A Generalized Fuzzy Linguistic Model for Predicting Component Concentrations in an Optical Gas Sensing System

Motivated by environmental protection concerns, monitoring the flue gas of thermal power plant is now often mandatory due to the need to ensure that emission levels stay within safe limits. Optical based gas sensing systems are increasingly employed for this purpose, with regression techniques used to relate gas optical absorption spectra to the concentrations of specific gas components of interest (NOx, SO2 etc.). Accurately predicting gas concentrations from absorption spectra remains a challenging problem due to the presence of nonlinearities in the relationships and the high-dimensional and correlated nature of the spectral data. This article proposes a generalized fuzzy linguistic model (GFLM) to address this challenge. The GFLM is made up of a series of “If-Then” fuzzy rules. The absorption spectra are input variables in the rule antecedent. The rule consequent is a general nonlinear polynomial function of the absorption spectra. Model parameters are estimated using least squares and gradient descent optimization algorithms. The performance of GFLM is compared with other traditional prediction models, such as partial least squares, support vector machines, multilayer perceptron neural networks and radial basis function networks, for two real flue gas spectral datasets: one from a coal-fired power plant and one from a gas-fired power plant. The experimental results show that the generalized fuzzy linguistic model has good predictive ability, and is competitive with alternative approaches, while having the added advantage of providing an interpretable model.

Introduction: dispersed minorities and non-territorial autonomy

The concept of non-territorial autonomy gives rise to at least two important questions: the range of functional areas over which autonomy extends, and the extent to which this autonomy is indeed non-territorial. A widely used early description significantly labelled this ‘national cultural autonomy’, implying that its focus is mainly on cultural matters, such as language, religion, education and family law. In many of the cases that are commonly cited, ‘autonomy’ may not even extend this far: its most visible expression is the existence of separate electoral registers or quotas for the various groups. Part of the dilemma lies in the difficulty of devolving substantial power on a non-territorial basis: to the extent that devolved institutions are state-like, they ideally require a defined territory. Ethnic groups, however, vary in the extent to which they are territorially concentrated, and therefore in the degree to which any autonomous arrangements for them are territorial or non-territorial. This article explores the dilemma generated by this tension between ethnic geography (pattern of ethnic settlement) and political autonomy (degree of selfrule), and introduces a set of case studies where the relationship between these two features is discussed further: the Ottoman empire and its successor states, the Habsburg monarchy, the Jewish minorities of Europe, interwar Estonia, contemporary Belgium, and two indigenous peoples, the Sa´mi in Norway and the Maori in New Zealand.

A generalized fuzzy linguistic model for predicting component concentrations in an optical gas sensing system

Motivated by environmental protection concerns, monitoring the flue gas of thermal power plant is now often mandatory due to the need to ensure that emission levels stay within safe limits. Optical based gas sensing systems are increasingly employed for this purpose, with regression techniques used to relate gas optical absorption spectra to the concentrations of specific gas components of interest (NO_x, SO₂ etc.). Accurately predicting gas concentrations from absorption spectra remains a challenging problem due to the presence of nonlinearities in the relationships and the high-dimensional and correlated nature of the spectral data. This article proposes a generalized fuzzy linguistic model (GFLM) to address this challenge. The GFLM is made up of a series of “If-Then” fuzzy rules. The absorption spectra are input variables in the rule antecedent. The rule consequent is a general nonlinear polynomial function of the absorption spectra. Model parameters are estimated using least squares and gradient descent optimization algorithms. The performance of GFLM is compared with other traditional prediction models, such as partial least squares, support vector machines, multilayer perceptron neural networks and radial basis function networks, for two real flue gas spectral datasets: one from a coal-fired power plant and one from a gas-fired power plant. The experimental results show that the generalized fuzzy linguistic model has good predictive ability, and is competitive with alternative approaches, while having the added advantage of providing an interpretable model.