To see the other types of publications on this topic, follow the link: Prediction Motion.
Dissertations / Theses on the topic 'Prediction Motion'
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 'Prediction Motion.'
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
Lee, Suk Jin. "PREDICTION OF RESPIRATORY MOTION." VCU Scholars Compass, 2012. http://scholarscompass.vcu.edu/etd/336.
Full textAbstract:
Radiation therapy is a cancer treatment method that employs high-energy radiation beams to destroy cancer cells by damaging the ability of these cells to reproduce. Thoracic and abdominal tumors may change their positions during respiration by as much as three centimeters during radiation treatment. The prediction of respiratory motion has become an important research area because respiratory motion severely affects precise radiation dose delivery. This study describes recent radiotherapy technologies including tools for measuring target position during radiotherapy and tracking-based delivery systems. In the first part of our study we review three prediction approaches of respiratory motion, i.e., model-based methods, model-free heuristic learning algorithms, and hybrid methods. In the second part of our work we propose respiratory motion estimation with hybrid implementation of extended Kalman filter. The proposed method uses the recurrent neural network as the role of the predictor and the extended Kalman filter as the role of the corrector. In the third part of our work we further extend our research work to present customized prediction of respiratory motion with clustering from multiple patient interactions. For the customized prediction we construct the clustering based on breathing patterns of multiple patients using the feature selection metrics that are composed of a variety of breathing features. In the fourth part of our work we retrospectively categorize breathing data into several classes and propose a new approach to detect irregular breathing patterns using neural networks. We have evaluated the proposed new algorithm by comparing the prediction overshoot and the tracking estimation value. The experimental results of 448 patients’ breathing patterns validated the proposed irregular breathing classifier.
2
Chibisov, Dmitry. "Design of algorithms for motion planning and motion prediction." kostenfrei, 2009. https://mediatum2.ub.tum.de/node?id=958521.
Full text
3
Ranvik, Arne. "Slip Prediction Based on Manipulator Motion." Thesis, Norges teknisk-naturvitenskapelige universitet, Institutt for teknisk kybernetikk, 2014. http://urn.kb.se/resolve?urn=urn:nbn:no:ntnu:diva-26705.
Full textAbstract:
Predicting slip during robotic manipulation is of interest for a variety of appli-cations. Especially applications where weak grasps are applied. In this thesis, amodel for predicting slip for a two fingered grasping scenario is considered. Otherthan model parameters, the only measurements or sensor information assumed isof the manipulator joints. Soft objects that deform substantially under appliedforces are especially interesting in terms of frictional behaviour. A soft ball wasused as a test object and parameters for friction and deformation was experimen-tally determined. By grasping and moving the ball with an industrial manipulator,slip and object loss was induced in order to compare these observations againstmodel predictions.It was found that the models prediction of slip was reasonable when compared tothe observations. However, the model could not be fully tested and validated be-cause the simple geometry of the test object did not excite any frictional behaviourfrom the soft characteristics.
4
Braun, Jennifer L. "The Prediction of Motion Sickness Through People's Perception of Postural Motion." Miami University / OhioLINK, 2012. http://rave.ohiolink.edu/etdc/view?acc_num=miami1353943941.
Full text
5
Wiest, Jürgen [Verfasser]. "Statistical long-term motion prediction / Jürgen Wiest." Ulm : Universität Ulm, 2017. http://d-nb.info/1128728931/34.
Full text
6
Chung, Hing-yip Ronald, and 鍾興業. "Fast motion estimation with search center prediction." Thesis, The University of Hong Kong (Pokfulam, Hong Kong), 1999. http://hub.hku.hk/bib/B31220721.
Full text
7
Tavakoli, Behrooz. "Prediction of Strong Ground Motion and Hazard Uncertainties." Doctoral thesis, Uppsala University, Department of Earth Sciences, 2003. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-3535.
Full textAbstract:
<p>The purpose of this thesis is to provide a detailed description of recent methods and scientific basis for characterizing earthquake sources within a certain region with distinct tectonic environments. The focus will be on those characteristics that are most significant to the ground-shaking hazard and on how we can incorporate our current knowledge into hazard analyses for engineering design purposes. I treat two particular geographical areas where I think current hazard analysis methods are in need of significant improvement, and suggest some approaches that have proven to be effective in past applications elsewhere. A combined hazard procedure is used to estimate seismicity in <i>northern Central America</i>, where there appear to be four tectonic environments for modeling the seismogenic sources and in <i>Iran</i>, where the large earthquakes usually occur on known faults. A preferred seismic hazard model for northern Central America and the western Caribbean plate based on earthquake catalogs, geodetic measurements, and geological information is presented. I used the widely practiced method of relating seismicity data to geological data to assess the various seismic hazard parameters and test parameter sensitivities. </p><p>The sensitivity and overall uncertainty in peak ground acceleration (PGA) estimates are calculated for northwestern Iran by using a <i>specific randomized blocks design</i>. A Monte Carlo approach is utilized to evaluate the ground motion hazard and its uncertainties in northern Central America. A set of new seismic hazard maps, exhibiting probabilistic values of peak ground acceleration (PGA) with 50%, 10%, and 5% probabilities of exceedance (PE) in 50 years, is presented for the area of relevance. <i>Disaggregation of seismic hazard</i> is carried out for cities of San Salvador and Guatemala by using a spatial distribution of epicenters around these sites to select design ground motion for seismic risk decisions. </p><p>In conclusion, consideration of the effect of parameters such as seismic moment, fault rupture, rupture directivity and stress drop are strongly recommended in estimating the near field ground motions. The rupture process of the 2002 Changureh earthquake (<i>M</i><i>w</i> = 6.5), Iran, was analyzed by using the<i> empirical Green’s function (EGF) method</i>. This method simulates strong ground motions for future large earthquakes at particular sites where no empirical data are available.</p>
8
Fromreide, Mads. "Motion Prediction by Optimal Paths Through Disordered Landscapes." Thesis, Norges teknisk-naturvitenskapelige universitet, Institutt for fysikk, 2014. http://urn.kb.se/resolve?urn=urn:nbn:no:ntnu:diva-24781.
Full textAbstract:
The ability to navigate safely and efficiently through a given landscape is relevant for any intelligent moving object. Examples range from robotic science and traffic analysis to the behavior within an ecosystem. Through this thesis, methods for finding traffic patterns and predicting future motion, have been constructed based on theory of optimal paths. The algorithms are applied to maritime traffic, in terms of recorded vessel coordinates. \newline By considering the structure of a given traffic situation as a disordered energy landscape, one can define optimal routes within the area. An algorithm for finding hierarchies of optimal paths in a disordered energy landscape is implemented. The algorithms are used in two settings, one for detecting patterns of motion within a given area, and a method for estimating single vessel trajectories. The results found in the thesis, show that the methods have great potential for analyzing traffic patterns and predict future motion.
9
Backman, Anton. "Motion prediction of ego vehicle in complex scenarios." Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-278497.
Full textAbstract:
In this thesis, we study the trajectory prediction problem of an ego vehicle,i.e. "predicting" the location of the ego vehicle in the short future. Instead oftraditional methods, we use Machine Learning (ML) techniques since they easilyincorporate features, such as contextual information from the environment, theprediction process The contextual features signicantly improve the predictionquality since they provide important information about the driving environmentand scenarios.The Long Short-Term Memory (LSTM) model is used to develop variouspredictors which utilize dierent features. The predictors are evaluated againsta Zero-order hold (ZOH) model as a baseline. All models are evaluated ona complete test data set as well as specic, complex, test cases. The resultsshow that the proposed predictors generally outperform the ZOH model. Furthermore,the Root Mean Square Error (RMSE) is halved in many complexscenarios, suggesting more reliable predictions.<br>Detta examensarbete handlar om att tackla problemet med att prediktera bratrajektorier av egofordonet, det vill säga att ”gissa” vart egofordonet kommer attåka i nära framtiden. Genom att använda maskininlärning istället för att göra modeller på det traditionella sättet så har det blivit enklare att använda andra kännetäcken, såsom kontextuell information från omgivningen, i modellerna. Dessa kännetäcken hjälper modellerna att göra bra prediktioner eftersom de ger ledtrådar om vilken situation egofordonet är i. Maskininlärning kan också vara det bättre alternativet eftersom maskininlärningsmodeller kan potentiellt se mönster som de traditionella metoderna inte kan se.LSTM modeller som använder olika kännetäcken har skapats. Dessa har evaluerats för att undersöka vilka kännetäcken som, till synes, verkar vara de viktigaste för prediktionerna. Modellerna har ställts mot en nollte ordningens model som är satt som en baslinje. Alla modeller har evaluerats på ett helt test dataset. De har också blivit evaluerade på specfika, komplexa, testfall. Resultaten visar att de förslagna modellerna är generellt bättre än nollte ordningens modellen samt att maskininlärningmodellernas RMSE är halverad i många kom-plexa testfall, vilket antyder en förbättring.
