Tesi sul tema "Filtre intervalle"
Cita una fonte nei formati APA, MLA, Chicago, Harvard e in molti altri stili
Vedi i top-33 saggi (tesi di laurea o di dottorato) per l'attività di ricerca sul tema "Filtre intervalle".
Accanto a ogni fonte nell'elenco di riferimenti c'è un pulsante "Aggiungi alla bibliografia". Premilo e genereremo automaticamente la citazione bibliografica dell'opera scelta nello stile citazionale di cui hai bisogno: APA, MLA, Harvard, Chicago, Vancouver ecc.
Puoi anche scaricare il testo completo della pubblicazione scientifica nel formato .pdf e leggere online l'abstract (il sommario) dell'opera se è presente nei metadati.
Vedi le tesi di molte aree scientifiche e compila una bibliografia corretta.
Mohammedi, Irryhl. "Contribution à l’estimation robuste par intervalle des systèmes multivariables LTI et LPV : Application aux systèmes aérospatiaux". Electronic Thesis or Diss., Bordeaux, 2024. http://www.theses.fr/2024BORD0142.
Testo completoThe work of this thesis aims at developing new approaches based on a new particular class of state estimators, the so-called interval or ensemble filters.Like the class of interval observers, the objective is to estimate, in a guaranteed way, the upper and lower bounds of the states of a system, at each time instant.The proposed approach is based on the theory of monotonic systems and on the knowledge of the domain of membership, supposedly bounded, of the uncertainties of the system, such as disturbances, noise and bias of sensors, etc.The key element of the proposed approach is to use a filter structure advantage, rather than an observer-based structure (relying only on a dynamic structure of the studied system).The synthesis of the filter parameters is based on the resolution of a constrained optimization problem of linear and bilinear matrix inequalities (LMI and BMI) allowing to guarantee simultaneously the existence conditions of the filter as well as a performance level, either in an energy context for LTI systems, or in an amplitude context or in a mixed energy/amplitude context for LPV systemsThe proposed synthesis methodology is illustrated on an academic example and is compared with other existing methods in the literature. Finally, the methodology is applied to the case of attitude and acceleration control of a satellite, under realistic simulation conditions
Tran, Tuan Anh. "Cadre unifié pour la modélisation des incertitudes statistiques et bornées : application à la détection et isolation de défauts dans les systèmes dynamiques incertains par estimation". Thesis, Toulouse 3, 2017. http://www.theses.fr/2017TOU30292/document.
Testo completoThis thesis deals with state estimation in discrete-time dynamic systems in the context of the integration of statistical and bounded error uncertainties. Motivated by the drawbacks of the interval Kalman filter (IKF) and its improvement (iIKF), we propose a filtering algorithm for linear systems subject to uncertain Gaussian noises, i.e. with the mean and covariance matrix defined by their membership to intervals. This new interval Kalman filter (UBIKF) relies on finding a punctual gain matrix minimizing an upper bound of the set of estimation error covariance matrices by respecting the bounds of the parametric uncertainties. An envelope containing all possible estimates is then determined using interval analysis. The UBIKF reduces not only the computational complexity of the set inversion of the matrices intervals appearing in the iIKF, but also the conservatism of the estimates. We then discuss different frameworks for representing incomplete or imprecise knowledge, including the cumulative distribution functions, the possibility theory and the theory of belief functions. Thanks to the last, a model in the form of a mass function for an uncertain multivariate Gaussian distribution is proposed. A box particle filter based on this theory is developed for non-linear dynamic systems in which the process noises are bounded and the measurement errors are represented by an uncertain Gaussian mass function. Finally, the UBIKF is applied to fault detection and isolation by implementing the generalized observer scheme and structural analysis. Through various examples, the capacity for detecting and isolating sensor/actuator faults of this tool is illustrated and compared to other approaches
Pepy, Romain. "Vers une planification robuste et sûre pour les systèmes autonomes". Phd thesis, Université Paris Sud - Paris XI, 2009. http://tel.archives-ouvertes.fr/tel-00845477.
Testo completoNicola, Jérémy. "Robust, precise and reliable simultaneous localization and mapping for and underwater robot. Comparison and combination of probabilistic and set-membership methods for the SLAM problem". Thesis, Brest, 2017. http://www.theses.fr/2017BRES0066/document.
Testo completoIn this thesis, we work on the problem of simultaneously localizing an underwater robot while mapping a set of acoustic beacons lying on the seafloor, using an acoustic range-meter and an inertial navigation system. We focus on the two main approaches classically used to solve this type of problem: Kalman filtering and set-membership filtering using interval analysis. The Kalman filter is optimal when the state equations of the robot are linear, and the noises are additive, white and Gaussian. The interval-based filter do not model uncertainties in a probabilistic framework, and makes only one assumption about their nature: they are bounded. Moreover, the interval-based approach allows to rigorously propagate the uncertainties, even when the equations are non-linear. This results in a high reliability in the set estimate, at the cost of a reduced precision.We show that in a subsea context, when the robot is equipped with a high precision inertial navigation system, a part of the SLAM equations can reasonably be seen as linear with additive Gaussian noise, making it the ideal playground of a Kalman filter. On the other hand, the equations related to the acoustic range-meter are much more problematic: the system is not observable, the equations are non-linear, and the outliers are frequent. These conditions are ideal for a set-based approach using interval analysis.By taking advantage of the properties of Gaussian noises, this thesis reconciles the probabilistic and set-membership processing of uncertainties for both linear and non-linear systems with additive Gaussian noises. By reasoning geometrically, we are able to express the part of the Kalman filter equations linked to the dynamics of the vehicle in a set-membership context. In the same way, a more rigorous and precise treatment of uncertainties is described for the part of the Kalman filter linked to the range-measurements. These two tools can then be combined to obtain a SLAM algorithm that is reliable, precise and robust. Some of the methods developed during this thesis are demonstrated on real data
Akhbari, Mahsa. "Analyse des intervalles ECG inter- et intra-battement sur des modèles d'espace d'état et de Markov cachés". Thesis, Université Grenoble Alpes (ComUE), 2016. http://www.theses.fr/2016GREAT026.
