Accepted Papers

  • Robust Real Time Face Recognition and Tracking On GPU Using Fusion of RGB and Depth Image
    Narmada Naik and G.N Rathna, Indian Institute of science, India.
    This paper presents a real-time face recognition system using kinect sensor. The algorithm is implemented on GPU using opencl and significant speed improvements are observed. We use kinect depth image to increase the robustness and reduce computational cost of conventional LBP based face recognition. The main objective of this paper was to perform robust, high speed fusion based face recognition and tracking.
  • XML Security Technologies
    Abd El-Aziz Ahmed ,Cairo UNI,Egypt
    XML has been widely adopted for information exchange across various networks due to flexibility providing common syntax for messaging systems. XML documents may contain private information that cannot be shared by all user communities. Therefore, XML Security has a great importance to the overall security of the distributed systems. In this paper, two XML security technologies, namely, XML signature and encryption have been presented. It presents an overview of how they integrate with XML in such a way, as to maintain the advantages and capabilities of XML, while adding the necessary security capabilities.
  • The Development of Electronic Document Archiving System for Mindanao University of Science and Technology
    Love Jhoye Raboy, Dwiff Baconguis, Rose Glenn Fuentes and Lee Jonuel Bagabuyo, Mindanao University of science and technology, Philippines
    Manual handling of the documents is hard to manage due to these factors such as possible misplaced of documents, lost documents and searching is time consuming especially when the documents stored increases in volume. The study aims to develop an Electronic Document Archiving System (EDAS) that can help offices keep back-up copies of their physical files or documents and provide easy search and retrieval of the documents. The EDAS produces a digitized copy from a hard copy document through capturing an image of it. Various Application Programming Interfaces (APIs) was used to link the input devices, which are the webcam and scanner, in consolidating the images into one document and for archiving the files. Specified document information and keyword tagging method were applied to act as a metadata of the files that are stored in the database. Metadata serves as a complete tag of each files generated, that can be used in the identification of files. A text search query was used to match the metadata of files in searching and retrieval of the file. EDAS average searching time is 0.09 seconds while manual searching takes 20.59 seconds. The result of the study states that the overall system searching time is 99.56% faster than the manual searching.
  • Intentional approach to improve the discovery of Web services
    Sara Alaoui, ENSIAS, Morocco
    The web service discovery is mechanism of locating a Web Service which description match with the costumer request. The performance of discovery depends on the satisfaction of user intent; however this satisfaction has two main limitations: (1) the huge quantity of information available through the Internet, and (2) mismatch between the low level, technical software-service descriptions, and high level expressions of user needs. To overcome this problem, we propose in this paper to enrich the service oriented architecture (SOA) by an intentional approach to reduce a distance between the user and the service.
  • Subject-based Algorithm for Association Rules Classification
    Manijeh Abbasi,Computer Faculty of Technology and Science University, Iran.
    One of the techniques in the field of data mining is association rules. As an initial definition of these techniques, we must say: Often there is a close correlation between a given set of data, so the association rules that we sometimes called them the dependence rules or the community rules are made and applied for generating new patterns among the data. In finding the community rules generally we do not follow any particular purpose and we just look in finding all the relationships and dependencies, while the category purpose is clearly defined.

