WSEAS Transactions on
Information Science and Applications
Contents:
2016 | 2015 | 2014 | 2013 | 2012 | 2011 | 2010 | 2009 | 2008 | Pre-2008
Print ISSN: 1790-0832
E-ISSN: 2224-3402
Volume 12, 2015
Notice: As of 2014 and for the forthcoming years, the publication frequency/periodicity of WSEAS Journals is adapted to the 'continuously updated' model. What this means is that instead of being separated into issues, new papers will be added on a continuous basis, allowing a more regular flow and shorter publication times. The papers will appear in reverse order, therefore the most recent one will be on top.
Volume 12, 2015
Title of the Paper: ICT for the Disabled: Policies and Issues
Authors: Paul Nikolaidis, Dimitrios Xanthidis
Abstract: The concept of impairment (of some extend) rather than disability, shifted the perception of technology usage by the disabled people. The contemporary policy in developed countries for the disabled does not reflect only the commitment of these communities for the development and use of the special technology in support for those individuals but, also, for non-discrimination at any level. The rapid developments and relevant innovations in the ICT field, whether wired or wireless, mainly based on the broadband paradigm promise a better quality of life without exceptions and improved results in the battle against the digital divide. The communities worldwide can, reasonably, hope that the, thought as, minorities of the people with disabilities will suffer gradually less from e-exclusion thanks to ICT innovation and supportive state policies.
Keywords: ICT, People with disabilities
WSEAS Transactions on Information Science and Applications, ISSN / E-ISSN: 1790-0832 / 2224-3402, Volume 12, 2015, Art. #36, pp. 359-367
Title of the Paper: A TOGAF-Based Method for Migrating Applications to Clouds
Authors: Jyhjong Lin, Chaoyu Lin
Abstract: For the advances of Cloud Computing technologies in recent years, cloud applications have been popularity for their rich set of features. The advantages of cloud applications include that users can utilize them in a low cost-, threshold-, and risk-way; these applications can be quickly deployed on the clouds without duplication of work such that developers can focus on enhancing their QoS to improve core competitiveness. Therefore, their practical use on business with promising values can be expected. As such, cloud applications are recognized as a trend for the next generation of business applications, and hence how to migrate these on-premise applications to the clouds becomes a desired field in the literature. For this need, we present a migration method that employs the well-known TOGAF framework to support an effective migration of on-premise applications into the clouds. For illustration, the method is applied to the migration of a CSS application to its cloud version.
Keywords: cloud computing, migration method, on-premise application, cloud application, TOGAF
WSEAS Transactions on Information Science and Applications, ISSN / E-ISSN: 1790-0832 / 2224-3402, Volume 12, 2015, Art. #35, pp. 351-358
Title of the Paper: Developing Fast Training Resource from Demonstration
Authors: Miao-Kuei Ho, Hung-Jen Yang, Li-Min Chen, Hsieh-Hua Yang, Wen-Chen Ho
Abstract: The purpose of this study was to identify the procedure and feasibility of developing fast training resources from demonstration. Technology is growing and updating information quickly, people need to constantly update their knowledge and empowerment. For industry competition, the employees require to enhance the skills on their job. There is a need to develop fast training resources. In a short time frame, Preparing and disseminating relevant and timely information and instruction to the right people has become the main challenge for most human resource departments. Traditional instructional design and development processes often require months or even years, and involves a big budget. This resulted in the emergence of a faster, cheaper and more effective solution for developing e-learning resource. Computer operating for accomplishing jobs had become a major characteristic in this information age. It is necessary to figure out a way of e-learning developing based upon computer operating demonstration. In this study, a general procedure of demonstration based fast training resource development was verified and concluded.
Keywords: Demonstration Based e-learning Resource, Fast Training Resource Development, Technology in Human Resource Development
WSEAS Transactions on Information Science and Applications, ISSN / E-ISSN: 1790-0832 / 2224-3402, Volume 12, 2015, Art. #34, pp. 341-350
Title of the Paper: Community Cloud: an Infrastructure Solution for a Logistics Project
Authors: Maria Teresa Baldassarre, Nicola Boffoli, Danilo Caivano, Gennaro Del Campo, Giuseppe Visaggio
Abstract: Cloud computing is becoming more and more adopted as infrastructure for providing service oriented solutions. Such a solution is especially critical when software and hardware resources are remotely distributed. In this paper we illustrate our experience
Keywords: cloud computing, private cloud, SaaS, integrated logistics
WSEAS Transactions on Information Science and Applications, ISSN / E-ISSN: 1790-0832 / 2224-3402, Volume 12, 2015, Art. #33, pp. 330-340
Title of the Paper: ICT Tools for Crisis Management Events – Rescue by Aeronautical Means
Authors: Georgia Moutzouropoulou, Emmanouil Zoulias
Abstract: Within this research we try to offer new approaches to reengineering the current rescue procedure in case of rescue by aeronautical means in Hellenic public territory. The proposed reengineering will give answer to existing problems like luck of resources
Keywords: emergencies, crisis management, modeling, BPMN, Bizagi, information tools, search and rescue
WSEAS Transactions on Information Science and Applications, ISSN / E-ISSN: 1790-0832 / 2224-3402, Volume 12, 2015, Art. #32, pp. 324-329
Title of the Paper: Compensation for Non-linear Iris Pattern Deformation Based on the Tensile Properties of Iris
Authors: Dae Sik Jeong, Dalho Cho, Jihye Jo, Min-Kyeong Bae, Min Woo Park, Eui Chul Lee
Abstract: In general, iris recognition can be performed to identify users based on the unique iris patterns between their pupils and scleras. The main function of iris is to control the size of the pupil according to the amount of environmental light. Therefore, the iris patterns dilate and contract based on changing lighting conditions. To guarantee robust recognition accuracy in spite of these deformed iris patterns, previous research has used the linear rubber band model and uniform track allocation in iris regions. However, some iris patterns are actually deformed nonlinearly due to the complicated movements of certain iris muscles including the sphincter and the dilator. To overcome these problems, we propose a new method of extracting iris features by nonlinear and dynamic track allocation. This proposed method is based on the nonlinear tensile properties of iris patterns. This paper presents two contributions over previous works. First, we automatically detected the nonlinear positions of the iris patterns in the radial direction when the pupil dilated and contracted with changing illumination conditions. This was possible because we used a template matching process with five iris patches. From the process, we were able to allocate tracks in the iris region nonlinearly and dynamically. We then extracted robust iris features for recognition. Second, we found that the nonlinear tensile properties of the iris patterns differed individually. Based on that, we adopted a user-dependent method of dynamic track allocation, which greatly improved recognition accuracy. Experimental results showed that the accuracy of the proposed method was superior to that of conventional methods which use uniform track allocations based on the linear rubber band model.
