Adaptive Markov chain Monte Carlo and Bayesian filtering for state space models

This thesis is concerned with the state and parameter estimation in state space models. The estimation of states and parameters is an important task when mathematical modeling is applied to many different application areas such as the global positioning systems, target tracking, navigation, brain imaging, spread of infectious diseases, biological processes, telecommunications, audio signal processing, stochastic optimal control, machine learning, and physical systems. In Bayesian settings, the estimation of states or parameters amounts to computation of the posterior probability density function. Except for a very restricted number of models, it is impossible to compute this density function in a closed form. Hence, we need approximation methods. A state estimation problem involves estimating the states (latent variables) that are not directly observed in the output of the system. In this thesis, we use the Kalman filter, extended Kalman filter, Gauss–Hermite filters, and particle filters to estimate the states based on available measurements. Among these filters, particle filters are numerical methods for approximating the filtering distributions of non-linear non-Gaussian state space models via Monte Carlo. The performance of a particle filter heavily depends on the chosen importance distribution. For instance, inappropriate choice of the importance distribution can lead to the failure of convergence of the particle filter algorithm. In this thesis, we analyze the theoretical Lᵖ particle filter convergence with general importance distributions, where p ≥2 is an integer. A parameter estimation problem is considered with inferring the model parameters from measurements. For high-dimensional complex models, estimation of parameters can be done by Markov chain Monte Carlo (MCMC) methods. In its operation, the MCMC method requires the unnormalized posterior distribution of the parameters and a proposal distribution. In this thesis, we show how the posterior density function of the parameters of a state space model can be computed by filtering based methods, where the states are integrated out. This type of computation is then applied to estimate parameters of stochastic differential equations. Furthermore, we compute the partial derivatives of the log-posterior density function and use the hybrid Monte Carlo and scaled conjugate gradient methods to infer the parameters of stochastic differential equations. The computational efficiency of MCMC methods is highly depend on the chosen proposal distribution. A commonly used proposal distribution is Gaussian. In this kind of proposal, the covariance matrix must be well tuned. To tune it, adaptive MCMC methods can be used. In this thesis, we propose a new way of updating the covariance matrix using the variational Bayesian adaptive Kalman filter algorithm.

The oral motor capacity and feeding performance of preterm newborns at the time of transition to oral feeding

The objective of the present study was to determine the oral motor capacity and the feeding performance of preterm newborn infants when they were permitted to start oral feeding. This was an observational and prospective study conducted on 43 preterm newborns admitted to the Neonatal Intensive Care Unit of UFSM, RS, Brazil. Exclusion criteria were the presence of head and neck malformations, genetic disease, neonatal asphyxia, intracranial hemorrhage, and kernicterus. When the infants were permitted to start oral feeding, non-nutritive sucking was evaluated by a speech therapist regarding force (strong vs weak), rhythm (rapid vs slow), presence of adaptive oral reflexes (searching, sucking and swallowing) and coordination between sucking, swallowing and respiration. Feeding performance was evaluated on the basis of competence (defined by rate of milk intake, mL/min) and overall transfer (percent ingested volume/total volume ordered). The speech therapist's evaluation showed that 33% of the newborns presented weak sucking, 23% slow rhythm, 30% absence of at least one adaptive oral reflex, and 14% with no coordination between sucking, swallowing and respiration. Mean feeding competence was greater in infants with strong sucking fast rhythm. The presence of sucking-swallowing-respiration coordination decreased the days for an overall transfer of 100%. Evaluation by a speech therapist proved to be a useful tool for the safe indication of the beginning of oral feeding for premature infants.

L’amélioration de la performance et de la structure cardiaque par la moxonidine chez les SHR est accompagnée d’une diminution des cytokines, de la MAPK p38 et de l’Akt

