To see the other types of publications on this topic, follow the link: Fusion approaches.
Dissertations / Theses on the topic 'Fusion approaches'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 dissertations / theses for your research on the topic 'Fusion approaches.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse dissertations / theses on a wide variety of disciplines and organise your bibliography correctly.
1
Michael, Andrew M. "Imaging schizophrenia : data fusion approaches to characterize and classify /." Online version of thesis, 2009. http://hdl.handle.net/1850/9673.
Full text
2
Andrade, Valente da Silva Michelle. "SLAM and data fusion for autonomous vehicles : from classical approaches to deep learning methods." Thesis, Paris Sciences et Lettres (ComUE), 2019. http://www.theses.fr/2019PSLEM079.
Full textAbstract:
L'arrivée des voitures autonomes va provoquer une transformation très importante de la mobilité urbaine telle que nous la connaissons, avec un impact significatif sur notre vie quotidienne. En effet, elles proposent un nouveau système de déplacement plus efficace, plus facilement accessible et avec une meilleure sécurité routière. Pour atteindre cet objectif, les véhicules autonomes doivent effectuer en toute sécurité et de manière autonome trois tâches principales: la perception, la planification et le contrôle. La perception est une tâche particulièrement difficile en milieu urbain, car elle se doit d'être suffisamment précise pour assurer à la fois la sécurité du conducteur et celle des autres. Il est décisif d’avoir une bonne compréhension de l’environnement et de ses obstacles, ainsi qu’une localisation précise, afin que les autres tâches puissent être performantes. L'objectif de cette thèse est d'explorer différentes techniques pour la cartographie et la localisation des voitures autonomes en milieu urbain, en partant des approches classiques jusqu'aux algorithmes d'apprentissage profond. On s'intéresse plus spécifiquement aux véhicules équipés de capteurs bon marché avec l'idée de maintenir un prix raisonnable pour les futures voitures autonomes. Dans cette optique, nous utilisons dans les méthodes proposées des capteurs comme des scanner laser 2D, des caméras et des centrales inertielles à bas coût. Dans la première partie, nous introduisons des méthodes classiques utilisant des grilles d'occupation évidentielles. Dans un premier temps, nous présentons une nouvelle approche pour faire de la fusion entre une caméra et un scanner laser 2D pour améliorer la perception de l'environnement. De plus, nous avons ajouté une nouvelle couche dans notre grille d'occupation afin d'affecter un état à chaque objet détecté. Cet état permet de suivre l'objet et de déterminer s'il est statique ou dynamique. Ensuite, nous proposons une méthode de localisation s'appuyant sur cette nouvelle couche ainsi que sur des techniques de superposition d'images pour localiser le véhicule tout en créant une carte de l'environnement. Dans la seconde partie, nous nous intéressons aux algorithmes d'apprentissage profond appliqués à la localisation. D'abord, nous introduisons une méthode d'apprentissage pour l'estimation d'odométrie utilisant seulement des données issues de scanners laser 2D. Cette approche démontre l'intérêt des réseaux de neurones comme un bon moyen pour analyser ce type de données, dans l'optique d'estimer le déplacement du véhicule. Ensuite, nous étendons la méthode précédente en fusionnant le laser scanner 2D avec une caméra dans un système d'apprentissage de bout-en-bout. L'ajout de cette caméra permet d'améliorer la précision de l'estimation d'odométrie et prouve qu'il est possible de faire de la fusion de capteurs avec des réseaux de neurones. Finalement, nous présentons un nouvel algorithme hybride permettant à un véhicule de se localiser dans une région déjà cartographiée. Cet algorithme s'appuie à la fois sur une grille évidentielle prenant en compte les objets dynamiques et sur la capacité des réseaux de neurones à analyser des images. Les résultats obtenus lors de cette thèse nous ont permis de mieux comprendre les problématiques liées à l'utilisation de capteurs bon marché dans un environnement dynamique. En adaptant nos méthodes à ces capteurs et en introduisant une fusion de leur information, nous avons amélioré la perception générale de l'environnement ainsi que la localisation du véhicule. De plus, notre approche a permis d'identifier les avantages et inconvénients entre les différentes méthodes classiques et d'apprentissage. Ainsi, nous proposons une manière de combiner ces deux types d'approches dans un système hybride afin d'obtenir une localisation plus précise et plus robusteSelf-driving cars have the potential to provoke a mobility transformation that will impact our everyday lives. They offer a novel mobility system that could provide more road safety, efficiency and accessibility to the users. In order to reach this goal, the vehicles need to perform autonomously three main tasks: perception, planning and control. When it comes to urban environments, perception becomes a challenging task that needs to be reliable for the safety of the driver and the others. It is extremely important to have a good understanding of the environment and its obstacles, along with a precise localization, so that the other tasks are well performed. This thesis explores from classical approaches to Deep Learning techniques to perform mapping and localization for autonomous vehicles in urban environments. We focus on vehicles equipped with low-cost sensors with the goal to maintain a reasonable price for the future autonomous vehicles. Considering this, we use in the proposed methods sensors such as 2D laser scanners, cameras and standard IMUs. In the first part, we introduce model-based methods using evidential occupancy grid maps. First, we present an approach to perform sensor fusion between a stereo camera and a 2D laser scanner to improve the perception of the environment. Moreover, we add an extra layer to the grid maps to set states to the detected obstacles. This state allows to track an obstacle overtime and to determine if it is static or dynamic. Sequentially, we propose a localization system that uses this new layer along with classic image registration techniques to localize the vehicle while simultaneously creating the map of the environment. In the second part, we focus on the use of Deep Learning techniques for the localization problem. First, we introduce a learning-based algorithm to provide odometry estimation using only 2D laser scanner data. This method shows the potential of neural networks to analyse this type of data for the estimation of the vehicle's displacement. Sequentially, we extend the previous method by fusing the 2D laser scanner with a camera in an end-to-end learning system. The addition of camera images increases the accuracy of the odometry estimation and proves that we can perform sensor fusion without any sensor modelling using neural networks. Finally, we present a new hybrid algorithm to perform the localization of a vehicle inside a previous mapped region. This algorithm takes the advantages of the use of evidential maps in dynamic environments along with the ability of neural networks to process images. The results obtained in this thesis allowed us to better understand the challenges of vehicles equipped with low-cost sensors in dynamic environments. By adapting our methods for these sensors and performing the fusion of their information, we improved the general perception of the environment along with the localization of the vehicle. Moreover, our approaches allowed a possible comparison between the advantages and disadvantages of learning-based techniques compared to model-based ones. Finally, we proposed a form of combining these two types of approaches in a hybrid system that led to a more robust solution
3
Pakhotin, Ivan. "Fusion of first principles driven and system science approaches to advance radiation belt forecasting." Thesis, University of Sheffield, 2014. http://etheses.whiterose.ac.uk/7260/.
Full textAbstract:
Modern radiation belt models can be broadly split into either physics-driven diffusion based algorithms, or data science techniques that utilise the continuous data coverage from satellites at geostationary orbit and the Lagrange point L1 to apply statistical data analysis methods to predict electron fluxes at geostationary orbit. The first kind, while posessing generality due to their physical nature, lack accuracy compared to their data-driven counterparts. This is because the magnetosphere is a highly complex system that is not easy to model and its dynamics are not yet fully understood. Meanwhile, data-driven methods possess statistical accuracy, but cannot predict outside their operating parameters, and so on their own provide no information about what happens in the wider radiation belt region. This thesis is devoted to the development of a model that combines the two approaches into one unified system, attempting to combine the predictive range of physical modelling with the accuracy of the data-driven approach. This model uses geosynchronous orbit fluxes predicted using an advanced data science technique as an input to drive a physics-based radiation belt modelling code. The model has been developed and tested for a range of energy channels, magnetospheric conditions, and with various modifications. It was validated using data from NASA's recent Van Allen probes mission and with NOAA's GOES-13 geostationary satellite. The model results are in good agreement with observations, with the sources of inaccuracies explored in the manuscript. This work is a first attempt to create such a model, and potential improvements are outlined that should further increase accuracy. A further modification of the model is explored that is found to provide superior performance at geostationary orbit at the cost of degraded performance elsewhere. It is proposed to use this modification in tandem with the main model, where accurate information about geostationary orbit is required. The modification has been tested on long-duration time periods and was found to generate good predictions for high-energy electron fluxes. The role of electromagnetic ion cyclotron (EMIC) waves is explored using wave vector analysis and calculation of minimum resonant energies. The aim is to identify what effect EMIC waves have on electron dynamics at energies below 1 MeV. The conclusions are that EMIC waves, under certain conditions, do affect these electron populations in the magnetosphere, and their effect should be included in a representative radiation belt model. This is suggested as a further improvement to the simulation.
