{"title":"A novel approach combining recurrent neural network and support vector machines for time series classification","authors":"Abdulrahman Alalshekmubarak, L. Smith","doi":"10.1109/INNOVATIONS.2013.6544391","DOIUrl":"https://doi.org/10.1109/INNOVATIONS.2013.6544391","url":null,"abstract":"Echo state network (ESN) is a relatively recent type of recurrent neural network that has proved to achieve state-of-the-art performance in a variety of machine-learning tasks. This robust performance that incorporates the simplicity of ESN implementation has led to wide adoption in the machine-learning community. ESN's simplicity stems from the weights of the recurrent nodes being assigned randomly, known as the reservoir, and weights are only learnt in the output layer using a linear read-out function. In this paper, we present a novel approach that combines ESN with support vector machines (SVMs) for time series classification by replacing the linear read-out function in the output layer with SVMs with the radial basis function kernel. The proposed model has been evaluated with an Arabic digits speech recognition task. The well-known Spoken Arabic Digits Dataset, which contains 8800 instances of Arabic digits 0-9 spoken by 88 different speakers (44 males and 44 females) was used to develop and validate the suggested approach. The result of our system can be compared to the state-of-the-art models introduced by Hammami et al. (2011) and P. R. Cavalin et al. (2012) , which are the best reported results found in the literature that used the same dataset. The result shows that ESN and ESNSVMs can both provide superior performance at a 96.91% and 97.45% recognition accuracy, respectively, compared with 95.99% and 94.04% for other models. The result also shows that when using a smaller reservoir size significant differences exist in the performance of ESN and ESNSVMs, as the latter approach achieves higher accuracy by more than 15% in extreme cases.","PeriodicalId":438270,"journal":{"name":"2013 9th International Conference on Innovations in Information Technology (IIT)","volume":"371 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122779671","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Modeling packet rate covert timing channels","authors":"P. Shrestha, M. Hempel, M. Alahmad, H. Sharif","doi":"10.1109/INNOVATIONS.2013.6544393","DOIUrl":"https://doi.org/10.1109/INNOVATIONS.2013.6544393","url":null,"abstract":"Covert channels provide a medium for secret communication by exploiting caveats in common networking protocols to hide information exchanges within benign activities, without being detected by unsuspecting hosts and network firewalls. This makes covert channels a significant security concern. Therefore, it is of utmost importance to develop effective and comprehensive countermeasures. In general, the more secret data capacity a covert channel provides the higher its estimated threat level is, as it diminishes the time available to detect and disrupt such activities and prevent the information exchange. Hence, determining the capacity of a covert channel is important. However, most work in capacity estimation is specifically targeted at individual algorithms only, and thus is similarly in applicability. A general mathematical model that can predict the capacity of most algorithms is a key research need for effective covert channel prevention. In this paper, we have provided a general analytical model to determine the capacity of timing-based covert channels, and verified the model with computer simulations.","PeriodicalId":438270,"journal":{"name":"2013 9th International Conference on Innovations in Information Technology (IIT)","volume":"76 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127289589","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Combining semantic techniques to enhance arabic Web content retrieval","authors":"Anfal M Aiawajy, J. Berri","doi":"10.1109/INNOVATIONS.2013.6544408","DOIUrl":"https://doi.org/10.1109/INNOVATIONS.2013.6544408","url":null,"abstract":"This paper introduces an approach that combines a set of semantic techniques to enhance traditional information retrieval for the Arabic language. The approach uses a set of linguistic techniques to deal with the Web content. It expands first the initial user's query with additional related words by using lexical semantic relations (synonyms) covered in Arabic WordNet thesaurus and by domain specific words and abbreviations collected from the corpus. Second, it makes use of linguistic methods to match semantically the query objective with the text content in the search results. The paper presents the approach used and also the implementation of the system. Experimental results show that semantic retrieval outperforms the traditional information retrieval which is based only on query keywords matching.","PeriodicalId":438270,"journal":{"name":"2013 9th International Conference on Innovations in Information Technology (IIT)","volume":"416 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134419396","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
M. Fraiwan, N. Khasawneh, A. Malkawi, Muhammed Al-Jarrah, R. Alsa'di, S. Al-Momani
