Francesco Corona

Extreme learning machines for soybean classification in remote sensing hyperspectral images

This paper focuses on the application of Extreme Learning Machines (ELM) to the classification of remote sensing hyperspectral data. The specific aim of the work is to obtain accurate thematic maps of soybean crops, which have proven to be difficult to identify by automated procedures. The classification process carried out is as follows: First, spectral data is transformed into a hyper-spherical representation. Second, a robust image gradient is computed over the hyper-spherical representation allowing an image segmentation that identifies major crop plots. Third, feature selection is achieved by a greedy wrapper approach. Finally, a classifier is trained and tested on the selected image pixel features. The classifiers used for feature selection and final classification are Single Layer Feedforward Networks (SLFN) trained with either the ELM or the incremental OP-ELM. Original image pixel features are computed following a Functional Data Analysis (FDA) characterization of the spectral data. Conventional ELM training of the SLFN improves over the classification performance of state of the art algorithms reported in the literature dealing with the data treated in this paper. Moreover, SLFN-ELM uses less features than the referred algorithms. OP-ELM is able to find competitive results using the FDA features from a single spectral band.

Data-derived soft-sensors for biological wastewater treatment plants: An overview

Abstract This paper surveys and discusses the application of data-derived soft-sensing techniques in biological wastewater treatment plants. Emphasis is given to an extensive overview of the current status and to the specific challenges and potential that allow for an effective application of these soft-sensors in full-scale scenarios. The soft-sensors presented in the case studies have been found to be effective and inexpensive technologies for extracting and modelling relevant process information directly from the process and laboratory data routinely acquired in biological wastewater treatment facilities. The extracted information is in the form of timely analysis of hard-to-measure primary process variables and process diagnostics that characterize the operation of the plants and their instrumentation. The information is invaluable for an effective utilization of advanced control and optimization strategies.

Non-parametric residual variance estimation in supervised learning

The residual variance estimation problem is well-known in statistics and machine learning with many applications for example in the field of nonlinear modelling. In this paper, we show that the problem can be formulated in a general supervised learning context. Emphasis is on two widely used non-parametric techniques known as the Delta test and the Gamma test. Under some regularity assumptions, a novel proof of convergence of the two estimators is formulated and subsequently verified and compared on two meaningful study cases.

On Nonparametric Residual Variance Estimation

In this paper, the problem of residual variance estimation is examined. The problem is analyzed in a general setting which covers non-additive heteroscedastic noise under non-iid sampling. To address the estimation problem, we suggest a method based on nearest neighbor graphs and we discuss its convergence properties under the assumption of a Hölder continuous regression function. The universality of the estimator makes it an ideal tool in problems with only little prior knowledge available.

Residual variance estimation in machine learning

The problem of residual variance estimation consists of estimating the best possible generalization error obtainable by any model based on a finite sample of data. Even though it is a natural generalization of linear correlation, residual variance estimation in its general form has attracted relatively little attention in machine learning. In this paper, we examine four different residual variance estimators and analyze their properties both theoretically and experimentally to understand better their applicability in machine learning problems. The theoretical treatment differs from previous work by being based on a general formulation of the problem covering also heteroscedastic noise in contrary to previous work, which concentrates on homoscedastic and additive noise. In the second part of the paper, we demonstrate practical applications in input and model structure selection. The experimental results show that using residual variance estimators in these tasks gives good results often with a reduced computational complexity, while the nearest neighbor estimators are simple and easy to implement.

Bounds on the mean power-weighted nearest neighbour distance

In this paper, bounds on the mean power-weighted nearest neighbour distance are derived. Previous work concentrates mainly on the infinite sample limit, whereas our bounds hold for any sample size. The results are expected to be of importance, for example in statistical physics, non-parametric statistics and computational geometry, where they are related to the structure of matter as well as properties of statistical estimators and random graphs.

On the topological modeling and analysis of industrial process data using the SOM

In this paper, we overview and discuss the implementation of topology-based approaches to modeling and analyzing industrial process data. Emphasis is given to the representation of the data obtained with the self-organizing map (SOM). The methods are used in visualizing process measurements and extracting relevant information by exploiting the topological structure of the observations. Benefits of the SOM with industrial data are presented for a set of process measurements measured in an industrial gas treatment plant. The practical goal is to identify significant operational modes and most sensitive process variables before developing an alternative control strategy. The results confirmed that the SOM-based approach is capable of providing valuable information and offers possibilities for direct application to other process monitoring tasks.

Minimal Learning Machine

In this work, a novel supervised learning method, the Minimal Learning Machine (MLM), is proposed. Learning in MLM consists in building a linear mapping between input and output distance matrices. In the generalization phase, the learned distance map is used to provide an estimate of the distance from K output reference points to the unknown target output value. Then, the output estimation is formulated as multilateration problem based on the predicted output distance and the locations of the reference points. Given its general formulation, the Minimal Learning Machine is inherently capable of operating on nonlinear regression problems as well as on multidimensional response spaces. In addition, an intuitive extension of the MLM is proposed to deal with classification problems. A comprehensive set of computer experiments illustrates that the proposed method achieves accuracies that are comparable to more traditional machine learning methods for regression and classification thus offering a computationally valid alternative to such approaches.

Extreme learning machine: a robust modeling technique? yes!

In this paper is described the original (basic) Extreme Learning Machine (ELM). Properties like robustness and sensitivity to variable selection are studied. Several extensions of the original ELM are then presented and compared. Firstly, Tikhonov-Regularized Optimally-Pruned Extreme Learning Machine (TROP-ELM) is summarized as an improvement of the Optimally-Pruned Extreme Learning Machine (OP-ELM) in the form of a L2 regularization penalty applied within the OP-ELM. Secondly, a Methodology to Linearly Ensemble ELM (ELM-ELM) is presented in order to improve the performance of the original ELM. These methodologies (TROP-ELM and ELM-ELM) are tested against state of the art methods such as Support Vector Machines or Gaussian Processes and the original ELM and OP-ELM, on ten different data sets. A specific experiment to test the sensitivity of these methodologies to variable selection is also presented.

Nitrous Oxide Production at a Fully Covered Wastewater Treatment Plant: Results of a Long-Term Online Monitoring Campaign

The nitrous oxide emissions of the Viikinmäki wastewater treatment plant were measured in a 12 month online monitoring campaign. The measurements, which were conducted with a continuous gas analyzer, covered all of the unit operations of the advanced wastewater-treatment process. The relation between the nitrous oxide emissions and certain process parameters, such as the wastewater temperature, influent biological oxygen demand, and ammonium nitrogen load, was investigated by applying online data obtained from the process-control system at 1 min intervals. Although seasonal variations in the measured nitrous oxide emissions were remarkable, the measurement data indicated no clear relationship between these emissions and seasonal changes in the wastewater temperature. The diurnal variations of the nitrous oxide emissions did, however, strongly correlate with the alternation of the influent biological oxygen demand and ammonium nitrogen load to the aerated zones of the activated sludge process. Overall, the annual nitrous oxide emissions of 168 g/PE/year and the emission factor of 1.9% of the influent nitrogen load are in the high range of values reported in the literature but in very good agreement with the results of other long-term online monitoring campaigns implemented at full-scale wastewater-treatment plants.