<p>Many methods used for estimation and detection consider only the mean and variance of the involved noise instead of the full noise descriptions. One reason for this is that the mathematics is often considerably simplified this way. However, the implications of the simplifications are seldom studied, and this thesis shows that if no approximations are made performance is gained. Furthermore, the gain is quantified in terms of the useful information in the noise distributions involved. The useful information is given by the intrinsic accuracy, and a method to compute the intrinsic accuracy for a given distribution, using Monte Carlo methods, is outlined.</p><p>A lower bound for the covariance of the estimation error for any unbiased estimator s given by the Cramér-Rao lower bound (CRLB). At the same time, the Kalman filter is the best linear unbiased estimator (BLUE) for linear systems. It is in this thesis shown that the CRLB and the BLUE performance are given by the same expression, which is parameterized in the intrinsic accuracy of the noise. How the performance depends on the noise is then used to indicate when nonlinear filters, e.g., a particle filter, should be used instead of a Kalman filter. The CRLB results are shown, in simulations, to be a useful indication of when to use more powerful estimation methods. The simulations also show that other techniques should be used as a complement to the CRLB analysis to get conclusive performance results.</p><p>For fault detection, the statistics of the asymptotic generalized likelihood ratio (GLR) test provides an upper bound on the obtainable detection performance. The performance is in this thesis shown to depend on the intrinsic accuracy of the involved noise. The asymptotic GLR performance can then be calculated for a test using the actual noise and for a test using the approximative Gaussian noise. Based on the difference in performance, it is possible to draw conclusions about the quality of the Gaussian approximation. Simulations show that when the difference in performance is large, an exact noise representation improves the detection. Simulations also show that it is difficult to predict the exact influence on the detection performance caused by substituting the system noise with Gaussian noise approximations.</p> / <p>Många metoder som används i estimerings- och detekteringssammanhang tar endast hänsyn till medelvärde och varians hos ingående brus istället för att använda en fullständig brusbeskrivning. En av anledningarna till detta är att den förenklade brusmodellen underlättar många beräkningar. Dock studeras sällan de effekter förenklingarna leder till. Denna avhandling visar att om inga förenklingar görs kan prestandan förbättras och det visas också hur förbättringen kan relateras till den intressanta informationen i det involverade bruset. Den intressanta informationen är den inneboende noggrannheten (eng. intrinsic accuracy) och ett sätt för att bestämma den inneboende noggrannheten hos en given fördelning med hjälp av Monte-Carlo-metoder presenteras.</p><p>Ett mått på hur bra en estimator utan bias kan göras ges av Cramér-Raos undre gräns (CRLB). Samtidigt är det känt att kalmanfiltret är den bästa lineära biasfria estimatorn (BLUE) för lineära system. Det visas här att CRLB och BLUE-prestanda ges av samma matematiska uttryck där den inneboende noggrannheten ingår som en parameter. Kunskap om hur informationen påverkar prestandan kan sedan användas för att indikera när ett olineärt filter, t.ex. ett partikelfilter, bör användas istället för ett kalmanfilter. Med hjälp av simuleringar visas att CRLB är ett användbart mått för att indikera när mer avancerade metoder kan vara lönsamma. Simuleringarna visar dock också att CRLB-analysen bör kompletteras med andra tekniker för att det ska vara möjligt att dra definitiva slutsatser.</p><p>I fallet feldetektion ger de asymptotiska egenskaperna hos den generaliserade sannolikhetskvoten (eng. generalized likelihood ratio, GLR) en övre gräns för hur bra detektorer som kan konstrueras. Det visas här hur den övre gränsen beror på den inneboende noggrannheten hos det aktuella bruset. Genom att beräkna asymptotisk GLR-testprestanda för det sanna bruset och för en gaussisk brusapproximation går det att dra slutsatser om huruvida den gaussiska approximationen är tillräckligt bra för att kunna användas. I simuleringar visas att det är lönsamt att använda sig av en exakt brusbeskrivning om skillnaden i prestanda är stor mellan de båda fallen. Simuleringarna indikerar också att det kan vara svårt att förutsäga den exakta effekten av en gaussisk brusapproximation.</p> / Report code: LiU-Tek-Lic-2005:54

No description available.

