Skip to main content
main-content

Über dieses Buch

The KES-IDT-2016 proceedings give an excellent insight into recent research, both theoretical and applied, in the field of intelligent decision making. The range of topics explored is wide, and covers methods of grouping, classification, prediction, decision support, modelling and many more in such areas as finance, linguistics, medicine, management and transportation.

This proceedings contain several sections devoted to specific topics, such as:

· Specialized Decision Techniques for Data Mining, Transportation and Project Management

· Pattern Recognition for Decision Making Systems

· New Advances of Soft Computing in Industrial and Management Engineering

· Recent Advances in Fuzzy Systems

· Intelligent Data Analysis and Applications

· Reasoning-based Intelligent Systems

· Intelligent Methods for Eye Movement Data Processing and Analysis

· Intelligent Decision Technologies for Water Resources Management

· Intelligent Decision Making for Uncertain Unstructured Big Data

· Decision Making Theory for Economics

· Interdisciplinary Approaches in Business Intelligence Research and Practice

· Pattern Recognition in Audio and Speech Processing

The KES-IDT conference is a well-established international annual conference, interdisciplinary in nature. These two volumes of proceedings form an excellent account of the latest results and outcomes of recent research in this leading-edge area.

Inhaltsverzeichnis

Frontmatter

Intelligent Data Analysis and Applications

Frontmatter

Comparison of Four Methods of Combining Classifiers on the Basis of Dispersed Medical Data

The main aim of the article is to compare the results obtained using four different methods of combining classifiers in a dispersed decision-making system. In the article the following fusion methods are used: the majority vote, the weighted majority vote, the Borda count method and the highest rank method. Two of these methods are used if the individual classifier generates a class label and two are used in the case when the individual classifier produces ranking of classes instead of unique class choice. All of these methods were tested in a situation when we have access to data from medical field and this data are in a dispersed form. The use of dispersed medical data is very important because it is common situation that medical data from one domain are collected in many different medical centers. It would be good to be able to use all this accumulated knowledge at the same time.

Małgorzata Przybyła-Kasperek

Estimation of Coefficient of Static Friction of Surface by Analyzing Photo Images

We propose a method to estimate the coefficient of static friction of floor surfaces by analyzing photo image of the floor tiles. The image features that we use to estimate the coefficient are micro-shape features and micro-depth features. We extract the difference between the flash images and the non-flash images of floor tiles. We have composed an equation by applying multiple linear regression analysis that sets the image features as explanatory variables and the measurements of the tile images as objective values. As the result, we have obtained an estimate equation that coefficient of determination R2 is 0.97 and we observed the two-sided 95 % confidence interval ±0.053. We can say that the equation is good enough for practical use.

Hitoshi Tamura, Yasushi Kambayashi

Decision Case Management for Digital Enterprise Architectures with the Internet of Things

The Internet of Things (IoT), Enterprise Social Networks, Adaptive Case Management, Mobility systems, Analytics for Big Data, and Cloud services environments are emerging to support smart connected products and services and the digital transformation. Biological metaphors of living and adaptable ecosystems with service-oriented enterprise architectures provide the foundation for self-optimizing and resilient run-time environments for intelligent business services and related distributed information systems. We are investigating mechanisms for flexible adaptation and evolution for the next digital enterprise architecture systems in the context of the digital transformation. Our aim is to support flexibility and agile transformation for both business and related enterprise systems through adaptation and dynamical evolution of digital enterprise architectures. The present research paper investigates mechanisms for decision case management in the context of multi-perspective explorations of enterprise services and Internet of Things architectures by extending original enterprise architecture reference models with state of art elements for architectural engineering for the digitization and architectural decision support.

Alfred Zimmermann, Rainer Schmidt, Dierk Jugel, Kurt Sandkuhl, Christian Schweda, Michael Möhring, Justus Bogner

Exploiting Emoticons to Generate Emotional Dictionaries from Facebook Pages

During the first events of the Tunisian revolution, the social network, Facebook, played a key role in Tunisia and everywhere in the world. It became the first political tool that allows the Tunisian people to share trending news in actual time. Facebook provides the opportunity for users to comment on the news by expressing their sentiments. In this paper, we focus on emotion analysis of Tunisian Facebook pages. To do this, we first collect comments from the Facebook pages in order to analyze sentiments written in Tunisian dialect. Then, we propose a new method for emotional dictionaries construction. In fact, we distinguish nine emotional classes: surprised, satisfied, happy, gleeful, romantic, disappointed, sad, angry and disgusted. At this step, we focus on the use of emotion symbols as indicators of sentiment polarity. Finally, we present the experimental results of our method. Our system achieves effective and consistent results.

