Knowledge-Based and Intelligent Information and Engineering Systems

Text categorization is one of the most common themes in data mining and machine learning fields. Unlike structured data, unstructured text data is more complicated to be analyzed because it contains too much information, e.g., syntactic and semantic. In this paper, we propose a semantics-based model to represent text data in two levels. One level is for syntactic information and the other is for semantic information. Syntactic level represents each document as a term vector, and the component records tf-idf value of each term. The semantic level represents document with Wikipedia concepts related to terms in syntactic level. The syntactic and semantic information are efficiently combined by our proposed multi-layer classification framework. Experimental results on benchmark dataset (Reuters-21578) have shown that the proposed representation model plus proposed classification framework improves the performance of text classification by comparing with the flat text representation models (term VSM, concept VSM, term+concept VSM) plus existing classification methods.

High dimensionality is a major challenge in document clustering. Some of the recent algorithms address this problem by using frequent itemsets for clustering. But, most of these algorithms neglect the semantic relationship between the words. On the other hand there are algorithms that take care of the semantic relations between the words by making use of external knowledge contained in WordNet, Mesh, Wikipedia, etc but do not handle the high dimensionality. In this paper we present an efficient solution that addresses both these problems. We propose a hierarchical clustering algorithm using closed frequent itemsets that use Wikipedia as an external knowledge to enhance the document representation. We evaluate our methods based on F-Score on standard datasets and show our results to be better than existing approaches.

In this work we investigate the use of various character, lexical, and syntactic level features and their combinations in automatic authorship attribution. Since the majority of text representation features are language specific, we examine their application on texts written in Croatian language. Our work differs from the similar work in at least three aspects. Firstly, we use slightly different set of features than previously proposed. Secondly, we use four different data sets and compare the same features across those data sets to draw stronger conclusions. The data sets that we use consist of articles, blogs, books, and forum posts written in Croatian language. Finally, we employ a classification method based on a strong classifier. We use the Support Vector Machines to learn classifiers which achieve excellent results for longer texts: 91% accuracy and

F

1

measure for blogs, 93% acc. and

F

1

for articles, and 99% acc. and

F

1

for books. Experiments conducted on forum posts show that more complex features need to be employed for shorter texts.

This work presents a survey of methods that visualize text streams. Existing methods are classified and compared from the aspect of visualization process. We introduce new aspects of method comparison: data type, text representation, and the temporal drawing approach. The subjectivity of visualization is described, and evaluation methodologies are explained. Related research areas are discussed and some future trends in the field anticipated.

In this article, an architecture for image retrieval in an Object-Relational Database Management System is proposed. It combines the use of low-level descriptors and semantic metadata for similarity search. The architecture has three levels: content-based, semantic data and an interface integrating them. Several database User Defined Types (UDT) and operations are defined for that purpose. A case study about vehicles is implemented and results obtained show an important improvement in image similarity search.

The area of Urban Computing has emerged from the paradigm of Ubiquitous Computing. Urban Computing shares the same requirements with its predecessor. However, Urban Computing needs to support spontaneous social groups. Therefore, a key requirement of Urban Computing is spontaneity, which is about composing services during runtime, without having predefined templates of applications. This paper leverages the approach of task-oriented computing, in order to compose a task by extending an existing task template with new or substitute functionality. The inclusion of new functionality is realized by analyzing the history of task execution. The appropriateness of the task composition mechanism is illustrated by an example scenario in our campus.

In recent years there has been a growing interest in mobile recommender systems for the tourism domain, because they can support users visiting new places, suggesting restaurants, hotels, attractions, or entire itineraries. The effectiveness of their suggestions mainly depends on the item retrieval process. How well is the system able to retrieve items that meet users’ needs and preferences? In this paper we propose a multi-criteria collaborative approach, that offers a complete method for calculating users’ similarities and rating predictions on items to be recommended. It is a purely multi-criteria approach, that uses Pearson’s correlation coefficient to compute similarities among users. Experimental results evaluating the retrieval effectiveness of the proposed approach in a prototype mobile cultural heritage recommender system (that suggests visits to cultural locations in Apulia region) show a better retrieval precision than a standard collaborative approach based on the same metrics.

In recent years, ontologies have become an essential tool to structure and reuse the exponential growth of information in the Web. As the number of publicly available ontologies increases, researchers face the problem of finding the ontology (or ontologies) which provides the best coverage for a particular context. In this paper, we propose an approach to automatically recommend the best ontology for an initial set of terms. The approach is based on measuring the adequacy of the ontology according to three different criteria: (1) How well the ontology covers the given terms, (2) the semantic richness of the ontology and, importantly, (3) the popularity of the ontology in the Web 2.0. In order to evaluate this approach, we implemented a prototype to recommend ontologies in the biomedical domain. Results show the importance of using collaborative knowledge in the field of ontology recommendation.

