Dissertations / Theses on the topic 'Neural network model of identification'
To see the other types of publications on this topic, follow the link: Neural network model of identification.
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 'Neural network model of identification.'
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
Wilhelm, Hedwig. "A Neural Network Model of Invariant Object Identification." Doctoral thesis, Universitätsbibliothek Leipzig, 2010. http://nbn-resolving.de/urn:nbn:de:bsz:15-qucosa-62050.
Full textAbstract:
Invariant object recognition is maybe the most basic and fundamental property of our visual system. It is the basis of many other cognitive tasks, like motor actions and social interactions. Hence, the theoretical understanding and modeling of invariant object recognition is one of the central problems in computational neuroscience.
Indeed, object recognition consists of two different tasks: classification and identification.
The focus of this thesis is on object identification under the basic geometrical
transformations shift, scaling, and rotation. The visual system can
perform shift, size, and rotation invariant object identification.
This thesis consists of two parts. In the first part, we present and investigate the VisNet model proposed by Rolls. The generalization problems of VisNet triggered our development of a new neural network model for invariant object identification. Starting point for an improved generalization behavior is the search for an operation that extracts images features that are invariant under shifts, rotations, and scalings. Extracting invariant features guarantees that an object seen once in a specific pose can be identified in any pose.
We present and investigate our model in the second part of this thesis.
2
Samal, Mahendra Engineering & Information Technology Australian Defence Force Academy UNSW. "Neural network based identification and control of an unmanned helicopter." Awarded by:University of New South Wales - Australian Defence Force Academy. Engineering & Information Technology, 2009. http://handle.unsw.edu.au/1959.4/43917.
Full textAbstract:
This research work provides the development of an Adaptive Flight Control System (AFCS) for autonomous hover of a Rotary-wing Unmanned Aerial Vehicle (RUAV). Due to the complex, nonlinear and time-varying dynamics of the RUAV, indirect adaptive control using the Model Predictive Control (MPC) is utilised. The performance of the MPC mainly depends on the model of the RUAV used for predicting the future behaviour. Due to the complexities associated with the RUAV dynamics, a neural network based black box identification technique is used for modelling the behaviour of the RUAV. Auto-regressive neural network architecture is developed for offline and online modelling purposes. A hybrid modelling technique that exploits the advantages of both the offline and the online models is proposed. In the hybrid modelling technique, the predictions from the offline trained model are corrected by using the error predictions from the online model at every sample time. To reduce the computational time for training the neural networks, a principal component analysis based algorithm that reduces the dimension of the input training data is also proposed. This approach is shown to reduce the computational time significantly. These identification techniques are validated in numerical simulations before flight testing in the Eagle and RMAX helicopter platforms. Using the successfully validated models of the RUAVs, Neural Network based Model Predictive Controller (NN-MPC) is developed taking into account the non-linearity of the RUAVs and constraints into consideration. The parameters of the MPC are chosen to satisfy the performance requirements imposed on the flight controller. The optimisation problem is solved numerically using nonlinear optimisation techniques. The performance of the controller is extensively validated using numerical simulation models before flight testing. The effects of actuator and sensor delays and noises along with the wind gusts are taken into account during these numerical simulations. In addition, the robustness of the controller is validated numerically for possible parameter variations. The numerical simulation results are compared with a base-line PID controller. Finally, the NN-MPCs are flight tested for height control and autonomous hover. For these, SISO as well as multiple SISO controllers are used. The flight tests are conducted in varying weather conditions to validate the utility of the control technique. The NN-MPC in conjunction with the proposed hybrid modelling technique is shown to handle additional disturbances successfully. Extensive flight test results provide justification for the use of the NN-MPC technique as a reliable technique for control of non-linear complex dynamic systems such as RUAVs.
3
Ciccone, Francesco. "Dynamic system model identification of inertial sensors by means of neural networks." Master's thesis, Alma Mater Studiorum - Università di Bologna, 2020. http://amslaurea.unibo.it/21548/.
Full textAbstract:
The thesis presents the design of a feedforward neural network for the model identification of a dynamical system of a general inertial sensor.
According to the universal approximation theorem, feedforward network with a linear output layer and at least one hidden layer with any activation function can approximate any measurable function with any desired non-zero amount of error provided that the network is given enough hidden units. This theorem simply states that no matter what function we are trying to learn there is always a neural network which will be able to represent the function. So, strong of this result, the work consisted to simulate a black box approach in which the data of input and output of the dynamical system have been used first to train the neural network to predict the future behaviour of the system itself, and then to validate the model.
4
Hay, Robert James. "Identification of robotic manipulators' inverse dynamics coefficients via model-based adaptive networks." Thesis, Loughborough University, 1998. https://dspace.lboro.ac.uk/2134/32803.
Full textAbstract:
The values of a given manipulator's dynamics coefficients need to be accurately identified in order to employ model-based algorithms in the control of its motion. This thesis details the development of a novel form of adaptive network which is capable of accurately learning the coefficients of systems, such as manipulator inverse dynamics, where the algebraic form is known but the coefficients' values are not. Empirical motion data from a pair of PUMA 560s has been processed by the Context-Sensitive Linear Combiner (CSLC) network developed, and the coefficients of their inverse dynamics identified. The resultant precision of control is shown to be superior to that achieved from employing dynamics coefficients derived from direct measurement. As part of the development of the CSLC network, the process of network learning is examined. This analysis reveals that current network architectures for processing analogue output systems with high input order are highly unlikely to produce solutions that are good estimates throughout the entire problem space. In contrast, the CSLC network is shown to generalise intrinsically as a result of its structure, whilst its training is greatly simplified by the presence of only one minima in the network's error hypersurface. Furthermore, a fine-tuning algorithm for network training is presented which takes advantage of the CSLC network's single adaptive layer structure and does not rely upon gradient descent of the network error hypersurface, which commonly slows the later stages of network training.
5
Shamsudin, Syariful Syafiq. "The Development of Neural Network Based System Identification and Adaptive Flight Control for an AutonomousHelicopter System." Thesis, University of Canterbury. Mechanical Engineering Department, 2013. http://hdl.handle.net/10092/8803.
Full textAbstract:
This thesis presents the development of self adaptive flight controller for an unmanned helicopter system under hovering manoeuvre. The neural network (NN) based model predictive control (MPC) approach is utilised in this work. We use this controller due to its ability to handle system constraints and the time varying nature of the helicopter dynamics. The non-linear NN based MPC controller is known to produce slow solution convergence due to high computation demand in the optimisation process. To solve this problem, the automatic flight controller system is designed using the NN based approximate predictive control (NNAPC) approach that relies on extraction of linear models from the non-linear NN model at each time step. The sequence of control input is generated using the prediction from the linearised model and the optimisation routine of MPC subject to the imposed hard constraints. In this project, the optimisation of the MPC objective criterion is implemented using simple and fast computation of the Hildreth's Quadratic Programming (QP) procedure.