L’hypertrophie du ventricule gauche (HVG) est un processus adaptif et compensatoire qui se développe conséquemment à l’hypertension artérielle pour s’opposer à l’élévation chronique de la pression artérielle. L’HVG est caractérisée par une hypertrophie des cardiomyocytes suite à l’augmentation de la synthèse d’ADN, une prolifération des fibroblastes, une augmentation du dépôt de collagène et une altération de la matrice extracellulaire (MEC). Ces changements génèrent des troubles de relaxation et mènent au dysfonctionnement diastolique, ce qui diminue la performance cardiaque. La suractivité du système nerveux sympathique (SNS) joue un rôle essentiel dans le développement de l’hypertension artérielle et de l’HVG à cause de la libération excessive des catécholamines et de leurs effets sur la sécrétion des cytokines pro-inflammatoires et sur les différentes voies de signalisation hypertrophiques et prolifératives. Le traitement antihypertenseur avec de la moxonidine, un composé sympatholytique d’action centrale, permet une régression de l’HVG suite à une réduction soutenue de la synthèse d'ADN et d’une stimulation transitoire de la fragmentation de l'ADN qui se produit au début du traitement. En raison de l’interaction entre l’HVG, les cytokines inflammatoires, le SNS et leurs effets sur les protéines de signalisation hypertrophiques, l’objectif de cette étude est de détecter dans un modèle animal d’hypertension artérielle et d’HVG, les différentes voies de signalisation associées à la régression de l’HVG et à la performance cardiaque. Des rats spontanément hypertendus (SHR, 12 semaines) ont reçu de la moxonidine à 0, 100 et 400 µg/kg/h, pour une période de 1 et 4 semaines, via des mini-pompes osmotiques implantées d’une façon sous-cutanée. Après 4 semaines de traitement, la performance cardiaque a été mesurée par écho-doppler. Les rats ont ensuite été euthanasiés, le sang a été recueilli pour mesurer les concentrations des cytokines plasmatiques et les cœurs ont été prélevés pour la détermination histologique du dépôt de collagène et de l'expression des protéines de signalisation dans le ventricule gauche. Le traitement de 4 semaines n’a eu aucun effet sur les paramètres systoliques mais a permis d’améliorer les paramètres diastoliques ainsi que la performance cardiaque globale. Par rapport au véhicule, la moxonidine (400 µg/kg/h) a permis d’augmenter transitoirement la concentration plasmatique de l’IL-1β après une semaine et de réduire la masse ventriculaire gauche. De même, on a observé une diminution du dépôt de collagène et des concentrations plasmatiques des cytokines IL-6 et TNF-α, ainsi qu’une diminution de la phosphorylation de p38 et d’Akt dans le ventricule gauche après 1 et 4 semaines de traitement, et cela avec une réduction de la pression artérielle et de la fréquence cardiaque. Fait intéressant, les effets anti-hypertrophiques, anti-fibrotiques et anti-inflammatoires de la moxonidine ont pu être observés avec la dose sous-hypotensive (100 µg/kg/h). Ces résultats suggèrent des effets cardiovasculaires bénéfiques de la moxonidine associés à une amélioration de la performance cardiaque, une régulation de l'inflammation en diminuant les niveaux plasmatiques des cytokines pro-inflammatoires ainsi qu’en inhibant la MAPK p38 et Akt, et nous permettent de suggérer que, outre l'inhibition du SNS, moxonidine peut agir sur des sites périphériques.

Étude de la performance d’un algorithme Metropolis-Hastings avec ajustement directionnel

Les méthodes de Monte Carlo par chaîne de Markov (MCMC) sont des outils très populaires pour l’échantillonnage de lois de probabilité complexes et/ou en grandes dimensions. Étant donné leur facilité d’application, ces méthodes sont largement répandues dans plusieurs communautés scientifiques et bien certainement en statistique, particulièrement en analyse bayésienne. Depuis l’apparition de la première méthode MCMC en 1953, le nombre de ces algorithmes a considérablement augmenté et ce sujet continue d’être une aire de recherche active. Un nouvel algorithme MCMC avec ajustement directionnel a été récemment développé par Bédard et al. (IJSS, 9 :2008) et certaines de ses propriétés restent partiellement méconnues. L’objectif de ce mémoire est de tenter d’établir l’impact d’un paramètre clé de cette méthode sur la performance globale de l’approche. Un second objectif est de comparer cet algorithme à d’autres méthodes MCMC plus versatiles afin de juger de sa performance de façon relative.

Speech sample estimation from composite zerocrossings and encoding via adaptive switching of transforms

This thesis investigates the potential use of zerocrossing information for speech sample estimation. It provides 21 new method tn) estimate speech samples using composite zerocrossings. A simple linear interpolation technique is developed for this purpose. By using this method the A/D converter can be avoided in a speech coder. The newly proposed zerocrossing sampling theory is supported with results of computer simulations using real speech data. The thesis also presents two methods for voiced/ unvoiced classification. One of these methods is based on a distance measure which is a function of short time zerocrossing rate and short time energy of the signal. The other one is based on the attractor dimension and entropy of the signal. Among these two methods the first one is simple and reguires only very few computations compared to the other. This method is used imtea later chapter to design an enhanced Adaptive Transform Coder. The later part of the thesis addresses a few problems in Adaptive Transform Coding and presents an improved ATC. Transform coefficient with maximum amplitude is considered as ‘side information’. This. enables more accurate tfiiz assignment enui step—size computation. A new bit reassignment scheme is also introduced in this work. Finally, sum ATC which applies switching between luiscrete Cosine Transform and Discrete Walsh-Hadamard Transform for voiced and unvoiced speech segments respectively is presented. Simulation results are provided to show the improved performance of the coder

