Learning and using taxonomies for visual and olfactory classification

Humans are able of distinguishing more than 5000 visual categories even in complex environments using a variety of different visual systems all working in tandem. We seem to be capable of distinguishing thousands of different odors as well. In the machine learning community, many commonly used multi-class classifiers do not scale well to such large numbers of categories. This thesis demonstrates a method of automatically creating application-specific taxonomies to aid in scaling classification algorithms to more than 100 cate- gories using both visual and olfactory data. The visual data consists of images collected online and pollen slides scanned under a microscope. The olfactory data was acquired by constructing a small portable sniffing apparatus which draws air over 10 carbon black polymer composite sensors. We investigate performance when classifying 256 visual categories, 8 or more species of pollen and 130 olfactory categories sampled from common household items and a standardized scratch-and-sniff test. Taxonomies are employed in a divide-and-conquer classification framework which improves classification time while allowing the end user to trade performance for specificity as needed. Before classification can even take place, the pollen counter and electronic nose must filter out a high volume of background “clutter” to detect the categories of interest. In the case of pollen this is done with an efficient cascade of classifiers that rule out most non-pollen before invoking slower multi-class classifiers. In the case of the electronic nose, much of the extraneous noise encountered in outdoor environments can be filtered using a sniffing strategy which preferentially samples the visensor response at frequencies that are relatively immune to background contributions from ambient water vapor. This combination of efficient background rejection with scalable classification algorithms is tested in detail for three separate projects: 1) the Caltech-256 Image Dataset, 2) the Caltech Automated Pollen Identification and Counting System (CAPICS) and 3) a portable electronic nose specially constructed for outdoor use.

Contributions on distance-based algorithms, multi-classifier construction and pairwise classification

179 p.

Marine and estuarine ecosystem and habitat classification

The Ecological Society of America and NOAA's Offices of Habitat Conservation and Protected Resources sponsored a workshop to develop a national marine and estuarine ecosystem classification system. Among the 22 people involved were scientists who had developed various regional classification systems and managers from NOAA and other federal agencies who might ultimately use this system for conservation and management. The objectives were to: (1) review existing global and regional classification systems; (2) develop the framework of a national classification system; and (3) propose a plan to expand the framework into a comprehensive classification system. Although there has been progress in the development of marine classifications in recent years, these have been either regionally focused (e.g., Pacific islands) or restricted to specific habitats (e.g., wetlands; deep seafloor). Participants in the workshop looked for commonalties across existing classification systems and tried to link these using broad scale factors important to ecosystem structure and function.

Some Extensions of the K-Means Algorithm for Image Segmentation and Pattern Classification

In this paper we present some extensions to the k-means algorithm for vector quantization that permit its efficient use in image segmentation and pattern classification tasks. It is shown that by introducing state variables that correspond to certain statistics of the dynamic behavior of the algorithm, it is possible to find the representative centers fo the lower dimensional maniforlds that define the boundaries between classes, for clouds of multi-dimensional, mult-class data; this permits one, for example, to find class boundaries directly from sparse data (e.g., in image segmentation tasks) or to efficiently place centers for pattern classification (e.g., with local Gaussian classifiers). The same state variables can be used to define algorithms for determining adaptively the optimal number of centers for clouds of data with space-varying density. Some examples of the applicatin of these extensions are also given.

Contact, trust and social capital in Northern Ireland: a qualitative study of three mixed communities

In a recent paper, Robert Putnam (2007) challenges the contact hypothesis by arguing that ethnic diversity causes people to ‘hunker down’ and essentially withdraw themselves from society. Drawing on
qualitative data collected from three mixed communities in Northern Ireland, this paper explores the extent and quality of contact experienced by Protestants and Catholics in their everyday lives. Themes emerging from our data are generally consistent with the contact hypothesis. There is also some support for Putnam’s theory that mixed environments can induce ‘hunkering down’ and that inter-group trust may be compromised. However, our data challenge Putnam’s argument that these responses are a consequence of ‘anomie’ or ‘social malaise’. Rather, we find that withdrawal from social activity in the neighbourhoods we observed was a calculated response at times of threat, often aimed at protecting existent positive inter-ethnic relations.

Erythrocytosis in children and adolescents-classification, characterization, and consensus recommendations for the diagnostic approach

During recent years, the increasing knowledge of genetic and physiological changes in polycythemia vera (PV) and of different types of congenital erythrocytosis has led to fundamental changes in recommendations for the diagnostic approach to patients with erythrocytosis. Although widely accepted for adult patients this approach may not be appropriate with regard to children and adolescents affected by erythrocytosis. The "congenital erythrocytosis" working group established within the framework of the MPN&MPNr-EuroNet (COST action BM0902) addressed this question in a consensus finding process and developed a specific algorithm for the diagnosis of erythrocytosis in childhood and adolescence which is presented here. Pediatr Blood Cancer 2013;9999:XX-XX. © 2013 Wiley Periodicals, Inc.

Does intergenerational contact reduce Ageism: When and How Contact Interventions Actually Work?

Although the past two decades have seen concrete attempts to reduce ethnic and racial prejudice, relatively little has been done to diminish age related prejudice. In this paper, we review intergenerational contact interventions have been applied in a real world setting, the results are mixed. While contact interventions are not a panacea, they do constitute a main plank in efforts to redress ageism. We, therefore, examine the types of interventions that are effective, the processes underlying their enhanced impact, and clarifying when and how intergenerational contact can predict more positive attitudes towards the elderly. Finally, we highlight ways in which findings might be applied to the development of more effective interventions aimed at combating a pervasive stereotype of aging, drawing out lessons for theory and implications for practice.