Class-specific metrics for multidimensional data projection applied to CBIR

Content-based image retrieval is still a challenging issue due to the inherent complexity of images and choice of the most discriminant descriptors. Recent developments in the field have introduced multidimensional projections to burst accuracy in the retrieval process, but many issues such as introduction of pattern recognition tasks and deeper user intervention to assist the process of choosing the most discriminant features still remain unaddressed. In this paper, we present a novel framework to CBIR that combines pattern recognition tasks, class-specific metrics, and multidimensional projection to devise an effective and interactive image retrieval system. User interaction plays an essential role in the computation of the final multidimensional projection from which image retrieval will be attained. Results have shown that the proposed approach outperforms existing methods, turning out to be a very attractive alternative for managing image data sets.

Two-Phase Mapping for Projecting Massive Data Sets

Most multidimensional projection techniques rely on distance (dissimilarity) information between data instances to embed high-dimensional data into a visual space. When data are endowed with Cartesian coordinates, an extra computational effort is necessary to compute the needed distances, making multidimensional projection prohibitive in applications dealing with interactivity and massive data. The novel multidimensional projection technique proposed in this work, called Part-Linear Multidimensional Projection (PLMP), has been tailored to handle multivariate data represented in Cartesian high-dimensional spaces, requiring only distance information between pairs of representative samples. This characteristic renders PLMP faster than previous methods when processing large data sets while still being competitive in terms of precision. Moreover, knowing the range of variation for data instances in the high-dimensional space, we can make PLMP a truly streaming data projection technique, a trait absent in previous methods.

Visualizing and classifying data using a hybrid intelligent system

In this paper, a hybrid intelligent system that integrates the SOM (Self-Organizing Map) neural network, kMER (kernel-based Maximum Entropy learning Rule), and Probabilistic Neural Network (PNN) for data visualization and classification is proposed. The rationales of this Probabilistic SOM-kMER model are explained, and its applicability is demonstrated using two benchmark data sets. The results are analyzed and compared with those from a number of existing methods. Implication of the proposed hybrid system as a useful and usable data visualization and classification tool is discussed.

Novel visualization methods for protein data

Visualization of high-dimensional data has always been a challenging task. Here we discuss and propose variants of non-linear data projection methods (Generative Topographic Mapping (GTM) and GTM with simultaneous feature saliency (GTM-FS)) that are adapted to be effective on very high-dimensional data. The adaptations use log space values at certain steps of the Expectation Maximization (EM) algorithm and during the visualization process. We have tested the proposed algorithms by visualizing electrostatic potential data for Major Histocompatibility Complex (MHC) class-I proteins. The experiments show that the variation in the original version of GTM and GTM-FS worked successfully with data of more than 2000 dimensions and we compare the results with other linear/nonlinear projection methods: Principal Component Analysis (PCA), Neuroscale (NSC) and Gaussian Process Latent Variable Model (GPLVM).

Characterisation of indoor air organic pollutants in Brisbane

The occurrence and levels of airborne polycyclic aromatic hydrocarbons and volatile organic compounds in selected non-industrial environments in Brisbane have been investigated as part of an integrated indoor air quality assessment program. The most abundant and most frequently encountered compounds include, nonanal, decanal, texanol, phenol, 2-ethyl-1-hexanol, ethanal, naphthalene, 2,6-tert-butyl-4-methyl-phenol (BHT), salicylaldehyde, toluene, hexanal, benzaldehyde, styrene, ethyl benzene, o-, m- and pxylenes, benzene, n-butanol, 1,2-propandiol, and n-butylacetate. Many of the 64 compounds usually included in the European Collaborative Action method of TVOC analysis were below detection limits in the samples analysed. In order to extract maximum amount of information from the data collected, multivariate data projection methods have been employed. The implications of the information extracted on source identification and exposure control are discussed.

Thomson-Craighead at Studion

Moderna Museet invited Mejan Labs to curate two installations by the British artists Thomson & Craighead. This solo exhibition was in Studion at Moderna Museet, Stockholm. Works included: BEACON when it is shown as a data projection in a gallery. As with the online version and railway flap sign, live web searches are continuously relayed as they are being made around the world -in this case onto a gallery wall in series and at regular intervals as an endless concrete poetry. Decorative Newsfeeds use a live feed from the web to present up to the minute headline news from around the world as a series of pleasant animations, allowing viewers to keep informed while contemplating a kind of readymade sculpture or perhaps an automatic drawing.

Use of Information Visualization Methods Eliminating Cross Talk in Multiple Sensing Units Investigated for a Light-Addressable Potentiometric Sensor

The integration of nanostructured films containing biomolecules and silicon-based technologies is a promising direction for reaching miniaturized biosensors that exhibit high sensitivity and selectivity. A challenge, however, is to avoid cross talk among sensing units in an array with multiple sensors located on a small area. In this letter, we describe an array of 16 sensing units, of a light-addressable potentiometric sensor (LAPS), which was made with layer-by-Layer (LbL) films of a poly(amidomine) dendrimer (PAMAM) and single-walled carbon nanotubes (SWNTs), coated with a layer of the enzyme penicillinase. A visual inspection of the data from constant-current measurements with liquid samples containing distinct concentrations of penicillin, glucose, or a buffer indicated a possible cross talk between units that contained penicillinase and those that did not. With the use of multidimensional data projection techniques, normally employed in information Visualization methods, we managed to distinguish the results from the modified LAPS, even in cases where the units were adjacent to each other. Furthermore, the plots generated with the interactive document map (IDMAP) projection technique enabled the distinction of the different concentrations of penicillin, from 5 mmol L(-1) down to 0.5 mmol L(-1). Data visualization also confirmed the enhanced performance of the sensing units containing carbon nanotubes, consistent with the analysis of results for LAPS sensors. The use of visual analytics, as with projection methods, may be essential to handle a large amount of data generated in multiple sensor arrays to achieve high performance in miniaturized systems.

