Skip to main content
main-content

Über dieses Buch

This book constitutes the proceedings of the 14th IFIP TC 8 International Conference on Computer Information Systems and Industrial Management, CISIM 2015, held in Warsaw, Poland, in September 2015.
The 47 papers presented in this volume were carefully reviewed and selected from about 80 submissions. The main topics covered are biometrics, security systems, multimedia, classification and clustering with applications, and industrial management.

Inhaltsverzeichnis

Frontmatter

Full Keynote and Invited Papers

Frontmatter

Privacy Analysis of Android Apps: Implicit Flows and Quantitative Analysis

A static analysis is presented, based on the theory of abstract interpretation, for verifying privacy policy compliance by mobile applications. This includes instances where, for example, the application releases the user’s location or device ID without authorization. It properly extends previous work on datacentric semantics for verification of privacy policy compliance by mobile applications by (i) tracking implicit information flow, and (ii) performing a quantitative analysis of information leakage. This yields to a novel combination of qualitative and quantitative analyses of information flows in mobile applications.

Gianluca Barbon, Agostino Cortesi, Pietro Ferrara, Marco Pistoia, Omer Tripp

Probabilistic Principal Components and Mixtures, How This Works

Classical Principal Components Analysis (PCA) is widely recognized as a method for dimensionality reduction and data visualization. This is a purely algebraic method, it considers just some optimization problem which fits exactly to the gathered data vectors with their particularities. No statistical significance tests are possible. An alternative is to use probabilistic principal component analysis (PPCA), which is formulated on a probabilistic ground. Obviously, to do it one has to know the probability distribution of the analyzed data. Usually the Multi-Variate Gaussian (MVG) distribution is assumed. But what, if the analyzed data are decidedly not MVG? We have met such problem when elaborating multivariate gearbox data derived from a heavy duty machine. We show here how we have dealt with the problem.

In our analysis, we assumed that the considered data are a mixture of two groups being MVG, specifically: each of the sub-group follows a probabilistic principal component (PPC) distribution with a MVG error function. Then, by applying Bayesian inference, we were able to calculate for each data vector x its a posteriori probability of belonging to data generated by the assumed model. After estimation of the parameters of the assumed model we got means - based on a sound statistical basis - for constructing confidence boundaries of the data and finding outliers.

Anna M. Bartkowiak, Radoslaw Zimroz

Music Information Retrieval - Soft Computing Versus Statistics

Music Information Retrieval (MIR) is an interdisciplinary research area that covers automated extraction of information from audio signals, music databases and services enabling the indexed information searching. In the early stages the primary focus of MIR was on music information through Query-by- Humming (QBH) applications, i.e. on identifying a piece of music by singing (singing/whistling), while more advanced implementations supporting Queryby- Example (QBE) searching resulted in names of audio tracks, song identification, etc. Both QBH and QBE required several steps, among others an optimized signal parametrization and the soft computing approach. Nowadays, MIR is associated with research based on the content analysis that is related to the retrieval of a musical style, genre or music referring to mood or emotions. Even though, this type of music retrieval called Query-by-Category still needs feature extraction and parametrization optimizing, but in this case search of global online music systems and services applications with their millions of users is based on statistical measures. The paper presents details concerning MIR background and answers a question concerning usage of soft computing versus statistics, namely: why and when each of them should be employed.

Bozena Kostek

Integrals Based on Monotone Measure: Optimization Tools and Special Functionals

Integrals on finite spaces (e.g., sets of criteria in multicriteria decision support) based on capacities are discussed, axiomatized and examplified. We introduce first the universal integrals, covering the Choquet, Shilkret and Sugeno integrals. Based on optimization approach, we discuss decomposition and superdecomposition integrals. We introduce integrals which are universal and decomposition (superdecomposition) ones and integrals constructed by means of copulas. Several distinguished integrals are represented as particular functionals. Finally, we recall also OWA operators and some their generalizations.

Radko Mesiar

Graph Databases: Their Power and Limitations

Real world data offers a lot of possibilities to be represented as graphs. As a result we obtain undirected or directed graphs, multigraphs and hypergraphs, labelled or weighted graphs and their variants. A development of graph modelling brings also new approaches, e.g., considering constraints. Processing graphs in a database way can be done in many different ways. Some graphs can be represented as JSON or XML structures and processed by their native database tools. More generally, a graph database is specified as any storage system that provides index-free adjacency, i.e. an explicit graph structure. Graph database technology contains some technological features inherent to traditional databases, e.g. ACID properties and availability. Use cases of graph databases like Neo4j, OrientDB, InfiniteGraph, FlockDB, AllegroGraph, and others, document that graph databases are becoming a common means for any connected data. In Big Data era, important questions are connected with scalability for large graphs as well as scaling for read/write operations. For example, scaling graph data by distributing it in a network is much more difficult than scaling simpler data models and is still a work in progress. Still a challenge is pattern matching in graphs providing, in principle, an arbitrarily complex identity function. Mining complete frequent patterns from graph databases is also challenging since supporting operations are computationally costly. In this paper, we discuss recent advances and limitations in these areas as well as future directions.

