Preface

Preface

Preface     

Robust invariant sets for constrained storage systems

Several items are produced and stored into n buffers in order to supply an external demand without interruptions. We consider the classical problem of determining control laws and smallest buffer levels guaranteeing that an unknown bounded demand is always satisfied. A simple model with n decoupled integrators and n additive bounded disturbances is employed. The coupling arises from bounds on the total production capacity and on the total demand. Invariant set theory for linear and switched linear systems is exploited to compute robust positive invariant sets and controlled robust invariant sets for two commonly adopted scheduling policies. This paper provides the explicit expression of the invariant sets for any arbitrary n.     

A multi-matcher system based on knuckle-based features

We describe a new multi-matcher biometric approach, using knuckle-based features extracted from the middle finger and from the ring finger, with fusion applied at the matching-score level. The features extraction is performed by Radon transform and by Haar wavelet, then these features are transformed by non-linear Fisher transform. Finally, the matching process is based on Parzen window classifiers. Moreover, we study a method based on tokenised pseudo-random numbers and user specific knuckle features. The experimental results show the effectiveness of the system in terms of equal error rate (EER) (near zero equal error rate).

Machine learning multi-classifiers for peptide classification

In this paper, we study the performance improvement that it is possible to obtain combining classifiers based on different notions (each trained using a different physicochemical property of amino-acids). This multi-classifier has been tested in three problems: HIV-protease; recognition of T-cell epitopes; predictive vaccinology. We propose a multi-classifier that combines a classifier that approaches the problem as a two-class pattern recognition problem and a method based on a one-class classifier. Several classifiers combined with the “sum rule” enables us to obtain an improvement performance over the best results previously published in the literature.

Automatic selection of arterial input function on dynamic contrast-enhanced MR images

Dynamic susceptibility contrast-magnetic resonance imaging (DSC-MRI) data analysis requires the knowledge of the arterial input function (AIF) to quantify the cerebral blood flow (CBF), volume (CBV) and the mean transit time (MTT). AIF can be obtained either manually or using automatic algorithms. We present a method to derive the AIF on the middle cerebral artery (MCA). The algorithm draws a region of interest (ROI) where the MCA is located. Then, it uses a recursive cluster analysis on the ROI to select the arterial voxels. The algorithm had been compared on simulated data to literature state of art automatic algorithms and on clinical data to the manual procedure. On in silico data, our method allows to reconstruct the true AIF and it is less affected by partial volume effect bias than the other methods. In clinical data, automatic AIF provides CBF and MTT maps with a greater contrast level compared to manual AIF ones. Therefore, AIF obtained with the proposed method improves the estimate reliability and provides a quantitatively reliable physiological picture.     

Mixture of KL subspaces for relevance feedback

Relevance feedback has recently emerged as a solution to the problem of improving the retrieval performance of an image retrieval system based on low-level information such as color, texture and shape features. Most of the relevance feedback approaches limit the utilization of the user’s feedback to a single search session, performing a short-term learning. In this paper we present a novel approach for short and long term learning, based on the definition of an adaptive similarity metric and of a high level representation of the images. For short-term learning, the relevant and non-relevant information given by the user during the feedback process is employed to create a positive and a negative subspace of the feature space. For long-term learning, the feedback history of all the users is exploited to create and update a representation of the images which is adopted for improving retrieval performance and progressively reducing the semantic gap between low-level features and high-level semantic concepts. The experimental results prove that the proposed method outperforms many other state of art methods in the short-term learning, and demonstrate the efficacy of the representation adopted for the long-term learning.

Relational Analysis and Precision via Probabilistic Abstract Interpretation

Within the context of a quantitative generalisation of the well established framework of Abstract Interpretation – i.e. Probabilistic Abstract Interpretation – we investigate a quantitative notion of precision which allows us to compare analyses on the basis of their expected exactness for a given program. We illustrate this approach by considering various types of numerical abstractions of the values of variables for independent analysis as well as weakly and fully relational analysis. We utilise for this a linear operator semantics of a simple imperative programming language. In this setting, fully relational dependencies are realised via the tensor product. Independent analyses and weakly relational analyses are realised as abstractions of the fully relational analysis.     

A simple method for improving local binary patterns by considering non-uniform patterns

The basic idea behind LBP is that an image is composed of micropatterns. A histogram of these micropatterns contains information about the local features in an image. These micropatterns can be divided into two types: uniform and non-uniform. In standard applications using LBP, only the uniform patterns are used. The non-uniform patterns are considered in only a single bin of the histogram that is used to extract features in the classification stage. Non-uniform patterns have undesirable characteristics: they are of a high dimension, partially correlated, and introduce unwanted noise. To offset these disadvantages, we explore using random subspace, well-known to work well with noise and correlated features, to train features based also on non-uniform patterns. We find that a stand-alone support vector machine performs best with the uniform patterns and random subspace with histograms of 50 bins performs best with the non-uniform patterns. Superior results are obtained when the two are combined. Based on extensive experiments conducted in several domains using several benchmark databases, it is our conclusion that non-uniform patterns improve classifier performance.