Accepted Papers

  • Jelly Fish Periodic Drop Attack using Voice Traffic under MANET
    Sunil Kumar, Punjab Agricultural University, India
    ABSTRACT

    Mobile ad hoc network got outstanding success as well as tremendous attention due to its self maintenance and self configuration properties or behavior. Mobile Ad hoc Networks (MANETs) work without any fixed infrastructure and each node in the network behaves as a router in order to transmit data towards the destination. MANET’s are vulnerable to various types of attacks due to inherently in-secure wireless communication medium and multi hop routing communication process. Jelly Fish periodic drop attack is a new Denial of Service (DoS) attack. In Periodic Drop attack, JF nodes randomly discard some packets over a specified period during communication process over the network. Due to congestion, a node is forced to drop packets and if node drops packets periodically then TCP throughput will reduce to zero good put. In this paper, an implementation of periodic drop attack is implemented using routing protocols over voice based traffic in MANET. In addition to this, our simulation results also shed some light on the seriousness of the attacks caused by JF nodes and their effects on data communication.

  • An Intelligent Decision Support System For Assessing The Default Risk In Small And Medium-Sized Enterprises
    Diana Manjarres1,Itziar Landa-Torres1 and Imanol Andonegui2, 1TECNALIA Research & Innovation, E-48160 Derio, Spain and 2 University of the Basque Country UPV/EHU, Spain
    ABSTRACT

    In the last years, default prediction systems have become an important tool for a wide variety of financial institutions, such as banking systems or credit business, for which being able of detecting credit and default risks, translates to a better financial status. Nevertheless, small and medium-sized enterprises did not focus its attention on customer default prediction but in maximizing the sales rate. Consequently, many companies could not cope with the customers' debt and ended up closing the business. In order to overcome this issue, this paper presents a novel decision support system for default prediction specially tailored for small and medium-sized enterprises that retrieves the information related to the customers in an Enterprise Resource Planning (ERP) system and obtains the default risk probability of a new order or client. The resulting approach has been tested in a Graphic Arts printing company of The Basque Country allowing taking prioritized and preventive actions with regard to the default risk probability and the customer's characteristics. Simulation results verify that the proposed scheme achieves a better performance than a naïve Random Forest (RF) classification technique in real scenarios with unbalanced datasets.

  • Chaotic Prey Predator Algorithm
    Surafel Lulesged Tilahun and Jean Medard T Ngnotchouye, University of KwaZulu-Natal, South Africa
    ABSTRACT

    Prey predator algorithm is a recently introduced metaheuristic optimization algorithm. It uses a trial and error approach with a learning mechanism based on random steps from uniform probability distribution. It has been tested on different applications and found to be effective. Chaotic maps are non-repetitive and erogodic, hence suitable to properly explore the solution space. It has been used in different algorithms are found to be effective. Hence, in this paper, a chaotic prey predator algorithm will be discussed. The chaotic mapping replace the random step lengths from the uniform distribution. Simulation results show that the ended outperform the standard algorithm.

  • Efficient Individual Plankton Separation From Clumped Plankton Images
    YoungsungSoh and QadirMudasar, Myongji University, Korea
    ABSTRACT

    In the plankton image, planktons of same species may appear separated or clumped. To count the number of planktons in the clumped plankton image, we need to separate them into individual planktons. In Korea, there are three harmful species that cause red tide, blood poisoning, etc. Two of them are round shape and one is rod type. We propose an efficient separation method for round type planktons. We use concavity detection method with clustering algorithm to find concavity points and adopt average curvature based extrapolation technique to retrieve planktons with shape as close to the original as possible. We applied the method to many clumped images of two round type harmful species and obtained more than 95% separation accuracy.