Jaroslav Pokorný

Algorithms

Frontmatter

Performance Analysis and Tuning for Parallelization of Ant Colony Optimization by Using OpenMP

Ant colony optimization algorithm (ACO) is a soft computing metaheuristic that belongs to swarm intelligence methods. ACO has proven a well performance in solving certain NP-hard problems in polynomial time. This paper proposes the analysis, design and implementation of ACO as a parallel metaheuristics using the OpenMP framework. To improve the efficiency of ACO parallelization, different related aspects are examined, including scheduling of threads, race hazards and efficient tuning of the effective number of threads. A case study of solving the traveling salesman problem (TSP) using different configurations is presented to evaluate the performance of the proposed approach. Experimental results show a significant speedup in execution time for more than 3 times over the sequential implementation.

Ahmed A. Abouelfarag, Walid Mohamed Aly, Ashraf Gamal Elbialy

Acceleration of Blender Cycles Path-Tracing Engine Using Intel Many Integrated Core Architecture

This paper describes the acceleration of the most computationally intensive kernels of the Blender rendering engine, Blender Cycles, using Intel Many Integrated Core architecture (MIC). The proposed parallelization, which uses OpenMP technology, also improves the performance of the rendering engine when running on multi-core CPUs and multi-socket servers. Although the GPU acceleration is already implemented in Cycles, its functionality is limited. Our proposed implementation for MIC architecture contains all features of the engine with improved performance. The paper presents performance evaluation for three architectures: multi-socket server, server with MIC (Intel Xeon Phi 5100p) accelerator and server with GPU accelerator (NVIDIA Tesla K20m).

Milan Jaroš, Lubomír Říha, Petr Strakoš, Tomáš Karásek, Alena Vašatová, Marta Jarošová, Tomáš Kozubek

A Modified Complete Spline Interpolation and Exponential Parameterization

In this paper a modified complete spline interpolation based on reduced data is examined in the context of trajectory approximation. Reduced data constitute an ordered collection of interpolation points in arbitrary Euclidean space, stripped from the corresponding interpolation knots. The exponential parameterization (controlled by

λε

[0, 1]) compensates the above loss of information and provides specific scheme to approximate the distribution of the missing knots. This approach is commonly used in computer graphics or computer vision in curve modeling and image segmentation or in biometrics for feature extraction. The numerical verification of asymptotic orders

α

(

λ

) in trajectory estimation by modified complete spline interpolation is performed here for regular curves sampled more-or-less uniformly with the missing knots parameterized according to exponential parameterization. Our approach is equally applicable to either sparse or dense data. The numerical experiments confirm a slow linear convergence orders

α

(

λ

) = 1 holding for all

λε

[0, 1) and a quartic one

α

(1) = 4 once modified complete spline is used. The paper closes with an example of medical image segmentation.

Ryszard Kozera, Lyle Noakes, Magdalena Wilkołazka

Chaotic Properties of Gait Kinematic Data

Time delay reconstruction for real systems is a widely explored area of nonlinear time series analysis. However, the majority of related work relates only to univariate time series, while multivariate time series data are common too. One such example is human gait kinematic data. The main goal of this article is to present a method of nonlinear analysis for kinematic time series. This nonlinear analysis is designed for detection of chaotic behavior. The presented approach also allows for the largest Lyapunov’s exponent estimation for kinematic time series. This factor helps in judging the stability of the examined system and its chaotic properties.

Michal Piorek

Comparison of ASIM Traffic Profile Detectors and Floating Car Data During Traffic Incidents

Intelligent Transportation Systems are highly dependent on the quality and quantity of road traffic data. The complexity of input data is often crucial for effectiveness and sufficient reliability of such systems. Recent days, the fusion of various data sources is the topic which attracts attention of several researchers. The algorithms for data fusion take benefit of the advantages and disadvantages of each technology, resulting in an optimal solution for traffic management problems. The paper is focused on finding relations between two main data sources, floating car data and ASIM traffic profile detectors. Time series of speed and other information obtained from these data sources were analysed by Granger causality with intention to use both data sources efficiently for traffic monitoring and control during traffic incidents.

Lukáš Rapant, Kateřina Slaninová, Jan Martinovič, Marek Ščerba, Martin Hájek

Verification of ArchiMate Behavioral Elements by Model Checking

In this paper we investigate the problem of verification of business processes specified with ArchiMate language. The proposed solution employs model checking techniques. As a verification platform the state of the art symbolic model checker NuSMV is used.We describe a method of fully automated translation of behavioral elements embedded in ArchiMate models into a representation in NuSMV language, which is then submitted to verification with respect to requirements expressed in CTL. The requirements specification can be entered by user, but we also propose to derive some of them automatically, based on analysis of control flows within business processes. The solution was implemented as a plugin to Archi, a popular ArchiMate modeling tool. Application of the method is presented on an example of a small business process.

Piotr Szwed

Time-Dependent Route Planning for the Highways in the Czech Republic

This paper presents an algorithm for dynamic travel time computation along Czech Republic highways. The dynamism is represented by speed profiles used for computation of travel times at specified time. These speed profiles have not only the information about an optimal speed, but also a probability of this optimal speed and the probability of the speed which represents the possibility of traffic incident occurrence. Thus, the paper is focused on the analysis of paths with the uncertainty created by traffic incidents. The result of the algorithm is the probability distribution of travel times on a selected path. Based on these results, it is possible to plan a departure time with the best mean travel time for routes along the Czech Republic highways for a specified maximal acceptable travel time. This method will be a part of a larger algorithm for dynamic traffic routing.

