Samira Chabaa

Identification and Prediction of Internet Traffic Using Artificial Neural Networks

This paper presents the development of an artificial neural network (ANN) model based on the multi-layer perceptron (MLP) for analyzing internet traffic data over IP networks. We applied the ANN to analyze a time series of measured data for network response evaluation. For this reason, we used the input and output data of an internet traffic over IP networks to identify the ANN model, and we studied the performance of some training algorithms used to estimate the weights of the neuron. The comparison between some training algorithms demonstrates the efficiency and the accu-racy of the Levenberg-Marquardt (LM) and the Resilient back propagation (Rp) algorithms in term of statistical crite-ria. Consequently, the obtained results show that the developed models, using the LM and the Rp algorithms, can successfully be used for analyzing internet traffic over IP networks, and can be applied as an excellent and fundamental tool for the management of the internet traffic at different times.

ANFIS method for forecasting internet traffic time series

In This paper we have applied the adaptive neuro-fuzzy inference system (ANFIS) which is realized by an appropriate combination of fuzzy systems and neural networks for forecasting a set of input and output data of internet traffic time series. Several statistical criteria are applied to provide the effectiveness of this model. The obtained results demonstrate that the ANFIS model present a good precision in the prediction process of internet traffic in terms of statistical indicators. This model fits well real data and provides an effective description of network condition at different times.

Review article: Identification of quadratic systems using higher order cumulants and neural networks: Application to model the delay of video-packets transmission

This work concerns the development of two approaches for the identification of diagonal parameters of quadratic systems from only the output observation. The systems considered are excited by an unobservable independent identically distributed (i.i.d), stationary zero mean, non-Gaussian process and corrupted by an additive Gaussian noise. The proposed approaches exploit higher order cumulants (HOC) (fourth order cumulants) and are the extension of the algorithms developed in the linear version 1D, which uses a non-Gaussian signal input. For test and validity purpose, these approaches are compared to recursive least square (RLS), least mean square (LMS) and neural network identification algorithms using non-linear model in noisy environment. To demonstrate the applicability of the theoretical methods on real processes, we applied the developed approaches to search for models able to describe the delay of the video-packets transmission over IP networks from video server. The simulation results show the correctness and the efficiency of the developed approaches.

Modeling non linear real processes with ANN techniques

In this paper we are interested to model real process by applying artificial neural networks technique. The performance and the aptitude of two types of this technique (multilayer perceptron neural network (MLP) and a radial basis function neural network (RBF)) are compared and applied for identifying non linear system of internet traffic network processes. In term of statistical criteria, the obtained results show the advantages of the developed model based on the RBF to describe the internet traffic.

Design of a miniaturized Microstrip Patch Antenna for a passive UHF RFID tag

This paper present a design and miniaturization of rectangular patch antenna with balanced feed. The miniaturized patch antenna for a passive radio frequency identification (RFID) tag witch can operate in the ultra-high frequency (UHF), the resonant frequency is 915MHz. The simulation was performed in High Frequency Structure Simulator Software (HFSS). The miniaturized antenna has an acceptable results in terms of efficiency, size, return loss (S11), and Input Impedance.

Identification of IP packet transmission time series using neuro-fuzzy techniques

In this paper we are interested to applied the adaptive neuro-fuzzy inference system (ANFIS) technique, which is realized by an appropriate combination of fuzzy systems and neural networks, for identifying and forecasting a set of input and output data of packet transmission over internet protocol (IP) networks. The obtained results demonstrate that the developed model presents the same statistical characteristics as those really observed. This model fits well real data and provides an effective description of network condition at different times.

Application of the MLP neural networks for analyzing non Gaussian signal

In this investigation we applied the Multi Layer Perceptron (MLP) neural networks for modeling and predicting a real non Gaussian process. The obtained results show that an agreement between predicted and measured values. The statistical error analysis used to evaluate the performance of the correlations, between measured and predicted values provides satisfactory results. The developed model is tested and compared with an other model based on Volterra system. The obtained result demonstrates the efficiency of the developed model.

Application of adaptive neuro-fuzzy inference systems for analyzing non-Gaussian signal

In this paper, we developed a model based on the adaptive neuro-fuzzy inference systems (ANFIS) for analyzing a real non Gaussian process. The obtained results show that the generated values using ANFIS techniques have similar statistical characteristics as real data. Additionally, the developed model fits well real data and can be used for predicting purpose. Compared with existing model obtained by third order moment (TOM) method, our model has better prediction accuracy.

3 th and 4 th order cumulant techniques for supervising identification of non linear systems: Application to internet network

In This paper we develop an algorithm based on the 3th and 4th order cumulant techniques for supervising identification of non linear systems. This algorithm is compared with the recursive least square (RLS) algorithm for different signal to noise ratios (SNR) and different length of output sequences. The simulation results prove the performance of the developed algorithm. In the last part, we apply it to search a pattern able to model the data of packet transmission in networks.