  • Enhancing The Performance Of Sentiment Analysis Supervised Learning Using Sentiments Keywords Based Technique
    Amira Abdelwahab, Fahd Alqasemi, and Hatem Abdelkader, Menoufia University, Egypt
    ABSTRACT

    Sentiment Analysis (SA) and machine learning techniques are collaborating to understand the attitude of text writer, implied in particular text. Although, SA is an important challenging itself, it is very important challenging in Arabic language. In this paper, we are enhancing sentiment analysis in Arabic language. Our approach had begun with a special pre-processing steps. Then, we had adopted sentiment keywords co-occurrence measure (SKCM), as an algorithm extracted sentiment-based feature selection method. This feature selection method had utilized on three sentiment corpora using SVM classifier. We compared our approach with some traditional methods, followed by most SA works. The experimental results were very promising for enhancing SA accuracy

  • Preventing Direct Url Access In Viewing Intellectual Property (IP) Details In Intellectual Property Management System (Ipms)
    Nooraisyah Saat , Mimos Berhad, Malaysia
    ABSTRACT

    Sentiment Analysis (SA) and machine learning techniques are collaborating to understand the attitude of text writer, implied in particular text. Although, SA is an important challenging itself, it is very important challenging in Arabic language. In this paper, we are enhancing sentiment analysis in Arabic language. Our approach had begun with a special pre-processing steps. Then, we had adopted sentiment keywords co-occurrence measure (SKCM), as an algorithm extracted sentiment-based feature selection method. This feature selection method had utilized on three sentiment corpora using SVM classifier. We compared our approach with some traditional methods, followed by most SA works. The experimental results were very promising for enhancing SA accuracy

  • Light Weight Solution For Stem And Leaf Classification In Black Tea Industry
    Nalin D. Karunasinghe, A.Yasara Dissanayake, Asela Priyadarshana, Buddhika Pathirana Jayawardhana, Lakmini Chathurika , University of Moratuwa, Sri Lanka
    ABSTRACT

    Sentiment Analysis (SA) and machine learning techniques are collaborating to understand the attitude of text writer, implied in particular text. Although, SA is an important challenging itself, it is very important challenging in Arabic language. In this paper, we are enhancing sentiment analysis in Arabic language. Our approach had begun with a special pre-processing steps. Then, we had adopted sentiment keywords co-occurrence measure (SKCM), as an algorithm extracted sentiment-based feature selection method. This feature selection method had utilized on three sentiment corpora using SVM classifier. We compared our approach with some traditional methods, followed by most SA works. The experimental results were very promising for enhancing SA accuracy

  • Identifying False Data Injection Attacks In Industrial Control Systems Using Artificial Neural Networks
    Sasanka Potluri, Girish Kumar Reddy Sangala and Christian Diedrich, Otto-von-Guericke University Magdeburg, Germany
    ABSTRACT

    Sentiment Analysis (SA) and machine learning techniques are collaborating to understand the attitude of text writer, implied in particular text. Although, SA is an important challenging itself, it is very important challenging in Arabic language. In this paper, we are enhancing sentiment analysis in Arabic language. Our approach had begun with a special pre-processing steps. Then, we had adopted sentiment keywords co-occurrence measure (SKCM), as an algorithm extracted sentiment-based feature selection method. This feature selection method had utilized on three sentiment corpora using SVM classifier. We compared our approach with some traditional methods, followed by most SA works. The experimental results were very promising for enhancing SA accuracy

  • Probabilistic Model Checking of One-Dimensional Nano Communication System
    Athraa Juhi, Dariusz R. Kowalski, Alexei Lisitsa, University of Liverpool, UK
    ABSTRACT

    Molecular communication is considered a bio-inspired paradigm, in which molecules are transmitted, propagated and received between nanoscale machines. Establishing controlled molecular transmissions between theses nanomachines represents a major challenge. Many studies have aimed to model the physical medium (channel) of molecular communication, primarily from a communication or informationtheoretical perspective. The main objective of this paper is to model a simple time-slotted communication system between nanoscale machines in a one-dimensional environment. This communication system employs some bio-inspired rules that can be checked at each interval. The system model has been verified using the probabilistic model checking tool PRISM on different sized networks

Copyrights @ CCSIT 2017