The problem of knowledge extraction from the data left by web users during their interactions is a very attractive research task. The extracted knowledge can be used for different goals such as service personalization, site structure simplification, web server performance improvement or even for studying the human behavior. We constructed a system, called

ELM

(Event Logger Manager), able to register and analyze data from different applications. The registered data can be specified in an experiment. ELM provides several knowledge mining algorithms i.e. Apriori, ID3, C4.5. The objective of this paper is to present knowledge mining in data from interactions between user and a simple application conducted with ELM system.

The retrieval of similar documents from large scale datasets has been the one of the main concerns in knowledge management environments, such as plagiarism detection, news impact analysis, and the matching of ideas within sets of documents. In all of these applications, a light-weight architecture can be considered as fundamental for the large scale of information needed to be analyzed. Furthermore, the relevance score for documents retrieval can be significantly improved using several previously built search engines and taking into account the relevance feedback from users. In this work, we propose a web-services architecture for the retrieval of similar documents from the web. We focus on software engineering to support the manipulation of users’ knowledge into the retrieval algorithm. An human evaluation for the relevance feedback of the system over a built set of documents is presented, showing that the proposed architecture can retrieve similar documents by using the main search engines. In particular, the document plagiarism detection task was evaluated, for which its main results are shown.

Exploratory Learning Environments (ELEs) allow learners to approach a problem in different ways; they are particularly suitable for ill-defined problems where knowledge is less structured and open-ended exploration is allowed. Moreover, multiple solutions which are equally valid are possible and a common and efficient way to convey this is by promoting and supporting students’ collaboration. Successful collaboration, however, depends on forming groups in which the activity is relevant for all members of the group. In this paper we present a computational model for group formation for open-ended exploration in ELEs by modelling the various strategies that learners adopt to solve the same task. This is underpinned by Group Technology techniques that use as criteria the learners’ strategies and the similarity among them to form groups that match pedagogy considerations. The proposed mechanism is tested in an exploratory learning environment for mathematical generalisation.

In teaching field, the building of programs, curricula, courses and lectures is considered as key phase in the development of learning contents and materials. Therefore, an issued learning content satisfied principle of complete, logical, and pedagogical qualities is necessary and quite challenge task for teaching and learning process in both traditional learning and e-Learning environment. In this paper, we propose an approach to creating on-line course, called e-Course, which is able to meet requirements above. The proposed e-Course is based on pedagogical analyses and basic teaching principles, its application focuses on two main actors of an e-Learning system in which the instructor designs and builds e-Course that its result is a set of interacted topics or lessons, and the learner uses e-Course in self-study activities on-line or not.

In exploratory learning environments, learners can use different strategies to solve a problem. To the designer or teacher, however, not all these strategies are known in advance and, even if they were, introducing them in the knowledge base would involve considerable time and effort. In previous work, we have proposed a case-based knowledge representation, modelling the learners’ behaviour when constructing/exploring models through simple cases and sequences of cases, called strategies. In this paper, we enhance this approach with adaptive mechanisms for expanding the knowledge base. These mechanisms allow to identify and store inefficient cases, i.e. cases that pose additional difficulty to students in their learning process, and to gradually enrich the knowledge base by detecting and adding new strategies.

Reprogramming sensor nodes is important for managing sensor networks. Since the number of deployments is increasing, the need for an efficient and reliable reprogramming service is growing. Reprogramming protocols use radio communication to distribute software data. Many studies about software data dissemination have been done, but there have been little knowledge about reprogramming on sensor nodes, and challenges with reprogramming in real sensor networks have not resolved. Therefore, we designed and implemented a reprogramming scheme on real sensor nodes.

As a result of investigation on learning preferences and e-learning course adaptability among the students of full online courses offered by a consortium of higher education institutions, it has been found that there is a relationship between the two factors (the preference for asynchronous learning and that for the use of computer) in the learning preferences and the e-learning course adaptability. In addition, it has been found that the learning preferences of a student may change after taking an e-learning course. Furthermore, it has been found that a multiple regression analysis of the learning preferences of a student at the beginning of an e-learning course can somewhat predict the adaptability of the course at the end.

Describing incomplete sequential information is of growing importance in Knowledge Representation in Artificial Intelligence and Computer Science. To obtain logical foundations for representing incomplete sequential information, a new logic, called sequence-indexed constructive propositional logic (SLJ), is introduced as a Gentzen-type sequent calculus by extending Gentzen’s LJ for intuitionistic logic. The system LJ is known as useful for representing incomplete information, and SLJ is obtained from LJ by adding a sequence modal operator which can represent sequential information. The cut-elimination and decidability theorems for SLJ are proved. A sequence-indexed Kripke semantics is introduced for SLJ, and the completeness theorem with respect to this semantics is proved. A logic programming framework can be developed based on SLJ.

