Search

The objective of this project is twofold. Firstly, researchers wants to identify between multiple financial and shipping related measures, the features that have statistically significant impact on the estimation of the spot voyage time charter price of P1A Panamax shipping route which is daily issued from the London-based Baltic Exchange. Secondly, significant objective of this thesis is to examine the predictive ability of multiple multivariant feature models (based on the results of the first objective) and of single variable time series models answering to the question “What is the estimated voyage time charter price of P1A shipping route for tomorrow?”.

The possibility to apply the intercriteria analysis over normalized data is discussed. An example, related to evaluation of six arithmetic functions, is given.

Pain is the most common symptom of the many musculoskeletal pathologies. Musculoskeletal pain affects the muscles, ligaments, tendons, nerves and bones and might be caused by diverse factors. Musculoskeletal pain ranges from mild to severe. It can be local or diffuse, and acute or chronic. Due to the wide range of conditions that may cause such a symptom, diagnosing process is challenging and a systematic approach is necessary. In this investigation we present a successful example of generalized nets application in medical diagnosing and propose a novel approach leading to the appropriate diagnostic considerations. The method proposed in this investigation accurately identifies the various steps during the muscle pain diagnosing process and significantly improves the health care level. Obtained so far results could be used to assist in the decision making in the diagnostic processes.

The possibility to apply the intercriteria analysis over normalized data is discussed. An example, related to evaluation of crude oil data, is given.

The need for explicit time representation in workflow environments has been recently identified. Although the concept of time is an intrinsic part of a workflow application, time management has been treated as an issue of ordering the constructs of the workflow specification. This traditional approach aids mainly in the monitoring of activity deadlines. There is limited support for modelling and representation of time constraints associated with the processes and their activities or cases. This paper presents a temporal formalism for representing indeterminacy to workflow specifications. We further argue that integrating workflows with temporal databases can further enhance the workflow specification. Finally we utilise agents as part of a temporal workflow environment. Particular attention is paid in the allocation of agents to workflow activities with reference to the properties of conflict resolution and moving hierarchies.

Query answering requirements for a knowledge-based treatment of user requests led us to introduce the concept of closure of an intuitionistic fuzzy set over a universe that has a hierarchical structure. We recommend the automatic analysis of queries according to concepts defined as part of knowledge-based hierarchies to guide the query answering as part of an integrated database environment with the aid of hierarchical intuitionistic fuzzy sets (H-IFS). In this paper based on the notion of H-IFS, we propose an ad hoc utility build on top of Oracle10g that allows us to enhance the query capabilities of by providing better, knowledgeable, and optimized answers to user's requests. © 2010 Wiley Periodicals, Inc. © 2011 Wiley Periodicals, Inc.

Purpose – Data preparation plays an important role in data mining as most real life data sets contained missing data. This paper aims to investigate different treatment methods for missing data. Design/methodology/approach – This paper introduces, analyses and compares well‐established treatment methods for missing data and proposes new methods based on naive Bayesian classifier. These methods have been implemented and compared using a real life geriatric hospital dataset. Findings – In the case where a large proportion of the data is missing and many attributes have missing data, treatment methods based on naive Bayesian classifier perform very well. Originality/value – This paper proposes an effective missing data treatment method and offers a viable approach to predict inpatient length of stay from a data set with many missing values.

A theory of the Generalized nets was used to construct a generalized net model which describes the possibility to evaluate the time of the occurrence or completion of the events. Twenty predicates for checking the validity of the special circumstances, related to time-moments of two events were introduced. The model can be used to analyze the specific moments in which the facts have happened. In result we can answer questions such as: “Is the fact valid?” “How many facts it contradicts”, “How many facts it confirms?”

Sensorial analysis based on the utilisation of human senses, is one of the most important investigation methods in food and chemical analysis. Recently, the use of smell in clinical diagnosis has been rediscovered due to major advances in odour sensing technology and artificial intelligence. An array of gas sensors has been employed to identify in vivo urine samples from patients with suspected uncomplicated UTI who were scheduled for microbiological analysis in a UK Health Laboratory environment. An intelligent model consisting of an odour generation mechanism, rapid volatile delivery and recovery system, and a classifier system based on intelligent techniques has been developed. The implementation of an advanced neural network scheme and the concept of fusion of multiple classifiers dedicated to specific feature parameters have been adopted in this study. The experimental results confirm the validity of the presented methods. This study has shown the potential for early detection of microbial contaminants in urine samples using electronic nose technology.