The system identification of the helicopter dynamics is typically performed using the time regression network (NNARX) with the input variables. Their time lags are fed into a static feed-forward network such as the multi-layered perceptron (MLP) network. NN based modelling that uses the NNARX structure to represent a dynamical system usually requires a priori knowledge about the model order of the system. Low model order assumption generally leads to deterioration of model prediction accuracy. Furthermore, massive amount of weights in the standard NNARX model can result in an increased NN training time and limit the application of the NNARX model in a real-time application. In this thesis, three types of NN architectures are considered to represent the time regression network: the multi-layered perceptron (MLP), the hybrid multi-layered perceptron (HMLP) and the modified Elman network. The latter two architectures are introduced to improve the training time and the convergence rate of the NN model. The model structures for the proposed architecture are selected using the proposed Lipschitz coefficient and k-cross validation methods to determine the best network configuration that guarantees good generalisation performance for model prediction.
Most NN based modelling techniques attempt to model the time varying dynamics of a helicopter system using the off-line modelling approach which are incapable of representing the entire operating points of the flight envelope very well. Past research works attempt to update the NN model during flight using the mini-batch Levenberg-Marquardt (LM) training. However, due to the limited processing power available in the real-time processor, such approaches can only be employed to relatively small networks and they are limited to model uncoupled helicopter dynamics. In order to accommodate the time-varying properties of helicopter dynamics which change frequently during flight, a recursive Gauss-Newton (rGN) algorithm is developed to properly track the dynamics of the system under consideration.
It is found that the predicted response from the off-line trained neural network model is suitable for modelling the UAS helicopter dynamics correctly. The model structure of the MLP network can be identified correctly using the proposed validation methods. Further comparison with model structure selection from previous studies shows that the identified model structure using the proposed validation methods offers improvements in terms of generalisation error. Moreover, the minimum number of neurons to be included in the model can be easily determined using the proposed cross validation method. The HMLP and modified Elman networks are proposed in this work to reduce the total number of weights used in the standard MLP network. Reduction in the total number of weights in the network structure contributes significantly to the reduction in the computation time needed to train the NN model. Based on the validation test results, the model structure of the HMLP and modified Elman networks are found to be much smaller than the standard MLP network. Although the total number of weights for both of the HMLP and modified Elman networks are lower than the MLP network, the prediction performance of both of the NN models are on par with the prediction quality of the MLP network.
The identification results further indicate that the rGN algorithm is more adaptive to the changes in dynamic properties, although the generalisation error of repeated rGN is slightly higher than the off-line LM method. The rGN method is found capable of producing satisfactory prediction accuracy even though the model structure is not accurately defined. The recursive method presented here in this work is suitable to model the UAS helicopter in real time within the control sampling time and computational resource constraints. Moreover, the implementation of proposed network architectures such as the HMLP and modified Elman networks is found to improve the learning rate of NN prediction. These positive findings inspire the implementation of the real time recursive learning of NN models for the proposed MPC controller. The proposed system identification and hovering control of the unmanned helicopter system are validated in a 6 degree of freedom (DOF) safety test rig. The experimental results confirm the effectiveness and the robustness of the proposed controller under disturbances and parameter changes of the dynamic system.
6
Wredh, Simon. "Neural Network Based Model Predictive Control of Turbulent Gas-Solid Corner Flow." Thesis, Uppsala universitet, Signaler och system, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-420056.
Full textAbstract:
Over the past decades, attention has been brought to the importance of indoor air quality and the serious threat of bio-aerosol contamination towards human health. A novel idea to transport hazardous particles away from sensitive areas is to automatically control bio-aerosol concentrations, by utilising airflows from ventilation systems. Regarding this, computational fluid dynamics (CFD) may be employed to investigate the dynamical behaviour of airborne particles, and data-driven methods may be used to estimate and control the complex flow simulations. This thesis presents a methodology for machine-learning based control of particle concentrations in turbulent gas-solid flow. The aim is to reduce concentration levels at a 90 degree corner, through systematic manipulation of underlying two-phase flow dynamics, where an energy constrained inlet airflow rate is used as control variable. A CFD experiment of turbulent gas-solid flow in a two-dimensional corner geometry is simulated using the SST k-omega turbulence model for the gas phase, and drag force based discrete random walk for the solid phase. Validation of the two-phase methodology is performed against a backwards facing step experiment, with a 12.2% error correspondence in maximum negative particle velocity downstream the step. Based on simulation data from the CFD experiment, a linear auto-regressive with exogenous inputs (ARX) model and a non-linear ARX based neural network (NN) is used to identify the temporal relationship between inlet flow rate and corner particle concentration. The results suggest that NN is the preferred approach for output predictions of the two-phase system, with roughly four times higher simulation accuracy compared to ARX. The identified NN model is used in a model predictive control (MPC) framework with linearisation in each time step. It is found that the output concentration can be minimised together with the input energy consumption, by means of tracking specified target trajectories. Control signals from NN-MPC also show good performance in controlling the full CFD model, with improved particle removal capabilities, compared to randomly generated signals. In terms of maximal reduction of particle concentration, the NN-MPC scheme is however outperformed by a manually constructed sine signal. In conclusion, CFD based NN-MPC is a feasible methodology for efficient reduction of particle concentrations in a corner area; particularly, a novel application for removal of indoor bio-aerosols is presented. More generally, the results show that NN-MPC may be a promising approach to turbulent multi-phase flow control.
7
Yu, Ssu-Hsin. "Model-based identification and control of nonlinear dynamic systems using neural networks." Thesis, Massachusetts Institute of Technology, 1996. http://hdl.handle.net/1721.1/39609.
Full text
8
Mitchell, Ryan. "A WANFIS Model for Use in System Identification and Structural Control of Civil Engineering Structures." Digital WPI, 2012. https://digitalcommons.wpi.edu/etd-theses/1165.
Full textAbstract:
With the increased deterioration of infrastructure in this country, it has become important to find ways to maintain the strength and integrity of a structure over its design life. Being able to control the amount a structure displaces or vibrates during a seismic event, as well as being able to model this nonlinear behavior, provides a new challenge for structural engineers. This research proposes a wavelet-based adaptive neuro- fuzzy inference system for use in system identification and structural control of civil engineering structures. This algorithm combines aspects of fuzzy logic theory, neural networks, and wavelet transforms to create a new system that effectively reduces the number of sensors needed in a structure to capture its seismic response and the amount of computation time needed to model its nonlinear behavior. The algorithm has been tested for structural control using a three-story building equipped with a magnetorheological damper for system identification, an eight-story building, and a benchmark highway bridge. Each of these examples has been tested using a variety of earthquakes, including the El-Centro, Kobe, Hachinohe, Northridge, and other seismic events.
9
Al, Seyab Rihab Khalid Shakir. "Nonlinear model predictive control using automatic differentiation." Thesis, Cranfield University, 2006. http://hdl.handle.net/1826/1491.
