No description available.

Knowledge Discovery in Databases (KDD), or Data Mining is used to discover interesting or useful patterns and relationships in data, with an emphasis on large volume of observational databases. Among many other types of information (knowledge) that can be discovered in data, patterns that are expressed in terms of features are popular because they can be understood and used directly by people. The recently proposed Emerging Pattern (EP) is one type of such knowledge patterns. Emerging Patterns are sets of items (conjunctions of attribute values) whose frequency change significantly from one dataset to another. They are useful as a means of discovering distinctions inherently present amongst a collection of datasets and have been shown to be a powerful method for constructing accurate classifiers. (For complete abstract open document)

Made available in DSpace on 2014-06-12T15:57:37Z (GMT). No. of bitstreams: 2 arquivo3214_1.pdf: 3789743 bytes, checksum: 5121a8308f93d20405e932f1e9bab193 (MD5) license.txt: 1748 bytes, checksum: 8a4605be74aa9ea9d79846c1fba20a33 (MD5) Previous issue date: 2010 / Universidade Federal do Amazonas / Um breve exame do atual tráfego Internet mostra uma mistura de serviços conhecidos e desconhecidos, novas e antigas aplicações, tráfego legítimo e ilegítimo, dados solicitados e não solicitados, tráfego altamente relevante ou simplesmente indesejado. Entre esses, o tráfego Internet não desejado tem se tornado cada vez mais prejudicial para o desempenho e a disponibilidade de serviços, tornando escasso os recursos das redes. Tipicamente, este tipo de tráfego é representado por spam, phishing, ataques de negação de serviço (DoS e DDoS), vírus e worms, má configuração de recursos e serviços, entre outras fontes. Apesar dos diferentes esforços, isolados e/ou coordenados, o tráfego Internet não desejado continua a crescer. Primeiramente, porque representa uma vasta gama de aplicações de usuários, dados e informações com diferentes objetivos. Segundo, devido a ineficácia das atuais soluções em identificar e reduzir este tipo de tráfego. Por último, uma definição clara do que é não desejado tráfego precisa ser feita. A fim de solucionar estes problemas e motivado pelo nível atingido pelo tráfego não desejado, esta tese apresenta: 1. Um estudo sobre o universo do tráfego Internet não desejado, apresentado definições, discussões sobre contexto e classificação e uma série de existentes e potencias soluções. 2. Uma metodologia para identificar tráfego não desejado baseada em orquestração. OADS (Orchestration Anomaly Detection System) é uma plataforma única para a identificação de tráfego não desejado que permite um gerenciamento cooperativa e integrado de métodos, ferramentas e soluções voltadas a identificação de tráfego não desejado. 3. O projeto e implementação de soluções modulares integráveis a metodologia proposta. A primeira delas é um sistema de suporte a recuperação de informações na Web (WIRSS), chamado OADS Miner ou simplesmente ARAPONGA, cuja função é reunir informações de segurança sobre vulnerabilidades, ataques, intrusões e anomalias de tráfego disponíveis na Web, indexá-las eficientemente e fornecer uma máquina de busca focada neste tipo de informação. A segunda, chamada Alert Pre- Processor, é um esquema que utilize uma técnica de cluster para receber múltiplas fontes de alertas, agregá-los e extrair aqueles mais relevantes, permitindo correlações e possivelmente a percepção das estratégias usadas em ataques. A terceira e última é um mecanismo de correlação e fusão de alertas, FER Analyzer, que utilize a técnica de descoberta de episódios frequentes (FED) para encontrar sequências de alertas usadas para confirmar ataques e possivelmente predizer futuros eventos. De modo a avaliar a proposta e suas implementações, uma série de experimentos foram conduzidos com o objetivo de comprovar a eficácia e precisão das soluções

Purpose: The aim of the systematic review was to explore the role that anxiety plays in hospital admissions for those with Chronic Obstructive Pulmonary Disease (COPD). The empirical study aimed to examine whether the frequency of COPD related admissions is related to psychological factors (anxiety, depression, catastrophising, and mindfulness), disease severity, perceived disability and demographic factors. It also sought to examine whether cognitive factors (mindfulness and catastrophising) may explain unique variance in predicting anxiety and COPD-related admissions when other relevant factors are controlled for. Methods: The literature was systematically searched for research related to the predictive power of anxiety in relation to COPD related hospital admissions. A postal cross-sectional survey of 54 people with COPD examined the psychological profile of those who are admitted to hospital for COPD, and if mindfulness and catastrophising can predict anxiety and COPD hospital admissions. Correlations and multiple regressions were utilised to explore these hypotheses. Results: Fourteen studies met inclusion criteria for the systematic review, demonstrating mixed results regarding whether anxiety plays a role in COPD related hospital admissions. Findings from the empirical study suggest that a significant relationship exists between disease severity and number of COPD hospital admissions and catastrophising and overall mindfulness predicted 16.3% of variance in COPD hospital admissions (non-significant). Anxiety scores were significantly correlated with breathlessness, depression, catastrophising and mindfulness with catastrophising and mindfulness predicting 22.3% of variance in anxiety (significant). Conclusions: Further research with robust measures of anxiety and hospital utilization are needed to aid our understanding of the role of anxiety in COPD related admissions. Further research is necessary to determine if mindfulness and catastrophising are useful constructs in predicting anxiety levels and hospital admissions in those with COPD. This will help to inform future psychological interventions with this population.