In the present paper is constructed a Generalized net model of a process of sequential pattern mining by a generalized sequential pattern algorithm. Sequence pattern mining is a technique used for predictive data mining. It is used for discovering of frequent sequences in the databases. A sequence is regarded as frequent when it occurs in the data above a previously user defined minimum support within the applied time constraints. The analysis is an extension of frequent pattern mining technique that extracts frequent itemsets. They can be used for the creation of association rules. GSP algorithm was realized with metrological observations from weather databases, infrared camera and smoke detector to determine the possibility of forest fire. The proposed Generated net model can be used to monitor the sequence pattern mining process depending on meteorological parameters.

The internet is undoubtedly the biggest data source ever with tons of data from different sources following different formats. One of the main challenges in computer science is how to make data sharing and exchange between these sources possible; or in other words, how to develop a system that can deal with all these differences in data representation and extract useful knowledge from there. And since XML is the de facto standard for representing data on the internet, XML query matching has gained so much popularity recently. In this paper we present new types of fuzzy arc matching that can match a pattern arc to a schema arc as long as the correspondent parent and child nodes are there and have reachability between them. Experimental results shown that the proposed approach provided better results than previous works.

XML is undoubtedly becoming the predominant de facto standard for data representation and communication, especially on the web, which in turn is causing XML data repositories to grow rapidly. Current XML Query languages, such as Xquery, have limited capabilities in querying multiple data sources with different structures (schemas) which is inefficient. Therefore, an urgent need has been identified for XML querying techniques that can overcome the rising diversity in XML data schemas. In this work, we propose our approach of using Intuitionistic Fuzzy Trees (IFTr) to achieve approximate XML query matching by considering a novel approach of matching arcs as basic units of data schemas. Additionally, we provide an algorithm for rewriting the original query to be able to retrieve data from local data sources. Our approach was tested using synthetic data sources with high degree of structural diversity, and it proved useful result while pertaining good performance and low memory usage.

In the paper we describe a generalized net GACOA realizing an arbitrary algorithms for ant colony optimization. In this sense, this net is universal for all standard algorithms for ant colony optimization, since it describes the way of functioning and results of their work. Then, we discuss the way of constructing a GN that includes the GACOA as a subnet. In this way, we ensure the generalized net tokens' optimal transfer with regard to the results of GACOA . Thus, we construct a generalized net, featuring an optimization component and thus optimally functioning.

As XML is becoming the de facto standard for data representation and communication, especially on the web, a need has been identified for efficient XML querying techniques that can overcome the dilemma of heterogeneity in XML data sources. In this work, we propose our approach of using Intuitionistic Fuzzy Trees (IFTr) to achieve approximate XML query matching, making the query results include not just the XML data trees that exactly match the query, but also the ones that partially match it. We believe that our approach has a potential to return useful query answers while pertaining good performance.

Primary Care Prescribing is one of the most complex established NHS therapeutic processes. A wide array of drugs is prescribed on a regular and irregular basis to a large cohort of the population. The prescribing budget funds the costs of drugs prescribed in primary care. Typically a primary care trust overspends its prescribing budgets on drugs with dynamic prescribing patterns and pricing. Furthermore, prescribing patterns are an accurate indicator of the quality of healthcare provided in primary care. In this paper a data warehousing approach is proposed that allows integrating prescribing data from different GP practices, equipped with an adhoc OLAP utility that allows measurement of the local prescribing activity within available resources.

As the popularity of XML as a de facto standard for data representation and communication is rising, a need has been identified for efficient XML querying techniques that can overcome the dilemma of diversity in the structure of XML data sources. In this work, we propose our approach of using Intuitionistic Fuzzy Trees (IFTr) to achieve approximate XML query matching, making the query result include not just the XML data trees that exactly match the query, but also the ones that partially match it. Our approach has a potential to return useful query answers while pertaining good performance. Users will have the option to choose between quick and less accurate results or time costing and more accurate results.

Data Warehouse (DWH) Models are based on static dimensions having single hierarchies. With the evolution of World Wide Web, including external knowledge can enrich those models and provide better results of data analysis. Therefore, it would be useful to have intelligent transformation utilities that can mine various data structures and extract useful knowledge participating in the construction of flexible DWH models. This paper proposes a new approach towards intelligent transformation utilities that will allow the utilisation of multiple hierarchical schemata when defining the dimensions of data-warehouses. By allowing a particular dimension to have multiple but semantically close definitions, we allow same users to query same data with the aid of different semantics. To put it differently users are allowed to change or refine the axis of analysis with respect to a particular query, in their effort to achieve a more meaningful answer. We make use of Intuitionistic Fuzzy Logic to soften the rules of calculating the similarity between different hierarchies which in turn is used to decide if the hierarchies can be included in the definition of data warehouse dimension. Data transformations are used to transform the data from one hierarchy to another. With the aid of external data, some sort of estimation is used to estimate values of new hierarchy levels and then based on the user's request the desired hierarchy is used to view an OLAP cube.

