Dimitris Voukantsis

Intercomparison of air quality data using principal component analysis, and forecasting of PM10 and PM2.5 concentrations using artificial neural networks, in Thessaloniki and Helsinki

In this paper we propose a methodology consisting of specific computational intelligence methods, i.e. principal component analysis and artificial neural networks, in order to inter-compare air quality and meteorological data, and to forecast the concentration levels for environmental parameters of interest (air pollutants). We demonstrate these methods to data monitored in the urban areas of Thessaloniki and Helsinki in Greece and Finland, respectively. For this purpose, we applied the principal component analysis method in order to inter-compare the patterns of air pollution in the two selected cities. Then, we proceeded with the development of air quality forecasting models for both studied areas. On this basis, we formulated and employed a novel hybrid scheme in the selection process of input variables for the forecasting models, involving a combination of linear regression and artificial neural networks (multi-layer perceptron) models. The latter ones were used for the forecasting of the daily mean concentrations of PM₁₀ and PM₂.₅ for the next day. Results demonstrated an index of agreement between measured and modelled daily averaged PM₁₀ concentrations, between 0.80 and 0.85, while the kappa index for the forecasting of the daily averaged PM₁₀ concentrations reached 60% for both cities. Compared with previous corresponding studies, these statistical parameters indicate an improved performance of air quality parameters forecasting. It was also found that the performance of the models for the forecasting of the daily mean concentrations of PM₁₀ was not substantially different for both cities, despite the major differences of the two urban environments under consideration.

Personalized pollen-related symptom-forecast information services for allergic rhinitis patients in Europe.

We report on the development of personalized pollen‐related information services that include sensitivity categorization, threshold identification, and symptom forecasting, addressing patients with allergic rhinitis in Europe.

Predicting daily ragweed pollen concentrations using Computational Intelligence techniques over two heavily polluted areas in Europe

Forecasting ragweed pollen concentration is a useful tool for sensitive people in order to prepare in time for high pollen episodes. The aim of the study is to use methods of Computational Intelligence (CI) (Multi-Layer Perceptron, M5P, REPTree, DecisionStump and MLPRegressor) for predicting daily values of Ambrosia pollen concentrations and alarm levels for 1-7 days ahead for Szeged (Hungary) and Lyon (France), respectively. Ten-year daily mean ragweed pollen data (within 1997-2006) are considered for both cities. 10 input variables are used in the models including pollen level or alarm level on the given day, furthermore the serial number of the given day of the year within the pollen season and altogether 8 meteorological variables. The study has novelties as (1) daily alarm thresholds are firstly predicted in the aerobiological literature; (2) data-driven modelling methods including neural networks have never been used in forecasting daily Ambrosia pollen concentration; (3) algorithm J48 has never been used in palynological forecasts; (4) we apply a rarely used technique, namely factor analysis with special transformation, to detect the importance of the influencing variables in defining the pollen levels for 1-7 days ahead. When predicting pollen concentrations, for Szeged Multi-Layer Perceptron models deliver similar results with tree-based models 1 and 2 days ahead; while for Lyon only Multi-Layer Perceptron provides acceptable result. When predicting alarm levels, the performance of Multi-Layer Perceptron is the best for both cities. It is presented that the selection of the optimal method depends on climate, as a function of geographical location and relief. The results show that the more complex CI methods perform well, and their performance is case-specific for ≥2 days forecasting horizon. A determination coefficient of 0.98 (Ambrosia, Szeged, one day and two days ahead) using Multi-Layer Perceptron ranks this model the best one in the literature.

