Skip to main content
main-content

Über dieses Buch

This book contains the contributions presented at the ninth international KES conference on Intelligent Interactive Multimedia: Systems and Services, which took place in Puerto de la Cruz, Tenerife, Spain, June 15-17, 2016. It contains 65 peer-reviewed book chapters that focus on issues ranging from intelligent image or video storage, retrieval, transmission and analysis to knowledge-based technologies, from advanced information technology architectures for video processing and transmission to advanced functionalities of information and knowledge-based services. We believe that this book will serve as a useful source of knowledge for both academia and industry, for all those faculty members, research scientists, scholars, Ph.D. students and practitioners, who are interested in fundamental and applied facets of intelligent interactive multimedia.

Inhaltsverzeichnis

Frontmatter

Analysis of Similarity Measurements in CBIR Using Clustered Tamura Features for Biomedical Images

Content based image retrieval (CBIR) is an important research topic in many applications, in particular in the biomedical field. In this domain, the CBIR has the aim of helping to improve the diagnosis, retrieving images of patients for which a diagnosis has already been made, similar to the current image. The main issue of CBIR is the selection of the visual contents (feature descriptors) of the images to be extracted for a correct image retrieval. The second issue is the choice of the similarity measurement to use to compare the feature descriptors of the query image to ones of the other images of the database. This paper focuses on a comparison among different similarity measurements in CBIR, with particular interest to a biomedical images database. The adopted technique for CBIR is based on clustered Tamura features. The selected similarity measurements are used both to evaluate the adopted technique for CBIR and to estimate the stability of the results. A comparison with some methods in literature has been carried out, showing the best results for the proposed technique.

Nadia Brancati, Francesco Camastra

2-Stripes Block-Circulant LDPC Codes for Single Bursts Correction

In this paper the low-density parity-check (LDPC) codes are considered applied to correction of error bursts. Errors grouping and forming of so-called bursts are typical effect in real communication and data storage systems, however, this effect is typically ignored, and the coding task is reduced to correction of independent errors, which makes the practical characteristics of coding systems worse comparing to possibly reachable. Nevertheless, LDPC codes are able to protect from burst errors as well as independent ones. The main result of the paper is dedicated to evaluation of maximum correctable burst length of Gilbert codes, which are the 2-stripes special case of LDPC block-permutation codes, the construction which is often used in modern practical applications and research.

Evgenii Krouk, Andrei Ovchinnikov

Data Dictionary Extraction for Robust Emergency Detection

In this work we aim at generating association rules starting from meteorological measurements from a set of heterogeneous sensors displaced in a region. To create rules starting from the statistical distribution of the data we adaptively extract dictionaries of values. We use these dictionaries to reduce the data dimensionality and represent the values in a symbolic form. This representation is driven by the set of values in the training set and is suitable for the extraction of rules with traditional methods. Furthermore we adopt the boosting technique to build strong classifiers out of simpler association rules: their use shows promising results with respect to their accuracy a sensible increase in performance.

Emanuele Cipolla, Filippo Vella

SmartCARE—An ICT Platform in the Domain of Stroke Pathology to Manage Rehabilitation Treatment and Telemonitoring at Home

This paper describes the SmartCARE ICT eco-system, which goal is to deliver advanced health collaboration services in the rehabilitation domain. The system provides a set of tools that enable the continuity of care at home to patients affected by stroke diseases. Moreover, by taking advantage of motion sensing-based serious games and virtual companions, the system can stimulate the patient at being more reactive both at neuro-motorial and neuro-cognitive levels.

Francesco Adinolfi, Giuseppe Caggianese, Luigi Gallo, Juan Grosso, Francesco Infarinato, Nazzareno Marchese, Patrizio Sale, Emiliano Spaltro

Optimal Design of IPsec-Based Mobile Virtual Private Networks for Secure Transfer of Multimedia Data

Optimal design of IPsec-based mobile virtual private networks (MVPN) for a secure transfer of multimedia data, in general case, depends on multiple factors and parameters such as to-be-selected MVPN’s architectural model, hardware and software setups and technical platform’s solutions, network topology models, modes of tunnel’s operation, levels of the Open Systems Interconnection (OSI) model, encryption/decryption algorithms, modes of cipher operation, security protocols, security associations and key management techniques, connectivity modes, parameters of security algorithms, computer architectures, number of tunnels in MVPN, and other factors. This paper presents the outcomes of research project on multi-objective optimization of IPsec mobile virtual private network design based on non-isomorphic groups of order 4—Cayley Tables—for three major MVPN factors: (1) level of data transfer security provided by MVPN, (2) MVPN performance and (3) cost of designed virtual private network.

Alexander V. Uskov, Natalia A. Serdyukova, Vladimir I. Serdyukov, Adam Byerly, Colleen Heinemann

Malicious Event Detecting in Twitter Communities

Social networking services gain more often interest for research goals in several fields and applications. The number of active users of social networking services like Twitter raised up to 320 million per month in 2015. The rich knowledge that has accumulated in the social sites enables to catch the reflection of real world events. In this work we present a general framework for event detection from Twitter. The framework implements techniques that can be exploited for malicious event detection in Twitter communities.

Flora Amato, Giovanni Cozzolino, Antonino Mazzeo, Sara Romano

Adopting Decision Tree Based Policy Enforcement Mechanism to Protect Reconfigurable Devices

The Field Programmable Gate Array technology invaded the electronic market by offering economic advantages and many attractive features, such as the possibility to dynamically reprogram the hardware configuration in field. However, FPGA devices are not free of secure drawbacks, which include the possibility of install third-party components which may damage the system on which they are hosted. In this paper, we devise a policy enforcement mechanism to monitor and control the access of a dynamically installed component and we design it by employing Decision Trees. We demonstrate, with a significant experimental setup conducted on a commercial device, namely the Xilinx Zynq-7020, the efficacy of the DT based policy enforcer.

Mario Barbareschi, Antonino Mazzeo, Salvatore Miranda

Arabic Named Entity Recognition—A Survey and Analysis

As Arabic digital data has been increasing in abundance; the need for processing this information is growing. Named entity recognition (NER) is an information extraction technique that is vital to the processes of natural language processing (NLP). The ambiguous characteristics of the Arabic language make tasks related to NER and NLP very challenging. In addition to that, work related to Arabic NER is rather limited and under-studied. In this study, we survey previous works and methodologies and provide an analysis and discussion on the feature sets used, evaluation tools and advantages and disadvantages of each technique.