Many methods used for estimation and detection consider only the mean and variance of the involved noise instead of the full noise descriptions. One reason for this is that the mathematics is often considerably simplified this way. However, the implications of the simplifications are seldom studied, and this thesis shows that if no approximations are made performance is gained. Furthermore, the gain is quantified in terms of the useful information in the noise distributions involved. The useful information is given by the intrinsic accuracy, and a method to compute the intrinsic accuracy for a given distribution, using Monte Carlo methods, is outlined. A lower bound for the covariance of the estimation error for any unbiased estimator s given by the Cramér-Rao lower bound (CRLB). At the same time, the Kalman filter is the best linear unbiased estimator (BLUE) for linear systems. It is in this thesis shown that the CRLB and the BLUE performance are given by the same expression, which is parameterized in the intrinsic accuracy of the noise. How the performance depends on the noise is then used to indicate when nonlinear filters, e.g., a particle filter, should be used instead of a Kalman filter. The CRLB results are shown, in simulations, to be a useful indication of when to use more powerful estimation methods. The simulations also show that other techniques should be used as a complement to the CRLB analysis to get conclusive performance results. For fault detection, the statistics of the asymptotic generalized likelihood ratio (GLR) test provides an upper bound on the obtainable detection performance. The performance is in this thesis shown to depend on the intrinsic accuracy of the involved noise. The asymptotic GLR performance can then be calculated for a test using the actual noise and for a test using the approximative Gaussian noise. Based on the difference in performance, it is possible to draw conclusions about the quality of the Gaussian approximation. Simulations show that when the difference in performance is large, an exact noise representation improves the detection. Simulations also show that it is difficult to predict the exact influence on the detection performance caused by substituting the system noise with Gaussian noise approximations. / Många metoder som används i estimerings- och detekteringssammanhang tar endast hänsyn till medelvärde och varians hos ingående brus istället för att använda en fullständig brusbeskrivning. En av anledningarna till detta är att den förenklade brusmodellen underlättar många beräkningar. Dock studeras sällan de effekter förenklingarna leder till. Denna avhandling visar att om inga förenklingar görs kan prestandan förbättras och det visas också hur förbättringen kan relateras till den intressanta informationen i det involverade bruset. Den intressanta informationen är den inneboende noggrannheten (eng. intrinsic accuracy) och ett sätt för att bestämma den inneboende noggrannheten hos en given fördelning med hjälp av Monte-Carlo-metoder presenteras. Ett mått på hur bra en estimator utan bias kan göras ges av Cramér-Raos undre gräns (CRLB). Samtidigt är det känt att kalmanfiltret är den bästa lineära biasfria estimatorn (BLUE) för lineära system. Det visas här att CRLB och BLUE-prestanda ges av samma matematiska uttryck där den inneboende noggrannheten ingår som en parameter. Kunskap om hur informationen påverkar prestandan kan sedan användas för att indikera när ett olineärt filter, t.ex. ett partikelfilter, bör användas istället för ett kalmanfilter. Med hjälp av simuleringar visas att CRLB är ett användbart mått för att indikera när mer avancerade metoder kan vara lönsamma. Simuleringarna visar dock också att CRLB-analysen bör kompletteras med andra tekniker för att det ska vara möjligt att dra definitiva slutsatser. I fallet feldetektion ger de asymptotiska egenskaperna hos den generaliserade sannolikhetskvoten (eng. generalized likelihood ratio, GLR) en övre gräns för hur bra detektorer som kan konstrueras. Det visas här hur den övre gränsen beror på den inneboende noggrannheten hos det aktuella bruset. Genom att beräkna asymptotisk GLR-testprestanda för det sanna bruset och för en gaussisk brusapproximation går det att dra slutsatser om huruvida den gaussiska approximationen är tillräckligt bra för att kunna användas. I simuleringar visas att det är lönsamt att använda sig av en exakt brusbeskrivning om skillnaden i prestanda är stor mellan de båda fallen. Simuleringarna indikerar också att det kan vara svårt att förutsäga den exakta effekten av en gaussisk brusapproximation. / <p>Report code: LiU-Tek-Lic-2005:54</p>