10
Vatis, Yuri. "Non-symmetric adaptive interpolation filter for motion compensated prediction /." Düsseldorf : VDI-Verl, 2009. http://d-nb.info/998470724/04.
Full text
11
Mazzon, Riccardo. "Motion prediction and interaction localisation of people in crowds." Thesis, Queen Mary, University of London, 2013. http://qmro.qmul.ac.uk/xmlui/handle/123456789/8605.
Full textAbstract:
The ability to analyse and predict the movement of people in crowded scenarios can be of fundamental importance for tracking across multiple cameras and interaction localisation. In this thesis, we propose a person re-identification method that takes into account the spatial location of cameras using a plan of the locale and the potential paths people can follow in the unobserved areas. These potential paths are generated using two models. In the first, people’s trajectories are constrained to pass through a set of areas of interest (landmarks) in the site. In the second we integrate a goal-driven approach to the Social Force Model (SFM), initially introduced for crowd simulation. SFM models the desire of people to reach specific interest points (goals) in a site, such as exits, shops, seats and meeting points while avoiding walls and barriers. Trajectory propagation creates the possible re-identification candidates, on which association of people across cameras is performed using spatial location of the candidates and appearance features extracted around a person’s head. We validate the proposed method in a challenging scenario from London Gatwick airport and compare it to state-of-the-art person re-identification methods. Moreover, we perform detection and tracking of interacting people in a framework based on SFM that analyses people’s trajectories. The method embeds plausible human behaviours to predict interactions in a crowd by iteratively minimising the error between predictions and measurements. We model people approaching a group and restrict the group formation based on the relative velocity of candidate group members. The detected groups are then tracked by linking their centres of interaction over time using a buffered graph-based tracker. We show how the proposed framework outperforms existing group localisation techniques on three publicly available datasets.
12
Conte, Dean Edward. "Autonomous Robotic Escort Incorporating Motion Prediction with Human Intention." Thesis, Virginia Tech, 2021. http://hdl.handle.net/10919/102581.
Full textAbstract:
This thesis presents a framework for a mobile robot to escort a human to their destination successfully and efficiently. The proposed technique uses accurate path prediction incorporating human intention to locate the robot in front of the human while walking. Human intention is inferred by the head pose, an effective past-proven implicit indicator of intention, and fused with conventional physics-based motion prediction. The human trajectory is estimated and predicted using a particle filter because of the human's nonlinear and non-Gaussian behavior, and the robot control action is determined from the predicted human pose allowing for anticipative autonomous escorting. Experimental analysis shows that the incorporation of the proposed human intention model reduces human position prediction error by approximately 35% when turning. Furthermore, experimental validation with an omnidirectional mobile robotic platform shows escorting up to 50% more accurate compared to the conventional techniques, while achieving 97% success rate.<br>Master of Science<br>This thesis presents a method for a mobile robot to escort a human to their destination successfully and efficiently. The proposed technique uses human intention to predict the walk path allowing the robot to be in front of the human while walking. Human intention is inferred by the head direction, an effective past-proven indicator of intention, and is combined with conventional motion prediction. The robot motion is then determined from the predicted human position allowing for anticipative autonomous escorting. Experimental analysis shows that the incorporation of the proposed human intention reduces human position prediction error by approximately 35% when turning. Furthermore, experimental validation with an mobile robotic platform shows escorting up to 50% more accurate compared to the conventional techniques, while achieving 97% success rate. The unique escorting interaction method proposed has applications such as touch-less shopping cart robots, exercise companions, collaborative rescue robots, and sanitary transportation for hospitals.
13
Vasquez, Govea Alejandro Dizan. "Incremental learning for motion prediction of pedestrians and vehicles." Grenoble INPG, 2007. https://tel.archives-ouvertes.fr/tel-00155274.
Full textAbstract:
Le thème principal de cette thèse est la prédiction des mouvements. Ce thème est traité en partant de l'hypothèse que les piétons et les véhicules ne déplacent pas au hasard, mais ils suivent des « comportements typiques» qui peuvent être appris et utilisés ensuite dans une phase de prédiction. L'approche proposée aborde trois questions fondamentales: Modélisation: Ce travail se base en l'utilisation d'un modèle probabiliste, les modèles cachés de Markov, pour représenter les comportements typiques. Apprentissage: La thèse propose une extension aux modèles cachés de Markov qui permet d'apprendre la structure et les paramètres du modèle de façon incrémentale. Prédiction: La prédiction utilise l'inférence bayésienne exacte. Grâce aux propriétés de la structure apprise, la complexité de l'inférence est linéaire par rapport au nombre d'états<br>The main subject of this thesis is motion prediction. The problem is studied on the basis of the assumption that pedestrians and vehicles do not move randomly but follow typical "motion patterns" which may be learned and then user in a prediction phase. The approach addresses three fundamental questions: Modelling: This work is based in the utilisation of a probabilistic model, Hidden Markov Models, to represent typical motion patterns. Learning: This thesis proposes an extension to Hidden Markov Models that allows to learn the structure and parameters of the model in an incremental fashion. Prediction: Prediction is done using exact Bayesian inference. Thanks to the properties of the learned structure, the complexity of inference is linear with respect to the number of states in the model
14
Yang, Tao. "visual tracking and object motion prediction for intelligent vehicles." Thesis, Bourgogne Franche-Comté, 2019. http://www.theses.fr/2019UBFCA005.
Full textAbstract:
Le suivi d’objets et la prédiction de mouvement sont des aspects importants pour les véhicules autonomes. Tout d'abord, nous avons développé une méthode de suivi mono-objet en utilisant le compressive tracking, afin de corriger le suivi à base de flux optique et d’arriver ainsi à un compromis entre performance et vitesse de traitement. Compte tenu de l'efficacité de l'extraction de caractéristiques comprimées (compressive features), nous avons appliqué cette méthode de suivi au cas multi-objets pour améliorer les performances sans trop ralentir la vitesse de traitement. Deuxièmement, nous avons amélioré la méthode de suivi mono-objet basée sur DCF en utilisant des caractéristiques provenant d’un CNN multicouches, une analyse de fiabilité spatiale (via un masque d'objet) ainsi qu’une stratégie conditionnelle de mise à jour de modèle. Ensuite, nous avons appliqué la méthode améliorée au cas du suivi multi-objets. Les VGGNet-19 et DCFNet pré-entraînés sont testés respectivement en tant qu’extracteurs de caractéristiques. Le modèle discriminant réalisé par DCF est pris en compte dans l’étape d'association des données. Troisièmement, deux modèles LSTM (seq2seq et seq2dense) pour la prédiction de mouvement des véhicules et piétons dans le système de référence de la caméra sont proposés. En se basant sur des données visuelles et un nuage de points 3D (LiDAR), un système de suivi multi-objets basé sur un filtre de Kalman avec un détecteur 3D sont utilisés pour générer les trajectoires des objets à tester. Les modèles proposées et le modèle de régression polynomiale, considéré comme méthode de référence, sont comparés et évalués<br>Object tracking and motion prediction are important for autonomous vehicles and can be applied in many other fields. First, we design a single object tracker using compressive tracking to correct the optical flow tracking in order to achieve a balance between performance and processing speed. Considering the efficiency of compressive feature extraction, we apply this tracker to multi-object tracking to improve the performance without slowing down too much speed. Second, we improve the DCF based single object tracker by introducing multi-layer CNN features, spatial reliability analysis (through a foreground mask) and conditionally model updating strategy. Then, we apply the DCF based CNN tracker to multi-object tracking. The pre-trained VGGNet-19 and DCFNet are tested as feature extractors respectively. The discriminative model achieved by DCF is considered for data association. Third, two proposed LSTM models (seq2seq and seq2dense) for motion prediction of vehicles and pedestrians in the camera coordinate are proposed. Based on visual data and 3D points cloud (LiDAR), a Kalman filter based multi-object tracking system with a 3D detector are used to generate the object trajectories for testing. The proposed models, and polynomial regression model, considered as baseline, are compared for evaluation
15
Bataineh, Mohammad Hindi. "New neural network for real-time human dynamic motion prediction." Thesis, The University of Iowa, 2015. http://pqdtopen.proquest.com/#viewpdf?dispub=3711174.