This paper presents a novel modification to an existing algorithm for spatial anomaly detection in binary labeled point data sets, using the Bernoulli version of the Spatial Scan Statistic. We identify a potential ambiguity in p-values produced by Monte Carlo testing, which (by the selection of the most conservative p-value) can lead to sub-optimal power. When such ambiguity occurs, the modification uses a very inexpensive secondary test to suggest a less conservative p-value. Using benchmark tests, we show that this appears to restore power to the expected level, whilst having similarly retest variance to the original. The modification also appears to produce a small but significant improvement in overall detection performance when multiple anomalies are present.

One of the challenges of applications of distributed database (DDB) systems is the possibility of expanding through the use of the Internet, so widespread nowadays. One of the most difficult problems in DDB systems deployment is distribution design. Additionally, existing models for optimizing the data distribution design have only aimed at optimizing query transmission and processing costs overlooking the delays incurred by query transmission and processing times, which is a major concern for Internet-based systems. In this paper a mathematical programming model is presented, which describes the behavior of a DDB with vertical fragmentation and permits to optimize its design taking into account the nonlinear nature of roundtrip response time (query transmission delay, query processing delay, and response transmission delay). This model was solved using two metaheuristics: the threshold accepting algorithm (a variant of simulated annealing) and tabu search, and comparative experiments were conducted with these algorithms in order to assess their effectiveness for solving this problem.

In this paper the linear ordering problem with cumulative costs is approached. The best known algorithm solution for the problem is the tabu search proposed by Duarte. In this work an experimental study was performed to evaluate the intensification and diversification balance between these phases. The results show that the heuristic construction phase has a major impact on the tabu search algorithm performance, which tends to diminish with large instances. Then to evaluate the diversification potential of the heuristic construction, two iterated local search algorithms were developed. Experimental evidence shows that the distribution of the heuristic construction proposed as diversification mechanism is more adequate for solving large instances. The diversification potential of the heuristic construction method was confirmed, because with this approach we found 26 best known solutions, not found by the tabu search algorithm.

Systems for Ambient Intelligence contexts are expected to exhibit an autonomous and intelligent behavior, by understanding and reacting to the activities that take place in such contexts. These activities, specially those labeled as trivial or simple tasks, are carried out in an effortless manner by most people. In contrast to what it might be expected, computers have struggled to deal with these activities, while easily performing some others, such as high profile calculations, that are hard for humans. Imagine a situation where, while holding an object, the holder walks to a contiguous room. We effortlessly infer that the object is changing its location along with its holder. However, such inferences are not well addressed by computers due to their lack of common-sense knowledge and reasoning capability. Providing systems with these capabilities implies collecting a great deal of knowledge about everyday life and implementing inference mechanisms to derive new information from it. The work proposed here advocates a common-sense approach as a solution to the shortage of current systems for Ambient Intelligence.

A query written in natural language (NL) may involve several linguistic problems that cause a query not being interpreted or translated correctly into SQL. One of these problems is implicit information or semantic ellipsis, which can be understood as the omission of important words in the wording of a query written in NL. An exhaustive survey on NLIDB works has revealed that most of these works has not systematically dealt with semantic ellipsis. In experiments conducted on commercial NLIDBs, very poor results have been obtained (7% to 16.9%) when dealing with query corpora that involve semantic ellipsis. In this paper we propose a dialogue manager (DM) for a NLIDB for solving semantic ellipsis problems. The operation of this DM is based on a typification of elliptical problems found in queries, which permits to systematically deal with this problem. Additionally, the typification has two important characteristics: domain independence, which permits the typification to be applied to queries of different databases, and generality, which means that it holds for different languages such as English, French, Italian, Spanish, etc. These characteristics are inherited to the dialogue processes implemented in the DM, since they are based on this typification. In experiments conducted with this DM and a NLIDB on a corpus of elliptical queries, an increase of correctly answered queries of 30-35% was attained.

The increasing interest in gesture recognition is inspired largely by creating a system which can identify specific human gestures and using gestures to convey information or control devices. In this paper we present a novel approach for recognizing hand gestures. The proposed approach is based on segmented singular value decomposition(

SegSVD

) and considers both local and global information regarding gesture data. In this approach, first singular vectors and singular values are evaluated together to define the similarity of two gestures. Experiments with hand gesture data prove that our approach can recognize gestures with high accuracy.

Our paper studies a formalization of reasoning in basic linear temporal logic

$\mathcal{BLTL}$

in terms of admissible inference rules. The paper contains necessary preliminary information and description of new evolved technique allowing by a sequence of mathematical lemmas to get our main result. Main result is found explicit basis for rules admissible in

$\mathcal{BLTL}$

(which, in particular, allows to compute admissible rules).

This work deals with the design and analysis of a nonlinear and neural adaptive control strategy for an anaerobic depollution bioprocess. A direct adaptive controller based on a radial basis function neural network used as on-line approximator to learn the time-varying characteristics of process parameters is developed and then is compared with a classical linearizing controller. The controller design is achieved by using an input-output feedback linearization technique. Numerical simulations, conducted in the case of a strongly nonlinear, time varying and not exactly known dynamical kinetics wastewater biodegradation process, are included to illustrate the behaviour and the performance of the presented controller.