4
江卓庭 and Cheuk-ting Kong. "Understanding the function of the Mll-een leukaemic fusion gene by embryonic stem cell approaches." Thesis, The University of Hong Kong (Pokfulam, Hong Kong), 2003. http://hub.hku.hk/bib/B31244312.
Full text
5
Stone, David L. "The Application of Index Based, Region Segmentation, and Deep Learning Approaches to Sensor Fusion for Vegetation Detection." VCU Scholars Compass, 2019. https://scholarscompass.vcu.edu/etd/5708.
Full textAbstract:
This thesis investigates the application of index based, region segmentation, and deep learning methods to the sensor fusion of omnidirectional (O-D) Infrared (IR) sensors, Kinnect sensors, and O-D vision sensors to increase the level of intelligent perception for unmanned robotic platforms. The goals of this work is first to provide a more robust calibration approach and improve the calibration of low resolution and noisy IR O-D cameras. Then our goal was to explore the best approach to sensor fusion for vegetation detection. We looked at index based, region segmentation, and deep learning methods and compared them with a goal of significant reduction in false positives while maintaining reasonable vegetation detection.
The results are as follows:
Direct Spherical Calibration of the IR camera provided a more consistent and robust calibration board capture and resulted in the best overall calibration results with sub-pixel accuracy
The best approach for sensor fusion for vegetation detection was the deep learning approach, the three methods are detailed in the following chapters with the results summarized here.
Modified Normalized Difference Vegetation Index approach achieved 86.74% recognition and 32.5% false positive, with peaks to 80%
Thermal Region Fusion (TRF) achieved a lower recognition rate at 75.16% but reduced false positives to 11.75% (a 64% reduction)
Our Deep Learning Fusion Network (DeepFuseNet) results demonstrated that deep learning approach showed the best results with a significant (92%) reduction in false positives when compared to our modified normalized difference vegetation index approach. The recognition was 95.6% with 2% false positive.
Current approaches are primarily focused on O-D color vision for localization, mapping, and tracking and do not adequately address the application of these sensors to vegetation detection. We will demonstrate the contradiction between current approaches and our deep sensor fusion (DeepFuseNet) for vegetation detection. The combination of O-D IR and O-D color vision coupled with deep learning for the extraction of vegetation material type, has great potential for robot perception. This thesis will look at two architectures: 1) the application of Autoencoders Feature Extractors feeding a deep Convolution Neural Network (CNN) fusion network (DeepFuseNet), and 2) Bottleneck CNN feature extractors feeding a deep CNN fusion network (DeepFuseNet) for the fusion of O-D IR and O-D visual sensors. We show that the vegetation recognition rate and the number of false detects inherent in the classical indices based spectral decomposition are greatly improved using our DeepFuseNet architecture.
We first investigate the calibration of omnidirectional infrared (IR) camera for intelligent perception applications. The low resolution omnidirectional (O-D) IR image edge boundaries are not as sharp as with color vision cameras, and as a result, the standard calibration methods were harder to use and less accurate with the low definition of the omnidirectional IR camera. In order to more fully address omnidirectional IR camera calibration, we propose a new calibration grid center coordinates control point discovery methodology and a Direct Spherical Calibration (DSC) approach for a more robust and accurate method of calibration. DSC addresses the limitations of the existing methods by using the spherical coordinates of the centroid of the calibration board to directly triangulate the location of the camera center and iteratively solve for the camera parameters. We compare DSC to three Baseline visual calibration methodologies and augment them with additional output of the spherical results for comparison. We also look at the optimum number of calibration boards using an evolutionary algorithm and Pareto optimization to find the best method and combination of accuracy, methodology and number of calibration boards. The benefits of DSC are more efficient calibration board geometry selection, and better accuracy than the three Baseline visual calibration methodologies.
In the context of vegetation detection, the fusion of omnidirectional (O-D) Infrared (IR) and color vision sensors may increase the level of vegetation perception for unmanned robotic platforms. A literature search found no significant research in our area of interest. The fusion of O-D IR and O-D color vision sensors for the extraction of feature material type has not been adequately addressed. We will look at augmenting indices based spectral decomposition with IR region based spectral decomposition to address the number of false detects inherent in indices based spectral decomposition alone. Our work shows that the fusion of the Normalized Difference Vegetation Index (NDVI) from the O-D color camera fused with the IR thresholded signature region associated with the vegetation region, minimizes the number of false detects seen with NDVI alone. The contribution of this work is the demonstration of two new techniques, Thresholded Region Fusion (TRF) technique for the fusion of O-D IR and O-D Color. We also look at the Kinect vision sensor fused with the O-D IR camera. Our experimental validation demonstrates a 64% reduction in false detects in our method compared to classical indices based detection.
We finally compare our DeepFuseNet results with our previous work with Normalized Difference Vegetation index (NDVI) and IR region based spectral fusion. This current work shows that the fusion of the O-D IR and O-D visual streams utilizing our DeepFuseNet deep learning approach out performs the previous NVDI fused with far infrared region segmentation. Our experimental validation demonstrates an 92% reduction in false detects in our method compared to classical indices based detection. This work contributes a new technique for the fusion of O-D vision and O-D IR sensors using two deep CNN feature extractors feeding into a fully connected CNN Network (DeepFuseNet).
6
Lingenfelser, Florian [Verfasser], and Elisabeth [Akademischer Betreuer] André. "From Synchronous to Asynchronous Event-driven Fusion Approaches in Multi-modal Affect Recognition / Florian Lingenfelser ; Betreuer: Elisabeth André." Augsburg : Universität Augsburg, 2018. http://d-nb.info/1168591031/34.
Full text
7
Ghattas, Andrew Emile. "Medical imaging segmentation assessment via Bayesian approaches to fusion, accuracy and variability estimation with application to head and neck cancer." Diss., University of Iowa, 2017. https://ir.uiowa.edu/etd/5759.
Full textAbstract:
With the advancement of technology, medical imaging has become a fast growing area of research. Some imaging questions require little physician analysis, such as diagnosing a broken bone, using a 2-D X-ray image. More complicated questions, using 3-D scans, such as computerized tomography (CT), can be much more difficult to answer. For example, estimating tumor growth to evaluate malignancy; which informs whether intervention is necessary. This requires careful delineation of different structures in the image. For example, what is the tumor versus what is normal tissue; this is referred to as segmentation. Currently, the gold standard of segmentation is for a radiologist to manually trace structure edges in the 3-D image, however, this can be extremely time consuming. Additionally, manual segmentation results can differ drastically between and even within radiologists. A more reproducible, less variable, and more time efficient segmentation approach would drastically improve medical treatment. This potential, as well as the continued increase in computing power, has led to computationally intensive semiautomated segmentation algorithms. Segmentation algorithms' widespread use is limited due to difficulty in validating their performance. Fusion models, such as STAPLE, have been proposed as a way to combine multiple segmentations into a consensus ground truth; this allows for evaluation of both manual and semiautomated segmentation in relation to the consensus ground truth. Once a consensus ground truth is obtained, a multitude of approaches have been proposed for evaluating different aspects of segmentation performance; segmentation accuracy, between- and within -reader variability.
The focus of this dissertation is threefold. First, a simulation based tool is introduced to allow for the validation of fusion models. The simulation properties closely follow a real dataset, in order to ensure that they mimic reality. Second, a statistical hierarchical Bayesian fusion model is proposed, in order to estimate a consensus ground truth within a robust statistical framework. The model is validated using the simulation tool and compared to other fusion models, including STAPLE. Additionally, the model is applied to real datasets and the consensus ground truth estimates are compared across different fusion models. Third, a statistical hierarchical Bayesian performance model is proposed in order to estimate segmentation method specific accuracy, between- and within -reader variability. An extensive simulation study is performed to validate the model’s parameter estimation and coverage properties. Additionally, the model is fit to a real data source and performance estimates are summarized.
8
Dalvi, Rupin. "Novel approaches for multi-modal imaging and fusion in orthopaedic research for analysis of bone and joint anatomy and motion." Thesis, University of British Columbia, 2009. http://hdl.handle.net/2429/15857.