An Intelligent Human-Computer Interaction System for Decision Support

This paper proposes a novel architecture for
developing decision support systems. Unlike conventional decision support systems, the proposed architecture endeavors to reveal the decision-making process such that humans' subjectivity can be
incorporated into a computerized system and, at the same time, to
preserve the capability of the computerized system in processing information objectively. A number of techniques used in developing the decision support system are elaborated to make the decisionmarking
process transparent. These include procedures for high dimensional data visualization, pattern classification, prediction, and evolutionary computational search. An artificial data set is first
employed to compare the proposed approach with other methods. A simulated handwritten data set and a real data set on liver disease diagnosis are then employed to evaluate the efficacy of the proposed
approach. The results are analyzed and discussed. The potentials of the proposed architecture as a useful decision support system are demonstrated.

Digital library of historical cartography: open access to cultural heritage and public good

This paper describes the integration of information between Digital Library of Historical Cartography and Bibliographical Database (DEDALUS), both of the University of São Paulo (USP), to guarantee open, public access by Internet to the maps in the collection and make them available to users everywhere. This digital library was designed by Historical Cartography Studies Laboratory team (LECH/USP), and provides maps images on the Web, of high resolution, as well as such information on these maps as technical-scientific data (projection, scale, coordinates), printing techniques and material support that have made their circulation and cultural consumption possible. The Digital Library of Historical Cartography is accessible not only to the historical cartography researchers, but also to students and the general public. Beyond being a source of information about maps, the Digital Library of Historical Cartography seeks to be interactive, exchanging information and seeking dialogue with different branches of knowledge

Projector-based augmented reality for intuitive intraoperative guidance in image-guided 3D interstitial brachytherapy

PURPOSE: The aim of this study is to implement augmented reality in real-time image-guided interstitial brachytherapy to allow an intuitive real-time intraoperative orientation. METHODS AND MATERIALS: The developed system consists of a common video projector, two high-resolution charge coupled device cameras, and an off-the-shelf notebook. The projector was used as a scanning device by projecting coded-light patterns to register the patient and superimpose the operating field with planning data and additional information in arbitrary colors. Subsequent movements of the nonfixed patient were detected by means of stereoscopically tracking passive markers attached to the patient. RESULTS: In a first clinical study, we evaluated the whole process chain from image acquisition to data projection and determined overall accuracy with 10 patients undergoing implantation. The described method enabled the surgeon to visualize planning data on top of any preoperatively segmented and triangulated surface (skin) with direct line of sight during the operation. Furthermore, the tracking system allowed dynamic adjustment of the data to the patient's current position and therefore eliminated the need for rigid fixation. Because of soft-part displacement, we obtained an average deviation of 1.1 mm by moving the patient, whereas changing the projector's position resulted in an average deviation of 0.9 mm. Mean deviation of all needles of an implant was 1.4 mm (range, 0.3-2.7 mm). CONCLUSIONS: The developed low-cost augmented-reality system proved to be accurate and feasible in interstitial brachytherapy. The system meets clinical demands and enables intuitive real-time intraoperative orientation and monitoring of needle implantation.

Visualisation of bioinformatics datasets

Analysing the molecular polymorphism and interactions of DNA, RNA and proteins is of fundamental importance in biology. Predicting functions of polymorphic molecules is important in order to design more effective medicines. Analysing major histocompatibility complex (MHC) polymorphism is important for mate choice, epitope-based vaccine design and transplantation rejection etc. Most of the existing exploratory approaches cannot analyse these datasets because of the large number of molecules with a high number of descriptors per molecule. This thesis develops novel methods for data projection in order to explore high dimensional biological dataset by visualising them in a low-dimensional space. With increasing dimensionality, some existing data visualisation methods such as generative topographic mapping (GTM) become computationally intractable. We propose variants of these methods, where we use log-transformations at certain steps of expectation maximisation (EM) based parameter learning process, to make them tractable for high-dimensional datasets. We demonstrate these proposed variants both for synthetic and electrostatic potential dataset of MHC class-I. We also propose to extend a latent trait model (LTM), suitable for visualising high dimensional discrete data, to simultaneously estimate feature saliency as an integrated part of the parameter learning process of a visualisation model. This LTM variant not only gives better visualisation by modifying the project map based on feature relevance, but also helps users to assess the significance of each feature. Another problem which is not addressed much in the literature is the visualisation of mixed-type data. We propose to combine GTM and LTM in a principled way where appropriate noise models are used for each type of data in order to visualise mixed-type data in a single plot. We call this model a generalised GTM (GGTM). We also propose to extend GGTM model to estimate feature saliencies while training a visualisation model and this is called GGTM with feature saliency (GGTM-FS). We demonstrate effectiveness of these proposed models both for synthetic and real datasets. We evaluate visualisation quality using quality metrics such as distance distortion measure and rank based measures: trustworthiness, continuity, mean relative rank errors with respect to data space and latent space. In cases where the labels are known we also use quality metrics of KL divergence and nearest neighbour classifications error in order to determine the separation between classes. We demonstrate the efficacy of these proposed models both for synthetic and real biological datasets with a main focus on the MHC class-I dataset.