Testing is a process detecting errors in the design of software and hardware. Tests can normally not prove the correctness of programs or hardware, since they usually form only a small subset of all possible inputs or situations. Therefore, test cases should be chosen carefully and should cover the set or space of possible inputs or situations as broadly as possible. Thus, test coverage is one of the crucial question in testing.

In this paper, we focus on conformance test for low level communication protocols like FlexRay or LIN as they are found very often in cars. These conformance tests are usually defined by choosing specific values for a larger number of variables. In this paper, we propose a method that can visualise the test cases in comparison to all possible situation and provides important information about the test coverage.

The report describes the means for dynamic control of the computation process that are available in Spider – a language for Control Network Programming.

The report describes the type of improved uninformed or heuristic search algorithms that are well-suited for non-procedural implementation in Control network programming, and how this can be achieved using the tools for dynamic computation control.

The semantic web dates back to 2001 and a number of tools, and representational forms are proposed and defined. However, the challenges of the semantic web are still largely unfulfilled, in the opinion of the authors. What is proposed here is a synthesis of ideas and techniques aimed a presenting the user with a much more structured search result that can expose the relationships contained within them. This does not increase semantic search, but can provide a much richer view for the user to apply human understanding though exposing the semantics represented by the structure within search results.

The traditional method of recommender systems suffers from the Sparsity problem whereby incomplete dataset results in poor recommendations. Another issue is the drifting preference, i.e. the change of the user’s preference with time. In this paper, we propose an algorithm that takes minimal inputs to do away with the Sparsity problem and takes the drift into consideration giving more priority to latest data. The streams of elements are decomposed into the corresponding attributes and are classified in a preferential list with tags as “Sporadic”, “New”, “Regular”, “Old” and “Past” – each category signifying a changing preference over the previous respectively. A repeated occurrence of attribute set of interest implies the user’s preference for such attribute(s). The proposed algorithm is based on drifting preference and has been tested with the Yahoo Webscope R4 dataset. Results have shown that our algorithm have shown significant improvements over the comparable “Sliding Window” algorithm.

The design and development of a spellchecker for highly inflected languages is commonly regarded as a challenging task. In this paper we present the architecture of Hascheck, a spellchecking system developed for Croatian language. We describe functional elements that make it an intelligent system and discuss specific issues related to Hascheck’s dictionary size as well as its guessing and learning capabilities.

In this paper, an adaptable light-weight access control scheme is proposed for an evolutionary computing environment. The existing access control environment relies on the server to solve security problems. The current environment has become almost distributed and ubiquitous. This change has spawned the need for light-weight access control by clients, which have a resource-limited environment. Existing studies using role-based prime number labeling (RPNL) are limited by the scalability of the prime number. The problem of scalability of the prime number was addressed with the use of the strong point of RPNL and implementation of persistent XML labeling and efficient query processing. The proposal has the advantage of having an adaptable access control scheme for an existing XML labeling method. We showed the efficiency of the proposed approach through experiments.

Within the framework of constraint reasoning we introduce a newer distributed particle swarm approach. The latter is a new multi-agent approach which addresses additive Constraint Satisfaction problems ((CSPs). It is inspired by the dynamic distributed double guided genetic algorithm (D

3

G

2

A) for Constraint reasoning. It consists of agents dynamically created and cooperating in order to solve problems. Each agent performs locally its own particle swarm optimization algorithm (PSO). This algorithm is slightly different from other PSO algorithms. As well, not only do the new approach parameters allow diversification but also permit escaping from local optima. Second,. Experimentations are held to show effectiveness of our approach.

Throughout Europe, environmental concerns are increasingly resulting in accelerated development of high-speed rail networks. The Pantograph-Catenary (PAC) power collection system has been retained for compatibility reasons, but the normally-reliable passive system can suffer increasing failure of contact at elevated speeds due to wave motion of the catenary. The results include loss of power and premature component failure due to formation of electric arcs.

The paper discusses simulation of a fuzzy logic based active PAC control system using the MATLAB-Simulink suite of software. A flexible control system model is developed and initial test simulations are described. Future refinements are proposed for improved system modelling and control.

This work is funded under an Interreg IV project, “PAntograph Catenary Interaction Framework for Intelligent Control (PACIFIC)”.

In modern buildings, the position(s) of elevator system(s) affects strongly the efficiency of people circulation especially during periods of peak demand. The present study introduces a simple model that correlates circulation data (building type, population size and density, space use, etc.) with structural/architectural data (net usable space, circulation space, structural intrusions, facilities etc) of a typical floor of a building. A circulation index is defined as function of these data and its value is calculated for every cell of the grid that partitions all usable spaces. Euclidean norms are used for calculating weighted mean distance values and for locating the point on floor’s surface that corresponds to minimal mean walking distance to/from the floor’s usable spaces. A heuristic search algorithm combines calculations of distance values, constraints and empirical knowledge for fine tuning hoistway position around this point. A case study of a typical building floor served by a single-elevator system exemplifies the proposed approach.