Full textAbstract:
Although nonlinear model predictive control (NMPC) might be the best choice for a
nonlinear plant, it is still not widely used. This is mainly due to the computational
burden associated with solving online a set of nonlinear differential equations and a
nonlinear dynamic optimization problem in real time. This thesis is concerned with
strategies aimed at reducing the computational burden involved in different stages
of the NMPC such as optimization problem, state estimation, and nonlinear model
identification.
A major part of the computational burden comes from function and derivative evaluations
required in different parts of the NMPC algorithm. In this work, the problem is
tackled using a recently introduced efficient tool, the automatic differentiation (AD).
Using the AD tool, a function is evaluated together with all its partial derivative from
the code defining the function with machine accuracy.
A new NMPC algorithm based on nonlinear least square optimization is proposed.
In a first–order method, the sensitivity equations are integrated using a linear formula
while the AD tool is applied to get their values accurately. For higher order
approximations, more terms of the Taylor expansion are used in the integration for
which the AD is effectively used. As a result, the gradient of the cost function against
control moves is accurately obtained so that the online nonlinear optimization can be
efficiently solved.
In many real control cases, the states are not measured and have to be estimated for
each instance when a solution of the model equations is needed. A nonlinear extended
version of the Kalman filter (EKF) is added to the NMPC algorithm for this purpose.
The AD tool is used to calculate the required derivatives in the local linearization
step of the filter automatically and accurately.
Offset is another problem faced in NMPC. A new nonlinear integration is devised
for this case to eliminate the offset from the output response. In this method, an integrated disturbance model is added to the process model input or output to correct
the plant/model mismatch. The time response of the controller is also improved as a
by–product.
The proposed NMPC algorithm has been applied to an evaporation process and a
two continuous stirred tank reactor (two–CSTR) process with satisfactory results to
cope with large setpoint changes, unmeasured severe disturbances, and process/model
mismatches.
When the process equations are not known (black–box) or when these are too complicated
to be used in the controller, modelling is needed to create an internal model for
the controller. In this thesis, a continuous time recurrent neural network (CTRNN)
in a state–space form is developed to be used in NMPC context. An efficient training
algorithm for the proposed network is developed using AD tool. By automatically
generating Taylor coefficients, the algorithm not only solves the differentiation equations
of the network but also produces the sensitivity for the training problem. The
same approach is also used to solve online the optimization problem of the NMPC.
The proposed CTRNN and the predictive controller were tested on an evaporator
and two–CSTR case studies. A comparison with other approaches shows that the
new algorithm can considerably reduce network training time and improve solution
accuracy.
For a third case study, the ALSTOM gasifier, a NMPC via linearization algorithm is
implemented to control the system. In this work a nonlinear state–space class Wiener
model is used to identify the black–box model of the gasifier. A linear model of the
plant at zero–load is adopted as a base model for prediction. Then, a feedforward
neural network is created as the static gain for a particular output channel, fuel gas
pressure, to compensate its strong nonlinear behavior observed in open–loop simulations.
By linearizing the neural network at each sampling time, the static nonlinear
gain provides certain adaptation to the linear base model. The AD tool is used here
to linearize the neural network efficiently. Noticeable performance improvement is
observed when compared with pure linear MPC. The controller was able to pass all
tests specified in the benchmark problem at all load conditions.
10
Sonntag, Dag. "A Study of Quadrotor Modelling." Thesis, Linköpings universitet, Institutionen för datavetenskap, 2011. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-66503.
Full textAbstract:
Quadrotors are a type of aircraft that lately has gained increased popularity within the UAV-scientific area. Many research groups around the world have implemented control systems that allow for autonomous flight of quadrotors with the help of the known dynamics. This thesis presents two approaches to modelling the dynamics of the quadrotor. The first is a linear greybox approach where the structure is derived from known equations and some constants are measured and some identified through system identification techniques. The second model is a blackbox model where a neural network is trained and used. The two models are then evaluated using known error measurements with the help of previously recorded flight data and the results are presented. It is for example shown that with the untreated flight data the traditional greybox model have accurate dynamics but is sensitive to noise and drifts in the measurements. It is also shown that better results generally can be achieved using a neural network model, especially for noisy unpreprocessed data.
11
Koessler, Denise Renee. "A Predictive Model for Secondary RNA Structure Using Graph Theory and a Neural Network." Digital Commons @ East Tennessee State University, 2010. https://dc.etsu.edu/etd/1684.
Full textAbstract:
In this work we use a graph-theoretic representation of secondary RNA structure found in the database RAG: RNA-As-Graphs. We model the bonding of two RNA secondary structures to form a larger structure with a graph operation called merge. The resulting data from each tree merge operation is summarized and represented by a vector. We use these vectors as input values for a neural network and train the network to recognize a tree as RNA-like or not based on the merge data vector.
The network correctly assigned a high probability of RNA-likeness to trees identified as RNA-like in the RAG database, and a low probability of RNA-likeness to those classified as not RNA-like in the RAG database. We then used the neural network to predict the RNA-likeness of all the trees of order 9. The use of a graph operation to theoretically describe the bonding of secondary RNA is novel.
12
Wilgenbus, Erich Feodor. "The file fragment classification problem : a combined neural network and linear programming discriminant model approach / Erich Feodor Wilgenbus." Thesis, North-West University, 2013. http://hdl.handle.net/10394/10215.
Full textAbstract:
The increased use of digital media to store legal, as well as illegal data, has created the need
for specialized tools that can monitor, control and even recover this data. An important task
in computer forensics and security is to identify the true le type to which a computer le
or computer le fragment belongs. File type identi cation is traditionally done by means
of metadata, such as le extensions and le header and footer signatures. As a result,
traditional metadata-based le object type identi cation techniques work well in cases where
the required metadata is available and unaltered. However, traditional approaches are not
reliable when the integrity of metadata is not guaranteed or metadata is unavailable. As
an alternative, any pattern in the content of a le object can be used to determine the
associated le type. This is called content-based le object type identi cation.
Supervised learning techniques can be used to infer a le object type classi er by exploiting
some unique pattern that underlies a le type's common le structure. This study builds
on existing literature regarding the use of supervised learning techniques for content-based
le object type identi cation, and explores the combined use of multilayer perceptron neural
network classi ers and linear programming-based discriminant classi ers as a solution to the
multiple class le fragment type identi cation problem.
The purpose of this study was to investigate and compare the use of a single multilayer
perceptron neural network classi er, a single linear programming-based discriminant classi-
er and a combined ensemble of these classi ers in the eld of le type identi cation. The
ability of each individual classi er and the ensemble of these classi ers to accurately predict
the le type to which a le fragment belongs were tested empirically.
The study found that both a multilayer perceptron neural network and a linear programming-
based discriminant classi er (used in a round robin) seemed to perform well in solving
the multiple class le fragment type identi cation problem. The results of combining
multilayer perceptron neural network classi ers and linear programming-based discriminant
classi ers in an ensemble were not better than those of the single optimized classi ers.MSc (Computer Science), North-West University, Potchefstroom Campus, 2013
13
Pant, Gaurav. "Hybrid Dynamic Modelling of Engine Emissions on Multi-Physics Simulation Platform. A Framework Combining Dynamic and Statistical Modelling to Develop Surrogate Models of System of Internal Combustion Engine for Emission Modelling." Thesis, University of Bradford, 2018. http://hdl.handle.net/10454/17223.