Amal Dandashi, Jihad Al Jaam, Sebti Foufou

Exploitation of Web Resources Towards Increased Conversions and Effectiveness

The development of Internet technologies is impacting the need to increase their effectiveness in achieving commercial goals. Selecting the most appropriate parameters for their functioning is highly important particularly in the area of online marketing and e-commerce platforms. Moreover, the focus on system performance is observed in terms of conversions and direct responses leading to maximum results. The proposed approach targets the reduction of complexity in the decision-making process with a multistage factorial analysis that is applied to advance the performance of internet websites towards better conversions.

Jarosław Jankowski, Jarosław Wątróbski, Paweł Ziemba, Wojciech Sałabun

How to Manage Keys and Reconfiguration in WSNs Exploiting SRAM Based PUFs

A wide spectrum of security challenges were arose by Wireless Sensor Network (WSN) architectures and common security techniques used in traditional networks are impractical. In particular, being the sensor nodes often deployed in unattended areas, physical attacks are possible and have to be taken into account during the architecture design. Whenever an attacker enters in possession of a node, he/she can jeopardize the network by extracting cryptographic keys used for secure communication. Moreover, an attacker can also try to brute force the keys, hence they should be fully random and hard to guess. In this paper, we propose a novel solution based on generating keys from unique physical characteristics of a node integrated circuit without requiring additional hardware compared to common WSN node architectures. To this aim, we exploit the Static Random Access Memory based Physically Unclonable Functions and we show their applicability to the WSN by implementing a working prototype based on the STM32F4 microcontroller.

Domenico Amelino, Mario Barbareschi, Ermanno Battista, Antonino Mazzeo

Fast Salient Object Detection in Non-stationary Video Sequences Based on Spatial Saliency Maps

In recent years, a number of methods of salient object detection in images have been proposed in the field of computer vision. However, sometimes the shooting conditions are far from the ideal, and the unpredicted camera jitters significantly impair the quality of video sequences. In this paper, the salient objects are roughly detected from the keyframes of non-stationary video sequences with two main purposes. First, the removal of salient objects helps to estimate a motion in background more accurately. Second, a visibility of salient objects can be improved after stabilization of video sequence. In this sense, the fast generation of multi-feature approximate saliency map is required. Various fast techniques suitable to extract intensity, color, contrast, edge, angle, and symmetry features from the keyframes are discussed. Some of them are based on Gaussian pyramid decomposition. The Law’s 2D convolution kernels are applied for fast estimation of texture energy contrast and texture gradient contrast in particular. The experiments show the acceptable spatial saliency maps in order to obtain good background motion model of non-stationary video sequence.

Margarita Favorskaya, Vladimir Buryachenko

Global Motion Estimation Using Saliency Maps in Non-stationary Videos with Static Scenes

The global motion estimation is a cornerstone of successful video stabilization. In current research, the stabilization task of non-stationary video sequence with static scenes is solved using saliency maps and the trajectories of feature descriptors. First, the feature descriptors are built in keyframes with the removed regions of moving foreground objects, which are considered the salient objects. The tracking results of feature descriptors form the feature trajectories. Second, a distinctiveness of a short-term trajectory is evaluated by histogram approach. Third, a temporal coherence of a long-term trajectory is exploited to verify the global motion through a whole video sequence. In this research, the constant flow and the affine flow are considered. The proposed algorithm permits to increase the peak signal to noise ratio up 4–7 dB on the average comparing with conventional stabilization methods in video sequences with static scenes.

Margarita Favorskaya, Vladimir Buryachenko, Anastasia Tomilina

SVM-Based Cancer Grading from Histopathological Images Using Morphological and Topological Features of Glands and Nuclei

The paper puts forward a new data set comprising 357 histopathological image samples obtained from colon tissues and distinguished into four cancer grades. At the same time, it proposes an automatic methodology for extracting knowledge from these images and discriminating between the disease stages on its base. The approach identifies the glands and nuclei and uses morphological and topological features related to these components to generate 76 attributes that are further used for classification via support vector machines. The values of one parameter used for the identification of the nuclei are tuned and surprisingly good results are reached when overlapping nuclei are identified as singular objects.

Catalin Stoean, Ruxandra Stoean, Adrian Sandita, Daniela Ciobanu, Cristian Mesina, Corina Lavinia Gruia

On Preservation of Video Data When Transmitting in Systems that Use Open Networks

This paper considers the task of selection of an image processing method to be applied to frames of a video sequence to ensure the best quality at the receiving side of systems that use open networks. The basic definitions of masking and unmasking are provided. The advantages of the frame body pre-scaling method and the masking method based on the standard compression procedure using Hadamard-Mersenne quasi-orthogonal matrices are assessed.

Anton Vostrikov, Mikhail Sergeev, Nikolaj Solovjov

An Invariant Subcode of Linear Code

An invariant subcode of a linear block code under the permutation is introduced. The concept of invariant subcode has two types of applications. The first type is decoding of linear block codes given the group of symmetry. The second type is the attack the McEliece cryptosystem based on codes correcting errors. Several examples illustrating the concept are presented.

Sergei V. Fedorenko, Eugenii Krouk

Development Prospects of the Visual Data Compression Technologies and Advantages of New Approaches

The static image and video information compression algorithms development over the last 15–20 years, as well as standardized and non-standardized formats for data storage and transmission have been analyzed; the main factors affecting the further development of approaches that eliminate the redundancy of transmitted and stored visual information have been studied. The conclusion on the current prospects for the development of image compression technologies has been made. New approaches that use new low-level quasi-orthogonal matrices as transform operators have been defined. The advantages of such approaches opening new fundamentally different opportunities in the field of applied processing of digital visual information have been identified and presented.

Anton Vostrikov, Mikhail Sergeev

A Near-Far Resistant Preambleless Blind Receiver with Eigenbeams Applicable to Sensor Networks

BRAKE has been proposed as a preambleless blind receiver (PBR) applicable to spread spectrum (SS) signals. However, the performance is degraded under the near-far problem. In this paper, we propose an eigenbeam BRAKE, i.e., the combination of BRAKE with the pre-beamforming using the eigenvectors derived from the correlation matrix. This scheme is to avoid the performance degradation under the near-far problem. Although this combination is expected to be effective, a new algorithm for controlling BRAKE is required to make it work with eigenbeams. So this paper proposes the BRAKE control algorithm as well. The performance is verified through computer simulations.