Designing a reconfigurable manufacturing robotic workcell is a complex and resource demanding procedure. In this work a multi criteria index is introduced, allowing the designer to evaluate the various anatomies achieved by a reconfigurable manipulator, and to define the area in the manipulator’s configuration space where a task can be accomplished with good performance under the selected performance measure. An adaptive neuro-fuzzy inference system is trained, in order to rapidly produce the index value for arbitrary anatomies achieved by the manipulator. The system is tested using a case study reconfigurable manipulator, and the derived results determined by the system after its training are presented and compared to the actual index value for calculated for the relevant anatomy.

In this paper we discuss Alpha Galois lattices (

Alpha lattices

for short) and the corresponding association rules. An alpha lattice is

coarser

than the related concept lattice and so contains fewer nodes, so fewer

closed patterns

, and a smaller basis of

association rules

. Coarseness depends on a

a priori

classification, i.e. a cover

${\mathcal C}$

of the powerset of the instance set

I

, and on a granularity parameter

α

. In this paper, we define and experiment a

Merge

operator that when applied to two Alpha lattices

$G({\mathcal C}_1,\alpha) $

and

$G({\mathcal C}_2,\alpha)$

generates the Alpha lattice

$G({\mathcal C}_1 \cup {\mathcal C}_2,\alpha)$

, so leading to a

class-incremental

construction of Alpha lattices. We then briefly discuss the implementation of the incremental process and describe the

min-max bases of association rules

extracted from Alpha lattices.

Wireless sensor networks (WSN) have become an important research domain and have been deployed in many applications, e.g., military, ambient intelligence, medical, and industrial tasks. The location of wireless sensor nodes is a crucial aspect to understand the context of the measured values in industrial processes. Numerous existing technologies, e.g., based on radio frequency (RF), light, and acoustic waves, have been developed and adapted for requirements of localization in WSN. However, physical constraints of the application environment and each localization technology lead to different aptness. In particular, for liquid media in industrial containers, determining the location of every sensor nodes becomes very challenging. In this paper, a localization concept based on intelligent magnetic sensing system using triaxial anisotropic magnetoresistive (AMR) sensor with appropriate switched coils combined with a centralized localization algorithm based on iterative non-linear mapping (NLM) is presented. Here, our system is extended by low power and fast localization based on triangulation for feasible local position computation. The experimental results, both in the air as well as in liquid filled stainless steel container, delivered in the average an absolute localization error in the order of 6 cm for both NLM and triangulation. In future work, we will scale our approach to industrial container size required for beer brewing industry and increase the accuracy and speed by timely electronics and calibration.

This paper presents a milling machine tool cutting process monitoring system based upon microcontroller architecture. The work was undertaken to explore the degree of autonomous intelligent decision making that such an approach can support. It is based upon the embedding of a number of linked algorithms within a microcontroller architecture. The practical implementation and results of the dynamic digital filtering algorithms thus employed are presented and consideration is given to how their outputs can be combined to provide high level process monitoring functions. The same technique can be used for monitoring applications for processes that depend upon health monitoring functions requiring simultaneous multiple parameter analysis.

Alarm systems provide an interface between operators and the machinery in a chemical plant because they allow abnormalities or faults caused by operators to be detected at an early stage. Alarms should be used to enable operators to diagnose faults and plan countermeasures, and nuisance alarms should be eliminated. We propose the use of a selection algorithm of sets of pairs of alarm variables and their signs. The signs mean the upper or lower limits of the alarm variables. The selected sets of pairs are theoretically guaranteed to be able to qualitatively distinguish all assumed faults. We propose using a two-layer cause-effect model for the algorithm, which represents the cause and effect relationship between state variables based on the topology of a plant. This model is applied to a simple process. The simulation results illustrate the usefulness of our method.

A model-based method is proposed in this paper for algorithmic generation of diagnosers in coloured Petri net (CPN) form from characteristic input-output traces obtained from a qualitative model of lumped process systems. The qualitative model contains the description of the considered persistent faults in the form of fault indicators, and it is transformed into a CPN. The diagnosers are constructed from a CPN obtained by the process mining methodology using the generated input-output traces for identically constant inputs. The concepts and methods are illustrated using a simple case study consisting of an industrial storage tank system with additive and multiplicative failures on sensors, and on the behaviour of a pump.

Today’s enterprises have complex manufacturing processes with several automation systems. These systems generate enormous amount of data in real-time representing feedbacks, positions, and alerts, among others. This data can be stored in relational databases as historical data which can be used for product tracking and genealogy, and so forth. However, historical data is not been utilized to proactively control the manufacturing processes. The current contribution proposes a novel methodology to overcome the aforementioned drawback. The methodology encompasses three process steps. First, offline identification of critical control-related parameters of manufacturing processes and defining a case base utilizing previously identified process parameters. Second, update the case base with real-time data acquired from automation systems during execution of manufacturing processes. Finally, employ similarity search algorithms to retrieve similar cases from the case base and adapt the retrieved cases to control the manufacturing processes proactively. The proposed methodology is validated to proactively control the manufacturing process of a molding machine.