Modified Block Adaptive Predictive Coder For Speech Processing

This thesis investigated the potential use of Linear Predictive Coding in speech communication applications. A Modified Block Adaptive Predictive Coder is developed, which reduces the computational burden and complexity without sacrificing the speech quality, as compared to the conventional adaptive predictive coding (APC) system. For this, changes in the evaluation methods have been evolved. This method is as different from the usual APC system in that the difference between the true and the predicted value is not transmitted. This allows the replacement of the high order predictor in the transmitter section of a predictive coding system, by a simple delay unit, which makes the transmitter quite simple. Also, the block length used in the processing of the speech signal is adjusted relative to the pitch period of the signal being processed rather than choosing a constant length as hitherto done by other researchers. The efficiency of the newly proposed coder has been supported with results of computer simulation using real speech data. Three methods for voiced/unvoiced/silent/transition classification have been presented. The first one is based on energy, zerocrossing rate and the periodicity of the waveform. The second method uses normalised correlation coefficient as the main parameter, while the third method utilizes a pitch-dependent correlation factor. The third algorithm which gives the minimum error probability has been chosen in a later chapter to design the modified coder The thesis also presents a comparazive study beh-cm the autocorrelation and the covariance methods used in the evaluaiicn of the predictor parameters. It has been proved that the azztocorrelation method is superior to the covariance method with respect to the filter stabf-it)‘ and also in an SNR sense, though the increase in gain is only small. The Modified Block Adaptive Coder applies a switching from pitch precitzion to spectrum prediction when the speech segment changes from a voiced or transition region to an unvoiced region. The experiments cont;-:ted in coding, transmission and simulation, used speech samples from .\£=_‘ajr2_1a:r1 and English phrases. Proposal for a speaker reecgnifion syste: and a phoneme identification system has also been outlized towards the end of the thesis.

Adaptive Real-time Anomaly-based Intrusion Detection using Data Mining and Machine Learning Techniques

