Mutual information for Lucas-Kanade Tracking (MILK): an inverse compositional formulation

Mutual Information (MI) is popular for registration via function optimisation. This work proposes an inverse compositional formulation of MI for Levenberg-Marquardt optimisation. This yields a constant Hessian, which may be pre-computed. Speed improvements of 15% were obtained, with convergence accuracies similar to those of the standard formulation.     

Topological Repairing of 3D Digital Images

We present here a new randomized algorithm for repairing the topology of objects represented by 3D binary digital images. By “repairing the topology”, we mean a systematic way of modifying a given binary image in order to produce a similar binary image which is guaranteed to be well-composed. A 3D binary digital image is said to be well-composed if, and only if, the square faces shared by background and foreground voxels form a 2D manifold. Well-composed images enjoy some special properties which can make such images very desirable in practical applications. For instance, well-known algorithms for extracting surfaces from and thinning binary images can be simplified and optimized for speed if the input image is assumed to be well-composed. Furthermore, some algorithms for computing surface curvature and extracting adaptive triangulated surfaces, directly from the binary data, can only be applied to well-composed images. Finally, we introduce an extension of the aforementioned algorithm to repairing 3D digital multivalued images. Such an algorithm finds application in repairing segmented images resulting from multi-object segmentations of other 3D digital multivalued images.

A model to predict land susceptibility to wind erosion in western Queensland,Australia

This paper describes the development and validation of the Australian Land Erodibility Model (AUSLEM), designed to predict land susceptibility to wind erosion in western Queensland, Australia. The model operates at a 5 × 5 km spatial resolution on a daily time-step with inputs of grass and tree cover, soil moisture, soil texture and surficial stone cover. The system was implemented to predict land erodibility, i.e. susceptibility to wind erosion, for the period 1980–1990. Model performance was evaluated using cross-correlation analyses to compare trajectories of mean annual land erodibility at selected locations with trends in wind speed and observational records of dust events and a Dust Storm Index (DSI). The validation was conducted at four spatial length scales from 25 to 150 km using windows to represent potential dust source areas centered on and positioned around eight meteorological stations within the study area. The predicted land erodibility had strong correlations with dust-event frequencies at half of the stations. Poor correlations at the other stations were linked to the inability of the model to account for temporal changes in soil erodibility, and comparing trends in the land erodibility of regions with dust events whose source areas lie outside the regions of interest. The model agreement with dust-event frequency trends was found to vary across spatial scales and was highly dependent on land type characteristics around the stations and on the types of dust events used for validation.     

Hierarchical classification of protein function with ensembles of rules and particle swarm optimisation

This paper focuses on hierarchical classification problems where the classes to be predicted are organized in the form of a tree. The standard top-down divide and conquer approach for hierarchical classification consists of building a hierarchy of classifiers where a classifier is built for each internal (non-leaf) node in the class tree. Each classifier discriminates only between its child classes. After the tree of classifiers is built, the system uses them to classify test examples one class level at a time, so that when the example is assigned a class at a given level, only the child classes need to be considered at the next level. This approach has the drawback that, if a test example is misclassified at a certain class level, it will be misclassified at deeper levels too. In this paper we propose hierarchical classification methods to mitigate this drawback. More precisely, we propose a method called hierarchical ensemble of hierarchical rule sets (HEHRS), where different ensembles are built at different levels in the class tree and each ensemble consists of different rule sets built from training examples at different levels of the class tree. We also use a particle swarm optimisation (PSO) algorithm to optimise the rule weights used by HEHRS to combine the predictions of different rules into a class to be assigned to a given test example. In addition, we propose a variant of a method to mitigate the aforementioned drawback of top-down classification. These three types of methods are compared against the standard top-down hierarchical classification method in six challenging bioinformatics datasets, involving the prediction of protein function. Overall HEHRS with the rule weights optimised by the PSO algorithm obtains the best predictive accuracy out of the four types of hierarchical classification method.     