Radek Tomis, Jan Martinovič, Kateřina Slaninová, Lukáš Rapant, Ivo Vondrák

Self Organizing Maps with Delay Actualization

The paper deals with the Self Organizing Maps (SOM). The SOM is a standard tool for clustering and visualization of highdimensional data. The learning phase of SOM is time-consuming especially for large datasets. There are two main bottleneck in the learning phase of SOM: finding of a winner of competitive learning process and updating of neurons’ weights. The paper is focused on the second problem. There are two extremal update strategies. Using the first strategy, all necessary updates are done immediately after processing one input vector. The other extremal choice is used in Batch SOM - updates are processed at the end of whole epoch. In this paper we study update strategies between these two extremal strategies. Learning of the SOM with delay updates are proposed in the paper. Proposed strategies are also experimentally evaluated.

Lukáš Vojáček, Pavla Dráždilová, Jiří Dvorský

Biometrics and Biometrics Applications

Frontmatter

Person Identification Technique Using RGB Based Dental Images

Dental signature captures information about teeth, including tooth contours, relative positions of neighboring teeth, and shapes of the dental work. However, this is complicated as dental features change with time. In this paper, we proposed a new, safe and low cost dental biometric technique based on RGB images. It uses three phases: image acquisition with noise removal, segmentation and feature extraction. The key issue that makes our approach distinct is that the features are extracted mainly from incisor teeth only. Thus the proposed solution is low cost besides being safe for human.

Soma Datta, Nabendu Chaki

A Novel Double Fault Diagnosis and Detection Technique in Digital Microfluidic Biochips

This paper presents a rigorous offline double fault diagnosis as well as a detection technique for Digital Microfluidic Biochips (DMFBs). Due to the underlying mixed technology biochips exhibit unique failure mechanisms and defects. Thus, offline and online test mechanisms are required to certify the dependability of the system. In this paper, the proposed algorithm detects double faults anywhere in the chip satisfying the dynamic fluidic constraints and improves the fault diagnosis time to an extent.

Sagarika Chowdhury, Rajat Kumar Pal, Goutam Saha

Biometric Swiping on Touchscreens

Touchscreen devices have become very popular in the last decade and eased our modern life. It is now possible to automatically log in to any web page connected to our touchscreen phones, such as social networks, e-commerce sites and even mobile banking. Given these facts, the emerging touchscreen technology brings out a potential security issue: weakness of authentication protocols. Therefore, we put forward a biometric enhancement on “swiping” authentication, which is one of the options to log in a touchscreen phone however with the lowest security. We created a ghost password by extracting the features of coordinates and swipe durations to use them as the inputs of the Levenberg-Marquardt based neural network and adaptive neuro-fuzzy classifiers which both discriminate real attempts from fraud attacks after training.

Orcan Alpar, Ondrej Krejcar

Simple Displaying Method for Genealogy with Assisted Reproductive Technologies

In this research, a new layout style, ‘Nodes of Effects and/or Way through for TYing Particular Elements (NeWTYPe)’, for displaying genealogy with assisted reproductive technologies (ART) that include a sperm/ovum donor and/or a surrogate mother using our WHIteBasE method is proposed. The NeWTYPe is a node with symbols; ‘Arrow’, ‘Pipe’, and ‘Arrow and Pipe’. Using the NeWTYPe, complex relations of the ART can be understood easily. Note that previous WHIteBasE method has perfectly been able to integrate each relation that includes a married couple and their children, and has been able to display complex relations with segment intersections and various layout styles easily, and also, our JaBBRoW method for abbreviating some jointed relations on the WHIteBasE has been proposed. As a result, displaying both regular complex genealogy and the ART can be realized simultaneously. Our improved software that can display the NeWTYPe automatically and seamlessly by only mouse operations is presented.

Seiji Sugiyama, Daisuke Yokozawa, Atsushi Ikuta, Satoshi Hiratsuka, Miyuki Shibata, Tohru Matsuura

Data Analysis and Information Retrieval

Frontmatter

U-Stroke Pattern Modeling for End User Identity Verification Through Ubiquitous Input Device

Identity verification on ubiquitous input devices is a major concern to validate end-users, because of mobility of the devices. User device interaction (UDI) is capable to capture end-users’ behavioral nature from their device usage pattern. The primary goal of this paper is to collect heterogeneous parameters of usage patterns from any device and build personal profile with good-recognition capability. This work mainly focuses on finding multiple features captured from the usage of smart devices; so that parameters could be used to compose hybrid profile to verify end- users accurately. In this paper, U-Stroke modeling is proposed to capture behavioral data mainly from smart input devices in ubiquitous environment. In addition to this, concept of CCDA (capture, checking, decision, and action) model is proposed to process U-Stroke data efficiently to verify enduser’s identity. This proposal can draw attention of many researchers working on this domain to extend their research towards this direction.

Tapalina Bhattasali, Nabendu Chaki, Khalid Saeed, Rituparna Chaki

A Geometrical Approach to Rejecting Option in Pattern Recognition Problem

Frequently it happens that during symbols recognition, not all of them are the proper ones. This may cause deterioration of a classifying process. In this paper we present a way to “separate the wheat from the chaff”, by constructing a rejector, based on geometrical figures enclosing “wheat” and excluding “chaff”. We assume that entities of wheat, called native elements, are structured in some way and that there is no a priori knowledge about chaff, named foreign symbols. For the purpose of this study we present simple geometrical figures to generalize the distribution of symbols and to govern the rejection process.