Kuniaki Yano, Yukihiro Kamiya

A New Approach for Subsurface Wireless Sensor Networks

Subsurface wireless sensor network is a sensor network in which sensors are installed under water or soil. This is to monitor earthquakes or Tsunami, to secure a society against natural disasters. The subsurface wireless communication is not easy since the power mitigation of the signal is severe due to the water and soil. In addition, the battery capacity in the sensor node is very limited. In this paper, based on the spread spectrum (SS) which is robust against low signal-to-noise power ratio (SNR), we propose a new transmitter and receiver configurations achieving code division multiplexing (CDM) for the subsurface wireless sensor networks. The proposed method is advantageous in terms of the following points. First, it realizes CDM by using a single spreading code. Second, the receiver does not need the training sequence to adjust the multiple antenna for the SNR improvement. This is effective to reduce the battery consumption at the sensor node since it does not need to send the training sequence. The performance is verified through computer simulations.

Hikaru Koike, Yukihiro Kamiya

Implementation of Mobile Sensing Platform with a Tree Based Sensor Network

This paper develops a new mobile sensing platform employing a tree based sensor network. The mobile sensing platform consists of mobile sensor devices, relay devices, and a sink device. We assume that robots, UAVs, etc. carry a mobile sensor device to measure environment. Therefore, the mobile sensor device can be easily relocated and can perform sensing at any locations. The relay devices can construct a tree based route to the sink device. Functions of the relay devices are data collection from the mobile sensor devices and data forwarding to the sink device. They also implement our special routing protocol and a media access control mechanism to avoid interference of radio signals in a sensor network and to reduce power consumption. We have developed special software for wireless module System on Chip (SoC) for IEEE 802.15.4 because our research target is to design a feasible and reasonable sensor network system. The consumed power of the SoC is 15 mA in a transmission, 17 mA in a reception, and 6 $$\upmu $$μA in a sleep mode. Therefore, our mobile sensing platform can work with a solar cell and a Li-Po battery. The evaluation results show that our protocol can synchronize timing among relay devices, and can create a tree based route to a sink device. Additionally, they can find that mobile sensor devices can inform measured data to a sink device through relay devices.

Katsuhiro Naito, Shunsuke Tani, Daichi Takai

Prototype Implementation of Actuator Sensor Network for Agricultural Usages

Information technology (IT) agricultural systems for field observation and environmental control have attracted considerable attention. Recently, various kinds of dedicated devices for IT agricultural systems have been released for large-scale farmers. It is well known that introducing IT agricultural systems can enhance agricultural production. On the contrary, an initial cost of the system is quite expensive even if typical dedicated devices are introduced. Therefore, reducing an initial cost of the system is a big challenge to disseminate the IT agricultural systems among small and medium-sized farmers. This paper proposes a prototype of IT agricultural systems that can measure an environment and can control the environment according to the measured information. To mitigate the initial cost of the system, our prototype uses Arduino compatible boards that are one of well-known micro-computer boards for general purposes. Therefore, it has a flexibility for designing a hardware and a capability of software development on the Arduino integrated development environment. The proposed system consists of sensing and control devices, a gateway device, and a web service. The sensing and control devices have some sensors such as a temperature, humidity, and soil moisture sensors, and a control function of a water sprinkling. The web service provides a user interface to manage the information in the database system. Experimental results show that the developed prototype system can realize a periodic environmental monitoring and environmental control according to the measured information. Additionally, users can observe the environment visually through the web service.

Takuya Wada, Katsuhiro Naito

Development of Multi-hop Field Sensor Networks with Arduino Board

Wireless sensor networks have been focused to enhance agricultural production because environmental information is useful to estimate growing conditions of plants, diseases of plants etc. A density of sensors is also an important factor to obtain an accurate estimation. Therefore, a lot of sensors are required in a practical field sensing. In conventional systems, the number of sensors is limited due to a cost of an installation and management. Additionally, their devices typically use a single-hop communication. Hence, it is difficult to cover a larger area due to the limit of a communication distance. This paper proposes a wireless sensor network for agricultural usages. The proposed protocols for the wireless sensor network can work with a limited memory resource and CPU performance. Therefore, a developed system can employ Arduino micro-computer boards that have a limited hardware resource. Since a price of Arduino boards is usually inexpensive, it is easy to deploy a lot of sensors in a field to improve an accuracy of estimation. Additionally, our network supports multi-hop communication to extend a sensing area. It also supports a sleep operation at all nodes to mitigate consumed power even if typical multi-hop routing protocols do not support a sleep operation at relay nodes. Experimental results show that the developed sensor network can construct a multi-hop network by the proposed protocols, and work well on a resource constrained hardware.

Tomoya Ogawa, Katsuhiro Naito

Communication Simulator with Network Behavior Logging Function for Supporting Network Construction Exercise for Beginners

Interconnecting virtual machines realizes computer networks on ordinary personal computers. Such a technique enables each student instead of a group to construct networks in network exercises for beginners. In the exercises, students may ask teachers to judge the correctness/incorrectness of their networks and to support the debugging for their networks. The waiting time of students can be long because the number of teachers is less than the number of students. An effective solution to this problem is to develop a system that can judge whether students’ networks are correct and visualize the behavior of students’ networks as hints. Detail logs of network behavior are necessary for realizing such a system. Here, we propose a communication simulator to record network behavior in detail during request/response communications, which are the transmissions of request data (e.g., icmp echo request) and the corresponding response data (e.g., icmp echo reply).

Yuichiro Tateiwa, Naohisa Takahashi

A New Method to Apply BRAKE to Sensor Networks Aiming at Power Saving

Wireless sensor network is a powerful solution for improving the efficiency of agricultural industries. A main concern is the battery life of sensors. To reduce the power consumption of the sensors, we want to shorten the length of the signal as much as possible. BRAKE [7], a blind receiver for spread spectrum systems, is interesting to cope with this matter since it does not need preambles which are usually put at the head of packets for enabling the receiver to detect the packets and its timing. However, BRAKE is not suitable for sensor networks as it is, because BRAKE cannot work with short signals. In this paper, we propose a new simple method to apply BRAKE to the sensor networks. Computer simulations verify the drastic effect of the proposed method.

