Management of data imprecision has become increasingly important, especially with the advance of technology enabling applications to collect and store huge amount data from multiple sources. Data collected in such applications involve a large number of variables and various types of data imperfections. These data, when used in knowledge discovery applications, require the following: 1) computationally efficient algorithms that works faster with limited resources, 2) an effective methodology for modeling data imperfections and 3) procedures for enabling knowledge discovery and quantifying and propagating partial or incomplete knowledge throughout the decision-making process. Bayesian Networks (BNs) provide a convenient framework for modeling these applications probabilistically enabling a compact representation of the joint probability distribution involving large numbers of variables. BNs also form the foundation for a number of computationally efficient algorithms for making inferences. The underlying probabilistic approach however is not sufficiently capable of handling the wider range of data imperfections that may appear in many new applications (e.g., medical data). Dempster-Shafer theory on the other hand provides a strong framework for modeling a broader range of data imperfections. However, it must overcome the challenge of a potentially enormous computational burden. In this dissertation, we introduce the joint Dirichlet BoE, a certain mass assignment in the DS theoretic framework, that simplifies the computational complexity while enabling one to model many common types of data imperfections. We first use this Dirichlet BoE model to enhance the performance of the EM algorithm used in learning BN parameters from data with missing values. To form a framework of reasoning with the Dirichlet BoE, the DS theoretic notions of conditionals, independence and conditional independence are revisited. These notions are then used to develop the DS-BN, a BN-like graphical model in the DS theoretic framework, that enables a compact representation of the joint Dirichlet BoE. We also show how one may use the DS-BN in different types of reasoning tasks. A local message passing scheme is developed for efficient propagation of evidence in the DS-BN. We also extend the use of the joint Dirichlet BoE to Markov models and hidden Markov models to address the uncertainty arising due to inadequate training data. Finally, we present the results of various experiments carried out on synthetically generated data sets as well as data sets from medical applications.

Any one organization or agency, whether for-profit or non-profit organizations that are seeking to enhance their efficiency, improve production technology, thereby achieving the goal of improving productivity, with a view to the current competitive environment. Efficiency measurement is very important, it can help decision makers understand whether the organization achieve technology progress and innovation objectives. In recent years, the government and civil organizations devote themselves to measure the change of organizational efficiency and productivity. Academia constantly research and develop various models of efficiency and productivity analysis, and application to actual cases analysis. Efficiency and productivity analysis has leapt to the mainstream of production economic studies. This empirical study adopts the census data of the classification of the Chamber of Commerce and industry of manufacturing in Taiwan, using two-stage approach to explore dynamic agglomeration externalities of 2-digit manufacturing. In the first stage, we apply dynamic network data envelopment analysis and Malmquist productivity index to calculate static efficiency and dynamic efficiency of 2-digit manufacturing. In the second stage, we apply Tobit regression analysis to verify a manufacturing geographical concentration effects on productive efficiency. We also adopt two-stage least squares methods (2SLS) to validate dynamic agglomeration externalities effects of manufacturing. Based on the results of this empical study, we propose some specific practical policy alternatives and management strategies. In the last 20 years, the strctures of Taiwan manufacturing industries have significant changes, the livelihood industry and of the sharp decline in industry, the chemical industry, electronics industry, metal machinery industry is growing fast. There is an obvous agglomeration tendency toward northern Taiwan region. In static efficiency, labour-intensive manufacturing industries tend to be diminishing return to scale rendering, while knowledge-intensive industries are rendering the increasing trend. The scale efficiency of eastern region manufacturing is very low, resulting in their productive efficiency significantly lower than the northern, central, southern regional manufacturing. In dynamic efficiency, the total factor productivity (TFP) of Taiwan manufacturing industries are rendering the growth trend, achieving the goal of innovation effect. However, the technical efficiency of manufacturing are rendering decline trend. This study found that the most important impact factor on production efficiency is the internal economies of scale. Localization economies, urbanization economies, and other static agglomeration economies external effect gradually reduce. Moreover, this study also found that Taiwan manufacturing industries have notable MAR professional dynamic external economics and notable Porter regional competitive dynamic external economic effect. Besides, Taiwan manufacturing industries has noticeable human resource dynamic external economics, but we also found low wages is beneficial to regional economic growth. We should not expand to explain Taiwan manufacturing-sweatshops. This phenomenon may be caused by high salaries, high rents, high land costs and high labor costs, these factors offset the interest of agglomeration economies. Finally, Taiwan and mainland China signed a cross-strait economic cooperation framework agreement (ECFA) in Chongqing on 29 June 2010. Taiwan manufacturing inevitably be impacted and influenced by ECFA. This is an important topic worthy of further study and discussion in the future.