Full textAbstract:
<p> Artificial neural networks (ANNs) have been used successfully in various practical problems. Though extensive improvements on different types of ANNs have been made to improve their performance, each ANN design still experiences its own limitations. The existing digital human models are mature enough to provide accurate and useful results for different tasks and scenarios under various conditions. There is, however, a critical need for these models to run in real time, especially those with large-scale problems like motion prediction which can be computationally demanding. For even small changes to the task conditions, the motion simulation needs to run for a relatively long time (minutes to tens of minutes). Thus, there can be a limited number of training cases due to the computational time and cost associated with collecting training data. In addition, the motion problem is relatively large with respect to the number of outputs, where there are hundreds of outputs (between 500-700 outputs) to predict for a single problem. Therefore, the aforementioned necessities in motion problems lead to the use of tools like the ANN in this work. </p><p> This work introduces new algorithms for the design of the radial-basis network (RBN) for problems with minimal available training data. The new RBN design incorporates new training stages with approaches to facilitate proper setting of necessary network parameters. The use of training algorithms with minimal heuristics allows the new RBN design to produce results with quality that none of the competing methods have achieved. The new RBN design, called Opt_RBN, is tested on experimental and practical problems, and the results outperform those produced from standard regression and ANN models. In general, the Opt_RBN shows stable and robust performance for a given set of training cases. </p><p> When the Opt_RBN is applied on the large-scale motion prediction application, the network experiences a CPU memory issue when performing the optimization step in the training process. Therefore, new algorithms are introduced to modify some steps of the new Opt_RBN training process to address the memory issue. The modified steps should only be used for large-scale applications similar to the motion problem. The new RBN design proposes an ANN that is capable of improved learning without needing more training data. Although the new design is driven by its use with motion prediction problems, the consequent ANN design can be used with a broad range of large-scale problems in various engineering and industrial fields that experience delay issues when running computational tools that require a massive number of procedures and a great deal of CPU memory. </p><p> The results of evaluating the modified Opt_RBN design on two motion problems are promising, with relatively small errors obtained when predicting approximately 500-700 outputs. In addition, new methods for constraint implementation within the new RBN design are introduced. Moreover, the new RBN design and its associated parameters are used as a tool for simulated task analysis. This work initiates the idea that output weights (<i>W</i>) can be used to determine the most critical basis functions that cause the greatest reduction in the network test error. Then, the critical basis functions can specify the most significant training cases that are responsible for the proper performance achieved by the network. The inputs with the most change in value can be extracted from the basis function centers (<i>U</i>) in order to determine the dominant inputs. The outputs with the most change in value and their corresponding key body degrees-of-freedom for a motion task can also be specified using the training cases that are used to create the network's basis functions. </p>
16
Sheikh, M. S. "Prediction of particle residence times in cascading rotary dryers." Thesis, Teesside University, 1987. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.378933.
Full textAbstract:
The objectives of this research were to provide a better understanding of particle motion in cascading rotary dryers. This would lead to more soundly based design procedures. Experiments were performed, to check the validity of a proposed design method for dryers operating in the under-loaded and design loaded conditions developed by Matchett and Baker, on a pilot plant rig at Teesside Polytechnic using wheat and sand in the absence of airflow. The model considers the particles to move in two parallel phases, the airborne phase contains the material in flight and the dense phase contains the remaining material which is caught on the flights and on the bottom of the drum. There is continuous Interchange of material between the two phases. A dimensionless number, dense phase velocity number 'a', has been defined which is a measure of the axial velocity of the material in the dense phase of the drum. The 'a' values were found to be in agreement with existing data and were found to be dependent on material and not on dryer speed or slope. Photographic studies of the dryer internals suggested that the assumption of a constant 0 value (measure of flight loading) In the original model was not valid and that 4) varied with number of flights. A model was developed to predict 0 which worked extremely well for large number of flights. The existing design model was therefore modified to take account of the variation In 4). However, the paired t-test Indicated that at 5% level of significance there was no difference between the original and the modified model, even though the modified model is physically more realistic. It is, however, recommended that the models be tested on a large number of flights and also large equipment, because It is expected that with a large number of flights there will be differences between the two models and the 0 model will be superior. The 'a' and am (the am value is a modified form of the 'a' value which takes into account the variation in flight loading) values were found to be Independent of operating conditions, flight angle and also dryer size but were dependent on material. The 'a' and am values were proportional to 1/number of flights. Particle motion in the dense is by bouncing, rolling and sliding, but the high dense phase velocity numbers obtained with zero flights (ar) suggested ii that rolling and sliding are the important mechanisms of the dense phase motion and may be far more important than bouncing. A model has also been developed to study the over-loaded regime. In the over-loaded regime It was found that dryer speed, slope, material and number of flights affected the dense phase motion and a simple relationship between the over-loaded dense phase velocity number (ao) and number of flights could not be developed with the limited data. Particle motion In the over-loaded regime was found to be very complex. The ao values could be predicted to within ± 35%. Estimates have been made of the transition holdup, marking the change from under-loaded to over-loaded behaviour, but It was found that the prediction of the transition holdup is also complex and could be predicted to within ± 45%. The am values could be predicted to an accuracy of ± 10%. Thus suggesting that the ao and the transition holdup numbers are not so reliable. Future work has been recommended particularly in the over-loaded regime and also on the transition region since it was found that the particle motion in these regions was complex. It has also been suggested that the models be tested in large Industrial units with and without air flow.
17
Matsangas, Panagiotis. "A linear physiological visual-vestibular interaction model for the prediction of motion sickness incidence." Thesis, Monterey, Calif. : Springfield, Va. : Naval Postgraduate School ; Available from National Technical Information Service, 2004. http://library.nps.navy.mil/uhtbin/hyperion/04Sep%5FMatsangas.pdf.
Full textAbstract:
Thesis (M.S. in Operations Research and M.S. in Modeling, Virtual Environments and Simulation)--Naval Postgraduate School, Sept. 2004.<br>Thesis Advisor(s): Michael McCauley, Nita Miller. Includes bibliographical references (p. 149-162). Also available online.
18
Volz, Claudius. "Concealment of Video Transmission Packet Losses Based on Advanced Motion Prediction." Thesis, Linköping University, Department of Electrical Engineering, 2003. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-1771.
Full textAbstract:
<p>Recent algorithms for video coding achieve a high-quality transmission at moderate bit rates. On the other hand, those coders are very sensitive to transmission errors. Many research projects focus on methods to conceal such errors in the decoded video sequence. </p><p>Motion compensated prediction is commonly used in video coding to achieve a high compression ratio. This thesis proposes an algorithm which uses the motion compensated prediction of a given video coder to predict a sequence of several complete frames, based on the last correctly decoded images, during a transmission interruption. The proposed algorithm is evaluated on a video coder which uses a dense motion field for motion compensation. </p><p>A drawback of predicting lost fields is the perceived discontinuity when the decoder switches back from the prediction to a normal mode of operation. Various approaches to reduce this discontinuity are investigated.</p>
19
Alnowami, Majdi Rashed S. "Adaptive modelling and prediction of respiratory motion in external beam radiotherapy." Thesis, University of Surrey, 2012. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.582747.
Full textAbstract:
The latter two decades of the last century saw significant improvements in External Beam Radiotherapy (EBRT), moved primarily by the advances in imaging modalities and computer-based treatment planning. These advances led to introducing the addition of a fourth dimension, time, to the three-dimensional EBRT arena. This new era in EBRT brings with it challenges and opportunities, in particular to compensate for the effect of respiratory-induced target motion and enhancing treatment delivery. Thus, characterising and modelling respiratory motion is of major importance in this research area. This thesis aims to enhance the understanding and control the effect of respiratory motion. As part of this work, the first principal component analysis (PCA) of respiratory motion is presented, as a basis for compactly and visually representing respiratory style and variation. These studies can be divided into two main aspects: firstly, understanding and characterising respiratory motion as the basis of any further steps towards compensating respiratory motion and secondly, utilising this knowledge in predicting and correlating internal and external respiratory motion in the abdominal thoracic region. This work has been developed starting with a piecewise sinusoidal model in an Eigenspace for modelling, Adaptive kernel density estimation (AKDE) for prediction and finally Canonical Correlation Analysis (CCA) for external-internal target correlation. A comparative study between these proposed approaches and state-of-the-art prior works showed promising results in terms of accuracy and computational efficiency: 20% error reduction compared to support vector regression (SVR) and kernel density estimation (KDE) and a significant reduction in computation speed during training stage. This journey into modelling and predicting respiratory behaviour has naturally raised questions of how best to track external motion. The need to track the surface with more than one marker, established within the aforementioned PCA analysis, motivates the desire for markerless tracking. Therefore, two different markerless systems have been studied, as potential solutions for this area, combined with a mesh model of the anterior surface. This suggests that the Microsoft Kinect camera is a promising low-cost technology for makerless respiratory tracking with less than 3.1 ± 0.6 mm accuracy.
20
Salui, Kumar Bappaditya. "Prediction of hydrodynamic coefficients during roll motion of ship using RANSE." Thesis, University of Strathclyde, 2004. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.431847.