Pinch technology is a familiar energy-saving technology in the chemical industries and has been incorporated in the process simulation software, however the skilled engineers’ considerations are required to make preferable heat exchanger networks (HEN). We introduced a multiagent oriented simulation framework into the HEN design to save the energy usage and also reduce the CO

2

emissions. In our framework, a number of “HEN design agents” have their own strategies to optimize HEN respectively. In this paper, we show the effectiveness of our framework applying to two chemical processes.

Human operators in abnormal situations must plan adequate countermeasures against abnormal corrections in chemical plants. Operators in these situations switch some of controllers from automatic to manual and manipulate one variable while observing another during each countermeasure and/or change the set values for the throughput controller when some manipulated variables have become saturated. However, a flow rate controller may not work for a throughput controller in abnormal situations. Therefore, the efficiency of countermeasures needs to be checked by systems that support operators. Hamaguchi et al. proposed a method of configuring a multi-loop controller using CE-matrices for a system that planned countermeasures. We propose a method of checking the consistency with which inventory is controlled so that adequate countermeasures can be planned.

In order to reduce risks associated with Liquefied Natural Gas (LNG) production facilities, one approach is to provide real time and risk-based accident forecasting mechanisms and tools that will enable the early understanding of process deviations and link with possible accident scenarios. In this paper, process and fault modeling technique is presented to model causation models and link with accident scenarios using fault semantic networks (FSN). A forecasting algorithm is developed to identify and estimate safety measures for each operation step and process model element and validated with process condition.

In this paper, we propose the fuzzy group decision making to tackle the rate of aggregative risk in software development. The proposed method is easily implemented and also suitable for only one evaluator.

Conventional power system optimization problems deal with the power demand and spinning reserve through real values. In this research, we employ fuzzy variables to better characterize these values in uncertain environment. In building the fuzzy power system reliable model, fuzzy Value-at-Risk (VaR) can evaluate the greatest value under given confidence level and is a new technique to measure the constraints and system reliability. The proposed model is a complex nonlinear optimization problem which cannot be solved by simplex algorithm. In this paper, particle swarm optimization (PSO) is used to find optimal solution. The original PSO algorithm is improved to straighten out local convergence problem. Finally, the proposed model and algorithm are exemplified by one numerical example.

Video tracking can be defined as an action which can estimate the trajectory of an object in the image plane as it moves within a scene. A tracker assigns consistent labels to the tracked objects in different frames of a video. The objective of this paper is to provide information on the present state of the art and to discuss future trends in the use of multi-camera tracking systems. In the literature, three main types of multi-camera tracking system have been outlined. The first type relies on challenges in the camera tracking system. The second concerns the methodology of tracking systems in general. The third type relies on current trends in camera tracking systems. We provide an overview of the current research status by summarizing promising avenues for further research.

In this paper, an intelligent predictor model for forecasting the behaviour of buyers in the product they would be interested to purchase using best customers and biggest customer index as inputs to the predictor. The model is based on fuzzy logic and Ordinal Structure Fuzzy Logic (OSFL). These intelligent models are developed based on the market survey data of the U.S. Bureau of Labour Statistics (BLS) data. The market survey data are sets of consumers categorized in various demographics their spending on the products. The association factors among the products and the consumer’s spending habits are determined using indexes as proposed by New Strategist in order to develop the Fuzzy predictor model. A software is developed to simulate he predictor based on the demographics. The software outputs a list of products based on probability priorities. The result of simulations of the software is compared with the BLA data and found to be quite accurate.

Kansei means human feelings in Japanese. Many studies on the analysis or evaluation of Kansei have been conducted. However Kansei is very complicated and it is not easy to analyze or evaluate. When we consider how we feel about color, it is necessary to take various things into consideration. For example, it must be very important to consider that our preference of colors might vary with objects. Here we take the interior (curtain, wall, floor) and the tableware (plate, cup, pan) and examine how human preference varies with objects using method of order.

In this paper, genetic algorithm (GA) and neural network (NN) are integrated to produce a hybrid intelligent algorithm for solving the bilevel programming models. GA is used to select a set of potential combination from the entire generated combination. Then a meta-controlled Boltzmann machine which is formulated by comprising a Hopfield network and a Boltzmann machine (BM) is used to effectively and efficiently determine the optimal solution. The proposed method is used to solve the examples of bilevel programming for two- level investment in a new facility. The upper layer will decide the optimal company investment. The lower layer is used to decide the optimal department investment. Typical application examples are provided to illustrate the effectiveness and practicability of the hybrid intelligent algorithm.