ITC/USA 2014 Conference Proceedings / The Fiftieth Annual International Telemetering Conference and Technical Exhibition / October 20-23, 2014 / Town and Country Resort & Convention Center, San Diego, CA / The Enhanced Query Data Recorder (EQDR) has been developed under the Test Resource Management Center's (TRMC) Spectrum Efficient Technologies (SET) T&E S&T program. The EQDR is a network flight recorder built around the iNET standards and which is intended to meet the future needs of the networked telemetry environment. The EQDR is designed to support the "fetch" of recorded test data during a test without interruption to the ongoing recording of data from the test article vehicle network. The key benefits of the network data recorder as implemented in the EQDR are increased flexibility and efficiency of test in an environment with increasing demands on spectrum available for telemetered data. EQDR enables retrieval of individual recorded parameters on an as-needed basis. Having the flexibility to send data only when it is required rather than throughout the duration of the test significantly increases the efficiency with which limited spectrum resources are used. EQDR enables parametric-level data retrieval, based not only on time interval and data source, but also on the content of the recorded data messages. EQDR enables selective, efficient retrieval of individual parameters using indexes derived from the actual values of recorded data.

ITC/USA 2012 Conference Proceedings / The Forty-Eighth Annual International Telemetering Conference and Technical Exhibition / October 22-25, 2012 / Town and Country Resort & Convention Center, San Diego, California / The Test Resource Management Center's (TRMC) Spectrum Efficient Technologies (SET) S&T program is sponsoring development of the Enhanced Query Data Recorder (EQDR), a network flight recorder that is intended to meet the future needs of the networked telemetry environment. EQDR is designed to support the "fetch" of recorded test data during a test without interrupting the ongoing recording of data from the test article vehicle network. The key benefits of the network data recorder as implemented in EQDR are increased flexibility and efficiency of test in an environment with increasing demands on spectrum available for telemetered data. EQDR enables retrieval of individual recorded parameters on an as-needed basis. Having the flexibility to send data only when it is required rather than throughout the duration of the test significantly increases the efficiency with which limited spectrum resources are used. EQDR enables parametric-level data retrieval, based not only on time interval and data source, but also on the content of the recorded data messages. EQDR enables selective, efficient retrieval of individual parameters using indexes derived from the actual values of recorded data. This paper describes the design of EQDR and the benefits of selective data storage and retrieval in the application of networked telemetry. In addition it describes the performance of the EQDR in terms of data recording and data retrieval rates when implemented on single board computers designed for use in the aeronautical test environment with size, weight, and power constraints.

With the advancement of the Internet and related technologies, many traditional crimes have made the leap to digital environments. The successes of data mining in a wide variety of disciplines have given birth to crime analysis. Traditional crime analysis is mainly focused on understanding crime patterns, however, it is unsuitable for identifying and monitoring emerging crimes. The true nature of crime remains buried in unstructured content that represents the hidden story behind the data. User feedback leaves valuable traces that can be utilised to measure the quality of various aspects of products or services and can also be used to detect, infer, or predict crimes. Like any application of data mining, the data must be of a high quality standard in order to avoid erroneous conclusions. This thesis presents a methodology and practical experiments towards discovering whether (i) user feedback can be harnessed and processed for crime intelligence, (ii) criminal associations, structures, and roles can be inferred among entities involved in a crime, and (iii) methods and standards can be developed for measuring, predicting, and comparing the quality level of social data instances and samples. It contributes to the theory, design and development of a novel framework for crime intelligence and algorithm for the estimation of social data quality by innovatively adapting the methods of monitoring water contaminants. Several experiments were conducted and the results obtained revealed the significance of this study in mining social data for crime intelligence and in developing social data quality filters and decision support systems. / Commonwealth Scholarship Commission.

Yes / Using a sample of Brazilian listed companies during 2010-2019, the study investigates the endogeneity and the directional cause-effect relationship between firm efficiency, market structure and firms’ ESG performance under a Stochastic Structural Relationship Programming (SSRP) model. Also, comprehensive market structure indicators are used. The efficiency is estimated under a two-stage network Data Envelopment Analysis (NDEA) model. Our empirical evidence is threefold. First, our evidence indicates that firms with better environmental performance are more efficient, whereas lower ESG performance and poorer corporate governance practices are associated with a higher level of efficiency. Second, our findings suggest that market structure measures (i.e., competition and market power) have heterogeneous impacts on various ESG indexes. Specifically, higher market competition is associated with better overall ESG performance and environmental performance but worse corporate governance performance, although market power can only enhance the environmental and governance performance of firms. Third, the two market structure proxies employed in this study are significantly attributed to firm efficiency. Our findings provide practical implications for various stakeholders and suggest avenues for future studies that can build on our evidence.

