A Knowledge-based System for Intelligent Support in Pharmacogenomics Evidence Assessment: Ontology-driven Evidence Representation, Retrieval, Classification and Interpretation

Thesis (Ph.D.)--University of Washington, 2016-06

Reliability measures for local nodes assessment in classification trees

Most of the modem developments with classification trees are aimed at improving their predictive capacity. This article considers a curiously neglected aspect of classification trees, namely the reliability of predictions that come from a given classification tree. In the sense that a node of a tree represents a point in the predictor space in the limit, the aim of this article is the development of localized assessment of the reliability of prediction rules. A classification tree may be used either to provide a probability forecast, where for each node the membership probabilities for each class constitutes the prediction, or a true classification where each new observation is predictively assigned to a unique class. Correspondingly, two types of reliability measure will be derived-namely, prediction reliability and classification reliability. We use bootstrapping methods as the main tool to construct these measures. We also provide a suite of graphical displays by which they may be easily appreciated. In addition to providing some estimate of the reliability of specific forecasts of each type, these measures can also be used to guide future data collection to improve the effectiveness of the tree model. The motivating example we give has a binary response, namely the presence or absence of a species of Eucalypt, Eucalyptus cloeziana, at a given sampling location in response to a suite of environmental covariates, (although the methods are not restricted to binary response data).

Using secondary knowledge to support decision tree classification of retrospective clinical data

Retrospective clinical data presents many challenges for data mining and machine learning. The transcription of patient records from paper charts and subsequent manipulation of data often results in high volumes of noise as well as a loss of other important information. In addition, such datasets often fail to represent expert medical knowledge and reasoning in any explicit manner. In this research we describe applying data mining methods to retrospective clinical data to build a prediction model for asthma exacerbation severity for pediatric patients in the emergency department. Difficulties in building such a model forced us to investigate alternative strategies for analyzing and processing retrospective data. This paper describes this process together with an approach to mining retrospective clinical data by incorporating formalized external expert knowledge (secondary knowledge sources) into the classification task. This knowledge is used to partition the data into a number of coherent sets, where each set is explicitly described in terms of the secondary knowledge source. Instances from each set are then classified in a manner appropriate for the characteristics of the particular set. We present our methodology and outline a set of experiential results that demonstrate some advantages and some limitations of our approach. © 2008 Springer-Verlag Berlin Heidelberg.

Protein-protein interactions classification from text via local learning with class priors

Text classification is essential for narrowing down the number of documents relevant to a particular topic for further pursual, especially when searching through large biomedical databases. Protein-protein interactions are an example of such a topic with databases being devoted specifically to them. This paper proposed a semi-supervised learning algorithm via local learning with class priors (LL-CP) for biomedical text classification where unlabeled data points are classified in a vector space based on their proximity to labeled nodes. The algorithm has been evaluated on a corpus of biomedical documents to identify abstracts containing information about protein-protein interactions with promising results. Experimental results show that LL-CP outperforms the traditional semisupervised learning algorithms such as SVMand it also performs better than local learning without incorporating class priors.

Classification of Data to Extract Knowledge from Neural Networks

A major drawback of artificial neural networks is their black-box character. Therefore, the rule extraction algorithm is becoming more and more important in explaining the extracted rules from the neural networks. In this paper, we use a method that can be used for symbolic knowledge extraction from neural networks, once they have been trained with desired function. The basis of this method is the weights of the neural network trained. This method allows knowledge extraction from neural networks with continuous inputs and output as well as rule extraction. An example of the application is showed. This example is based on the extraction of average load demand of a power plant.

Linked knowledge sources for topic classification of microposts:a semantic graph-based approach

Short text messages a.k.a Microposts (e.g. Tweets) have proven to be an effective channel for revealing information about trends and events, ranging from those related to Disaster (e.g. hurricane Sandy) to those related to Violence (e.g. Egyptian revolution). Being informed about such events as they occur could be extremely important to authorities and emergency professionals by allowing such parties to immediately respond. In this work we study the problem of topic classification (TC) of Microposts, which aims to automatically classify short messages based on the subject(s) discussed in them. The accurate TC of Microposts however is a challenging task since the limited number of tokens in a post often implies a lack of sufficient contextual information. In order to provide contextual information to Microposts, we present and evaluate several graph structures surrounding concepts present in linked knowledge sources (KSs). Traditional TC techniques enrich the content of Microposts with features extracted only from the Microposts content. In contrast our approach relies on the generation of different weighted semantic meta-graphs extracted from linked KSs. We introduce a new semantic graph, called category meta-graph. This novel meta-graph provides a more fine grained categorisation of concepts providing a set of novel semantic features. Our findings show that such category meta-graph features effectively improve the performance of a topic classifier of Microposts. Furthermore our goal is also to understand which semantic feature contributes to the performance of a topic classifier. For this reason we propose an approach for automatic estimation of accuracy loss of a topic classifier on new, unseen Microposts. We introduce and evaluate novel topic similarity measures, which capture the similarity between the KS documents and Microposts at a conceptual level, considering the enriched representation of these documents. Extensive evaluation in the context of Emergency Response (ER) and Violence Detection (VD) revealed that our approach outperforms previous approaches using single KS without linked data and Twitter data only up to 31.4% in terms of F1 measure. Our main findings indicate that the new category graph contains useful information for TC and achieves comparable results to previously used semantic graphs. Furthermore our results also indicate that the accuracy of a topic classifier can be accurately predicted using the enhanced text representation, outperforming previous approaches considering content-based similarity measures. © 2014 Elsevier B.V. All rights reserved.

