Lakshmi Rajamani

Parameterless penalty function for solving constrained evolutionary optimization

A criticism of Evolutionary Algorithms might be the lack of efficient and robust generic methods to handle constraints. The most widespread approach for constrained search problems is to use penalty methods, because of their simplicity and ease of implementation. The penalty function approach is generic and applicable to any type of constraint (linear or nonlinear). Nonetheless, the most difficult aspect of the penalty function approach is to find an appropriate penalty parameters needed to guide the search towards the constrained optimum. In this paper, GAs population-based approach and Ranks are exploited to devise a penalty function approach that does not require any penalty parameter called Adaptive GA-RRWS. Adaptive penalty parameters assignment among feasible and infeasible solutions are made with a view to provide a search direction towards the feasible region. Rank-based Roulette Wheel selection operator (RRWS) is used. The new adaptive penalty and rank-based roulette wheel selection operator allow GAs to continuously find better feasible solutions, gradually leading the search near the true optimum solution. GAs with this constraint handling approach have been tested on five problems commonly used in the literature. In all cases, the proposed approach has been able to repeatedly find solutions closer to the true optimum solution than that reported earlier.

Experiments with CPU Scheduling Algorithm on a Computational Grid

The Grid is an emerging technology for enabling resource sharing and coordinated problem solving in dynamic multi-institutional virtual organizations. The resource-matching problem in the Grid involves assigning resources to tasks in order to satisfy task requirements and resource policies. Just as the World Wide Web has changed the way that society deals with information, researchers and educators now expect the grid to change the way that they deal with computing resources and, ultimately, how they deal with knowledge. It is important to mention that, so far, the computational grid has reached a much higher level of maturity than the other types of grid. This paper deals with the implementation of a computer program, which employs Grid Computing (GCs) technique in the quest for reducing the computational time. The program is written in Java and incorporates a grid-gain strategy for faster evolution. The factors like average turn around time, waiting time, and the execution time has been calculated for the given data set. Comparison has been made between the execution times of this algorithm with and without using grid environment and finally given the best choice for CPU scheduling algorithms (i.e. SJF (shortest job first), PRIORITY, and FCFS (first come first serve)) for given data set. In the future in order to construct large, repeatable experiments, a simulation environment designed to examine application scheduling on the grid such as Simgrid [7] could be used.

APD: ARM Deceptive Phishing Detector System Phishing Detection in Instant Messengers Using Data Mining Approach

Deceptive Phishing, is the major problem in Instant Messengers, one is able to disclose sensitive information, including personal information, fact or even patterns that are not supposed to be disclosed, the simplistic solution to address this problem of privacy in Instant Messengers (IM) is presented using Association Rule mining technique a data mining approach. Online criminals have adapted traditional fraudulent schemes like phishing in electronic form. Increasingly, such schemes target an individual’s IM where they mingle among masked by honest communications. The targeting and conniving nature of these schemes are an infringement upon an individual’s personal privacy as well as a threat to personal safety. In order to focus on privacy preserving the proposed APD (Anti phishing detector) system embeds association rule mining (ARM) technique in IM’s to detect deceptive phishing. There are many techniques developed to tackle e-mail phishing, a little research literature not yet done on deceptive phishing in Instant Messengers where the identification of user is often unknown to users. This is one of the motivating factor for the research project described, tested and experimented.

Probability apriori based approach to mine rare association rules

It is a difficult task to set rare association rules to handle unpredictable items since approaches such as apriori algorithm and frequent pattern-growth, a single minimum support application based suffers from low or high minimum support. If minimum support is set high to cover the rarely appearing items it will miss the frequent patterns involving rare items since rare items fail to satisfy high minimum support. In the literature, an effort has been made to extract rare association rules with multiple minimum supports. In this paper, we explore the probability and propose multiple minsup based apriori-like approach called Probability Apriori Multiple Minimum Support (PAMMS) to efficiently discover rare association rules. Experimental results show that the proposed approach is efficient.

Single lock manager approach for achieving concurrency control in mobile environments

In a mobile computing environment, users can perform on-line transaction processing independent of their physical location. In a mobile environment, multiple mobile hosts may update the data simultaneously which may result in inconsistency of data. To solve such problems many concurrency control techniques have been proposed. The traditional two phase locking protocol has some inherent problems such as deadlocks & long unpredictable blocking. In this paper we propose a concurrency control mechanism with dynamic timer adjustment which helps in reducing the communication overhead and enhances the transaction throughput. The simulation results specify the performance trade off metrics.