Keywords: Iris recognition, Tensile properties of iris patterns, Dynamic track allocation
WSEAS Transactions on Information Science and Applications, ISSN / E-ISSN: 1790-0832 / 2224-3402, Volume 12, 2015, Art. #31, pp. 315-323
Title of the Paper: An Iterative Algorithm for Single-Pair K Shortest Paths Computation
Authors: Guisong Liu, Zhao Qiu, Wenyu Chen
Abstract: In this paper, we report a novel method to compute the k shortest paths between a given pair of nodes in a given directed weighted graph, where loops are allowed in the solution paths. Once the shortest path from source node to goal node has been computed, the algorithm finds the next k - 1 shortest paths recursively. A* and on-the-fly search strategies are also applied to the proposed algorithm. The correctness of the presented algorithm is analyzed mathematically, and the simulative results confirming the superior performance of the algorithm to others in the literature for real road datasets are reported, especially when k is rather small.
Keywords: K shortest paths, Heuristic search, On-the-fly search
WSEAS Transactions on Information Science and Applications, ISSN / E-ISSN: 1790-0832 / 2224-3402, Volume 12, 2015, Art. #30, pp. 305-314
Title of the Paper: FingerDOS: A Fingerprint Database Based on Optical Sensor
Authors: Florence Francis-Lothai, David B. L. Bong
Abstract: Fingerprint image acquisition is known to be a challenging aspect in fingerprint recognition. Many fingerprint databases were developed in conjunction with the growth of fingerprint algorithms. However, some of the databases are not publicly available, or insufficient number of samples provided, or having inconsistent fingerprint images. The purpose of this study is to present a new fingerprint database based on optical sensor. The main feature of this database is that the displacement of finger on the sensor plate is kept minimum. This is to provide additional test platform for fingerprint recognition algorithm whereby less attention is given for displaced finger, and more focus on the ability to recognize complete fingerprints. There are 3600 fingerprint images acquired from 60 subjects. Each of the subjects contributed 60 fingerprint images of his six fingers (thumb, index finger and middle finger for left and right hands). In this paper, the acquisition protocols are outlined and the content of the database are described. This database is then compared with other existing online fingerprint database and a list of the characteristics of the databases is summarized. In comparison, our database has more number of fingerprint samples with minimal displaced finger. Request for the database is available at http://www.fingerdos.wordpress.com.
Keywords: Fingerprint database, biometric, optical sensor
WSEAS Transactions on Information Science and Applications, ISSN / E-ISSN: 1790-0832 / 2224-3402, Volume 12, 2015, Art. #29, pp. 297-304
Title of the Paper: Genetic Algorithm Based Feature Selection in High Dimensional Text Dataset Classification
Authors: Ferhat Ӧzgür Ҫatak
Abstract: Vector space model based bag-of-words language model is commonly used to represent documents in a corpus. But this representation model needs a high dimensional input feature space that has irrelevant and redundant features to represent all corpus files. Non-Redundant feature reduction of input space improves the generalization property of a classifier. In this study, we developed a new objective function based on models F1 score and feature subset size based. In this paper, we present work on genetic algorithm for feature selection in order to reduce modeling complexity and training time of classification algorithms used in text classification task. We used genetic algorithm based meta-heuristic optimization algorithm to improve the F1 score of classifier hypothesis. Firstly; (i) we’ve developed a new objective function to maximize; (ii) then we choose candidate features for classification algorithm; and (iii) finally support vector machine (SVM), maximum entropy (MaxEnt) and stochastic gradient descent (SGD) classification algorithms are used to find classification models of public available datasets.
Keywords: Feature selection, support vector machines, logistic regression, stochastic gradient descent, document classification
WSEAS Transactions on Information Science and Applications, ISSN / E-ISSN: 1790-0832 / 2224-3402, Volume 12, 2015, Art. #28, pp. 290-296
Title of the Paper: Analysis of Uncertainty Influence on an E-Tailer with a Threshold Policy and Alternative E-Fulfillment Options
Authors: Yue-Peng Cheng, Bo Li, Yi-Nan Li
Abstract: Drop shipping is very popular on the Internet. E-tailers use this service to fulfill customer demand. This study analyzes a supply chain consisting of a supplier and an e-tailer. The e-tailer uses a private inventory and drop shipping option for e-fulfillment, whereas the supplier provides replenishing and drop shipping service with limited capability for the e-tailer. The e-tailer selects a threshold policy in the private inventory and provides two different priorities to customer demand, namely, high priority demand and low priority demand. This paper designs a general framework to obtain the optimal threshold of the private inventory for the e-tailer to achieve his average profit maximization. We also analyze the impact of different uncertainties and proportion variability of high priority demand on the optimal threshold in different scenarios through Monte Carlo simulation. The results can provide a significant guideline for the e-tailers who adopt drop shipping as an alternative e-fulfillment option, especially when they face complex operating environments.