Testo completoCardiovascular diseases are one of the major causes of mortality in humans. One way to diagnose heart diseases and abnormalities is processing of cardiac signals such as ECG. In many of these processes, inter-beat and intra-beat features of ECG signal must be extracted. These features include peak, onset and offset of ECG waves, meaningful intervals and segments that can be defined for ECG signal. ECG fiducial point (FP) extraction refers to identifying the location of the peak as well as the onset and offset of the P-wave, QRS complex and T-wave which convey clinically useful information. However, the precise segmentation of each ECG beat is a difficult task, even for experienced cardiologists.In this thesis, we use a Bayesian framework based on the McSharry ECG dynamical model for ECG FP extraction. Since this framework is based on the morphology of ECG waves, it can be useful for ECG segmentation and interval analysis. In order to consider the time sequential property of ECG signal, we also use the Markovian approach and hidden Markov models (HMM). In brief in this thesis, we use dynamic model (Kalman filter), sequential model (HMM) and their combination (switching Kalman filter (SKF)). We propose three Kalman-based methods, an HMM-based method and a SKF-based method. We use the proposed methods for ECG FP extraction and ECG interval analysis. Kalman-based methods are also used for ECG denoising, T-wave alternans (TWA) detection and fetal ECG R-peak detection.To evaluate the performance of proposed methods for ECG FP extraction, we use the "Physionet QT database", and a "Swine ECG database" that include ECG signal annotations by physicians. For ECG denoising, we use the "MIT-BIH Normal Sinus Rhythm", "MIT-BIH Arrhythmia" and "MIT-BIH noise stress test" databases. "TWA Challenge 2008 database" is used for TWA detection and finally, "Physionet Computing in Cardiology Challenge 2013 database" is used for R-peak detection of fetal ECG. In ECG FP extraction, the performance of the proposed methods are evaluated in terms of mean, standard deviation and root mean square of error. We also calculate the Sensitivity for methods. For ECG denoising, we compare methods in their obtained SNR improvement
Dandach, Hoda. "Prédiction de l'espace navigable par l'approche ensembliste pour un véhicule routier". Thesis, Compiègne, 2014. http://www.theses.fr/2014COMP1892/document.
Testo completoIn this thesis, we aim to characterize a vehicle stable state domain, as well as vehicle state estimation, using interval methods.In the first part of this thesis, we are interested in the intelligent vehicle state estimation.The Bayesian approach is one of the most popular and used approaches of estimation. It is based on the calculated probability of the density function which is neither evident nor simple all the time, conditioned on the available measurements.Among the Bayesian approaches, we know the Kalman filter (KF) in its three forms(linear, non linear and unscented). All the Kalman filters assume unimodal Gaussian state and measurement distributions. As an alternative, the Particle Filter(PF) is a sequential Monte Carlo Bayesian estimator. Contrary to Kalman filter,PF is supposed to give more information about the posterior even when it has a multimodal shape or when the noise follows non-Gaussian distribution. However,the PF is very sensitive to the imprecision due by bias or noise, and its efficiency and accuracy depend mainly on the number of propagated particles which can easily and significantly increase as a result of this imprecision. In this part, we introduce the interval framework to deal with the problems of the non-white biased measurements and bounded errors. We use the Box Particle Filter (BPF), an estimator based simultaneously on the interval analysis and on the particle approach. We aim to estimate some immeasurable state from the vehicle dynamics using the bounded error Box Particle algorithm, like the roll angle and the lateral load transfer, which are two dynamic states of the vehicle. BPF gives a guaranteed estimation of the state vector. The box encountering the estimation is guaranteed to encounter thereal value of the estimated variable as well.In the second part of this thesis, we aim to compute a vehicle stable state domain.An algorithm, based on the set inversion principle and the constraints satisfaction,is used. Considering the longitudinal velocity and the side slip angle at the vehicle centre of gravity, we characterize the set of these two state variables that corresponds to a stable behaviour : neither roll-over nor sliding. Concerning the roll-over risk,we use the lateral transfer ratio LTR as a risk indicator. Concerning the sliding risk, we use the wheels side slip angles. All these variables are related geometrically to the longitudinal velocity and the side slip angle at the centre of gravity. Using these constraints, the set inversion principle is applied in order to define the set ofthe state variables where the two mentioned risks are avoided. The algorithm of Sivia is implemented. Knowing the vehicle trajectory, a maximal allowed velocityon every part of this trajectory is deduced
Avcu, Soner. "Radar Pulse Repetition Interval Tracking With Kalman Filter". Thesis, METU, 2006. http://etd.lib.metu.edu.tr/upload/12607691/index.pdf.
