledge requirements, extracted knowledge types, domain partitioning, rule structuring and modifications. Simulated experimental results are presented in terms of motor fault detection accuracy and knowledge extraction feasibility. Results suggest new and promising research areas for using NN/FZ inference systems for incipient fault detection and diagnosis in induction motors.

A new scheme based on multi-objective hierarchical genetic algorithm (MOHGA) is proposed to extract interpretable rule-based knowledge from data. The approach is derived from the use of multiple objective genetic 13 algorithm (MOGA), where the genes of the chromosome are arranged into control genes and parameter genes. These genes are in a hierarchical form so that the control genes can manipulate the parameter genes in a more 15 effective manner. The effectiveness of this chromosome formulation enables the fuzzy sets and rules to be optimally reduced. Some important concepts about the interpretability are introduced and the fitness function in the MOGA 17 will consider both the accuracy and interpretability of the fuzzy model. In order to remove the redundancy of the rule base proactively, we further apply an interpretability-driven simplification method to newborn individuals. In 19 our approach, we first apply the fuzzy clustering to generate an initial rule-based model. Then the multi-objective hierarchical genetic algorithm and the recursive least square method are used to obtain the optimized fuzzy models.

This paper deals with the problem of detection and diagnosis of induction motor faults. Using the fuzzy logic strategy, a better understanding of heuristics underlying the motor faults detection and diagnosis process can be achieved. The proposed fuzzy approach is based on the stator current Concordia patterns. Induction motor stator currents are measured, recorded, and used for Concordia patterns computation under different operating conditions, particularly for different load levels. Experimental results are presented in terms of accuracy in the detection motor faults and knowledge extraction feasibility. The preliminary results show that the proposed fuzzy approach can be used for accurate stator fault diagnosis if the input data are processed in an advantageous way, which is the case of the Concordia patterns.

In this paper, we argue that a core ontology is one of the key building blocks necessary to enable the scalable assimilation of information from diverse sources. A complete and extensible ontology that expresses the basic concepts that are common across a variety of domains and can provide the basis for specialization into domain-specific concepts and vocabularies, is essential for well-defined mappings between domain-specific knowledge representations (i.e., metadata vocabularies) and the subsequent building of a variety of services such as cross-domain searching, browsing, data mining and knowledge extraction. This paper describes the results of a series of three workshops held in 2001 and 2002 which brought together representatives from the cultural heritage and digital library communities with the goal of harmonizing their knowledge perspectives and producing a core ontology. The knowledge perspectives of these two communities were represented by the CIDOC/CRM [31], an ontology for information exchange in the cultural heritage and museum community, and the ABC ontology [33], a model for the exchange and integration of digital library information. This paper describes the mediation process between these two different knowledge biases and the results of this mediation -the harmonization of the ABC and CIDOC/CRM ontologies, which we believe may provide a useful basis for information integration in the wider scope of the involved communities.

The Lattes platform is the major scientific information system maintained by the National Council for Scientific and Technological Development (CNPq). This platform allows to manage the curricular information of researchers and institutions working in Brazil based on the so called Lattes Curriculum. However, the public information is individually available for each researcher, not providing the automatic creation of reports of several scientific productions for research groups. It is thus difficult to extract and to summarize useful knowledge for medium to large size groups of researchers. This paper describes the design, implementation and experiences with scriptLattes: an open-source system to create academic reports of groups based on curricula of the Lattes Database. The scriptLattes system is composed by the following modules: (a) data selection, (b) data preprocessing, (c) redundancy treatment, (d) collaboration graph generation among group members, (e) research map generation based on geographical information, and (f) automatic report creation of bibliographical, technical and artistic production, and academic supervisions. The system has been extensively tested for a large variety of research groups of Brazilian institutions, and the generated reports have shown an alternative to easily extract knowledge from data in the context of Lattes platform. The source code, usage instructions and examples are available at http://scriptlattes.sourceforge.net/.

The process knowledge assets make a substantial contribution to the risk management (RM) for contractors in the construction phase. To effectively reuse these assets, knowledge extraction becomes a significant research area. This paper was designed to explore an approach to conduct knowledge extraction by establishing project risk ontology. Specifically, the study proposed the ontology-based risk management (ORM) framework to enhance the RM performance by improving the RM workflow and knowledge reuse. The ORM framework facilitated the identification, analysis, and response of project risks. This study validated the ORM framework through a case demonstration. Through the implementation and application, the results demonstrated that the ORM framework was able to apply to the RM workflow for contractors, and more importantly, it greatly increased the effectiveness of project RM.