Keywords: Uncertainty, Threshold Policy, E-fulfillment, Lead Time, Drop Shipping, Inventory, Alternative
WSEAS Transactions on Information Science and Applications, ISSN / E-ISSN: 1790-0832 / 2224-3402, Volume 12, 2015, Art. #27, pp. 277-289
Title of the Paper: User-Independent and Self-Optimizing Intrusion Detection Framework for Large Database Systems
Authors: Reza Adinehnia, Nur Izura Udzir, Lilly Suriani Affendey, Iskandar Ishak, Zurina Mohd Hanapi
Abstract: Despite various access control approaches, databases are still vulnerable to intruders who are able to bypass these protective methods and access data, or prevent insiders like authorized users who misuse their privilege. To prevent all such intrusions, this study proposes a multilayer profiling method to provide suitable and reliable valid patterns to be used in the proposed database intrusion detection framework. With the help of association rule learning and Naive Bayes classifier this framework can provide a considerable rate of intrusion detection. The main contributions of this paper are summarized in a granular profiling structure and a detection framework that helps to detect database intrusions even if they are initiated by insiders.
Keywords: database intrusion detection, query profiling, data mining, apriori
WSEAS Transactions on Information Science and Applications, ISSN / E-ISSN: 1790-0832 / 2224-3402, Volume 12, 2015, Art. #26, pp. 269-276
Title of the Paper: POKMS: A Process-Oriented and Ontology-Based Knowledge Management System in Exploration and Development
Authors: Yanhong Zhao, Hongqi Li, Liping Zhu, Rui Han
Abstract: As information technologies have become widely applied enabling technologies in different engineering disciplines such as oil/gas exploration and development, various (especially legacy) applications are deployed with different data models and they constitute a business process that must be accomplished through the coordination and cooperation of different specialized departments. However, heterogeneous data sources together with different data models give rise to two key challenges in automating the process. First, acquiring and standardizing data is error-prone. The second, and more important, challenge is that small human errors will affect decision significantly. Without a domain-specific business process enabling platform, decision makers could not acquire progresses on each activity in time, and thus delaying the transferring and sharing of the produced results among different departments. In this paper, we propose POKMS, a process-oriented and ontology-based approach for knowledge management and heterogeneous data integration. POKMS first automatically builds the exploration and development ontology from the epicentre data model, which is a global petroleum industry data model published by the petro-technical open standards consortium. Subsequently, POKMS uses the domain ontology to define the basic entities in business process modeling. Following this approach, we built a web-based knowledge service platform providing graphical tools for users to visually design the business processes. Using this platform, decision makers can acquire progresses on each activity instantly, thereby timely transferring and sharing results produced by each activity among departments, experts, and non-experts. Furthermore, end users, in particular non-experts, can reuse the domain knowledge and monitor the processes of the ongoing projects, and thus help improve the efficiency of decision making.
Keywords: Ontology, Heterogeneous data integration, Business process modeling, Knowledge management
WSEAS Transactions on Information Science and Applications, ISSN / E-ISSN: 1790-0832 / 2224-3402, Volume 12, 2015, Art. #25, pp. 254-268
Title of the Paper: MiKe: Algorithm for Mining Keyphrases
Authors: Vinothini Kasinathan, Aida Mustapha, Chan Kin Mun
Abstract: The main challenge in mining from presentation slides lies in the fact that slides already contain keywords and keyphrases. A presentation mining system needs a keyphrase extraction algorithm that is able to mine the keywords/keyphrases in the slides and reorganize them from sequential to network-based while keeping the relationships within slides intact. This paper introduces a new keyphrase extraction algorithm called MiKe that extracts keyphrases from a collection of presentation slides and reconstruct the keyphrases into mind map-like visualization output. The descriptions include application of MiKe to a case study that illustrates the flow of MiKe in a presentation mining system.
Keywords: Keyphrase extraction, Knowledge visualization, Text mining, Powerpoint slide, Mind map
WSEAS Transactions on Information Science and Applications, ISSN / E-ISSN: 1790-0832 / 2224-3402, Volume 12, 2015, Art. #24, pp. 241-253
Title of the Paper: Extending the Teknomo-Fernandez Background Image Generation Algorithm on the HSV Colour Space
Authors: Patricia Angela Abu, Proceso Fernandez
Abstract: Background subtraction, a procedure required in many video analysis applications such as object tracking, is dependent on the model background image. One efficient algorithm for background image generation is the Teknomo-Fernandez (TF) Algorithm, which uses modal values and a tournament-like strategy to produce a good background image very quickly. A previous study showed that the TF algorithm can be extended from the original 3 frames per tournament (TF3) to TF5 and TF7, resulting in increased accuracies at a cost of increased processing times. In this study, we explore extending the TF3, TF5 and TF7 from the original RGB colour space to the HSV colour space. A ground truth model background image for HSV was also developed for comparing the performances between the TF implementations on the RGB and HSV channels. The results show that the TF algorithm generates accurate background images when implemented on the HSV colour space. However, the RGB implementations still exhibit higher accuracies than the corresponding HSV implementations. Finally, background subtraction was applied on the HSV generated background images. A comparison with other promising baseline techniques validates the competitiveness of the TF algorithm implemented on HSV channels.
