Fast training of self organizing maps for the visual exploration of molecular compounds

Visual exploration of scientific data in life science area is a growing research field due to the large amount of available data. The Kohonen’s Self Organizing Map (SOM) is a widely used tool for visualization of multidimensional data. In this paper we present a fast learning algorithm for SOMs that uses a simulated annealing method to adapt the learning parameters. The algorithm has been adopted in a data analysis framework for the generation of similarity maps. Such maps provide an effective tool for the visual exploration of large and multi-dimensional input spaces. The approach has been applied to data generated during the High Throughput Screening of molecular compounds; the generated maps allow a visual exploration of molecules with similar topological properties. The experimental analysis on real world data from the National Cancer Institute shows the speed up of the proposed SOM training process in comparison to a traditional approach. The resulting visual landscape groups molecules with similar chemical properties in densely connected regions.

Reduction of invasive tests in chagasic patients with a modified self-organizing map

The applicability of AI methods to the Chagas' disease diagnosis is carried out by the use of Kohonen's self-organizing feature maps. Electrodiagnosis indicators calculated from ECG records are used as features in input vectors to train the network. Cross-validation results are used to modify the maps, providing an outstanding improvement to the interpretation of the resulting output. As a result, the map might be used to reduce the need for invasive explorations in chronic Chagas' disease.

Organizing for sustainable procurement: theories, institutions and practice

That construction procurement needs to be re-organized to make it more sustainable implies that there is a problem with the current situation. Starting from this assumption, an overview of construction procurement sets the scene for a discussion of some recent developments relating to organizational frameworks for sustainable construction procurement. Emergent theories dealing with sustainable procurement are considered. There is a plethora of standards and guidance documents for organizing sustainable procurement, originating from a variety of organizations involved. These considerations form the context for approaches being used in practice to achieve sustainable procurement. The Chapter concludes with reflections on why current approaches are insufficient. It seems difficult to persuade clients to spend less money over the life cycle of their buildings. Future directions needed to translate sustainable procurement from rhetoric to reality include the development of suitable incentives and appropriate organizational structures.

Context-aware visual exploration of molecular databases

Facilitating the visual exploration of scientific data has received increasing attention in the past decade or so. Especially in life science related application areas the amount of available data has grown at a breath taking pace. In this paper we describe an approach that allows for visual inspection of large collections of molecular compounds. In contrast to classical visualizations of such spaces we incorporate a specific focus of analysis, for example the outcome of a biological experiment such as high throughout screening results. The presented method uses this experimental data to select molecular fragments of the underlying molecules that have interesting properties and uses the resulting space to generate a two dimensional map based on a singular value decomposition algorithm and a self organizing map. Experiments on real datasets show that the resulting visual landscape groups molecules of similar chemical properties in densely connected regions.

Organizational effects of fetal testosterone on human corpus callosum size and asymmetry

Previous theory and research in animals has identified the critical role that fetal testosterone (FT) plays in organizing sexually dimorphic brain development. However, to date there are no studies in humans directly testing the organizational effects of FT on structural brain development. In the current study we investigated the effects of FT on corpus callosum size and asymmetry. High-resolution structural magnetic resonance images (MRI) of the brain were obtained on 28 8-11-year-old boys whose exposure to FT had been previously measured in utero via amniocentesis conducted during the second trimester. Although there was no relationship between FT and midsaggital corpus callosum size, increasing FT was significantly related to increasing rightward asymmetry (e.g., Right>Left) of a posterior subsection of the callosum, the isthmus, that projects mainly to parietal and superior temporal areas. This potential organizational effect of FT on rightward callosal asymmetry may be working through enhancing the neuroprotective effects of FT and result in an asymmetric distribution of callosal axons. We suggest that this possible organizational effect of FT on callosal asymmetry may also play a role in shaping sexual dimorphism in functional and structural brain development, cognition, and behavior.

A new linear initialization in SOM for biomolecular data

In the past decade, the amount of data in biological field has become larger and larger; Bio-techniques for analysis of biological data have been developed and new tools have been introduced. Several computational methods are based on unsupervised neural network algorithms that are widely used for multiple purposes including clustering and visualization, i.e. the Self Organizing Maps (SOM). Unfortunately, even though this method is unsupervised, the performances in terms of quality of result and learning speed are strongly dependent from the neuron weights initialization. In this paper we present a new initialization technique based on a totally connected undirected graph, that report relations among some intersting features of data input. Result of experimental tests, where the proposed algorithm is compared to the original initialization techniques, shows that our technique assures faster learning and better performance in terms of quantization error.

Improved SOM learning using simulated annealing

Self-Organizing Map (SOM) algorithm has been extensively used for analysis and classification problems. For this kind of problems, datasets become more and more large and it is necessary to speed up the SOM learning. In this paper we present an application of the Simulated Annealing (SA) procedure to the SOM learning algorithm. The goal of the algorithm is to obtain fast learning and better performance in terms of matching of input data and regularity of the obtained map. An advantage of the proposed technique is that it preserves the simplicity of the basic algorithm. Several tests, carried out on different large datasets, demonstrate the effectiveness of the proposed algorithm in comparison with the original SOM and with some of its modification introduced to speed-up the learning.

