Time series analysis is reformulated to allow processing of segmented data. This involves the reformulation of parameter estimation and order selection. Parameter estimation for autoregressive (AR) models is done by tting a single model to all segments simultaneously. Parameter estimation for moving average (MA) and the combined ARMA models can be derived entirely from long autoregressive mode...

In this article we analyze several vibration time series measured on a real fan test rig before and after it is hit by a flying object. We show first evidence that a windowed autoregressive model may be used to detect the shock after it occurred. We compare these results with a second time series that measures the rotation period of the fan. Lastly we repeat this experiment using adaptive autor...

This paper is concerned with the construction of bootstrap prediction intervals for autoregressive fractionally integrated movingaverage processes which is a special class of long memory time series. For linear short-range dependent time series, the bootstrap based prediction interval is a good nonparametric alternative to those constructed under parameter assumptions. In the long memory case, ...

This paper introduces the concept of dynamic embedding manifold (DEM), which allows the Kohonen self-organizing map (SOM) to learn dynamic, nonlinear input-ouput mappings. The combination of the DEM concept with the SOM results in a new modelling technique that we called Vector-Quantized Temporal Associative Memory (VQTAM). We use VQTAM to propose an unsupervised neural algorithm called Self-Or...

We proposed a new model for non-stationary time series analysis based on the IAR (inhomogeneous autoregressive) model, and a method for model parameter estimation when the set of basis is given [1], [2]. In this paper, we further propose a method for parameter estimation including that of basis set: we set a new condition that power of the input sequence is concentrated in low-frequency domain,...

Durbin’s methods for moving average (MA) and autoregressive-moving average (ARMA) estimation use the parameters of a long AR model to compute the MA parameters. Linear regression theory is applied to find the best AR order. This yields two different orders: one for the best predicting AR model and another one for the long AR model with the best parameter accuracy, as intermediate for Durbin’s e...

In this study, EEG signals were analyzed using autoregressive (AR) method. Parameters in AR method were realized by using maximum likelihood estimation (MLE). Results were compared with fast Fourier transform (FFT) method. It is observed that AR method gives better results in the analysis of EEG signals. On the other hand, the results have also showed that AR method can also be used for some ot...

The subject of this paper is autoregressive AR approximations of a stationary Gaus sian discrete time process based on a nite sequence of observations We adopt the non parametric minimax framework and study how well can the process be approximated by a nite order autoregressive model Our results show that a properly chosen model dimen sion leads to an optimal in order minimax estimator

In this work we will explore the theoretical connections existing between fuzzy rule-based systems (FRBS) applied on univariate time series and two statistical reference tools, the autoregressive (AR) models and the smooth transition autoregressive (STAR) model. We will show that a TSK fuzzy rule happens to be a localised AR model and that a STAR model can hence be interpreted as a restricted F...

This article aims to identify an adequate mathematical model to predict battery power depletion at the nodes of a Wireless Sensor Network (WSN), by analyzing the Received Signal Strength Indicator (RSSI). Six general models were tested, the simplest Average model, Linear Regression model, Autoregressive (AR) models and Autoregressive Moving Average (ARMA) models.The selected model (AR) presente...