Made available in DSpace on 2014-12-17T14:09:18Z (GMT). No. of bitstreams: 1 ClaudiaACF_TESE.pdf: 6242500 bytes, checksum: 7a857ce8be46bd85b252fca3bf3fa45c (MD5) Previous issue date: 2013-05-24 / The increasing use of fossil fuels in line with cities demographic explosion carries out to huge environmental impact in society. For mitigate these social impacts, regulatory requirements have positively influenced the environmental consciousness of society, as well as, the strategic behavior of businesses. Along with this environmental awareness, the regulatory organs have conquered and formulated new laws to control potentially polluting activities, mostly in the gas stations sector. Seeking for increasing market competitiveness, this sector needs to quickly respond to internal and external pressures, adapting to the new standards required in a strategic way to get the Green Badge . Gas stations have incorporated new strategies to attract and retain new customers whom present increasingly social demand. In the social dimension, these projects help the local economy by generating jobs and income distribution. In this survey, the present research aims to align the social, economic and environmental dimensions to set the sustainable performance indicators at Gas Stations sector in the city of Natal/RN. The Sustainable Balanced Scorecard (SBSC) framework was create with a set of indicators for mapping the production process of gas stations. This mapping aimed at identifying operational inefficiencies through multidimensional indicators. To carry out this research, was developed a system for evaluating the sustainability performance with application of Data Envelopment Analysis (DEA) through a quantitative method approach to detect system s efficiency level. In order to understand the systemic complexity, sub organizational processes were analyzed by the technique Network Data Envelopment Analysis (NDEA) figuring their micro activities to identify and diagnose the real causes of overall inefficiency. The sample size comprised 33 Gas stations and the conceptual model included 15 indicators distributed in the three dimensions of sustainability: social, environmental and economic. These three dimensions were measured by means of classical models DEA-CCR input oriented. To unify performance score of individual dimensions, was designed a unique grouping index based upon two means: arithmetic and weighted. After this, another analysis was performed to measure the four perspectives of SBSC: learning and growth, internal processes, customers, and financial, unifying, by averaging the performance scores. NDEA results showed that no company was assessed with excellence in sustainability performance. Some NDEA higher efficiency Gas Stations proved to be inefficient under certain perspectives of SBSC. In the sequence, a comparative sustainable performance and assessment analyzes among the gas station was done, enabling entrepreneurs evaluate their performance in the market competitors. Diagnoses were also obtained to support the decision making of entrepreneurs in improving the management of organizational resources and promote guidelines the regulators. Finally, the average index of sustainable performance was 69.42%, representing the efforts of the environmental suitability of the Gas station. This results point out a significant awareness of this segment, but it still needs further action to enhance sustainability in the long term / A crescente utiliza??o de combust?veis f?sseis alinhada ? explos?o demogr?fica em centros urbanos tem ocasionado grandes problemas de impacto ambiental na sociedade. Para mitigar esses impactos, as exig?ncias dos ?rg?os reguladores t?m influenciado positivamente na consci?ncia ambiental da sociedade, bem como no comportamento estrat?gico das empresas. Com essa consci?ncia ambiental, os ?rg?os t?m conquistado maiores respaldos e formulado novas legisla??es no controle de atividades potencialmente poluidoras, sobretudo no setor dos postos revendedores de combust?veis. Em busca de aumentar a competitividade no mercado, esse segmento precisa responder rapidamente ?s press?es (externas e internas), adequando-se aos novos padr?es exigidos de maneira estrat?gica na obten??o do selo verde. Os postos t?m incorporado novas estrat?gias para atrair e fidelizar clientes cada vez mais exigentes. No ?mbito social, esses empreendimentos auxiliam a economia local com a gera??o de empregos e distribui??o de renda. Mediante esse contexto, o presente trabalho tem como objetivo alinhar as dimens?es social, econ?mica e ambiental caracterizando a mensura??o do desempenho sustent?vel nos postos de revenda de combust?vel na cidade do Natal/RN. As perspectivas do Balanced Scorecard Sustent?vel (SBSC) foram fundamentadas por meio de um conjunto de indicadores para mapear o processo produtivo dos postos. Esse mapeamento visou identificar a inefici?ncia operacional por meio de indicadores multidimensionais. Na condu??o desta pesquisa, elaborou-se um sistema de avalia??o do desempenho sustent?vel com aplica??o do Data Envelopment Analysis (DEA), uma abordagem quantitativa para detectar o n?vel de efici?ncia do sistema. Com o intuito de compreender a complexidade sist?mica, os sub processos organizacionais foram analisados por meio da t?cnica Network Data Envelopment Analysis (NDEA) com o desmembramento das suas micro atividades para identificar e diagnosticar as reais causas de inefici?ncia. O tamanho amostral foi composto por 33 postos de revenda de combust?vel e o modelo conceitual contemplou 15 indicadores distribu?dos nas tr?s dimens?es da sustentabilidade: social, ambiental e econ?mica. Essas tr?s dimens?es foram mensuradas por meio de modelos cl?ssicos DEA-CCR com orienta??o input. Visando unificar o escore de desempenho individual das dimens?es, foi elaborado um ?nico ?ndice considerado parcialmente agrupado por meio de duas m?dias: aritm?tica e ponderada. Posteriormente, outra an?lise foi realizada para mensurar as quatro perspectivas do SBSC: aprendizado e crescimento; processos internos; clientes; e, financeira, unificando, por meio da m?dia os escores de desempenho. Os resultados do modelo NDEA apontaram que nenhuma empresa foi avaliada com excel?ncia no desempenho sustent?vel. Os postos com maiores ?ndices de efici?ncia mostraram-se ineficientes em determinadas perspectivas do SBSC. Na sequ?ncia, as an?lises apresentaram uma avalia??o do desempenho sustent?vel e das perspectivas de maneira comparativa entre os postos, possibilitando aos empres?rios avaliarem seu desempenho entre os concorrentes. Foram tamb?m obtidos diagn?sticos para subsidiar a tomada de decis?o dos empres?rios na melhoria do gerenciamento dos recursos organizacionais e promover diretrizes balizadoras nos ?rg?os regulamentadores. O escore m?dio do desempenho sustent?vel foi 69,42% representando os esfor?os empreendidos na adequa??o ambiental dos postos. Isso sinaliza uma consider?vel consci?ncia desse segmento, por?m ainda necessita de novas a??es para incrementar a sustentabilidade no longo prazo