Jakub Ciecierski, Bartomiej Dybisz, Agnieszka Jastrzebska, Witold Pedrycz

Identification Effectiveness of the Shape Recognition Method Based on Sonar

Sonars are among the most popular navigation elements used in autonomous vehicles. Beside their well known properties, they have unexplored specifics offering interesting information. In this paper, we present the results of an experiment with the drawbacks of sonars. Our approach combined the regular information obtained from a sonar system with information deriving from measurement aberration. The experiments with an ultrasonic range measurement system of a mobile robot showed that the usually neglected sonar drawbacks could be unusually helpful. This paper emphasizes the effectiveness of identification, which was calculated based on the ratio of the quantities of parallelepipeds to cylinders. The experimental results are presented. Further work aims to implement this idea on a robot on an HCR base. Another possibility is also suitable implementation of map building with a relative degree of confidence.

Teodora Dimitrova-Grekow, Marcin Jarczewski

MRI Texture Analysis for Differentiation Between Healthy and Golden Retriever Muscular Dystrophy Dogs at Different Phases of Disease Evolution

In this study, a texture analysis is applied to T2-weighted Magnetic Resonance Images (MRI) of canine pelvic limbs in order to differentiate between Golden Retriever Muscular Dystrophy (GRMD) dogs and healthy ones. The differentiation is performed at three phases of canine growth and/or disease development: 2-4 months (the first phase), 5-6 months (the second phase), and 7 months and more (the third phase). Eight feature extraction methods (statistical, model-based, and filter-based) and five classifiers are tested. Four types of muscles are analyzed: the

Extensor Digitorum Longus

(EDL), the

Gastrocnemius Lateralis

(GasLat), the

Gastrocnemius Medialis

(GasMed) and the

Tibial Cranialis

(TC). The experiments were performed on five healthy and five GRMDdogs. Each of themuscles was considered separately. The best classification results were 95.81% (the EDL muscle), 97.19% (GasLat), and 91.37% (EDL) correctly recognized cases, for the first, second and third phase, respectively. These results were obtained with an SVM classifier.

Dorota Duda, Marek Kretowski, Noura Azzabou, Jacques D. de Certaines

Policy-Based Slicing of Hibernate Query Language

This paper introduces a policy-based slicing of Hibernate Query Language (HQL) based on a refined notion of dependence graph. The policies are defined on persistent objects, rather than transient objects, which are stored in an underlying database. We extend the Class Dependence Graph (ClDG) of object-oriented languages to the case of HQL, and we refine it by applying semantics-based Abstract Interpretation framework. This leads to a slicing refinement of HQL programs, producing more precise slices

w.r.t.

policies and we refine by using semantics equivalence, according to the Abstract Interpretation framework.

Angshuman Jana, Raju Halder, Nabendu Chaki, Agostino Cortesi

Uncovering Document Fraud in Maritime Freight Transport Based on Probabilistic Classification

Deficient visibility in global supply chains causes significant risks for the customs brokerage practices of freight forwarders. One of the risks that freight forwarders face is that shipping documentation might contain document fraud and is used to declare a shipment. Traditional risk controls are ineffective in this regard since the creation of shipping documentation is uncontrollable by freight forwarders. In this paper, we propose a data mining approach that freight forwarders can use to detect document fraud from supply chain data. More specifically, we learn models that predict the presence of goods on an import declaration based on other declared goods and the trajectory of the shipment. Decision rules are used to produce miscoding alerts and smuggling alerts. Experimental tests show that our approach outperforms the traditional audit strategy in which random declarations are selected for further investigation.

Ron Triepels, Ad Feelders, Hennie Daniels

Modelling and Optimization

Frontmatter

Telerobotic Surgery: Fuzzy Path Planning Control for a Telerobotic Assistant Surgery

A strategy of path planning with fuzzy logic for a telerobotic assistant surgery is presented in this paper. Telerobotic surgery occurred a long track in its short history. While teleconsultation proceeds to be used today, the advent of high speed communications and increased computational competence is making long distance remote control of operating instruments, called telepresence surgery, a reality. Based on laparoscopic technology, telerobotic surgery was tested first on animals and, more recently, on humans with success. The technology offers several advantages, including improved accuracy and the capability to bring difficult procedures to rural and remote locations where trained surgeons are not available. A dynamic model is computed first for the telerobots using Lagrange formulation. A fuzzy control strategy is used in order to validate the path planning method and the theoretical developments in motion constraints analysis. The paper is ended with a conclusion.

Rahma Boucetta

A Model for an Aggression Discovery Through Person Online Behavior

Reports on aggression acts are quite often in modern community. Its bigger part actively uses Internet resources. The paper considers a hypothesis on a presence of the relationship between real world aggressive behavior and behavior in Internet. The presented model assumes a conduction of aggression tests and monitoring web user online behavior. Gathered data serves as a training data set required for machine learning, which will let to classify an aggression through a person online behavior.