    This paper inverstigates the sorting methods in this field with emphasis on the classification based on subject methods (expert's interference), statistical and mathematical methods and also phasic methods. The items of the community rules that are very similar to each other and they also are numeroususually need the expert's idea for classification. Subject matter algorithms are one of the algorithms kinds which are present for classification and grouping. The algorithm presented here is a method for association rules classification with the expert's idea. The tested data shown here are those in the medical field and the algorithm and the algorithm here with using Apriori algorithm produces the rules for the dataand as before the expert idea is used here as a data value parameter so the rules are valuable, the Early zadeh rule is used here. In the next section, 5 classes are considered as number of groups or classes that are determined according to their values and the expert's idea. After that the rules with different values assign to these groups. The next step is the user's interact with the system; the desired signs are matched with the rules at the science site and cause to find the desired rules from those classes.One step of the algorithm is an update rule parameter that evaluates the errors of the system; and after some repetitions and algorithm run, it detects the right class rules. The utility isused for the evaluation of the algorithm factors, these factors change according to the time and the number of repetition. It means that the less time of the use of the rules, the more use of the algorithm evaluation; so called the utility of the rule is increased and this led to an increase in the speed of the algorithm. It should be noted that this algorithm does not follow any particular hypothesis and it is a general methodology.
  • Have WLAN networks outgrown their usefulness?A viability study of WLAN Networks in DenseNets: an analysis based on QoS/QoE and handover
    Jéssica Castilho, Marcelo Moraes, Ramz Fraiha, Jasmine Araujo and Carlos Frances, Federal University of Para, Brazil
    In this paper, we addressed the question of WLAN as an efficient alternative to offload traffic from basic access networks not only as a supplementary technology but as the key technology in terms of coverage, quality and mobility analysis. Thus, mesh networks, based on IEEE 802.11 standard, have emerged as an alternative to provide a network infrastructure to metropolitan areas, due to its low cost and the fact that it is easy to install, maintain and expand. In this study a performance analysis of the influence of mobility and handoff on video reception, (based on the measurements of a mesh network) was carried out to validate the initial estimates of an exponential increase in the future traffic of cellular networks.
  • Supervised Classification of Satellite Images to Analyze Multi-Temporal Land Use and Coverage: A Case Study for the town of Marabá, State of Pará, Brazil
    Priscila Siqueira Aranha, Flavia Pessoa Monteiro and Paulo André Ignácio Pontes, Federal University of Para, Brazil
    Amazon has one of the most complex and diversified biome of the planet. Its environmental preservation has an impact in the global scenario. However, besides the environmental aspects, the complexity of the region involves other different aspects such as social, economical and cultural. In fact, they are intrinsically interrelated in such a way, that, for example, cultural aspects may affect on the relationships between land use and coverage when the focus is Amazon. Moreover, depending on the scale of such changes, there may be consequences on the planet.

    This is very critical for the region and several government actions as well as actions from organizations, social movements and international community seek to rationalize the land use and coverage with a focus on sustainable exploration of natural resources.

    An important government program is the settlements with a proper support with respect to certain access to financial resources for infrastructure, equipment, seeds, seedlings, technical assistance, etc.