Testo completoGomes, Adriano de Araújo. "Algoritmo das projeções sucessivas para seleção de variáveis em calibração de segunda ordem". Universidade Federal da Paraíba, 2015. http://tede.biblioteca.ufpb.br:8080/handle/tede/8196.
Testo completoMade available in DSpace on 2016-05-12T12:35:36Z (GMT). No. of bitstreams: 1 arquivo total.pdf: 5933598 bytes, checksum: f90080e0529915a4c5c37308259bee89 (MD5) Previous issue date: 2015-06-29
Coordenação de Aperfeiçoamento de Pessoal de Nível Superior - CAPES
In this work it was developed a new strategy for intervals selection using the successive projections algorithm (SPA) coupled to N-PLS and U-PLS models, both with residual bilinearização (RBL) as a post-calibration step. The new algorithm coupled to N-PLS/RBL models was evaluated in two cases of studies. The first was simulated data for quantitation of two analytes (A and B) in the presence of a single interfering. On the second study was conducted a quantitation of ofloxacin in water in the presence of interferents (ciprofloxacin and danofloxacin) by means of liquid chromatography with diode array detection (LC-DAD) data modeling. The results were compared to the N-PLS/RBL model and the variables selection with the genetic algorithm (GA-N-PLS/RBL). In the first case of study (simulated data) were observed RMSEP values (x 10-3 in arbitrary units) for the analytes A and B in the order of 6.7 to 47.6; 10.6 to 11.4; and 6.0 to 14.0 for the N-PLS/RBL, Ga-N-PLS/RBL and the proposed method, respectively. On the second case of study (HPLC-DAD data) RMSEP value (mg/L) of 0.72 (N-PLS/RBL); 0.70 (GA-N-PLS/RBL) and 0.64 (iSPA N-PLS/RBL) were obtained. When combined with the U-PLS/RBL, the new algorithm was evaluated in the EEM modeling in the presence of inner filter effect. Simulated data and quantitation of phenylephrine in the presence of acetaminophen in water sample and interferences (ibuprofen and acetylsalicylic acid) were used as a case of studies. The results were compared to the U-PLS/RBL and e twell established method PARAFAC. For simulated data was observed the following RMSEP values (in arbitrary units) 1.584; 0.077 and 0.066 for PARAFAC; U-PLS/RBL and the proposed method, respectively. In the quantitation of phenylephrine the found RMSEP (in μg/L) were of 0.164 (PARAFAC); 0.089 (U-PLS/RBL) and 0.069 (ISPA-U-PLS/RBL). In all cases it was shown that variables selection is a useful tool capable of improving accuracy when compared with the respective global models (model without variables selection) leading to more parsimonious models. It was observed in all cases, that the sensitivity loss promoted by variables selection is compensated by using more selective channels, justifying the obtained RMSEP smaller values. Finally, it was also observed that the models based on variables selection such as the proposed method were free from significant bias at 95% confidence.
Neste trabalho foi desenvolvida uma nova estratégia para seleção de intervalos empregando o algoritmo das projeções sucessivas (SPA) acoplado a modelos N-PLS e U-PLS, ambos com etapa pós-calibração de bilinearização residual (RBL). O novo algoritmo acoplado a modelos N-PLS/RBL, foi avaliado em dois estudos de casos. O primeiro envolvendo dados simulados para quantificação de dois analitos (A e B) na presença de um único interferente. No segundo foi conduzida a quantificação de ofloxacina em água na presença de interferentes (ciprofloxacina e danofloxacina) por meio da modelagem de dados cromatografia liquida com detecção por arranjo de diodos (LC-DAD). Os resultados obtidos foram comparados ao modelo N-PLS/RBL e a seleção de variáveis com o algoritmo genético (GA-N-PLS/RBL). No primeiro estudo de caso (dados simulados) foram observados valores de RMSEP (x 10-3 em unidades arbitrárias) para os analitos A e B da ordem de 6,7 e 47,6; 10,6 e 11,4; 6,0 e 14,0 para o N-PLS/RBL, GA-N-PLS/RBL e o método proposto, respectivamente. No segundo estudo de caso (dados HPLC-DAD) valores de RMSEP (em mg/L) de 0,72 (N-PLS/RBL); 0,70 (GA-N-PLS/RBL) e 0,64 (iSPA-N-PLS/RBL) foram obtidos. Quando combinado com o U-PLS/RBL o novo algoritmo foi avaliado na modelagem de EEM em presença efeito de filtro interno. Dados simulados e a quantificação de fenilefrina na presença de paracetamol em amostras de água e interferentes (Ibuprofeno e ácido acetil salicílico) foram usados como estudos de caso. Os resultados obtidos foram comparados ao modelo U-PLS/RBL e ao bem estabelecido método PARAFAC. Para dados simulados foram observado os seguintes valores de RMSEP (em unidades arbitrarias) 1,584; 0,077 e 0,066 para o PARAFAC; U-PLS/RBL e método proposto, respectivamente. Na quantificação de fenilefrina os RMSEP (em μg/L) encontrados foram de 0,164 (PARAFAC); 0,089 (U-PLS/RBL) e 0,069 (iSPA-U-PLS/RBL). Em todos os casos foi demostrado que seleção de variáveis é uma ferramenta útil capaz de melhorar a acurácia quando comparados aos respectivos modelos globais (modelo sem seleção de variáveis) e tornar os modelos mais parcimoniosos. Foi observado ainda para todos os casos, que a perda de sensibilidade promovida pela seleção de variáveis é compensada pelo uso de canais mais seletivos, justificando os menores valores de RMSEP obtidos. E por fim, foi também observado que os modelos baseados em seleção de variáveis como o método proposto foram isentos de bias significativos a 95% de confiança.