Germanas Budnikas

Modeling On-demand Transit Transportation System Using an Agent-Based Approach

We consider the real-time routing of driverless vehicles in an on-demand transit transportation system with time window. Because fast dispatching decisions are required, decentralized decisions system are generally used in these contexts. For that purpose, we introduce a new multi agent-based simulation model where intelligent vehicle agents determine their specific routes and which transportation requests to serve. They interact with passengers, who strive for minimum waiting time. Our approach offers several advantages: it is fast, make it easy for vehicles to determine their specific routes and needs little information for vehicles. We propose also a specific algorithm for the independent vehicles’agent in order to determine their specific routes. Preliminaries computational tests of our multi-agent model and our developed algorithm prove that our approach is very promising.

Olfa Chebbi, Jouhaina Chaouachi

Optimal Fleet Sizing of Personal Rapid Transit System

In this paper, we address the problem of determining the optimal fleet size for Personal Rapid Transit system (PRT). In our problem, we consider electric battery and distance constraints which are found in real world application of the PRT system. To tackle this problem, we propose two valid mathematical formulations that are able to find optimal fleet size. Extensive computational experiments show that the edge based formulation performs impressively well, in terms of solution quality and computational time in comparison to the node based formulation.

Olfa Chebbi, Jouhaina Chaouachi

Viability of Implementing Smart Mobility Tool in the Case of Tunis City

Nowadays, different changes from the economical, societal and environmental contexts are happen in cities. In fact, cities are generally the best place to endorse and enhance various experience in order to improve the quality of life of its citizens. In this context, the new vision of Smart Mobility fill into this context. The concept of Smart Mobility as a means to enhance the mobility experience of citizen has been gaining increasing importance in the agendas of cities stakeholder. It represents the best balance the economic, environmental and societal aspect of current transportation tools. The implementation of the smart mobility concept in the case of Tunis city is the subject matter of the paper. In fact, we focus on considering the Personal Rapid Transit system as an effective and efficient tool to bring smart mobility experience to Tunis city. This paper also presents and study the viability of implementing PRT in our specific context. An extensive simulation and economic feasibility study is conducted to validate our proposal. Computational results prove the different advantages of our proposal in the studied context.

Ezzeddine Fatnassi, Olfa Chebbi, Jouhaina Chaouachi

Optimal Input Signal Design for a Second Order Dynamic System Identification Subject to D-Efficiency Constraints

System identification, in practice, is carried out by perturbing processes or plants under operation. That is why in many industrial applications an optimal input signal would be preferred for system identification. In this case, the objective function was formulated through maximisation of the Fisher information matrix determinant (D-optimality) expressed in conventional Bolza form. As setting such conditions of the identification experiment we can only say about the D-suboptimality, we quantify the plant trajectories using the Defficiency measure. An additional constraint, imposed on D-efficiency of the solution, should allow to attain the most adequate contents of information from the plant which operating point is perturbed in the least invasive way. A simple numerical example, which clearly demonstrates the idea presented in the paper, is included and discussed.

Wiktor Jakowluk

Modelling Human Cognitive Processes

Unipolar Vs Bipolar Uncertainty

The article presents an application of fuzzy sets with triangular norms and balanced fuzzy sets with balanced norms to decision making modelling. We elaborate on a vector-based method for decision problem representation, where each element of a vector corresponds to an argument analysed by a decision maker. Vectors gather information that influence given decision making task. Decision is an outcome of aggregation of information gathered in such vectors. We have capitalized on an inherent ability of balanced norms to aggregate positive and negative premises of different intensity. We have contrasted properties of a bipolar model with a unipolar model based on triangular norms and fuzzy sets. Secondly, we have proposed several aggregation schemes that illustrate different real-life decision making situations. We have shown suitability of the proposed model to represent complex and biased decision making cases.

Agnieszka Jastrzebska, Wojciech Lesinski, Mariusz Rybnik

Experiments on Minimization Method of Incompletely Specified Finite State Machines for Low Power Design

This paper presents a heuristic method for minimization of incompletely specified finite state machine with unspecified values of output variables. The proposed method is based on two states merging. In this method, such optimization criteria as the power consumption and possibility of merging other states are taken into account already at the stage of minimizing internal states. In addition to reduction of the finite state machine (FSM) states, the method also allows reducing the number of FSM transitions and FSM input variables. Experimental results for various styles of state assignment are presented. The results show that this approach to minimization of FSM in most of cases is more effective than classical methods in respect of power consumption.

Adam Klimowicz, Valery Solov’ev

Designing of Hierarchical Structures for Binary Comparators on FPGA/SoC

The article considers the general synthesis technique of hierarchical tree structures on FPGA/SoC for binary comparators. Designing of first level comparators is given. The best hierarchical comparator structure for the specific FPGA/SoC family is found empirically by experimental researches. The offered method allows reducing an area from 5.3% to 43.0%, and for high bitwidth comparators (with an input word length 1024) by 2.225 times. In the conclusion additional opportunities of the offered method are marked, and main directions of further researches are presented.

Valery Salauyou, Marek Gruszewski

Pattern Recognition and Image Processing

Frontmatter

Registration and Sequencing of Vessels Section Images at Macroscopic Levels

In this paper we present a new approach to registration and sequencing of microscope images obtained from serial sections of large blood vessels at macroscopic levels of magnification. It is assumed that subsequent section images may be located inadequately in the image series. Translations and rotations of the object of interest can occur. Some images can be also reflected vertically or horizontally. The proposed algorithm is based on the center of gravity estimation and the phase-only correlation (POC) and uses standard image normalization as a preprocessing procedure. The method is fully-automatic and robust to common image distortions. The quality of registration is measured by the mean value of the sum of absolute difference between images. This criterion can be used also for slide images sequencing, when the image acquisition is performed independently for each section. A set of experiments, carried out using sampled microscopic images of a vein section, proves experimentally the effectiveness of the proposed approach.