Minori Kinose, Yukihiro Kamiya

A Tool for Visualization of Meteorological Data Studied for Integration in a Multi Risk Management System

This paper presents a tool for visualization of meteorological data integrated in an application for management of a multi risk situation. As part of a much more complex and demanding visualization system, the tool was developed taking into account some constraints as the scarcity of screen space and processing power in the considered system. Due to these limitations the tool was developed as web application optimized for mobile devices and is capable to present time series data in a compact and effective visualization. The tool also can process the available data in order to detect exceptional events and to put them in the contest allowing a very fast visual analysis.

Emanuele Cipolla, Riccardo Rizzo, Dario Stabile, Filippo Vella

An Algorithm for Calculating Simple Evacuation Routes in Evacuation Guidance Systems

This paper proposes an algorithm for calculating simple evacuation routes in evacuation guidance systems. In order to ensure that evacuees move to the shelters safely in disaster situations, our algorithm produces the simple routes in which the minimum number of turns is included. Evacuees can move to the shelters by following simple routes with low risk of making a mistake. For calculating simple routes, a road network is transformed so that an edge in the road network is converted into a vertex and a vertex is converted into several edges. Experimental results show that the length of the produced simple routes is not so different from that of the shortest routes.

Koichi Asakura, Toyohide Watanabe

SkyCube-Tree Based Group-by Query Processing in OLAP Skyline Cubes

SkyCube-tree has been developed to realize efficient range query processing for Skyline Cube (SC). Apart from range queries, this paper demonstrates that SkyCube-tree can be made use of efficient group-by query processing, though it is originally designed to realize efficient range query processing. Since a group-by query for SC includes the entire dataset as its processing range, the query processing time is potentially large. From the experimental evaluation, the followings are clarified:The size of SkyCube-trees is sufficiently allowable, since it is at most 2.5 times as large as that of materialized view.The time of SkyCube-tree based sequential processing is nearly equal to that of materialized view based one, regardless of its dedication to range query processing.The time of SkyCube-tree based parallel processing is comparatively small and stable. Even though cell-granularity is over 80 $$\%$$%, its processing time is around 10 $$\%$$% of that of materialized view based one.

Hideki Sato, Takayuki Usami

Trends in Teaching/Learning Research Through Analysis of Conference Presentation Articles

Information Technology (IT) has been changing the procedural means/methods used in social activities, and this effect has influenced directly or indirectly the behaviors of human beings. Of course, in teaching/learning activities, this observation is nothing out of the ordinary. Currently, IT plays an important role in supporting the teaching and learning processes both effectively and effectually. In this paper, we investigate current research trends, examining various articles published in conferences so as to extract the features correlated with specific research interests and objectives. We discuss these research features on the basis of our “knowledge transfer scheme” learning principle.

Toyohide Watanabe

Motion Prediction for Ship-Based Autonomous Air Vehicle Operations

A ship operating in an open sea environment undergoes stochastic motions which make deployment and landing of UAVs and other vehicles on a ship difficult and potentially dangerous. There is always a delay between the decision to commit and the moment of actual launch or recovery. This paper presents an artificial neural network trained using singular value decomposition, genetic algorithm and conjugate gradient method for the real time prediction of ship motions. These predictions assist in determining the best moment of commitment to launch or to recover. Predictions generated using these algorithms allow improvements in safety as well reducing the number of missed or aborted attempts. It is shown that the artificial neural network produces excellent predictions and is able to predict the ship motion satisfactorily for up to 7 s ahead.

Ameer A Khan, Kaye E Marion, Cees Bil, Milan Simic

The Effect of Receding Horizon Pure Pursuit Control on Passenger Comfort in Autonomous Vehicles

Passengers in autonomous vehicles are prone to motion sickness. Receding horizon control of pure pursuit tracking algorithms has been shown to improve path tracking performance. In this paper we present a numerical study on the effect of the receding horizon pure pursuit controller on passenger comfort. Three standard cases at the different speeds are utilized to compare the effect of traditional and receding horizon pure pursuit control on passenger comfort. The results show improvements in passenger comfort at higher speeds using receding horizon control and that path continuity is more influential that optimal tracking control.

Mohamed Elbanhawi, Milan Simic, Reza Jazar

From Automotive to Autonomous: Time-Triggered Operating Systems

This paper presents an approach for application of time-triggered paradigm to the domain of autonomous systems. Autonomous systems are intensively used in areas, or situations, which could be dangerous to humans or which are remote and hardly accessible. In the case when an autonomous system is safety critical and should react to the environmental changes running within a very limited time frame, we deal with the same kind of problems as automotive and avionic systems: timing properties and their analysis become a crucial part of the system development. To analyse timing properties and to show the fault-tolerance of the communication, a predictable timing of the system is needed.

Maria Spichkova, Milan Simic, Heinz Schmidt

Active Suspension Investigation Using Physical Networks

Active suspension systems consist of mechanical, electrical, electronics and other subsystems. Different types of physical signals and forms of energy circulate between subsystems which make system design a challenging task. Various physical systems can be expressed using the same type of ordinary differential equations. This gives us a common platform for the complex systems’ design. Using physical networks’ approach modeling of an active suspension system is conducted and evaluated for various on road scenarios. Active suspension contributes to the ride comfort, safety, better and easier car control both by the human driver, or autonomous system.

Milan Simic

Automatic Generation of Trajectory Data Warehouse Schemas

A mobile object is a spatial object that changes the form and the location permanently over the time. Each displacement creates a trajectory that reflects the evolution of its position in space during a given time interval. It generates, then, a huge amount of trajectory data that are stored into trajectory data warehouse because it is the only tool that can analysis the historical trajectory data. In this work, we focus on the design of trajectory data warehouse schema and we propose automating this task to reduce human intervention since it is done manually and requires good knowledge of the domain. To achieve this goal, firstly, we automate the extraction of trajectory data mart schemas from a moving data base. Then, we merge them to get the trajectory data warehouse schema using a new schema integration methodology that is composed by schema matching and schema mapping.