Hanen Ameur, Salma Jamoussi, Abdelmajid Ben Hamadou

Multiple Ontology-Based Indexing of Multimedia Documents on the World Wide Web

In order to cope with the growing need to search multimedia documents with precision on the Web, we propose a multimedia conceptual indexing framework incorporating semantic relations between annotation words. To do this, we utilize our DOM Tree-based Webpage segmentation algorithm to automatically extract surrounding textual information of the multimedia documents in Webpages. Next, we employ knowledge represented in multiple ontologies to discover the latent semantic dimensions of the surrounding textual information. As a consequence, indexes (represented as semantic networks) are constructed where nodes of each network capture words that exist in the ontologies and edges represent the semantic relations that hold between those words. To address the semantic heterogeneity problem between the produced networks, we employ a multi-level merging algorithm that combines heterogeneous networks into a more coherent network. Additionally, we utilize concept-relatedness measures to address the issue of unrecognized entities by the ontologies. We evaluate the techniques of the proposed framework using three different multimedia dataset types. Experimental results indicate that the proposed techniques are effective and precise.

Mohammed Maree, Mohammed Belkhatir, Fariza Fauzi, Aseel B. Kmail, Ahmad Ewais, Muath Sabha

Feature Selection Methods Based on Decision Rule and Tree Models

Feature selection methods, as a preprocessing step to machine learning, is effective in reducing dimensionality, removing irrelevant data, increasing learning accuracy, and improving result comprehensibility. However, the recent increase of dimensionality of data poses a severe challenge to many existing feature selection methods with respect to efficiency and effectiveness. In this work, a novel concepts of relevant feature selection based on information gathered from decision rule and decision tree models were introduced. A new measures DRQualityImp and DTLevelImp were additionally defined. The first one is based on feature presence frequency and rule quality, while the second is based on feature presence on different levels inside decision tree. The efficiency and effectiveness of that method is demonstrated through the exemplary use of five real-world datasets. Promising initial results of classification efficiency could be gained together with substantial reduction of problem dimensionality.

Wiesław Paja

Automatic Categorization of Email into Folders by Ant Colony Decision Tree and Social Networks

This paper presents a new approach to an automatic categorization of email messages into mailbox folders. The aim of this paper is to create an algorithm that would allow one to improve the classification of emails into folders by using solutions that have been applied in Ant Colony Decision Tree (ACDT). Additionally, elements of Social Network Analysis (SNA) were included in this algorithm. The new algorithm that is proposed here was tested on the publicly available Enron E-mail data set and all experiments were conducted on uncleaned data. For the purpose of comparing the results, additional tests were carried out by using selected classifiers which were generally available. The obtained results confirm that the proposed approach allows one to improve the accuracy with which new emails are assigned to particular folders based on an analysis of previous correspondence, even when uncleaned data sets are used.

Urszula Boryczka, Barbara Probierz, Jan Kozak

Using Dissimilarity Matrix for Eye Movement Biometrics with a Jumping Point Experiment

The paper presents studies on the application of the dissimilarity matrix-based method to the eye movement analysis. This method was utilized in the biometric identification task. To assess its efficiency four different datasets based on similar scenario (‘jumping point’ type) yet using different eye trackers, recording frequencies and time intervals have been used. It allowed to build the common platform for the research and to draw some interesting comparisons. The dissimilarity matrix, which has never been used for identifying people on the basis of their eye movements, was constructed with usage of different distance measures. Additionally, there were different signal transforms and metrics checked and their performance on various datasets was compared. It is worth mentioning that the paper presents the algorithm that was used during the BioEye 2015 competition and ranked as one of the top three methods.

Pawel Kasprowski, Katarzyna Harezlak

Epigenetically Inspired Modification of Genetic Algorithm and His Efficiency on Biological Sequence Alignment

In this paper the modification of genetic algorithm inspired by the epigenetic process is presented. The results of the efficiency of the proposed modified algorithm are compared with standard genetic algorithm and a tool which does not use evolutionary processes.