Full textAbstract:
Faced with an increasingly aging and overweight population, our modern societies, particularly in the west, are set to witness a steep rise in various orthopaedic health problems in the coming decades, especially joint diseases such as arthritis. Better understanding of the way bones of the joints work is thus imperative for studying the nature and effects of these diseases and for finding cures. The data obtained from conventional sources such as skin markers and x-ray/fluoroscopy scans are generally useful but quite limited in terms of accuracy, quantification abilities and three-dimensional visualization potential. The continuous increase in the quality and versatility of various modern imaging modalities is enabling many new means for enhanced visualization and analysis of motion data of the joints. In this thesis we make use of ultrasound (US) and magnetic resonance (MR) imaging to facilitate robust, accurate and efficient analysis of the bones of joints in motion. We achieve this by obtaining motion data using 3D US with high temporal resolution which is then fused with a high spatial resolution, but static MRI volume of the same region (we mostly focus on the knee joint area). Our contributions include novel ways for improved segmentation and localization of the bones from image data. In particular, a highly effective method for improving bone segmentation in MRI volumes by enhancing the contrast at the bone-cartilage interface is proposed. Our contribution also focuses on robust and accurate registration of image data. To achieve this, a new method for stitching US bone volumes is proposed for generating larger fields of view. Further, we also present a novel method for US-MRI bone surface registration. The tools developed during the course of this thesis facilitate orthopaedic research efforts aiming to improving our understanding of the workings of the joints. The tools and methodologies proposed are versatile and expected to be applicable to other applications.
9
Jensfelt, Patric. "Approaches to Mobile Robot Localization in Indoor Environments." Doctoral thesis, Stockholm : Tekniska högsk, 2001. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-3194.
Full text
10
Jiao, Lianmeng. "Classification of uncertain data in the framework of belief functions : nearest-neighbor-based and rule-based approaches." Thesis, Compiègne, 2015. http://www.theses.fr/2015COMP2222/document.
Full textAbstract:
Dans de nombreux problèmes de classification, les données sont intrinsèquement incertaines. Les données d’apprentissage disponibles peuvent être imprécises, incomplètes, ou même peu fiables. En outre, des connaissances spécialisées partielles qui caractérisent le problème de classification peuvent également être disponibles. Ces différents types d’incertitude posent de grands défis pour la conception de classifieurs. La théorie des fonctions de croyance fournit un cadre rigoureux et élégant pour la représentation et la combinaison d’une grande variété d’informations incertaines. Dans cette thèse, nous utilisons cette théorie pour résoudre les problèmes de classification des données incertaines sur la base de deux approches courantes, à savoir, la méthode des k plus proches voisins (kNN) et la méthode à base de règles.Pour la méthode kNN, une préoccupation est que les données d’apprentissage imprécises dans les régions où les classes de chevauchent peuvent affecter ses performances de manière importante. Une méthode d’édition a été développée dans le cadre de la théorie des fonctions de croyance pour modéliser l’information imprécise apportée par les échantillons dans les régions qui se chevauchent. Une autre considération est que, parfois, seul un ensemble de données d’apprentissage incomplet est disponible, auquel cas les performances de la méthode kNN se dégradent considérablement. Motivé par ce problème, nous avons développé une méthode de fusion efficace pour combiner un ensemble de classifieurs kNN couplés utilisant des métriques couplées apprises localement. Pour la méthode à base de règles, afin d’améliorer sa performance dans les applications complexes, nous étendons la méthode traditionnelle dans le cadre des fonctions de croyance. Nous développons un système de classification fondé sur des règles de croyance pour traiter des informations incertains dans les problèmes de classification complexes. En outre, dans certaines applications, en plus de données d’apprentissage, des connaissances expertes peuvent également être disponibles. Nous avons donc développé un système de classification hybride fondé sur des règles de croyance permettant d’utiliser ces deux types d’information pour la classificationIn many classification problems, data are inherently uncertain. The available training data might be imprecise, incomplete, even unreliable. Besides, partial expert knowledge characterizing the classification problem may also be available. These different types of uncertainty bring great challenges to classifier design. The theory of belief functions provides a well-founded and elegant framework to represent and combine a large variety of uncertain information. In this thesis, we use this theory to address the uncertain data classification problems based on two popular approaches, i.e., the k-nearest neighbor rule (kNN) andrule-based classification systems. For the kNN rule, one concern is that the imprecise training data in class over lapping regions may greatly affect its performance. An evidential editing version of the kNNrule was developed based on the theory of belief functions in order to well model the imprecise information for those samples in over lapping regions. Another consideration is that, sometimes, only an incomplete training data set is available, in which case the ideal behaviors of the kNN rule degrade dramatically. Motivated by this problem, we designedan evidential fusion scheme for combining a group of pairwise kNN classifiers developed based on locally learned pairwise distance metrics.For rule-based classification systems, in order to improving their performance in complex applications, we extended the traditional fuzzy rule-based classification system in the framework of belief functions and develop a belief rule-based classification system to address uncertain information in complex classification problems. Further, considering that in some applications, apart from training data collected by sensors, partial expert knowledge can also be available, a hybrid belief rule-based classification system was developed to make use of these two types of information jointly for classification
11
Zhu, Hao. "Modelling and interpreting the coupling between coherent nonlinear structures and ambient turbulence in fusion plasmas using approaches derived from the Lotka-Volterra equations." Thesis, University of Warwick, 2015. http://wrap.warwick.ac.uk/73495/.
Full textAbstract:
Turbulent transport in magnetized plasmas is one of the fundamental issues in fusion plasma physics. It is recognized that the interactions between zonal flows(ZFs) and micro-scale drift wave turbulence can influence plasma transport in both Tokamaks and Stellarators. These interactions are believed to play a significant role in the transition from low energy confinement regime(L-mode) to high confinement regime(H-mode). In the desired H-mode, the temperatures and densities are higher than those in L-mode, and this can typically generate a doubling of the confinement time. Anomalous, turbulent-linked transport between the plasma edge and the core is also significant in fusion plasma physics. Heat pulse experiments, which involve strongly nonlinear localised perturbation of the plasma, probe the character of anomalous transport in both Tokamaks and Stellarators. In this thesis, we interpret the zonal ow-turbulence interactions in terms of the Lotka-Volterra model, which is derived in ecology and is widely utilized in many fields of science. We discover a novel limit cycle manifold for the plasma state as characterised by micro-scale drift wave turbulence, the electron temperature gradient and the energy of meso-scale structures such as zonal flows. In fusion experiments, an apparent limit cycle manifold called the I-phase has been found in many Tokamaks during L-H transitions. We investigate the possible links between this phenomenology and our model, and also report transitions between different confinement regimes in the model. Finally, we describe heat pulse propagation experiments in Large Helical Device(LHD), which is a Stellarator, in terms of a new model for anomalous transport phenomena from the plasma edge to the core.
12
Bandmann, Nina. "Rational and combinatorial genetic engineering approaches for improved recombinant protein production and purification." Doctoral thesis, Stockholm : Bioteknologi, Kungliga Tekniska högskolan, 2007. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-4318.
Full text
13
Ameyaw, Daniel Adofo [Verfasser], and Dirk [Akademischer Betreuer] Söffker. "New parametric evaluation and fusion strategy for vibration diagnosis systems and classification approaches applied to machine learning and computer vision systems / Daniel Adofo Ameyaw ; Betreuer: Dirk Söffker." Duisburg, 2020. http://d-nb.info/1218465220/34.
Full text
14
Bogner, Pamela [Verfasser]. "Generation of recombinant antibody fragments specific formurine mesangial cells : functionalization of highly specific fusion proteins for diagnostic approaches and the development of a murine mesangioproliferative glomerulonephritis disease models / Pamela Bogner." Aachen : Hochschulbibliothek der Rheinisch-Westfälischen Technischen Hochschule Aachen, 2015. http://d-nb.info/1066813574/34.
Full text
15
Alqasrawi, Yousef T. N. "Natural scene classification, annotation and retrieval : developing different approaches for semantic scene modelling based on Bag of Visual Words." Thesis, University of Bradford, 2012. http://hdl.handle.net/10454/5523.
