Sarina Sulaiman

Intelligent Web Caching Using Neurocomputing and Particle Swarm Optimization Algorithm

Web caching is a technology for improving network traffic on the internet. It is a temporary storage of Web objects (such as HTML documents) for later retrieval. There are three significant advantages to Web caching; reduced bandwidth consumption, reduced server load, and reduced latency. These rewards have made the Web less expensive with better performance. In this paper, an Artificial Intelligence (AI) approach is introduced for Web caching to determine the type of Web request, either to cache or not, and to optimize the performance on Web cache. Two methods are employed in this study; Artificial Neural Network (ANN), and Particle Swarm Optimization (PSO). The experimental results have revealed that some improvements have been accomplished compared to the existing technique in terms of Web cache size.

Rough Neuro-PSO Web caching and XML prefetching for accessing Facebook from mobile environment

Prefetching and Web caching have been known as techniques to increase the speed of Web loading process. Previous studies have been conducted to infuse artificial intelligence such as Artificial Neural Network (ANN) into Web caching. In this paper, we propose a new hybrid technique based on combination of ANN and Particle Swarm Optimization (PSO) for classification Web object either to cache or not and generate rules from log data by using Rough Set technique on proxy server (Rough Neuro-PSO). It is needed because mobile context has limited resources like speed and memory. Our method is by using XML file for prefetching which is saved into mobile memory. Prefetching that used xml file is much faster to be searched or accessed. In Web caching side, we enhance the speed by using Rough Neuro-PSO in order to choose the log. At the end of this paper, we present a new framework that is believed to speed up the access of Web page in mobile environment context.

An Implementation of Rough Set in Optimizing Mobile Web Caching Performance (Invited Paper)

The stipulation of internet content rises dramatically in recent years. Servers have become extremely powerful and the bandwidth of end user connections and backbones grew constantly during the previous decade. Nonetheless, users frequently experience poor performance to access web sites or download files primarily if mobile devices have been used due to their limited storage, processing, display, power and communication resources. The causes are often performance which access directly on the servers (e.g. pitiable performance of server-side applications or during burst crowds) and network infrastructure (e.g. long geographical distances, network overloads,etc.). Hence, the goal of this study is to propose Rough Set (RS) as a knowledge representation for uncertainty in data of client behavior and mobile event specification with resource dependencies to reduce latency by prefetching selected resources to resolve the problems in handling dynamic web pages. We conducted the trace-based experiments on the RS approach for better classification outcomes.

Rough Web Caching

The demand for Internet content rose dramatically in recent years. Servers became more and more powerful and the bandwidth of end user connections and backbones grew constantly during the last decade. Nevertheless users often experience poor performance when they access web sites or download files. Reasons for such problems are often performance problems, which occur directly on the servers (e.g. poor performance of server-side applications or during flash crowds) and problems concerning the network infrastructure (e.g. long geographical distances, network overloads, etc.). Web caching and prefetching have been recognized as the effective schemes to alleviate the service bottleneck and to minimize the user access latency and reduce the network traffic. In this chapter, we model the uncertainty in Web caching using the granularity of rough set (RS) and inductive learning. The proposed framework is illustrated using the trace-based experiments from Boston University Web trace data set.

Fusion Global-Local-Topology Particle Swarm Optimization for Global Optimization Problems

In recent years, particle swarm optimization (PSO) has been extensively applied in various optimization problems because of its structural and implementation simplicity. However, the PSO can sometimes find local optima or exhibit slow convergence speed when solving complex multimodal problems. To address these issues, an improved PSO scheme called fusion global-local-topology particle swarm optimization (FGLT-PSO) is proposed in this study. The algorithm employs both global and local topologies in PSO to jump out of the local optima. FGLT-PSO is evaluated using twenty (20) unimodal and multimodal nonlinear benchmark functions and its performance is compared with several well-known PSO algorithms. The experimental results showed that the proposed method improves the performance of PSO algorithm in terms of solution accuracy and convergence speed.

Web caching and prefetching: What, why, and how?

