Backward elimination model construction for regression and classification using leave-one-out criteria

A fundamental principle in practical nonlinear data modeling is the parsimonious principle of constructing the minimal model that explains the training data well. Leave-one-out (LOO) cross validation is often used to estimate generalization errors by choosing amongst different network architectures (M. Stone, "Cross validatory choice and assessment of statistical predictions", J. R. Stast. Soc., Ser. B, 36, pp. 117-147, 1974). Based upon the minimization of LOO criteria of either the mean squares of LOO errors or the LOO misclassification rate respectively, we present two backward elimination algorithms as model post-processing procedures for regression and classification problems. The proposed backward elimination procedures exploit an orthogonalization procedure to enable the orthogonality between the subspace as spanned by the pruned model and the deleted regressor. Subsequently, it is shown that the LOO criteria used in both algorithms can be calculated via some analytic recursive formula, as derived in this contribution, without actually splitting the estimation data set so as to reduce computational expense. Compared to most other model construction methods, the proposed algorithms are advantageous in several aspects; (i) There are no tuning parameters to be optimized through an extra validation data set; (ii) The procedure is fully automatic without an additional stopping criteria; and (iii) The model structure selection is directly based on model generalization performance. The illustrative examples on regression and classification are used to demonstrate that the proposed algorithms are viable post-processing methods to prune a model to gain extra sparsity and improved generalization.

Land-cover classification from airborne LIDAR data fused with aerial optical images

Airborne LIght Detection And Ranging (LIDAR) provides accurate height information for objects on the earth, which makes LIDAR become more and more popular in terrain and land surveying. In particular, LIDAR data offer vital and significant features for land-cover classification which is an important task in many application domains. In this paper, an unsupervised approach based on an improved fuzzy Markov random field (FMRF) model is developed, by which the LIDAR data, its co-registered images acquired by optical sensors, i.e. aerial color image and near infrared image, and other derived features are fused effectively to improve the ability of the LIDAR system for the accurate land-cover classification. In the proposed FMRF model-based approach, the spatial contextual information is applied by modeling the image as a Markov random field (MRF), with which the fuzzy logic is introduced simultaneously to reduce the errors caused by the hard classification. Moreover, a Lagrange-Multiplier (LM) algorithm is employed to calculate a maximum A posteriori (MAP) estimate for the classification. The experimental results have proved that fusing the height data and optical images is particularly suited for the land-cover classification. The proposed approach works very well for the classification from airborne LIDAR data fused with its coregistered optical images and the average accuracy is improved to 88.9%.

Classification of instability modes in a model of aluminium reduction cells with a uniform magnetic field

A unified view on the interfacial instability in a model of aluminium reduction cells in the presence of a uniform, vertical, background magnetic field is presented. The classification of instability modes is based on the asymptotic theory for high values of parameter β, which characterises the ratio of the Lorentz force based on the disturbance current, and gravity. It is shown that the spectrum of the travelling waves consists of two parts independent of the horizontal cross-section of the cell: highly unstable wall modes and stable or weakly unstable centre, or Sele’s modes. The wall modes with the disturbance of the interface being localised at the sidewalls of the cell dominate the dynamics of instability. Sele’s modes are characterised by a distributed disturbance over the whole horizontal extent of the cell. As β increases these modes are stabilized by the field.

Identifying problematic classes in text classification

Real-world text classification tasks often suffer from poor class structure with many overlapping classes and blurred boundaries. Training data pooled from multiple sources tend to be inconsistent and contain erroneous labelling, leading to poor performance of standard text classifiers. The classification of health service products to specialized procurement classes is used to examine and quantify the extent of these problems. A novel method is presented to analyze the labelled data by selectively merging classes where there is not enough information for the classifier to distinguish them. Initial results show the method can identify the most problematic classes, which can be used either as a focus to improve the training data or to merge classes to increase confidence in the predicted results of the classifier.

Variable selection for financial distress classification using a genetic algorithm

This paper is concerned with the use of a genetic algorithm to select financial ratios for corporate distress classification models. For this purpose, the fitness value associated to a set of ratios is made to reflect the requirements of maximizing the amount of information available for the model and minimizing the collinearity between the model inputs. A case study involving 60 failed and continuing British firms in the period 1997-2000 is used for illustration. The classification model based on ratios selected by the genetic algorithm compares favorably with a model employing ratios usually found in the financial distress literature.

Sector, region or function? A MAD reassessment of real estate diversification in Great Britain

This paper re-examines whether it is more advantageous in terms of risk reduction to diversify by sector or region by comparing the performance of the ‘conventional’ regional classification of the UK with one based on modern socio-economic criteria using a much larger real estate data set than any previous study and the MAD portfolio approach. The general conclusion of this analysis is that property market sectors still dominate regions, however defined and so should be the first level of analysis when developing a portfolio diversification strategy. This is in line with previous research. When the performance of Functional groups is compared with the ‘conventional’ administrative regions the results here show that, when functionally based, groupings can in some cases provide greater risk reduction. In addition the underlying characteristics of these functional groups may be much more insightful and acceptable to real estate portfolio managers in considering the assets that a portfolio might contain.

The monitoring of ecological quality and the classification of standing waters in temperate regions: a review and proposal based on a worked scheme for British waters

This paper reviews the ways that quality can be assessed in standing waters, a subject that has hitherto attracted little attention but which is now a legal requirement in Europe. It describes a scheme for the assessment and monitoring of water and ecological quality in standing waters greater than about I ha in area in England & Wales although it is generally relevant to North-west Europe. Thirteen hydrological, chemical and biological variables are used to characterise the standing water body in any current sampling. These are lake volume, maximum depth, onductivity, Secchi disc transparency, pH, total alkalinity, calcium ion concentration, total N concentration,winter total oxidised inorganic nitrogen (effectively nitrate) concentration, total P concentration, potential maximum chlorophyll a concentration, a score based on the nature of the submerged and emergent plant community, and the presence or absence of a fish community. Inter alia these variables are key indicators of the state of eutrophication, acidification, salinisation and infilling of a water body.