Full textAbstract:
With the availability of inexpensive hardware and software, digital imaging has become an important medium of communication in our daily lives. A huge amount of digital images are being collected and become available through the internet and stored in various fields such as personal image collections, medical imaging, digital arts etc. Therefore, it is important to make sure that images are stored, searched and accessed in an efficient manner. The use of bag of visual words (BOW) model for modelling images based on local invariant features computed at interest point locations has become a standard choice for many computer vision tasks. Based on this promising model, this thesis investigates three main problems: natural scene classification, annotation and retrieval. Given an image, the task is to design a system that can determine to which class that image belongs to (classification), what semantic concepts it contain (annotation) and what images are most similar to (retrieval). This thesis contributes to scene classification by proposing a weighting approach, named keypoints density-based weighting method (KDW), to control the fusion of colour information and bag of visual words on spatial pyramid layout in a unified framework. Different configurations of BOW, integrated visual vocabularies and multiple image descriptors are investigated and analyzed. The proposed approaches are extensively evaluated over three well-known scene classification datasets with 6, 8 and 15 scene categories using 10-fold cross validation. The second contribution in this thesis, the scene annotation task, is to explore whether the integrated visual vocabularies generated for scene classification can be used to model the local semantic information of natural scenes. In this direction, image annotation is considered as a classification problem where images are partitioned into 10x10 fixed grid and each block, represented by BOW and different image descriptors, is classified into one of predefined semantic classes. An image is then represented by counting the percentage of every semantic concept detected in the image. Experimental results on 6 scene categories demonstrate the effectiveness of the proposed approach. Finally, this thesis further explores, with an extensive experimental work, the use of different configurations of the BOW for natural scene retrieval.
16
Lindh, Magnus. "Regionen och EU? : Uppfattningar och attityder till EU-relaterade frågor i Västsverige." Doctoral thesis, Karlstads universitet, Institutionen för samhälls- och kulturvetenskap, 2016. http://urn.kb.se/resolve?urn=urn:nbn:se:kau:diva-46958.
Full textAbstract:
This thesis explores perceptions and preferences on regional action in EU-related frameworks among regional actors in Western Sweden. Building upon the literature on Europeanisation and the Fusion approach, three dimensions of Europeanisation are clarified and explored– download, upload and crossload – and together with a set of five variables that constitute the Micro Fusion Framework; a comprehensive analytical tool is developed. The thesis analyses the intense debate among the members of West Sweden that took place from 2011 to 2013 that focused on how to functionally organise the regional office in Brussels in order to meet future challenges. Surprisingly, the members eventually decided to terminate their cooperation and close the jointly owned office in Brussels in spite of the fact that it has been widely regarded as successful and effective. Diverging perceptions and preferences is understood in terms of three positions on regional action; a download-, upload- and a coherent oriented position. Finally, the thesis presents the empirical findings and discusses in relation to three fusion scenarios, infusion, defusion and clustered fusion. In terms of Micro Fusion Framework, the dynamics shaping why West Sweden was finally regarded as a dysfunctional arena for regional action are explained by a shift of attention and action among regional actors in Western Sweden that led to pressure for further institutional adaptation in order to meet the demand of how ‘to get the best out of the EU’. Further, this redefinition of how to handle EU-affairs within the upload-oriented position was accompanied by positive attitudes towards the potential to bypass the state and thereby pursue regional priorities directly in Brussels given the compound nature of the EU. In contrast, those regional actors that are found to be more download-oriented often question the benefits of uploading activities in practice and advocate close relations to the state. A coherent oriented position recognises the importance of activities related to both of the vertical dimensions of Europeanisation.I avhandlingen studeras regionala aktörers uppfattningar och attityder till regionalt handlande i EU-relaterade frågor. För att hantera EU-frågor etableras ofta regionala representationskontor i Bryssel. Ett av de största och framgångsrikaste regionala kontoren i Bryssel var West Sweden som representerade västsvenska kommuner och regioners intressen i EU. År 2011 inleds en intern diskussion bland dess medlemmar om hur kontoret bör utvecklas för att möta nya utmaningar i en föränderlig omvärld. Diskussionerna är intensiva, och något överraskande beslutar dess medlemmar att lägga ned verksamheten ett par år senare. I avhandlingen analyseras diskussionen utifrån ett europeiseringsperspektiv. Med hjälp av en analysram som definierar tre dimensioner av europeiseringsprocesser identifieras tre olika positioner i diskussionen; en download-, upload- respektive sammanhållen position. Det kan vara frestande att förstå West Swedens nedläggning som ett uttryck för att subnationella aktörer ”drar sig tillbaka” och föredrar aktiviteter inom nationalstatens domäner. Avhandlingen argumenterar för att så är inte fallet. Nedläggningen av West Sweden förstås som en konsekvens av ökade spänningar mellan regionala aktörer som anammar ett download- respektive upload-orienterat förhållningssätt.
17
Yilmaz, Bulent. "Stochastic Approach To Fusion Dynamics." Phd thesis, METU, 2007. http://etd.lib.metu.edu.tr/upload/12608517/index.pdf.
Full textAbstract:
This doctoral study consists of two parts. In the first part, the quantum statistical effects on the formation process of the heavy ion fusion reactions have been investigated by using the c-number quantum Langevin equation approach. It has been shown that the quantum effects enhance the over-passing probability at low temperatures. In the second part, we have developed a simulation technique for the quantum noises which can be approximated by two-term exponential colored noise.
18
Saleem, Amina. "Image enhancement using a perceptual fusion approach." Paris 13, 2012. http://scbd-sto.univ-paris13.fr/intranet/edgalilee_th_2012_saleem.pdf.
Full textAbstract:
Due to limitations in image acquisition and transmission systems, image enhancement is established as an important area in image processing. Removing noise and blur, improving contrast to reveal details, coding artifact reduction and luminance adjustment are some image processing tasks that fall in the broader category of image enhancement operations. The problem of image enhancement is not a trivial task, since each image has its own characteristics and different image applications demand different enhancement requirements. It is therefore, hard to find a universal enhancement technique that would satisfy such diverse requirements. This justifies the presence of number of enhancement methods and ongoing research to find methods that can achieve different enhancement goals at the same time. Generally, image enhancement algorithms are developed to achieve some attributes of enhancement at the expense of some others. In our thesis, we develop a framework for fusion based image enhancement which is presented as a solution to the deficiencies of image enhancement algorithms. Fusion based methods for contrast enhancement, multi-focus image fusion and deblocking are developed with applications to tone mapping for HDR and natural enhancement of color imagesLa qualité de l’image perceptuelle depend essentiellement des conditions d’observation et d’acquisition, et les limitations des systems de numérisation et de transmission. On a souvent recours aux méthodes de restauration d’image et de réduction des artéfacts générés durant l’acquisition, le codage ou la transmission. Cependant, l’amélioration de la qualité d’image est un problème difficile en soi en raison de l’absence de critères objectifs bien établis pour juger des résultats. En effet, la qualité d’image est avant tout une notion subjective qui dépend de plusieurs paramètres psycho-visuels incontrôlables. De plus, chaque image a ses propres charactéristiques, et les solutions proposées dépendent aussi des applications visées. Par exemple, le réhaussement de contraste peut s’avérer efficace dans certaines zones de l’image, mais néfaste dans d’autres. Il est donc difficile de trouver une technique d’amélioration universelle qui puisse satisfaire les diverses exigences inhérentes au signal d’image. L’objectif de ce travail est de développer des méthodes basées sur une nouvelle approche où l’on fait appel à la fusion d’information et la modélisation des mécanismes de la perception visuelle. Dans ce cadre, nous proposons des méthodes de réhaussement de contraste, de filtrage et de bruit, de réductions des artefacts de codage et d’ajustement et d’équilibrage de tonalité chromatique dans le cas d’images, « HDRI ». Les performances des méthodes développées peuvent pallier les limitations des solutions de l’état de l’art et ouvrent ainsi de grandes perspectives
19
Forsyth, William A. "State and local intelligence fusion centers : an evaluative approach in modeling a state fusion center." Thesis, Monterey, Calif. : Springfield, Va. : Naval Postgraduate School ; Available from National Technical Information Service, 2005. http://library.nps.navy.mil/uhtbin/hyperion/05Sep%5FForsyth.pdf.
Full textAbstract:
Thesis (M.A. in Security Studies (Homeland Security and Defense)--Naval Postgraduate School, September 2005.Thesis Advisor(s): Robert Simeral. Includes bibliographical references (p. 91-92). Also available online.