Full text
14
Ben, Letaifa Wissal. "Le timing de versement des dividendes : étude de la réaction du marché boursier français et identification de ses déterminants." Thesis, Nice, 2013. http://www.theses.fr/2013NICE0058.
Full textAbstract:
La thèse vise à identifier, dans un premier temps, l’influence du timing de versement des dividendes des sociétés françaises cotées sur les cours boursiers. Elle cherche à identifier, dans un deuxième temps, les déterminants du timing de versement des dividendes. La démarche retenue pour argumenter ces propos est la suivante : dans une première partie, nous avons posé notre cadre théorique. Le positionnement de la thèse dans l’ancrage de la théorie politico-contracteulle et la théorie des signaux nous a orienté vers l’étude du contenu informationnel du timing de versement des dividendes dans un premier temps et à identifier ses déterminants dans un deuxième temps. La seconde partie est consacrée à l’étude empirique réalisée auprès de 69 entreprises initiatrices de dividendes cotées à l’indice SBF 120 durant l’année 2007 afin de répondre à notre premier objectif, et portée sur un échantillon de 57 sociétés françaises distributrices d’un dividende annuel durant la période 2003-2009 afin de répondre à notre second objectif. S’agissant de notre premier objectif, le recours à la méthodologie des études d’évènement a révélé que les cours réagissent à la date de versement des dividendes ce qui confirme que le timing de versement des dividendes possède un contenu informationnel. Quant à notre second objectif, les dispositions réglementaires souples sur la fixation de la date de versement du dividende et son emploi en tant que signal émis de la firme vers le marché posent la question du choix de cette date dans le contexte français à système juridique civil connu pour la protection des intérêts des actionnaires minoritaires. Les résultats de la littérature antérieure restent timides en raison de leur focalisation sur la date de versement du premier dividende – et notamment sur la probabilité d’initier un dividende suite à l’introduction en bourse. Les résultats de notre étude empirique confirment l’impact significatif de la présence d’un actionnaire majoritaire, de la profitabilité, de la liquidité et de la durée de versement du dividende précédent sur la fixation de la date de versement de cette année. Cet impact semble se manifester à travers une limitation de la durée entre la date de l’assemblée des actionnaires et la date de paiement effectif des dividendes et une reconnaissance de cette durée comme étant une bonne nouvelle par rapport aux autres signaux émis par l’entreprise au marché boursierThe purpose of this study is to identify the informational content of the dividend pay date and its determinants. Namely, is there information in the timing of the dividend payments? The empirical evidence indicates that the market reacts at the dividend pay date. Mean excess returns of stock prices on the pay date are significantly positive and are insignificant and negative around the entire population of dividend pay dates. On the other side we are interested in the determinants of the dividend pay date. Our multivariate analysis shows that the ownership structure, the liquidity of the firm, the result, and the previous timing of dividend payment influence the fixing of the dividend pay date. This impact is shown as shorten as the delay between the date of the general meeting and the dividend pay date. This duration is considered as good news and can be a signal employed to attract new investors in the stock market
15
Dabiri, Sina. "Semi-Supervised Deep Learning Approach for Transportation Mode Identification Using GPS Trajectory Data." Thesis, Virginia Tech, 2018. http://hdl.handle.net/10919/86845.
Full textAbstract:
Identification of travelers' transportation modes is a fundamental step for various problems that arise in the domain of transportation such as travel demand analysis, transport planning, and traffic management. This thesis aims to identify travelers' transportation modes purely based on their GPS trajectories. First, a segmentation process is developed to partition a user's trip into GPS segments with only one transportation mode. A majority of studies have proposed mode inference models based on hand-crafted features, which might be vulnerable to traffic and environmental conditions. Furthermore, the classification task in almost all models have been performed in a supervised fashion while a large amount of unlabeled GPS trajectories has remained unused. Accordingly, a deep SEmi-Supervised Convolutional Autoencoder (SECA) architecture is proposed to not only automatically extract relevant features from GPS segments but also exploit useful information in unlabeled data. The SECA integrates a convolutional-deconvolutional autoencoder and a convolutional neural network into a unified framework to concurrently perform supervised and unsupervised learning. The two components are simultaneously trained using both labeled and unlabeled GPS segments, which have already been converted into an efficient representation for the convolutional operation. An optimum schedule for varying the balancing parameters between reconstruction and classification errors are also implemented. The performance of the proposed SECA model, trip segmentation, the method for converting a raw trajectory into a new representation, the hyperparameter schedule, and the model configuration are evaluated by comparing to several baselines and alternatives for various amounts of labeled and unlabeled data. The experimental results demonstrate the superiority of the proposed model over the state-of-the-art semi-supervised and supervised methods with respect to metrics such as accuracy and F-measure.Master of Science
Identifying users' transportation modes (e.g., bike, bus, train, and car) is a key step towards many transportation related problems including (but not limited to) transport planning, transit demand analysis, auto ownership, and transportation emissions analysis. Traditionally, the information for analyzing travelers' behavior for choosing transport mode(s) was obtained through travel surveys. High cost, low-response rate, time-consuming manual data collection, and misreporting are the main demerits of the survey-based approaches. With the rapid growth of ubiquitous GPS-enabled devices (e.g., smartphones), a constant stream of users' trajectory data can be recorded. A user's GPS trajectory is a sequence of GPS points, recorded by means of a GPS-enabled device, in which a GPS point contains the information of the device geographic location at a particular moment. In this research, users' GPS trajectories, rather than traditional resources, are harnessed to predict their transportation mode by means of statistical models. With respect to the statistical models, a wide range of studies have developed travel mode detection models using on hand-designed attributes and classical learning techniques. Nonetheless, hand-crafted features cause some main shortcomings including vulnerability to traffic uncertainties and biased engineering justification in generating effective features. A potential solution to address these issues is by leveraging deep learning frameworks that are capable of capturing abstract features from the raw input in an automated fashion. Thus, in this thesis, deep learning architectures are exploited in order to identify transport modes based on only raw GPS tracks. It is worth noting that a significant portion of trajectories in GPS data might not be annotated by a transport mode and the acquisition of labeled data is a more expensive and labor-intensive task in comparison with collecting unlabeled data. Thus, utilizing the unlabeled GPS trajectory (i.e., the GPS trajectories that have not been annotated by a transport mode) is a cost-effective approach for improving the prediction quality of the travel mode detection model. Therefore, the unlabeled GPS data are also leveraged by developing a novel deep-learning architecture that is capable of extracting information from both labeled and unlabeled data. The experimental results demonstrate the superiority of the proposed models over the state-of-the-art methods in literature with respect to several performance metrics.
16
Lebeda, Aleš. "Model soustavy motorů s pružným členem." Master's thesis, Vysoké učení technické v Brně. Fakulta elektrotechniky a komunikačních technologií, 2012. http://www.nusl.cz/ntk/nusl-219693.
