A meta-learning approach to automatic kernel selection for support vector machines

Appropriate choice of a kernel is the most important ingredient of the kernel-based learning methods such as support vector machine (SVM). Automatic kernel selection is a key issue given the number of kernels available, and the current trial-and-error nature of selecting the best kernel for a given problem. This paper introduces a new method for automatic kernel selection, with empirical results based on classification. The empirical study has been conducted among five kernels with 112 different classification problems, using the popular kernel based statistical learning algorithm SVM. We evaluate the kernels’ performance in terms of accuracy measures. We then focus on answering the question: which kernel is best suited to which type of classification problem? Our meta-learning methodology involves measuring the problem characteristics using classical, distance and distribution-based statistical information. We then combine these measures with the empirical results to present a rule-based method to select the most appropriate kernel for a classification problem. The rules are generated by the decision tree algorithm C5.0 and are evaluated with 10 fold cross validation. All generated rules offer high accuracy ratings.

Development of a contact probe incorporating a bragg grating strain sensor for nano coordinate measuring machines

This paper presents a novel optical fibre based micro contact probe system with high sensitivity and repeatability. In this optical fibre probe with a fused spherical tip, a fibre Bragg grating has been utilized as a strain sensor in the probe stem. When the probe tip contacts the surface of the part, a strain will be induced along the probe stem and will produce a Bragg wavelength shift. The contact signal can be issued once the wavelength shift signal is produced and demodulated. With the fibre grating sensor element integrated into the probe directly, the probe system shows a high sensitivity. In this work, the strain distributions along the probe stem with the probe under axial and lateral load are analysed. A simulation of the strain distribution was performed using the finite element package ANSYS 11. Performance tests using a piezoelectric transducer stage with a displacement resolution of 1.5 nm yielded a measurement resolution of 60 nm under axial loading.

Prediction of wool knitwear pilling propensity using support vector machines

The propensity of wool knitwear to form entangled fiber balls, known as pills, on the surface is affected by a large number of factors. This study examines, for the first time, the application of the support vector machine (SVM) data mining tool to the pilling propensity prediction of wool knitwear. The results indicate that by using the binary classification method and the radial basis function (RBF) kernel function, the SVM is able to give high pilling propensity prediction accuracy for wool knitwear without data over-fitting. The study also found that the number of records available for each pill rating greatly affects the learning and prediction capability of SVM models.

Dealing with rogue virtual machines in a cloud services environment

In current cloud services hosting solutions, various mechanisms have been developed to minimize the possibility of hosting staff from breaching security. However, while functions such as replicating and moving machines are legitimate actions in clouds, we show that there are risks in administrators being able to perform them. We describe three threat scenarios related to hosting staff on the cloud architecture and indicate how an appropriate accountability architecture can mitigate these risks in the sense that the attacks can be detected and the perpetrators identified. We identify requirements and future research and development needed to protect cloud service environments from these attacks.

Ordinal Boltzmann machines for collaborative filtering

Collaborative filtering is an effective recommendation technique wherein the preference of an individual can potentially be predicted based on preferences of other members. Early algorithms often relied on the strong locality in the preference data, that is, it is enough to predict preference of a user on a particular item based on a small subset of other users with similar tastes or of other items with similar properties. More recently, dimensionality reduction techniques have proved to be equally competitive, and these are based on the co-occurrence patterns rather than locality. This paper explores and extends a probabilistic model known as Boltzmann Machine for collaborative filtering tasks. It seamlessly integrates both the similarity and cooccurrence in a principled manner. In particular, we study parameterisation options to deal with the ordinal nature of the preferences, and propose a joint modelling of both the user-based and item-based processes. Experiments on moderate and large-scale movie recommendation show that our framework rivals existing well-known methods.

Mixed-variate restricted Boltzmann machines

Modern datasets are becoming heterogeneous. To this end, we present in this paper Mixed- Variate Restricted Boltzmann Machines for simultaneously modelling variables of multiple types and modalities, including binary and continuous responses, categorical options, multicategorical choices, ordinal assessment and category-ranked preferences. Dependency among variables is modeled using latent binary variables, each of which can be interpreted as a particular hidden aspect of the data. The proposed model, similar to the standard RBMs, allows fast evaluation of the posterior for the latent variables. Hence, it is naturally suitable for many common tasks including, but not limited to, (a) as a pre-processing step to convert complex input data into a more convenient vectorial representation through the latent posteriors, thereby oering a dimensionality reduction capacity, (b) as a classier supporting binary, multiclass, multilabel, and label-ranking outputs, or a regression tool for continuous outputs and (c) as a data completion tool for multimodal and heterogeneous data. We evaluate the proposed model on a large-scale dataset using the world opinion survey results on three tasks: feature extraction and visualization, data completion and prediction.

Intelligent machines : an introduction

In this chapter, an introduction to intelligent machine is presented. An explanation on intelligent behavior, and the difference between intelligent and repetitive natural or programmed behavior is provided. Some learning techniques in the field of Artificial Intelligence in constructing intelligent machines are then discussed. In addition, applications of intelligent machines to a number of areas including aerial navigation, ocean and space exploration, and humanoid robots are presented.

Embedded restricted Boltzmann machines for fusion of mixed data types and applications in social measurements analysis

Analysis and fusion of social measurements is important to understand what shapes the public’s opinion and the sustainability of the global development. However, modeling data collected from social responses is challenging as the data is typically complex and heterogeneous, which might take the form of stated facts, subjective assessment, choices, preferences or any combination thereof. Model-wise, these responses are a mixture of data types including binary, categorical, multicategorical, continuous, ordinal, count and rank data. The challenge is therefore to effectively handle mixed data in the a unified fusion framework in order to perform inference and analysis. To that end, this paper introduces eRBM (Embedded Restricted Boltzmann Machine) – a probabilistic latent variable model that can represent mixed data using a layer of hidden variables transparent across different types of data. The proposed model can comfortably support largescale data analysis tasks, including distribution modelling, data completion, prediction and visualisation. We demonstrate these versatile features on several moderate and large-scale publicly available social survey datasets.