Die zunehmende Vernetzung der Informations- und Kommunikationssysteme führt zu einer weiteren Erhöhung der Komplexität und damit auch zu einer weiteren Zunahme von Sicherheitslücken. Klassische Schutzmechanismen wie Firewall-Systeme und Anti-Malware-Lösungen bieten schon lange keinen Schutz mehr vor Eindringversuchen in IT-Infrastrukturen. Als ein sehr wirkungsvolles Instrument zum Schutz gegenüber Cyber-Attacken haben sich hierbei die Intrusion Detection Systeme (IDS) etabliert. Solche Systeme sammeln und analysieren Informationen von Netzwerkkomponenten und Rechnern, um ungewöhnliches Verhalten und Sicherheitsverletzungen automatisiert festzustellen. Während signatur-basierte Ansätze nur bereits bekannte Angriffsmuster detektieren können, sind anomalie-basierte IDS auch in der Lage, neue bisher unbekannte Angriffe (Zero-Day-Attacks) frühzeitig zu erkennen. Das Kernproblem von Intrusion Detection Systeme besteht jedoch in der optimalen Verarbeitung der gewaltigen Netzdaten und der Entwicklung eines in Echtzeit arbeitenden adaptiven Erkennungsmodells. Um diese Herausforderungen lösen zu können, stellt diese Dissertation ein Framework bereit, das aus zwei Hauptteilen besteht. Der erste Teil, OptiFilter genannt, verwendet ein dynamisches "Queuing Concept", um die zahlreich anfallenden Netzdaten weiter zu verarbeiten, baut fortlaufend Netzverbindungen auf, und exportiert strukturierte Input-Daten für das IDS. Den zweiten Teil stellt ein adaptiver Klassifikator dar, der ein Klassifikator-Modell basierend auf "Enhanced Growing Hierarchical Self Organizing Map" (EGHSOM), ein Modell für Netzwerk Normalzustand (NNB) und ein "Update Model" umfasst. In dem OptiFilter werden Tcpdump und SNMP traps benutzt, um die Netzwerkpakete und Hostereignisse fortlaufend zu aggregieren. Diese aggregierten Netzwerkpackete und Hostereignisse werden weiter analysiert und in Verbindungsvektoren umgewandelt. Zur Verbesserung der Erkennungsrate des adaptiven Klassifikators wird das künstliche neuronale Netz GHSOM intensiv untersucht und wesentlich weiterentwickelt. In dieser Dissertation werden unterschiedliche Ansätze vorgeschlagen und diskutiert. So wird eine classification-confidence margin threshold definiert, um die unbekannten bösartigen Verbindungen aufzudecken, die Stabilität der Wachstumstopologie durch neuartige Ansätze für die Initialisierung der Gewichtvektoren und durch die Stärkung der Winner Neuronen erhöht, und ein selbst-adaptives Verfahren eingeführt, um das Modell ständig aktualisieren zu können. Darüber hinaus besteht die Hauptaufgabe des NNB-Modells in der weiteren Untersuchung der erkannten unbekannten Verbindungen von der EGHSOM und der Überprüfung, ob sie normal sind. Jedoch, ändern sich die Netzverkehrsdaten wegen des Concept drif Phänomens ständig, was in Echtzeit zur Erzeugung nicht stationärer Netzdaten führt. Dieses Phänomen wird von dem Update-Modell besser kontrolliert. Das EGHSOM-Modell kann die neuen Anomalien effektiv erkennen und das NNB-Model passt die Änderungen in Netzdaten optimal an. Bei den experimentellen Untersuchungen hat das Framework erfolgversprechende Ergebnisse gezeigt. Im ersten Experiment wurde das Framework in Offline-Betriebsmodus evaluiert. Der OptiFilter wurde mit offline-, synthetischen- und realistischen Daten ausgewertet. Der adaptive Klassifikator wurde mit dem 10-Fold Cross Validation Verfahren evaluiert, um dessen Genauigkeit abzuschätzen. Im zweiten Experiment wurde das Framework auf einer 1 bis 10 GB Netzwerkstrecke installiert und im Online-Betriebsmodus in Echtzeit ausgewertet. Der OptiFilter hat erfolgreich die gewaltige Menge von Netzdaten in die strukturierten Verbindungsvektoren umgewandelt und der adaptive Klassifikator hat sie präzise klassifiziert. Die Vergleichsstudie zwischen dem entwickelten Framework und anderen bekannten IDS-Ansätzen zeigt, dass der vorgeschlagene IDSFramework alle anderen Ansätze übertrifft. Dies lässt sich auf folgende Kernpunkte zurückführen: Bearbeitung der gesammelten Netzdaten, Erreichung der besten Performanz (wie die Gesamtgenauigkeit), Detektieren unbekannter Verbindungen und Entwicklung des in Echtzeit arbeitenden Erkennungsmodells von Eindringversuchen.

Identifying adaptive genetic divergence among populations from genome scans

The identification of signatures of natural selection in genomic surveys has become an area of intense research, stimulated by the increasing ease with which genetic markers can be typed. Loci identified as subject to selection may be functionally important, and hence (weak) candidates for involvement in disease causation. They can also be useful in determining the adaptive differentiation of populations, and exploring hypotheses about speciation. Adaptive differentiation has traditionally been identified from differences in allele frequencies among different populations, summarised by an estimate of F-ST. Low outliers relative to an appropriate neutral population-genetics model indicate loci subject to balancing selection, whereas high outliers suggest adaptive (directional) selection. However, the problem of identifying statistically significant departures from neutrality is complicated by confounding effects on the distribution of F-ST estimates, and current methods have not yet been tested in large-scale simulation experiments. Here, we simulate data from a structured population at many unlinked, diallelic loci that are predominantly neutral but with some loci subject to adaptive or balancing selection. We develop a hierarchical-Bayesian method, implemented via Markov chain Monte Carlo (MCMC), and assess its performance in distinguishing the loci simulated under selection from the neutral loci. We also compare this performance with that of a frequentist method, based on moment-based estimates of F-ST. We find that both methods can identify loci subject to adaptive selection when the selection coefficient is at least five times the migration rate. Neither method could reliably distinguish loci under balancing selection in our simulations, even when the selection coefficient is twenty times the migration rate.

Adaptive control of event integration

Identifying 2 target stimuli in a rapid stream of visual symbols is much easier if the 2nd target appears immediately after the 1st target (i.e., at Lag 1) than if distractor stimuli intervene. As this phenomenon comes with a strong tendency to confuse the order of the targets, it seems to be due to the integration of both targets into the same attentional episode or object file. The authors investigated the degree to which people can control the temporal extension of their (episodic) integration windows by manipulating the expectations participants had with regard to the time available for target processing. As predicted, expecting more time to process increased the number of order confusions at Lag 1. This was true for between-subjects and within-subjects (trial-to-trial) manipulations, suggesting that integration windows can be adapted actively and rather quickly.