Aneta Górniak, Ewa Skubalska-Rafajłowicz

Comprehensive Performance Evaluation of Various Feature Extraction Methods for OCR Purposes

Optical Character Recognition (OCR) is a very extensive branch of pattern recognition. The existence of super effective software designed for omnifont text recognition, capable of handling multiple languages, creates an impression that all problems in this field have already been solved. Indeed, focus of research in the OCR domain has constantly been shifting from offline, typewritten, Latin character recognition towards Asiatic alphabets, handwritten scripts and online process. Still, however, it is difficult to come across an elaboration which would not only cover the topic of numerous feature extraction methods for printed, Latin derived, isolated characters conceptually, but which would also attempt to implement, compare and optimize them in an experimental way. This paper aims at closing this gap by thoroughly examining the performance of several statistical methods with respect to their recognition rate and time efficiency.

Dawid Sas, Khalid Saeed

Lagrange Piecewise-Quadratic Interpolation Based on Planar Unordered Reduced Data

This paper discusses the problem of fitting non-parametric unordered reduced data (i.e. a collection of interpolation points) with piecewise-quadratic interpolation to estimate an unknown curve

γ

in Euclidean space

E

2

. The term reduced data stands for the situation in which the corresponding interpolation knots are unavailable. The construction of ordering algorithm based on

e-graph of points

(i.e. a complete weighted graph using euclidean distances between points as respective weights) is introduced and tested here. The unordered set of input points is transformed into an ordered one upon using a minimal spanning tree (applicable for open curves). Once the order on points is imposed a piecewise-quadratic interpolation

$\hat{\gamma}2$

combined with the socalled

cumulative chords

is used to fit unordered reduced data. The entire scheme is tested initially on sparse data. The experiments carried out for dense set of interpolation points and designed to test the asymptotics in

γ

approximation by

$\hat{\gamma}2$

result in numerically computed cubic convergence order. The latter coincides with already established asymptotics derived for

γ

estimation via piecewise-quadratic interpolation based on ordered reduced data and cumulative chords.

Ryszard Kozera, Piotr Szmielew

A Novel Phase-Based Approach to Tear Film Surface Quality Assessment Using Lateral Shearing Interferometry

Lateral shearing interferometry (LSI) can be used for assessing the properties of tear film. In particular, it has the capability of acquiring dynamic variations in tear film surface quality (TFSQ) during an interblink interval in an

in”-vivo

fashion. The purpose of this study was to assess the suitability of LSI based two”-dimensional (2”=D) phase estimation procedures in the analysis of tear film dynamics. The paper discusses the main difficulty in 2”=D phase estimation ”+ the problem of phase unwrapping, proposes a modification of one of the popular phase unwrapping algorithms, and suggests a set of phase parameters that could be exploited as LSI”-based TFSQ descriptors.

Piotr Szyperski, D. Robert Iskander

Various Aspects of Computer Security

Frontmatter

The Impact of the TPM Weights Distribution on Network Synchronization Time

Two neural networks with randomly chosen initial weights may achieve the same weight vectors in the process of their mutual learning. This phenomenon is called a network synchronization, and can be used in cryptography to establish the keys for further communication. The time required to achieve consistent weights of networks depends on the initial similarity and on the size of the network. In the previous work related to this topic the weights in TPM networks are randomly chosen and no detailed research on used distribution is performed. This paper compares the synchronization time obtained for the network weights randomly chosen from either the uniform distribution or from the Gaussian distribution with different values of standard deviation. The synchronization time of the network is examined here as a function of different numbers of inputs and of various weights belonging to the intervals with varying sizes. The standard deviation of Gaussian distribution is selected depending on this interval size in order to compare networks with different weights intervals, which also constitutes a new approach for selecting the distribution’s parameters. The results of all analyzed networks are shown as a percentage of the synchronization time of a network with weights drawn from uniform distribution. The weights drawn from the Gaussian distribution with decreasing standard deviation have shorter synchronization time especially for a relatively small network.

Michał Dolecki, Ryszard Kozera

Verification of Mutual Authentication Protocol for MobInfoSec System

This paper presents a detailed analysis of the mutual authentication protocol developed especially for the system MobInfoSec - for a mobile device to share and protect classified information. MobInfoSec uses fine-grained access rules described by general access structures. In this paper we describe the architecture and functioning of the system, and the requirements imposed on cryptographic authentication protocols, resulting from both: standards, the collection of good practices, as well as directly from the vision of the system. The article contains a description of the protocol’s parts and formal analysis of its security.

Olga Siedlecka-Lamch, Imed El Fray, Mirosław Kurkowski, Jerzy Pejaś

AQoPA: Automated Quality of Protection Analysis Framework for Complex Systems

Analysis of security economics for the IT systems is one of the important issues to be solved. The quality of protection (QoP) of IT System can be achieved on different levels. One can choose factors which have a different impact on the overall system security. Traditionally, security engineers configure IT systems with the strongest possible security mechanisms. Unfortunately, the strongest protection (especially in low resource devices) can lead to unreasoned increase of the system load and finally influence system availability. In such a situation the quality of protection models which scales the protection level depending on the specific requirements can be used. One of the most challenging issues for quality of protection models is performing quality of protection evaluation for complex and distributed systems. The manual analysis of such systems is almost impossible to perform. In the article, we proposed the Automated Quality of Protection Analysis framework (AQoPA). The AQoPA performs the automatic evaluation of complex system models which are created in the Quality of Protection Modelling Language (QoP-ML). In the article the case study of complex wireless sensor network analysis is presented. The network is deployed on a roller-coaster.