Keywords: background subtraction, boolean operation, HSV, mode values
WSEAS Transactions on Information Science and Applications, ISSN / E-ISSN: 1790-0832 / 2224-3402, Volume 12, 2015, Art. #23, pp. 230-240
Title of the Paper: Cluster Ensemble Extraction for Knowledge Reuse Framework
Authors: Ebrahim Akbari, Halina Mohamed Dahlan, Roliana Ibrahim
Abstract: Cluster ensemble framework attempts to find stable and robust results through composing calculated clusterings obtained from basic clustering algorithms without accessing the features or algorithms that determine these clusterings. Diversity of clusterings is a important factor for improving cluster ensemble performance, where an ensemble of small size of identical clusterings dose not improve the quality and robustness of solution. Concerning limited access to the raw data, how new clusterings with more diversity and size can be created using a few base clusterings. This paper proposes a new approach, cluster ensemble extraction, as a knowledge reuse framework to create a new diversity without accessing the raw data. This approach creates a new set of clusterings from the existing clusterings, which have more diversity and size compared to base clusterings. To evaluate the performance of the proposed approach, several experiments were conducted on several real data sets and the results were compered to the results obtained from executing of cluster ensemble on base clusterings. The comparison results showed the superiority of the proposed approach over the cluster ensemble approach in terms of quality.
Keywords: Clustering, Knowledge reuse, Diversity, Cluster ensemble extraction
WSEAS Transactions on Information Science and Applications, ISSN / E-ISSN: 1790-0832 / 2224-3402, Volume 12, 2015, Art. #22, pp. 219-229
Title of the Paper: Arabic Text Dimensionality Reduction Using Semantic Analysis
Authors: Enas Sedki, Abdelfattah Alzaqah, Arafat Awajan
Abstract: An efficient method to compress and reduce the dimensionality of Arabic texts using semantic model-based representation of text is introduced. The proposed system creates equivalence classes, where similar words, generated according to the rich productive morphology of the language and based on the stem-root-pattern paradigm, are grouped together and represented by a class identifier. In addition, synonyms and similarly named entities are regrouped in order to improve the representation and reduce its size. The reduced representation of the text is accessible to most machine learning algorithms and natural language processing applications that require heavy computational complexity. Distributional similarity measures were used to create equivalence classes of similar words. These measures were applied to the word-context matrix associated with the document in order to identify similar words based on a text's context. The results confirmed that the proposed method shows that incorporation of sematic information in vector representation is superior to classical bag-of-words representation, in terms of size reduction and results quality of applications. The best results are achieved for the clustering of words that are semantically similar, based on their stems. In addition, regrouping differently named entities representing the same concepts improved the reduction amount by 5%.
Keywords: Semantic vector space model, word-context matrix, Arabic natural language processing, text dimension reduction, semantic feature extraction
WSEAS Transactions on Information Science and Applications, ISSN / E-ISSN: 1790-0832 / 2224-3402, Volume 12, 2015, Art. #21, pp. 209-218
Title of the Paper: Brainwaves Analysis of Positive and Negative Emotions
Authors: Fu-Chien Kao, Shinping R. Wang, Yu-Jung Chang
Abstract: Emotions, is the generic term for various subjective cognitive experiences and a psychological and physiological synthesized state generates under a variety of perceptions, thoughts, and behaviours. In general, emotion can be categorized into Joyful, Angry, Protected, Sad, Surprised, Fear, Satisfied and Unconcerned eight types of positive-negative emotions. More subtle and delicate emotions include jealousy, humiliation, shame, pride and other emotions. Emotion is often under influence of mood, personality, temperament, purpose and other factors. It can also be affected by hormones and neuro transmitters. Whether positive or negative emotions are all motivations and trigger action. Although some emotional behaviour seems take place inadvertent, however conscious plays an important role in producing emotion. This paper from the perspective of cognitive neuroscience investigates difference of human brainwave of 8 types of positive and negative emotions i.e. Joyful, Angry, Protected, Sad, Surprised, Fear, Satisfied and Unconcerned. The experiment uses acoustic stimuli to stimulate the positive and negative emotions of the test subjects and uses Electroencephalogram (EEG) to extract test subjects’ frontal lobe brainwave. The extracted brainwave is further transformed into frequency domain signal where sub-band energy is calculated, characterized, and finally digital encoded for analysis. The encoded characteristic brainwaves of positive and negative emotion are compared for theirs difference. It shows 8 different positive and negative emotions can be effectively identified by the proposed emotional brainwave digital encoding technique and the technique is promising for developing future emotion identification technique.
Keywords: Brainwave, Cognitive Neuroscience, Emotion Recognition
WSEAS Transactions on Information Science and Applications, ISSN / E-ISSN: 1790-0832 / 2224-3402, Volume 12, 2015, Art. #20, pp. 200-208
Title of the Paper: Optimization of the Radiation Performances of Square Shaped Patch Antenna for RFID Reader
Authors: Ali El Alami, Saad Dosse Bennani, Abdellatif Slimani
Abstract: The main objective of this work is to optimize the radiation performances of square shaped patch antenna. This antenna is excited by microstrip line having a power port adapted to 50 GHz and intended for RFID reader. The slots inserted at the edges of the radiating element have a direct and positive impact on improving the radiation characteristics of this antenna in terms of reflection coefficient, voltage standing wave ratio, input impedance and radiation pattern around a resonance frequency of 2.45 GHz. The simulation results obtained by the two simulators HFSS (High Frequency Structure Simulator) and CST (Computer Simulation Technology) is almost consistent good.