Feature extraction is an important aspect in data mining and knowledge discovery. In this paper an integrated feature extraction approach, which is based on rough set theory and genetic algorithms (GAs), is proposed. Based on this approach, a prototype feature extraction system has been established and illustrated in an application for the simplification of product quality evaluation. The prototype system successfully integrates the capability of rough set theory in handling uncertainty with a robust search engine, which is based on a GA. The results show that it can remarkably reduce the cost and time consumed on product quality evaluation without compromising the overall specifications of the acceptance tests.

Patterns summarizing mutual associations between class decisions and attribute values in a pre-classified database, provide insight into the significance of attributes and also useful classificatory knowledge. In this paper we have proposed a conditional probability based, efficient method to extract the significant attributes from a database. Reducing the feature set during pre-processing enhances the quality of knowledge extracted and also increases the speed of computation. Our method supports easy visualization of classificatory knowledge. A likelihood-based classification algorithm that uses this classificatory knowledge is also proposed. We have also shown how the classification methodology can be used for cost-sensitive learning where both accuracy and precision of prediction are important.

Data mining offers tools for discovery of relationships, patterns, and knowledge in large databases. The knowledge extraction process is computationally complex and therefore a subset of all data is normally considered for mining. In this paper, numerous methods for decomposition of data sets are discussed. Decomposition enhances the quality of knowledge extracted from large databases by simplification of the data mining task. The ideas presented are illustrated with examples and an industrial case study. In the case study reported in this paper, a data mining approach is applied to extract knowledge from a data set. The extracted knowledge is used for the prediction and prevention of manufacturing faults in wafers.

MEDSYNDIKATE is a natural language processor for automatically acquiring knowledge from medical finding reports. The content of these documents is transferred to formal representation structures which constitute a corresponding text knowledge base. The system architecture integrates requirements from the analysis of single sentences, as well as those of referentially linked sentences forming cohesive texts. The strong demands MEDSYNDIKATE poses to the availability of expressive knowledge sources are accounted for by two alternative approaches to (semi)automatic ontology engineering. We also present data for the knowledge extraction performance of MEDSYNDIKATE for three major syntactic patterns in medical documents.

We present a novel, innovative user interface to music repositories. Given an arbitrary collection of digital music files, our system creates a virtual landscape which allows the user to freely navigate in this collection. This is accomplished by automatically extracting features from the audio signal and training a Self-Organizing Map (SOM) on them to form clusters of similar sounding pieces of music. Subsequently, a Smoothed Data Histogram (SDH) is calculated on the SOM and interpreted as a three-dimensional height profile. This height profile is visualized as a three-dimensional island landscape containing the pieces of music. While moving through the terrain, the closest sounds with respect to the listener's current position can be heard. This is realized by anisotropic auralization using a 5.1 surround sound model. Additionally, we incorporate knowledge extracted automatically from the web to enrich the landscape with semantic information. More precisely, we display words and related images that describe the heard music on the landscape to support the exploration.

Pathology ordering by General Practitioners (GPs) is a significant contributor to rising health care costs both in Australia and worldwide. A thorough understanding of the nature and patterns of pathology utilization is an essential requirement for effective decision support for pathology ordering. In this paper a novel methodology for integrating data mining and case based reasoning for decision support for pathology ordering is proposed. It is demonstrated how this methodology can facilitate intelligent decision support that is both patient-oriented and deeply rooted in practical peer-group evidence. Comprehensive data collected by professional pathology companies provide a system-wide profile of patient-specific pathology requests by various GPs as opposed to that limited to an individual GP practice. Using the real data provided by XYZ Pathology Company in Australia that contain more than 1.5 million records of pathology requests by general practitioners (GPs), we illustrate how knowledge extracted from these data through data mining with Kohonen's Self-Organizing Maps constitutes the base that, with further assistance of modern data visualization tools and on-line processing interfaces, can provide "peer-group consensus" evidence support for solving new cases of pathology test ordering problem. The conclusion is that the formal methodology that integrates case-based reasoning principles which are inherently close to GPs' daily practice, and data-driven computationally intensive knowledge discovery mechanisms which can be applied to massive amounts of the pathology requests data routinely available at professional pathology companies, can facilitate more informed evidential decision making by doctors in the area of pathology ordering.