Full textAbstract:
This thesis deals with problem of experimental identification using principles of artificial intelligence and development of nonlinear models. It shows how to estimate parameters of nonlinear models and it compares different types of nonlinear models based on analytical analysis which were developed from measured data in simulation and real system motors with flexible component.
17
Ma, Xiren. "Deep Learning-Based Vehicle Recognition Schemes for Intelligent Transportation Systems." Thesis, Université d'Ottawa / University of Ottawa, 2021. http://hdl.handle.net/10393/42247.
Full textAbstract:
With the increasing highlighted security concerns in Intelligent Transportation System (ITS), Vision-based Automated Vehicle Recognition (VAVR) has attracted considerable attention recently. A comprehensive VAVR system contains three components: Vehicle Detection (VD), Vehicle Make and Model Recognition (VMMR), and Vehicle Re-identification (VReID). These components perform coarse-to-fine recognition tasks in three steps. The VAVR system can be widely used in suspicious vehicle recognition, urban traffic monitoring, and automated driving system. Vehicle recognition is complicated due to the subtle visual differences between different vehicle models. Therefore, how to build a VAVR system that can fast and accurately recognize vehicle information has gained tremendous attention.
In this work, by taking advantage of the emerging deep learning methods, which have powerful feature extraction and pattern learning abilities, we propose several models used for vehicle recognition. First, we propose a novel Recurrent Attention Unit (RAU) to expand the standard Convolutional Neural Network (CNN) architecture for VMMR. RAU learns to recognize the discriminative part of a vehicle on multiple scales and builds up a connection with the prominent information in a recurrent way. The proposed ResNet101-RAU achieves excellent recognition accuracy of 93.81% on the Stanford Cars dataset and 97.84% on the CompCars dataset. Second, to construct efficient vehicle recognition models, we simplify the structure of RAU and propose a Lightweight Recurrent Attention Unit (LRAU). The proposed LRAU extracts the discriminative part features by generating attention masks to locate the keypoints of a vehicle (e.g., logo, headlight). The attention mask is generated based on the feature maps received by the LRAU and the preceding attention state generated by the preceding LRAU. Then, by adding LRAUs to the standard CNN architectures, we construct three efficient VMMR models. Our models achieve the state-of-the-art results with 93.94% accuracy on the Stanford Cars dataset, 98.31% accuracy on the CompCars dataset, and 99.41% on the NTOU-MMR dataset. In addition, we construct a one-stage Vehicle Detection and Fine-grained Recognition (VDFG) model by combining our LRAU with the general object detection model. Results show the proposed VDFG model can achieve excellent performance with real-time processing speed. Third, to address the VReID task, we design the Compact Attention Unit (CAU). CAU has a compact structure, and it relies on a single attention map to extract the discriminative local features of a vehicle. We add two CAUs to the truncated ResNet to construct a small but efficient VReID model, ResNetT-CAU. Compared with the original ResNet, the model size of ResNetT-CAU is reduced by 60%. Extensive experiments on the VeRi and VehicleID dataset indicate the proposed ResNetT-CAU achieve the best re-identification results on both datasets. In summary, the experimental results on the challenging benchmark VMMR and VReID datasets indicate our models achieve the best VMMR and VReID performance, and our models have a small model size and fast image processing speed.
18
Jeník, Ivan. "Identifikace parametrů elasto-plastických modelů materiálu z experimentálních dat." Master's thesis, Vysoké učení technické v Brně. Fakulta strojního inženýrství, 2015. http://www.nusl.cz/ntk/nusl-231979.
Full textAbstract:
This master's thesis deals with the identification of the material flow curve from record of tensile test of smooth cylindrical specimen. First, necessary theory background is presented. Basic terms of incremental theory of plasticity, tensile test procedure and processing its outputs are described. Furthermore, possibilities of mathematical expression of the elastic-plastic material constitutive law, thus mathematical expression of the material flow curve itself. Mechanism of ductile damage of material is explained briefly as well. Overview of recent methods of the flow curve identification is given, focused on cases, when the stress distribution in a specimen is not uniaxial. That is either kind of analytic correction of basic formulas derived for uniaxial stress state, or application of mathematical optimization techniques combined with numerical simulation of the tensile test. Also unusual method of neural network is mentioned. For 8 given materials, the flow curve identification was performed using different methods. Namely by analytic correction, optimization, sequential identification and neural network. Algorithms of the last two methods were modified. Based on assessment of obtained results, application field and adjusting the parameters of single algorithms was recommended. It showed up, that an effective way to the accurate and credible results is the combination of different methods during flow curve identification procedure.
19
Радюк, Павло Михайлович, and Pavlo Radiuk. "Інформаційна технологія раннього діагностування пневмонії за індивідуальним підбором параметрів моделі класифікації медичних зображень легень." Дисертація, Хмельницький національний університет, 2021. http://elar.khnu.km.ua/jspui/handle/123456789/11937.
Full textAbstract:
Дисертаційна робота присвячена розв’язанню актуальної науково-прикладної задачі автоматизації процесу діагностування вірусного пневмонічного запалення за медичними зображеннями легень через розроблення інформаційної технології раннього діагностування пневмонії за індивідуальним підбором параметрів моделі класифікації медичних зображень легень. Застосування розробленої інформаційної технології раннього діагностування пневмонії в клінічній практиці дає змогу підвищити точність та надійність ідентифікації пневмонії на ранніх стадіях за медичними зображеннями грудної клітини людини.
Об’єктом дослідження є процес діагностування пневмонії за медичними зображеннями грудної клітини людини.
Предметом дослідження є моделі, методи та засоби інформаційної технології для раннього діагностування пневмонії за медичними зображеннями грудної клітини людини.
У дисертаційній роботі визначено актуальність застосування інформаційних технологій у галузі цифрового діагностування захворювань легень за медичними зображеннями грудної клітини. На основі проведено аналізу методів та підходів до виявлення пневмонії встановлено, що нейромережеві моделі є найкращим рішенням для розроблення інформаційної технології раннього діагностування. Досліджено методи для налаштування нейромережевої моделі та підходи до пояснення та інтерпретування результатів ідентифікації захворювання легень. За аналізом сучасних підходів, методів та інформаційних технологій для діагностування захворювання легень на ранніх стадіях за медичними зображеннями грудної клітини обґрунтовано потребу в створенні інформаційної технології раннього діагностування пневмонії.The present thesis is devoted to solving the topical scientific and applied problem of automating the process of diagnosing viral pneumonia by medical images of the lungs through the development of information technology for early diagnosis of pneumonia by the individual selection of parameters of the classification model by medical images of the lungs. Applying the developed information technology for the early diagnosis of pneumonia in clinical practice by medical images of the human chest increases the accuracy and reliability of pneumonia identification in the early stages
20
Arain, Muhammad Asif, Ayala Helon Vicente Hultmann, and Muhammad Adil Ansari. "Nonlinear System Identification Using Neural Network." University of Genova (Italy) and Warsaw University of Technology (Poland), 2012. http://urn.kb.se/resolve?urn=urn:nbn:se:oru:diva-28937.