    However, in spite of the all the involved efforts, a solution is extremely complex as correlation of factors to be evaluated and combined towards success and improvement of such programs. Thus, with all this complexity, it is of fundamental importance to employ technological tools to quantitatively measure the degree of evolution of land use and coverage in the regions that are part of Amazon biome. One of the fundamental evaluations is the observation of the evolution of change in land use as it is a variable that changes with time and implicates on the natural landscape and environment as a whole. This paper proposes a innovative methodology to investigate changes in critical factors in the environment based on a case study in the 26th March Settlement, in the city of Marabá, State of Pará, in the Brazilian Amazon. In order to conduct such study of land use, LANDSAT 5 satellite images as well as data from TeraClass project were used to apply CART algorithm. The proposed methodology demonstrated, from the obtained results, an improvement of the efficiency of the classification technique to determine different thematic classes as well as a substantial improvement in the precision of 0.97Kappa indices. One more aspect is the process of automation in the process with a minimum computational effort in performing the required analyses. The developed framework may be used to improve the government programs as well as to serve as a tool for the society to monitor and inspect.
  • Using Spectral Radius Ratio for Node Degree to Analyze the Evolution of Scale-Free Networks and Small-World Networks
    Natarajan Meghanathan, Jackson State University, United States.
    In this paper, we show the evaluation of the spectral radius for node degree as the basis to analyze the variation in the node degrees during the evolution of scale-free networks and small-world networks. Spectral radius is the principal eigenvalue of the adjacency matrix of a network graph and spectral radius ratio for node degree is the ratio of the spectral radius and the average node degree. We observe a very high positive correlation between the spectral radius ratio for node degree and the coefficient of variation of node degree (ratio of the standard deviation of node degree and average node degree). We show how the spectral radius ratio for node degree can be used as the basis to tune the operating parameters of the evolution models for scale-free networks and small-world networks as well as evaluate the impact of the number of links added per node introduced during the evolution of a scale-free network and evaluate the impact of the probability of rewiring during the evolution of a small-world network from a regular network.
  • A novel Hybrid Evolutionary Algorithm for Solving Multi-objective Optimization of Master Production Scheduling Problems
    Jalal Sultan and Abdulhakeem Hasan, University of Mosul, Iraq
    Maximizing customer service level, minimizing inventory level and overtime, and respecting safety stock levels are conflicting objectives which make part of the optimization of most master production scheduling problems. In such cases, using a multiobjective optimization approach may represent the complexity of the problem more precisely. It is therefore suggested the use of heuristic and artificial intelligence techniques to find near to optimal (some times even optimal) solutions in acceptable time. In this paper, a novel hybrid evolutionary algorithm (ICA-GA) is proposed, which integrates the merits of both Imperialist competitive algorithm and Genetic algorithm for solving multi-objective MPS problems. In the proposed algorithm, the Colonies in each empire has be represented a small population and communicate with each other using Genetic operators. By testing on 5 production scenarios, the numerical results of ICA-GA algorithm show the efficiency and capabilities of the new hybrid algorithm in finding the optimum solutions, the ICA-GA solutions yield the lower inventory level and keep customer satisfaction high and the required overtime is also lower, compared with results of GA and SA in all production scenarios.
  • Applicability and Performance Analysis of Vehicular Ad-hoc Network Routing Protocols in Different Traffic Scenarios
    Parul Tyagi and Deepak Dembla, JECRC University, Jaipur, India
    With rapid and widespread dissemination of Infostations, Roadside units and communication capable on-board units, wireless communication and secure access technologies are expected to evolve and gain ubiquitous presence. Wireless communication has become an embedded part of almost every electronic component and its reach has extended to daily life objects such as smart-vehicles and smart-homes. These pervasive devices make use of networks such as IEEE 802.11, 3G/4G, WiMAX, multimedia networks and wireless sensor networks for data transmission and device to device communication. Such protocols have largely integrated into the next-generation communication networks, known as ad-hoc networks. Two broad categories of ad-hoc networks are the mobile ad-hoc networks and the vehicular ad-hoc networks, where the latter has emerged as a subfield of the former and are aimed at providing safety to vehicle drivers by initiating autonomous communication with the nearby vehicles. Each vehicle in the ad-hoc network acts as an intelligent mobile node characterized by high mobility and formation of dynamic large scale networks.

    This paper analyses the efficient and secure communication requirements for vehicular communications. The prerequisites for such communication varies significantly from traditional wireless communication as the vehicles are consistently in motion and real-time multimedia applications require more bandwidth. The essential factors that need to be examined are throughput, packet collision, and call drop. Various protocols have been developed to specifically cater to the needs of ad-hoc communication, and some commonly used protocols are found to offer an array of advantages over the others. Consequently, selection of routing protocols is important in these vehicular communications which call for specific real-time application requirements. This paper presents a comparison of two leading VANET routing protocols: the Dynamic Source Routing (DSR) protocol with the Ad-hoc On-demand Distance Vector (AODV) routing protocol. Simulation results show that DSR outperforms AODV in data communication.
  • Performance Analysis and Quality-of-service Monitoring of Packet flow in TCP Networks in VANET
    Parul Tyagi and Deepak Dembla, JECRC University, Jaipur, India
    The research trends in computer and wireless communication networks are growingly facilitated with the emergence of various Network Simulation tools. Network simulation software enables users to model network behavior demonstrating the packet transmission behavior and interaction amongst the nodes. These models are further used to analyze and predict the behavior of a computer network on various devices such as links and applications. Network Simulators also permit these network topologies to be studied and tested on several popular protocols such as WLAN, Wi-Max, TCP, WSN, cognitive radio. The network analyses are often characterized by rules defining the network topologies, goals & objectives of the data packet transmissions between nodes, outcomes & feedback, conflict resolution, competition for bandwidth, interaction, and efficient message communication.