{"title":"Therapy central: On the development of computer games for physiotherapy","authors":"M. Fraiwan, N. Khasawneh, A. Malkawi, Muhammed Al-Jarrah, R. Alsa'di, S. Al-Momani","doi":"10.1109/INNOVATIONS.2013.6544388","DOIUrl":"https://doi.org/10.1109/INNOVATIONS.2013.6544388","url":null,"abstract":"The physiotherapy and rehabilitation process is an expensive and time consuming affair. It also requires the direct supervision of the specialists for effective results. This high cost coupled with high demand prohibits many patients from receiving appropriate care. Moreover, the emotional and mental strain is excessive for patients and is counterproductive to the therapy. In this paper, we tackle the boredom aspect of the rehabilitation process wherein we develop a therapy system that uses computer games to emulate the therapeutic activities. We describe, in some details, the issues involved in the development process. Commercial of the shelf product is employed (the Xbox Kinect) so the cost is significantly reduced and the accessibility is greatly increased. The system was tested on children at a local hospital, and the feedback was highly encouraging. This work opens avenues for more research to be conducted in exercise development, movement emulation, and game design. Moreover, commercialization of these games is an interesting endeavor.","PeriodicalId":438270,"journal":{"name":"2013 9th International Conference on Innovations in Information Technology (IIT)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124315847","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A novel approach to develop large-scale virtual environment applications using script-language","authors":"A. Zarrad, A. Bensefia.","doi":"10.1109/INNOVATIONS.2013.6544413","DOIUrl":"https://doi.org/10.1109/INNOVATIONS.2013.6544413","url":null,"abstract":"Modern Collaborative Virtual Environments (CVEs) are no longer developed as a one-piece to support specific applications such as online games, Virtual shopping, and E-health. In the traditional way, any modifications in VE applications require a service interruption in order to change both programming code and the supporting structure. As a consequence the ability to build and/or extend 3D VEs during the runtime becomes tedious task and requires long development time with advanced programming knowledge. Nowadays, it is important to offer an easy and rapid way for users and game developers to build and/or to extend CVE applications during the runtime without having the option to interrupt the system. In this paper, we propose a novel dynamic approach based on event atomic actions management, thanks to the state machine. We employ two different high-level scripting abstractions called class modeling and instance modeling. Class modeling controls what seems to be the simulation scenario, while, instance modeling controls objects and avatars behaviors in the virtual environment. Both class and instance modeling are implemented as a scripting plug-in and mastered respectively by atomic simulation and atomic behavior concepts. The atomic behavior concept is not only limited to object behaviors, it also handles the avatar facial animation parameters as defined in MPEG-4 SNHC standard. We evaluate the benefits of our proposed solution by describing a complex firefighter's game scenario. Through this scenario we explore the interaction between class and instance script modeling as well as the implication of atomic concepts on making code writing, when a VE application modification is required.","PeriodicalId":438270,"journal":{"name":"2013 9th International Conference on Innovations in Information Technology (IIT)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114729818","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"An efficient broadcasting scheme in support of military ad hoc communications in battle field","authors":"A. Karam, Liren Zhang, Abderrahmane Lakas","doi":"10.1109/INNOVATIONS.2013.6544397","DOIUrl":"https://doi.org/10.1109/INNOVATIONS.2013.6544397","url":null,"abstract":"In this paper, we present a Lemma to achieve the upper bound of coverage for broadcasting relay in military ad hoc based wireless communications in critical battle field environment. Then, a scalable random directional broadcasting relay (RDBR) scheme based on the theorem presented in the Lemma is presented, so that a source node is able to effectively determine the forwarding nodes, especially when the density of nodes is high. The numerical results show that the proposed RDBR scheme associated with relative forwarding distance and angle is able to increase the successful delivery ratio up to 10% compared to conventional distance based broadcasting approaches.","PeriodicalId":438270,"journal":{"name":"2013 9th International Conference on Innovations in Information Technology (IIT)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125597872","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Cloud forensics: A research perspective","authors":"S. Almulla, Youssef Iraqi, Andrew Jones","doi":"10.1109/INNOVATIONS.2013.6544395","DOIUrl":"https://doi.org/10.1109/INNOVATIONS.2013.6544395","url":null,"abstract":"Cloud computing and