N. R. Sunitha

TL;DR: A deep-learning based model is proposed that is a hybrid of artificial neural network (ANN), autoencoder and semi-supervised generative adversarial network (GAN) and triumphs excellent accuracy than other models towards click fraud detection.

TL;DR: This work proposes a new feature selection mechanism, an amalgamation of the filter and the wrapper techniques by taking into consideration the benefits of both the methods, based on a two phase process where the features are ranked and the best subset of features are chosen based on the ranking.

TL;DR: The proposed model, CFXGB (Cascaded Forest and XGBoost), is a combination of two learning models used for feature transformation and classification that showcases its superior performance compared to other related models, and makes a comparison with multiple click fraud datasets with varying sizes.

TL;DR: A matrix- based key pre-distribution scheme for SCADA systems that supports device join, leave and key update operations with less communication cost and is compared with existing schemes through simulation results and analyzing the findings.

TL;DR: The objective of the proposed work is to model multi-time-scale time series data on AR/MA by relying only on time and the label without the need of too many attributes and to model different time scales separately on Auto-regression (AR) and Moving Average (MA) models.