Malicious websites are the most unsafe criminal exercises in cyberspace. Since a large number of users go online to access the services offered by the government and financial establishments, there has been a notable increase in malicious websites attacks for the past few years. This paper presents a model for Malicious website URL detection using Feed Forward Neural Network. The design methodology used here is Object-Oriented Analysis and Design. The model uses a Malicious website URLs dataset, which comprises 48,006 legitimate website URLs and 48,006 Malicious website URLs making 98,012 website URLs. The dataset was pre-processed by removing all duplicate and Nan values, therefore making it fit for better training performance. The dataset was segmented into X_train and y_train, X_test and y_test which holds 60% training data and 40% testing data. The X_train contains the dataset of malicious and benign websites, while the y_train holds the label which indicates if the dataset is malicious or not. For the testing dataset the X_test contains both the malicious and non-malicious websites, while the y_test holds label which indicates if the dataset is malicious or not. The model was trained using Feed Forward Neural Network, which had an optimal accuracy 97%.
Application of Neural Networks in Weather Forecasting (Published)
Weather Forecasting is the task of determining future state of the atmosphere. Accurate weather forecasting is very important because agricultural and industrial sector largely depend on it. Weather forecasting has become an important field of research in the last few decades. In most of the cases the researcher had attempted to establish a linear relationship between the input weather data and the corresponding target data. The Neural Networks package supports different types of training or learning algorithms. In this paper, the application of neural networks to study the design of neural network technique for Kanyakumary District,Tamil Nadu, India. A total of ten years of data collected for training the net work. The network is trained using the Back propagation Algorithm, Radial Basis Function, Regression Neural Network, Optical Neural Network, and Fuzzy ARTMAP Neural Network. The Fuzzy ARTMAP network can give the best overall results in terms of accuracy and training time. It is better correlated compared to the BPN,RBFN,GRNN and ONN networks. The proposed Fuzzy ARTMAP neural network can also overcome several limitations such as a highly non-linear weight update and the slow convergence rate.
An Improved Model for Financial Institutions Loan Management System: A Machine Learning Approach (Published)
The inability of financial instructions, especially the Microfinance Banks, to forecast for the need of borrowers in order to make provision for them has been a cause for concern. Applications are made and most times the reply is that funds are not available. This paper demonstrated the design and implementation of neural network model for development of an improved loan-based application management system. The back propagation algorithm was used to train the neural network model to ascertain corrections between the data and to obtain the threshold value. The data was collected over a period of three years from UCL machine learning repository. The system was designed using object oriented methodology and implemented with Java programming language and MATLAB. The results obtained showed the mean squared error values 1.09104e-12, 5.56228e-9 and 5.564314e-4 for the training, testing and validation respectively. It was seen from the result that neural network can forecast the financial market with minimum error.
DETECTION OF FETAL ELECTROCARDIOGRAM FROM MULTIVARIATE ABDOMINAL RECORDINGS BY USING WAVELETS AND NEURO-FUZZY SYSTEMS (Published)
The fetal electrocardiogram (FECG) signal is outcome of the electrical activity of the fetal heart after 21 days of the pregnancy. It contains information about the health status of the fetus and so, an early diagnosis of any cardiac defects before delivery (Specially in case of labour pain) increases the chance of the appropriate treatment. In this paper we consider one signal from the thoracic and another from abdomen of the mother. The artificial neural network fuzzy inference system (ANFIS) is used to obtain the FECG component from abdominal ECG recording and reference thoracic maternal electrocardiogram (MECG) signal. The obtained FECG is being enhanced by using wavelet transform.