digital forensics are both developing topics and researching these topics requires an understanding of the main aspects of both cloud computing and digital forensics. In cloud computing it is necessary not only to understand its characteristics and the different services and deployment models but also to survey the underpinning elements of cloud computing such as virtualization and the distributed computing which are important to identify its impact on current digital forensics guidelines and procedures. Unlike papers discussing the challenges and opportunities presented by cloud computing in relation to digital forensics, in this paper, we will discuss the underpinning cloud computing elements which are required to provide forensics friendly cloud services. Furthermore, we suggest a set of questions that will aid in the process of cloud forensics analysis.","PeriodicalId":438270,"journal":{"name":"2013 9th International Conference on Innovations in Information Technology (IIT)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125600056","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Image in-painting techniques - A survey and analysis","authors":"S. Ravi, P. Pasupathi, S. Muthukumar, N. Krishnan","doi":"10.1109/INNOVATIONS.2013.6544390","DOIUrl":"https://doi.org/10.1109/INNOVATIONS.2013.6544390","url":null,"abstract":"Digital in-painting is relatively a young research area, yet a large variety of techniques were proposed by the researchers to correct the occlusion. Image in-painting aims to restore images with partly information loss and tries to make in-painting results as these missing parts in such a way that the reconstructed image looks natural. Many different types of image in-painting algorithms exist in the literature. However no recent study has been undertaken for a comparative evaluation of these algorithms to provide a comprehensive visualization. This paper compares different types of image in-painting algorithms. The algorithms are analyzed in both theoretical and experimental ways, which have made the suitability of these image in-painting algorithms over different kinds of applications in diversified areas.","PeriodicalId":438270,"journal":{"name":"2013 9th International Conference on Innovations in Information Technology (IIT)","volume":"68 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124279235","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Graphical description of WS-CDL","authors":"I. Yahmadi, Y. Baghdadi, Z. Al-Khanjari","doi":"10.1109/INNOVATIONS.2013.6544417","DOIUrl":"https://doi.org/10.1109/INNOVATIONS.2013.6544417","url":null,"abstract":"The widespread acceptance of SOA, as an architectural style to build solutions by composing loosely coupled, interoperable, distributed services, having separate concerns into solutions is promoting modeling of cross-organizations business processes (BPs). In these BPs, different participants from different organizations would like to participate and get involved in a collaboration to achieve a common goal. Meanwhile, Web Service Choreography Description Language (WS-CDL) is an XML-based language for describing peer-to-peer collaborations by defining from a neutral perspective their collaborative observable behavior. It defines a set of ordered message exchanges that accomplish a common business goal. Yet, this language lacks a standardized graphical description that would ease the understanding of the collaborative behavior, where different types of stakeholders need to communicate the collaboration. Our approach in this paper is to investigate the WS-CDL language and propose a graphical description by utilizing UML models.","PeriodicalId":438270,"journal":{"name":"2013 9th International Conference on Innovations in Information Technology (IIT)","volume":"61 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122575831","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"News auto-tagging using Wikipedia","authors":"Shaimaa Shams Eldin, S. El-Beltagy","doi":"10.1109/INNOVATIONS.2013.6544411","DOIUrl":"https://doi.org/10.1109/INNOVATIONS.2013.6544411","url":null,"abstract":"This paper presents an efficient method for automatically annotating Arabic news stories with tags using Wikipedia. The idea of the system is to use Wikipedia article names, properties, and re-directs to build a pool of meaningful tags. Sophisticated and efficient matching methods are then used to detect text fragments in input news stories that correspond to entries in the constructed tag pool. Generated tags represent real life entities or concepts such as the names of popular places, known organizations, celebrities, etc. These tags can be used indirectly by a news site for indexing, clustering, classification, statistics generation or directly to give a news reader an overview of news story contents. Evaluation of the system has shown that the tags it generates are better than those generated by MSN Arabic news.","PeriodicalId":438270,"journal":{"name":"2013 9th International Conference on Innovations in Information Technology (IIT)","volume":"179 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128271664","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}