Parallel Computational Intelligence-Based Multi-Camera Surveillance System

In this work, we present a multi-camera surveillance system based on the use of self-organizing neural networks to represent events on video. The system processes several tasks in parallel using GPUs (graphic processor units). It addresses multiple vision tasks at various levels, such as segmentation, representation or characterization, analysis and monitoring of the movement. These features allow the construction of a robust representation of the environment and interpret the behavior of mobile agents in the scene. It is also necessary to integrate the vision module into a global system that operates in a complex environment by receiving images from multiple acquisition devices at video frequency. Offering relevant information to higher level systems, monitoring and making decisions in real time, it must accomplish a set of requirements, such as: time constraints, high availability, robustness, high processing speed and re-configurability. We have built a system able to represent and analyze the motion in video acquired by a multi-camera network and to process multi-source data in parallel on a multi-GPU architecture.

3D reconstruction of medical images from slices automatically landmarked with growing neural models

In this study, we utilise a novel approach to segment out the ventricular system in a series of high resolution T1-weighted MR images. We present a brain ventricles fast reconstruction method. The method is based on the processing of brain sections and establishing a fixed number of landmarks onto those sections to reconstruct the ventricles 3D surface. Automated landmark extraction is accomplished through the use of the self-organising network, the growing neural gas (GNG), which is able to topographically map the low dimensionality of the network to the high dimensionality of the contour manifold without requiring a priori knowledge of the input space structure. Moreover, our GNG landmark method is tolerant to noise and eliminates outliers. Our method accelerates the classical surface reconstruction and filtering processes. The proposed method offers higher accuracy compared to methods with similar efficiency as Voxel Grid.

Convergence analysis and validation of low cost distance metrics for computational cost reduction of the Iterative Closest Point algorithm

The Iterative Closest Point algorithm (ICP) is commonly used in engineering applications to solve the rigid registration problem of partially overlapped point sets which are pre-aligned with a coarse estimate of their relative positions. This iterative algorithm is applied in many areas such as the medicine for volumetric reconstruction of tomography data, in robotics to reconstruct surfaces or scenes using range sensor information, in industrial systems for quality control of manufactured objects or even in biology to study the structure and folding of proteins. One of the algorithm’s main problems is its high computational complexity (quadratic in the number of points with the non-optimized original variant) in a context where high density point sets, acquired by high resolution scanners, are processed. Many variants have been proposed in the literature whose goal is the performance improvement either by reducing the number of points or the required iterations or even enhancing the complexity of the most expensive phase: the closest neighbor search. In spite of decreasing its complexity, some of the variants tend to have a negative impact on the final registration precision or the convergence domain thus limiting the possible application scenarios. The goal of this work is the improvement of the algorithm’s computational cost so that a wider range of computationally demanding problems from among the ones described before can be addressed. For that purpose, an experimental and mathematical convergence analysis and validation of point-to-point distance metrics has been performed taking into account those distances with lower computational cost than the Euclidean one, which is used as the de facto standard for the algorithm’s implementations in the literature. In that analysis, the functioning of the algorithm in diverse topological spaces, characterized by different metrics, has been studied to check the convergence, efficacy and cost of the method in order to determine the one which offers the best results. Given that the distance calculation represents a significant part of the whole set of computations performed by the algorithm, it is expected that any reduction of that operation affects significantly and positively the overall performance of the method. As a result, a performance improvement has been achieved by the application of those reduced cost metrics whose quality in terms of convergence and error has been analyzed and validated experimentally as comparable with respect to the Euclidean distance using a heterogeneous set of objects, scenarios and initial situations.

Automatic Abdominal Aortic Aneurysm segmentation in MR images

Abdominal Aortic Aneurism is a disease related to a weakening in the aortic wall that can cause a break in the aorta and the death. The detection of an unusual dilatation of a section of the aorta is an indicative of this disease. However, it is difficult to diagnose because it is necessary image diagnosis using computed tomography or magnetic resonance. An automatic diagnosis system would allow to analyze abdominal magnetic resonance images and to warn doctors if any anomaly is detected. We focus our research in magnetic resonance images because of the absence of ionizing radiation. Although there are proposals to identify this disease in magnetic resonance images, they need an intervention from clinicians to be precise and some of them are computationally hard. In this paper we develop a novel approach to analyze magnetic resonance abdominal images and detect the lumen and the aortic wall. The method combines different algorithms in two stages to improve the detection and the segmentation so it can be applied to similar problems with other type of images or structures. In a first stage, we use a spatial fuzzy C-means algorithm with morphological image analysis to detect and segment the lumen; and subsequently, in a second stage, we apply a graph cut algorithm to segment the aortic wall. The obtained results in the analyzed images are pretty successful obtaining an average of 79% of overlapping between the automatic segmentation provided by our method and the aortic wall identified by a medical specialist. The main impact of the proposed method is that it works in a completely automatic way with a low computational cost, which is of great significance for any expert and intelligent system.

