Building Support Vector Machines in the Context of Regularised Least Squares

This paper formulates a linear kernel support vector machine (SVM) as a regularized least-squares (RLS) problem. By defining a set of indicator variables of the errors, the solution to the RLS problem is represented as an equation that relates the error vector to the indicator variables. Through partitioning the training set, the SVM weights and bias are expressed analytically using the support vectors. It is also shown how this approach naturally extends to Sums with nonlinear kernels whilst avoiding the need to make use of Lagrange multipliers and duality theory. A fast iterative solution algorithm based on Cholesky decomposition with permutation of the support vectors is suggested as a solution method. The properties of our SVM formulation are analyzed and compared with standard SVMs using a simple example that can be illustrated graphically. The correctness and behavior of our solution (merely derived in the primal context of RLS) is demonstrated using a set of public benchmarking problems for both linear and nonlinear SVMs.

Machine learning classification of surgical pathology reports and chunk recognition for information extraction noise reduction

Background and aims: Machine learning techniques for the text mining of cancer-related clinical documents have not been sufficiently explored. Here some techniques are presented for the pre-processing of free-text breast cancer pathology reports, with the aim of facilitating the extraction of information relevant to cancer staging.

Materials and methods: The first technique was implemented using the freely available software RapidMiner to classify the reports according to their general layout: ‘semi-structured’ and ‘unstructured’. The second technique was developed using the open source language engineering framework GATE and aimed at the prediction of chunks of the report text containing information pertaining to the cancer morphology, the tumour size, its hormone receptor status and the number of positive nodes. The classifiers were trained and tested respectively on sets of 635 and 163 manually classified or annotated reports, from the Northern Ireland Cancer Registry.

Results: The best result of 99.4% accuracy – which included only one semi-structured report predicted as unstructured – was produced by the layout classifier with the k nearest algorithm, using the binary term occurrence word vector type with stopword filter and pruning. For chunk recognition, the best results were found using the PAUM algorithm with the same parameters for all cases, except for the prediction of chunks containing cancer morphology. For semi-structured reports the performance ranged from 0.97 to 0.94 and from 0.92 to 0.83 in precision and recall, while for unstructured reports performance ranged from 0.91 to 0.64 and from 0.68 to 0.41 in precision and recall. Poor results were found when the classifier was trained on semi-structured reports but tested on unstructured.

Conclusions: These results show that it is possible and beneficial to predict the layout of reports and that the accuracy of prediction of which segments of a report may contain certain information is sensitive to the report layout and the type of information sought.