20
Krieger, Evan. "Adaptive Fusion Approach for Multiple Feature Object Tracking." University of Dayton / OhioLINK, 2018. http://rave.ohiolink.edu/etdc/view?acc_num=dayton15435905735447.
Full text
21
Lewis, John Joseph. "A region-based approach to image and video fusion." Thesis, University of Bristol, 2008. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.492593.
Full textAbstract:
Image and video fusion is the process of combining information from multiple sensors that a single fused image or video is produced containing the useful information from all sources. The data from multiple sensors is often complimentary, either because the sensors are of different modalities, or because the data was recorded from different ositions or at different times. Image fusion has wide ranging applications, including surveillance, navigation, target classification and medicine.
22
Canga, Eduardo Fernandez. "A New approach to Image Fusion in the Compressed Domain." Thesis, University of Bristol, 2009. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.520168.
Full text
23
Manyika, James. "An information-theoretic approach to data fusion and sensor management." Thesis, University of Oxford, 1993. http://ora.ox.ac.uk/objects/uuid:6e6dd2a8-1ec0-4d39-8f8b-083289756a70.
Full textAbstract:
The use of multi-sensor systems entails a Data Fusion and Sensor Management requirement in order to optimize the use of resources and allow the synergistic operation of sensors. To date, data fusion and sensor management have largely been dealt with separately and primarily for centralized and hierarchical systems. Although work has recently been done in distributed and decentralized data fusion, very little of it has addressed sensor management. In decentralized systems, a consistent and coherent approach is essential and the ad hoc methods used in other systems become unsatisfactory. This thesis concerns the development of a unified approach to data fusion and sensor management in multi-sensor systems in general and decentralized systems in particular, within a single consistent information-theoretic framework. Our approach is based on considering information and its gain as the main goal of multi-sensor systems. We develop a probabilistic information update paradigm from which we derive directly architectures and algorithms for decentralized data fusion and, most importantly, address sensor management. Presented with several alternatives, the question of how to make decisions leading to the best sensing configuration or actions, defines the management problem. We discuss the issues in decentralized decision making and present a normative method for decentralized sensor management based on information as expected utility. We discuss several ways of realizing the solution culminating in an iterative method akin to bargaining for a general decentralized system. Underlying this is the need for a good sensor model detailing a sensor's physical operation and the phenomenological nature of measurements vis-a-vis the probabilistic information the sensor provides. Also, implicit in a sensor management problem is the existence of several sensing alternatives such as those provided by agile or multi-mode sensors. With our application in mind, we detail such a sensor model for a novel Tracking Sonar with precisely these capabilities making it ideal for managed data fusion. As an application, we consider vehicle navigation, specifically localization and map-building. Implementation is on the OxNav vehicle (JTR) which we are currently developing. The results show, firstly, how with managed data fusion, localization is greatly speeded up compared to previous published work and secondly, how synergistic operation such as sensor-feature assignments, hand-off and cueing can be realised decentrally. This implementation provides new ways of addressing vehicle navigation, while the theoretical results are applicable to a variety of multi-sensing problems.
24
Hoegh, Andrew B. "Predictive Model Fusion: A Modular Approach to Big, Unstructured Data." Diss., Virginia Tech, 2016. http://hdl.handle.net/10919/70921.
Full textAbstract:
Data sets of increasing size and complexity require new approaches for prediction as the sheer volume of data from disparate sources inhibits joint processing and modeling. Rather modular segmentation is required, in which a set of models process (potentially overlapping) partitions of the data to independently construct predictions. This framework enables individuals models to be tailored for specific selective superiorities without concern for existing models, which provides utility in cases of segmented expertise. However, a method for fusing predictions from the collection of models is required as models may be correlated. This work details optimal principles for fusing binary predictions from a collection of models to issue a joint prediction. An efficient algorithm is introduced and compared with off the shelf methods for binary prediction. This framework is then implemented in an applied setting to predict instances of civil unrest in Central and South America. Finally, model fusion principles of a spatiotemporal nature are developed to predict civil unrest. A novel multiscale modeling is used for efficient, scalable computation for combining a set of spatiotemporal predictions.Ph. D.
25
Locks, Stephanie Isabel. "General Bayesian approach for manufacturing equipment diagnostics using sensor fusion." Thesis, Georgia Institute of Technology, 2016. http://hdl.handle.net/1853/55036.
Full textAbstract:
Statistical analysis is used quite heavily in production operations. To use certain advanced statistical approaches such as Bayesian analysis, statistical models must be built. This thesis demonstrates the process of building the Bayesian models and addresses some of the classical limitations by presenting mathematical examples and proofs, by demonstrating the process with experimental and simulated implementations, and by completing basic analysis of the performance of the implemented models. From the analysis, it is shown that the performance of the Bayesian models is directly related to the amount of separation between the likelihood distributions that describe the behavior of the data features used to generate the multivariate Bayesian models. More specifically, the more features that had clear separation between the likelihood distributions for each possible condition, the more accurate the results were. This is shown to be true regardless of the quantity of data used to generate the model distributions during model building. In cases where distribution overlap is present, it is found that models performance become more consistent as the amount of data used to generate the models increases. In cases where distribution overlap is minimal, it is found that models performance become consistent within 4-6 data sets.
26
Chennupati, Om sai teja. "A structured approach to JPEG tampering detection using enhanced fusion algorithm." Thesis, Blekinge Tekniska Högskola, Institutionen för datavetenskap, 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:bth-21195.
Full text
27
Colling, Bethany R. "Blanket performance and radioactive waste of fusion reactors : a neutronics approach." Thesis, Lancaster University, 2016. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.730246.
Full textAbstract:
Fusion energy for use in power plants is a continually developing area and many of the related parameters are not yet fixed. The investigation of fusion neutronics and development of computational approaches for assessment is imperative in the road to commercial realisation of fusion power. This research has explored blanket performance, including tritium breeding and the shielding requirements, and assessed radioactive waste, utilising the 3-D Monte Carlo transport code MCNP, and the activation inventory code FISPACT. The performance of some solid and liquid breeder materials has been compared with regards to tritium breeding, energy production and shielding. In the case of novel spherical tokamak concepts, that make use of high temperature superconducting magnets and have no inboard blanket, scoping studies have been performed to investigate the impact of shielding requirements on how small the tokamak can be. Fusion power plants will not produce high level waste, as seen in nuclear fission plants, however the components and structures will become active as a result of interactions with high energy neutrons. A suitable radioactive waste management plan will be required in order to deal with this material appropriately, with an aim to recycle or clear from regulatory control all materials 100 years after shutdown. The study indicates that through suitable material selection and the use of component dismantling the requirement could potentially be satisfied. In terms of computational methods, the neutron flux averaging has been assessed throughout the work and has shown in neutronics estimates to produce some substantial differences. The recently developed unstructured mesh approach to neutronics modelling has been explored and the potential use for more accurate radioactive waste inventory calculations. Although the analysis and comparison shows promising results, it still requires significant development and improvement in the work flow to create a robust neutronic analysis method.
28
Wu, Michael. "Transfer Learning Approach to Powder Bed Fusion Additive Manufacturing Defect Detection." DigitalCommons@CalPoly, 2021. https://digitalcommons.calpoly.edu/theses/2324.
Full textAbstract:
Laser powder bed fusion (LPBF) remains a predominately open-loop additive manufacturing process with minimal in-situ quality and process control. Some machines feature optical monitoring systems but lack automated analytical capabilities for real-time defect detection. Recent advances in machine learning (ML) and convolutional neural networks (CNN) present compelling solutions to analyze images in real-time and to develop in-situ monitoring.
Approximately 30,000 selective laser melting (SLM) build images from 31 previous builds are gathered and labeled as either “okay” or “defect”. Then, 14 open-sourced CNN were trained using transfer learning to classify the SLM build images. These models were evaluated by F1 score and down selected to the top 3 models. The top 3 models were then retrained and evaluated using Dietterich’s 5x2 cross-validation and compared with pairwise student t-tests. The pairwise t-test results show no statistically significant difference in performance between VGG- 19, Xception, and InceptionResNet. All models are strong candidates for future development and refinement.
Additional work addresses the entire model development process and establishes a foundation for future work. Collaborations with computer science students has produced an image pre-processing program to enhance as-taken SLM images. Other outcomes include initial work to overlay CAD layer images and preliminary hardware integration plan for the SLM machine. The results from this work have demonstrated the potential of an optical layer-wise image defect detection system when paired with a CNN.