Nouha Arfaoui, Jalel Akaichi

A Taxonomy of Support Vector Machine for Event Streams Classification

Radio Frequency Identification technologies have been widely used in various domain. They allowed experts to automatically record on-line data of everyday life at a rapid rate. Consequently, in order to extract knowledge, these data should be treated rigorously. Among these treatments, we cite the classification that is paramount. Generally, for this purpose several classification’ technologies exists. Particularly, Support Vector Machine has been applied to several domains to improve results efficiency. But, with the changes and the evolution of event streams and to support such changes, the SVM technique evolution is seen in many researches. The goal of this paper is to present an overview of different works related to SVM evolution, then we propose a comparative study between those works. As a result we obtain a taxonomy which shows in details support vector machine types and correlations between different types.

Hanen Bouali, Yasser Al Mashhour, Jalel Akaichi

Social Networks Security Policies

Social networks present useful tools for communication and information sharing. While these networks have a considerable impact on users daily life, security issues are various such as privacy defects, threats on publishing personal information, spammers and fraudsters. Consequently, motivated by privacy problems in particular the danger of sexual predators, we seek in this work to present a generic model for security policies that must be followed by social networks users based on sexual predators identification. In order to detect those distrustful users, we use text mining techniques to distinguish suspicious conversations using lexical and behavioral features classification. Experiments are conducted comparing between two machine learning algorithms: support vector machines (SVM) and Nave Bayes (NB).

Zeineb Dhouioui, Abdullah Ali Alqahtani, Jalel Akaichi

Recommending Multidimensional Spatial OLAP Queries

Huge volumes of data are stored in a spatial data warehouse. Stored data is explored and analyzed by different users. The users interrogate spatial data cube through Spatial OLAP queries which are generally misspoke, leading to non-pertinent results. Therefore, we propose in this paper a Spatial OLAP queries recommendation system based on the SOLAP server query log; that helps and guides users in their exploration. Compared to the users needs, the proposed queries return more relevant results.

Olfa Layouni, Fahad Alahmari, Jalel Akaichi

Modeling Moving Regions: Colorectal Cancer Case Study

Objects in space have to be represented in order to be stored and analyzed. The three basic abstractions of spatial moving objects are moving point, line or region. The first two abstractions are highly handled. However, moving regions have always been a challenge due to their unstable shape and movement. Researchers are not giving enough attention for managing and querying this particular type of spatial data in order to solve real world problems. Motivated by this fact, we present in this paper an overview on moving regions. We survey region’s modeling aspects. Then, we support our research by studying a biomedical case to highlight the importance of using moving regions. The case study illustrates the conceptual aspect of the movement of the colorectal cancer. We also use fuzzy logic thanks for its simplicity and its easy understanding. The combination offers an easier understanding for decision makers.

Marwa Massaâbi, Jalel Akaichi

A UML/MARTE Extension for Designing Energy Harvesting in Wireless Sensor Networks

Power supply is the major concern in the wireless sensor networks (WSNs) applications. Currently, the node lifetime is limited by a battery supply which is a short lifetime, unmanageable and uneconomical. Energy Harvesting was proposed as a promising alternative to power sensor nodes in many application fields. Several energy harvesting concepts are considered in WSNs systems such as solar, vibration, thermal, kinetic, acoustic noise, radio frequency (RF), biochemical and hybrid energy sources. The existing modeling design for the power supply section of sensor nodes is limited to the design of solar energy harvesting method which is mostly employed in outdoor applications with sufficient sun light. However, other energy harvesting concepts are potential ambient sources of energy which offer an enough amount of power for sensor nodes. In this paper, we propose a high level methodology based on UML/MARTE standard to model specifications of outlined energy harvesting devices in the WSNs. We define new packages extending the “HW_Harvesting” package which is extending the “HW_PowerSupply” package. A case study of a WSNs system regarding leak detection in water pipeline monitoring is used to evaluate the practical use of our proposal.

Raoudha Saida, Yessine Hadj Kacem, M. S. BenSaleh, Mohamed Abid

A Survey on Web Service Mining Using QoS and Recommendation Based on Multidimensional Approach

The process of web service mining intends to discover required services so as to provide the users with the services that are important and desired. While as the system that has been proposed has an important role in the recommendation of services to the users. Multiple techniques have been projected to execute the proposed actions, the collaborative filtering technique is mostly used for the recommended system here, we will describe different approaches which make use of collaborative filtering and also QOS, (a technical notation that is applied to the Web service mining). We will also discuss some methodologies of recommended system which use the multidimensional approach.

Ilhem Feddaoui, Faîçal Felhi, Imran Hassan Bergi, Jalel Akaichi

Mapping and Pocketing Techniques for Laser Marking of 2D Shapes on 3D Curved Surfaces

Laser marking has been used since the invention of lasers but it is only in the last decade that it started evolving into 3D surface marking. The problem of defining the toolpath for a 3 axis laser marking machine can seem to be the same as the definition of the toolpath for the CNC milling machines but this is not completely true. In the case of laser marking is not only the last pass that will affect surface finish but every pass made. This implies that to obtain the desired final effect on the material it is crucial to define different pocketing and filling patterns together with the laser parameters. Defining new patterns that meet the requirements for the laser marking on 3D curved surface is a non-trivial problem; the toolpaths, depending on the application, may need to have different properties such as constant distance or density between path lines, non-crossing of path lines or defined angle of intersection. When trying to mark non flat surfaces with 2D images or paths, in certain cases, distortion of the 2D space cannot be avoided. This paper will analyze different proposed techniques for mapping and marking 3D solids with a 3 axes, mirror based, laser marking CNC machine analyzing advantages and disadvantages of each one from the software development point of view.

Federico Devigili, Davide Lotto, Raffaele de Amicis

3DHOG for Geometric Similarity Measurement and Retrieval on Digital Cultural Heritage Archives

With projects such as CultLab3D, 3D Digital preservation of cultural heritage will become more affordable and with this, the number of 3D-models representing scanned artefacts will dramatically increase. However, once mass digitization is possible, the subsequent bottleneck to overcome is the annotation of cultural heritage artefacts with provenance data. Current annotation tools are mostly based on textual input, eventually being able to link an artefact to documents, pictures, videos and only some tools already support 3D models. Therefore, we envisage the need to aid curators by allowing for fast, web-based, semi-automatic, 3D-centered annotation of artefacts with metadata. In this paper we give an overview of various technologies we are currently developing to address this issue. On one hand we want to store 3D models with similarity descriptors which are applicable independently of different 3D model quality levels of the same artefact. The goal is to retrieve and suggest to the curator metadata of already annotated similar artefacts for a new artefact to be annotated, so he can eventually reuse and adapt it to the current case. In addition we describe our web-based, 3D-centered annotation tool with meta- and object repositories supporting various databases and ontologies such as CIDOC-CRM.