Merlinge, Nicolas. "State estimation and trajectory planning using box particle kernels". Thesis, Université Paris-Saclay (ComUE), 2018. http://www.theses.fr/2018SACLS425/document.
Testo completoState estimation and trajectory planning are two crucial functions for autonomous systems, and in particular for aerospace vehicles.Particle filters and sample-based trajectory planning have been widely considered to tackle non-linearities and non-Gaussian uncertainties.However, these approaches may produce erratic results due to the sampled approximation of the state density.In addition, they have a high computational cost which limits their practical interest.This thesis investigates the use of box kernel mixtures to describe multimodal probability density functions.A box kernel mixture is a weighted sum of basic functions (e.g., uniform kernels) that integrate to unity and whose supports are bounded by boxes, i.e., vectors of intervals.This modelling yields a more extensive description of the state density while requiring a lower computational load.New algorithms are developed, based on a derivation of the Box Particle Filter (BPF) for state estimation, and of a particle based chance constrained optimisation (Particle Control) for trajectory planning under uncertainty.In order to tackle ambiguous state estimation problems, a Box Regularised Particle Filter (BRPF) is introduced.The BRPF consists of an improved BPF with a guaranteed resampling step and a smoothing strategy based on kernel regularisation.The proposed strategy is theoretically proved to outperform the original BPF in terms of Mean Integrated Square Error (MISE), and empirically shown to reduce the Root Mean Square Error (RMSE) of estimation.BRPF reduces the computation load in a significant way and is robust to measurement ambiguity.BRPF is also integrated to federated and distributed architectures to demonstrate its efficiency in multi-sensors and multi-agents systems.In order to tackle constrained trajectory planning under non-Gaussian uncertainty, a Box Particle Control (BPC) is introduced.BPC relies on an interval bounded kernel mixture state density description, and consists of propagating the state density along a state trajectory at a given horizon.It yields a more accurate description of the state uncertainty than previous particle based algorithms.A chance constrained optimisation is performed, which consists of finding the sequence of future control inputs that minimises a cost function while ensuring that the probability of constraint violation (failure probability) remains below a given threshold.For similar performance, BPC yields a significant computation load reduction with respect to previous approaches
Janapala, Arun. "RR INTERVAL ESTIMATION FROM AN ECG USING A LINEAR DISCRETE KALMAN FILTER". Master's thesis, University of Central Florida, 2005. http://digital.library.ucf.edu/cdm/ref/collection/ETD/id/3426.
Testo completoM.S.E.E.
Department of Electrical and Computer Engineering
Engineering and Computer Science
Electrical Engineering
Motwani, Amit. "Interval Kalman filtering techniques for unmanned surface vehicle navigation". Thesis, University of Plymouth, 2015. http://hdl.handle.net/10026.1/3368.
Testo completoGiacobini, Giulia. "Quando la possibilità filtra attraverso la volontà: esplorazione del concetto giapponese di MA". Bachelor's thesis, Alma Mater Studiorum - Università di Bologna, 2015. http://amslaurea.unibo.it/8889/.
Testo completoPereda, Sebastián Diego de. "Methods for the treatment of uncertainty in dynamical systems: Application to diabetes". Doctoral thesis, Universitat Politècnica de València, 2015. http://hdl.handle.net/10251/54121.
Testo completo[ES] Los pacientes que sufren de diabetes tipo 1 no son capaces de secretar insulina, por lo que tienen que administrársela externamente. La investigación actual se centra en el desarrollo de un páncreas artificial, un sistema de control que administre automáticamente la insulina en función de las necesidades del paciente. El trabajo que aquí se presenta tiene como objetivo mejorar la eficiencia y la seguridad de los algoritmos de control para el páncreas artificial. Los modelos de glucosa-insulina tratan de emular la administración externa de la insulina, la absorción de carbohidratos y la influencia de ambos en la concentración de glucosa en sangre. El problema es que estos procesos son infinitamente complejos y se caracterizan por su alta variabilidad. Los modelos matemáticos utilizados suelen ser una versión simplificada que no incluye toda la variabilidad del proceso y, por lo tanto, no coinciden con la realidad. Esta deficiencia de los modelos puede subsanarse considerando inciertos sus parámetros y las condiciones iniciales, de manera que se desconoce su valor exacto pero sí podemos englobarlos en ciertos intervalos que comprendan toda la variabilidad del proceso considerado. Cuando los valores de los parámetros y de las condiciones iniciales son conocidos, existe, por lo general, un único comportamiento posible. Sin embargo, si están delimitados por intervalos se obtiene un conjunto de posibles soluciones. En este caso, interesa obtener una envoltura de las soluciones que garantice la inclusión de todos los comportamientos posibles. Una técnica habitual que facilita el cómputo de esta envoltura es el análisis de la monotonicidad del sistema. Sin embargo, si el sistema no es totalmente monótono la envoltura obtenida estará sobrestimada. En esta tesis se han desarrollado varios métodos para reducir, o incluso eliminar, la sobrestimación en el cálculo de envolturas, al tiempo que se satisface la garantía de inclusión. Otro inconveniente con el que nos encontramos durante el uso de un páncreas artificial es que solo es posible medir en tiempo real, con cierto ruido en la medida, la glucosa subcutánea. El resto de los estados del sistema son desconocidos, pero podrían ser estimados a partir de este conjunto limitado de mediciones con ruido utilizando observadores de estado, como el Filtro de Kalman. Un ejemplo detallado se muestra al final de la tesis, donde se estima en tiempo real la concentración de insulina en plasma en función de la comida ingerida y de mediciones periódicas de la glucosa subcutánea con ayuda de un Filtro de Kalman Extendido.