Simplified parameter adaptive control

A simple parameter adaptive controller design methodology is introduced in which steady-state servo tracking properties provide the major control objective. This is achieved without cancellation of process zeros and hence the underlying design can be applied to non-minimum phase systems. As with other self-tuning algorithms, the design (user specified) polynomials of the proposed algorithm define the performance capabilities of the resulting controller. However, with the appropriate definition of these polynomials, the synthesis technique can be shown to admit different adaptive control strategies, e.g. self-tuning PID and self-tuning pole-placement controllers. The algorithm can therefore be thought of as an embodiment of other self-tuning design techniques. The performances of some of the resulting controllers are illustrated using simulation examples and the on-line application to an experimental apparatus.

Self-organising neural networks for adaptive control

Self-organizing neural networks have been implemented in a wide range of application areas such as speech processing, image processing, optimization and robotics. Recent variations to the basic model proposed by the authors enable it to order state space using a subset of the input vector and to apply a local adaptation procedure that does not rely on a predefined test duration limit. Both these variations have been incorporated into a new feature map architecture that forms an integral part of an Hybrid Learning System (HLS) based on a genetic-based classifier system. Problems are represented within HLS as objects characterized by environmental features. Objects controlled by the system have preset targets set against a subset of their features. The system's objective is to achieve these targets by evolving a behavioural repertoire that efficiently explores and exploits the problem environment. Feature maps encode two types of knowledge within HLS — long-term memory traces of useful regularities within the environment and the classifier performance data calibrated against an object's feature states and targets. Self-organization of these networks constitutes non-genetic-based (experience-driven) learning within HLS. This paper presents a description of the HLS architecture and an analysis of the modified feature map implementing associative memory. Initial results are presented that demonstrate the behaviour of the system on a simple control task.

Blind adaptive channel estimation for dual-rate DS/CDMA signals

This letter proposes the subspace-based blind adaptive channel estimation algorithm for dual-rate quasi-synchronous DS/CDMA systems, which can operate at the low-rate (LR) or high-rate (HR) mode. Simulation results show that the proposed blind adaptive algorithm at the LR mode has a better performance than that at the HR mode, with the cost of an increasing computational complexity.

Subspace-based blind adaptive multiuser detection for multirate DS/CDMA signals

The existing dual-rate blind linear detectors, which operate at either the low-rate (LR) or the high-rate (HR) mode, are not strictly blind at the HR mode and lack theoretical analysis. This paper proposes the subspace-based LR and HR blind linear detectors, i.e., bad decorrelating detectors (BDD) and blind MMSE detectors (BMMSED), for synchronous DS/CDMA systems. To detect an LR data bit at the HR mode, an effective weighting strategy is proposed. The theoretical analyses on the performance of the proposed detectors are carried out. It has been proved that the bit-error-rate of the LR-BDD is superior to that of the HR-BDD and the near-far resistance of the LR blind linear detectors outperforms that of its HR counterparts. The extension to asynchronous systems is also described. Simulation results show that the adaptive dual-rate BMMSED outperform the corresponding non-blind dual-rate decorrelators proposed by Saquib, Yates and Mandayam (see Wireless Personal Communications, vol. 9, p.197-216, 1998).

A self-structured adaptive decision feedback equalizer

In a decision feedback equalizer (DFE), the structural parameters, including the decision delay, the feedforward filter (FFF), and feedback filter (FBF) lengths, must be carefully chosen, as they greatly influence the performance. Although the FBF length can be set as the channel memory, there is no closed-form expression for the FFF length and decision delay. In this letter, first we analytically show that the two-dimensional search for the optimum FFF length and decision delay can be simplified to a one-dimensional search and then describe a new adaptive DFE where the optimum structural parameters can be self-adapted.

Equalisation with adaptive time lag

In an adaptive equaliser, the time lag is an important parameter that significantly influences the performance. Only with the optimum time lag that corresponds to the best minimum-mean-square-error (MMSE) performance, can there be best use of the available resources. Many designs, however, choose the time lag either based on preassumption of the channel or simply based on average experience. The relation between the MMSE performance and the time lag is investigated using a new interpretation of the MMSE equaliser, and then a novel adaptive time lag algorithm is proposed based on gradient search. The proposed algorithm can converge to the optimum time lag in the mean and is verified by the numerical simulations provided.