Full text
21
Khays, Samir. "Motion Prediction of Surrounding Vehicles in Highway Scenarios With Deep Learning." Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-254408.
Full textAbstract:
Anticipating the future positions of the surrounding vehicles is a crucial task foran autonomous vehicle in order to drive safely. To foresee complex manoeuvresfor longer time horizons, a framework that relies on high-level properties ofmotion and is able to incorporate, e.g. contextual features, is needed. In thisthesis, the problem of predicting the trajectories of the surrounding vehicles ona highway is tackled by using machine learning. The objective is to evaluate theperformance of recurrent neural networks for trajectory prediction, specificallylong-short term memory neural networks. Moreover, the goal is to investigateif contextual features can improve the predictions.The problem of predicting future trajectories is solved by using two differentapproaches, which are compared by using the same framework. The firstapproach is based on the vehicle states of the surrounding vehicles relative tothe ego-vehicle, where the reference system is in the ego-vehicle. The secondapproach is based on the velocities of the vehicles relative to the ground, wherethe reference system is in the ground. The results show that, with the proposedarchitecture, the latter approach results in a lower RMSE in the longitudinaldirection compared with the former approach. The results also show that theproposed models, overall, outperform a simple model, which is based on polynomialfitting, particularly in the lateral direction where the proposed modelsare significantly better than the polynomial models. Furthermore, contextualfeatures do not improve the predictions significantly. However, the results indicatethat contextual information has a positive impact on the predictions inspecific scenarios.<br>Att kunna förutse framtida rörelser av kringliggande fordon är en viktig uppgiftför att ett autonomt fordon ska kunna köra säkert. För att kunna förutspå komplexamanövreringar för längre tidshorisonter, behövs ett ramverk baserat påavancerade egenskaper hos rörelser och som kan integrera t.ex. kontextuell information.I detta examensarbete betraktas problemet att förutspå trajektorierav kringliggande fordon på motorväg med hjälp av maskininlärning. Målet äratt utvärdera prestandan av recurrent neural networks för denna uppgift, specifiktlong-short term memory neural networks. Målet är också att undersöka omkontextuell information kan förbättra prediktionerna.Problemet att prediktera framtida trajektorier är löst genom att användatvå olika tillvägagångssätt. Det ena tillvägagångssättet är baserat på fordonstillståndenav de kringliggande fordonen relativt ego-fordonet, där referenssystemetär i ego-fordonet. Det andra tillvägagångssättet är baserat på hastigheternaav fordonen relativt marken, där referenssystemet är i marken. Resultatetvisar att det sistnämnda tillvägagångssättet resulterar i ett lägre RMSE i denlongitudinella riktningen, med den föreslagna arkitekturen, jämfört med detförstnämnda. Resultaten visar även att de framtagna modellerna, totalt sett,presterar bättre än en simpel modell som är baserad på polynomanpassning,speciellt i lateral riktning där de framtagna modellerna är betydligt bättreän polynomanpassningarna. Det visar sig också att kontextuell informationinte förbättrar prediktionerna signifikant, däremot indikerar resultaten att detpåverkar prediktionerna positivt i specifika scenarier.
22
Sapankevych, Nicholas. "Constrained Motion Particle Swarm Optimization for Non-Linear Time Series Prediction." Scholar Commons, 2015. https://scholarcommons.usf.edu/etd/5569.
Full textAbstract:
Time series prediction techniques have been used in many real-world applications such as financial market prediction, electric utility load forecasting, weather and environmental state prediction, and reliability forecasting. The underlying system models and time series data generating processes are generally complex for these applications and the models for these systems are usually not known a priori. Accurate and unbiased estimation of time series data produced by these systems cannot always be achieved using well known linear techniques, and thus the estimation process requires more advanced time series prediction algorithms.
One type of time series interpolation and prediction algorithm that has been proven to be effective for these various types of applications is Support Vector Regression (SVR) [1], which is based on the Support Vector Machine (SVM) developed by Vapnik et al. [2, 3]. The underlying motivation for using SVMs is the ability of this methodology to accurately forecast time series data when the underlying system processes are typically nonlinear, non-stationary and not defined a-priori. SVMs have also been proven to outperform other non-linear techniques including neural-network based non-linear prediction techniques such as multi-layer perceptrons.
As with most time series prediction algorithms, there are typically challenges associated in applying a given heuristic to any general problem. One difficult challenge in using SVR to solve these types of problems is the selection of free parameters associated with the SVR algorithm. There is no given heuristic to select SVR free parameters and the user is left to adjust these parameters in an ad hoc manner.
The focus of this dissertation is to present an alternative to the typical ad hoc approach of tuning SVR for time series prediction problems by using Particle Swarm Optimization (PSO) to assist in the SVR free parameter selection process. Developed by Kennedy and Eberhart [4-8], PSO is a technique that emulates the process living creatures (such as birds or insects) use to discover food resources at a given geographic location. PSO has been proven to be an effective technique for many different kinds of optimization problems [9-11].
The focus of this dissertation is to present an alternative to the typical ad hoc approach of tuning SVR for time series prediction problems by using Particle Swarm Optimization (PSO) to assist in the SVR free parameter selection process. Developed by Kennedy and Eberhart [4-8], PSO is a technique that emulates the process living creatures (such as birds or insects) use to discover food resources at a given geographic location. PSO has been proven to be an effective technique for many different kinds of optimization problems [9-11].
23
Lasota, Przemyslaw A. (Przemyslaw Andrzej). "Robust human motion prediction for safe and efficient human-robot interaction." Thesis, Massachusetts Institute of Technology, 2019. https://hdl.handle.net/1721.1/122497.
Full textAbstract:
Thesis: Ph. D. in Autonomous Systems, Massachusetts Institute of Technology, Department of Aeronautics and Astronautics, 2019<br>Cataloged from PDF version of thesis.<br>Includes bibliographical references (pages 175-188).<br>From robotic co-workers in factories to assistive robots in homes, human-robot interaction (HRI) has the potential to revolutionize a large array of domains by enabling robotic assistance where it was previously not possible. Introducing robots into human-occupied domains, however, requires strong consideration for the safety and efficiency of the interaction. One particularly effective method of supporting safe an efficient human-robot interaction is through the use of human motion prediction. By predicting where a person might reach or walk toward in the upcoming moments, a robot can adjust its motions to proactively resolve motion conflicts and avoid impeding the person's movements. Current approaches to human motion prediction, however, often lack the robustness required for real-world deployment. Many methods are designed for predicting specific types of tasks and motions, and do not necessarily generalize well to other domains.<br>It is also possible that no single predictor is suitable for predicting motion in a given scenario, and that multiple predictors are needed. Due to these drawbacks, without expert knowledge in the field of human motion prediction, it is difficult to deploy prediction on real robotic systems. Another key limitation of current human motion prediction approaches lies in deficiencies in partial trajectory alignment. Alignment of partially executed motions to a representative trajectory for a motion is a key enabling technology for many goal-based prediction methods. Current approaches of partial trajectory alignment, however, do not provide satisfactory alignments for many real-world trajectories. Specifically, due to reliance on Euclidean distance metrics, overlapping trajectory regions and temporary stops lead to large alignment errors.<br>In this thesis, I introduce two frameworks designed to improve the robustness of human motion prediction in order to facilitate its use for safe and efficient human-robot interaction. First, I introduce the Multiple-Predictor System (MPS), a datadriven approach that uses given task and motion data in order to synthesize a high performing predictor by automatically identifying informative prediction features and combining the strengths of complementary prediction methods. With the use of three distinct human motion datasets, I show that using the MPS leads to lower prediction error in a variety of HRI scenarios, and allows for accurate prediction for a range of time horizons. Second, in order to address the drawbacks of prior alignment techniques, I introduce the Bayesian ESTimator for Partial Trajectory Alignment (BEST-PTA).<br>This Bayesian estimation framework uses a combination of optimization, supervised learning, and unsupervised learning components that are trained and synthesized based on a given set of example trajectories. Through an evaluation on three human motion datasets, I show that BEST-PTA reduces alignment error when compared to state-of-the-art baselines. Furthermore, I demonstrate that this improved alignment reduces human motion prediction error. Lastly, in order to assess the utility of the developed methods for improving safety and efficiency in HRI, I introduce an integrated framework combining prediction with robot planning in time. I describe an implementation and evaluation of this framework on a real physical system. Through this demonstration, I show that the developed approach leads to automatically derived adaptive robot behavior. I show that the developed framework leads to improvements in quantitative metrics of safety and efficiency with the use of a simulated evaluation.<br>"Funded by the NASA Space Technology Research Fellowship Program and the National Science Foundation"--Page 6<br>by Przemyslaw A. Lasota.<br>Ph. D. in Autonomous Systems<br>Ph.D.inAutonomousSystems Massachusetts Institute of Technology, Department of Aeronautics and Astronautics
24
Rai, Manisha. "Topographic Effects in Strong Ground Motion." Diss., Virginia Tech, 2015. http://hdl.handle.net/10919/56593.