This study examines three applications of control charts used for monitoring syndromic data with different characteristics. The first part develops a seasonal autoregressive integrated moving average (SARIMA) based surveillance chart, and compares it with the CDC Early Aberration Reporting System (EARS) W2c method using both authentic and simulated data. After successfully removing the long-term trend and the seasonality involved in syndromic data, the performance of the SARIMA approach is shown to be better than the performance of the EARS method in terms of two key surveillance characteristics, the false alarm rate and the average time to detect the outbreaks. In the second part, we propose a generalized likelihood ratio (GLR) control chart to detect a wide range of shifts in the mean of Poisson distributed biosurveillance data. The application of a sign function on the original GLR chart statistics leads to downward-sided, upward-sided, and two-sided GLR chart statistics in an unified framework. To facilitate the use of such charts in practice, we provide detailed guidance on developing and implementing the GLR chart. Under the steady-state framework, this study indicates that the overall GLR chart performance in detecting a range of shifts of interest is superior to the performance of traditional control charts including the EARS method, Shewhart charts, EWMA charts, and CUSUM charts. There is often an excessive number of zeros involved in health care related data. Zero-inflated Poisson (ZIP) models are more appropriate than Poisson models to describe such data. The last part of the dissertation considers the GLR chart for ZIP data under a research framework similar to the second part. Because small sample sizes may influence the estimation of ZIP parameters, the efficiency of MLEs is investigated in depth, followed by suggestions for improvement. Numerical approaches to solving for the MLEs are discussed as well. Statistics for a set of GLR charts are derived, followed by modifications changing them from two-sided statistics to one-sided statistics. Although not a complete study of GLR charts for ZIP processes, due to limited time and resources, suggestions for future work are proposed at the end of this dissertation. / Ph. D.

Software engineers need to understand the structure of the programs they construct. This task is made difficult by the intangible nature of software, and its complexity, size and changeability. Static analysis tools can help by extracting information from source code and conveying it to software engineers. However, the information provided by typical tools is limited, and some potentially rich veins of information - particularly metrics and visualisations - are under-utilised because developers cannot easily acquire or make use of the data. This thesis documents new tools and techniques for static analysis of software. It addresses the problem of generating parsers directly from standard grammars, thus avoiding the com-mon practice of customising grammars to comply with the limitations of a given parsing al-gorithm, typically LALR(1). This is achieved by a new parser generator that applies a range of bottom-up parsing algorithms to produce a hybrid parsing automaton. Consequently, we can generate more powerful deterministic parsers - up to and including LR(k) - without incurring the combinatorial explosion that makes canonical LR(k) parsers impractical. The range of practical parsers is further extended to include GLR, which was originally developed for natural language parsing but is shown here to also have advantages for static analysis of programming languages. This emphasis on conformance to standard grammars im-proves the rigour of static analysis tools and allows clearer definition and communication of derived information, such as metrics. Beneath the syntactic structure of software (exposed by parsing) lies the deeper semantic structure of declarations, scopes, classes, methods, inheritance, invocations, and so on. In this work, we present a new tool that performs semantic analysis on parse trees to produce a comprehensive semantic model suitable for processing by other static analysis tools. An XML pipeline approach is used to expose the syntactic and semantic models of the software and to derive metrics and visualisations. The approach is demonstrated producing several types of metrics and visualisations for real software, and the value of static analysis for informing software engineering decisions is shown.

In this thesis two different problems in distributed sensor networks are considered. Part I involves optimal quantiser design for decentralised estimation of a two-state hidden Markov model with dual sensors. The notion of optimality for quantiser design is based on minimising the probability of error in estimating the hidden Markov state. Equations for the filter error are derived for the continuous (unquantised) sensor outputs (signals), which are used to benchmark the performance of the quantisers. Minimising the probability of filter error to obtain the quantiser breakpoints is a difficult problem therefore an alternative method is employed. The quantiser breakpoints are obtained by maximising the mutual information between the quantised signals and the hidden Markov state. This method is known to work well for the single sensor case. Cases with independent and correlated noise across the signals are considered. The method is then applied to Markov processes with Gaussian signal noise, and further investigated through simulation studies. Simulations involving both independent and correlated noise across the sensors are performed and a number of interesting new theoretical results are obtained, particularly in the case of correlated noise. In Part II, the focus shifts to the detection of faults in helicopter transmission systems. The aim of the investigation is to determine whether the acoustic signature can be used for fault detection and diagnosis. To investigate this, statistical change detection algorithms are applied to acoustic vibration data obtained from the main rotor gearbox of a Bell 206 helicopter, which is run at high load under test conditions.