OLAP query answering requirements for a knowledge based treatment of user requests led us to introduce the concept of hierarchical preferences over a universe that has a hierarchical structure. We introduce the automatic analysis of queries according to concepts defined as part of knowledge based hierarchy in order to guide the query answering as part of a data-warehouse environment with the aid of hierarchical Intuitionistic fuzzy sets, H-IFS. Based on the notion of H-IFS we propose an ad-hoc utility build on top of current OLAP tools like Oracle10g that allows us to enhance the query capabilities of by providing better and knowledgeable answers to user’s requests. The theoretical aspects as well the practical issues and achieved results are presented throughout the rest of the paper.

Query answering requirements for a knowledge based treatment of user requests led us to introduce the concept of closure of an Intuitionistic fuzzy set over a universe that has a hierarchical structure. We introduce the automatic analysis of queries according to concepts defined as part of a knowledge based hierarchy in order to guide the query answering as part of an integrated database environment with the aid of hierarchical Intuitionistic fuzzy sets, H-IFS. In this paper based on the notion of H-IFS we propose an ad-hoc utility build on top of Oracle10g that allows us to enhance the query capabilities of by providing better and knowledgeable answers to userpsilas requests. The theoretical aspects as well the practical issues and achieved results are presented throughout the rest of the paper.

In this paper we revise the context of ldquovalue imprecisionrdquo, as part of an knowledge-based environment. We present our approach for including value imprecision as part of a non-rigid hierarchical structures of organization. This led us to introduce the concept of closure of an intuitionistic fuzzy set over a universe that has a hierarchical structure. Intuitively, in the closure of this intuitionistic fuzzy set, the ldquokind ofrdquo relation is taken into account by propagating the degree associated with an element to its sub-elements in the hierarchy. We introduce the automatic analysis according to concepts defined as part of a knowledge hierarchy in order to guide the query answering as part of an integrated database environment with the aid of hierarchical intuitionistic fuzzy sets.

An Integrated Data Management System is required for representing and managing indicative information from multiple sources describing the state of an enterprise. In such environments, information may be partially known because the related information from the real world corresponds to a set of possible values including the unknown. Here, we present a way to replace unknown values using background knowledge of data that is often available arising from a concept hierarchy, as integrity constraints, from database integration, or from knowledge possessed by domain experts. We present and examine the case of H-IFS to represent support contained in subsets of the domain as a candidate for replacing unknown values mostly referred in the literature as NULL values.

Multi-phase models of patient flow offer a practical but scientifically robust approach to the studying and understanding of the different streams of patients cared for by health care units. In this chapter, we put forward a decision support system that is specifically designed to identify the different streams of patient flow and to investigate the effects of the interaction between them by using readily available administrative data. The richness of the data dictate the use of data warehousing and On-Line Analytical Processing (OLAP) for data analysis and pre-processing; the complex and stochastic nature of health care systems suggested the use of discrete event simulation as the decision model. We demonstrate the application of the decision support system by reporting on a case study based on data of patients over 65 with a stroke related illness discharged by English hospitals over a year.

Traditional data repositories are typically focused on the storage and querying of crisp-precise domains of data. As a result, current commercial data repositories have no facilities for either storing or querying imprecise-approximate data. However, when considering scientific data (i.e. medical data, sensor data etc) value uncertainty is inherited to scientific measurements. In this paper we revise the context of “value uncertainty”, and examine common models related to value uncertainty as part of the OLAP model. We present our approach for extending the OLAP model to include treatment of value uncertainty as part of a multidimensional model inhabited by flexible date and non-rigid hierarchical structures of organisation.

In the Bulgarian health care system patients are transferred between different health care units within the health care facility, and occasionally between units that are far apart, depending on the stage of the patient's treatment progress. Determining patient resource consumption prior to utilization is vital for the management and planning of health care resources. In this paper we propose a generalized net model of patient flows that can be used to evaluate the current design (or alternative designs) in order to improve the management of the diagnostic consultative centres.

In this paper we revise the context of "value uncertainty", as part of an OLAP based environment. A new multidimensional-cubic model named as the if-cube is introduced which is able to operate over data with imprecision either in the facts or in the dimensional hierarchies. These query requirements led us to introduce the concept of closure of an intuitionistic fuzzy set over a universe that has a hierarchical structure, H-IFS. We introduce the automatic recommendation of analysis according to the concepts defined as part of a domain ontology in order to guide the decision making with the aid of H-IFS.