BackgroundOpen-source clinical natural-language-processing (NLP) systems have lowered the barrier to the development of effective clinical document classification systems. Clinical natural-language-processing systems annotate the syntax and semantics of clinical text; however, feature extraction and representation for document classification pose technical challenges.MethodsThe authors developed extensions to the clinical Text Analysis and Knowledge Extraction System (cTAKES) that simplify feature extraction, experimentation with various

Traditional Content-Based Image Retrieval (CBIR) systems only deliver visual outputs that are not directly interpretable by the physicians. Our objective is to provide a system for endomicroscopy video retrieval which delivers both visual and semantic outputs that are consistent with each other. In a previous study, we developed an adapted bag-of-visual-words method for endomicroscopy retrieval that computes a visual signature for each video. In this study, we first leverage semantic ground-truth data to transform these visual signatures into semantic signatures that reflect how much the presence of each semantic concept is expressed by the visual words describing the videos. Using cross-validation, we demonstrate that our visual-word-based semantic signatures enable a recall performance which is significantly higher than those of several state-of-the-art methods in CBIR. In a second step, we propose to improve retrieval relevance by learning, from a perceived similarity ground truth, an adjusted similarity distance. Our distance learning method allows to improve, with statistical significance, the correlation with the perceived similarity. Our resulting retrieval system is efficient in providing both visual and semantic information that are correlated with each other and clinically interpretable by the endoscopists.

The flow of data generated from low-cost modern sensing technologies and wireless telecommunication devices enables novel research fields related to the management of this new kind of data and the implementation of appropriate analytics for knowledge extraction. In this work, we investigate how the traditional data cube model is adapted to trajectory warehouses in order to transform raw location data into valuable information. In particular, we focus our research on three issues that are critical to trajectory data warehousing: (a) the trajectory reconstruction procedure that takes place when loading a moving object database with sampled location data originated e.g. from GPS recordings, (b) the ETL procedure that feeds a trajectory data warehouse, and (c) the aggregation of cube measures for OLAP purposes. We provide design solutions for all these issues and we test their applicability and efficiency in real world settings.

Alzheimer's dementia is developing ever more as a complex syndrome with various unknown genetic and epigenetic contributions. These are compounded on and exacerbating the underlying amyloid and tau pathology that remain the basis of the pathological definition of ...

Creating and maintaining software systems is a knowledge intensive task. One needs to have a good understanding of the application domain, the problem to solve and all its requirements, the software process used, technical details of the programming language(s), the system's architecture and how the diVerent parts Wt together, how the system interacts with its environment, etc. All this knowledge is diYcult and costly to gather. It is also diYcult to store and usually lives only in the mind of the software engineers who worked on a particular project.

We describe the web usage mining activities of an on-going project, called ClickWorld 1 , that aims at extracting models of the navigational behaviour of a web site users. The models are inferred from the access logs of a web server by means of data and web mining techniques. The extracted knowledge is deployed to the purpose of offering a personalized and proactive view of the web services to users. We first describe the preprocessing steps on access logs necessary to clean, select and prepare data for knowledge extraction. Then we show two sets of experiments: the first one tries to predict the sex of a user based on the visited web pages, and the second one tries to predict whether a user might be interested in visiting a section of the site.

Analyzing data from well logs and seismic is often a complex and laborious process because a physical relationship cannot be established to show how the data are correlated. In this study, we will develop the next generation of AintelligentB software that will identify the nonlinear relationship and mapping between well logsrrock properties and seismic Ž . information and extract rock properties, relevant reservoir information and rules knowledge from these databases. The software will use fuzzy logic techniques because the data and our requirements are imperfect. In addition, it will use neural network techniques, since the functional structure of the data is unknown. In particular, the software will be used to group data into important data sets; extract and classify dominant and interesting patterns that exist between these data sets; discover secondary, tertiary and higher-order data patterns; and discover expected and unexpected structural relationships between data sets. q 2001 Published by Elsevier Science B.V.

This study presents a data mining approach for modeling TripAdvisor score using 504 reviews published in 2015 for the 21 hotels located in the Strip, Las Vegas. Nineteen quantitative features characterizing the reviews, hotels and the users were prepared and used for feeding a support vector machine for modeling the score. The results achieved reveal the model demonstrated adequate predictive performance. Therefore, a sensitivity analysis was applied over the model for extracting useful knowledge translated into features' relevance for the score. The findings unveiled user features related to TripAdvisor membership experience play a key role in influencing the scores granted, clearly surpassing hotel features. Also, both seasonality and the day of the week were found to influence scores. Such knowledge may be helpful in directing efforts to answer online reviews in alignment with hotel strategies, by profiling the reviews according to the member and review date.