Kornel Chromiński, Mariusz Boryczka

Meta-Bayes Classifier with Markov Model Applied to the Control of Bioprosthetic Hand

The paper presents an advanced method of recognition of patient’s intention to move of multijoint hand prosthesis during the grasping of objects. In the considered decision problem we assume that each prosthesis operation can be divided into sequence of elementary actions and the patient’s intention means his will to perform a specific elementary action. A characteristic feature of the explored sequential decision problem is the dependence between its phases at particular instants which should be taken into account in the recognition algorithm. The proposed classification method is based on multiclassifier (MC) system working in sequential fashion, dedicated to EMG and MMG biosignals and with dynamic combining mechanism using the Bayes scheme and Markov model of dependences. The performance of proposed MC system with 3 different types of base classifiers was experimentally compared against 3 sequential classifiers for 1—and 2-instant backward dependence using real data concerning the recognition of six types of grasping movements. The results obtained indicate that use of MC system dedicated to the sequential scheme of recognition process, essentially improves performance of patient’s intent classification and that this improvement depends on the type of base classifiers and order of dependence.

Marek Kurzynski, Marcin Majak

Contextual Modelling Collaborative Recommender System—Real Environment Deployment Results

Nowadays, recommender systems are widely used in many areas as a solution to deal with information overload. There are some popular and effective methods to build a good recommendation system: collaborative filtering, content-based, knowledge-based and hybrid. Another approach, which made a significant progress over the last several years, are context-aware recommenders. There are many additional information related to the context or application area of recommender systems, which can be useful to generate accurate propositions, e.g. user localisation, items categories or attributes, a day of a week or time of a day, weather. Another issue is recommenders evaluation. Usually, they are only assessed with respect to their prediction accuracy (RMSE, MAE). This is good solution, due to possibility of off-line calculation. However, in real environment recommendation lists are finally evaluated by users who take into consideration many various factors, like novelty or diversity of items. In this article a multi-module collaborative filtering recommender system with consideration of context information is presented. The context is included both in post-filtering module as well as in a similarity measure. Evaluation was made off-line with respect to prediction accuracy and on-line, on real shopping platform.

Urszula Kużelewska

Decision Trees on the Foreign Exchange Market

In this article we present a novel approach to generate a data set directly from real-world forex market data. The data are transformed into a decision table. Every single object in such a table consists of conditional attributes—in this case values of technical analysis indicators as well as of the decision class (BUY, SELL or WAIT). Our second goal was to test the quality of the classification based on two well-known algorithms used for decision tree construction: the CART algorithm and the C4.5 algorithm. All experiments were conducted on three different currency pairs—with 3 data sets for each pair.

Juszczuk Przemyslaw, Kozak Jan, Trynda Katarzyna

On Granular Rough Computing: Covering by Joint and Disjoint Granules in Epsilon Concept Dependent Granulation

In this work we present the optimization methods of epsilon concept-dependent granulation. We consider two cases of parallel covering and granulation, based on joint and disjoint granules. Additionally we check two variants of majority voting, the first one based on descriptors, which are epsilon-indiscernible with the centers of granules, and the second variant uses all descriptors of respective granules. We verify the effectiveness of our methods on the real data sets from UCI Repository using the SVM classifier. It turned out that disjoint granules versus joint give almost identical results of classification with a significant acceleration of the granulation process. Additionally, the majority voting, based on the epsilon indiscernible descriptors, stabilised the process of granulation in terms of the accuracy of classification. This is a significant result, which lets us to accelerate the process of classification for many popular classifiers at least for k-NN, Naive Bayes, many rough set methods and the SVM classifier, which is supported by our recent works.

Piotr Artiemjew, Jacek Szypulski

On Approaches to Discretization of Datasets Used for Evaluation of Decision Systems

The paper describes research on ways of datasets discretization, when test datasets are used for evaluation of a classifier. Three different approaches of processing for training and test datasets are presented: “independent”—where discretization is performed separately for both sets assuming that the same algorithm parameters are used; “glued”—where both sets are concatenated, discretized, and resulting set is separated to obtain training and test sets, and finally “test on learn”—where test dataset is discretized using ranges obtained from learning data. All methods have been investigated and tested in authorship attribution domain using Naive Bayes classifier.