Full textAbstract:
Ground motions from earthquakes are known to be affected by earth's surface topography. Topographic effects are a result of several physical phenomena such as the focusing or defocusing of seismic waves reflected from a topographic feature and the interference between direct and diffracted seismic waves. This typically causes an amplification of ground motion on convex features such as hills and ridges and a de-amplification on concave features such as valleys and canyons. Topographic effects are known to be frequency dependent and the spectral accelerations can sometimes reach high values causing significant damages to the structures located on the feature. Topographically correlated damage pattern have been observed in several earthquakes and topographic amplifications have also been observed in several recorded ground motions. This phenomenon has also been extensively studied through numerical analyses. Even though different studies agree on the nature of topographic effects, quantifying these effects have been challenging. The current literature has no consensus on how to predict topographic effects at a site. With population centers growing around regions of high seismicity and prominent topographic relief, such as California, and Japan, the quantitative estimation of the effects have become very important. In this dissertation, we address this shortcoming by developing empirical models that predict topographic effects at a site. These models are developed through an extensive empirical study of recorded ground motions from two large strong-motion datasets namely the California small to medium magnitude earthquake dataset and the global NGA-West2 datasets, and propose topographic modification factors that quantify expected amplification or deamplification at a site.
To develop these models, we required a parameterization of topography. We developed two types of topographic parameters at each recording stations. The first type of parameter is developed using the elevation data around the stations, and comprise of parameters such as smoothed slope, smoothed curvature, and relative elevation. The second type of parameter is developed using a series of simplistic 2D numerical analysis. These numerical analyses compute an estimate of expected 2D topographic amplification of a simple wave at a site in several different directions. These 2D amplifications are used to develop a family of parameters at each site. We study the trends in the ground motion model residuals with respect to these topographic parameters to determine if the parameters can capture topographic effects in the recorded data. We use statistical tests to determine if the trends are significant, and perform mixed effects regression on the residuals to develop functional forms that can be used to predict topographic effect at a site. Finally, we compare the two types of parameters, and their topographic predictive power.<br>Ph. D.
25
Pei, Jiantao, and n/a. "The Accuracy of Time-to-Contact Estimation in the Prediction Motion Paradigm." University of Canberra. Applied Science, 2002. http://erl.canberra.edu.au./public/adt-AUC20050627.143329.
Full textAbstract:
This thesis is concerned with the accuracy of our estimation of time to make contact
with an approaching object as measured by the “Prediction Motion” (PM) technique.
The PM task has commonly been used to measure the ability to judge time to contact
(TTC). In a PM task, the observer's view of the target is occluded for some period
leading up to the moment of impact. The length of the occlusion period is varied and
the observer signals the moment of impact by pressing a response key. The interval
separating the moment of occlusion and the response is interpreted as the observer's
estimate of TTC made at the moment of occlusion. This technique commonly
produces large variability and systematic underestimation. The possibility that this
reflects genuine perceptual errors has been discounted by most writers, since this
seems inconsistent with the accuracy of interceptive actions in real life. Instead, the
poor performance in the PM task has been attributed to problems with the PM
technique. Several hypotheses have been proposed to explain the poor PM
performance. The motion extrapolation hypothesis asserts that some form of mental
representation of the occluded part of the trajectory is used to time the PM response;
the errors in PM performance are attributed to errors in reconstructing the target
motion. The clocking hypothesis assumes that the TTC is accurately perceived at the
moment of occlusion and that errors arise in delaying the response for the required
period. The fear-of-collision hypothesis proposes that the underestimation seen in
the PM tasks reflects a precautionary tendency to anticipate the estimated moment of
contact. This thesis explores the causes of the errors in PM measurements.
Experiments 1 and 2 assessed the PM performance using a range of motion scenarios
involving various patterns of movement of the target, the observer, or both. The
possible contribution of clocking errors to the PM performance was assessed by a
novel procedure designed to measure errors in the wait-and-respond component of
the PM procedure. In both experiments, this procedure yielded a pattern of
systematic underestimation and high variability similar to that in the TTC estimation
task. Experiment 1 found a small effect of motion scenario on TTC estimation.
However, this was not evident in Experiment 2.
The collision event simulated in Experiment 2 did not involve a solid collision. The
target was simply a rectangular frame marked on a tunnel wall. At the moment of
“contact”, the observers passed “through” the target without collision. However,
there was still systematic underestimation of TTC and there was little difference
between the estimates obtained in Experiments 1 and 2. Overall, the results of
Experiments 1 and 2 were seen as inconsistent with either the motion extrapolation
hypothesis or the fear-of-collision hypothesis. It was concluded that observers
extracted an estimate of the TTC based on optic TTC information at a point prior to
the moment of collision, and used a timing process to count down to the moment of
response. The PM errors were attributed to failure in this timing process. The results
of these experiments were seen as implying an accurate perception of TTC.
It was considered possible that in Experiments 1 and 2 observers based their TTC
judgements on either the retinal size or the expansion rate of the target rather than
TTC. Experiments 3 and 4 therefore investigated estimation of TTC using a range of
simulated target velocities and sizes. TTC estimates were unaffected by the resulting
variation in expansion rate and size, indicating that TTC, rather than retinal size or
image expansion rate per se, was used to time the observers' response.
The accurate TTC estimation found in Experiments 1-4 indicates that the TTC
processing is very robust across a range of stimulus conditions. Experiment 5 further
explored this robustness by requiring estimation of TTC with an approaching target
which rotated in the frontoparallel plane. It was shown that moderate but not fast
rates of target rotation induced an overestimation of TTC. However, observers were
able to discriminate between TTCs for all rates of rotation. This shows that the
extraction of TTC information is sensitive to perturbation of the local motion of the
target border, but it implies that, in spite of these perturbations, the mechanism is
flexible enough to pick up the optic TTC information provided by the looming of the
retinal motion envelop of the rotating stimulus.
26
Kelling, Nicholas J. "An investigation of human capability to predict the future location of objects in motion." Diss., Atlanta, Ga. : Georgia Institute of Technology, 2009. http://hdl.handle.net/1853/28103.
Full textAbstract:
Thesis (M. S.)--Psychology, Georgia Institute of Technology, 2009.<br>Committee Chair: Dr. Gregory M. Corso; Committee Member: Dr. Arthur D. Fisk; Committee Member: Dr. Bruce Walker; Committee Member: Dr. Lawrence R. James; Committee Member: Dr. Paul Corballis; Committee Member: Dr. Robert Gregor
27
DAK, HAZIRBABA YILDIZ. "IMAGE-BASED MODELING AND PREDICTION OF NON-STATIONARY GROUND MOTIONS." OpenSIUC, 2015. https://opensiuc.lib.siu.edu/dissertations/1008.
Full textAbstract:
Nonlinear dynamic analysis is a required step in seismic performance evaluation of many structures. Performing such an analysis requires input ground motions, which are often obtained through simulations, due to the lack of sufficient records representing a given scenario. As seismic ground motions are characterized by time-varying amplitude and frequency content, and the response of nonlinear structures is sensitive to the temporal variations in the seismic energy input, ground motion non-stationarities should be taken into account in simulations. This paper describes a nonparametric approach for modeling and prediction of non-stationary ground motions. Using Relevance Vector Machines, a regression model which takes as input a set of seismic predictors, and produces as output the expected evolutionary power spectral density, conditioned on the predictors. A demonstrative example is presented, where recorded and predicted ground motions are compared in time, frequency, and time-frequency domains. Analysis results indicate reasonable match between the recorded and predicted quantities.
28
Patrick, Timothy. "The Influence of Attentional Entrainment on Temporal and Spatial Predictions of Inferred Motion." Bowling Green State University / OhioLINK, 2019. http://rave.ohiolink.edu/etdc/view?acc_num=bgsu1562538488263969.
Full text
29
Wang, Anqi. "Prediction of Human Hand Motions based on Surface Electromyography." Thesis, Virginia Tech, 2017. http://hdl.handle.net/10919/78289.