Keywords: Square patch antenna, microstrip line, RFID reader, reflection coefficient, voltage standing wave ratio, input impedance, radiation pattern, simulators HFSS and CST
WSEAS Transactions on Information Science and Applications, ISSN / E-ISSN: 1790-0832 / 2224-3402, Volume 12, 2015, Art. #19, pp. 194-199
Title of the Paper: Mitigating Supply Chain Risks by Evaluating Supplier Bankruptcy Probabilities Through Web Services and the Black-Scholes-Merton Model
Authors: Sherif Barrad, Raul Valverde
Abstract: Industry consolidation and globalization represents a challenge for procurement organizations who typically become either recipients of the acquired company’s supplier base or are directly responsible for this increase by securing new suppliers to meet the operational demands of a global supply chain. An increased supplier base not only makes it more difficult to manage suppliers but also represents higher supply chain risks. The proposed model attempts to proactively evaluate bankruptcy probabilities of suppliers by capturing financial information using web services, computing this data using a modified equation version of a well-known financial model and producing risk potentials, in percentage points, for supplier bankruptcies. The study clearly shows the usefulness of the prototype when operating in a Service Oriented Architecture and offered to end users as a leading indicator of risk.
Keywords: Web Services, Black-Scholes-Merton, Supply Chain Finance, Supply Chain Risk Management
WSEAS Transactions on Information Science and Applications, ISSN / E-ISSN: 1790-0832 / 2224-3402, Volume 12, 2015, Art. #18, pp. 186-193
Title of the Paper: On Cognitive Processes of Analysis and Synthesis in Cognitive Computing
Authors: Yingxu Wang
Abstract: Analysis and synthesis are a pair of fundamental cognitive processes at the inference layer of the brain. The former is an inference process that deductively decomposes an object or a system into its constituting attributes and components. The latter is an inference process that inductively composes individual attributes of components into a complex whole. This paper presents the cognitive foundations of analysis and synthesis in cognitive inferences. A set of mathematical models of analysis and synthesis is created. Based on the cognitive and mathematical models, the cognitive processes of analysis and synthesis are formally described in Real-Time Process Algebra (RTPA), which enable a rigorous explanation of the cognitive mechanisms of mental inferences in cognitive computing and cognitive robotics.
Keywords: Cognitive informatics, brain science, LRMB, cognitive models, cognitive processes, mathematical models, denotational mathematics, RTPA, cognitive computing, computational intelligence, AI, inference, reasoning, cognitive robotics
WSEAS Transactions on Information Science and Applications, ISSN / E-ISSN: 1790-0832 / 2224-3402, Volume 12, 2015, Art. #17, pp. 177-185
Title of the Paper: Prototype Framework for Integration of Digital Repository Systems with e-Learning Platforms
Authors: Hrvoje Jerkovic
Abstract: Modern repository platforms like Dspace, ePrints or FEDORA (Flexible and Extensible Digital Object and Repository Architecture) are information systems and frameworks for handling digital objects. They are rich with various features so they might serve as much better interactive storage than internal LMS (Learning Management System) storage used by LSM like Blackboard or Moodle. This paper analyzes features of commonly used repository platforms as possible storage solution for e-learning digital objects and tools. We explain our experiences while creating integrated framework system for commonly used LMS with commonly used repository platforms. Comparison analysis of existing repository platforms is made with focus on features necessary for effective integration with LMS and similar e-learning systems. Prototype application was created to demonstrated key features and benefits of integrated solution.
Keywords: repository platforms, learning management systems, API, integration, e-learning tools, prototype application
WSEAS Transactions on Information Science and Applications, ISSN / E-ISSN: 1790-0832 / 2224-3402, Volume 12, 2015, Art. #16, pp. 167-176
Title of the Paper: DBpedia As a Formal Knowledge Base – An Evaluation
Authors: Tomasz Boiński, Adrian Ambrożewicz, Julian Szymański
Abstract: DBpedia is widely used by researchers as a mean of accessing Wikipedia in a standardized way. In this paper it is characterized from the point of view of questions answering system. Simple implementation of such system is also presented. The paper also characterizes alternatives to DBpedia in form of OpenCyc and YAGO knowledge bases. A comparison between DBpedia and those knowledge bases is presented.
Keywords: Knowledge base, Natural language processing
WSEAS Transactions on Information Science and Applications, ISSN / E-ISSN: 1790-0832 / 2224-3402, Volume 12, 2015, Art. #15, pp. 161-166
Title of the Paper: Effective Aggregation and Querying of Probabilistic RFID Data in a Location Tracking Context
Authors: Razia Haider, Federica Mandreoli, Riccardo Martoglia
Abstract: RFID applications usually rely on RFID deployments to manage high-level events such as tracking the location that products visit for supply-chain management, localizing intruders for alerting services, and so on. However, transforming low-level streams into high-level events poses a number of challenges. In this paper, we deal with the well known issues of data redundancy and data-information mismatch: we propose an on-line summarization mechanism that is able to provide small space representation for massive RFID probabilistic data streams while preserving the meaningfulness of the information. We also show that common information needs, i.e. detecting complex events meaningful to applications, can be effectively answered by executing temporal probabilistic SQL queries directly on the summarized data. All the techniques presented in this paper are implemented in a complete framework and successfully evaluated in real-world location tracking scenarios.