Harnessing linked knowledge sources for topic classification in social media

Topic classification (TC) of short text messages offers an effective and fast way to reveal events happening around the world ranging from those related to Disaster (e.g. Sandy hurricane) to those related to Violence (e.g. Egypt revolution). Previous approaches to TC have mostly focused on exploiting individual knowledge sources (KS) (e.g. DBpedia or Freebase) without considering the graph structures that surround concepts present in KSs when detecting the topics of Tweets. In this paper we introduce a novel approach for harnessing such graph structures from multiple linked KSs, by: (i) building a conceptual representation of the KSs, (ii) leveraging contextual information about concepts by exploiting semantic concept graphs, and (iii) providing a principled way for the combination of KSs. Experiments evaluating our TC classifier in the context of Violence detection (VD) and Emergency Responses (ER) show promising results that significantly outperform various baseline models including an approach using a single KS without linked data and an approach using only Tweets. Copyright 2013 ACM.

The exclusive fishing zone for the artisanal fishery in Chocó Colombia: origins, development, and consequences for artisanal fisheries and food security.

Exclusive Fishing Zones (EFZs) are a type of place-based management tool often used to mitigate conflicts between fishing sectors by granting fishing rights to one of the sectors. This case study enhances our knowledge of the pre- and post-implementation processes associated with EFZs as well as its consequences for fish stocks and artisanal fishers and their families. The study draws upon interviews with artisanal fishers and key informants related to an EFZ established in 2008 in Colombia (the Chocó-EFZ). The findings of this research indicate that conflicts at sea and on land between artisanal and industrial fisheries triggered the Chocó-EFZ process. Results also show some potential benefits of the Chocó-EFZ including: a) mitigating conflicts between artisanal fishers and industrial shrimpers; b) contributing to the food security of artisanal fishing households and sustaining local fish stocks; c) supporting an existing informal community-based management as well as promoting the development of a co-management regime. Potential negative effects of the Chocó-EFZ include: a) displacement of industrial fishing effort and, b) job loss within the industrial shrimp industry. The findings of this research also indicate that there are multiple factors that jeopardize the effectiveness and continuation of the Chocó-EFZ, some of which include diversity of fisheries, power struggles among stakeholders, and disagreement about exclusive access to fish resources.

Knowledge and Control in the Contemporary Land Rush : Making Local Land Legible and Corporate Power Applicable in Rural Sierra Leone

13/01/15 Funded by •Faculty of Management at Radboud University Nijmegen

Knowledge and Control in the Contemporary Land Rush : Making Local Land Legible and Corporate Power Applicable in Rural Sierra Leone

13/01/15 Funded by •Faculty of Management at Radboud University Nijmegen

The effects of agglomeration economies on the productivity of manufacturing local units in Ireland