The demand for Internet content rose dramatically in recent years. Servers became more and more powerful and the bandwidth of end user connections and backbones grew constantly during the last decade. Nevertheless users often experience poor performance when they access web sites or download files. Reasons for such problems are often performance problems which occur directly on the servers (e.g. poor performance of server-side applications or during flash crowds) and problems concerning the network infrastructure (e.g. long geographical distances, network overloads, etc.). Web caching and prefetching have been recognized as the effective schemes to alleviate the service bottleneck, minimize the user access latency and reduce the network traffic. In this paper, we express the discussion on what is the Web caching and prefetching, why we have to opt its and how to pertain of these two technologies.

Intelligent Web caching using Adaptive Regression Trees, Splines, Random Forests and Tree Net

Web caching is a technology for improving network traffic on the internet. It is a temporary storage of Web objects (such as HTML documents) for later retrieval. There are three significant advantages to Web caching; reduced bandwidth consumption, reduced server load, and reduced latency. These rewards have made the Web less expensive with better performance. The aim of this research is to introduce advanced machine learning approaches for Web caching to decide either to cache or not to the cache server, which could be modelled as a classification problem. The challenges include identifying attributes ranking and significant improvements in the classification accuracy. Four methods are employed in this research; Classification and Regression Trees (CART), Multivariate Adaptive Regression Splines (MARS), Random Forest (RF) and TreeNet (TN) are used for classification on Web caching. The experimental results reveal that CART performed extremely well in classifying Web objects from the existing log data and an excellent attribute to consider for an accomplishment of Web cache performance enhancement.

A knowledge-based approach to facilitate queries by hajj pilgrims

Hajj pilgrims need to undergo a proper and comprehensive training before leaving their mother countries in order to perform a successful and rewarding hajj. Despite of being trained, the pilgrims might not be aware of some rules and regulations that may affect their hajj rituals or rites if the pilgrims do not follow them. They may have many queries pertaining to hajj rituals, which cannot be found in their guidebooks. They could have the queries while doing any of the rituals in the middle of the crowded areas and might need to call the experts to solve the queries. However if they cannot contact the experts at the moment, they might not be able to find the solution immediately. We propose a question and answer (Q&A) expert system using a knowledge-based approach to facilitate queries by the hajj pilgrims either before or while performing their hajj rituals. We have developed the research prototype on a Web-based application, which we suggest to be installed on kiosks located around Mecca or Madinah or in handheld devices. This paper covers the theoretical aspects of knowledge-based approach to facilitate queries by hajj pilgrims. We also discuss some basic examples of how the approach can be realized in a hajj Q&A system as a personalized e-hajj guidebook.

A point-based semi-automatic expertise classification (PBaSE) method for knowledge management of an online Special Interest Group

An online Special Interest Group is a group of people with the same interest gather to form an online community through the Internet. In certain cases where the knowledge is being manipulated, the portal of a Special Interest Group is in a form of knowledge portal. This portal allows interaction among its community members. Interaction through forum in the portal makes activities such as discussion of problems and knowledge sharing among each other possible. The need to classify users’ expertise in a Special Interest Group is crucial task. This paper describes a Point-based Semiautomatic Expertise classification method to classify users’ expertise in a Special Interest Group knowledge portal.

Meaningless to meaningful Web log data for generation of Web pre-caching decision rules using Rough Set

Web caching and pre-fetching are vital technologies that can increase the speed of Web loading processes. Since speed and memory are crucial aspects in enhancing the performance of mobile applications and websites, a better technique for Web loading process should be investigated. The weaknesses of the conventional Web caching policy include meaningless information and uncertainty of knowledge representation in Web logs data from the proxy cache to mobile-client. The organisation and learning task of the knowledge-processing for Web logs data require explicit representation to deal with uncertainties. This is due to the exponential growth of rules for finding a suitable knowledge representation from the proxy cache to the mobileclient. Consequently, Rough Set is chosen in this research to generate Web pre-caching decision rules to ensure the meaningless Web log data can be changed to meaningful information.