[CAT] Els pacients que pateixen de diabetis tipus 1 no són capaços de secretar insulina, motiu pel qual han d'administrar-se-la externament. La investigació actual es centra en el desenvolupament d'un pàncrees artificial, un sistema de control que administre automàticament la insulina en funció de les necessitats del pacient. El treball que ací es presenta té com a objectiu millorar l'eficiència i la seguretat dels algorismes de control per al pàncrees artificial. Els models de glucosa-insulina tracten d'emular l'administració externa de la insulina, l'absorció de carbohidrats i la influència d'ambdós factors en la concentració de glucosa en sang. El problema és que estos processos són infinitament complexos i es caracteritzen per la seua alta variabilitat. Els models matemàtics emprats solen ser una versió simplificada que no inclou tota la variabilitat del procés i, per tant, no coincideixen amb la realitat. Esta deficiència dels models pot esmenar-se considerant incerts els seus paràmetres i les condicions inicials, de manera que es desconeix el seu valor exacte però sí podem englobar-los en certs intervals que comprenguen tota la variabilitat del procés considerat. Quan els valors dels paràmetres i de les condicions inicials són coneguts, existeix, en general, un únic comportament possible. No obstant, si estan delimitats per intervals s'obté un conjunt de possibles solucions. En este cas, interessa obtindre un embolcall de les solucions que assegure la inclusió de tots els comportaments possibles. Una tècnica habitual que facilita el còmput d'este embolcall és l'anàlisi de la monotonicitat del sistema. No obstant, si el sistema no és totalment monòton l'embolcall obtingut estarà sobreestimat. En esta tesi s'han desenvolupat diversos mètodes per a reduir, o fins i tot eliminar, la sobreestimació en el càlcul dels embolcalls, al temps que se satisfà la garantia d'inclusió. Altre inconvenient amb què ens trobem durant l'ús d'un pàncrees artificial és que només és possible mesurar en temps real, amb cert soroll en la mesura, la glucosa subcutània. La resta dels estats del sistema són desconeguts, però podrien ser estimats a partir d'este conjunt limitat de mesures amb soroll utilitzant observadors d'estat, com el Filtre de Kalman. Un exemple detallat es mostra al final de la tesi, on s'estima en temps real la concentració d'insulina en plasma en funció del menjar ingerit i de les mesures periòdiques de la glucosa subcutània amb ajuda d'un Filtre de Kalman Estés.
Pereda Sebastián, DD. (2015). Methods for the treatment of uncertainty in dynamical systems: Application to diabetes [Tesis doctoral no publicada]. Universitat Politècnica de València. https://doi.org/10.4995/Thesis/10251/54121
TESIS
Nicklas, Richard B. "An application of a Kalman Filter Fixed Interval Smoothing Algorithm to underwater target tracking". Thesis, Monterey, California. Naval Postgraduate School, 1989. http://hdl.handle.net/10945/25691.
Testo completoGalinis, William J. "Fixed interval smoothing algorithm for an extended Kalman filter for over-the-horizon ship tracking". Thesis, Monterey, California. Naval Postgraduate School, 1989. http://hdl.handle.net/10945/27057.
Testo completoAraya, Ignacio. "Exploitation des sous-expressions communes et de la monotonie des fonctions pour les algorithmes de filtrage sur intervalles". Nice, 2010. http://www.theses.fr/2010NICE4069.
Testo completoThis thesis deals with the solving of nonlinear systems of equations/constraints by interval-based methods. We present four contributions, all of them aiming at improving constraint propagation algorithms. Constraint propagation contracts the variable domains of individual constraints with a revise procedure and propagates the changes to the rest of the system. Our first two contributions are related to monotonicity of functions and to the dependency problem that occurs when a variable appears several times in a function f. In this case, interval-based methods can generally compute only an approximation of the exact range of f. In the same way, these methods cannot contract optimally the variable domains related to an individual constraint. First, we propose a new Mohc-Revise algorithm that computes the optimal contraction of variables (w. R. T. An individual constraint) when the function is monotonic. The second contribution is an Occurrence Grouping technique that transforms a function f into an equivalent function f_opg, such that the range of f_og can be better approximated by using the monotonicity property. The third contribution is related to the common subexpression elimination technique (CES). CSE is a well-known technique mainly used in code optimization. It basically consists in replacing each subexpression g(X) shared by two or more expressions by an auxiliary variable v and adding the new constraint v = g(X). In this thesis, we prove that the use of CSE techniques in interval analysis as a preprocessing can improve the filtering power of constraint propagation algorithms. Finally, we propose a new partial focusing on well-constrained subsystems of size k. Contracting these subsystems can bring additional filtering compared to global contractors (like interval Newton) and revise procedure used in constraint propagation
Al, Mashhadani Waleed. "The use of multistaic radar in reducing the impact of wind farm on civilian radar system". Thesis, University of Manchester, 2017. https://www.research.manchester.ac.uk/portal/en/theses/the-use-of-multistaic-radar-in-reducing-the-impact-of-wind-farm-on-civilian-radar-system(a80fd906-e670-42a0-9efb-ea22250c87f2).html.