The purpose of this study is to examine the effects of agglomeration economies on the productivity of manufacturing local units in Ireland. Four types of agglomeration economies are considered in this study. These are internal economies of scale, localization economies, related variety and urbanization economies. This study makes a number of contributions to the literature. Firstly, this is the first study to conduct an investigation of the effects of agglomeration economies on the productivity of manufacturing local units operating in Ireland. Secondly, this study distinguishes between indigenous and foreign-owned local units which is important given the dual nature of the Irish economy (Krugman, 1997). Thirdly, in addition to considering the effects of agglomeration economies, this study examines the impact of spurious agglomeration on the productivity of foreign-owned local units. Using data from the Census of Industrial Local Units and a series of IV GMM estimators to control for endogeneity, the results of the analysis conducted in Chapter 6 reveal that there are differences in the effects of agglomeration economies on the productivity of indigenous and foreign-owned local units. In Chapter 7 the Census of Industrial Local Units is supplemented by additional data sources and more in-depth measures are generated to capture the features of each of the external agglomeration economies considered in this analysis. There is some evidence to suggest that the availability of local inputs has a negative and significant impact on productivity. The NACE based measures of related variety reveal that the availability of local inputs and knowledge spillovers for related sectors have a negative and significant impact on productivity. There is clear evidence to suggest that urbanization economies are important for increasing the productivity of indigenous local units. The findings reveal that a 1% increase in population density in the NUTS 3 region leads to an increase in the productivity of indigenous local units of approximately 0.07% to 0.08%. The results also reveal that there is a significant difference in the effects of agglomeration economies on the productivity of low-tech and medium/high-tech indigenous local units. The more in-depth measures of agglomeration economies used in Chapter 7 are also used in Chapter 8. A series of IV GMM regressions are estimated in order to identify the impact of agglomeration economies and spurious agglomeration on the productivity of foreign-owned local units operating in Ireland. There is some evidence found to suggest that the availability of a pool of skilled labour has a positive and significant on productivity of foreign-owned local units. There is also evidence to suggest that localization knowledge spillovers have a negative impact on the productivity of foreign-owned local units. There is strong evidence to suggest that the availability of local inputs has a negative impact on the productivity. The negative impact is not confined to the NACE 4-digit sector but also extends into related sectors as determined by Porter’s (2003) cluster classification. The cluster based skills measure of related variety has a positive and significant impact on the productivity of foreign-owned local units. Similar to Chapter 7, there is clear evidence to suggest that urbanization economies are important for increasing the productivity of foreign-owned local units. Both the summary measure and each of the more in-depth measures of agglomeration economies have a positive and significant impact on productivity. Spurious agglomeration has a positive and significant impact on the productivity of foreign-owned local units. The results indicate that the more foreign-owned local units of the same nationality in the country the greater the levels of productivity for the local unit. From a policy perspective, urbanization economies are clearly important for increasing the productivity of both indigenous and foreign-owned local units. Furthermore, the availability of a pool of skilled labour appears to be important for increasing the productivity of foreign-owned local units. Another policy implication that arises from these results relates to the differences observed between indigenous local units and foreign-owned local units and also between low-tech and medium/high-tech indigenous local units. These findings indicate that ‘one-size-fits-all’ type policies are not appropriate for increasing the productivity of local units operating in Ireland. Policies should be tailored to the needs of either indigenous or foreign-owned local units and also to specific sectors. This positive finding for own country spurious agglomeration is important from a policy perspective and is one that IDA Ireland should take on board.

Macro-epibenthic communities, bathymetry and enviromental information at the tip of the Antarctic Peninsula

The Southern Ocean ecosystem at the Antarctic Peninsula has steep natural environmental gradients, e.g. in terms of water masses and ice cover, and experiences regional above global average climate change. An ecological macroepibenthic survey was conducted in three ecoregions in the north-western Weddell Sea, on the continental shelf of the Antarctic Peninsula in the Bransfield Strait and on the shelf of the South Shetland Islands in the Drake Passage, defined by their environmental envelop. The aim was to improve the so far poor knowledge of the structure of this component of the Southern Ocean ecosystem and its ecological driving forces. It can also provide a baseline to assess the impact of ongoing climate change to the benthic diversity, functioning and ecosystem services. Different intermediate-scaled topographic features such as canyon systems including the corresponding topographically defined habitats 'bank', 'upper slope', 'slope' and 'canyon/deep' were sampled. In addition, the physical and biological environmental factors such as sea-ice cover, chlorophyll-a concentration, small-scale bottom topography and water masses were analysed. Catches by Agassiz trawl showed high among-station variability in biomass of 96 higher systematic groups including ecological key taxa. Large-scale patterns separating the three ecoregions from each other could be correlated with the two environmental factors, sea-ice and depth. Attribution to habitats only poorly explained benthic composition, and small-scale bottom topography did not explain such patterns at all. The large-scale factors, sea-ice and depth, might have caused large-scale differences in pelagic benthic coupling, whilst small-scale variability, also affecting larger scales, seemed to be predominantly driven by unknown physical drivers or biological interactions.

Ecological classification of Herschel Island based on supervised classification of multispectral satellite imagery

Permafrost landscapes experience different disturbances and store large amounts of organic matter, which may become a source of greenhouse gases upon permafrost degradation. We analysed the influence of terrain and geomorphic disturbances (e.g. soil creep, active-layer detachment, gullying, thaw slumping, accumulation of fluvial deposits) on soil organic carbon (SOC) and total nitrogen (TN) storage using 11 permafrost cores from Herschel Island, western Canadian Arctic. Our results indicate a strong correlation between SOC storage and the topographic wetness index. Undisturbed sites stored the majority of SOC and TN in the upper 70 cm of soil. Sites characterised by mass wasting showed significant SOC depletion and soil compaction, whereas sites characterised by the accumulation of peat and fluvial deposits store SOC and TN along the whole core. We upscaled SOC and TN to estimate total stocks using the ecological units determined from vegetation composition, slope angle and the geomorphic disturbance regime. The ecological units were delineated with a supervised classification based on RapidEye multispectral satellite imagery and slope angle. Mean SOC and TN storage for the uppermost 1?m of soil on Herschel Island are 34.8 kg C/m**2 and 3.4 kg N/m**2, respectively.