29
Bak, Poul Erik. "A dynamical systems approach to experimentally observed edge localized modes in JET." Thesis, Imperial College London, 1998. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.287197.
Full text
30
Koh, Leonard Phin-Liong. "A neural network approach to multisensor data fusion for vessel traffic services." Thesis, Monterey, Calif. : Springfield, Va. : Naval Postgraduate School ; Available from National Technical Information Service, 1995. http://handle.dtic.mil/100.2/ADA294251.
Full text
31
Scott, Dale Charles. "A data fusion approach to verifying hand-written signatures on bank cheques." Thesis, National Library of Canada = Bibliothèque nationale du Canada, 1998. http://www.collectionscanada.ca/obj/s4/f2/dsk2/tape17/PQDD_0027/MQ33271.pdf.
Full text
32
Humphries, William Arthur. "Characterising fusion proteins for an ADEPT approach to colorectal and gastric cancer." Thesis, University of Kent, 2013. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.655202.
Full textAbstract:
Following breast and lung cancer, colorectal cancer is the third most common cancer seen in the UK. In Z008, 39,991 cases of large bowel cancer were registered, and colorectal cancer remains the second most common cause of death from cancer behind lung cancer. Carcinoembryonic antigen (CEA) was first identified in 1965 in human colon cancer tissue extracts. Since then it has been found being expressed in other cancer patients, such as those with pancreatic, lung and breast carcinoma. Although it has been identified in other cancer types, it is for its role in gastric cancer that we are currently investigating the use of this antigen for a novel targeted chemotherapeutic method known as Antibody-Directed Enzyme Prodrug Therapy (ADEPT). ADEPT is a technique that delivers a cytotoxic agent specifically to tumour sites. An antibodyenzyme complex (fusion protein) is administered to the patient and after allowing sufficient time a clearing agent is added to remove any unbound fusion protein. A prodrug is then administered and in the presence of the fusion protein, the prodrug becomes a cytotoxic agent able to kill tumour cells in the vicinity of the tumour giving more specificity of action than traditional cytotoxic agents. ADEPT has been trialled clinically before with mixed results, however this project is for an "enhanced-ADEPT" system, an idea that has received EUROSTARS funding. As with previous versions of ADEPT ScFv (Single chain variable Fragment) fusion protein fusion proteins are to be used. These fusion proteins have had key features re-designed by molecular biological methods in order to provide step changes in performance over previous ADEPT systems. To generate the fusion proteins we are investigated, we used the yeast expression system Pichia pink. The yeast expression host is an ideal tool to manufacture fusion proteins. The Pichia pink expression system is capable of post-translational modification of proteins and can secrete completed fusion proteins into the growth media, allowing for a simple method of harvesting and purification. The Pichia pink system also gives some control over glycosylation and limiting proteolysis. The aims of the project were to generate and optimise expression of anti CEA fusion protein using the Pichia pink system; and characterise anti CEA fusion protein, using a variety of experimental techniques including flow cytometry, confocal microscopy, biolayer interferometry and cytotoxicity assays. Two novel ScFv fusion protein's were expressed in Pichia pink strain 1. Different production batches of these were shown to have variable enzyme activity as determined by a methotrexate hydrolysis assay, between 0 and 115U jmL. Specific binding of these fusion proteins to CEA was observed using biolayer interferometry, with average KD values in the low nanomolar range. While no binding of HEKZ93, a CEA negative cell line was observed, fusion proteins were found to adhere to both LoVo and MKN45 CEA positive cell lines, via flow cytometry and confocal microscopy. The fusion proteins were shown, in the presence of prodrug to cause the death of MKN45 cells in a modified clonogenic assay, while HEKZ93 cells remained largely unaffected. The CEA positive cell line LoVo however exhibited resistance to the drug. Further testing of these fusion proteins is certainly recommended.
33
Devine, Timothy Andrew. "Fusing Modeling and Testing to Enhance Environmental Testing Approaches." Thesis, Virginia Tech, 2019. http://hdl.handle.net/10919/101685.
Full textAbstract:
A proper understanding of the dynamics of a mechanical system is crucial to ensure the highest levels of performance. The understanding is frequently determined through modeling and testing of components. Modeling provides a cost effective method for rapidly developing a knowledge of the system, however the model is incapable of accounting for fluctuations that occur in physical spaces. Testing, when performed properly, provides a near exact understanding of how a pat or assembly functions, however can be expensive both fiscally and temporally.
Often, practitioners of the two disciplines work in parallel, never bothering to intersect with the other group. Further advancement into ways to fuse modeling and testing together is able to produce a more comprehensive understanding of dynamic systems while remaining inexpensive in terms of computation, financial cost, and time. Due to this, the goal of the presented work is to develop ways to merge the two branches to include test data in models for operational systems. This is done through a series of analytical and experimental tasks examining the boundary conditions of various systems.
The first venue explored was an attempt at modeling unknown boundary conditions from an operational environment by modeling the same system in known configurations using a controlled environment, such as what is seen in a laboratory test. An analytical beam was studied under applied environmental loading with grounding stiffnesses added to simulate an operational condition and the response was attempted to be matched by a free boundaries beam with a reduced number of excitation points. Due to the properties of the inverse problem approach taken, the response between the two systems matched at control locations, however at non-control locations the responses showed a large degree of variation. From the mismatch in mechanical impedance, it is apparent that improperly representing boundary conditions can have drastic effects on the accuracy of models and recreational tests.
With the progression now directed towards modeling and testing of boundary conditions, methods were explored to combine the two approaches working together in harmony. The second portion of this work focuses on modeling an unknown boundary connection using a collection of similar testable boundary conditions to parametrically interpolate to the unknown configuration. This was done by using data driven models of the known systems as the interpolating functions, with system boundary stiffness being the varied parameter. This approach yielded near identical parametric model response to the original system response in analytical systems and showed some early signs of promise for an experimental beam.
After the two conducted studies, the potential for extending a parametric data driven model approach to other systems is discussed. In addition to this, improvements to the approach are discussed as well as the benefits it brings.Master of Science
34
Tanriverdi, Vedat. "Nuclear Dissipative Dynamics In Langevin Approach." Master's thesis, METU, 2004. http://etd.lib.metu.edu.tr/upload/12605034/index.pdf.
Full textAbstract:
In this thesis Langevin approach is applied to analyze the nuclear
dissipative dynamics in fission and fusion reactions. In these
investigations, the nuclear elongation coordinate and the
corresponding momentum are chosen as collective variables. By
considering changes in these variables the decay rate of fission
and the formation probability of fusion for heavy ion reactions
are calculated. These calculations are performed using simulation
techniques and the results thus obtained are compared with the
corresponding results of analytic solutions.
35
Russell, Jared S. "An optimization approach to plant-controller co-design /." Online version of thesis, 2009. http://hdl.handle.net/1850/10769.
Full text
36
Stein, Kathryn Kreimborg. "Sperm proteins involved in sperm-egg fusion : a cell biological and proteomic approach /." For electronic version search Digital dissertations database. Restricted to UC campuses. Access is free to UC campus dissertations, 2005. http://uclibs.org/PID/11984.
Full text
37
Egger, Sean Robert. "A Turbo Approach to Distributed Acoustic Detection and Estimation." Thesis, Virginia Tech, 2009. http://hdl.handle.net/10919/35866.
Full textAbstract:
Networked, multi-sensor array systems have proven to be advantageous in the
sensor world. A large amount of research has been conducted with these systems, with a
main interest in data fusion. Intelligently processing the large amounts of data collected
by these systems is required in order to fully utilize the benefits of a multi-sensor array
system. A robust but flexible simulation environment would provide a platform for
accurately comparing current and future data fusion theories.
This thesis proposes a simulator model for testing fusion theories for these acoustic
multi-sensor networks. An iterative, lossless data fusion algorithm was presented as the
model for simulation development. The arrangement and orientation of objects in the
simulation environment, as well as most other system parameters are defined by the user
before the simulation runs. The sensor data, including noise, is generated at the
appropriate time delay and propagation loss before being processed by a delay and sum
beamformer and a matched filter. The resulting range-Doppler maps are modified to
probability density functions, and translated to a single point of reference. The data is
then combined into a single world model.
An iterative process is used to filter out false targets and amplify true target
detections. Data is fused from each multi-sensor array and from each simulation run.