Cette thèse consiste à proposer une méthode de caractérisation non-supervisée des intervenants dans les documents audiovisuels, en exploitant des données liées à leur apparence physique et à leur voix. De manière générale, les méthodes d'identification automatique, que ce soit en vidéo ou en audio, nécessitent une quantité importante de connaissances a priori sur le contenu. Dans ce travail, le but est d'étudier les deux modes de façon corrélée et d'exploiter leur propriété respective de manière collaborative et robuste, afin de produire un résultat fiable aussi indépendant que possible de toute connaissance a priori. Plus particulièrement, nous avons étudié les caractéristiques du flux audio et nous avons proposé plusieurs méthodes pour la segmentation et le regroupement en locuteurs que nous avons évaluées dans le cadre d'une campagne d'évaluation. Ensuite, nous avons mené une étude approfondie sur les descripteurs visuels (visage, costume) qui nous ont servis à proposer de nouvelles approches pour la détection, le suivi et le regroupement des personnes. Enfin, le travail s'est focalisé sur la fusion des données audio et vidéo en proposant une approche basée sur le calcul d'une matrice de cooccurrence qui nous a permis d'établir une association entre l'index audio et l'index vidéo et d'effectuer leur correction. Nous pouvons ainsi produire un modèle audiovisuel dynamique des intervenants.

In this thesis two different problems in distributed sensor networks are considered. Part I involves optimal quantiser design for decentralised estimation of a two-state hidden Markov model with dual sensors. The notion of optimality for quantiser design is based on minimising the probability of error in estimating the hidden Markov state. Equations for the filter error are derived for the continuous (unquantised) sensor outputs (signals), which are used to benchmark the performance of the quantisers. Minimising the probability of filter error to obtain the quantiser breakpoints is a difficult problem therefore an alternative method is employed. The quantiser breakpoints are obtained by maximising the mutual information between the quantised signals and the hidden Markov state. This method is known to work well for the single sensor case. Cases with independent and correlated noise across the signals are considered. The method is then applied to Markov processes with Gaussian signal noise, and further investigated through simulation studies. Simulations involving both independent and correlated noise across the sensors are performed and a number of interesting new theoretical results are obtained, particularly in the case of correlated noise. In Part II, the focus shifts to the detection of faults in helicopter transmission systems. The aim of the investigation is to determine whether the acoustic signature can be used for fault detection and diagnosis. To investigate this, statistical change detection algorithms are applied to acoustic vibration data obtained from the main rotor gearbox of a Bell 206 helicopter, which is run at high load under test conditions.

This thesis investigates the European Union (EU) effect on the economic activity across the Green Line in the divided Cyprus between 2004 and 2016. The primary focus is on the development and implementation of the EU's Green Line Regulation (GLR), which regulates and enables such activity from three aspects: movement of goods, services, and persons. In tracing the EU effect, this thesis provides a critical appraisal of the GLR on whether it provides an adequate legal framework for the economic activity in those three aspects and the extent to which it has contributed to the development of economic cooperation between the Turkish Cypriot and Greek Cypriot communities across the divide. The analysis also pays an equal level of attention to the extent to which the EU effect has been mediated by the factors at the domestic level: the roles of legal framework, ethno-politics in political elites, ethno-politics in civil society, and governance. The investigation of this study is pegged in two academic literatures. The first one is the Europeanisation debate, which concerns with the EU effect in the domestic affairs of countries associated with the EU. This thesis borrows three mechanisms of Europeanisation from this debate in order to test the EU effect on the three aspects of economic activity across the divide in Cyprus: i) institutional compliance, ii) change of domestic opportunity structures, iii) cognitive change. The second academic literature is the liberal peace, which it proposes that greater economic interactions and development of economic interdependence between countries facilitate resolution of their conflicts. The insights from this debate is utilised for conceptualising the EU's GLR as a liberal peace project. While Europeanisation is portrayed as a 'process', liberal peace objectives are seen as the 'ultimate destination', which the 'vehicle' of the EU's GLR will drive the island towards it. This thesis argues that the GLR has only achieved a limited success and largely failed to contribute to the development of economic cooperation across the divide in Cyprus. This is mainly because the Europeanisation process have been heavily mediated and negated by the design shortcomings of the GLR as well as the factors at the domestic level, which are inherently linked to the politics of division. In this context, this thesis aspires to make contribution in both empirical and conceptual terms. The in-depth and critical investigation of the GLR as well as of the economic activity across the divide in Cyprus provides a much-needed contribution to the contemporary politics of Cyprus, which has been largely ignored by the existing academic literature. Additionally, the conceptual framework developed in this thesis allows exploring synergies between the theoretical literatures of Europeanisation and liberal peace and combines them with examination of new empirical evidence. This focus captures insights on how Europeanisation can be used as a 'tool' for pursuing liberal peace objectives in contested statehood, beyond what has been researched so far and also provides a blueprint for other similar cases of conflict.