Full textAbstract:
Magneto-rheological damper is a nonlinear system. In this case study, system has been identified using Neural Network tool. Optimization between number of neurons in the hidden layer and number of epochs has been achieved and discussed by using multilayer perceptron Neural Network.
21
Mezina, Anzhelika. "Superrozlišení obličeje ze sekvence snímků." Master's thesis, Vysoké učení technické v Brně. Fakulta elektrotechniky a komunikačních technologií, 2020. http://www.nusl.cz/ntk/nusl-413064.
Full textAbstract:
Táto práce se zabývá použitím hlubokého učení neuronových sítí ke zvýšení rozlišení obrázků, které obsahují obličeje. Tato metoda najde uplatnění v různých oblastech, zejména v bezpečnosti, například, při bezpečnostním incidentu, kdy policie potřebuje identifikovat podezřelého z nahraného videa ze sledovací kamery. Cílem této práce je navrhnout minimálně dvě architektury neuronových sítí, které budou pracovat se sekvencí snímků, a porovnat je s metodami zpracování jediného snímku. Pro tento účel je také vytvořena nová trénovací množina, obsahující sekvenci snímku obličeje. Metody zpracování jednoho snímku jsou natrénované na nové množině. Dále jsou navrženy nové metody zvětšení obrázků na základě sekvence snímků. Tyto metody jsou založené na U-Net modelu, který je úspěšný v segmentaci, ale také v superrozlišení. Pro zlepšení architektury byly použity reziduální bloky a jejich modifikace, a navíc také percepční ztrátová funkce, která dovoluje vyhnout se rozmazání a získání více detailů. První čast této práce je věnovana popisu neuronových sítí a některých architektur, jejichž modifikace mohou být použity v superrozlišení. Druhá část se poté zabývá popisem metod pro zvýšení rozlišení obrazu pomocí jednoho snímku, několika snímků a videa. Ve třetí části jsou popsány navržené metody a experimenty a v poslední části porovnaná metod založených na jednom snímku a několika snímcích. Navržené metody jsou schopny získat více detailů v obraze, ale mohou produkovat artefakty. Ty lze ale poté eliminovat pomocí filtru, například Gaussova. Nové metody méně selhávají při detekci obličejů, a to je podstatné u identifikace člověka v případě incidentu.
22
Li, Chao. "WELD PENETRATION IDENTIFICATION BASED ON CONVOLUTIONAL NEURAL NETWORK." UKnowledge, 2019. https://uknowledge.uky.edu/ece_etds/133.
Full textAbstract:
Weld joint penetration determination is the key factor in welding process control area. Not only has it directly affected the weld joint mechanical properties, like fatigue for example. It also requires much of human intelligence, which either complex modeling or rich of welding experience. Therefore, weld penetration status identification has become the obstacle for intelligent welding system. In this dissertation, an innovative method has been proposed to detect the weld joint penetration status using machine-learning algorithms.
A GTAW welding system is firstly built. Project a dot-structured laser pattern onto the weld pool surface during welding process, the reflected laser pattern is captured which contains all the information about the penetration status. An experienced welder is able to determine weld penetration status just based on the reflected laser pattern. However, it is difficult to characterize the images to extract key information that used to determine penetration status. To overcome the challenges in finding right features and accurately processing images to extract key features using conventional machine vision algorithms, we propose using convolutional neural network (CNN) to automatically extract key features and determine penetration status.
Data-label pairs are needed to train a CNN. Therefore, an image acquiring system is designed to collect reflected laser pattern and the image of work-piece backside. Data augmentation is performed to enlarge the training data size, which resulting in 270,000 training data, 45,000 validation data and 45,000 test data. A six-layer convolutional neural network (CNN) has been designed and trained using a revised mini-batch gradient descent optimizer. Final test accuracy is 90.7% and using a voting mechanism based on three consequent images further improve the prediction accuracy.
23
FARINAS, MAYTE SUAREZ. "THE LINEAR LOCAL-GLOBAL NEURAL NETWORK MODEL." PONTIFÍCIA UNIVERSIDADE CATÓLICA DO RIO DE JANEIRO, 2003. http://www.maxwell.vrac.puc-rio.br/Busca_etds.php?strSecao=resultado&nrSeq=3694@1.
Full textAbstract:
CONSELHO NACIONAL DE DESENVOLVIMENTO CIENTÍFICO E TECNOLÓGICONesta tese apresenta-se o Modelo de Redes Neurais Globais- Locais (RNGL) dentro do contexto de modelos de séries temporais. Esta formulação abrange alguns modelos não- lineares já existentes e admite também o enfoque de Mistura de Especialistas. Dedica-se especial atenção ao caso de especialistas lineares, e são discutidos extensivamente aspectos teóricos do modelo: condições de estacionariedade, identificabilidade do modelo, existência, consistência e normalidade assintótica dos estimadores dos parâmetros. Considera-se também uma estratégia de construção do modelo e são discutidos os procedimentos numéricos de estimação, apresentando uma solução para o cálculo de valores iniciais. Finalmente, ilustra-se a metodologia apresentada em duas séries temporais reais, amplamente utilizada na literatura de modelos não lineares.
In this thesis, the Local Global Neural Networks model is proposed within the context of time series models. This formulation encompasses some already existing nonlinear models and also admits the Mixture of Experts approach. We place emphasis on the linear expert case and extensively discuss the theoretical aspects of the model: stationary conditions, existence, consistency and asymptotic normality of the parameter estimates, and model identifiability. A model building strategy is also considered and the whole procedure is illustrated with two real time-series.
24
Winqvist, Rebecka. "Neural Network Approaches for Model Predictive Control." Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-284323.
