Mean Squared Error (MSE) has been the most widely used tool to solve the linear filter estimation or system identification problem. However, MSE gives biased results when the input signals are noisy. This paper presents a novel Error Whitening Criterion (EWC) to tackle the problem of linear system identification in the presence of additive white disturbances. We will motivate the theory behind ...

The problem of accurately estimating the Mean Squared Error (MSE) of Small Area Estimators (SAE’s) within a Fay-Herriot (1979) normal-error model is studied theoretically in the common setting where the model is fitted to a logarithmically transformed response variable. For bias-corrected EBLUP small-area point estimators, MSE formulas and estimators are provided, with biases of smaller order t...

The problem of fuzzy time series forecasting plays an important role in many scientific areas such as statistics and neural networks. While forecasting fuzzy time series, most of forecasting applications use the same length of intervals. The determination of length of intervals is significant and critical in fuzzy time series forecasting. The usage of convenient performance measure may also hav...

A minimum bit error rate (MBER) multiuser detector designed for space division multiple access (SDMA) aided orthogonal frequency division multiplexing (OFDM) systems is proposed. It is shown that the MBER detector outperforms the minimum mean squared error (MMSE) detector, since the MBER detector directly minimises the BER, while the MMSE detector minimises the mean-squared error (MSE), which d...

This paper presents the adaptation of a single layer complex valued neural network (NN) to use entropy in the cost function instead of the usual mean squared error (MSE). This network has the good property of having only one layer so that there is no need to search for the number of hidden layer neurons: the topology is completely determined by the problem. We extend the existing stochastic MSE...

Realistic systems generally are systems with various inputs and outputs also known as Multiple Input Multiple Output (MIMO). Such systems usually prove to be complex and difficult to model and control purposes. Therefore, decomposition was used to separate individual inputs and outputs. A PID is assigned to each individual pair to regulate desired settling time. Suitable parameters of PIDs obta...

In this contribution, we propose a Minimum Bit Error Rate (MBER) multiuser detector for Space Division Multiple Access (SDMA) aided Orthogonal Frequency Division Multiplexing (OFDM) systems. It is shown that the MBER detector outperforms the Minimum Mean Squared Error (MMSE) detector, since the MBER detector directly minimizes the BER, while MMSE detector minimizes the mean-squared error (MSE),...

Mean Squared Error (MSE) has been the most widely used tool to solve the linear filter estimation or system identification problem. However, MSE gives biased results when the input signals are noisy. This paper presents a novel Error Whitening Criterion (EWC) to tackle the problem of linear system identification in the presence of additive white disturbances. We will motivate the theory behind ...