PMCRI: a parallel modular classification rule induction framework

In a world where massive amounts of data are recorded on a large scale we need data mining technologies to gain knowledge from the data in a reasonable time. The Top Down Induction of Decision Trees (TDIDT) algorithm is a very widely used technology to predict the classification of newly recorded data. However alternative technologies have been derived that often produce better rules but do not scale well on large datasets. Such an alternative to TDIDT is the PrismTCS algorithm. PrismTCS performs particularly well on noisy data but does not scale well on large datasets. In this paper we introduce Prism and investigate its scaling behaviour. We describe how we improved the scalability of the serial version of Prism and investigate its limitations. We then describe our work to overcome these limitations by developing a framework to parallelise algorithms of the Prism family and similar algorithms. We also present the scale up results of a first prototype implementation.

Parallel induction of modular classification rules

The Distributed Rule Induction (DRI) project at the University of Portsmouth is concerned with distributed data mining algorithms for automatically generating rules of all kinds. In this paper we present a system architecture and its implementation for inducing modular classification rules in parallel in a local area network using a distributed blackboard system. We present initial results of a prototype implementation based on the Prism algorithm.

P-Prism: a computationally efficient approach to scaling up classification rule induction

Top Down Induction of Decision Trees (TDIDT) is the most commonly used method of constructing a model from a dataset in the form of classification rules to classify previously unseen data. Alternative algorithms have been developed such as the Prism algorithm. Prism constructs modular rules which produce qualitatively better rules than rules induced by TDIDT. However, along with the increasing size of databases, many existing rule learning algorithms have proved to be computational expensive on large datasets. To tackle the problem of scalability, parallel classification rule induction algorithms have been introduced. As TDIDT is the most popular classifier, even though there are strongly competitive alternative algorithms, most parallel approaches to inducing classification rules are based on TDIDT. In this paper we describe work on a distributed classifier that induces classification rules in a parallel manner based on Prism.

Towards a computationally efficient approach to modular classification rule induction

Induction of classification rules is one of the most important technologies in data mining. Most of the work in this field has concentrated on the Top Down Induction of Decision Trees (TDIDT) approach. However, alternative approaches have been developed such as the Prism algorithm for inducing modular rules. Prism often produces qualitatively better rules than TDIDT but suffers from higher computational requirements. We investigate approaches that have been developed to minimize the computational requirements of TDIDT, in order to find analogous approaches that could reduce the computational requirements of Prism.

J-PMCRI: a methodology for inducing pre-pruned modular classification rules

Inducing rules from very large datasets is one of the most challenging areas in data mining. Several approaches exist to scaling up classification rule induction to large datasets, namely data reduction and the parallelisation of classification rule induction algorithms. In the area of parallelisation of classification rule induction algorithms most of the work has been concentrated on the Top Down Induction of Decision Trees (TDIDT), also known as the ‘divide and conquer’ approach. However powerful alternative algorithms exist that induce modular rules. Most of these alternative algorithms follow the ‘separate and conquer’ approach of inducing rules, but very little work has been done to make the ‘separate and conquer’ approach scale better on large training data. This paper examines the potential of the recently developed blackboard based J-PMCRI methodology for parallelising modular classification rule induction algorithms that follow the ‘separate and conquer’ approach. A concrete implementation of the methodology is evaluated empirically on very large datasets.

Induction of modular classification rules: using Jmax-pruning

The Prism family of algorithms induces modular classification rules which, in contrast to decision tree induction algorithms, do not necessarily fit together into a decision tree structure. Classifiers induced by Prism algorithms achieve a comparable accuracy compared with decision trees and in some cases even outperform decision trees. Both kinds of algorithms tend to overfit on large and noisy datasets and this has led to the development of pruning methods. Pruning methods use various metrics to truncate decision trees or to eliminate whole rules or single rule terms from a Prism rule set. For decision trees many pre-pruning and postpruning methods exist, however for Prism algorithms only one pre-pruning method has been developed, J-pruning. Recent work with Prism algorithms examined J-pruning in the context of very large datasets and found that the current method does not use its full potential. This paper revisits the J-pruning method for the Prism family of algorithms and develops a new pruning method Jmax-pruning, discusses it in theoretical terms and evaluates it empirically.

Jmax-pruning: a facility for the information theoretic pruning of modular classification rules

The Prism family of algorithms induces modular classification rules in contrast to the Top Down Induction of Decision Trees (TDIDT) approach which induces classification rules in the intermediate form of a tree structure. Both approaches achieve a comparable classification accuracy. However in some cases Prism outperforms TDIDT. For both approaches pre-pruning facilities have been developed in order to prevent the induced classifiers from overfitting on noisy datasets, by cutting rule terms or whole rules or by truncating decision trees according to certain metrics. There have been many pre-pruning mechanisms developed for the TDIDT approach, but for the Prism family the only existing pre-pruning facility is J-pruning. J-pruning not only works on Prism algorithms but also on TDIDT. Although it has been shown that J-pruning produces good results, this work points out that J-pruning does not use its full potential. The original J-pruning facility is examined and the use of a new pre-pruning facility, called Jmax-pruning, is proposed and evaluated empirically. A possible pre-pruning facility for TDIDT based on Jmax-pruning is also discussed.