Full textAbstract:
Model Predictive Control (MPC) is an optimization-based paradigm forfeedback control. The MPC relies on a dynamical model to make predictionsfor the future values of the controlled variables of the system. It then solvesa constrained optimization problem to calculate the optimal control actionthat minimizes the difference between the predicted values and the desiredor set values. One of the main limitations of the traditional MPC lies in thehigh computational cost resulting from solving the associated optimizationproblem online. Various offline strategies have been proposed to overcomethis, ranging from the explicit MPC (eMPC) to the recent learning-basedneural network approaches. This thesis investigates a framework for thetraining and evaluation of a neural network for learning to implement theMPC. As a part of the framework, a new approach for efficient generationof training data is proposed. Four different neural network structures arestudied; one of them is a black box network while the other three employMPC specific information. The networks are evaluated in terms of twodifferent performance metrics through experiments conducted on realistictwo-dimensional and four-dimensional systems. The experiments revealthat while using MPC specific structure in the neural networks resultsin performance gains when the training data is limited, all the networkstructures perform similarly as extensive training data is used. They furthershow that a recurrent neural network structure trained on both the state andcontrol trajectories of a family of MPCs is able to generalize to previouslyunseen MPC problems. The proposed methods in this thesis act as a firststep towards developing a coherent framework for characterization of learningapproaches in terms of both model validation and efficient training datageneration.Modell-prediktiv reglering (MPC) är en strategi inom återkopplad regleringmed rötter i optimeringsteori. MPC:n använder sig av en dynamiskmodell för att prediktera de framtida värdena på systemets styrvariabler.Den löser sedan ett optimeringsproblem för att beräkna en optimalstyrsignal som minimerar skillnaden mellan referensvärdena och depredikterade värdena. Att lösa det associerade optimeringsproblemetonline kan medföra höga beräkningskostnader, något som utgör en av dehuvudsakliga begränsningarna med traditionell MPC. Olika offline-strategierhar föreslagits för att kringgå detta, däribland explicit modell-prediktivreglering (eMPC) samt senare inlärningsmetoder baserade på neuronnät.Den här masteruppsatsen undersöker ett ramverk för träning och utvärderingav olika neuronnätsstrukturer för MPC-inlärning. En ny metod för effektivgenerering av träningsdata presenteras som en del av detta ramverk.Fyra olika nätstrukturer studeras; ett black box-nät samt tre nät sominkluderar MPC-specifik information. Näten evalueras i termer av två olikaprestandamått genom experiment på realistiska två- och fyrdimensionellasystem. Experimenten visar att en MPC-specifik nätstruktur resulterar iökad prestanda när mängden träningsdata är begränsad, men att de fyranäten presterar likvärdigt när mycket träningsdata finns att tillgå. De visarvidare att ett återkopplat neuronnät som tränas på både tillstånds- ochstyrsignalstrajektorier från en familj av MPC:er har förmågan att generaliseravid påträffandet av nya MPC-problem. De föreslagna metoderna i den häruppsatsen utgör ett första steg mot utvecklandet av ett enhetligt ramverk förkaraktärisering av inlärningsmetoder i termer av både modellvalidering ocheffektiv datagenerering.
25
Bakhary, Norhisham. "Structural condition monitoring and damage identification with artificial neural network." University of Western Australia. School of Civil and Resource Engineering, 2009. http://theses.library.uwa.edu.au/adt-WU2009.0102.
Full textAbstract:
Many methods have been developed and studied to detect damage through the change of dynamic response of a structure. Due to its capability to recognize pattern and to correlate non-linear and non-unique problem, Artificial Neural Networks (ANN) have received increasing attention for use in detecting damage in structures based on vibration modal parameters. Most successful works reported in the application of ANN for damage detection are limited to numerical examples and small controlled experimental examples only. This is because of the two main constraints for its practical application in detecting damage in real structures. They are: 1) the inevitable existence of uncertainties in vibration measurement data and finite element modeling of the structure, which may lead to erroneous prediction of structural conditions; and 2) enormous computational effort required to reliably train an ANN model when it involves structures with many degrees of freedom. Therefore, most applications of ANN in damage detection are limited to structure systems with a small number of degrees of freedom and quite significant damage levels. In this thesis, a probabilistic ANN model is proposed to include into consideration the uncertainties in finite element model and measured data. Rossenblueth's point estimate method is used to reduce the calculations in training and testing the probabilistic ANN model. The accuracy of the probabilistic model is verified by Monte Carlo simulations. Using the probabilistic ANN model, the statistics of the stiffness parameters can be predicted which are used to calculate the probability of damage existence (PDE) in each structural member. The reliability and efficiency of this method is demonstrated using both numerical and experimental examples. In addition, a parametric study is carried out to investigate the sensitivity of the proposed method to different damage levels and to different uncertainty levels. As an ANN model requires enormous computational effort in training the ANN model when the number of degrees of freedom is relatively large, a substructuring approach employing multi-stage ANN is proposed to tackle the problem. Through this method, a structure is divided to several substructures and each substructure is assessed separately with independently trained ANN model for the substructure. Once the damaged substructures are identified, second-stage ANN models are trained for these substructures to identify the damage locations and severities of the structural ii element in the substructures. Both the numerical and experimental examples are used to demonstrate the probabilistic multi-stage ANN methods. It is found that this substructuring ANN approach greatly reduces the computational effort while increasing the damage detectability because fine element mesh can be used. It is also found that the probabilistic model gives better damage identification than the deterministic approach. A sensitivity analysis is also conducted to investigate the effect of substructure size, support condition and different uncertainty levels on the damage detectability of the proposed method. The results demonstrated that the detectibility level of the proposed method is independent of the structure type, but dependent on the boundary condition, substructure size and uncertainty level.
26
Ouyang, Xiaohong. "Neural network identification and control of electrical power steering systems." Thesis, University of Wolverhampton, 2000. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.323099.
Full text
27
Hannan, Jeff. "Identification of a neural network for short term load forecasting." Thesis, University of Reading, 1997. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.363837.
Full text
28
Choi, Ju-Yeop. "Nonlinear system identification and control using a neural network approach." Diss., Virginia Tech, 1994. http://hdl.handle.net/10919/40199.
Full text
29
Yotter, Rachel A. "A network model of the hippocampus /." Thesis, Connect to this title online; UW restricted, 2007. http://hdl.handle.net/1773/5887.
Full text
30
Idir, Kamel. "Optimization and neural network model for induction motors." Thesis, National Library of Canada = Bibliothèque nationale du Canada, 1999. http://www.collectionscanada.ca/obj/s4/f2/dsk1/tape8/PQDD_0020/NQ46293.pdf.
Full text
31
Chen, Dong. "Neural network model for predicting performance of projects." Thesis, National Library of Canada = Bibliothèque nationale du Canada, 1999. http://www.collectionscanada.ca/obj/s4/f2/dsk1/tape9/PQDD_0021/MQ48059.pdf.
Full text
32
Rogers, Jonathan Brian. "A digital neural network model of motion perception." Thesis, Imperial College London, 2001. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.251619.
Full text
33
Padgett, Curtis. "A neural network model for facial affect classification /." Diss., Connect to a 24 p. preview or request complete full text in PDF format. Access restricted to UC campusesd, 1998. http://wwwlib.umi.com/cr/ucsd/fullcit?p9907599.
Full text
34
Wang, Hong. "A new model in designing neural network in optimization : a hybrid neural network approach to machine scheduling." Connect to resource, 1998. http://rave.ohiolink.edu/etdc/view.cgi?acc%5Fnum=osu1261316668.
Full text
35
Gaura, Elena Ioana. "Neural network techniques for the control and identification of acceleration sensors." Thesis, Coventry University, 2000. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.313132.
Full text
36
Tran, Michael. "Neural network identification of quarter-car passive and active suspension systems." Thesis, This resource online, 1992. http://scholar.lib.vt.edu/theses/available/etd-09292009-020158/.
Full text
37
CHAO, CHUNG JEN, and 趙崇仁. "A Artificial Neural Network Model for Freeway Hazardous Location Identification." Thesis, 1995. http://ndltd.ncl.edu.tw/handle/ya397s.