Grzegorz Baron, Katarzyna Harężlak

Intelligent Decision Making for Uncertain Unstructured Big Data

Frontmatter

A Bayesian Approach to Classify the Music Scores on the Basis of the Music Style

This article presents a new version of the algorithm proposed by Della Ventura (12th TELE-INFO International Conference on Recent Researches in Telecommunications, and Informatics, 2013, [1]) to classify the musical scores. Score classification means an automatic process of assignment of the specific score to a certain class or category: baroque, romantic or contemporary music. The algorithm is based on a Bayesian probabilistic model that extends the Naive Bayes classifier by adding a variable tied to the value of the information contained within the. The score is not seen as a single entity, but as a set of subtopics, every single one of which identifies and represents a standard feature of music writing. The classification of the score is done on the basis of its subtopics: an intermediate level of classification is thus introduced, which induces a hierarchical classification. The new algorithm performs equally well on the old dataset, but gives much better results on the new larger and more diverse dataset.

Michele Della Ventura

A Framework for Extracting Reliable Information from Unstructured Uncertain Big Data

Big Data is still in its initial stages and has prompted various basic issues and difficulties to rise, for example, the pace of exchange, information development, and assorted qualities of information and security issues. For example, overseeing and abusing immense measures of information make it more valuable and important has turned into a test driving basic learning for choice making and in picking up an understanding into the general circumstance. Huge information has gotten phenomenal consideration from open and private sectors and in addition from the educated community around the world. In advertising, enormous information is utilized to comprehend the practices and actives of clients. In the experimental fields, huge information can be misused by aiding and taking care of the issues confronting the investigative fields extending from nanotechnology to climatology to geophysics. In the field of law requirement, social administrations and country security, enormous information has exhibited its handiness for government organizations to bolster in their choice making.

Sanjay Kumar Singh, Neel Mani, Bharat Singh

Reasoning-Based Intelligent Systems

Frontmatter

Visual Builder of Rules for Spacecraft Onboard Real-Time Knowledge Base

Fault tolerance of spacecraft remains one of the most complex problems in space missions. There are several ways to implement the “onboard intelligence allowing the recovery of a spacecraft in case of abnormal situations caused by hardware or software failures. The most common but inflexible way is “to disperse” the recovery logic in the source code of the flight control software. Our approach implies using onboard real-time knowledge base. The rules of the knowledge base could be added or refined from Earth over the radio channel on a timely basis. Currently, the rules of an onboard knowledge base should be specified in a table form, which entails some misunderstandings in the mission team and consequently leads to errors. The improved approach presented in the paper provides special tools–the visualizer and the visual builder of rules. The approach allows space mission operation engineers without special mathematical or programming background to define, visualize and refine knowledge base rules in a very easy manner. Tools prototypes are currently introduced at JSC Information Satellite Systems, Russia.

Andrey Tyugashev

A Generic Document Retrieval Framework Based on UMLS Similarity for Biomedical Question Answering System

Biomedical document retrieval systems play a vital role in biomedical question answering systems. The performance of the latter depends directly on the performance of its biomedical document retrieval section. Indeed, the main goal of biomedical document retrieval is to find a set of citations that have high probability to contain the answers. In this paper, we propose a biomedical document retrieval framework to retrieve the relevant documents for the biomedical questions (queries) from the users. In our framework, we first use GoPubMed search engine to find the top-K results. Then, we re-rank the top-K results by computing the semantic similarity between questions and the title of each document using UMLS similarity. Our proposed framework is evaluated on the BioASQ 2014 task datasets. The experimental results show that our proposed framework has the best performance (MAP@100) compared to the existing state-of-the-art related document retrieval systems.

Mourad Sarrouti, Said Ouatik El Alaoui

An IoA Cloud-Based Farmer Support System “AgriMieru”

In recent years, the aging of agricultural workers has progressed rapidly, successor problem is becoming more serious. Under such circumstances are coming out also new farmers that will beginner to agriculture. However, the establishment of farming technology has become a major management challenge for new farmers. In this study, we focus our efforts to solve the management issues of the farming acquisition of technology and to develop an Internet of Agriculture (IoA) cloud-based designed farmer support system, called “AgriMieru”. In details, we will describe the water management system and Machine to Machine (M2M) system, cloud system design and interface, those are fundamental keystones of this newly proposed system.