Full textAbstract:
Tracking human hand motions has raised more attention due to the recent advancements of virtual reality (Rheingold, 1991) and prosthesis control (Antfolk et al., 2010). Surface electromyography (sEMG) has been the predominant method for sensing electrical activity in biomechanical studies, and has also been applied to motion tracking in recent years. While most studies focus on the classification of human hand motions within a predefined motion set, the prediction of continuous finger joint angles and wrist angles remains a challenging endeavor. In this research, a biomechanical knowledge-driven data fusion strategy is proposed to predict finger joint angles and wrist angles. This strategy combines time series data of sEMG signals and simulated muscle features, which can be extracted from a biomechanical model available in OpenSim (Delp et al., 2007). A support vector regression (SVR) model is used to firstly predict muscle features from sEMG signals and then to predict joint angles from the estimated muscle features. A set of motion data containing 10 types of motions from 12 participants was collected from an institutional review board approved experiment. A hypothesis was tested to validate whether adding the simulated muscle features would significantly improve the prediction performance. The study indicates that the biomechanical knowledge-driven data fusion strategy will improve the prediction of new types of human hand motions. The results indicate that the proposed strategy significantly outperforms the benchmark date-driven model especially when the users were performing unknown types of motions from the model training stage. The proposed model provides a possible approach to integrate the simulation models and data fusion models in human factors and ergonomics.<br>Master of Science
30
Lenkic, Peter Jordan. "Motion enhances or reduces target visibility, depending on prediction and postdiction of shape." Thesis, University of British Columbia, 2011. http://hdl.handle.net/2429/37054.
Full textAbstract:
Motion masking refers to the finding that objects are less visible when they appear as part of an apparent motion sequence than when they appear for the same duration in isolation. Against this backdrop of generally impaired visibility, there are reports of a relative visibility benefit when a target on the motion path is spatiotemporally predictable versus when it is unpredictable. The present study investigates whether prediction based on the shape of the originating stimulus in the motion sequence, and postdiction based on the terminating shape, is an aid to the visibility of a target in motion. In Experiment 1 these factors are examined separately for originating and terminating stimuli; in Experiment 2 they are examined in combination. The results show that both factors influence target discriminability in an additive way, suggesting that the processes of prediction and postdiction have independent influences on visibility. Experiment 3 examines the same display sequences with a different psychophysical task (i.e., detection) in an effort to reconcile the present findings with previous contradictory results. The upshot is that in contrast to the results for discrimination, target detection is influenced little by these factors. Experiments 4 and 5 examine the discrimination of a fine shape detail of the target, in contrast to the crude discrimination of target orientation in Experiments 1 and 2. This design also eliminates the opportunity for decision-biases to influence the results. The results show that predictable motion has a strong positive influence on target shape discrimination, to the extent that it makes a backward-masked target even more visible than when it appears in isolation. These findings are related to the empirical literature on visual masking and interpreted within the theoretical framework of object updating.
31
Verveniotis, Christos S. "Prediction of motion sickness on high-speed passenger vessels : a human-oriented approach." Thesis, University of Strathclyde, 2004. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.415297.
Full text
32
Petersamer, Matthias. "Prediction of motion trajectories based on motor imagery by a brain computer interface." Master's thesis, Pontificia Universidad Católica del Perú, 2017. http://tesis.pucp.edu.pe/repositorio/handle/123456789/11605.
Full textAbstract:
The aim of this Master's Thesis was to develop a naturally controllable BCI that can predict
motion trajectories from the imagination of motor execution. The approach to reach this aim
was to nd a correlation between movement and brain data, which can subsequently be used
for the prediction of movement trajectories only by brain signals. To nd this correlation, an
experiment was carried out, in which a participant had to do triggered movements with its right
arm to four di erent targets. During the execution of the movements, the kinematic and EEG
data of the participant were recorded. After a preprocessing stage, the velocity of the kinematic
data in x and y directions, and the band power of the EEG data in di erent frequency ranges
were calculated and used as features for the calculation of the correlation by a multiple linear
regression. When applying the resulting regression parameter to predict trajectories from EEG
signals, the best accuracies were shown in the mu and low beta frequency range, as expected.
However, the accuracies were not as high as necessary for control of an application.<br>El objetivo de esta Tesis de Maestría fue desarrollar un interfaz cerebro computador controlable
naturalmente que pueda predecir trayectorias de movimiento imaginadas. El enfoque para alcanzar
este objetivo fue encontrar una correlación entre el movimiento y los datos cerebrales
que puedan ser utilizados posteriormente para la predicción de las trayectorias de movimiento
sólo por medio de señales cerebrales. Para encontrar esta correlación, se realizó un experimento,
en cual un participante tuvo que realizar movimientos desencadenados con su brazo derecho a
cuatro puntos diferentes. Durante el examen de los movimientos, se registraron los datos cinemáticos y de EEG del participante. Después de una etapa de pre-procesamiento, se calcularon
las velocidades en las direcciones x y y, de los datos cinemáticos, y la potencia de la banda, de
los datos EEG en diferentes rangos de frecuencia, y se utilizaron como características para el
cálculo de la correlación mediante con una regresión lineal múltiple. Al aplicar el parámetro
de regresión resultante para predecir trayectorias a partir de señales de EEG, las mejores precisiones
estuvieron en el rango de frecuencia mu e inferior en beta, como se esperaba. Sin
embargo, los resultados no fueron suficientemente precisos como para usarlas para el control de
una aplicación.<br>Tesis
33
Callh, Sebastian. "Trajectory-based Arrival Time Prediction using Gaussian Processes : A motion pattern modeling approach." Thesis, Linköpings universitet, Institutionen för datavetenskap, 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-158623.
Full textAbstract:
As cities grow, efficient public transport systems are becoming increasingly important. To offer a more efficient service, public transport providers use systems that predict arrival times of buses, trains and similar vehicles, and present this information to the general public. The accuracy and reliability of these predictions are paramount, since many people depend on them, and erroneous predictions reflect badly on the public transport provider. When public transport vehicles move throughout the cities, they create motion patterns, which describe how their positions change over time. This thesis proposes a way of modeling their motion patterns using Gaussian processes, and investigates whether it is possible to predict the arrival times of public transport buses in Linköping based on their motion patterns. The results are evaluated by comparing the accuracy of the model with a simple baseline model and a recurrent neural network (RNN), and the results show that the proposed model achieves superior performance to that of an RNN trained on the same amounts of data, with excellent explainability and quantifiable uncertainty. However, an RNN is capable of training on much more data than the proposed model in the same amount of time, so in a scenario with large amounts of data the RNN outperforms the proposed model.
34
Bahrampouri, Mahdi. "Ground Motion Prediction Equations for Non-Spectral Parameters using the KiK-net Database." Thesis, Virginia Tech, 2017. http://hdl.handle.net/10919/87704.
Full textAbstract:
The KiK-net ground motion database is used to develop ground motion prediction equations for Arias Intensity (Ia), 5-95% Significant Duration (Ds5-95), and 5-75% Significant Duration (Ds5-75). Relationships are developed both for shallow crustal earthquakes and subduction zone earthquakes (hypocentral depth less than 45 km). The models developed consider site amplification using VS30 and the depth to a layer with VS=800 m/s (h800). We observe that the site effect for
is magnitude dependent. For Ds5-95 and Ds5-75, we also observe strong magnitude dependency in distance attenuation. We compare the results with previous GMPEs for Japanese earthquakes and observe that the relationships are similar. The results of this study also allow a comparison between earthquakes in shallow-crustal regions, and subduction regions. This comparison shows that Arias Intensity has similar magnitude and distance scaling between both regions and generally Arias Intensity of shallow crustal motions are higher than subduction motions. On the other hand, the duration of shallow crustal motions are longer than subduction earthquakes except for records with large distance and small magnitude causative earthquakes. Because small shallow crustal events saturate with distance, ground motions with large distances and small magnitudes have shorter duration for shallow crustal events than subduction earthquakes.
35
Sugito, Masata. "EARTHQUAKE MOTION PREDICTION, MICROZONATION, AND BURIED PIPE RESPONSE FOR URBAN SEISMIC DAMAGE ASSESSMENT." Kyoto University, 1987. http://hdl.handle.net/2433/138405.
Full text
36
Fan, Zheyu Jerry. "Kalman Filter Based Approach : Real-time Control-based Human Motion Prediction in Teleoperation." Thesis, KTH, Skolan för datavetenskap och kommunikation (CSC), 2016. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-189210.