Text-mining can assist biomedical researchers in reducing information overload by extracting useful knowledge from large collections of text. We developed a novel text-mining method based on analyzing the network structure created by symbol co-occurrences as a way to extend the capabilities of knowledge extraction. The method was applied to the task of automatic gene and protein name synonym extraction. Performance was measured on a test set consisting of about 50,000 abstracts from one year of MEDLINE. Synonyms retrieved from curated genomics databases were used as a gold standard. The system obtained a maximum F-score of 22.21% (23.18% precision and 21.36% recall), with high efficiency in the use of seed pairs. The method performs comparably with other studied methods, does not rely on sophisticated named-entity recognition, and requires little initial seed knowledge.

and-conditions-of-access.pdf This article may be used for research, teaching and private study purposes. Any substantial or systematic reproduction, redistribution , reselling , loan or sub-licensing, systematic supply or distribution in any form to anyone is expressly forbidden. The publisher does not give any warranty express or implied or make any representation that the contents will be complete or accurate or up to date. The accuracy of any instructions, formulae and drug doses should be independently verified with primary sources. The publisher shall not be liable for any loss, actions, claims, proceedings, demand or costs or damages whatsoever or howsoever caused arising directly or indirectly in connection with or arising out of the use of this material.

Discovery and Artificial Neural Networks in order to identify and analyse levels of country, business and political risk. Its main goal is to help business decision-makers understand the dynamics within the emerging market countries in which they operate. Most of the neural models applied in this study are defined within the framework of unsupervised learning. They are based on Exploratory Projection Pursuit, Topology Preserving Maps and Curvilinear Component Analysis. Two interesting real data sets are analysed to empirically probe the robustness of these models. The first case study describes information from a significant sample of Spanish Multinational Enterprises (MNEs). It analyses data pertaining to such aspects as decisions over the location of subsidiary enterprises in various regions across the world, the importance accorded to such decisions and the driving forces behind them.

This paper presents a general framework for designing a fuzzy rule-based classifier. Structure and parameters of the classifier are evolved through a two-stage genetic search. To reduce the search space, the classifier structure is constrained by a tree created using the evolving SOM tree algorithm. Salient input variables are specific for each fuzzy rule and are found during the genetic search process. It is shown through computer simulations of four real world problems that a large number of rules and input variables can be eliminated from the model without deteriorating the classification accuracy. By contrast, the classification accuracy of unseen data is increased due to the elimination.

In this paper, we introduce Artificial Nonmonotonic Neural Networks (ANNNs), a kind of hybrid learning systems that are capable of nonmonotonic reasoning. Nonmonotonic reasoning plays an important role in the development of artificial intelligent systems that try to mimic common sense reasoning, as exhibited by humans. On the other hand, a hybrid learning system provides an explanation capability to trained Neural Networks through acquiring symbolic knowledge of a domain, refining it using a set of classified examples along with Connectionist learning techniques and, finally, extracting comprehensible symbolic information. Artificial Nonmonotonic Neural Networks acquire knowledge represented by a multiple inheritance scheme with exceptions, such as nonmonotonic inheritance networks, and then can extract the refined knowledge in the same scheme. The key idea is to use a special cell operation during training in order to preserve the symbolic meaning of the initial inheritance scheme. Methods for knowledge initialization, knowledge refinement and knowledge extraction are introduced. We, also, prove that these methods address perfectly the constraints imposed by nonmonotonicity. Finally, performance of ANNNs is compared to other well-known hybrid systems, through extensive empirical tests.

The h-TechSight Knowledge Management Portal (KMP) enables support for knowledgeintensive industries in monitoring information resources on the Web, as an important factor in business competitiveness. The portal contains tools for identification of concepts and terms from an ontology relevant to the user's interests, and enables the user to monitor them over time. It also contains tools for ontology management and modification, based on the results of targeted knowledge extraction from the web. The platform provides a means for businesses to keep track of trends and topics of interest in their field, and alert them to changes. In this paper we focus on the tools for targeted search and ontology management, driven by an ontology-based information extraction system, which has been evaluated over a test set of 38 documents and achieves 97% Precision and 92% Recall.