Alireza Ahrary, Masayoshi Inada, Yoshitaka Yamashita

Review Paper: Paraconsistent Process Order Control

We have already proposed the paraconsistent process order control method based on an annotated logic program bf-EVALPSN. Bf-EVALPSN can deal with before-after relations between two processes (time intervals) in its annotations, and its reasoning system consists of two kinds of inference rules called the basic bf-inference rule and the transitive bf-inference rule. In this paper, we review how bf-EVALPSN can be applied to process order control with a simple example.

Kazumi Nakamatsu, Jair Minoro Abe, Seiki Akama

Recent Advances in Fuzzy Systems

Frontmatter

Modeling and Forecasting of Well-Being Using Fuzzy Cognitive Maps

In this paper we address the problem of modeling and forecasting of well-being. First, we apply a graph-based model of a Fuzzy cognitive map to discover cause-and-effect relationships among indicators of well-being. Second, the discovered model is applied to forecast the future state of well-being. The model is constructed using historical multivariate time series containing six consolidated indexes that represent well-being on the considered territory. Experiments with real-world data provided evidence for the usefulness of the proposed approach. Moreover, the interpretation of the obtained FCM graph led to the discovery of unknown dependencies within the data. The analysis of the unknown dependencies requires further research.

Tatiana Penkova, Wojciech Froelich

Embedded Dynamic Fuzzy Cognitive Maps for Controller in Industrial Mixer

This paper presents the application of certain intelligent techniques to control an industrial mixer. Control design is based on Hebbian modification of Fuzzy Cognitive Maps learning. This research study develops a Dynamic Fuzzy Cognitive Map (DFCM) based on Hebbian Learning algorithms. It was used Fuzzy Classic Controller to help validate simulation results of an industrial mixer of DFCM. Experimental analysis of simulations in this control problem was conducted. Additionally, the results were embedded using efficient algorithms into the Arduino platform in order to acknowledge the performance of the codes reported in this paper.

Márcio Mendonça, Flávio Neves, Lúcia V. R. de Arruda, Ivan Rossato Chrun, Elpiniki I. Papageorgiou

Analyzing Cloud Business Services with Choquet Fuzzy Integrals and Support Vector Machines

Cloud computing poses both opportunities and challenges for companies and IT professionals. Some of these are technical challenges that can be solved over time, while others are related to uncertainties arising from the commitment to a recent innovation. The objective of this research is to identify some of the uncertainties that IT professionals may have and can discourage them from adopting cloud computing. In fact, this paper is focused on predicting the perceived easy-of-use of cloud business services. For that purpose, we use Choquet Fuzzy Integral and Support Vector Machines.

Jose L. Salmeron, Pedro Palos

Intelligent Methods for Eye Movement Data Processing and Analysis

Frontmatter

Time-Preserving Visual Attention Maps

Exploring the visual attention paid to a static scene can be done by visual analysis in form of attention maps also referred to as heat maps. Such maps can be computed by aggregating eye movement data to a density field which is later color coded to support the rapid identification of hot spots. Although many attempts have been made to enhance such visual attention maps, they typically do not integrate the time-varying visual attention in the static map. In this paper we investigate the problem of incorporating the dynamics of the visual attention paid to a static scene in a corresponding attention map. To reach this goal we first compute time-weighted Voronoi-based density fields for each eye-tracked person which are aggregated or averaged for a group of those people. These density values are then smoothed by a box reconstruction filter to generate aesthetically pleasing diagrams. To achieve better readability of the similar color values in the maps we enrich them by interactively adaptable isolines indicating the borders of hot spot regions of different density values. We illustrate the usefulness of our time-preserving visual attention maps in an application example investigating the analysis of visual attention in a formerly conducted eye tracking study for solving route finding tasks in public transport maps.

Michael Burch

Eye Movements in Reading the Texts of Different Functional Styles: Evidence from Russian

This study is one of the first eye-tracking experiment on Russian language material, checking out if the functional text style is among the readability categories and if it influences the effect of reading perspective. In Experiment participants (30 native speakers of Russian) read three texts on different topics each written in a different functional style. Questionnaires and retelling the texts were additionally used to collect data on text comprehension and accessibility. We suggest that the following eye-tracking data can be informative when we need to evaluate text readability: amplitude of saccades, number of regressions, fixation duration while searching for an answer in the text. The results indicate that the text on the same topic is easier read if it is written in a publicistic style than in a scientific style. There were no significant differences in eye-tracking data between texts written in publicistic style and colloquial style.

