PSG College of Technology

About: PSG College of Technology is a based out in . It is known for research contribution in the topics: Machining & Thin film. The organization has 3174 authors who have published 3575 publications receiving 40690 citations.

HTTP botnet detection using adaptive learning rate multilayer feed-forward neural network

Abstract: Botnets have become a rampant platform for malicious attacks, which poses a significant threat to internet security. The recent botnets have begun using common protocols such as HTTP which makes it even harder to distinguish their communication patterns. Most of the HTTP bot communications are based on TCP connections. In this work some TCP related features have been identified for the detection of HTTP botnets. With these features a Multi-Layer Feed Forward Neural Network training model using Bold Driver Back-propagation learning algorithm is created. The algorithm has the advantage of dynamically changing the learning rate parameter during weight updation process. Using this approach, Spyeye and Zeus botnets are efficiently identified. A comparison of the actively trained neural network model with a C4.5 Decision Tree, Random Forest and Radial Basis Function indicated that the actively learned neural network model has better identification accuracy with less false positives.

Influence of nano titanium dioxide finish, prepared by sol-gel technique, on the ultraviolet protection, antimicrobial, and self-cleaning characteristics of cotton fabrics

Abstract: The performance of ultraviolet (UV) protection, antimicrobial activity, and self-cleaning characteristics of nano titanium dioxide (TiO2) with acrylic binder were assessed on the cotton fabric usin...

Optimization of continuous biodiesel production from rubber seed oil (RSO) using calcined eggshells as heterogeneous catalyst

Abstract: The present study illustrates about the continuous biodiesel production from rubber seed oil (RSO) as feedstock using calcium oxide (CaO) derived from eggshells as heterogeneous catalyst. Optimization of experimental parameters like methanol: oil molar ratio (mol/mol), residence time (hours) and catalyst concentration (wt % (oil)) using two different optimization tools response surface methodology (RSM) and artificial neural networks (ANN) was investigated. 97.84 % conversion of RSO to biodiesel was observed at optimum process conditions of 9:1 M ratio (mol/mol), 4 (hours) of residence time and 5 (wt % (oil)) catalyst concentration. A compelling design model with methanol: oil molar ratio as the influencing parameter on final response was observed from RSM studies. A mean square error (MSE) value of 4.4 × 10−5 at the best validation performance of 1.3421 at epoch-2 in ANN model was observed. On comparing the coefficient of determination R2 of value 0.9118 obtained from RSM and 0.99 obtained from ANN it was concluded that ANN model fits well with experimental data in continuous biodiesel production from RSO using calcined eggshells as catalyst.