In a Product Life Cycle (PLC) scenario, different Virtual Engineering Applications (VEA) are used in order to design, calculate and, in general, to provide an application scenario for computation engineering. The diverse VEA are not necessarily available when information sharing is needed, a fact that represents a semantic loss as the knowledge gained by using one VEA can be lost if a data translation occurs (e.g. a Finite Element program is normally able to export only the geometry). In this paper we present an architecture and a system implementation based on semantic technologies which allows a seamless information and knowledge sharing between VEA in a PLC scenario. Our approach is validated through a Plant Layout Design application which is able to collect knowledge provided by different VEA available. This work presents our system leaving a statistical analysis for future work, as at the moment our system is being tested.

The paper deals with the problem of guaranteeing high Quality of Service (QoS) in e-commerce Web servers. We focus on the problem of request admission control and scheduling in a Business-to-Consumer (B2C) Web server from the profit perspective of the owner of an e-business company. We propose extending a Web server system with the ability to identify and favour key customers of a Web store and to ensure the possibility of successful interaction for all customers finalizing their purchase transactions. We propose applying a

Recency-Frequency-Monetary

analysis (RFM) to discover key customer knowledge and using the resulting RFM scores in a novel QoS mechanism. We discuss the mechanism and some simulation results of its performance.

The aim of this paper is to present the conceptual structure of basic fuzzy model representing the Polish Internet mortgage market. The paper starts with an introduction describing the market complexities and challenges, and description of previously created rule based model. Then the steps of the process of proposed model fuzzyfication are presented. Final part of the paper consists of conclusions and directions for future research.

The gain of the paper is to introduce and to discuss a formal specification of computer system’s Service Level Agreement (SLA) and its translation into structure of complex services (composed of atomic services) delivering required functionalities and non-functionalities in distributed environment. The SLA is composed of two parts specifying quantitative and qualitative requirements. The former requirements define structure of the adequate complex services as a directed graph, where potential parallelism of atomic services performance may be taken into account. The qualitative requirements are applied to select the optimal complex service realization scenario; it is based on assumption that various atomic services distinguished in the complex services structure are available in the environment in different versions and locations. Different versions of atomic services are delivering the required functionalities and satisfy non-functionalities at various levels. Various locations of atomic services means that the time and cost of atomic services delivery (communication and calculation) may vary. Proposed model of SLA translation into complex services causes that a scenario variants may be applied — among others — to calculate upper and lower complex services’ delivering times and to estimate validity of possible parallelism in complex services.

The ontology engineering encompasses both, artificial intelligence methods and software engineering discipline. The paper tries to address a selection of aspects pertaining to development activities such as choice of the environmental framework, functionality description, specification methods and roles definition. Authors refer to the ontology development projects they were involved in.

The natural development of information technology area stimulates intense growth of various technologies which support basic organization processes. The range of technologies implies appropriate management thereof, as well as accurate correspondence with conducted activities. Abandonment of activities within individual branches in favour of project approach to performed assignments (especially those connected with software development) has recently become a popular subject of management. This approach involves a variety of technologies which support project tasks. Yet the question arises, how to harmonize proper technologies with project management in an effective way. Agent system that is built by authors is a kind of solution to this problem. That system is a kind of tool which serves to help project managers with the choice of a proper method and technology of project management. One of most important decision taken before project start is method and tools selection. When method is not fitted to project team it can provide to project’s failure. Also many times client’s knowledge about IT project area can be important for getting success.

Virtual Organizations (VOs) promote dynamic interaction between individuals, groups and organizations, who share their capabilities and resources to pursue a common goal and maximize their benefits. Among these resources, knowledge is a critical one that requires special attention in order to support problem-solving activities, decision making processes and provide strategic advantage. In this paper, we present an initial proposal for the creation of dynamic knowledge-based VOs inside the E-Decisional Community, an integrated knowledge sharing platform that aims at the creation of markets where knowledge is provided as a service. This approach will provide technological support for discovering, re-using evolving and sharing experiential knowledge represented by means of the Set of Experience Knowledge Structure (SOEKS) and Decisional DNA among several entities.

As a domain-independent, flexible and standard knowledge representation structure, Decisional DNA allows its domains to acquire and store experiential knowledge and formal decision events in an explicit way. In this paper, we explore an approach that integrates Decisional DNA with robots in order to test the usability and availability of this novel knowledge representation structure. Core issues in using this Decisional DNA-based method include capturing of knowledge, storage and indexing of knowledge, organization of the knowledge base memory, and retrieval of knowledge from memory according to current problems. We demonstrate our approach in a set of experiments, in which the robots capture knowledge from their tasks and are able to reuse such knowledge in following tests.

This paper is a summary of the authors’ work on a model of support for decision processes in organisation management. Key decisions in organisations are often made without sufficient knowledge and by people lacking the proper qualifications and experience. Without full support in decision processes, true threats to organisations are created. Therefore, to support decision processes in numerous organisations, apart from experts in their field, knowledge-based systems (expert) are applied. Those designed to support decision processes in technical systems are well described and applied. Those devoted to managers acting in sociotechnical systems are more complex and generally difficult to describe. An example of such a system for the needs of an IT organisation has been presented in this paper. The authors identify possible problems of an IT organisation and introduce a decision system supplemented with applicable elements in technical and sociotechnical systems.