Testo completoKubík, Pavel. "Měření intenzity provozu během pevně daných intervalů v AP". Master's thesis, Vysoké učení technické v Brně. Fakulta elektrotechniky a komunikačních technologií, 2011. http://www.nusl.cz/ntk/nusl-218833.
Testo completoLv, Xiaowei. "Indoor localization in wireless sensor networks". Thesis, Troyes, 2015. http://www.theses.fr/2015TROY0009/document.
Testo completoThis thesis is dedicated to solve the localization problem in mobile wireless sensor networks. It works mainly with fingerprints features and inertial movements information. The former tackles the RSSIs values between sensors while the latter deals with the objets movement attitude by using accelerometer and gyroscope. The combination of both information is performed in terms of interval analysis, or Kalman filtering. The proposed work introduces three orders mobility models to approximate nodes trajectories using accelerations, combined then to the weighted K nearest neighbors algorithm in a centralized scheme. Then the mobility models are extended up to the inertial information taking into consideration the rotations of the nodes. A decentralized localization method is also proposed in the following in view of the working mechanism of large scale sensor networks. Finally, this thesis proposes a zoning localization method aiming at determining the zones in which the nodes reside. The proposed method addresses the zoning problem by using both the belief functions theory and the interval analysis
Robinson, Elinirina Iréna. "Filtering and uncertainty propagation methods for model-based prognosis". Thesis, Paris, CNAM, 2018. http://www.theses.fr/2018CNAM1189/document.
Testo completoIn this manuscript, contributions to the development of methods for on-line model-based prognosis are presented. Model-based prognosis aims at predicting the time before the monitored system reaches a failure state, using a physics-based model of the degradation. This time before failure is called the remaining useful life (RUL) of the system.Model-based prognosis is divided in two main steps: (i) current degradation state estimation and (ii) future degradation state prediction to predict the RUL. The first step, which consists in estimating the current degradation state using the measurements, is performed with filtering techniques. The second step is realized with uncertainty propagation methods. The main challenge in prognosis is to take the different uncertainty sources into account in order to obtain a measure of the RUL uncertainty. There are mainly model uncertainty, measurement uncertainty and future uncertainty (loading, operating conditions, etc.). Thus, probabilistic and set-membership methods for model-based prognosis are investigated in this thesis to tackle these uncertainties.The ability of an extended Kalman filter and a particle filter to perform RUL prognosis in presence of model and measurement uncertainty is first studied using a nonlinear fatigue crack growth model based on the Paris' law and synthetic data. Then, the particle filter combined to a detection algorithm (cumulative sum algorithm) is applied to a more realistic case study, which is fatigue crack growth prognosis in composite materials under variable amplitude loading. This time, model uncertainty, measurement uncertainty and future loading uncertainty are taken into account, and real data are used. Then, two set-membership model-based prognosis methods based on constraint satisfaction and unknown input interval observer for linear discete-time systems are presented. Finally, an extension of a reliability analysis method to model-based prognosis, namely the inverse first-order reliability method (Inverse FORM), is presented.In each case study, performance evaluation metrics (accuracy, precision and timeliness) are calculated in order to make a comparison between the proposed methods
Robinson, Elinirina Iréna. "Filtering and uncertainty propagation methods for model-based prognosis". Electronic Thesis or Diss., Paris, CNAM, 2018. http://www.theses.fr/2018CNAM1189.
Testo completoIn this manuscript, contributions to the development of methods for on-line model-based prognosis are presented. Model-based prognosis aims at predicting the time before the monitored system reaches a failure state, using a physics-based model of the degradation. This time before failure is called the remaining useful life (RUL) of the system.Model-based prognosis is divided in two main steps: (i) current degradation state estimation and (ii) future degradation state prediction to predict the RUL. The first step, which consists in estimating the current degradation state using the measurements, is performed with filtering techniques. The second step is realized with uncertainty propagation methods. The main challenge in prognosis is to take the different uncertainty sources into account in order to obtain a measure of the RUL uncertainty. There are mainly model uncertainty, measurement uncertainty and future uncertainty (loading, operating conditions, etc.). Thus, probabilistic and set-membership methods for model-based prognosis are investigated in this thesis to tackle these uncertainties.The ability of an extended Kalman filter and a particle filter to perform RUL prognosis in presence of model and measurement uncertainty is first studied using a nonlinear fatigue crack growth model based on the Paris' law and synthetic data. Then, the particle filter combined to a detection algorithm (cumulative sum algorithm) is applied to a more realistic case study, which is fatigue crack growth prognosis in composite materials under variable amplitude loading. This time, model uncertainty, measurement uncertainty and future loading uncertainty are taken into account, and real data are used. Then, two set-membership model-based prognosis methods based on constraint satisfaction and unknown input interval observer for linear discete-time systems are presented. Finally, an extension of a reliability analysis method to model-based prognosis, namely the inverse first-order reliability method (Inverse FORM), is presented.In each case study, performance evaluation metrics (accuracy, precision and timeliness) are calculated in order to make a comparison between the proposed methods
Xiong, Jun. "Set-membership state estimation and application on fault detection". Phd thesis, Institut National Polytechnique de Toulouse - INPT, 2013. http://tel.archives-ouvertes.fr/tel-01068054.