Tatiana Petrova

Monitoring Dementia with Automatic Eye Movements Analysis

Eye movement patterns are found to reveal human cognitive and mental states that can not be easily measured by other biological signals. With the rapid development of eye tracking technologies, there are growing interests in analysing gaze data to infer information about people’ cognitive states, tasks and activities performed in naturalistic environments. In this paper, we investigate the link between eye movements and cognitive function. We conducted experiments to record subject’s eye movements during video watching. By using computational methods, we identified eye movement features that are correlated to people’s cognitive health measures obtained through the standard cognitive tests. Our results show that it is possible to infer people’s cognitive function by analysing natural gaze behaviour. This work contributes an initial understanding of monitoring cognitive deterioration and dementia with automatic eye movement analysis.

Yanxia Zhang, Thomas Wilcockson, Kwang In Kim, Trevor Crawford, Hans Gellersen, Pete Sawyer

Eye Movement Evidence of Cognitive Strategies in SL Vocabulary Learning

This paper presents the results of an experimental study modeling the situation of non-contextual foreign language vocabulary learning. Subjects (n = 31) memorized words of a foreign language, which were presented in pairs with their Russian translations. Eye movements were recorded during the trial. After the presentation subjects recalled the foreign words, and they also provided a post hoc report about the learning strategies they used. As a result, 3 main techniques of foreign vocabulary learning were distinguished (“graphical”, “phonemic” and “semantic” techniques), characterized by emphasis on the corresponding level of processing. Strong patterns of interrelation between the mnemonic techniques, recall score and eye movement characteristics were observed.

Irina Blinnikova, Anna Izmalkova

Application of Eye Tracking for Diagnosis and Therapy of Children with Brain Disabilities

Children affected by brain disabilities require a lot of attention and care to improve their life. The quicker the support will be introduced the better effect can be achieved. One of important impairments resulted from the brain disability is a cerebral visual one. In case of children, communicating with whom is difficult or impossible, assessment of vision quality is very challenging and eye tracking methods may prove very useful. The research discussed in this paper was devoted to development of a workspace, which may support the effort of therapists working on improving the quality of disabled children’s life. The important element of this solution is the implicit calibration procedure, making eye movement registration possible. Additionally, there were several stimuli developed and tested with cooperation of therapists from one of associations for children with developmental disabilities. Initial tests confirmed usefulness of the elaborated solution, which facilitates children’s vision assessment based on the eye movement signal and may be used for a further children therapy.

Katarzyna Harezlak, Pawel Kasprowski, Michalina Dzierzega, Katarzyna Kruk

Intelligent Decision Technologies for Water Resources Management

Frontmatter

Forecasting Domestic Water Consumption Using Bayesian Model

In this paper, we address the problem of forecasting domestic water consumption. A specific feature of the forecasted time series is that water consumption occurs at random time steps. This substantially limits the application of the standard state-of-the art forecasting methods. The other existing forecasting models dedicated to predicting water consumption in households rely on data collected from questionnaires or diaries, requiring additional effort for gathering data. To overcome those limitations, we propose in this paper a Bayesian model to be applied for the forecasting of the domestic water consumption time series. The proposed theoretical approach has been tested using real-world data gathered from an anonymous household.

Wojciech Froelich, Ewa Magiera

An Evaluation of the Instruments Aimed at Poland’s Water Savings

This paper evaluates the effectiveness and cost efficiency of a water abstraction tax fitted to the scarcity of surface water resources. The modelling of the hypothetical consequences of the proposed taxation scheme were conducted using several databases. These databases describe the availability of water resources in Poland, as well as the present schemes, the level of taxation and the economic conditions of Polish municipal water providers. All four scenarios were taken into consideration to meet the criteria of a better fitting of the unit intake tax to the scarcity of water at the local level. However, the progression of the rates and total fiscal effects were different. The proposed instrument was found to have a minor influence on the water operators and a very small influence on the end users; this was due to the low level of taxation at the present time.

Krzysztof Berbeka, Malgorzata Palys

Soft Computing Approaches for Urban Water Demand Forecasting

This paper presents an integrated framework for water resources management at urban level which consists of a Neuro-Fuzzy and Fuzzy Cognitive Map-based, (FCM) decision support system (DSS) based on multiple objectives and multiple disciplines for planning and forecasting. The proposed DSS has as primary goals to: (a) adaptively control the water pressure of the water distribution system by forecasting the water demand at the urban level and (b) to reduce leakage of the water network by controlling the water pressure. The system follows a model-driven architecture with the inclusion of the FCM-based models and a spatio-temporal model for arranging all data. The validation of the proposed learning algorithms is made for two case studies that comprise different water supply characteristics and correspond to different locations in Europe.