Nowadays, the technology usage is a massive practice where internet and digital documents are considered as powerful tools in both professional and personal domains. Although, as useful as they can be in a proper way, wrong practices can appear easily, where the

copy & paste

or plagiarism phenomenon is not far away from this. Documents’

copy & paste

is a world-wide growing practice, and Chile is not the exception. Therefore, all levels of educational fields, from elementary school to graduate students, are directly affected by this. Regarding to this concern, in Chile it’s been decided to tackle the plagiarism problem among students. For this, we apply Social Network Analysis to discover groups of people associated to each other by their documents’ similarity in a plagiarism detection context. Experiments were successfully performed in real reports of graduate students at University of Chile.

In order to have a successful VCoP two important tasks must be performed: on the one hand, it is always important that community provide useful information to every member by a good organization of contents and topics; on the other hand, to understand the behavior of members (i.e. which are the key members or experts, discover communities, etc). Social Network Analysis (SNA) is a powerful tool to understand the communities’ members, however, our theses is that state-of-the-art in SNA it is not sufficient to obtain useful knowledge from a VCoP. Moreover, we think that traditional SNA may lead to discover wrong results. We propose to combine traditional SNA with data mining techniques in order to produce results closer to reality and gather useful knowledge for VCoPs’ enhancement. In this work, we focused in discovering key members on a VCoP combining SNA with concept-based text mining.We successfully tested our approach on a real VCoP with more than 2500 members and we validate our results asking the community administrators.

Organizations develop a growth strategy of their informational platform based on certain key drivers. This determines business plans and their future informational and analytical capacity. However, each solution has a different deployment depending upon the selected architecture and the management model. In the specific case of Business Intelligence (BI) infrastructures, this should be decided according to the speed of the decision making processes, which is usually executing on real time. Therefore, it determines the flexibility rate at which the business can grow. Businesses grow but the key drivers can remain the same. This paper analyzes the elements required for an optimal deployment of business architecture.

In this article, behavior of a heuristic search with a heuristic function divided into two parts is discussed based on a geometric analysis, and a method for improving the heuristic function is proposed. One part of the divided heuristic function is called short-term forecast. Another part is called long-term forecast. Based on the discussion, it is suggested there exists a possibility that the difference of accuracy of both forecasts leads the search to an incorrect path. Since there exists a possibility that the search becomes efficient and that the search does not select an incorrect path by improving accuracy of a long-term forecast, a method to update the value of a long-term forecast is proposed. It is shown that the proposed method is effective under the tree structure which cost of the edge observed at deep location is greater or equal than that observed at shallow location.

This paper proposes a web-based community environment called “e-running” that supports the development of self-management for runners. The objective of the support is to promote the physical skill development which stabilizes their heart-rate by adjustments of their pace while running. In this scenario, runners wear GPS (Global Positioning System) and HRM (Heart Rate Monitor) in training, and after that, refer to the pace-simulation with avatars based on GPS data on the online community in order to remember their improvements toward the next training. In this simulation, runners are given a map-based annotation along with such improvement sections. Concretely speaking, an agent function provide opportunity to reflect upon the management of their pace and help the comprehension about the relationship between their heart-rate and their pace. It also covers a variety of landscape on the course as the environmental elements that affect their pace. We report the idea and design.

The effects of background colors on the scores of a computer-based English test were analyzed. Eight combinations of black text and a background color were chosen to examine if test takers’ scores differed, depending on the characteristics of a background color. Two hundred and forty six Japanese college students participated in the experiment. A computer-based test (CBT) that resembles the TOEIC® Test was used and the subjects, divided into eight groups, answered the same questions displayed on a background of eight different colors. The results showed that the subjects who took the test with light blue and blue background scored the highest and the second highest. Although many CBTs use the combination of a white background and black text, this combination was ranked the second worst. The results indicate that colors with higher values both in luminance and in brightness can cause lower performance, and test taker’s color preference does not affect his performance.

In a message ferry technology for sparse ad hoc networks, a ferry node stores a message from a source node and carries it to the destination node. In this technology, message ferry route design is one of the most important technical issues. To improve the performance, we propose a cluster-based route design where the ferry moves along the path formed by the centers of the clusters.

Moving objects and oncoming pedestrians sometimes become obstacles for a pedestrian either on a crosswalk or in the pavement at night. Low vision persons and aged people with low eye sight sometimes dodge against the other pedestrians or danger. A dynamic object should suggest a person its affordance for the safe and pleasant mobility as static object like a chair affords. We propose an affordance of dynamic object based on instinct and an affordance indicator system for safe mobility based on face recognition. The results of examination of the indicator both in a passage and on the stairs are also discussed.