In recent years, the providers of public and private sector health care services have been faced with some radical changes in the society they serve, and more importantly, development in the way that traditional health care is delivered to Information Technology (I.T) based communities. It is widely believed by health care professionals that the better health care results really come from the improved healthcare systems and more effective health care services' management. This paper focuses on using an agnet-based software engineering approach and design models to the development of an appropriate agent-based healthcare software system is described in which software researchers collaborate with environment builders to enhance the levels of cooperation and support provided within an integrated agent-based community healthcare system.

On-Line Analytical Processing (OLAP) tools use multidimensional views to provide quick access to information. They have become the de facto standard in the business world for analytical databases. In health care, care givers and managers could benefit from being able to perform interactive data exploration, ad-hoc analysis and possibly discover hidden trends and patterns in health data. However, health data have unique characteristics that distinguish them from common business examples, an aspect that makes the direct adaptation of the already established business oriented solutions difficult. In this paper we report the development of an OLAP system for analyzing hospital discharge data and for modeling hospital length of stay.

This paper presents a model for prediction of football league matches. We use intuitionistic fuzzy SQL (IFSQL) and intuitionistic fuzzy relational databases (IFRDB) to store and manage data about football matches and predictions. We take advantage of intuitionistic fuzzy sets by relating the degree of indefiniteness to an uncertainty about the estimation for a team’s capabilities. The uncertainty is produced by insufficient statistical data.

There is increasing worldwide awareness that bionics and artificial intelligence will play an important role in microbial analysis. An intelligent data-warehouse system consisting of an odour generation mechanism, rapid volatile delivery and recovery system, and a classifier system based on neural networks and genetic algorithms have been applied as part of a microbial analysis. The microbiological warehouse environment has, also adopted the concept of fusion of multiple classifiers dedicated to specific feature parameters. The experimental results confirm the soundness of the presented methods.

The paper presents MDDQL as a query language suitable for multi-lingual conceptual querying of collections of databases from a graphical user interface or from an application programming one. The query language, however, has been specified and implemented with the parametric theory of linguistic diversity in mind such that syntactic and semantic parsing of multi-lingual query expressions becomes quite simple and guarantees identical query results regardless the preferred natural language. We present a parsing algorithm, which shows that it is quite easy to formulate a query regardless the underlying type order of a natural language, be it Subject-Object-Verb, Subject-Verb-Object, or Object-Verb-Subject, etc., and still being able to grasp the meaning of the query at a minimal computational effort possible.

It is well accepted that many real-life datasets are full of missing data. In this paper we introduce, analyze and compare several well known treatment methods for missing data handling and propose new methods based on Naive Bayesian classifier to estimate and replace missing data. We conduct extensive experiments on datasets from UCI to compare these methods. Finally we apply these models to a geriatric hospital dataset in order to assess their effectiveness on a real-life dataset.

This work presents a framework for Web mining, which is developed to support and assist existing data mining algorithms in order to preliminarily refine browsing pattern with relevant constraints. Intuitionistic fuzzy sets are used to represent the possibility that backward steps are used while searching for the pages of interest.

With the rapid growing number of WWW users, hidden information becomes ever increasingly valuable. As a consequence of this phenomenon, mining Web data and analysing on-line users' behaviour and their on-line traversal pattern have emerged as a new area of research. Primarily based on the Web servers' log files, the main objective of traversal pattern mining is to discover the frequent patterns in users' browsing paths and behaviors. This paper presents a complete framework for Web mining, allowing users to pre-define physical constraints when analysing complex traversal patterns in order to improve the efficiency of algorithms and offer flexibility in producing the results.

In this paper we informally and formally defined what we mean by uncertain- ignorant information in relational databases and data warehouses. We classify proposed extensions to the relational data model that can represent and retrieve incomplete information. There are many different kinds of temporal ignorant information including information that is fuzzy, imprecise, indeterminate, indefinite, missing, partial, possible, probabilistic, unknown, uncertain, or vague. We will explore each variety of temporal ignorant information in detail with reference to database and data-warehouse design.

This paper is an attempt to provide an XML based framework for modelling and representing multi-source electronic patient records (EPR) as part of an integrated single source environment. The main focus of this framework is to capture the dynamic features of EPR data sources for further analysis and knowledge discovery with the aid of OLAP and data mining.