Keywords: RFID data streams, Data summarization, Probabilistic Data Management, Object tracking, Probabilistic Database
WSEAS Transactions on Information Science and Applications, ISSN / E-ISSN: 1790-0832 / 2224-3402, Volume 12, 2015, Art. #14, pp. 148-160
Title of the Paper: Survey on Score Normalization: A Case of Result Merging in Distributed Information Retrieval
Authors: Benjamin Ghansah, Shengli Wu
Abstract: Merging the outputs of different search engines or information sources in response to a query has been shown to improve performance. In most cases, scores produced by different information sources are not comparable: merging techniques are often segregated into a score normalization step followed by a combination step. The Combination step is usually straight forward and has been an area of active research. However, the normalization step has received less attention; in particular a peculiar attribute such as diversification is largely missing in most Result Merging studies. This survey seeks to explore the various domains of score normalization, especially the results merging phase of a Distributed Information Retrieval environment, and propose a general framework to diversify score normalization through the use of the covariance principle.
Keywords: Machine learning, Classification approach, Distributed Information retrieval, Result merging, Information Retrieval
WSEAS Transactions on Information Science and Applications, ISSN / E-ISSN: 1790-0832 / 2224-3402, Volume 12, 2015, Art. #13, pp. 138-147
Title of the Paper: Video Analysis in Interactive Application of Digital Television
Authors: Cristiane Zakimi Correia Pinto, Wagner Luiz Zucchi
Abstract: A digital television system can provide sounds and images of better quality than an analog broadcast system. But that is not all. The Brazilian digital terrestrial television system adopted in 2006 also makes it possible to receive TV signals on portable devices and mobile television receivers besides enabling interactivity. This paper consider digital terrestrial television, which is the digital television broadcast over the air, free of charge to all population, and presents a video analysis based in the Quality of Experience (QoE) that was made measuring the user perception with an interactive application of digital terrestrial television. Such an application was developed using NCL (Nested Context Language), which is the standard declarative programming language of Brazilian digital television system called Integrated Services Digital Broadcasting - Terrestrial Brazil (ISDB-TB). In that application a secondary video is loaded through a broadband Internet access simultaneously with the main video being received through broadcasting. A test platform was created where IP packet loss was introduced in a controlled way affecting the secondary video, as it is expected to occur in a real network. Video quality was assessed for each loss level with objective metrics in order to compare QoE in each situation. The objective of this research is to verify if it is feasible to use the broadband Internet as a return channel of an interactive application of Brazilian digital television.
Keywords: Digital television, ISDB-TB, Transmedia, QoE, Video signal processing, Broadcast, Broadband
WSEAS Transactions on Information Science and Applications, ISSN / E-ISSN: 1790-0832 / 2224-3402, Volume 12, 2015, Art. #12, pp. 130-137
Title of the Paper: Rice Blast Disease Forecasting for Northern Philippines
Authors: Alvin R. Malicdem, Proceso L. Fernandez
Abstract: Rice blast disease has become an enigmatic problem in several rice growing ecosystems of both tropical and temperate regions of the world. In this study, we develop models for predicting the occurrence and severity of rice blast disease, with the aim of helping to prevent or at least mitigate the spread of such disease. Data from 2 government agencies in selected provinces from northern Philippines were gathered, cleaned and synchronized for the purpose of building the predictive models. After the data synchronization, dimensionality reduction of the feature space was done, using Principal Component Analysis (PCA), to determine the most important weather features that contribute to the occurrence of the rice blast disease. Using these identified features, ANN and SVM binary classifiers (for prediction of the occurrence or non-occurrence of rice blast) and regression models (for estimation of the severity of an occurring rice blast) were built and tested. These classifiers and regression models produced sufficiently accurate results, with the SVM models showing a significantly better predictive power than the corresponding ANN models. These findings can be used in developing a system for forecasting rice blast, which may help reduce the occurrence of the disease.
Keywords: machine learning, artificial neural network, support vector machine, rice blast disease
WSEAS Transactions on Information Science and Applications, ISSN / E-ISSN: 1790-0832 / 2224-3402, Volume 12, 2015, Art. #11, pp. 120-129
Title of the Paper: Query Recommendation Based Terms and Relevant Documents Using Language Models
Authors: Btihal El Ghali, Abderrahim El Qadi, Omar El Midaoui, Mohamed Ouadou
Abstract: The query submitted by the user is only a partial and often ambiguous expression of his need. This implies that it is essential to suggest to the users the most related queries to the context of their queries. However, the notion of context is quite broad and includes all the elements related to the query (Its field, its environment, the user profile, his preferences and his search history). In this paper, we extract the environment of a user’s query in order to use it later in its query recommendation process. For this purpose, three different methods of query recommendation are proposed, and then compared based on the quality of the extracted environments, by calculating the Average Internal Similarity (AIS) of each built environment. The results show that the information of documents relevance influence the similarity between queries better than the information of existence of terms for all the proposed approaches. The final experiment was a comparison between the three approaches, and it shows that for short and long queries the highest value of AIS is reached by the TLM approach using Language Models based on common terms and relevant documents.