Damian Rusinek, Bogdan Ksiezopolski, Adam Wierzbicki

ICBAKE 2015 Workshop

Frontmatter

Text Data Mining of English Interviews

An “interview” is the technique to gain the particular data effectively which the interviewers want to know through the conversation. In this paper, we metrically analyzed some English interviews:

Larry King Live on CNN

, and compared these with English news (

CNN Live Today

) and the inaugural addresses of the three U.S. Presidents. In short, frequency characteristics of character- and word-appearance were investigated using a program written in C++. These characteristics were approximated by an exponential function. Furthermore, we calculated the percentage of American basic vocabulary to obtain the difficulty-level as well as the

K

-characteristic of each material.

Hiromi Ban, Haruhiko Kimura, Takashi Oyabu, Jun Minagawa

Relationship of Terror Feelings and Physiological Response During Watching Horror Movie

Movie is one of the most popular media types. Horror movie is a kind of attractive movie contents which part of people want to watch very much. Although the users feel terror of the contents, the users want to watch the horror movies to have extraordinary feelings such as excitements. Therefore, terror feelings of the horror movies are considered as an important factor to establish more attractive movie contents, and the effect of horror movie is highly believed. However, few previous studies have investigated a relationship of horror movie and its terror feelings. This study aims to investigate psychophysiological effects of horror movies on the user for clarifying the relationship. In the experiment, physiological data (electrocardiogram and respiration, and skin conductance) of ten male subjects were measured. Additionally, after watching movie contents, the experimenter asked the subjects points in movie affecting terror feelings on the subjects and how the subjects felt in these points. The experimental results shows that change in intensity and cycle of respiration: in the point affecting terror feelings on the subject, the intensity of respiration was augmented and the cycle of respiration was shortened.

Makoto Fukumoto, Yuuki Tsukino

Estimation of User’s Attention and Awareness in Occlusion-Rich Environments Using RGB-D Cameras

Objective recognition by systems often does not agree with subjective recognition by users. Therefore, it is an important to estimate users’ subjective states appropriately. Especially, in occlusion-rich environments, information on what a user can/cannot see, what he/she pays attention to, and what he/she is aware of or not in the environments is one of important clues to estimate his/her subjective states and predict next actions. In this paper, we propose a system for estimating maps of a user’s attention and awareness in such environments based on the view estimation system using RGB-D cameras. The proposed system can estimate what the user sees, what he/she pays attention to, and what he/she is aware of in environments in pixels of captured images. Experimental results in a real environments show effectiveness of the proposed system. Furthermore, we discuss an extension of the proposed system to estimation for multiple users.

Jun-ichi Imai, Masanori Nemoto

Factors to Affect Descriptions on Intra-Concept Relation in Introductory Concept Mapping

Introductory Concept mapping is a method that property of association task is introduced to Concept Mapping. With a certain extent of freedom permitted to experiment participants for association, the method is advantageous in that motivation of participants to construct maps is enhanced higher than Concept Mapping. Experiment participants are supposed to write down concepts which are associated from the concept of developmental psychology around the word, “developmental psychology”, written on a white paper. In an examination of correlation coefficient based on this method using score of intra-concept relation explanation as a dependent variable and previous (existing) knowledge score, number of mean expressed concepts, number of bifurcated concepts, number of cross-links, and number of forward reactions as independent variables, significant positive correlation was observed with all independent variables except for the number of cross-links. In addition, only number of bifurcated concepts and previous knowledge score remained as reasonable independent variable by a multiregression analysis performed based on stepwise way.

Jun Minagawa, Hiromi Ban

Investigation of Comfort of Uniform Shirt Made of Cellulose Considering Environmental Load

The purpose of this study is to evaluate the wearing comfort of uniform- shirts and to investigate the suitable value for the preset temperature of air conditioners thorough measuring material properties and psychophysiological responses. The uniform shirt was made of cellulose materials such as rayon and tencel for wearing in hot conditions like summers in Japan. Material properties measurement were made according to Kawabata Evaluation System (KES), Japan Industrial Standards (JIS) and Moisture Management Tester (MMT). Physiological response measurements were electrocardiogram (ECG), respiration, skin temperature and the humidity inside the clothes. Psychological response measurements were by semantic differential method and ranking method. We concluded that the uniform shirts made of rayon are comfortable even in hot conditions like summer in Japan. 29°C as the temperature setting of air conditioners is too hot for people. Respiration seems to be an important factor for evaluation of wearing comfort.

Hideaki Mizuhashi, Masayoshi Kamijo, Hiroaki Yoshida, Harumi Tamaki

Usability Evaluation for Continuous Error of Fingerprint Identification

It is generally quite difficult to apply the current usability evaluation methods to the interface for the biometric identification, because the operation time of the biometric identification is too short to analyze. In the current study, we conducted the interview research on the biometrics. From the results of the interview research, it was clarified that 71% users have an experience of continuous error while in use of the biometric identification. So, we conducted the evaluation experiments for continuous error of the fingerprint identification. In the experiment, the unsatisfaction which is one of the usability is evaluated from the aspect of the mental stress during the continuous error of fingerprint identification. Based on the results of the evaluation experiment, we can show a guideline that when the continuous error occurs X times, the fingerprint identification system should be changed to another identification method to avoid an increase in the user’s unsatisfaction.