A connectionist computational method for face recognition

In this work, a modified version of the elastic bunch graph matching (EBGM) algorithm for face recognition is introduced. First, faces are detected by using a fuzzy skin detector based on the RGB color space. Then, the fiducial points for the facial graph are extracted automatically by adjusting a grid of points to the result of an edge detector. After that, the position of the nodes, their relation with their neighbors and their Gabor jets are calculated in order to obtain the feature vector defining each face. A self-organizing map (SOM) framework is shown afterwards. Thus, the calculation of the winning neuron and the recognition process are performed by using a similarity function that takes into account both the geometric and texture information of the facial graph. The set of experiments carried out for our SOM-EBGM method shows the accuracy of our proposal when compared with other state-of the-art methods.

Sea-floor images from during POLARSTERN cruise ANT-XV/3 to the Weddell Sea, Antarctica

Transects of a Remotely Operated Vehicle (ROV) providing sea-bed videos and photographs were carried out during POLARSTERN expedition ANT-XV/3 focussing on the ecology of benthic assemblages on the Antarctic shelf in the South-Eastern Weddell Sea. The ROV-system sprint 103 was equiped with two video- and one still camera, lights, flash-lights, compass, and parallel lasers providing a scale in the images, a tether-management system (TMS), a winch, and the board units. All cameras used the same main lense and could be tilted. Videos were recorded in Betacam-format and (film-)slides were made by decision of the scientific pilot. The latter were mainly made under the aspect to improve the identification of organisms depicted in the videos because the still photographs have a much higher optical resolution than the videos. In the photographs species larger than 3 mm, in the videos larger than 1 cm are recognisable and countable. Under optimum conditions the transects were strait; the speed and direction of the ROV were determined by the drift of the ship in the coastal current, since both, the ship and the ROV were used as a drifting system; the option to operate the vehicle actively was only used to avoide obstacles and to reach at best a distance of only approximately 30 cm to the sea-floor. As a consequence the width of the photographs in the foreground is approximately 50 cm. Deviations from this strategy resulted mainly from difficult ice- and weather conditions but also from high current velocity and local up-welling close to the sea-bed. The sea-bed images provide insights into the general composition of key species, higher systematic groups and ecological guilds. Within interdisciplinary approaches distributions of assemblages can be attributed to environmental conditions such as bathymetry, sediment characteristics, water masses and current regimes. The images also contain valuable information on how benthic species are associated to each other. Along the transects, small- to intermediate-scaled disturbances, e.g. by grounding icebergs were analysed and further impact to the entire benthic system by local succession of recolonisation was studied. This information can be used for models predicting the impact of climate change to benthic life in the Southern Ocean. All these approaches contribute to a better understanding of the fiunctioning of the benthic system and related components of the entire Antarctic marine ecosystem. Despite their scientific value the imaging methods meet concerns about the protection of sensitive Antarctic benthic systems since they are non-invasive and they also provide valuable material for education and outreach purposes.

Speeding up the EM algorithm for mixture model-based segmentation of magnetic resonance images

Mixture models implemented via the expectation-maximization (EM) algorithm are being increasingly used in a wide range of problems in pattern recognition such as image segmentation. However, the EM algorithm requires considerable computational time in its application to huge data sets such as a three-dimensional magnetic resonance (MR) image of over 10 million voxels. Recently, it was shown that a sparse, incremental version of the EM algorithm could improve its rate of convergence. In this paper, we show how this modified EM algorithm can be speeded up further by adopting a multiresolution kd-tree structure in performing the E-step. The proposed algorithm outperforms some other variants of the EM algorithm for segmenting MR images of the human brain. (C) 2004 Pattern Recognition Society. Published by Elsevier Ltd. All rights reserved.

Numerical methods for strong solutions of stochastic differential equations: an overview

This paper gives a review of recent progress in the design of numerical methods for computing the trajectories (sample paths) of solutions to stochastic differential equations. We give a brief survey of the area focusing on a number of application areas where approximations to strong solutions are important, with a particular focus on computational biology applications, and give the necessary analytical tools for understanding some of the important concepts associated with stochastic processes. We present the stochastic Taylor series expansion as the fundamental mechanism for constructing effective numerical methods, give general results that relate local and global order of convergence and mention the Magnus expansion as a mechanism for designing methods that preserve the underlying structure of the problem. We also present various classes of explicit and implicit methods for strong solutions, based on the underlying structure of the problem. Finally, we discuss implementation issues relating to maintaining the Brownian path, efficient simulation of stochastic integrals and variable-step-size implementations based on various types of control.