Personalized symptoms forecasting for pollen-induced allergic rhinitis sufferers

Hay fever is a pollen-induced allergic reaction that strongly affects the overall quality of life of many individuals. The disorder may vary in severity and symptoms depending on patient-specific factors such as genetic disposition, individual threshold of pollen concentration levels, medication, former immunotherapy, and others. Thus, information services that improve the quality of life of hay fever sufferers must address the needs of each individual separately. In this paper, we demonstrate the development of information services that offer personalized pollen-induced symptoms forecasts. The backbone of these services consists of data of allergic symptoms reported by the users of the Personal Hay Fever Diary system and pollen concentration levels (European Aeroallergen Network) in several sampling sites. Data were analyzed using computational intelligence methods, resulting in highly customizable forecasting models that offer personalized warnings to users of the Patient Hay Fever Diary system. The overall system performance for the pilot area (Vienna and Lower Austria) reached a correlation coefficient of r = 0.71 ± 0.17 (average ± standard deviation) in a sample of 219 users with major contribution to the Pollen Hay Fever Diary system and an overall performance of r = 0.66 ± 0.18 in a second sample of 393 users, with minor contribution to the system. These findings provide an example of combining data from different sources using advanced data engineering in order to develop innovative e-health services with the capacity to provide more direct and personalized information to allergic rhinitis sufferers.

Personalized Information Services for Quality of Life: The Case of Airborne Pollen Induced Symptoms

Allergies due to airborne pollen affect approximately 15-20% of European citizens; therefore, the provision of health related services concerning pollen-induced symptoms can improve the overall quality of life. In this paper, we demonstrate the development of personalized quality of life services by adopting a data-driven approach. The data we use consist of allergic symptoms reported by citizens as well as detailed pollen concentrations of the most allergenic taxa. We apply computational intelligence methods in order to develop models that associate pollen concentration levels with allergic symptoms on a personal level. The results for the case of Austria, show that this approach can result to accurate and reliable models; we report a correlation coefficient up to r=0.70 (average of 102 citizens). We conclude that some of these models could serve as the basis for personalized health services.

Forecasting airborne pollen concentration of Poaceae (Grass) and Oleaceae (Olive), using Artificial Neural Networks and Genetic algorithms, in Thessaloniki, Greece

The impact of airborne pollen on human health was recognized many years ago as high pollen concentrations of specific taxa are responsible for triggering allergic reactions to humans, therefore affecting the quality of life. In this study, we develop data-driven pollen concentration forecasting models for the city of Thessaloniki (Greece), using Artificial Neural Networks - Multi-Layer Perceptron (ANN-MLP). The data correspond to the time period 1987 – 2002 and consist of daily time-series of pollen concentrations and several meteorological parameters. We focus on the taxa of Poaceae (Grass) and Oleaceae (Olive), both known to be of high allergenicity to humans. The input variables (features) for the models were selected with the aid of a multi-objective optimization method that employed genetic algorithms. For this purpose, the number of features and the performance of the models were optimized. The resulting models indicated satisfactory performance with an Index of Agreement (IA) up to 0.93 when predicting pollen concentrations 1 day ahead, whereas the same statistical index decreases to 0.85 when the forecasting horizon is 7 days ahead, meaning that they are suitable for operational implementation.

Investigation of Medication Dosage Influences from Biological Weather

Airborne pollen has been associated with allergic symptoms in sensitized individuals, whereas atmospheric pollution indisputably aggravates the impact on the overall quality of life. Therefore, it is of major importance to correlate, forecast and disseminate information concerning high concentration levels of allergic pollen types and air pollutants to the public, in order to safeguard the quality of life of the population. In this study, we investigate the relationship between the Defined Daily Dose (DDD) given to patients in a triggered allergy reaction and the different levels of air pollutants and pollen types. By profiling specific atmospheric conditions, specialists may define the need for medication to individuals suffering from pollen allergy, not only according to their personal medical record but also to the existing air quality observations. Paper results indicate some interesting interrelationships between the use of medication and atmospheric quality conditions and shows that the forecasting of daily medication is possible with the aid of proper algorithms.

Application of Computational Intelligence to the Analysis of Friction Measurements

Friction and the associated wear are complex phenomena, strongly affected by the operating and environmental conditions; the mechanical, physical, and chemical properties of the contacting bodies and of the lubricant used; as well as by the treatment of the mating surfaces. In the present article, computational intelligence (CI) methods were applied in order to analyze tribological data collected during a wear experiment, aiming to demonstrate experimental results description and knowledge extraction. Following this successful initial step, CI methods were employed and proved capable of successfully modeling the behavior of parameters of interest, such as the friction coefficient. It is therefore suggested that the computational procedure proposed could be applied in experimental design and evaluation of experimental strategies, as well as in the identification of malfunctioning experimental devices.