Keywords: Information Retrieval, Query Recommendation, Language Model, Recommendation Algorithm, Query’s context
WSEAS Transactions on Information Science and Applications, ISSN / E-ISSN: 1790-0832 / 2224-3402, Volume 12, 2015, Art. #10, pp. 112-119
Title of the Paper: On the Design of Time-Predictable Low-Leakage Cache Memory for Real-Time Embedded Systems
Authors: Mutaz Al-Tarawneh
Abstract: This paper presents a multidisciplinary study that aims at designing a time-predictable low-leakage cache memory for real-time embedded systems. Both state-preserving and state-destroying leakage-saving mechanisms have been tested on a superscalar processor with two-level cache hierarchy. Full system simulation has been used to examine leakage-saving capability of each mechanism. In addition, a statistical approach has been proposed to study processor’s time-predictability under potential leakage-saving techniques. Furthermore, the performance of real-time embedded systems in presence of leakage-saving techniques has been thoroughly analyzed using Matlab/Simulink-based models. Each possible design alternative has been evaluated in terms of four parameters that include: average power saving, degree of predictability (DoP), loss of schedulability (LoS) and performance of the underlying embedded system. Our results have shown that applying a state-preserving leakage-saving mechanism on either first-level data cache or last-level unified cache provides the most viable design option. The first alternative has achieved an average power saving of 32.61 %, a DoP of 93.05% and a LoS of 0% while the second alternative has achieved an average power saving of 50.21%, a DoP of 80.30% and a LoS of 13.68%. Moreover, neither of them has caused any disruption in the performance of the experimental embedded system models. Consequently, using a first-level data cache with a state-preserving leakage-saving mechanism represents the best feasible option for systems with very critical timing requirements while employing a state-preserving low-leakage last-level cache can be the suitable option for systems with soft timing requirements and stringent power constrains.
Keywords: cache memory, real-time, embedded, leakage power, time-predictability, performance
WSEAS Transactions on Information Science and Applications, ISSN / E-ISSN: 1790-0832 / 2224-3402, Volume 12, 2015, Art. #9, pp. 82-111
Title of the Paper: Methods to Protect Cryptographic Keys on Safety-Critical Systems
Authors: Rafael Costa, Davidson Boccardo, Luci Pirmez, Luiz Fernando Rust
Abstract: Safety-critical systems are embedded systems whose failure or malfunction could lead to unacceptable consequences. Despite the major worries about such systems are related to the design of its embedded software, the security is still a challenge to be faced, particularly in terms of data confidentiality, since they could store sensitive that, such as cryptographic keys, which could not be revealed by unauthorized people. Assuming that safety-critical systems are commonly arranged in unprotected areas, without being under surveillance, an attacker could easily capture the respective devices in order to disclosure its cryptographic keys. Thus, it is necessary to create solutions to keep cryptographic keys secret. In this paper is proposed methods to protect cryptographic keys based on code transformations. Since all major protections stand up to a determined attacker’s strategies till a certain period of time, we propose methods taking into account what strategies the attacker can perform. We conducted a case study and a discussion to show the difficulty to disclosure cryptographic keys if were used one or more methods proposed here.
Keywords: Security, Safety-Critical Systems, Cryptographic Key Protection, Obfuscation
WSEAS Transactions on Information Science and Applications, ISSN / E-ISSN: 1790-0832 / 2224-3402, Volume 12, 2015, Art. #8, pp. 68-81
Title of the Paper: One Time Enumeration of Maximal Biclique Patterns from 3d Symmetric Matrix
Authors: M. Dominic Savio, A. Sankar, R. V. Nataraj
Abstract: We propose an algorithm Cubeminer-MBC*, to extract maximal biclique patterns from a 3D symmetric adjacency matrix only once. In this paper, we introduce (i) a novel enumeration strategy and (ii) a new pruning strategy, which results 50% reduction in search space and maximal biclique patterns are generated only once, i.e., zero duplicates are generated. On the basis of experiments conducted, we observed Cubeminer-MBC* outperforms Cubeminer in terms of running time.
Keywords: Data Mining, Maximal Bicliques, Algorithms, Symmetric matrix, Duplicate pattern
WSEAS Transactions on Information Science and Applications, ISSN / E-ISSN: 1790-0832 / 2224-3402, Volume 12, 2015, Art. #7, pp. 61-67
Title of the Paper: A Novel Feature Extraction Method for Epileptic EEG Based on Degree Distribution of Complex Network
Authors: Fenglin Wang, Qingfang Meng, Yuehui Chen
Abstract: Automatic seizure detection is significant in relieving the heavy workload of inspecting prolonged electroencephalograph (EEG). Feature extraction method for automatic epileptic seizure detection has important research significance because the extracted feature seriously affects the detection algorithm performance. Recently complex network theory shows its advantages to analyze the nonlinear and non-stationary signals. In this paper, we propose a novel feature extraction method for epileptic EEG based on a statistical property of complex network. The EEG signal is first converted to complex network and the degree of every node in the network is computed. By analyzing the degree distribution, the weighted mean value of degree distribution is extracted as classification feature. A public dataset was utilized for evaluating the classifying performance of the extracted feature. Experimental results show that the extracted feature achieves not only higher classification accuracy up to 96.50% but also a very fast computation speed, which indicate the extracted feature can clearly distinguish the ictal EEG from interictal EEG and has great potentiality of real-time epileptic seizures detection.