Reimar Tausch, Hendrik Schmedt, Pedro Santos, Martin Schröttner, Dieter W. Fellner

Computer Aided Process as 3D Data Provider in Footwear Industry

One of the new emerging of ubiquitous manufacturing is Mass Customization. The combination of 3D scanning systems with mathematical technique makes possible the development of CAD system which can help the selection of good footwear for a given customer. During the surface reconstruction process, a mesh is calculated from points cloud. This mesh may have holes corresponding to deficiencies in the original point data. Although these data are given in an arbitrary position and orientation in 3D space. Moreover, there is a need to mesh segmentation in order to shape retrieval form shoe last data base. Thus to apply sophisticated modeling operation on data set, substantial preprocessing is usually required. In this paper first, we describe an algorithm for filling hole. Then all of the models are aligned and at the end the models are segmented in order to use for further analysis.

Bita Ture Savadkoohi, Raffaele De Amicis

CoolTour: VR and AR Authoring Tool to Create Cultural Experiences

This paper presents a platform to create complex VR and AR cultural experiences in an easy way. Each experience is composed by steps that contain a virtual scene and that are connected among them via end-user interactions. The platform presents three pillars that allow the author to configure the experience: the authoring tool, the experiences server and a mobile app. A use case consisting in a treasure hunt in a city has been developed to validate the platform.

Nagore Barrena, Andrés Navarro, Sara García, David Oyarzun

Emotional Platform for Marketing Research

In order to face new social and mobile realities, Marketing has advanced towards the reinforcement of customers’ relationship based on understanding consumers’ behavior. Emotions, having such an important role in our lives, are a key aspect on this behavior and should be incorporated in its analysis. We present in this paper a platform based on Affective Computing technology that allows marketers to gain insights of consumers’ emotional response, facilitating them with a great tool to study and design their marketing strategy, and enabling the generation of better consumers’ experiences. In this paper, we describe the design and implementation of the platform, as well as the uses cases that will allow the validation of the platform.

Andres Navarro, Catherine Delevoye, David Oyarzun

Gamification as a Key Enabling Technology for Image Sensing and Content Tagging

The advent of mobile phone with a multi-megapixel camera and autouploaders has democratised photography. Taking pictures and acquiring annotations is no longer an expensive task as it used to be. Yet performing these tasks in a systematically way is still very cumbersome for most users. In this paper, we outline two game mechanics that can be exploited for the purpose of large-scale image sensing and content annotation. Our first mechanic allows for better control over when, how and where people should acquire images. The problem with existent image providers is that their services usually do not cover the entire area of interest, are inaccurate or very expensive. Our second mechanism aims at making the annotation of crowd-sourcing images more engaging. It leverage on large end-user communities to annotate images while avoiding the pitfall of using annotations that are meaningful only to domain experts. Annotations that are not relevant to users’ interests cannot be directly leveraged to enable search and discovery. A drawback of using crowdsourced annotations is that they have low agreement rates. Our approach aims at a finding a balanced agreement rate between pre-established annotations and those defined by users.

Bruno Simões, Raffaele De Amicis

Bridging Heritage and Tourist UX: A Socially-Driven Perspective

The paper illustrates the potential of smart-phones as a medium of exchange of memories and experiences. Our application aims at providing diverse types of cultural user experience: to enable tourists to explore new places from a social-driven perceptive; to support new forms of connection and interaction between users and information (data exchange, contents sharing, feedback); to compose interactive narrative conveying the richness of information of interest to the user; to allow users to experience the narrative and underlying physical environment as a mixed-reality experience while allowing for deeper, context-specific exploration at any time through AR system.

Paola La Scala, Bruno Simões, Raffaele De Amicis

A Personalised Recommender System for Tourists on City Trips: Concepts and Implementation

In this paper we introduce a new recommender system for urban tourists. The goal of the system is to enrich tourists’ experience by offering them personalised tour recommendations tailored to their dynamic user profiles. Particular attention in the proposed approach is paid to the influence of basic leisure needs of an individual, which include new experiences, entertainment, being in open area, relaxation, physical exercise, and socialising, on the tour composition. These needs tend to be dynamic and give rise to saturation effects and variety seeking behaviour. The system is developed as part of the larger c-Space framework, in which a number of technologies, such as projective augmented reality, a newly proposed near real-time 4D dynamic scene reconstruction, and affective computing, are brought together and used to enrich experiences of users in their interactions with built environments. The paper describes the main concepts of the recommender system and its implementation in the specified context of the city of Trento, Italy.

Petr Aksenov, Astrid Kemperman, Theo Arentze

Experience-Driven Framework for Technologically-Enhanced Environments: Key Challenges and Potential Solutions

Technologically-enhanced physical environments are gradually replacing a natural part of our working and living environments. Although their use in everyday life is still rare, there has been a good effort towards a better understanding of their implications in our society, and the type of user experiences that can be provided. In this paper, we discuss various issues related to user-centric designs of technologically-enhanced environments based on our results and previous literature. We ground our argument on the hypotheses that these environments are becoming an indispensable part of people’s daily lives. The integration of technologically-enhanced environments into the fabric of everyday life requires, therefore, to take into consideration a set of human experience dimensions (e.g. emotional, instrumental value, etc.) when shaping the interaction between people and the environment they live and act in. Understanding people expectations, the experience they seek in technologically-enhanced environments, and enabling them to easily influence and shape their self-crafted environments according to their needs and ever-changing expectations, in a trustworthy and controllable, can help us shape a more acceptable and meaningful vision of technologically-enhanced environments for all those living and acting in them.

Bruno Simões, Raffaele De Amicis

Touchless Disambiguation Techniques for Wearable Augmented Reality Systems

The paper concerns target disambiguation techniques in egocentric vision for wearable augmented reality systems. In particular, the paper focuses on two of the most commonly used selection techniques in immersive environments: Depth Ray and SQUAD. The design and implementation of such techniques in a touchless augmented reality interface, together with the results of a preliminary usability evaluation carried out with inexpert users, are discussed. The user study provides insights on users’ preferences when dealing with the precision-velocity trade-off in selection tasks, carried out in an augmented reality scenario.