Frequent Itemset Mining, the process of finding frequently co-occurring sets of items in a dataset, has been at the core of the field of data mining for the past 25 years. During this time the datasets have grown much faster than the algorithms capacity to process them. Great progress was made at optimizing this task on a single computer however, despite years of research, very little progress has been made on parallelizing this task. FPGrowth based algorithms have proven notoriously difficult to parallelize and Apriori has largely fallen out of favor with the research community. In this thesis we introduce a parallel, Apriori based, Frequent Itemset Mining algo- rithm capable of distributing computation across large commodity clusters. Our case study demonstrates that our algorithm can efficiently scale to hundreds of cores, on a standard Hadoop MapReduce cluster, and can improve executions times by at least an order of magnitude at the lowest support levels. / Graduate / 0984 / 0800 / nclark@uvic.ca

A graph is a data structure that contains a set of nodes and a set of edges connecting these nodes. Nodes represent objects while edges model relationships among these objects. Graphs are used in various domains due to their ability to model complex relations among several objects. Given an input graph, the Frequent Subgraph Mining (FSM) task finds all subgraphs with frequencies exceeding a given threshold. FSM is crucial for graph analysis, and it is an essential building block in a variety of applications, such as graph clustering and indexing. FSM is computationally expensive, and its existing solutions are extremely slow. Consequently, these solutions are incapable of mining modern large graphs. This slowness is caused by the underlying approaches of these solutions which require finding and storing an excessive amount of subgraph matches. This dissertation proposes a scalable solution for FSM that avoids the limitations of previous work. This solution is composed of four components. The first component is a single-threaded technique which, for each candidate subgraph, needs to find only a minimal number of matches. The second component is a scalable parallel FSM technique that utilizes a novel two-phase approach. The first phase quickly builds an approximate search space, which is then used by the second phase to optimize and balance the workload of the FSM task. The third component focuses on accelerating frequency evaluation, which is a critical step in FSM. To do so, a machine learning model is employed to predict the type of each graph node, and accordingly, an optimized method is selected to evaluate that node. The fourth component focuses on mining dynamic graphs, such as social networks. To this end, an incremental index is maintained during the dynamic updates. Only this index is processed and updated for the majority of graph updates. Consequently, search space is significantly pruned and efficiency is improved. The empirical evaluation shows that the proposed components significantly outperform existing solutions, scale to a large number of processors and process graphs that previous techniques cannot handle, such as large and dynamic graphs.

Indiana University-Purdue University Indianapolis (IUPUI) / Text Mining is process of extracting high-quality knowledge from analysis of textual data. Rapidly growing interest and focus on research in many fields is resulting in an overwhelming amount of research literature. This literature is a vast source of knowledge. But due to huge volume of literature, it is practically impossible for researchers to manually extract the knowledge. Hence, there is a need for automated approach to extract knowledge from unstructured data. Text mining is right approach for automated extraction of knowledge from textual data. The objective of this thesis is to mine documents pertaining to research literature, to find novel associations among entities appearing in that literature using Incremental Mining. Traditional text mining approaches provide binary associations. But it is important to understand context in which these associations occur. For example entity A has association with entity B in context of entity C. These contexts can be visualized as multi-way associations among the entities which are represented by a Hypergraph. This thesis work talks about extracting such multi-way associations among the entities using Frequent Itemset Mining and application of a new concept called Output space sampling to extract such multi-way associations in space and time efficient manner. We incorporated concept of personalization in Output space sampling so that user can specify his/her interests as the frequent hyper-associations are extracted from the text.

No description available.

No description available.

Diagnosis techniques and treatments for Escherichia coli mastitis in the dairy bovine were evaluated in two experiments. The first experiment evaluated eosin methylene blue agar as a method of distinguishing E.coli from other gram-negative mastitis pathogens. Escherichia coli will usually produce a green metallic sheen on eosin methylene blue agar. One hundred and twenty-nine milk samples or gram-negative isolates from milk samples were used to compare eosin methylene blue agar to a commercial biochemical test strip (the accepted standard). There was an intermethod agreement of 96.9% and a k-value of 93.7% indicating excellent agreement beyond chance between test methods. Eosin methylene blue agar is a reliable method for differentiation of E. coli from other gram-negative mastitis pathogens. The second experiment evaluated the efficacy of frequent milk-out as a treatment for E. coli mastitis. Sixteen Holstein dairy cows were divided into 2 blocks and randomly assigned to 1 of 4 treatment groups: 1) non-infected, not frequently milked-out, i.e. not treated (NI-NT), 2) experimentally infected with E. coli, not treated (EC-NT), 3) non-infected, frequently milked-out (NI-FMO), and 4) experimentally infected with E. coli, frequently milked-out (EC-FMO). Hours to bacterial, clinical and systemic cure were not different between the EC-NT and EC-FMO treatment groups. Serum a-lactalbumin concentrations were evaluated between treatment groups as a measure of udder health. Serum a-lactalbumin concentrations were higher in cows in the EC-NT treatment group than cows in the NI-NT, NI-FMO and EC-FMO treatment groups at 12 hours post-experimental challenge. Serum a-lactalbumin concentrations were higher in cows in the NI-FMO treatment group than in cows in the NI-NT, EC-NT and EC-FMO treatment groups at 36 hours post-experimental challenge. Results from this study do not support frequent milk-out as a treatment for E. coli mastitis. / Master of Science