Target amplitudes are gained if they are present in all combined world models, and are
otherwise reduced. This thesis presents the results of the fusion algorithm used, including
multiple iterations, to prove the algorithms effectiveness.Master of Science
38
Azuaje, Francisco Javier. "An unsupervised neural learning approach to retrieval strategies for case-based reasoning and decision support." Thesis, University of Ulster, 2000. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.311877.
Full text
39
Ruthenberg, Thomas M. "Data fusion algorithm for the Vessel Traffic Services system : a fuzzy associative system approach /." Thesis, Monterey, Calif. : Springfield, Va. : Naval Postgraduate School ; Available from National Technical Information Service, 1995. http://handle.dtic.mil/100.2/ADA300458.
Full text
40
Keating, Jacqueline M. "The Inevitable Fusion: A Mixed-Methods Sociological Approach to Comprehensive Kodiak Bear Viewing Management." DigitalCommons@USU, 2017. https://digitalcommons.usu.edu/etd/5659.
Full textAbstract:
The Kodiak National Wildlife Refuge is home to one of the highest concentrations of brown bears in Alaska. As the public demand for bear viewing opportunities continues to increase, managers are faced with the challenge of accommodating this new kind of visitor use on a refuge that was traditionally managed for the sustainable hunting of bears. To inform the public use management planning process, the Kodiak Refuge allocated funding to support social science research that objectively assessed the current nature of bear viewing opportunities and the factors that influence the quality of those opportunities. Ecologist Aldo Leopold claimed that the outstanding advance of modern ecology would be the “inevitable fusion” of the social and natural sciences. Therefore, a conjoint constitution framework inspired by Freudenburg, Frickel, and Gramling (1995) enabled this study to examine the active interplay of social and environmental factors in a bear viewing experience.
Two seasons of research were conducted in partnership with Utah State University. The first season employed qualitative research methods to conduct detailed interviews with a wide variety of bear viewing stakeholders in Kodiak. This process informed the creation of a survey measurement tool that was administered to bear viewers the following summer. Survey results suggest that seeing a larger number of bears and seeing big bears are trip characteristics associated with higher satisfaction among visitors, while closer proximity to bears is associated with learning more about bear behavior.
The environmental sociology principle of “conjoint constitution” guided both phases of research by helping to examine how social and physical factors interact with one another to create trip outcomes. Just as there are ongoing biological inventory and monitoring processes that inform refuge management, there should be inventory and monitoring of human activity and the fluent sociological factors influencing the nature of that activity. As the Kodiak Refuge continues its public use planning process, the ongoing integration of both biological and social science data will be critical.
41
Armenis, Dimitris. "Self-organized maps for behavioural fusion : a CANopen approach to distributed intelligent real-time control." Thesis, University of Liverpool, 2005. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.428203.
Full text
42
Rutkowski, Adam J. "A BIOLOGICALLY-INSPIRED SENSOR FUSION APPROACH TO TRACKING A WIND-BORNE ODOR IN THREE DIMENSIONS." Case Western Reserve University School of Graduate Studies / OhioLINK, 2008. http://rave.ohiolink.edu/etdc/view?acc_num=case1196447143.
Full text
43
Xiao, Xiangyu. "A Multiple Sensors Approach to Wood Defect Detection." Diss., Virginia Tech, 1998. http://hdl.handle.net/10919/11145.
Full textAbstract:
In the forest products manufacturing industry, recent price increases in the cost of high-quality lumber together with the reduced availability of this resource have forced manufacturers to utilize lower grade hardwood lumber in their manufacturing operations. This use of low quality lumber means that the labor involved in converting this lumber to usable parts is also increased because it takes more time to remove the additional defects that occur in the lower grade material. Simultaneously, labor costs have gone up and availability of skilled workers capable of getting a high yield of usable parts has markedly decreased. To face this increasingly complex and competitive environment, the industry has a critical need for efficient and cost-effective new processing equipment that can replace human operators who locate and identify defects that need to be removed in lumber and then remove these defects when cutting the lumber into rough parts. This human inspection process is laborious, inconsistent and subjective in nature due to the demands of making decisions very rapidly in a noisy and tiring environment. Hence, an automatic sawing system that could remove defects in lumber while creating maximum yield, offers significant opportunities for increasing profits of this industry. The difficult part in designing an automatic sawing system is creating an automatic inspection system that can detect critical features in wood that affect the quality of the rough parts. Many automatic inspection systems have been proposed and studied for the inspection of wood or wood products. But, most of these systems utilize a single sensing modality, e.g., a single optical sensor or an X-ray imaging system. These systems cannot detect all critical defects in wood.
This research work reported in this dissertation is the first aimed at creating a vision system utilizes three imaging modalities: a color imaging system, a laser range profiling system and an X-ray imaging system. The objective of in designing this vision system is to detect and identify: 1) surface features such as knots, splits, stains; 2) geometry features such as wane, thin board; and 3) internal features such as voids, knots. The laser range profiling system is used to locate and identify geometry features. The X-ray imaging system is primarily used to detect features such as knots, splits and interior voids. The color imaging system is mainly employed to identify surface features.
In this vision system a number of methodologies are used to improve processing speed and identification accuracy. The images from different sensing modalities are analyzed in a special order to offset the larger amount of image data that comes from the multiple sensors and that must be analyzed. The analysis of laser image is performed first. It is used to find defects that have insufficient thickness. These defects are then removed from consideration in the subsequent analysis of the X-ray image. Removing these defects from consideration in the analysis of the X-ray image not only improves the accuracy of detecting and identifying defects but also reduces the amount of time needed to analyze the X-ray image. Similarly, defect areas such as knot and mineral streak that are found in the analysis of the X-ray image are removed from consideration in the analysis of the color image. A fuzzy logic algorithm -- the approaching degree method-- is used to assign defect labels. The fuzzy logic approach is used to mimic human behavior in identifying defects in hardwood lumber.
The initial results obtained from this vision system demonstrate the feasibility of locating and identifying all the major defects that occur in hardwood lumber. This was even true during the initial hardware development phase when only images of unsatisfactory quality from a limited lumber of samples were available. The vision system is capable of locating and identifying defects at the production speed of two linear feet per second that is typical in most hardwood secondary manufacturing plants. This vision system software was designed to run on a relative slow computer (200 MHz Pentium processor) with aid of special image processing hardware, i.e., the MORRPH board that was also designed at Virginia Tech.Ph. D.
44
Dar, Iqbal Mahmud. "An intelligent sensor fusion approach to pattern recognition with an application to bond validation of surface-mount components." Diss., Georgia Institute of Technology, 1996. http://hdl.handle.net/1853/15717.
Full text
45
Al-Mahri, Abdullah Khzam. "JERS-1 SAR and Landsat-5 TM image data fusion : an application approach for lithological mapping." Thesis, University College London (University of London), 1999. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.419943.
Full text
46
Edelstein, Mark R. "Examining the prevalence of persistent postsurgical pain in pediatric spinal fusion surgery patients: a biopsychosocial approach." Thesis, Boston University, 2013. https://hdl.handle.net/2144/12094.
Full textAbstract:
Thesis (M.A.)--Boston UniversityObjective: Despite extensive literature on chronic pain in surgical and nonsurgical adult patient populations and in the pediatric nonsurgical patient population, the acute to chronic postsurgical pain transition in children has been a largely neglected area of research. The purpose of this study was to examine the prevalence of persistent postsurgical pain in patients with adolescent idiopathic scoliosis who undergo spinal fusion surgery and to explore baseline differences between patients in varying longitudinal pain trajectories. Methods: The Scoliosis Research Society Questionnaire-30, which includes pain, self- image, mental health, and activity subscales, was administered to 219 patients at a large Northeast children’s hospital preoperatively and at one- and two-years postoperatively through their involvement in the Prospective Pediatric Scoliosis Study. A subset of these patients (n=77) also completed follow-up data at five-years post-surgery. Pain among this sample (in the past six months, in the past month, and at rest) was examined at each of the time points. Longitudinal pain trajectories were identified using the SAS PROC TRAJ procedure, and trajectory groups were compared for baseline differences in age, self-image, and mental health functioning through one-way analysis of variance and post- hoc analyses. Results: Preoperative pain was high in this sample, with 36% of patients prior to surgery reporting pain in the past month. The number of patients reporting pain in the past month postoperatively fell to 13% at one-year post-surgery but increased to 17% and 20% respectively at two- and five-years follow-up. A five-trajectory model emerged with a “no pain” group, a “pain improvement” group, a “short-term pain” group, a “delayed pain” group, and a “high pain” group with significant differences in baseline age (p<.01), self-image (p<.01), and mental health functioning (p<.01) found across groups. Conclusions: The study suggests that pediatric persistent postsurgical pain is potentially a significant health concern. This study also provides preliminary evidence that baseline psychosocial factors may contribute to patients’ longitudinal pain experiences postoperatively. Efforts should be taken to better understand the role that these predictors play in the emergence of persistent postsurgical pain in pediatric surgical patients and to explore how biological factors affect somatosensory phenotypes in this patient population.