MULTIPRED: A computational system for prediction of promiscuous HLA binding peptides

MULTIPRED is a web-based computational system for the prediction of peptide binding to multiple molecules ( proteins) belonging to human leukocyte antigens (HLA) class I A2, A3 and class II DR supertypes. It uses hidden Markov models and artificial neural network methods as predictive engines. A novel data representation method enables MULTIPRED to predict peptides that promiscuously bind multiple HLA alleles within one HLA supertype. Extensive testing was performed for validation of the prediction models. Testing results show that MULTIPRED is both sensitive and specific and it has good predictive ability ( area under the receiver operating characteristic curve A(ROC) > 0.80). MULTIPRED can be used for the mapping of promiscuous T-cell epitopes as well as the regions of high concentration of these targets termed T-cell epitope hotspots. MULTIPRED is available at http:// antigen.i2r.a-star.edu.sg/ multipred/.

Numerical modeling of 11.1 T MRI of a human head using MoM/FDTD methods

In a recent study, severe distortions in the proton images of an excised, fixed, human brain in an 11.1 Tesla/40 cm MR instrument have been observed, and the effect modeled on phantom images using a finite difference time domain (FDTD) model. in the present study, we extend these simulations to that of a complete human head, employing a hybrid FDTD and method of moments (MoM) approach, which provides a validated method for simulating biological samples in coil structures. The effect of fixative on the image distortions is explored. importantly, temperature distributions within the head are also simulated using a bioheat method based on parameters derived from the electromagnetic simulations. The MoM/FDTD simulations confirm that the transverse magnetic field (B,) from a ReCav resonator exhibits good homogeneity in air but strong inhomogeneity when loaded with the head with or without fixative. The fixative serves to increase the distortions, but they are still significant for the in vivo simulations. The simulated signal intensity (SI) distribution within the sample confirm the distortions in the experimental images are caused by the complex interactions of the incident electromagnetic fields with tissue, which is heterogeneous in terms of conductivity and permittivity. The temperature distribution is likewise heterogeneous, raising concerns regarding hot spot generation in the sample that may exceed acceptable levels in future in vivo studies. As human imaging at 11.1 T is some time away, simulations are important in terms of predicting potential safety issues as well as evaluating practical concerns about the quality of images. Simulation on a whole human head at 11.1 T implies the wave behavior presents significant engineering challenges for ultra-high-field (UHF) MRI. Novel strategies will have to be employed in imaging technique and resonator design for UHF MRI to achieve the theoretical signal-to-noise ratio (SNR) improvements it offers over lower field systems. (C) 2005 Wiley Periodicals, Inc.

ICICLE: A semantic-based retrieval system for WWW images

In this paper, we present ICICLE (Image ChainNet and Incremental Clustering Engine), a prototype system that we have developed to efficiently and effectively retrieve WWW images based on image semantics. ICICLE has two distinguishing features. First, it employs a novel image representation model called Weight ChainNet to capture the semantics of the image content. A new formula, called list space model, for computing semantic similarities is also introduced. Second, to speed up retrieval, ICICLE employs an incremental clustering mechanism, ICC (Incremental Clustering on ChainNet), to cluster images with similar semantics into the same partition. Each cluster has a summary representative and all clusters' representatives are further summarized into a balanced and full binary tree structure. We conducted an extensive performance study to evaluate ICICLE. Compared with some recently proposed methods, our results show that ICICLE provides better recall and precision. Our clustering technique ICC facilitates speedy retrieval of images without sacrificing recall and precision significantly.

Methods for Categorical Longitudinal Survey Data: Understanding Employment Status of Australian Women

Many variables that are of interest in social science research are nominal variables with two or more categories, such as employment status, occupation, political preference, or self-reported health status. With longitudinal survey data it is possible to analyse the transitions of individuals between different employment states or occupations (for example). In the statistical literature, models for analysing categorical dependent variables with repeated observations belong to the family of models known as generalized linear mixed models (GLMMs). The specific GLMM for a dependent variable with three or more categories is the multinomial logit random effects model. For these models, the marginal distribution of the response does not have a closed form solution and hence numerical integration must be used to obtain maximum likelihood estimates for the model parameters. Techniques for implementing the numerical integration are available but are computationally intensive requiring a large amount of computer processing time that increases with the number of clusters (or individuals) in the data and are not always readily accessible to the practitioner in standard software. For the purposes of analysing categorical response data from a longitudinal social survey, there is clearly a need to evaluate the existing procedures for estimating multinomial logit random effects model in terms of accuracy, efficiency and computing time. The computational time will have significant implications as to the preferred approach by researchers. In this paper we evaluate statistical software procedures that utilise adaptive Gaussian quadrature and MCMC methods, with specific application to modeling employment status of women using a GLMM, over three waves of the HILDA survey.