    This paper analyses the performance and quality-of-service of packet flow in TCP networks in VANET using novel network simulator and emulator known as NCTUns. The investigation and study of various VANET topologies is facilitated by NCTUns architecture, simulation methodology, functional design and execution steps. NCTUns offers a series of advantages over other contemporary network simulators where the outcomes of diverse quality of service (QoS) and resource management and schemes implemented on higher-layer protocols can be easily studied. Most importantly, NCTUns allows testing of time-consuming, complex or extravagant topologies without emulating them using hardware. This paper reviews Diffserv model used for monitoring packet flows in TCP architecture and gives an insight into the analysis of such networks.
  • Study of Wavelet Image Compression : JPEG2000 Standard
    Mohammed Erritali and Ansam Ennaciri, TIAD laboratory, Morocco
    If you have an image or a video and want to transmit it over a network, you will need to compress it to reduce the weight of the file in kilobytes. Many studies have focused on image compression techniques. In this paper, we only present the division based on wavelet compression that has recently become a highly debated research topic. The objective of this article is to study the main characteristics of wavelets that affect the image compression by using the discrete wavelet transform and lead to an image data compression while preserving the essential quality of the original image. This implies a good compromise between the image compression ratio and the PSNR (Peak Signal Noise Ration).
  • Semantic Indexing Approach Of a Corpora Based On Ontology
    Mohammed Erritali, Sultan Moulay Slimane University, Morocco
    This paper presents a new semantic indexing approach of a documentary corpus. The indexing process starts first by a term weighting phase to determine the importance of these terms in the documents .Then we will use a thesaurus like Wordnet to move to the conceptual level.
    Each candidate concept is evaluated by determining its level of representation of the document, that is to say, the importance of the concept in relation to other concepts of the document. Finally, the actual semantic index is constructed by attaching to each concept of the ontology, the documents of the corpus in which these concepts are found.
  • Classification of Brain Tissues Using A Hybrid Model Based on FCMPSO algorithm and Possibility Theory Context
    Lamiche Chaabane, M'sila university, Algeria
    In this research work, we propose an unsupervised method for the classification of the human brain tissues. The developed approach is based on particle swarm optimization (PSO) algorithm, fuzzy c-means clustering algorithm (FCM) and some of ideas of the possibility theory context. The fusion methodology is decomposed into three fundamental phases. We modeling information coming from T2 and PD weighted images in a common framework, in this step an hybridization between PSO and FCM algorithms is used. In the second phase, we combine the extracted data by an operator of fusion. Finally, an image of fusion is generated when a decision rule is applied. To validate the effectiveness of the proposed method, some results are presented using a set of simulated MRI image.
  • Clustering Assisted Fundamental Matrix Estimation
    Hao Wu and Yi Wan, Lanzhou University, China
    In computer vision, the estimation of the fundamental matrix is a basic problem that has been extensively studied. The accuracy of the estimation imposes a significant influence on subsequent tasks such as the camera trajectory determination and 3D reconstruction. In this paper we propose a new method for fundamental matrix estimation that makes use of clustering a group of 4D vectors. The key insight is the observtion that among the 4D vectors constructed from matching pairs of points obtained from the SIFT algorithm, well-defined cluster points tend to be reliable inliers suitable for fundamental matrix estimation. Based on this, we utilizes a recently proposed efficient clustering method through density peaks seeking and propose a new clustering assisted method. Experimental results show that the proposed algorithm is faster and more accurate than currently commonly used methods.


Copyright ® COSIT 2015