Web Usage Data Clustering Using Improved Genetic Fuzzy C-Means Algorithm
Authors: Karunesh Gupta, Manish Shrivastava
Abstract
Web usage mining involves application of data mining techniques to discover usage patterns from the web data. Clustering is one of the important functions in web usage mining. Recent attempts have adapted the C-means clustering algorithm as well as genetic algorithms to find sets of clusters .In this paper; we have proposed a new framework to improve the web sessions’ cluster quality from fuzzy c-means clustering using Improved Genetic Algorithm (GA). Initially a fuzzy c-means algorithm is used to cluster the user sessions. The refined initial starting condition allows the iterative algorithm to converge to a “better” local minimum. And in the second step, we have proposed a new GA based refinement algorithm to improve the cluster quality. The proposed algorithm is tested with web access logs collected from the UCI dataset repository.
Biologically Active Pyrimidine Hydrazones
Authors: Srivastav Sanchit, Luhach Kanishk, Shukla Chhama, Yadav Rajender
Abstract
Pyrimidine constitutes an important class of heterocycles in drug discovery and is very well known for their anticancer, antimicrobial, antioxidant and antiviral activities. Hydrazones is a class of organic compounds with the structure R1R2C=NNH2. They are formed usually by the action of hydrazine on ketones or aldehydes and have efficient CNS depressant, analgesics activity. In the same context, Schiff bases of pyrimidine hydrazones can be prepared by the reaction of “4-(4-Chloro-phenyl)-6-methyl-2-oxo-1,2,3,4-tetrahydro-pyrimidine-5-carboxylic acid hydrazide” with various terpenes such as citral, camphor, furfuraldehyde and menthone to make Schiff bases individually by refluxing them in the presence of glacial acetic acid (as solvent) for at least 2hrs to yield their respective derivatives. The present studies revealed that Pyrimidine hydrazone derivatives could be used to synthesize the compounds having potent biological activities such as anticancer, antimicrobial, antioxidant, CNS depressant, analgesic and antiviral activities. All the prepared derivatives were under investigation for their antimicrobial activity and likely to possess the same and desired action.
Design and Optimization of Aceclofenac Sustained Release Matrix Tablets Using 32 Factorial Design
Authors: Raavi Kishna Swetha, K. S. G. Arul Kumaran, Jenila B, Ganesh P C, Sravan Kumar Y
Abstract
Design, development and optimization of Aceclofenac SR matrix tablets by direct compression technique. It is composed of two different ratios of waxes. The optimization was carried out by using 32 factorial designs with Design Expert Software. IR studies reveled that drug and the waxes are compatible with each other. The tablets were subjected for various evaluations like pre and post compression parameters. All the parameters are within the limits. The release profile showed that as the concentration of bees wax increases the drug release decreases and it was not steady after definite concentration of bees wax. This may due to poor binding between the drug and waxes. The formulation (F7) with the ratios of 0.31:0.15 bees and lanette waxes respectively Show best sustained release and flow property. The dissolution profile showed 58.74% at 8th hr. It was observed that the bees and lanette waxes fulfilled the conditions for an optimum formulation for sustain release.
Intrusion Awareness Based on Data Fusion and SVM Classification
Authors: Ramnaresh Sharma, Manish Shrivastava
Abstract
Network intrusion awareness is important factor for risk analysis of network security. In the current decade various method and framework are available for intrusion detection and security awareness. Some method based on knowledge discovery process and some framework based on neural network. These entire model take rule based decision for the generation of security alerts. In this paper we proposed a novel method for intrusion awareness using data fusion and SVM classification. Data fusion work on the biases of features gathering of event. Support vector machine is super classifier of data. Here we used SVM for the detection of closed item of ruled based technique. Our proposed method simulate on KDD1999 DARPA data set and get better empirical evaluation result in comparison of rule based technique and neural network model.
Estimation of Levocetirizine in Bulk and Formulation by Second Order Derivative Area under Curve UV-Spectrophotometric Methods
Authors: Audumbar Digambar Mali, Manojkumar Patil
Abstract
Simple, fast and reliable spectrophotometric methods were developed for determination of Levocetirizine in bulk and pharmaceutical dosage forms. The solutions of standard and the sample were prepared in Methanol. The quantitative determination of the drug was carried out using the second order Derivative Area under Curve method values measured at 247-255nm. Calibration graphs constructed at their wavelengths of determination were linear in the concentration range of Levocetirizine using 5-25μg/ml (r²=0.999) for second order Derivative Area under Curve spectrophotometric method. The proposed methods have been extensively validated as per ICH guidelines. There was no significant difference between the performance of the proposed methods regarding the mean values and standard deviations. The developed methods were successfully applied to estimate the amount of Levocetirizine in pharmaceutical formulations.