Full textAbstract:
This work is to investigate the performance of two Kalman Filter Algorithms, namely Linear Kalman Filter and Extended Kalman Filter on control-based human motion prediction in a real-time teleoperation. The Kalman Filter Algorithm has been widely used in research areas of motion tracking and GPS-navigation. However, the potential of human motion prediction by utilizing this algorithm is rarely being mentioned. Combine with the known issue - the delay issue in today’s teleoperation services, the author decided to build a prototype of simple teleoperation model based on the Kalman Filter Algorithm with the aim of eliminated the unsynchronization between the user’s inputs and the visual frames, where all the data were transferred over the network. In the first part of the thesis, two types of Kalman Filter Algorithm are applied on the prototype to predict the movement of the robotic arm based on the user’s motion applied on a Haptic Device. The comparisons in performance among the Kalman Filters have also been focused. In the second part, the thesis focuses on optimizing the motion prediction which based on the results of Kalman filtering by using the smoothing algorithm. The last part of the thesis examines the limitation of the prototype, such as how much the delays are accepted and how fast the movement speed of the Phantom Haptic can be, to still be able to obtain reasonable predations with acceptable error rate. The results show that the Extended Kalman Filter has achieved more advantages in motion prediction than the Linear Kalman Filter during the experiments. The unsynchronization issue has been effectively improved by applying the Kalman Filter Algorithm on both state and measurement models when the latency is set to below 200 milliseconds. The additional smoothing algorithm further increases the accuracy. More important, it also solves shaking issue on the visual frames on robotic arm which is caused by the wavy property of the Kalman Filter Algorithm. Furthermore, the optimization method effectively synchronizes the timing when robotic arm touches the interactable object in the prediction. The method which is utilized in this research can be a good reference for the future researches in control-based human motion tracking and prediction.<br>Detta arbete fokuserar på att undersöka prestandan hos två Kalman Filter Algoritmer, nämligen Linear Kalman Filter och Extended Kalman Filter som används i realtids uppskattningar av kontrollbaserad mänsklig rörelse i teleoperationen. Dessa Kalman Filter Algoritmer har används i stor utsträckning forskningsområden i rörelsespårning och GPS-navigering. Emellertid är potentialen i uppskattning av mänsklig rörelse genom att utnyttja denna algoritm sällan nämnas. Genom att kombinera med det kända problemet – fördröjningsproblem i dagens teleoperation tjänster beslutar författaren att bygga en prototyp av en enkel teleoperation modell vilket är baserad på Kalman Filter algoritmen i syftet att eliminera icke-synkronisering mellan användarens inmatningssignaler och visuella information, där alla data överfördes via nätverket. I den första delen av avhandlingen appliceras både Kalman Filter Algoritmer på prototypen för att uppskatta rörelsen av robotarmen baserat på användarens rörelse som anbringas på en haptik enhet. Jämförelserna i prestandan bland de Kalman Filter Algoritmerna har också fokuserats. I den andra delen fokuserar avhandlingen på att optimera uppskattningar av rörelsen som baserat på resultaten av Kalman-filtrering med hjälp av en utjämningsalgoritm. Den sista delen av avhandlingen undersökes begräsning av prototypen, som till exempel hur mycket fördröjningar accepteras och hur snabbt den haptik enheten kan vara, för att kunna erhålla skäliga uppskattningar med acceptabel felfrekvens. Resultaten visar att den Extended Kalman Filter har bättre prestandan i rörelse uppskattningarna än den Linear Kalman Filter under experimenten. Det icke-synkroniseringsproblemet har förbättrats genom att tillämpa de Kalman Filter Algoritmerna på både statliga och värderingsmodeller när latensen är inställd på under 200 millisekunder. Den extra utjämningsalgoritmen ökar ytterligare noggrannheten. Denna algoritm löser också det skakande problem hos de visuella bilder på robotarmen som orsakas av den vågiga egenskapen hos Kalman Filter Algoritmen. Dessutom effektivt synkroniserar den optimeringsmetoden tidpunkten när robotarmen berör objekten i uppskattningarna. Den metod som används i denna forskning kan vara en god referens för framtida undersökningar i kontrollbaserad rörelse- spåning och uppskattning.
37
Boonpratatong, Amaraporn. "Motion prediction and dynamic stability analysis of human walking : the effect of leg property." Thesis, University of Manchester, 2013. https://www.research.manchester.ac.uk/portal/en/theses/motion-prediction-and-dynamic-stability-analysis-of-human-walking-the-effect-of-leg-property(f36922af-1231-4dac-a92f-a16cbed8d701).html.
Full textAbstract:
The objective of this thesis is to develop and validate a computational framework based on mathematical models for the motion prediction and dynamic stability quantification of human walking, which can differentiate the dynamic stability of human walking with different mechanical properties of the leg. Firstly, a large measurement database of human walking motion was created. It contains walking measurement data of 8 subjects on 3 self-selected walking speeds, which 10 trials were recorded at each walking speed. The motion of whole-body centre of mass and the leg were calculated from the kinetic-kinematic measurement data. The fundamentals of leg property have been presented, and the parameters of leg property were extracted from the measurement data of human walking where the effects of walking speed and condition of foot-ground contact were investigated. Three different leg property definitions comprising linear axial elastic leg property, nonlinear axial elastic leg property and linear axial-tangential elastic leg property were used to extracted leg property parameters. The concept of posture-dependent leg property has been proposed, and the leg property parameters were extracted from the measurement data of human walking motion where the effects of walking speed and condition of foot-ground contact were also investigated. The compliant leg model with axial elastic property (CAE) was used for the dynamic stability analysis of human walking with linear and nonlinear axial elastic leg property. The compliant leg model with axial and tangential elastic property (CATE) was used for that with linear axial-tangential elastic leg property. The posture - dependent elastic leg model (PDE) was used for that with posture-dependent leg property. It was found that, with linear axial elastic leg property, the global stability of human walking improves with the bigger touchdown contact angle. The average leg property obtained from the measurement data of all participants allows the maximum global stability of human walking. With nonlinear axial elastic leg property, the global stability decreases with the stronger nonlinearity of leg stiffness. The incorporation of the tangential elasticity improves the global stability and shifts the stable walking velocity close to that of human walking at self-selected low speed (1.1-1.25 m/s).By the PDE model, the human walking motions were better predicted than by the CATE model. The effective range of walking prediction was enlarged to 1.12 – 1.8 m/s. However, represented by PDE model, only 1-2 walking steps can be achieved. In addition, the profiles of mechanical energies represented by the PDE model are different from that of the orbital stable walking represented by CATE model. Finally, the minimal requirements of the human walking measurements and the flexibility of simple walking models with deliberate leg property definitions allow the computational framework to be applicable in the dynamic stability analysis of the walking motion with a wide variety of mechanical property of the leg.
38
Sharma, Yachna. "Surgical skill assessment using motion texture analysis." Diss., Georgia Institute of Technology, 2014. http://hdl.handle.net/1853/51890.
Full textAbstract:
In this thesis, we propose a framework for automated assessment of surgical skills to expedite the manual assessment process and to provide unbiased evaluations with possible dexterity feedback. Evaluation of surgical skills is an important aspect in training of medical students. Current practices rely on manual evaluations from faculty and residents and are time consuming. Proposed solutions in literature involve retrospective evaluations such as watching the offline videos. It requires precious time and attention of expert surgeons and may vary from one surgeon to another. With recent advancements in computer vision and machine learning techniques, the retrospective video evaluation can be best delegated to the computer algorithms. Skill assessment is a challenging task requiring expert domain knowledge that may be difficult to translate into algorithms. To emulate this human observation process, an appropriate data collection mechanism is required to track motion of the surgeon's hand in an unrestricted manner. In addition, it is essential to identify skill defining motion dynamics and skill relevant hand locations. This Ph.D. research aims to address the limitations of manual skill assessment by developing an automated motion analysis framework. Specifically, we propose (1) to design and implement quantitative features to capture fine motion details from surgical video data, (2) to identify and test the efficacy of a core subset of features in classifying the surgical students into different expertise levels, (3) to derive absolute skill scores using regression methods and (4) to perform dexterity analysis using motion data from different hand locations.
39
Hürtgen, Gisela [Verfasser], Achim [Akademischer Betreuer] Stahl, and Michael J. [Akademischer Betreuer] Eble. "Determination of lung tumour motion from PET raw data used for accelerometer based motion prediction / Gisela Hürtgen ; Achim Stahl, Michael J. Eble." Aachen : Universitätsbibliothek der RWTH Aachen, 2018. http://d-nb.info/1171323948/34.
Full text
40
Zhang, Harley (Harley H. ). "Analysis of one-dimensional transforms in coding motion compensation prediction residuals for video applications." Thesis, Massachusetts Institute of Technology, 2011. http://hdl.handle.net/1721.1/66707.
Full textAbstract:
Thesis (M. Eng.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2011.<br>This electronic version was submitted by the student author. The certified thesis is available in the Institute Archives and Special Collections.<br>Cataloged from student submitted PDF version of thesis.<br>Includes bibliographical references (p. 49).<br>In video coding, motion compensation prediction provides significant increases in overall compression efficiency. The prediction residuals are typically treated as images and compressed by applying two-dimensional transforms such as the two-dimensional discrete cosine transform (2D-DCT). Previous work has found that the use of direction-adaptive one-dimensional discrete cosine transforms (1D-DCTs) in coding motion compensation residuals can provide significant additional bitrate savings. However, this requires optimization over all of the available transforms to minimize the overall bitrate, which can be expensive in terms of time and computation. In this thesis, we examine the use of only the horizontal and vertical 1D-DCTs in addition to the 2D-DCT for coding motion compensation residuals. By reducing the number of available transforms, the amount of required computation decreases significantly, with a potential cost in performance. We perform experiments using a modified H.264/AVC codec to compare the performance of using different sets of available transforms. The results indicate that for typical applications of video coding, most of the performance benefit from using directional 1D-DCTs can be retained by keeping only the horizontal and vertical 1D-DCTs.<br>by Harley Zhang.<br>M.Eng.
