No abstract

Internet of things (IoT) is a revolutionary technology which changes our life and work. Many industry sectors such as manufacturing, transportation, utilities, health care, consumer electronics and automobiles are invested and adopted towards IoT technology. The major inconvenience with IoT is its safety, as it is prone to attack by hackers. Detection Systems are used to detect these intrusions to protect the information and communication systems. Hence it is essential to design an intrusion detection system for security threats of IoT networks. This paper focuses, on the development of Artificial Neural Network (ANN) based Intrusion Detection System for threat analysis in IoT network. KDD-99 data set with Denial of Service (DoS) type attack is used to train and test three different ANN models. In this research, a Feed Forward Back Propagation (FFBP) network is used to detect the DoS attack. The process of optimization of a FFBP network involves comparison of classification accuracy during both training and testing in terms of true positive and false positive rates. For the data set considered the optimised network has achieved 100% efficiency during both training and testing.

This paper is intended to present the outcome of a study conducted on the cavitation data collected from accelerometer which is installed at the down stream of the cavitation test loop, to illustrate that the hidden neurons in an ANN modelling tool, indeed, do have roles to play in percentage of classification of cavitation signal. It sheds light on the role of the hidden neurons in an Elman Recurrent type ANN model which is used to classify the cavitation signals. The results confirmed that the hidden-output connection weights become small as the number of hidden neurons becomes large and also that the trade-off in the learning stability between input-hidden and hidden-output connections exists. The Elman recurrent network propagates data from later processing stage to earlier stage. A copy of the previous values of the hidden units are maintained which allows the network to perform sequence-prediction. In the present work, the optimum number of hidden neurons is evolved through an elaborate trial and error procedure. It is concluded that our approach has a significant improvement in learning and also in classification of cavitation signals.

No abstract

No abstract