Keywords: Feature Extraction Method, Epileptic Seizure Detection, Electroencephalograph (EEG), Degree Distribution, Complex Network, Nonlinear Time Series Analysis
WSEAS Transactions on Information Science and Applications, ISSN / E-ISSN: 1790-0832 / 2224-3402, Volume 12, 2015, Art. #6, pp. 51-60
Title of the Paper: Drowsiness Detection for Drivers Using Computer Vision
Authors: C. Murukesh, Preethi Padmanabhan
Abstract: Drowsiness detection system is regarded as an effective tool to reduce the number of road accidents. This project proposes a non-intrusive approach for detecting drowsiness in drivers, using Computer Vision. The algorithm is coded on OpenCV platform in Linux environment. The parameters considered to detect drowsiness are face and eye detection, blinking, eye closure and gaze. Input is captured and live fed from a camera that supports night vision as well. The algorithm is Haar trained to detect the face and the eye from the incoming frame. Once the eye is detected, further coding is done to track the eye and automatically set a dynamic threshold value. Depending on the values obtained from each of the incoming frames and deviations from the threshold values, eyelid closure/blink/gaze is detected. Warning system is designed to alert the driver. This system renders an efficient solution to road accidents and the cost of developing it into a real time system is also feasible when compared to the cost involved in the manufacture of car.
Keywords: OpenCV, Linux, Haar Classifiers
WSEAS Transactions on Information Science and Applications, ISSN / E-ISSN: 1790-0832 / 2224-3402, Volume 12, 2015, Art. #5, pp. 43-50
Title of the Paper: Joint Shared Relaying and Base Station Coordination in LTE-Advanced Networks
Authors: Moubagou Deflandre Bertrand, Chang Yongyu
Abstract: In order to achieve high spectral efficiency with improved peak data rates of cell-edge uses and enable an enhanced network coverage with good throughput both in downlink and uplink, LTE-Advanced proposes separately base station coordination and relaying techniques. In the purpose to increase the cell-edge user data rates beyond what can be reached by using either one of the techniques alone, this paper introduces a novel transmission scheme, which combines relaying and base station coordination together. Numerical results show that the transmission scheme is a good solution for improving the cell-edge multi-user performance. The cooperative transmission scheme can enable the simultaneous transmissions to multiple users in different cells and gain higher sum-rate capacity than those systems applying relaying or base station coordination alone.
Keywords: LTE-Advanced, Relaying, Base station coordination, Throughput, SNR, Inter-cell interference
WSEAS Transactions on Information Science and Applications, ISSN / E-ISSN: 1790-0832 / 2224-3402, Volume 12, 2015, Art. #4, pp. 36-42
Title of the Paper: CIADS: A Framework for Secured Storage of Patients Medical Data in Cloud
Authors: Suresh Jaganathan, Dhivya Veerappan
Abstract: Patient medical details, diagnosis results and recommendations by the doctors considered as medical data. These data are a valuable asset for the hospitals and stored securely. Grid computing provides facility called ImageCare platform provided by DICOMGrid, which allows only authorized doctors to store, search and access medical data. Since the data resides in off-site, these considerations have to be checked, i) storage size, ii) security type, iii) backup and iv) recovery of data. In this paper, a new cloud storage model is proposed (CIADS[Confidential-Integrity-Authentication based Data Store]) for patient’s medical data, adopting DaaS model. The proposed model addresses the above-said considerations and also based on CDMI set of standards provided by SNIA.
Keywords: Security, Cloud Computing, Cloud Storage, Encryption, CDMI, Medical Data
WSEAS Transactions on Information Science and Applications, ISSN / E-ISSN: 1790-0832 / 2224-3402, Volume 12, 2015, Art. #3, pp. 22-35
Title of the Paper: Ground-Coupled Heat Transfer Test Cases as Ranking Simulation Software
Authors: Stanislav Sehnalek, Martin Zalesak, Jiri Vincenec, Michal Oplustil, Pavel Chrobak
Abstract: In the present work is International European Agency Building Energy Simulation Test Task 34 used as validation for SolidWorks Flow Simulation 2012. IEA BESTEST methodology is based on analytical verification of one model and on comparative validation of the rest of models. For appraisal was chosen 12 cases where half have stationary character and the remain half is periodical. In the beginning of the presented paper are described cases with appropriate application. The outcome of simulation follows with discussion about results which are segregated in the manner of periodic or steady character. The paper is wind up with outline of future research.
Keywords: Heat transfer, Finite Element Method, SolidWorks Flow Simulation, Software validation, Benchmark, Building simulation
WSEAS Transactions on Information Science and Applications, ISSN / E-ISSN: 1790-0832 / 2224-3402, Volume 12, 2015, Art. #2, pp. 11-21
Title of the Paper: Multibiometric Template Security Using CS Theory – SVD Based Fragile Watermarking Technique
Authors: Rohit Thanki, Komal Borisagar
Abstract: Protection of biometric template against spoofing or modification attack at system database is major issue in multibiometric system. Hence fragile digital watermarking technique is one of the solutions for biometric template protection against these attacks. In this paper, fingerprint watermarking technique based on SVD and Compressive Sensing theory proposed for protection of biometric template at system database of multibiometric system. This technique does not embed the fingerprint directly into face image instead using the concept of compressive sensing fingerprint convert into sparse measurements. The sparse measurements is generated at time of fingerprint embedding process and extracted from watermarked face image at extraction side for reconstruction of original watermark fingerprint image. SSIM value between original watermark fingerprint image and reconstructed watermark fingerprint image is the deciding factor for cross verification of individual. The experimental results show that the proposed technique does not affect verification and authentication performance of multibiometric system.
Keywords: Compressive Sensing Theory, Fragile, Multibiometric, SVD, Template Protection, Watermarking
WSEAS Transactions on Information Science and Applications, ISSN / E-ISSN: 1790-0832 / 2224-3402, Volume 12, 2015, Art. #1, pp. 1-10