Testo completoIpek, Ozlem. "Target Tracking With Phased Array Radar By Using Adaptive Update Rate". Master's thesis, METU, 2010. http://etd.lib.metu.edu.tr/upload/2/12611589/index.pdf.
Testo completomaneuvering segment in its trajectory. In this trajectory, the starting and final time instants of the single maneuver are specified clearly, which is important in the assessment of the algorithm performances. The effects of incorporating the variable update time interval into target tracking problem are presented and compared for several different test cases.
Vincke, Bastien. "Architectures pour des systèmes de localisation et de cartographie simultanées". Phd thesis, Université Paris Sud - Paris XI, 2012. http://tel.archives-ouvertes.fr/tel-00770323.
Testo completoGensel, Jérôme. "Contraintes et représentation de connaissances par objets : application au modèle Tropes". Phd thesis, Université Joseph Fourier (Grenoble), 1995. http://tel.archives-ouvertes.fr/tel-00005046.
Testo completoLévêque, Olivier. "Méthodes ensemblistes pour la localisation de véhicules". Compiègne, 1998. http://www.theses.fr/1998COMP1090.
Testo completoBroadly speaking, the context of these research works is hose or autonomous mobile robots which are designed to move in structured and par tially 2D-mapped environments. The presented thesis consists in studying the localization fonction. The localization problem is decomposed in two subproblems : the initialization and the dynamical tracking of the localization. Initializing the localization is an open problem, which is both complex and fundamental to enhance the robot autonomy. The sight of the localization fonction, that is not very tackle in the literature contrary to localization tracking problem for which experienced technical solutions are available, has motivated the works reported in this manuscript. The localization principle, common to the all different presented methods, is based on a mechanical analogy of the telemetric range measurement. The first original method is geometric and appeals to a clipping algorithm specially suited to our robotic application. The second localization method uses the extended KALMAN filtering which is a widely known statistical state estimation tool. The third localization method is a bounded-error set membership one, that leans on an ellipsoïdal technique of state estimation for linear models. The last developed rnethod, which is based on set inversion via interval analysis, constitutes an efficient, reliable and robust solution to answer to the critical localization initialization problem. In this guaranteed approach, the difficult matching step between the range measurements and the landmarks of the environrnent, that is needed to applicate the previously presented methods, becomes a sub-product of the set inversion localization method. When the telemetric measurements are ambignous, the method produces all the different localization hypotheses which allow to explain the measurements. All the four localization methods described in this document have been validated and compared by means of tests from both simulated data and real ones produced by the ultrasonic range sensors on board the experimental vehicle of the laboratory
Lank, Petr. "Externí kardiostimulátor". Master's thesis, Vysoké učení technické v Brně. Fakulta elektrotechniky a komunikačních technologií, 2008. http://www.nusl.cz/ntk/nusl-217226.
Testo completoMlčoch, Marek. "Kumulace biologických dat". Master's thesis, Vysoké učení technické v Brně. Fakulta elektrotechniky a komunikačních technologií, 2011. http://www.nusl.cz/ntk/nusl-219246.
Testo completoVestin, Albin, e Gustav Strandberg. "Evaluation of Target Tracking Using Multiple Sensors and Non-Causal Algorithms". Thesis, Linköpings universitet, Reglerteknik, 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-160020.
Testo completoShen, Kuan-Wei, e 沈冠緯. "Using a Hybrid of Interval Type-2 RFCMAC and Bilateral Filter for Satellite Image Dehazing". Thesis, 2017. http://ndltd.ncl.edu.tw/handle/764ug2.
Testo completo國立勤益科技大學
資訊工程系
105
With advances in technology, the development of Remote Sensing Satellite Image has been real-time and accurate to monitor the environment of the surface or prevent the inevitable disaster earlier. Owing to the changeable weather is just like clouds or haze constituted by atmospheric particles, then this phenomenon cause the low contrast presented in satellite image and lose many information on the surface of the earth. Therefore, in this paper we propose an issue for dehazing to single satellite image, which is to enhance the contrast of image and filter the haze that cover the location, then the losing information will be back. First, we use Interval Type-2 RFCMAC Model to estimate the initial transmission map of the image. When facing the problems of halo and color over saturation, we adopt the bilateral filter and the quadratic function nonlinear transformation step by step to refine the initial transmission map. At the atmospheric light estimation, we adopt the first 1% brightest area as the color vector of atmospheric light. Finally, we take the refined transmission map and atmospheric light as the two parameters of reconstruct image. The experiment result shows that the method of satellite image dehazing has an effective results in visibility details and color contrast of reconstruction image. Furthermore, in order to prove the effective results, we take the visual assessment and quantitative evaluation respectively to compare with other authors. After visual assessment and quantitative evaluation, we get the better result in visual and data indeed.