Giuseppe Caggianese, Luigi Gallo, Pietro Neroni

System Architecture and Functions of Internet-Based Production of Tailor-Made Clothes

Smart spaces are currently developed for different kinds of applications. We want to describe a smart space for the production of tailor-made clothes. In the paper, we review the production process for tailor-made clothes. Then, we describe the architecture for the smart production space. We describe the advantages of such a model for different commercial services that can be linked to the online production process. We also describe the kind of sensors and the functions of the sensors that are connected online to each other. In addition the software is described that allows controlling the smart space. Finally, we summarize our work.

Petra Perner

Influence of Some Parameters on Visiting Style Classification in a Cultural Heritage Case Study

A smart system for a cultural exhibition, generally, has the ability to infer interests of users and to track the propagation of the information into the event. We are interested in analysing and studying the visiting styles of users in a real cultural heritage exhibition, named The Beauty or the Truth. Starting from data that was collected during this exhibition, the interaction between visitors and artworks and the influences of the available technology on their behaviours are studied. Finally, we analyse how the tuning of some parameters on a classification strategy influences the users’ visiting styles. The obtained results have revealed interesting issues also to understand hidden aspects in the data and unattended in the analysis.

Salvatore Cuomo, Pasquale De Michele, Ardelio Galletti, Giovanni Ponti

Opinions Analysis in Social Networks for Cultural Heritage Applications

Social media provide a great amount of valuable information in the form of messages posted by users. Information extracted from posts can be considered like features giving insights about the preferences of users towards certain events. These features can be used to generate recommendations looking forward for upcoming events they might find interesting. In this work we present system for opinion analysis from tweets and recommendation of cultural heritage events. At this aim, we detect the events of interest from Tweets and propose a methodology for associating a sentiment degree with a tweet using NLP techniques.

Flora Amato, Giovanni Cozzolino, Sergio Di Martino, Antonino Mazzeo, Vincenzo Moscato, Antonio Picariello, Sara Romano, Giancarlo Sperlí

A Forward-Selection Algorithm for SVM-Based Question Classification in Cognitive Systems

Cognitive Systems have attracted attention in last years, especially regarding high interactivity of Question Answering systems. In this context, Question Classification plays an important role for individuation of answer type. It involves the use of Natural Language Processing of the question, the extraction of a broad variety of features, and the use of machine learning algorithms to map features with a given taxonomy of question classes. In this work, a novel learning approach is proposed, based on the use of Support Vector Machines, for building a set of classifiers, each one to use for different questions and comprising the respective features, chosen through a particular forward-selection procedure. This approach aims at decreasing the total number of features, by avoiding those giving scarce information and/or noise. A Question Classification framework is implemented, comprising new sets of features with low numerosity. The application on a benchmark dataset shows classification accuracy competitive with the state-of-the-art, by considering a lower number of features.

Marco Pota, Massimo Esposito, Giuseppe De Pietro

Supporting Autonomy in Agent Oriented Methodologies

Designing a software solution for a complex systems is always a demanding task, it becomes much more complex if we consider to design a multi agent system where agents have to exhibit autonomy; which abstractions and which concepts to take into consideration when using a design methodology we would like to support autonomy? In this paper, we answer this question by studying and analyzing literature on the concept of agents in order to establish the basic set of concepts an agent oriented methodology has to deal with.

Valeria Seidita, Massimo Cossentino

A Data-Driven Approach to Dynamically Learn Focused Lexicons for Recognizing Emotions in Social Network Streams

Opinion Mining aims at identifying and classifying subjective information in a collection of documents. A variety of approach exists in literature, ranging from Supervised Learning to Unsupervised Learning. Currently, one of the biggest opinion resource of opinionated texts existing on the Web is represented by Social Networks. Networks are not only a vast collection of documents but they also represent a dynamic evolving resource as the users keep posting their own opinions. We based our work relying on this idea of dynamicity, building an evolving model that updates itself in real time as users submit their posts. This is done through a set of supervised techniques based on a Lexicon of emotionally-tagged terms (i.e. anger, disgust, fear, joy, sadness and surprise) that expands accordingly to user’s dynamic content.

Diego Frias, Giovanni Pilato

Disaster Prevention Virtual Advisors Through Soft Sensor Paradigm

In this paper we illustrate the architecture of an intelligent advisor agent aimed at limiting, or as far as possible preventing, the damages caused by catastrophic events, such as floods and landslides. The agent models the domain and makes forecasting by exploiting both ontology models and belief network models. Furthermore, it uses a monitoring network to recommend preventive measures and giving alerts, if necessary, before that the event happens. The monitoring network can be implemented through both physical and soft sensors: this choice makes the measurements more adequate and available also in case of failure of some of the physical sensors. The front-end of the agent is made by a chat-bot, capable to interact with human users using natural language.

Agnese Augello, Umberto Maniscalco, Giovanni Pilato, Filippo Vella

A Personal Intelligent Coach for Smart Embodied Learning Environments

Within a Smart Learning Environment (SLE) learners are involved in a new learning process tailored to create a continuum of education by extending the current educational formal settings to real-life informal learning context. The goal of this paper is to describe the Cognitive Architecture (CA) of a Personal Intelligent Coach able to manage learning tasks and interactions within a complex Smart Learning Environment (SLE). PICo has two possible embodiments: humanoid robot, and an avatar on mobile device. We argue that the proposed intelligent coach can adapt to the contents, to the students needs and can evolve its strategies according the learning process.

Agnese Augello, Ignazio Infantino, Adriano Manfré, Giovanni Pilato, Filippo Vella, Manuel Gentile, Giuseppe Città, Giulia Crifaci, Rossella Raso, Mario Allegra

A Model of a Social Chatbot

Traditional chatbots lack the capability to correctly manage conversations according to the social context. However a dialogue is a joint activity that must consider both individual and social processes. In this work we propose a model of a social chatbot able to choose the most suitable dialogue plans according to what in sociological literature is called a “social practice”. The proposed model is discussed considering a case study of a work in progress aimed at the development of a serious game for communicative skills learning.

