Narrow Results

Data mining currently is a vital and core process because of advances in the technology, and numerous other forms of data. As an essential and significant constituent of data mining, classification has also become vital and a sought-after-option for research. Over the years, as various soft computing tools have been proven to be more complimentary than competitive, many hybrid approaches have evolved for pattern classification. A major thrust has always been there to apply hybrid approaches involving artificial neural network as the main tool for pattern classification. Here, one such hybrid approach is presented with application of Rough set philosophy to unsupervised artificial neural network (UANN) based pattern classifier. This enhances the performance of the classifier and makes it more suitable for real time classification applications dealing with large and unlabeled data. The idea presented here discusses with possibility and application of various Rough set based approaches at different levels of implementation of such classifier. The concluding section presents the results achieved for data of two case studies related to face recognition and mobile handoff prediction.

In this paper, a location-aided resource reservation scheme for handoff based on mobility prediction is proposed for wireless cellular networks. We analyze the performance of the proposed scheme and propose a two-dimensional random walk model for simulation. Performance evaluation is done by computing several key performance criteria, i.e., prediction accuracy, average number of reservation per call, reservation efficiency, and reservation time overhead. The influences of threshold distance, average distance where the mobile station moves along a straight line, location error and sample time are investigated, and the effectiveness of mobility prediction is also evaluated. Performance comparison reveals that the proposed scheme performs better than a solely distance-based scheme without mobility prediction.

The purpose of this paper is to evaluate the performance of H.323 handoff methods that use ad hoc multipoint conference, transfer, and third party rerouting signaling respectively. This performance is evaluated in terms of inter-operability and signaling delay. The inter-operability specification includes multipoint conference messages, H.450.2 messages, and null TerminalCapabilitySet message. The delay of each signaling is analyzed into number of TCP connections and number of logical channel setup procedures. The results of our experiment show that third party rerouting signaling has better result than other signalings in inter-operating with terminals of four vendors, since it uses only H.323 mandatory messages. Also it requires fewer number of TCP connections and logical channel setup procedures than the others do, so it can reduce the signaling delay by 1.4 sec in average.

Over the past few years, wireless mesh networks (WMNs) have emerged to become a ubiquitous solution for providing wireless access at lower cost, greater flexibility, higher reliability and performance compared to conventional wireless local area network (WLANs). As the demand for delay sensitive real-time applications such as VOIP and streaming media grows, mobility management is becoming a critical function of WMN. Although Mobility management schemes designed for Mobile Ad Hoc Networks (MANETs) and traditional fixed networks might be useful for WMNs, mobility management in WMNs is still an active research issue because of the special properties of WMNs. This chapter focuses on the mobility management in wireless mesh networks, which takes into account the unreliability of wireless mesh links and other special properties of WMNs. The chapter began by discussing the special properties of WMNs and the general concepts of mobility management, and then gives an overview of the mobility management problems in wireless mesh networks (layer 2 handoff, vertical handoff and cross layer design, etc.) with some potential solutions.