Konstantinos Kokkinos, Elpiniki I. Papageorgiou, Katarzyna Poczeta, Lefteris Papadopoulos, Chrysi Laspidou

Decision Making Theory for Economics

Frontmatter

Ranking Alternatives by Pairwise Comparisons Matrix with Fuzzy Elements on Alo-Group

The decision making problem considered in this paper is to rank n alternatives from the best to the worst, using the information given by the decision maker in the form of an n by n pairwise comparisons matrix. Here, we deal with a pairwise comparisons matrix with fuzzy elements (PCF matrix). Fuzzy elements of the pairwise comparisons matrix are applied whenever the decision maker is not sure about the value of his/her evaluation, or, the elements of the PCF matrix are aggregated crisp evaluations in a group decision making problem. We investigate pairwise comparisons matrices with elements from an abelian linearly ordered group (alo-group) over a real interval. We propose a method starting from construction of fuzzy elements of a reciprocal PCF matrix, calculating its consistency and resulting into computation of the priority vector associated to the ranking of the alternatives. Illustrating examples are presented and discussed.

Jaroslav Ramík

An Analysis on Three Inflection Points on Four Economic Phases

Economic cycles can be represented in a sequence of four economic phases. These four phases are Thetical economy, Bubble economy, Bubble collapse economy, and Antithetical economy. This is a description of an economic cycle in Kinoshita’s economic scheme: Thetical economics and Antithetical economics. In this paper, we describe mechanisms of three inflection points of these four phases. We focus on the consumption propensity, and we construct a model that a change of the consumption propensity causes transitions of these phases. Through the modeling and its analyses of inflection points, we clear a nature of economic phases. A market enlarges its economic scale in phases before a bubble collapse, and the market optimizes its economic activities in phases after the collapse.

Takafumi Mizuno, Eizo Kinoshita

Economic Rationalities and Governmental Actions on the Thetical Economics and the Antithetical Economics

Kinoshita has been proposed a macroeconomic paradigm. It consists of the Thetical economics and the Antithetical economics. In this paper, we describe behavioral principles of corporations and the government on the paradigm. The description is a model based on linear programming of Operations Research. And we discuss governmental activities using the model. In conclusion, we state that the government must adopt monetary policy in an economic phase which is dominated by the Thetical economics, and the government must adopt fiscal policy in another economic phase which is dominated by the Antithetical economics.

Eizo Kinoshita, Takafumi Mizuno

Improvement of the Weights Due to Inconsistent Pairwise Comparisons in the AHP

One of the most important problems in the Analytic Hierarchy Process (AHP) is consistency of pairwise comparisons by the decision maker. This study focuses on the comparison methods to be used when the weights of the alternatives and criteria in AHP are inconsistent. In general, the weights in AHP use the principal eigenvector of the pairwise comparison matrix. However, for example, due to the decision maker’s misunderstandings, inconsistencies in pairwise comparisons sometimes arise. The consistency of the pairwise comparison matrix is usually determined using Consistency Index (CI) values. In the traditional AHP, when judged inconsistent, repeating the pairwise comparison is usually recommended. However, if the repeated comparison is arbitrarily performed, the results will not be optimal. In fact, to obtain the overall evaluation of alternatives, we often use inconsistent weights, even given the inconsistencies in the latter. Another method for judging the consistency of the pairwise comparison is to use a directed graph. Cycles in a directed graph represent comparison inconsistencies. Therefore in this paper, based on the principal eigenvalue and cycles in the directed graph of the pairwise comparison matrix, a method of correcting the principal eigenvector taking into consideration consistency is proposed.

Kazutomo Nishizawa

Super Pairwise Comparison Matrix in the Dominant AHP

We have proposed an SPCM (Super Pairwise Comparison Matrix) to express all pairwise comparisons in the evaluation process of D-AHP (the dominant analytic hierarchy process) or the multiple dominant AHP as a single pairwise comparison matrix. This paper shows that the evaluation value resulting from the application of LLSM (the logarithmic least-squares method) to an SPCM matches the evaluation value determined by the application of D-AHP to the evaluation values obtained from each pairwise comparison matrix by using the geometric mean.