Agnese Augello, Manuel Gentile, Lucas Weideveld, Frank Dignum

An Experience of Engineering of MAS for Smart Environments: Extension of ASPECS

This paper presents a methodological approach for the engineering of Smart Environments based upon Multi-Agent Systems. This approach is an extension of an existing MAS methodology, namely ASPECS. The extension of ASPECS is allowed by the Situational Method Engineering principles underlying ASPECS and takes the form of several existing modified activities and corresponding meta-model elements. The key elements that are targeted by the contribution are: the identification of goals hierarchy, the expression of detailed requirements and associations of goals to sensors/effectors, different levels of ontologies to describe on the one hand, the problem conceptualization, and, on the other hand, the several involved expertness. The remaining, existing activities, refine the models in order to identify organizational structures/behaviours and theirs agentification. The approach is illustrated through a case study that consists in a platform dedicated to the Monitoring of patients with heart failures.

Philippe Descamps, Vincent Hilaire, Olivier Lamotte, Sebastian Rodriguez

A Norm-Based Approach for Personalising Smart Environments

People have a great variety in their needs. There is a great demand for personalized services, especially those interacting with their environment. In this paper, we propose a norm based approach for personalizing smart environments that constraint user requirements by means of non functional requirements expressed in terms of permissions, obligations or prohibitions.

Patrizia Ribino, Carmelo Lodato, Antonella Cavaleri, Massimo Cossentino

Adopting a Middleware for Self-adaptation in the Development of a Smart Travel System

A smart travel system is a complex distributed system acting as a tour operator for organizing holiday packages and supporting travelers on-the-run. A couple of key characteristics of such a system are the ability of self-configuring a set of heterogeneous services and self-adapting to unexpected circumstances. This paper reports an experience of developing a smart travel system by adopting MUSA, a Middleware for User-driven Service Adaptation. The prototype supports users in organizing their time by the specification of goals: this triggers the automatic composition and dynamic orchestration of touristic services. The chosen middleware has played a fundamental role by simplifying the development process thus to speed up the time-to-complete.

L. Sabatucci, A. Cavaleri, M. Cossentino

Pentas: Using Satellites for Smart Sensing

Smart environments are an important field of study and have suffered from an important evolution in the last decade. Smart technology makes an intensive use of wireless technology as the way of communicating all the elements of the system, including sensors. This paper tries to show how the use of satellites and radio waves may provide smart characteristics to environments that lack the common wireless technologies usually utilized. A system using Agent Oriented Software Engineering and based on that technology has been constructed and shows the suitability and advantages of the proposal.

Lorena Otero-Cerdeira, Alma Gómez-Rodríguez, Francisco J. Rodríguez-Martínez, Juan Carlos González-Moreno, Arno Formella

A Multiple Data Stream Management Framework for Ambient Assisted Living Emulation

The development of Ambient Assisted Living systems would be facilitated if there was a development environment that allowed to simulate in a computer the physical environment, its inhabitants, as well as the Ambient Assisted Living system. This requires, on the one hand, an infrastructure for simulating the physical environment and, on the other hand, an infrastructure for emulating the Ambient Assisted Living devices. Both can be interconnected through data streams that allow emulated devices to behave as if they were connected to the real world, since they get similar sensor input. This paper introduces advances on a simulation framework for ambient intelligence so that it becomes capable of producing such data streams.

Jorge J. Gómez-Sanz, Pablo Campillo Sánchez

Soft Sensor Network for Environmental Monitoring

This paper shows the application of a soft sensor network for the detection of meteorological events. A set of hard (real) sensor are placed in a territory, where they measure heterogeneous quantities. Starting from their measurements, a soft sensor network provides useful information coming from the data. In this contribution we show how prediction and validation of data can be done through machine learning approach by collecting data from the historical series. Furthermore, we show how the cluster based on correlation analysis among the data achieved by the sensors can be sensibly different from the ones simply drawn on geographical distance.

Umberto Maniscalco, Giovanni Pilato, Filippo Vella

The Use of Eye Tracking (ET) in Targeting Sports: A Review of the Studies on Quiet Eye (QE)

The Quiet Eye (QE) consists in the final visual fixation before the initiation of a critical phase of the movement, and functionally represent the time needed for the precise control of movements. The aims of the manuscript is provide a mini-review of the studies analyzing through Eye Tracking (ET) the Quiet Eye phenomena in ecological sport settings in the last decade. Using Scopus database was performed a search (January 2005–December 2015) including a combination of “Eye Track*” with “Quiet Eye”, and with “Sport” as keywords, and extracting only original research including adult athletes and focused on targeting sports (e.g. shooting, golf, etc). Overall, 30 studies were reviewed, confirming that ET was a useful instrument to address different research issues within sport domain. However, new studies need to confirm these results, and to combine ET with other instruments in order to understand deeply the processes underpinning successful performance in sport.

Dario Fegatelli, Francesco Giancamilli, Luca Mallia, Andrea Chirico, Fabio Lucidi

The Elapsed Time During a Virtual Reality Treatment for Stressful Procedures. A Pool Analysis on Breast Cancer Patients During Chemotherapy

Virtual reality (VR) during chemotherapy has resulted in an elapsed time compression effect, validating the use of VR in the treatment of some stressful conditions. In the past literature the framework of the pacemaker–accumulator cognitive model of time perception resulted very reliable to explain this effect. This pilot-study explored the efficacy of Virtual Reality in reducing the perception of time during receipt of intravenous chemotherapy. Patient’s retrospective estimates of time elapsed during this treatment were evaluated versus patient’s treated with Music-Therapy. Materials and methods 47 breast cancer patients were randomly assigned to 20 min of VR treatment (N = 24) or 20 min of Music-therapy (N = 23) during chemotherapy infusion. Difference between actual and perceived elapsed time during chemotherapy with VR and with MT were evaluated with ANOVA analysis. Results: The VR group underestimated the time spent with VR treatment, instead MT treatment group overestimated it. In one step anova model, the VR versus MT treatment showed a significant difference in terms of altered time perception (F = 5.06, p = 0.0008). Further analysis on the same panel of patients will be conducted to explain also the role of some possible mediator of this effect.

A. Chirico, M. D’Aiuto, M. Pinto, C. Milanese, A Napoli, F. Avino, G. Iodice, G. Russo, M. De Laurentiis, G. Ciliberto, A. Giordano, F. Lucidi

Backmatter

Weitere Informationen

Premium Partner

    Bildnachweise