As the rapid growing number of WWW users, the hidden information becomes ever increasingly valuable. As the consequence of such phenomenon, mining Web data and analysing on-line users' behaviour and their on-line traversal pattern have emerged into a new popular research area. Primarily based on the Web servers' log files, the main objective of traversal pattern mining is to discover the frequent patterns in users' browsing paths and behaviours. This paper presents a complete framework for web mining, allows users to predefine physical constraints when analysing complex traversal patterns in order to improve the efficiency of algorithms and offer flexibility in producing the results.

Recently, the use of smell in clinical diagnosis has been rediscovered due to major advances in odour sensing technology and artificial intelligence. It was well known in the past that a number of infectious or metabolic diseases could liberate specific odours characteristic of the disease stage and among others, urine volatile compounds have been identified as possible diagnostic markers. A newly developed electronic nose based on chemoresistive sensors has been employed to identify in vitro 13 bacterial clinical isolates, collected from patients diagnosed with urinary tract infections, gastrointestinal and respiratory infections, and in vivo urine samples from patients with suspected uncomplicated UTI who were scheduled for microbiological analysis in a UK Health Laboratory environment. An intelligent model consisting of an odour generation mechanism, rapid volatile delivery and recovery system, and a classifier system based on a neural networks, genetic algorithms, and multivariate techniques such as principal components analysis and discriminant function analysis-cross validation. The experimental results confirm the validity of the presented methods.

The need for explicit time representation in workflow environments has been recently identified. Although the concept of time is an intrinsic part of a workflow application, time management has been treated as an issue of ordering the constructs of the workflow specification. This traditional approach aids mainly in the monitoring of activity deadlines. There is limited support for modelling and representation of time constraints associated with the processes and their activities or cases. This paper presents a temporal formalism for representing indeterminacy to workflow specifications. We further argue that integrating workflows with temporal databases can further enhance the workflow specification.

Recently, the use of smell in clinical diagnosis has been rediscovered due to major advances in odour sensing technology and artificial intelligence. It was well known that a number of infectious or metabolic diseases could liberate specific odours characteristic of the disease stage and among others, urine volatile compounds have been identified as possible diagnostic markers. A newly developed “artificial nose” based on chemoresistive sensors has been employed to identify in vivo urine samples from 45 patients with suspected uncomplicated UTI who were scheduled for microbiological analysis in a UK Public Health Laboratory environment. An intelligent model consisting of an odour generation mechanism, rapid volatile delivery and recovery system, and a classifier system based on a hybrid system of genetic algorithms, neural networks and multivariate techniques such as principal components analysis and discriminant function analysis-cross validation. The experimental results confirm the validity of the presented method.

The paper presents a way of integrating conflicting temporal information from multiple information providers considering a property-based resolution. The properties considered in the paper are time and uncertainty because of conflicting information providers. The property based resolution requires a flexible query mechanism, where answers are considered as bounds, taking into account the tendency of things to occur and also the might happen ability of things. Finally, some attention is paid to a database environment with non-static members.

The increasing need for applications to utilise a community of information providers in their effort to answer an information request has been a lasting problem of research. In requesting a community of information providers two types of incompatibility may occur, namely structural and semantic. The former may be caused by differences in the attribute domain, format, units, and granularity (intentional inconsistencies). The latter can be caused by attribute value conflict, since similar defined attributes utilise different levels of a conceptual hierarchy (tree, lattice) in defining themselves (extensional inconsistencies).

Workflows are activities involving the coordinated execution of multiple tasks performed by entities, in the enterprise environment. Workflow systems support the encoding and execution of workflows. A workflow management system is proposed, in which a considerable attention is paid on the utilisation of the services of a flexible database formalism. Flexible database formalisms must permit the modelling of trends, seasonality (periodicity), cyclic variations of trends and irregular activities (no predictable patterns) in the enterprise environment Furthermore, the formalism must permit the, expression of enterprise concepts founded in various conceptual levels. This paper will be restricted in workflow management system design, and activity scheduling, in a post relational environment whereas relational operators utilise paths (links between domains), in order to express interdependencies between activities.

An information system is used for representing and managing indicative information from multiple sources describing the state of an enterprise. Most information systems model enterprises that are crisp. A crisp enterprise is one that is highly quantifiable; relationships are fixed and attributes are atomic valued. The premises for this paper are precise enterprises, where data are imperfect and multiple conflicting sources of information do exist. In such cases, information can be imperfect and/or temporal, or any possible combination of each two of them. In domains where information is perfect, all information sources are absolutely reliable. In more speculative domains, like diagnosis, information may be asserted relatively to some time intervals in which it is possibly defined and probably believed. In such domains different sources of information may be assigned different degrees of reliability. Value imperfection and/or temporal indeterminacy may cause uncertainty. Temporal information may be recurring, periodical or definite.