Microarray technology can measure the expression levels of thousands of genes in an experiment. This fact makes the use of computational methods in cancer research absolutely essential. One of the possible applications is in the use of Artificial Intelligence techniques. Several of these techniques have been used to analyze expression arrays, but there is a growing need for new and

New challenges in knowledge extraction include interpreting and classifying data sets while simultaneously considering related information to confirm results or identify false positives. We discuss a data fusion algorithmic framework targeted at this problem. It includes separate base classifiers for each data type and a fusion method for combining the individual classifiers. The fusion method is an extension of current ensemble classification techniques and has the advantage of allowing data to remain in heterogeneous databases. In this paper, we focus on the applicability of this framework to the protein phosphorylation prediction problem.

Background: Last years' mapping of diverse genomes has generated huge amounts of biological data which are currently dispersed through many databases. Integration of the information available in the various databases is required to unveil possible associations relating already known data. Biological data are often imprecise and noisy. Fuzzy set theory is specially suitable to model imprecise data while association rules are very appropriate to integrate heterogeneous data.

This paper deals with an evaluation and comparison of the accuracy and complexity of symbolic rules extracted from radial basis function networks and multilayer perceptrons. Here we examine the ability of rule extraction algorithms to extract meaningful rules that describe the overall performance of a particular network. In addition, the paper also highlights the suitability of a specific neural network architecture for particular classification problems. The study carried out on the extracted rule quality and complexity also has a direct bearing on the use of rule extraction algorithms for data mining and knowledge discovery

A traditional goal of Artificial Intelligence research has been a system that can read unrestricted natural language texts on a given topic, build a model of that topic and reason over the model. Natural Language Processing advances in syntax and semantics have made it possible to extract a limited form of meaning from sentences. Knowledge Representation research has shown that it is possible to model and reason over topics in interesting areas of human knowledge. It is useful for these two communities to reunite periodically to see where we stand with respect to the common goal of text understanding.

To reduce the increasing amount of time spent on literature search in the life sciences, several methods for automated knowledge extraction have been developed. Co-occurrence based approaches can deal with large text corpora like MEDLINE in an acceptable time but are not able to extract any specific type of semantic relation. Semantic relation extraction methods based on syntax trees, on the other hand, are computationally expensive and the interpretation of the generated trees is difficult. Several natural language processing (NLP) approaches for the biomedical domain exist focusing specifically on the detection of a limited set of relation types. For systems biology, generic approaches for the detection of a multitude of relation types which in addition are able to process large text corpora are needed but the number of systems meeting both requirements is very limited. We introduce the use of SENNA (''Semantic Extraction using a Neural Network Architecture''), a fast and accurate neural network based Semantic Role Labeling (SRL) program, for the large scale extraction of semantic relations from the biomedical literature. A comparison of processing times of SENNA and other SRL systems or syntactical parsers used in the biomedical domain revealed that SENNA is the fastest Proposition Bank (PropBank) conforming SRL program currently available. 89 million biomedical sentences were tagged with SENNA on a 100 node cluster within three days. The accuracy of the presented relation extraction approach was evaluated on two test sets of annotated sentences resulting in precision/recall values of 0.71/0.43. We show that the accuracy as well as processing speed of the proposed semantic relation extraction approach is sufficient for its large scale application on biomedical text. The proposed approach is highly generalizable regarding the supported relation types and appears to be especially suited for general-purpose, broad-scale text mining systems. The presented approach bridges the gap between fast, cooccurrencebased approaches lacking semantic relations and highly specialized and computationally demanding NLP approaches.

In this paper, we examine the use of knowledge query technology as applied to conversation bots in the instant messaging environment. Hence, we designed an artificial intelligent conversation robot or bots called Artificial Intelligence Natural language Identity (hereafter, AINI) to mimic human conversation. Our goal is to introduce a Domain Matrix Knowledge Model and an Automated Knowledge Extraction Agent (AKEA) to create AINI's knowledge bases, and in turn provide intelligent query mechanisms. We report an evaluation on the collection and analysis of a corpus containing over 3280 utterances in a series of real instant messages exchanged between the AINI conversation bot and 65 online ''buddies". About 1721 utterances were produced by AINI, 88.03% were from open-domain knowledge, 2.15% from domain-specific knowledge base and 9.82% were inappropriate and amusing responses. These results show that domain knowledge plays significant roles in conversations between two or more human users and in human-machine conversation.

In the post-genomic era, systems-level studies are being performed that seek to explain complex biological systems by integrating diverse resources from fields such as genomics, proteomics or transcriptomics. New information management systems are now needed for the collection, validation and analysis of the vast amount of heterogeneous data available. Multiple alignments of complete sequences provide an ideal environment for the integration of this information in the context of the protein family.