Mikko Kolehmainen

Analysis of gene expression data using self-organizing maps.

DNA microarray technologies together with rapidly increasing genomic sequence information is leading to an explosion in available gene expression data. Currently there is a great need for efficient methods to analyze and visualize these massive data sets. A self‐organizing map (SOM) is an unsupervised neural network learning algorithm which has been successfully used for the analysis and organization of large data files. We have here applied the SOM algorithm to analyze published data of yeast gene expression and show that SOM is an excellent tool for the analysis and visualization of gene expression profiles.

Neural networks and periodic components used in air quality forecasting

Abstract Forecasting of air quality parameters is one topic of air quality research today due to the health effects caused by airborne pollutants in urban areas. The work presented here aims at comparing two principally different neural network methods that have been considered as potential tools in that area and assessing them in relation to regression with periodic components. Self-organizing maps (SOM) represent a form of competitive learning in which a neural network learns the structure of the data. Multi-layer perceptrons (MLPs) have been shown to be able to learn complex relationships between input and output variables. In addition, the effect of removing periodic components is evaluated with respect to neural networks. The methods were evaluated using hourly time series of NO2 and basic meteorological variables collected in the city of Stockholm in 1994–1998. The estimated values for forecasting were calculated in three ways: using the periodic components alone, applying neural network methods to the residual values after removing the periodic components, and applying only neural networks to the original data. The results showed that the best forecast estimates can be achieved by directly applying a MLP network to the original data, and thus, that a combination of the periodic regression method and neural algorithms does not give any advantage over a direct application of neural algorithms.

Extensive evaluation of neural network models for the prediction of NO2 and PM10 concentrations, compared with a deterministic modelling system and measurements in central Helsinki

Five neural network (NN) models, a linear statistical model and a deterministic modelling system (DET) were evaluated for the prediction of urban NO2 and PM10 concentrations. The model evaluation work considered the sequential hourly concentration time series of NO2 and PM10, which were measured at two stations in central Helsinki, from 1996 to 1999. The models utilised selected traffic flow and pre-processed meteorological variables as input data. An imputed concentration dataset was also created, in which the missing values were replaced, in order to obtain a harmonised database that is well suited for the inter-comparison of models. Three statistical criteria were adopted: the index of agreement (IA), the squared correlation coefficient (R2) and the fractional bias. The results obtained with various non-linear NN models show a good agreement with the measured concentration data for NO2; for instance, the annual mean of the IA values and their standard deviations range from 0.86±0.02 to 0.91±0.01. In the case of NO2, the non-linear NN models produce a range of model performance values that are slightly better than those by the DET. NN models generally perform better than the statistical linear model, for predicting both NO2 and PM10 concentrations. In the case of PM10, the model performance statistics of the NN models were not as good as those for NO2 over the entire range of models considered. However, the currently available NN models are neither applicable for predicting spatial concentration distributions in urban areas, nor for evaluating air pollution abatement scenarios for future years.

Evolving the neural network model for forecasting air pollution time series

Abstract The modelling of real-world processes such as air quality is generally a difficult task due to both their chaotic and non-linear phenomenon and high dimensional sample space. Despite neural networks (NN) have been used successfully in this domain, the selection of network architecture is still problematic and time consuming task when developing a model for practical situation. This paper presents a study where a parallel genetic algorithm (GA) is used for selecting the inputs and designing the high-level architecture of a multi-layer perceptron model for forecasting hourly concentrations of nitrogen dioxide at a busy urban traffic station in Helsinki. In addition, the tuning of GAs parameters for the problem is considered in experimental way. The results showed that the GA is a capable tool for tackling the practical problems of neural network design. However, it was observed that the evaluation of NN models is a computationally expensive process, which set limits for the search techniques.