Deceptive phishing detection system: From audio and text messages in Instant Messengers using Data Mining approach

Deceptive Phishing is the major problem in Instant Messengers, much of sensitive and personal information, disclosed through socio-engineered text messages for which solution is proposed[2] but, detection of phishing through voice chatting technique in Instant Messengers is not yet done which is the motivating factor to carry out the work and solution to address this problem of privacy in Instant Messengers (IM) is proposed using Association Rule Mining (ARM) technique a Data Mining approach integrated with Speech Recognition system. Words are recognized from speech with the help of FFT spectrum analysis and LPC coefficients methodologies. Online criminals now-a-days adapted voice chatting technique along with text messages collaboratively or either of them in IMs and wraps out personal information leads to threat and hindrance for privacy. In order to focus on privacy preserving we developed and experimented Anti Phishing Detection system (APD) in IMs to detect deceptive phishing for text and audio collaboratively.

Automation of decision making process for selection of talented manpower considering risk factor: A data mining approach

Human Resource department (HR) plays vital and tedious role in recruiting manpower for organization and forced to use more accurate talent evaluation applications for selecting multi-talented personnel based on resumes, received in huge quantity but most of the talent evaluation applications are based on evaluating talent but not risk factors. This paper presents the solution for selecting appropriate talented personnel resumes without risk factors using association rule mining (ARM) technique of data mining. The automated intelligent agent based system (AIAS) built using knowledge-based system for decision making process on logical rules and facts obtained from domain expert and past learning experiences using ARM technique which guides the HR Department. The practical experimental results obtained from AIAS encourage HR department to take prompt decisions for recruiting talented personnel accurately without wasting interviewers time of employer and employee. The proposed system also reduces frequent resignations, improves performance of talented personnel without training cost and continuous monitoring.

Concurrency Control Strategy to Reduce Frequent Rollbacks in Mobile Environments

In a mobile database environment, multiple mobile hosts may access the similar data items independent of their physical locations. This may result in inconsistency of data items. Several Concurrency Control techniques have been proposed to eliminate the inconsistency of data items. However because of the mobility and disconnections, the traditional concurrency control strategies are not suitable in mobile environments. The timeout based mechanisms proposed to reduce the starvation problem in mobile environments doesn’t control the frequent rollbacks. In this paper we propose a preemptive dynamic timer adjustment strategy which achieves concurrency control and at the same time reduces the frequent rollbacks. Experimental results show better throughput, increase in commit rates and reduction in number of rollbacks as compared to the previous techniques.

Performance evaluation of Operating Systems in the private cloud with XenServer hypervisor using SIGAR Framework

Virtualization Technology plays prominent role in the success of cloud computing because the delivery of services is simplified by providing a platform for optimizing complex IT resources in a scalable manner, which makes cloud computing more cost effective. Hypervisors give near native performance by negating virtualization overhead. XenServer is one of the hypervisors which give near native performance using para virtualization technique. It is encouraging to study how different Operating Systems (OSes) perform in a virtualized environment in the Private Cloud with XenServer hypervisor. Guest OSes do come in Paravirtualized and Hardware Virtualized flavours and in free and commercial versions. It is innovative idea to compare them from performance perspective to give an idea about their performance variations in different tests and also to analyse the results with respect to Para versus Hardware virtualization techniques. This paper conducts different performance tests with low, medium, high workloads and results are gathered using SIGAR API (System Information Gatherer and Reporter) and explains the behaviour of each operating system and gives the reasoning of results with the help of three different virtualization techniques namely Full Virtualization, Paravirtualization and Hardware Assisted Virtualization. In the experiment, CloudStack (open source cloud computing software) is used to create a private cloud (proprietary computing architecture deployed behind a firewall with full control over infrastructure), in which management server is installed on Ubuntu 12.04 - 64 bit operating system. XenServer hypervisor is installed on bare metal as a host in the cluster. The guest operating systems are installed on XenServer hypervisor and their respective performances have been evaluated in detail by using SIGAR Framework.

Evaluation of different Operating Systems performance in the Private Cloud with ESXi hypervisor using SIGAR framework

Cloud computing model along with virtualization enables scalable infrastructures and provides on demand access to computing resources. Virtualization technology facilitates multiple virtual servers to run on a physical server to enhance the utilization of the server. Hypervisor as a virtualization layer provides an infrastructural support to multiple virtual machines above it by virtualizing hardware resources such as CPU, Memory, Disk and NIC. Hypervisors give near native performance by negating virtualization overhead. ESXi is one of the hypervisors which gives near native performance using full virtualization technique. It is encouraging to study how different Operating Systems (OSs) perform in a virtualized environment in the Private Cloud with ESXi hypervisor. Guest Operating Systems do come in para-virtualized and hardware virtualized flavors. It is innovative idea to compare them from performance perspective to give an idea about their performance variations in different tests. This paper conducts different performance tests with low, medium, high workloads and results are gathered using SIGAR API (System Information Gatherer and Reporter) and explains the behavior of each operating system and gives the reasoning of results with the help of different virtualization techniques. In the experiment, CloudStack (open source cloud computing software) is used to create a private cloud, in which management server is installed on Ubuntu 12.04 - 64 bit operating system. ESXi hypervisor is installed on bare metal as a host in the cluster. The different guest operating systems are installed on ESXi hypervisor and their performances have been evaluated in detail by using SIGAR Framework.