One of the challenging issues for mobile ad hoc network (MANET) applications is data replication. Unreliable wireless communication, mobility of network participators and limited resource capacities of mobile devices make conventional replication techniques useless for MANETs. Frequent network divisions and unexpected disconnections should be handled. In this thesis work, a novel mobility and power aware, data interest based data replication strategy is presented. Main objective is to improve data accessibility among a mission critical mobility group. A clustering approach depending on mobility and data interest patterns similarities is introduced. The investigated replica allocation methodology takes care of data access frequency and data correlation values together with mobile nodes&rsquo / remaining energy and memory capacities. Performance of the proposed approach is analyzed in terms of data accessibility / cache hit ratio and traffic metrics. Improvements are observed by data interest based clustering in addition to mobility awareness over sole mobility aware clustering. Advantages of power aware replica allocation are demonstrated by experimental simulations.

Reliable forecasting models are needed to achieve the climate related goals in the face of increasing transport demand. Such models can predict the long-term behavioural response to policy interventions, including infrastructure investments, and thus provide valuable pre-dictions for decision makers. Contemporary forecasting models are mainly based on national travel surveys. Unfortunately, the response rates of such surveys have steadily declined, implying that the respondents become less representative of the whole population. A particular weakness is that it is likely that respondents with a high valuation of time are less willing to respond to surveys (because they have less time available for such), and therefore there is a high chance that they are underrepresented among the respondents. The valuation of time plays an important role for the cost benefit analyses of public policies including transport investments, and there is no reliable way of controlling for this uneven sampling of time preferences. Fortunately, there is simultaneously an increase in the number of signals sent between mobile phones and network antennae, and research has now reached the point where it is possible to determine not only the travel destination but also the travel mode based on mobile phone network antennae connections. The aim of this thesis is to investigate if and how mobile phone network data can be used to estimate transportation mode choice demand models that can be used for forecasting and planning. Key challenges with using this data source in the context of mode choice models are identified and met. The identified challenges include uncertainty in the choice variable, the difficulty to distinguish car and bus trips, and the lack of information about the trip purpose. In the first paper we propose three possible model formulations and analyse how the uncertainty in the choice outcome variable would play a role in the different model formulations. We also conclude that it is indeed possible to estimate mode choice demand models based on mobile phone network data, with good results in terms of behavioural interpretability and significance. In the second paper we estimate models using a nested logit structure to account for the difficulty in separating bus and car, and a latent class model specification to meet the challenge of having an unknown trip purpose. / <p><strong>Funding agencies:</strong> The research in this thesis has mainly been funded by the research projects DEMOPAN and DEMOPAN-2 within the research program Transportekonomi at The Swedish Transport Administration.</p>

No description available.