47
Anzid, Hanan. "Fusion de données multimodales par combinaison de l’incertain et de modèles de perception." Thesis, Bourgogne Franche-Comté, 2019. http://www.theses.fr/2019UBFCK046.
Full textAbstract:
L’idée générale consiste à utiliser conjointement des informations multiples hétérogènes portant sur le même problème entachées d’imperfections et provenant de plusieurs sources afin d’améliorer la connaissance d’une situation donnée. La visualisation adaptée des images pour l’aide à la prise de décision en utilisant les informations perceptuelles porté par les cartes de saillanceThe general idea is to use together heterogeneous multiple information on the same problem tainted by imperfections and coming from several sources in order to improve the knowledge of a given situation. Appropriate visualization of the images to aid in decision making using the perceptual information carried by the salience maps
48
Wolf, Maik. "Effizienzen und europäische Zusammenschlusskontrolle die wettbewerbsrechtliche Integrationsfähigkeit einer "efficiency defence" am Beispiel horizontaler Zusammenschlüsse ; zugleich ein Beitrag zur kritischen Präzisierung eines "more economic approach"." Baden-Baden Nomos, 2007. http://d-nb.info/993924107/04.
Full text
49
Leishman, Robert C. "A Vision-Based Relative Navigation Approach for Autonomous Multirotor Aircraft." BYU ScholarsArchive, 2013. https://scholarsarchive.byu.edu/etd/3784.
Full textAbstract:
Autonomous flight in unstructured, confined, and unknown GPS-denied environments is a challenging problem. Solutions could be tremendously beneficial for scenarios that require information about areas that are difficult to access and that present a great amount of risk. The goal of this research is to develop a new framework that enables improved solutions to this problem and to validate the approach with experiments using a hardware prototype. In Chapter 2 we examine the consequences and practical aspects of using an improved dynamic model for multirotor state estimation, using only IMU measurements. The improved model correctly explains the measurements available from the accelerometers on a multirotor. We provide hardware results demonstrating the improved attitude, velocity and even position estimates that can be achieved through the use of this model. We propose a new architecture to simplify some of the challenges that constrain GPS-denied aerial flight in Chapter 3. At the core, the approach combines visual graph-SLAM with a multiplicative extended Kalman filter (MEKF). More importantly, we depart from the common practice of estimating global states and instead keep the position and yaw states of the MEKF relative to the current node in the map. This relative navigation approach provides a tremendous benefit compared to maintaining estimates with respect to a single global coordinate frame. We discuss the architecture of this new system and provide important details for each component. We verify the approach with goal-directed autonomous flight-test results. The MEKF is the basis of the new relative navigation approach and is detailed in Chapter 4. We derive the relative filter and show how the states must be augmented and marginalized each time a new node is declared. The relative estimation approach is verified using hardware flight test results accompanied by comparisons to motion capture truth. Additionally, flight results with estimates in the control loop are provided. We believe that the relative, vision-based framework described in this work is an important step in furthering the capabilities of indoor aerial navigation in confined, unknown environments. Current approaches incur challenging problems by requiring globally referenced states. Utilizinga relative approach allows more flexibility as the critical, real-time processes of localization and control do not depend on computationally-demanding optimization and loop-closure processes.
50
Vallet, Alexandra. "Hydrodynamic modelling of the shock ignition scheme for inertial confinement fusion." Thesis, Bordeaux, 2014. http://www.theses.fr/2014BORD0214/document.
Full textAbstract:
Le schéma d'allumage par choc pour la fusion par confinement inertiel utilise une impulsion laser intense à la fin d'une phase d'assemblage de combustible. Les paramètres clefs de ce schéma sont la génération d'une haute pression d'ablation, l'amplification de la pression du choc généré par un facteur supérieur à cent et le couplage du choc avec le point chaud de la cible. Dans cette thèse, de nouveaux modèles semi-analytiques sont développés afin de décrire le choc d'allumage depuis sa génération jusqu'à l'allumage du combustible. Tout d'abord, un choc sphérique convergent dans le coeur pré-chauffé de la cible est décrit. Le modèle est obtenu par perturbation de la solution auto-semblable de Guderley en tenant compte du nombre de Mach du choc élevé mais fini. La correction d'ordre un tient compte de l'effet de la force du choc. Un critère d'allumage analytique est exprimé en fonction de la densité surfacique du point chaud et de la pression du choc d'allumage. Le seuil d'allumage est plus élevé pour un nombre de Mach faible. Il est montré que la pression minimale du choc, lorsqu'il entre dans le coeur de la cible, est de 20Gbar. La dynamique du choc dans la coquille en implosion est ensuite analysée. Le choc se propage dans un milieu non inertiel avec un fort gradient de pression et une augmentation temporelle générale de la pression. La pression du choc est amplifiée plus encore durant la collision avec une onde de choc divergente provenant de la phase d'assemblage. Les modèles analytiques développés permettent une description de la pression et de la force du choc dans une simulation typique de l'allumage par choc. Il est démontré que, dans le cas d'une cible HiPER, une pression initiale du choc de l'ordre de 300 Mbar dans la zone d'ablation est nécessaire. Il est proposé une analyse des expériences sur la génération de chocs forts avec l'installation laser OMEGA. Il est montré qu'une pression du choc proche de 300Mbar est atteinte près de la zone d'ablation avec une intensité laser absorbée de l'ordre de 2 X 10(15) W.cm-2 et une longueur d'onde de 351 nm. Cette valeur de la pression est deux fois plus importante que la valeur attendue en considérant une absorption collisionnelle de l'énergie laser. Cette importante différence est expliquée par la contribution d'électrons supra-thermiques générés durant l'interaction laser/plasma dans la couronne. Les modèles analytiques proposés permettent une optimisation de l'allumage par choc lorsque les paramètres de la phase d'assemblage, sont pris en compte. Les diverses approches analytiques, numériques et expérimentales sont cohérentes entre-ellesThe shock ignition concept in inertial confinement fusion uses an intense power spike at the end of an assembly laser pulse. the key feature of shock ignition are the generation of a high ablation pressure, the shock pressure amplification by at least a factor of a hundred in the cold fuel shell and the shock coupling to the hot-spot. in this theses, new semi-analytical hydrodynamic models are developed to describe the ignitor shock from its generation up to the moment of fuel ignition. A model is developed to describe a spherical concerging shock wave in a pre-heated hotspot. The self-similar solution developed by Guderley is perturbed over the shock Mach number Ms >>1. The first order correction accounts for the effects of the shock strength. An analytical ignition criterion is defined in terms of the shock strength ans th hot-spot areal density. The ignition threshold is higher when the initial Mach number of the shock is lower. A minimal shock pressure of 20 Gbar is needed when it enters the hot-spot. The shock dynamics in the imploding shell is the analyzed. The shock is propagating into a non inertial medium with a high radial pressure gradient and an averall pressure increase with time. The collision with a returning shock coming from the assembly phase enhances further the ignitor shock pressure. The analytica theory allows to des cribe the shock pressure and strength evolution in a typical shock ignition implosion. It is demonstrated that, in the case of the HiPER target design, a generation shock pressure near the ablation zone on the order of 300-400 Mbar is needed. An analysis of experiments on the strong shock generation performed on the OMEGA laser facility is presented. It is sown that a shock presssure close to 300 Mbar near the ablation zone has been reached with an absorbed laser intensity up to 2 x 10(15) W:cm-2 and a laser wavelength of 351 nm. This value is two times higher than the one expected from collisional laser absorption only. That significant pressure enhancement is explained by contribution of hot-electrons generated by non-linear laser/plasma interaction in the corona. The proposed analytical models allow to optimize the shock ignition scheme, including the inuence of the implosion parameters. Analytical, numerical and experimental results are mutualy consistent