Agent Technologies for Sensor Networks

Wireless sensor networks are increasingly seen as a solution to the problem of performing continuous wide-area monitoring in many environmental, security, and military scenarios. The distributed nature of such networks and the autonomous behavior expected of them present many novel challenges. In this article, the authors argue that a new synthesis of electronic engineering and agent technology is required to address these challenges, and they describe three examples where this synthesis has succeeded. In more detail, they describe how these novel approaches address the need for communication and computationally efficient decentralized algorithms to coordinate the behavior of physically distributed sensors, how they enable the real-world deployment of sensor agent platforms in the field, and finally, how they facilitate the development of intelligent agents that can autonomously acquire data from these networks and perform information processing tasks such as fusion, inference, and prediction.     

Characterisation of flucloxacillin and 5-hydroxymethyl flucloxacillin haptenated HSA in vitro and in vivo

Flucloxacillin is a synthetic penicillin used in the treatment of Staphylococcal infections. Adverse reactions to the drug are believed to arise through covalent modification of proteins, with tissue damage occurring secondary to an immune reaction. Serum proteins have been shown by adduct-specific antibodies to be modified by flucloxacillin, but the nature and sites of modification have not been characterised. Here, in vitro studies on HSA have shown by MS that the modification of protein lysine residues occurs in a dose-, time- and site-dependent manner. Affinity, cation exchange and reversed phase chromatography prior to MS revealed in vivo modification of HSA with flucloxacillin in tolerant patients, with up to nine modified lysine residues being detected in each patient, and with modification of Lys190 and Lys212 being detected in 8/8 patients. It was also revealed for the first time that plasma proteins could be modified with the 5-hydroxymethyl metabolite of flucloxacillin, and that essentially the same Lys residues were targeted by both the parent drug and its metabolite. This study provides a detailed characterisation of sites of chemical modification of an endogenous target and reveals candidate peptides for T-cell and antibody assays of flucloxacillin hypersensitivity.     

The role of anergy in peripheral T cell unresponsiveness

When a T cell's encounter with specific antigen results in good signaling through the T cell antigen receptor yet does not lead to a proliferative response, the T cell enters a state of nonresponsiveness, or anergy. Anergy induction can result from a number of different situations, including antigen presentation by costimulation-deficient or "non-professional" antigen presenting cells, pharmacological blocking of T cell proliferation, or chronic stimulation of the T cell receptor by antigen. Anergy is a long-lived but temporary state characterized by a profound inability of the T cell to produce IL-2. Other effector functions may be affected to variable degrees. Anergy has been characterized most carefully under in vitro conditions, but several experimental models have demonstrated that T cells can also become anergic in vivo. This mechanism for tolerance induction may help to ensure that any mature autoreactive T cells which escape thymic deletion are unable to respond to host tissues. Furthermore, an understanding of the mechanism of anergy induction will most certainly lead to beneficial clinical applications, including improving graft acceptance and avoiding such deleterious immune responses as autoimmunity and allergy.     

An integrated behavioral medicine approach to improving care of patients with diabetes mellitus

A detailed approach to integrating behavioral techniques into patient education, case management, and treatment evaluation of persons with diabetes mellitus is offered. The author asks a series of "what if" questions to stimulate new thinking about ways to improve patient-physician relations in overcoming problems in managing the condition, citing recent research findings in the field. Adherence to regimens, self-management, goals of an integrated diabetes program and steps along the way to achieving it, psychophysiologic mechanisms in glucose metabolism, and the function of social support are among the topics covered.     

Rational wavelet decompositions of transfer functions in hardy-sobolev classes

The model approximation of transfer functions using rational wavelets (or molecular decompositions) is considered. By using techniques from Hardy-Sobolev spaces it is shown that Hilbert space methods such as a modified matching-pursuit algorithm and least-squares technique can be employed to obtain good approximations in bothH ² andH norms. Several theoretical results are given on rates of convergence when the methods are applied to delay systems and fractional filters.The research of the first author was supported by E.P.S.R.C.