<p>Plant height is an important agronomic trait and a major target for crop improvement. Owing to the ease of detection and measurement of plant stature, as well as its high heritability, several height-related mutants have been reported in maize. The genes underlying a few of those mutants have also been identified, with a majority of them related to the biosynthesis or signaling of two key phytohormones - gibberellins (GAs) and brassinosteroids (BRs). However, most other maize dwarfing mutants, and especially those that result from gain-of-function mutations, remain uncharacterized. The present study was undertaken to characterize a novel dominant dwarfing mutant, named <i>D13</i>. This mutant appeared in the M1 population of the inbred B73 that was generated by mutagenesis with ethyl methanesulfonate (EMS). Like most other maize dwarfing mutants, the reduction in <i>D13</i> height was largely due to the compression of the internodes. However, unlike the GA or BR mutants, <i>D13</i> had no defects in the female or male inflorescences. Further, in contrast to the GA and BR mutants, the mesocotyl elongation during etiolation was not impacted in <i>D13</i>. <i>D13</i> seedlings developed red coloration in two to three lowermost leaves. In addition, <i>D13</i> also showed enhanced tillering when the phenotype was very severe. The size of the shoot apical meristem of <i>D13</i> was reduced slightly, and significant aberrations in the structure of vascular bundles in the mutant were observed. All anatomical and phenotypic features of <i>D13</i> were highly exaggerated in homozygous state, indicating the partially dominant nature of the <i>D13</i> mutation. Interestingly, the heterozygous mutants showed remarkable variation in their phenotype, which was maintained across generations. Moreover, the <i>D13</i> phenotype was found to be sensitive to the genetic background, being completely suppressed in Mo17, Oh7B, enhanced in CML322, P39 and changed to different degrees in others. To identify the genetic defect responsible for the <i>D13</i> mutant phenotype, a map-based cloning approach was used, which identified a single base-pair change from G to A (G2976A) in the coding region of a glutamate receptor gene (Zm00001d015007). The G2976A missense mutation resulted in the replacement of alanine with threonine at the location 670. The replaced alanine is highly conserved in glutamate receptors across all domains of life from cyanobacteria to plants to mammals, suggesting a causal relationship between the G2976A substitution and the <i>D13</i> phenotype. To validate this relationship, a targeted EMS-based mutagenesis approach was used to knock-out (inactivate) the <i>D13</i> mutant allele. A suppressor mutant was found in which the <i>D13</i> mutant phenotype reverted to the normal tall phenotype. The sequence of the revertant allele, designated <i>D13</i>*, revealed that the original <i>D13</i> mutant allele underwent a second G to A mutation (G1520A) to change glycine into aspartic acid at position 473. This intragenic second-site mutation in the <i>D13</i> allele suppressed the function of the <i>D13</i> allele, thereby preventing it from interfering with the function of the wild type allele. To further unveil the genes and underlying mechanisms that enable the <i>D13</i> mutant to confer a dwarf phenotype, transcriptomic and metabolomic analyses of <i>D13</i> mutants were conducted and compared to the wild type sibs. While the omics analysis confirmed that stress responses were upregulated and genes related to shoot system development were downregulated in the mutant, the data did not allow us to pinpoint the underlying mechanisms that connect the <i>D13</i> mutation with its dwarfing phenotype. Furthermore, it remains unclear whether these stress and shoot system-related changes result in the manifestation of <i>D13</i> phenotype, or the dwarf phenotype due to <i>D13</i> mutation activates the stress-related mechanisms. This is the first study that signifies the importance of a glutamate receptor gene in controlling plant height.</p>