MORABITO F.C. - VERSACI M.; IJCNN2001. Prediction and Estimation of Atmospheric Pollutant Levels by Soft Computing Approach

Abstract
The goal of this paper is to design an environmental monitoring system able to estimate and predict the pollutant values of an important city area on the strait of Messina (Italy). In order to solve the problem, we propose the use of neuro-fuzzy inference techniques. This approach utilizes the concepts of Fuzzy Inference Systems (FIS) to estimate and predict the pollution level in the air. By using a specific MatLab® Toolbox, we carry out sophisticated FIS. Each rule of the IF…THEN structure in terms of linguistic frameworks in which the easy understanding due to the open box structure can help the politicians to take decisions about the urban traffic.

VERSACI M - MORABITO F.C.; MIC2002. A Comparison Between Traditional And Ellipsoidal Fuzzy Systems To Estimate And Predict Hydrocarbons Concentration In The Air

Abstract
The goal of this paper is to design an environmental monitoring system able to estimate and predict the pollutant values of an important city area on the strait of Messina (Italy). In order to solve the problem, we propose the use of neuro-fuzzy inference techniques. This approach utilizes the concepts of Fuzzy Inference Systems (FIS) to estimate and predict the pollution level in the air. By using a specific MatLab® Toolbox, we carry out sophisticated FIS. Each rule of the IF…THEN structure in terms of linguistic frameworks in which the easy understanding due to the open box structure can help the politicians to take decisions about the urban traffic.

VERSACI M - MORABITO F.C.; ASM2002 Creta (Grecia). A Soft Computing Approach for Forecasting Pollutants Concentration in the Air

Abstract
The goal of this paper is to predict pollutants concentrations in the air of Villa San Giovanni, a small town located in front of Messina Strait (Italy). Fuzzy inference systems and fuzzy time series models have been exploited in order to prediction of hydrocarbons concentration in the air. In particular, B and B* algorithms are exploited for our purposes. The achieved results are encouraging especially regarding the prediction of pollutant concentrations till four hours later, which represents the time needed to take decisions about the traffic regulation.

VERSACI M - MORABITO F.C.; ICAIET2002. Prediction of Hydrocarbons Concentration in the Air by means of a Two Factors Time-Variant Fuzzy Time Series Model

Abstract
Villa San Giovanni, a town located in front of Messina Strait, plays a strategic role in the European transportation network because its port represents the main embarking point of the ferry boat service to Sicily and vice versa. Consequently, due to the crossing and heavy vehicular traffic, organic and inorganic compounds can be often found in the urban atmosphere at a concentration higher than the alarm level fixed by law strongly affecting the health of citizens. In addition, ferries themselves are responsible in increasing the concentration of pollutants in some zones of Villa San Giovanni. The goal of this paper is the short time prediction of hydrocarbons concentration in the urban atmosphere, which in the case study represents the most dangerous pollutant because it exceeded the alarm threshold many times in the period under study. By means of Fuzzy Time Series, we are able to predict hydrocarbons concentration in the air, where the main factor is the pollutant (hourly sampled) and the secondary factor is the traffic (hourly number of vehicles). In particular, B and B* algorithms are exploited for our purposes. The achieved results are encouraging especially regarding the prediction of pollutant concentrations one hour later, which represents the time needed to take decisions about the traffic regulation.

MORABITO F.C. - VERSACI M.; IJCNN2002. Wavelet Neural Network Processing of Urban Air Pollution

Abstract
We present a multi-resolution dynamic forecasting system (MDFS) based on neural networks for multi-step prediction of a time series of urban air pollutant data (hydrocarbons, HC). The MDFS utilizes the wavelet transform and the Daubechies mother wavelet to compute the wavelet coefficients of the original signal at various scales and a recurrent neural network (RNN) in the wavelet coefficient space to form a set of dynamic non-linear models of the sub-bands of the data. The decomposition strategy is suggested by the Fourier analysis of the time series showing cyclical components. The global system is capable o predict the time series of the HC data with both long-term (coarse) and short-term (fine) resolution. The proposed approach can manage nonstationarity in the data and is suitable for on-line computation.

MORABITO F.C. - VERSACI M.; NATO. Environmental Data Interpretation: Intelligent Systems for Modeling and Prediction of Urban Air Pollution Data

Abstract
Environmental data processing is based on modelling and prediction of time series whose dynamic evolution is the result of the concurrence of many variables. The goal of this paper is to show how some recent advances in data driven approaches (like Artificial Neural Networks, ANN, and Fuzzy Inference Systems, FIS) can be of help to environmental problems solution. These kind of intelligent systems can be useful in environmental data analysis and interpretation from various perspectives: to perform knowledge discovery in large environmental databases ("environmental data mining"), to make prediction, to explain and interpret data and non linear correlation among predicting variables. The output of the intelligent processing systems can also facilitate decision making. Environmental data show some characteristics features and peculiarities (noise, non linearity, non stationarity, missing data, …) that largely justifies the use of data oriented models. Here we propose some specific open ended issues in environmental monitoring (in particular, in air pollution monitoring and control) which require a modern approach for their assessment: identificaton and diagnosis of a given situation based on the processing of time and spatially varying data; forecasting of a solution; inverse modelling. The paper will illustrate real practical applications in which intelligent systems have been deliberately introduced in the processing chains to solve problems that appears to be "unsolvable" by making use of more traditional statistical and model-based approach. The paper will hopefully stimulate a wide interest on environmental data analysis and monitoring within the framework of supervised and unsupervised learning.

MORABITO F.C. - VERSACI M.; NEURAL NETWORKS. Fuzzy Neural Identification and Forecasting Techniques to Process Experimental Urban Air Pollution Data

Abstract
This paper focuses on the processing of experimentally measured pollution data. Measuring locally both air quality parameters and atmospheric data can show how complex can be their interrelations and how they change spatially. Furthermore, apart from physical and biochemical dependencies, who important aspects need to be incorporated in the model, traffic data and topographic information, like presence and configuration of buildings and road. Since estimating the evolution of pollutant in the urban air can have significant economic impact already on a short term basis as well as relevant consequences on public health on a medium-long term scale, various interdisciplinary researches are under way on this subject. In this work, we pursue two goal. The first one is to derive a representative model of the multivariate relationships that should be able to reproduce local interactions; the second goal of the paper is to predict, when possible, the short term evolution of pollutants in order to prevent the onset of above threshold levels of pollutants that can be dangerous to humans. The threshold levels of interest are fixed by both EU recommendations and regional regulations. As a by-product of the research, we could derive some directives to be supplied to local authorities to properly organize car traffic in advance based on the estimated parameters. The case study here proposed is that of Villa San Giovanni, a small town at the tip of Italy, located just in front of Sicily, on the Messina Strait. This is a significant case, since the city is affected by the heavy traffic directed (and coming from) Sicily. The main results here reported include the short time prediction of the concentration of Hydrocarbons (HC) in the local air, the comparison between different methods based on fuzzy neural systems, and the proposal of local models of non-linear interactions, among traffic, atmospheric and pollution data. Additionally, comments on a longer horizon forecast are given.