Nobuyuki Nishiuchi, Yuki Buniu

Study of Cancelable Biometrics in Security Improvement of Biometric Authentication System

Recently, there is a widespread use of biometric authentication systems. This is because biometric systems have become open and large scale and enrolment and authentication systems are separate. Many methods have been proposed for cancelable biometrics technology in biometric systems. However, the security criterion in such is indefinite in cancelable biometrics technology. Moreover, there is still no work on the systematic study of the safety of biometric authentication systems. In this paper, we consider the cancelable biometric techniques from the perspective of the safety of the system. In addition, we also verify the effect on the security precaution of the liveness detection techniques using Fault Tree Analysis, a risk evaluation method about data protection and spoofing prevention techniques.

Sanggyu Shin, Yoichi Seto

Estimating a Shooting Angle in Ear Recognition

To improve on our earlier work on single-view-based ear biometrics, an estimation method is presented for the shooting angle of an ear image based on the summation of similarity scores over a threshold within a database of known shooting angles. Experimental results indicate that the estimation method can improve the robustness of ear recognition in varied poses.

Daishi Watabe, Takanari Minamidani, Hideyasu Sai, Taiyo Maeda, Takaharu Yamazaki, Jianting Cao

Music Information Processing Workshop

Frontmatter

Mobile System for Optical Music Recognition and Music Sound Generation

The paper presents a mobile system for generating a melody based on a photo of a musical score. The client-server architecture was applied. The client role is designated to a mobile application responsible for taking a photo of a score, sending it to the server for further processing and playing mp3 file received from the server. The server role is to recognize notes from the image, generate mp3 file and send it to the client application. The key element of the system is the program realizing the algorithm of notes recognition. It is based on the decision trees and characteristics of the individual symbols extracted from the image. The system is implemented in the Windows Phone 8 framework and uses a cloud operating system Microsoft Azure. It enables easy archivization of photos, recognized notes in the Music XML format and generated mp3 files. An easy transition to other mobile operating systems is possible as well as processing multiple music collections scans.

Julia Adamska, Mateusz Piecuch, Mateusz Podgórski, Piotr Walkiewicz, Ewa Lukasik

Audio Features Dedicated to the Detection of Four Basic Emotions

In this paper, we decided to study the effect of extracted audio features, using the analysis tool Essentia, on the quality of constructed music emotion detection classifiers. The research process included constructing training data, feature extraction, feature selection, and building classifiers. We selected features and found sets of features that were the most useful for detecting individual emotions. We examined the effect of low-level, rhythm and tonal features on the accuracy of the constructed classifiers. We built classifiers for different combinations of feature sets, which enabled distinguishing the most useful feature sets for individual emotions.

Jacek Grekow

AutoPRK - Automatic Drum Player

The paper presents the new solution of the robot playing percussion. There are two ideas of such robots: imitating a human body and realizing its function in an artificial way - without imitating a human. The presented solution belongs to the second group. It consists of 8 arms and two peripherials for control two pedals. Authors developed of entire construction of the robot and they write the software in Java for control the device.The sticks and pedals are excited with electromagnets controlled by the microcontroller ATmega328 on an Arduino board which interprete MIDI files. Authors declare full success of the project.

Filip Biedrzycki, Jakub Knast, Mariusz Nowak, Jakub Paszkowski

Optical Music Recognition: Standard and Cost-Sensitive Learning with Imbalanced Data

The article is focused on a particular aspect of classification, namely the issue of class imbalance. Imbalanced data adversely affects the recognition ability and requires proper classifier’s construction. In this work we present a case of music notation as an example of imbalanced data. Three classification algorithms - random forest, standard SVM and cost-sensitive SVM are described and tested. Feature selection based on random forest feature importance was used. Also, feature dimension reduction using PCA was studied.

Wojciech Lesinski, Agnieszka Jastrzebska

Emotion-Based Music Information Retrieval Using Lyrics

In this paper, we present a study on emotion-based music information retrieval using lyrics information. Listeners want to search the lyrics of music suitable for his/her emotion (impression of music), by using an information system from music libraries. As a solution of listeners’ needs, we have designed a system that retrieve the lyrics of music based on the emotion (or the impression) suitable for a listener’s feelings that the listener has selected, from 9 emotions and 9 impressions. We select the words, i.e. verb and adjective, from the bridge part of the lyrics of music that express emotion in lyrics by using natural language processing. We summarize the words into the representative words by using a dictionary of synonyms. We make a model that estimates a listener’s 9 emotion/impression of the representative words by using a machine learning method. And listeners want to understand why the recommended music by a system is suitable for his/her emotion/impression. Therefore, we select the representative words most related to a listeners emotion/impression and we use the selected words as the explanation of reason to a listener. We have made each model of emotion and impression for 9 subjects and have evaluated the accuracy of the model. We also have investigated the selected representative words related to emotion/impression.

Akihiro Ogino, Yuko Yamashita

Backmatter

Weitere Informationen

Premium Partner

    Bildnachweise