41
Hayes, E. R. "The prediction of droplet motion and breakup using a vortex model for turbulent flows." Thesis, Cranfield University, 1988. http://dspace.lib.cranfield.ac.uk/handle/1826/10285.
Full textAbstract:
This document describes the development of a computational model to
study the movement and breakup _of droplets in turbulent
two-component flows. The aim is to produce a suitable model which
will be economical of computing resources and practical for
engineering applications. The application of particular interest
here is that of water droplets in fully developed turbulent pipe
flows of oil.
The computational method uses Vortex filaments to produce, in a
novel way, instantaneous fluctuating velocities within the flow
domain. The trajectory of a particle within this field is predicted
by integrating the theoretical law of motion for the particle.
In addition, the breakup of a fluid particle in the turbulent field
may be predicted using an empirical criterion formulated using data
obtained from a series of experiments. The tests were designed to
study the deformation and breakup of a single water droplet in oil
subjected to shear.
Wherever possible the results of each development stage of the model
were compared with work published in the literature.
42
Arango-Gaviria, Maria Cristina. "Ground-motion prediction for subduction-zone earthquakes : insights from South and Central American data." Thesis, Imperial College London, 2010. http://hdl.handle.net/10044/1/5631.
Full textAbstract:
Models to predict the ground motion for earthquakes that occur in subduction zones are of great importance for earthquake risk reduction and mitigation in many parts of the world where there is a significant hazard from large earthquakes along the subduction interface and from earthquakes within the subducting slab. Most existing ground-motion predictive equations for subduction-zone events are primarily based on strong-motion recordings from Japan, Cascadia, Mexico, Alaska and New Zealand. In contrast, few records from South and Central America have been included in global predictive equations to date, although a major proportion of the seismicity of these regions is related to subduction-zone processes. The development of a strong-motion database from subduction-type events in South and Central America is therefore an important and essential step for ground-motion prediction in these regions as well as other subduction zones in the world. In this project two databases of strong-motion records from subduction-zone events along the Peruvian-Chilean and the Central American subduction zones have been developed. The Central American database compiled during this study consists of 554 triaxial ground-motion recordings from both interface and intraslab-type events of magnitudes between 5.0≤MW≤7.7. The database compiled for South America consists of 98 triaxial ground-motion recordings from 15 subduction-type events of magnitudes 6.3≤MW≤8.4, recorded at 55 different sites in Peru and Chile, between 1966 and 2007. These datasets have then been used to investigate the extent to which global and regional models for subduction regimes could be applied for the prediction of ground motions from the subduction events in these regions, following a maximum-likelihood approach. Regional differences in the ground-motion amplitudes amongst the South and Central America subduction zones are examined and preliminary adjustments to existing equations are made in order to resolve the differences between observed ground motions and predictions from these equations. This has led to suggestions for the prediction of ground motions from subductionzone earthquakes in the South and Central American regions.
43
Aryawan, Iwan Darajat. "Development of analysis methods for the assessment of hull girder loading and strength of a turret moored FPSO." Thesis, University of Newcastle Upon Tyne, 2000. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.327278.
Full text
44
Davuluri, Pavani. "Prediction of Breathing Patterns Using Neural Networks." VCU Scholars Compass, 2008. http://scholarscompass.vcu.edu/etd/718.
Full textAbstract:
During the radio therapy treatment, it has been difficult to synchronize the radiation beam with the tumor position. Many compensation techniques have been used before. But all these techniques have some system latency, up to a few hundred milliseconds. Hence it is necessary to predict tumor position to compensate for the control system latency. In recent years, many attempts have been made to predict the position of a moving tumor during respiration. Analyzing external breathing signals presents a methodology in predicting the tumor position. Breathing patterns vary from very regular to irregular patterns. The irregular breathing patterns make prediction difficult. A solution is presented in this paper which utilizes neural networks as the predictive filter to determine the tumor position up to 500 milliseconds in the future. Two different neural network architectures, feedforward backpropagation network and recurrent network, are used for prediction. These networks are initialized in the same manner for the comparison of their prediction accuracies. The networks are able to predict well for all the 5 breathing cases used in the research and the results of both the networks are acceptable and comparable. Furthermore, the network parameters are optimized using a genetic algorithm to improve the performance. The optimization results obtained proved to improve the accuracy of the networks. The results of both the networks showed that the networks are good for prediction of different breathing behaviors.
45
Baier, Volker [Verfasser]. "Motion perception and prediction / Volker Baier." 2006. http://d-nb.info/985175052/34.
Full text
46
Lei, Chun Chou, and 周雷峻. "A Dynamic Vector Motion Prediction Algorithm." Thesis, 2010. http://ndltd.ncl.edu.tw/handle/20994717687114093180.
Full text
47
詹文志. "Mobile Motion Prediction and QoS Improvement." Thesis, 2004. http://ndltd.ncl.edu.tw/handle/02417103242283851294.
Full textAbstract:
碩士<br>國立中正大學<br>資訊管理學系<br>92<br>There are many way to lower handoff drop rate, one of them is prediction. If we can predict the next cell which people will move in, we could preserve bandwidth for him or her, when people move in that cell, the phone call will not drop because of bandwidth reservation. Many people had develop their method to predict the user moving direction, but most of them use sophisticate stochastic processes or they need record huge data to complete the job. We are trying to use simple calculation and a little extract data to predict the user moving direction. What we are trying to do is using less cost to achieve the same, even better performance. Our prediction method keeps track of user mobility patterns and traffic patterns between cells. With the easy path comparing, we can derivate condition probability and the next target cell, the target cell will informed to reserve bandwidth basis of this probability. Through adjusting the reserved bandwidth dynamically, we could maintain the handoff drop rate under target value, mean while, using bandwidths efficiently and improving the quality of services.
48
Uou, Sheng-Tsang, and 游勝滄. "MOTION VECTOR PREDICTION Using CANDIDATE SET." Thesis, 2014. http://ndltd.ncl.edu.tw/handle/17265310302118610621.
Full textAbstract:
碩士<br>國立臺灣海洋大學<br>資訊工程學系<br>102<br>For video coding standards with high compression ratio and quality, prediction is an essential step. If the prediction is more accurate, then lower bit-rate will be achieved. In this paper, a method is proposed to improve the coding efficiency for motion vectors using predicted motion vector candidate set (PMVCS). PMVCS consists of the motion vectors of blocks, which are the spatial and temporal neighbors of an encoding block. Using the proposed method, a better predicted motion vector can be obtained, which lead to fewer bits allocated for motion vectors. Compared with JM18.4, the proposed method can reduce the bit allocation for motion vectors by 1.37% in average using the image sequence “Bus.” The proposed method can reduce the bit allocation for motion vector of error correction technique by about 0.31% using the same image sequence.
49
Chibisov, Dmitry [Verfasser]. "Design of algorithms for motion planning and motion prediction / Dmitry Chibisov." 2009. http://d-nb.info/1000381056/34.
Full text
50
Chien, Cheng-hui, and 簡誠輝. "Motion Estimation for Inter Prediction in HEVC." Thesis, 2013. http://ndltd.ncl.edu.tw/handle/94610595021564910069.
Full textAbstract:
碩士<br>國立中央大學<br>通訊工程學系<br>101<br>Inter Prediction of HEVC standard structure includes both Merge Mode Decision and Inter Mode Decision. Reviewing the previous work, someone exploited Template Matching algorithm which employs encoded information to predict in Inter Prediction. Under the condition that it is not necessary to transit header, decoder can reconstruct pictures to reach a reduction of bitrate. In this work, we utilize the same concept to apply on Inter Mode Decision. We proposed Template Matching algorithm in Uni-prediction and use both SABPD and Template Matching algorithm in Bi-prediction. Similarly, under the condition of without transition of header with motion vector, decoder can reconstruct pictures. The lower corrected probability of prediction results in worse encoding performance. We combine advantages of our proposed algorithm, SABPD and Template Matching, with advantages of HEVC standard structure. Finally, we combine Merge Mode Decision and Inter Mode Decision. In the same picture quality, the reduction of bitrate reaches 1.581%. The experiment results show that our proposed algorithm applying on HEVC standard structure can achieve better encoding performance.