A rigorous inter-comparison of ground-level ozone predictions

Novel statistical approaches to prediction have recently been shown to perform well in several scientific fields but have not, until now, been comprehensively evaluated for predicting air pollution. In this paper we report on a model inter-comparison exercise in which 15 different statistical techniques for ozone forecasting were applied to ten data sets representing different meteorological and emission conditions throughout Europe. We also attempt to compare the performance of the statistical techniques with a deterministic chemical trajectory model. Likewise, our exercise includes comparisons of sites, performance indices, forecasting horizons, etc. The comparative evaluation of forecasting performance (benchmarking) produced 1340 yearly time series of daily predictions and the results are described in terms of predefined performance indices. Through analysing associations between the performance indices, we found that the success index is of outstanding significance. For models that are excellent in predicting threshold exceedances and have a high success index, we also observe high performance in the overall goodness of fit. The 8-h average ozone concentration forecast accuracy was found to be superior to the 1-h mean ozone concentration forecast, which makes the former very significant for operational forecasting. The best forecasts were achieved for sites located in rural and suburban areas in Central Europe unaffected by extreme emissions (e.g. from industries). Our results demonstrate that a particular technique is often excellent in some respects but poor in others. For most situations, we recommend neural network and generalised additive models as the best compromise, as these can handle nonlinear associations and can be easily adapted to site specific conditions. In contrast, nonlinear modelling of the dynamical development of univariate ozone time-series was not profitable.

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.

Financial innovation

We propose an ANN/logistic credit risk hybrid model for SME lending.We find that the hybrid model is more accurate than either of the separate ones.Our study is one of few that sheds light on the hybrid model.Our study is one of few which focuses on credit risk models for SMEs.The hybrid model can help the bank decrease the errors in credit risk evaluations. Credit risk evaluation is an integral part of any lending process, and even more so for financial institutions involved in lending to SMEs. The importance of credit scoring has increased recently because of the financial crisis and increased capital requirements for banks. There are, however, only few studies that develop credit coring models for SME lending. The objective of this study is to introduce a novel, more accurate credit risk estimation approach for SMEs business lending. Based on traditional statistical methods and recent artificial intelligence (AI) techniques, we proposed a hybrid model which combines the logistic regression approach and artificial neural networks (ANN). In order to test the effectiveness and feasibility of the proposed hybrid model, we use the data of Finnish SMEs from the fiscal years 2004 to 2012. Our results suggest that the proposed ANN/logistic hybrid model is more accurate than either of the initial models ANN or logistic regression. This improvement in the accuracy of the credit scoring model decreases evaluation errors and has thereby many potential practical implications. First of all, a more accurate credit scoring model can result in better performance of the whole SME loan portfolio. Second, it can also result in lower capital requirements from the banks perspective and lower interest rates from the individual firms perspective. Combined, these effects will enhance the banks competitiveness in the market for SME loans.

Forecasting Air Quality Parameters Using Hybrid Neural Network Modelling

Urban air pollution has emerged as an acute problem in recent years because of its detrimental effects on health and living conditions. The research presented here aims at attaining a better understanding of phenomena associated with atmospheric pollution, and in particular with aerosol particles. The specific goal was to develop a form of air quality modelling which can forecast urban air quality for the next day using airborne pollutant, meteorological and timing variables.

Feature-based clustering for electricity use time series data

Time series clustering has been shown effective in providing useful information in various applications. This paper presents an efficient computational method for time series clustering and its application focusing creation of more accurate electricity use load curves for small customers. Presented approach was based on extraction of statistical features and their use in feature-based clustering of customer specific hourly measured electricity use data. The feature-based clustering was able to cluster time series using just a set of derive statistical features. The main advantages of this method were; ability to reduce the dimensionality of original time series, it is less sensitive to missing values and it can handle different lengths of time series. The performance of the approach was evaluated using real hourly measured data for 1035 customers during 84 days testing time period. After all, clustering resulted into more accurate load curves for this set of customers than present load curves used earlier. This kind of approach helps energy companies to take advantage of new hourly information for example in electricity distribution network planning, load management, customer service and billing.

Monitoring of yeast fermentation by ion mobility spectrometry measurement and data visualisation with Self-Organizing Maps

Abstract Ion mobility spectrometry (IMS) measurement combined with unsupervised neurocomputing is considered as a new potential method for on-line monitoring of fermentation and other processes producing volatile compounds that involve micro-organisms. This was demonstrated in a model system in which a strain of brewer’s yeast ( Saccharomyces cerevisiae ) was cultivated in a bench-top fermenter. Five phases of yeast growth could be detected from measurements of the exhaust gases from the fermenter, as indicated by the changes in ion mobility spectra analysed by computational methods. The data were first processed using the Self-Organizing Map (SOM) algorithm, the results showing that the phases of fermentation can be detected and identified. The cultivations were also shown by Sammon’s mapping to be comparable to a certain level of accuracy. Contaminated cultivation could be detected by its distinctive ion mobility spectrometry profile.