Indexing text and visual features for WWW images

In this paper, we present a novel indexing technique called Multi-scale Similarity Indexing (MSI) to index imagersquos multi-features into a single one-dimensional structure. Both for text and visual feature spaces, the similarity between a point and a local partitionrsquos center in individual space is used as the indexing key, where similarity values in different features are distinguished by different scale. Then a single indexing tree can be built on these keys. Based on the property that relevant images haves similar similarity values from the center of the same local partition in any feature space, certain number of irrelevant images can be fast pruned based on the triangle inequity on indexing keys. To remove the ldquodimensionality curserdquo existing in high dimensional structure, we propose a new technique called Local Bit Stream (LBS). LBS transforms imagersquos text and visual feature representations into simple, uniform and effective bit stream (BS) representations based on local partitionrsquos center. Such BS representations are small in size and fast for comparison since only bit operation are involved. By comparing common bits existing in two BSs, most of irrelevant images can be immediately filtered. Our extensive experiment showed that single one-dimensional index on multi-features improves multi-indices on multi-features greatly. Our LBS method outperforms sequential scan on high dimensional space by an order of magnitude.

Accelerated leap methods for simulating discrete stochastic chemical kinetics

Biologists are increasingly conscious of the critical role that noise plays in cellular functions such as genetic regulation, often in connection with fluctuations in small numbers of key regulatory molecules. This has inspired the development of models that capture this fundamentally discrete and stochastic nature of cellular biology - most notably the Gillespie stochastic simulation algorithm (SSA). The SSA simulates a temporally homogeneous, discrete-state, continuous-time Markov process, and of course the corresponding probabilities and numbers of each molecular species must all remain positive. While accurately serving this purpose, the SSA can be computationally inefficient due to very small time stepping so faster approximations such as the Poisson and Binomial τ-leap methods have been suggested. This work places these leap methods in the context of numerical methods for the solution of stochastic differential equations (SDEs) driven by Poisson noise. This allows analogues of Euler-Maruyuma, Milstein and even higher order methods to be developed through the Itô-Taylor expansions as well as similar derivative-free Runge-Kutta approaches. Numerical results demonstrate that these novel methods compare favourably with existing techniques for simulating biochemical reactions by more accurately capturing crucial properties such as the mean and variance than existing methods.

Evaluation and comparison of mammalian subcellular localization prediction methods

Background: Determination of the subcellular location of a protein is essential to understanding its biochemical function. This information can provide insight into the function of hypothetical or novel proteins. These data are difficult to obtain experimentally but have become especially important since many whole genome sequencing projects have been finished and many resulting protein sequences are still lacking detailed functional information. In order to address this paucity of data, many computational prediction methods have been developed. However, these methods have varying levels of accuracy and perform differently based on the sequences that are presented to the underlying algorithm. It is therefore useful to compare these methods and monitor their performance. Results: In order to perform a comprehensive survey of prediction methods, we selected only methods that accepted large batches of protein sequences, were publicly available, and were able to predict localization to at least nine of the major subcellular locations (nucleus, cytosol, mitochondrion, extracellular region, plasma membrane, Golgi apparatus, endoplasmic reticulum (ER), peroxisome, and lysosome). The selected methods were CELLO, MultiLoc, Proteome Analyst, pTarget and WoLF PSORT. These methods were evaluated using 3763 mouse proteins from SwissProt that represent the source of the training sets used in development of the individual methods. In addition, an independent evaluation set of 2145 mouse proteins from LOCATE with a bias towards the subcellular localization underrepresented in SwissProt was used. The sensitivity and specificity were calculated for each method and compared to a theoretical value based on what might be observed by random chance. Conclusion: No individual method had a sufficient level of sensitivity across both evaluation sets that would enable reliable application to hypothetical proteins. All methods showed lower performance on the LOCATE dataset and variable performance on individual subcellular localizations was observed. Proteins localized to the secretory pathway were the most difficult to predict, while nuclear and extracellular proteins were predicted with the highest sensitivity.