Takao Ohya, Eizo Kinoshita

Interdisciplinary Approaches in Business Intelligence Research and Practice

Frontmatter

Heterogeneous NoSQL Databases Abstraction Approach Based on Full Text Search Indexes

The exponential growth of unstructured data in the mobile applications, the social networks and the web technologies led to NoSQL database emergence. While this specific class of DBMS provided a better scalability for databases, the lack of a standard DML that unifies and simplifies querying NoSQL data stores is still a hard deal especially in heterogeneous environments. A simple SQL query can turn into a complex map-reduce function in the NoSQL world in order to obtain the same result in the standard SQL DDBMS. With no common convention between the large variety of NoSQL implementations and families, each product implemented its vision of the NoSQL concept. Each implementation covered distinct functional scopes, depending on the target domain and the creation purposes. Meanwhile, many successful NoSQL databases integrated a powerful full text component to enhance their search capabilities. To remedy this variety limitation, we propose a new incremental approach that allows (1) the standardization of NOSQL search queries among heterogeneous NoSQL data stores and (2) NoSQL search queries optimizing. This approach is based on (1) the definition of a new universal engine for full text indexing, (2) incremental synchronization of data and indexes between the stretched sites.

Hassen Fadoua, Grissa Touzi Amel

Potentials of Image Mining for Business Process Management

An enormous amount of data in the context of business processes is stored as images. They contain valuable information for business process management. Up to now this data had to be integrated manually into the business process. By advances of capturing it is possible to extract information from an increasing number of images. Therefore, we systematically investigate the potentials of Image Mining for business process management by a literature research and an in-depth analysis of the business process lifecycle. As a first step to evaluate our research, we developed a prototype for recovering process model information from drawings using Rapidminer.

Rainer Schmidt, Michael Möhring, Alfred Zimmermann, Ralf-Christian Härting, Barbara Keller

Decision Trees as Readable Models for Early Childhood Caries

Assessing risk for early childhood caries (ECC) is a relevant task in public health care and an important activity in fulfilling this task is increasing the knowledge about ECC. Discovering important information from data and sharing it in an understandable format with both experts and the general population could be beneficial for advancing and spreading the knowledge about this disease. After having experimented with association rule mining, we investigate the possibility of using decision trees as readable models in risk assessment. We build various decision trees using different algorithms and splitting criteria, favouring compact decision trees with good predictive performance. These decision trees are compared to the previous ECC models for the same analyzed population, namely a logistic regression model and an associative classifier, as well as to decision trees for caries from other studies. The results indicate flexibility and usefulness of decision trees in this context.

Vladimir Ivančević, Nemanja Igić, Branko Terzić, Marko Knežević, Ivan Luković

Pattern Recognition in Audio and Speech Processing

Frontmatter

Music Genre Classification Using a Gradient-Based Local Texture Descriptor

With the increasing popularity and availability of online music databases that store vast collections of music, automated classification of music genre has attracted significant attention for the management of such large-scale databases. This paper presents a new music genre classification method that utilizes gradient-based texture analysis of the spectrograms constructed from the audio signals. We propose to use gradient directional pattern (GDP)—a robust local texture descriptor that exploits the gradient directional information to encode the local texture properties of an image. The proposed method first computes spectrograms from the audio signals and then applies the GDP operator to construct the feature descriptors that represent micro-level texture details of the spectrograms. We use a support vector machine (SVM) for the classification task. The effectiveness of the proposed method is evaluated using the GTZAN genre collection music database. Our experiments show promising results for the proposed GDP-based spectrogram texture analysis, as compared against some other existing music genre classification methods.

Faisal Ahmed, Padma Polash Paul, Marina Gavrilova

Robust Speaker Identification in a Meeting with Short Audio Segments

The paper proposes a speaker identification scheme for a meeting scenario, that is able to answer the question “is somebody currently talking?”, if yes, “who is it?”. The suggested system has been designed to identify during a meeting conversation the current speaker from a set of pre-trained speaker models. Experimental results on two databases show the robustness of the approach to the overlapping phenomena and the ability of the algorithm to correctly identify a speaker with short audio segments.

Giorgio Biagetti, Paolo Crippa, Laura Falaschetti, Simone Orcioni, Claudio Turchetti

Backmatter

Weitere Informationen

Premium Partner

    Bildnachweise