Paczkowski, Sebastian. "Insect olfaction as an information filter for chemo-analytical applications". Doctoral thesis, 2013. http://hdl.handle.net/11858/00-1735-0000-0022-5E8A-A.
Testo completoXiong, Jun. Phd thesis, Institut National Polytechnique de Toulouse - INPT, 2013. http://tel.archives-ouvertes.fr/tel-01067345.
Testo completoCruz, Aniana da Rosa de Brito da. "Mental state monitoring for improving the Brain-Computer Interface robustness in a human-centered collaborative control". Doctoral thesis, 2021. http://hdl.handle.net/10316/95450.
Testo completoA brain-computer interface (BCI) is a useful device for people with severe motor disabilities, and several BCI applications and devices have already been validated, such as communication spellers, wheelchairs, prosthetic devices, etc. However, BCI still has a very limited application in daily real-world tasks due to its low speed, low reliability, and other practical aspects, such as the high user’s workload imposed by continuous focus, and the need for calibration in every session. BCI researchers have been striving to improve the reliability as well as other usability issues. The main goal of this PhD thesis was to research and develop new approaches and new methods to improve the reliability and usability of current BCI systems. This thesis contributes to the BCI field mainly on three topics. The first main contribution is a novel approach based on double error-related potential (ErrP) detection for automatic error correction. We introduce a second ErrP to validate automatic correction. The approach demonstrates the possibility of using ErrPs in a closed-loop human-computer interaction, allowing the user to change or confirm system decisions. The proposed approach was assessed offline and online through a set of experimental tests. Results showed that the proposed approach is effective with a significant increase in classification accuracy and information transfer rate. Secondly, a self-paced P300-based brain-controlled wheelchair (BCW) combined with a collaborative-controller and dynamic-time commands is proposed. The feasibility of this approach was analysed by measuring the impact of these three features on the system reliability, naturalness of interaction, and users’ effort. The proposed method was validated through extensive experiments conducted with able-bodied individuals and individuals with severe motor disabilities. Results showed high feasibility for both able-bodied and motor-disabled participants. The third main issue researched in this thesis is focused on model generalization across session and cross-subject variability. To achieve a good performance, the classification model is usually built from calibration data recorded at the beginning of each session. A novel statistical spatial filter is proposed that takes advantage of the Riemannian distance to extract features that are robust to the non-stationarity of electroencephalographic (EEG) signals. The results show that the proposed method improves generalization across sessions and it is robust to the variation of the amount of training data.
Uma interface cérebro-computador (ICC) é um dispositivo útil para pessoas com deficiências motoras graves e vários dispositivos e aplicações já foram validados, como por exemplo soletradores para comunicação, cadeiras de rodas, dispositivos protéticos, etc. No entanto, a aplicação das ICCs em tarefas do dia-a-dia ainda é limitada devido à sua baixa velocidade, baixa fiabilidade e outros aspetos práticos, como a alta carga de trabalho mental do utilizador imposta pelo foco contínuo e a necessidade de calibrar o sistema em cada sessão. Os investigadores das ICCs têm se esforçado para melhorar a fiabilidade e também outras questões relacionadas com usabilidade. Esta tese pretende investigar e desenvolver novas abordagens e novos métodos para melhorar a fiabilidade e usabilidade dos sistemas ICC. Esta tese contribui para a área das ICCs principalmente em três tópicos. A primeira contribuição é uma nova abordagem baseada na deteção dupla do potencial de erro (ErrP) para correção automática de erros. Introduzimos um segundo ErrP para validar a correção automática. A abordagem demonstra a possibilidade de usar ErrPs numa interação homem-computador em malha fechada, permitindo ao utilizador alterar ou confirmar as decisões do sistema. A abordagem proposta foi avaliada offline e online através de um conjunto de testes experimentais. Os resultados demostraram que a abordagem proposta é eficaz com um aumento significativo na precisão da classificação e na taxa de transferência de informação. Em segundo lugar, é proposta uma interface aplicada a uma cadeira de rodas atuada pelo cérebro baseada no potencial P300 ao ritmo do utilizador combinado com um controlador colaborativo e comandos com janela de tempo dinâmico. A viabilidade dessa abordagem foi testada através da medição do impacto dessas três características na fiabilidade do sistema, na naturalidade da interação e no esforço dos utilizadores. O desempenho dos métodos propostos foi avaliado através de um extenso conjunto de experiências realizadas com indivíduos saudáveis e indivíduos portadores de deficiência motora grave. Os resultados evidenciaram alta fiabilidade tanto para os participantes saudáveis como para os participantes com deficiência motora. A terceira questão abordada nesta tese está focada na generalização do modelo de classificação ErrP entre sessões e entre utilizadores. Para se obter um bom desempenho, o modelo de classificação é normalmente construído com os dados de calibração obtidos no início de cada sessão. É proposto um novo método de filtro espacial que tira partido da distância Riemanniana para extrair características que são robustas à não estacionariedade dos sinais eletroencefalográfico (EEG). Pode concluir-se dos resultados que o método proposto aumenta a generalização entre as sessões e é robusto à variação da quantidade de dados de treino.