Observations and modeling of banded orographic convection

Radar images and numerical simulations of three shallow convective precipitation events over the Coastal Range in western Oregon are presented. In one of these events, unusually well-defined quasi-stationary banded formations produced large precipitation enhancements in favored locations, while varying degrees of band organization and lighter precipitation accumulations occurred in the other two cases. The difference between the more banded and cellular cases appeared to depend on the vertical shear within the orographic cap cloud and the susceptibility of the flow to convection upstream of the mountain. Numerical simulations showed that the rainbands, which appeared to be shear-parallel convective roll circulations that formed within the unstable orographic cap cloud, developed even over smooth mountains. However, these banded structures were better organized, more stationary, and produced greater precipitation enhancement over mountains with small-scale topographic obstacles. Low-amplitude random topographic roughness elements were found to be just as effective as more prominent subrange-scale peaks at organizing and fixing the location of the orographic rainbands.

'Fair trade gold': Antecedents, prospects and challenges

This paper critically examines the challenges with, and impacts of, adopting the models in place for fair trade agriculture in the artisanal gold mining sector. Over the past two years, an NGO-led 'fair trade gold' movement has surfaced, its crystallization fuelled by a burgeoning body of evidence that points to impoverished artisanal miners in developing countries receiving low payments for their gold, as well as working in hazardous and unsanitary conditions. Proponents of fair trade gold contest that increased interaction between artisanal miners and Western jewellers could facilitate the former receiving fairer prices for gold, accessing support services, and ultimately, improving their quality of life. In the case of sub-Saharan Africa, however, the gold being mined on an artisanal scale does not supply Western retailers as perhaps believed; it is rather an important source of foreign exchange, which host governments employ buyers to collect for their coffers. It is maintained here that if the underlying purpose of fair trade is to improve the livelihoods and well-being of subsistence producers in developing countries, then the models that have proved so successful in alleviating the hardships of agro-producers of 'tropical' commodities such as coffee, tea, bananas and cocoa, should be adapted to artisanal gold mining in sub-Saharan Africa. Campaigns promoting 'fair trade gold' in the region should view host governments, and not Western retailers, as the 'end consumer', and focus on improving governance at the grassroots, organizing informal operators into working cooperatives, and addressing complications with purchasing arrangements - all of which would go a long way toward improving the livelihoods of subsistence artisanal miners. A case study of Noyem, Ghana, the location of a sprawling illegal gold mining community, is presented, which magnifies these challenges further and provides perspective on how they can be overcome. (c) 2007 Elsevier Ltd. All rights reserved.

Visualizing knowledge in project-based work

This article considers how visual practices are used to manage knowledge in project-based work. It compares project-based work in a capital goods manufacturer and an architectural firm. Visual representations are used extensively in both cases, but the nature of visual practice differs significantly between the two. The research explores the kinds of knowledge that are (and aren't) developed and made visible in strategizing and planning activities. For example, whereas the emphasis of project-based work in the former firm is on exploitation of knowledge and it visualizes its project context largely in commercial and processual terms, the emphasis in the latter is on exploration and it uses a wide range of visual materials to understand physical interdependencies across the project boundary. We contend particular kinds of visual tools can help project teams step between exploration and exploitation within a project, and articulate the types of representations, foci of attention and patterns of interaction involved. The findings suggest that business managers can make more deliberate choices about how knowledge is made visible, and can change visual practice to align the project with exploring and exploiting opportunities. It raises the question: What don't you see within your organization? The work contributes to academic debates about managing through projects, strategising and organizing, while the focus on visual representation disrupts the tacit-codified dichotomy in the broad debate on knowledge and learning, and highlights the craft skills central to strategizing and organizing.

Design and evaluation of intelligent classifier based intrusion detection system

We have discovered a novel approach of intrusion detection system using an intelligent data classifier based on a self organizing map (SOM). We have surveyed all other unsupervised intrusion detection methods, different alternative SOM based techniques and KDD winner IDS methods. This paper provides a robust designed and implemented intelligent data classifier technique based on a single large size (30x30) self organizing map (SOM) having the capability to detect all types of attacks given in the DARPA Archive 1999 the lowest false positive rate being 0.04 % and higher detection rate being 99.73% tested using full KDD data sets and 89.54% comparable detection rate and 0.18% lowest false positive rate tested using corrected data sets.

Generative topographic mapping applied to clustering and visualization of motor unit action potentials

The identification and visualization of clusters formed by motor unit action potentials (MUAPs) is an essential step in investigations seeking to explain the control of the neuromuscular system. This work introduces the generative topographic mapping (GTM), a novel machine learning tool, for clustering of MUAPs, and also it extends the GTM technique to provide a way of visualizing MUAPs. The performance of GTM was compared to that of three other clustering methods: the self-organizing map (SOM), a Gaussian mixture model (GMM), and the neural-gas network (NGN). The results, based on the study of experimental MUAPs, showed that the rate of success of both GTM and SOM outperformed that of GMM and NGN, and also that GTM may in practice be used as a principled alternative to the SOM in the study of MUAPs. A visualization tool, which we called GTM grid, was devised for visualization of MUAPs lying in a high-dimensional space. The visualization provided by the GTM grid was compared to that obtained from principal component analysis (PCA). (c) 2005 Elsevier Ireland Ltd. All rights reserved.