Volume 1, Issue 8, 2011

By | August 9, 2018

An Intra-Class Channel-Aware Scheduling in IEEE 802.16e 

Elnaz Limouchi, Mohammadali Pourmina, Afshin Salajeghe, Ashkan Zehni

Abstract: Scheduling mechanisms for both uplink and downlink channels in  IEEE 802.16 standard are open area for research. In this paper, we propose  a weighted fair priority intra class scheduling for point to multipoint mobile  WiMAX system. This method takes user’s battery charge level into account  to determine weights of the users. Simulation results show that overall system throughput is improved. 

Keywords :  WiMAX, Scheduling; OFDMA; Battery level; Resource allocation.


Detect CNP Fraudulent Transactions 

Adnan M. Al-Khatib

Abstract: Money in the e-commerce network, represents information moving at the speed of light, where fraud (digital crime) within the banking  and financial services happened very fast and can cost billions of dollars  each year-undetected and unreported. In this paper I present a comprehensive framework that mines and detect fraudulent transactions of  Card-Not-Present (CNP) in the e-payment systems with a high degree of  accuracy. 

Keywords :  Credit Card; Card-Not-Present; Fraud Detection; Data Mining;  Profiling; Accuracy; Rule.  


Improving Business Type Classification from Twitter Posts Based on Topic Model 

Chanattha Thongsuk, Choochart Haruechaiyasak, Somkid Saelee

Abstract: Today Twitter, a social networking website, has become a new  advertising channel to promote products and services using online social  network community. In this study, we propose a solution to recommend  Twitter users to follow businesses, which match their interests. Our  approach is based on classification algorithms to predict user’s interests by  analyzing their posts. The challenging issue is the short length  characteristic of Twitter posts. With only a few available key terms in each  post, classifying Twitter posts is very difficult and challenging. To alleviate  this problem, we propose a technique to improve the classification  performance by expanding the term features from a topic model to train  the classification models. A topic model is constructed from a set of topics  based on the Latent Dirichlet Allocation (LDA) algorithm. We propose two  feature processing approaches: (1) feature transformation, i.e., using a set  of topics as features and (2) feature expansion, i.e., appending a set of  topics to a set of terms. Experimental results of multi-classification showed  that the highest accuracy of 95.7% is obtained with the feature expansion  technique, an improvement of 19.1% over the Bag of Words (BOW) model.  In addition, we also compared between multi-classification and binary  classification using feature expansion approach to build the classification  models. The performance of feature expansion approach using binary  classification yielded higher accuracy than the multi-classification equal to  2.3%, 3.3% and 0.4%, for airline, food and computer & technology  businesses, respectively. 

Keywords : Classification; topic model; Latent Dirichlet Allocation (LDA);  Twitter.  


Policy Based Fast Handoff Mechanism for MANET

Ankur Gupta, A. K. Vatsa

 Abstract: Mobile ad hoc Network (MANET) has a challenging task because of  the dynamic and infrastructure less nature of the network. This dynamic  nature leads to the difficulty in handoff, addressing, routing and data  delivering process. For getting good QoS, better flexibility, effective and  efficient handoff process in this dynamic network  need better handoff  mechanism for avoiding any discontinuity, packet loss, delay and jitter  during handoff process. Therefore, it is necessary to make fast handoff  based on group mobility and policy driven approach for this network. Thus,  In this paper, We propose a policy based handoff mechanism with group  mobility over hierarchical cluster based architecture involving proactive  and reactive handoff approaches based on policy for nodes of MANET. 

Keywords : MANET (Mobile ad hoc Network); Fast Handoff; Proactive and  Reactive handoff; Policy based approach; Group mobility; Cluster head.


Solving the Puzzle Problem using a Multiagent Approach 

Kamel Khoualdi, Marwan El-Haj Mahmoud

Abstract: Toys problems, such as the puzzle problem, are solved using  classical artificial intelligence search algorithms Such as Breadth-first  search and depth-first search. These strategies requires the generation of a graph known as the state space search that consist of the different states a  problem may have. Using the above search techniques, a solution of the problem consists of a systematic exploration of the different state, starting  from an initial state and moving towards a final state. This approach is  time and memory consuming. In this paper, we propose a multiagent approach as an alternative to solve  the puzzle problem. Each block in the puzzle is considered as a reactive  agent. The paper shows how the solution is reached through the interaction  of the agents. 

Keywords : multiagent systems; puzzle problem; reactive agents; search  methods. 


Hop-by-Hop Rate Control Technique for Congestion Due to Concurrent Transmission in Wireless Sensor Network 

Rekha Chakravarthi, C.Gomathy

Abstract: Congestion plays a vital role in degrading the performance of  wireless sensor network. Thus an issue of detecting and controlling  congestion becomes essential to improve the performance of the network.  There are various sources for congestion like packet collision, buffer  overflow, concurrent transmission etc.  This paper focuses on congestion  due to concurrent transmission. We have proposed an efficient protocol to  detect and control congestion in a MAC. The level of congestion is  measured using a metric called Depth of Congestion (DC). Based on the  measured value the node effectively adapts its transmission data rate to  control congestion. This technique is implemented successfully in NS-2  simulator. Finally, simulation results have demonstrated the effectiveness  of our proposed protocol.  

Keywords : Wireless Sensor Networks; Depth of Congestion (DC); Congestion Detection; Congestion Control. 


Conniving the Information Assimilation and Retrieval (INAR) System for the Heterogeneous, Multi Related Information Sources 

L. Senthilvadivu, K. Duraiswamy

Abstract: The World Wide Web (WWW) is known for being a web of documents; however, little is known about the structure or growth of such  a web. Search engines such as Google have transformed the way people  access and use the web and have become a critical technology for finding and delivering information .In the proposed work, the tasks such as the  information assimilation and retrieval have been discussed. In the  information assimilation, the data synthesis have been done from multi  related and heterogeneous information sources and stored hierarchically.  The data can be collected from various resources under different domains.  The data are available in persistence storage by using default  programmatic methodology. In this paper we propose also a searching  algorithm to be used in web search engines that simply relies on  information that could be extracted based on user queries from multi  related and heterogeneous information resources. Hierarchical results from  Heterogeneous Domain, Build Positive Set and Fetch Positive Results are the most important aspects of the searching system. Keywords : Assimilation; Heterogeneous domain; persistence storage;  Hierarchical results.  


A Hybrid Approach for Classification of DICOM Image 

J. Umamaheswari, G. Radhamani

Abstract: Image classification is a most important step for image analysis.  As the same in medical area especially for diagnosing the disease of the  patient, classification plays a great role for the doctors to treat the patient  according to the severeness of the diseases. In case of DICOM images it is  very tough for optimal identification and early detection of diseases.  Classification is a computational procedure that separates the images into  groups according to their features that extracted. DICOM is latest medical  imaging technology. DICOM is used for brain scans and it is very useful and  effective technique to detect the dissimilarity in brain images. In this  paper a hybrid approach is proposed for DICOM image classification. The  approach consists of feature extraction and classification. The classification consists of Multi Linear Discriminent Analysis (MLDA) and Support Vector  Machine (SVM). Classification is done on the base of parameter extracted  by Gray Level Co-occurrence Matrix (GLCM) and histogram texture feature  extraction method. The feature is selected using fuzzy rough set and  Genetic Algorithm (GA). The proposed approach has high approximation  capability and much faster convergence. 

Keywords : Classification; Linear Discriminent Analysis (LDA); Support  Vector Machine (SVM); GA, Fuzzy Rough set; GLCM; Histogram Texture  feature.

Leave a Reply

Your email address will not be published. Required fields are marked *