Full text
38
Wilhelm, Hedwig [Verfasser]. "A neural network model of invariant object identification / vorgelegt von Hedwig Wilhelm." 2010. http://d-nb.info/1010194208/34.
Full text
39
Lo, Yu-Wen, and 羅玉雯. "Two-stage attentional auditory model inspired neural network and its application to speaker identification." Thesis, 2017. http://ndltd.ncl.edu.tw/handle/tw3tnd.
Full textAbstract:
碩士國立交通大學
電信工程研究所
106
Revealed by psychophysical and neuro-physiological studies, the cochlea analyzes the incoming sound in the time and logarithmic-frequency domains. Afterward, the neural activities pass through the auditory pathway to the primary auditory cortex (A1) for further analysis. From the functional point of view, the cochlea produces a 2-D auditory spectrogram and the A1 analyzes the 2-D spectrogram. In this thesis, we propose a neural network (NN) to simulate an attentional auditory model and apply it to speaker identification. The proposed NN consists of 1-D and 2-D convolutional neural networks which mimic the functions of the cochlea and the cortex respectively. By deriving initial kernels of the convolutional layers from the neuro-physiological auditory model, we demonstrated that the proposed NN can quickly reach the convergence state with high performance. In addition, even without training, the proposed system with auditory model based kernels outperforms the randomly initialized NN in speaker identification.
40
Lin, Chin Gao, and 林擎國. "Fuzzy Neural Network Approaches to Auditory Image Localization Control and Room Acoustic Model Identification." Thesis, 1993. http://ndltd.ncl.edu.tw/handle/52919850503743211596.
Full textAbstract:
碩士國立交通大學
電信研究所
81
This thesis includes two parts. The first part describles the design of a novel-based acoustic control used for the equalization of the response of a sound reproduction system. Since, the traditional adaptive equalizer is capable of dealing with linear systems or specific nonlinear systems, the time- delay feedforward neural network (TDNN) which bave the capability to learn arbitrary nonlinearity and process the temporal audio patterns are particularly recognized as the best nonlinear equalization of the sound reproduction. The performance of TDNN-based acoustic controller is verified by some simulation results. The second part presents a new fuzzy logic control (FLC) approach which leads to a sterephononic reproduction controller for localizing an auditory image in the desired direction and distance. The localization blur of auditory is usually less precisely resolved than physical sound space. In other words, it turns out that controlling the auditory image is more difficult than the sound controll. Different from the conventional sound image localization approach, the fuzzy logic controller can take into account human auditory perception knowledge. The ambiguous human auditory perception can be represented by a number of fuzzy-set values. From these fuzzy representations the auditory image localization controller characterizes the function of how control outputs depend on control inputs as fuzzy implications or associations. Furthermore, the overall sterephonic reproduction controller can be realized be a 45-rule fuzzy associative memory FAM system. The performance of FLC-based auditory image localization is verified by a number of experiments.
41
Ching-Yun, Kao, and 高清雲. "Artificial-Neural-Network-Based System Identification Models for Structural Health Monitoring." Thesis, 2002. http://ndltd.ncl.edu.tw/handle/84614696895269038156.
Full textAbstract:
博士國立交通大學
土木工程系
90
Conventional artificial-neural-network-based (ANN-based) structural damage assessment methods use artificial neural networks (ANNs) to extract and store the knowledge of the patterns in the response of undamaged and damaged structure. Since the failure modes of a structure are so varied and so unpredictable, it is not feasible to train the neural network by furnishing it with pairs of failure states and corresponding diagnostic response. ANNs are robust and fault tolerant. They can also effectively deal with qualitative, uncertain, and incomplete information, thereby making them highly promising for identifying systems that are typically encountered in structural dynamics. The weights of the approximating neural network store the knowledge of the structural properties of the identified system. The objective of this research was looking for some useful indices for global structural health monitoring directly or indirectly from the weights of the approximating neural network. Herein, three ANN-based system identification models (Partial Derivative Form models, Equivalent Linear System models, and Free Vibration models) for structural health monitoring were presented. Each model comprises two steps. In the first step, system identification, Neural System Identification Networks (NSINs) are used to identify the undamaged and damaged states of a structural system. The inputs of the NSIN are previous structural responses and previous and current external excitations, and the outputs are current structural responses. In the second step, structural damage detection, some useful indices for detecting structural damage are searched directly or indirectly from the weights of the NSIN. The useful indices for structural health monitoring in Partial Derivative Form model, Equivalent Linear System model, and Free Vibration model are partial derivatives of the outputs with respect to the inputs of a NSIN, modal parameters of an equivalent linear system, and the amplitudes and periods of the free vibrations generated from a NSIN respectively. By comparing the indices of damaged state with those of undamaged state, the extent of changes can be assessed. Numerical and experimental examples were presented to demonstrate the feasibility of proposed models for structural health monitoring. Besides, further studies were suggested in the area of extending this work to realistic structures, investigating how to determine the location and extent of the damage, exploring relations between structural properties and partial derivatives of the outputs with respect to the inputs of a NSIN, and developing on-line structural health monitoring methods.
42
Quiroga, Jabid Eduardo Mendez. "Stator winding fault detection for a PMSM using fuzzy logic classifier and neural network model identification." 2008. http://etd.lib.fsu.edu/theses/available/etd-04282008-100002.
Full textAbstract:
Thesis (M.S.)--Florida State University, 2008Advisor: Dave A. Cartes, Florida State University, College of Engineering, Dept. of Mechanical Engineering. Title and description from dissertation home page (viewed June 11, 2008). Document formatted into pages; contains xii, 82 pages. Includes bibliographical references.
43
Chung, Ming Hsien, and 鍾明憲. "Identification of High-Purity Distillation Columns : Dynamic Neural Networks Model Development." Thesis, 1995. http://ndltd.ncl.edu.tw/handle/17274952892096456857.
Full textAbstract:
碩士國立中央大學
化學工程研究所
83
Effective control of high-purity distillation columns is one of most challenging topics in the field of process control over the years. The unit is commonly employed to separate the final products and would normally consume vast amount of energy. Maintaining satisfactory separation of high-purity distillation columns is one of the most important concerns in in the chemical industry. Due to nonlinearity and loop inter- ation characteristics of high-purity distillation columns, it is difficult to describe dynamic behavior of such columns using simple linear mathematical models. A realistic dynamic simulation of a dual composition and temperature column is used in this study and the process is identified by using artificial neural network(ANN). Because ANN is capable of learning essential process nonlinearity from plant data , this ANN model can provide another means to describe the dynamic behavior of high-purity distillation column. Also in this work, different manipulated input excitation methods will be used to investigate the best input/output data as training set. The nonlinear model obtaioned via ANN will be compared to another nonlinear model using nonlinear ARX model.
44
(11184909), Chuhao Deng. "TRAJECTORY PATTERN IDENTIFICATION AND CLASSIFICATION FOR ARRIVALS IN VECTORED AIRSPACE." Thesis, 2021.
Find full textAbstract:
As the demand and complexity of air traffic increase, it becomes crucial to maintain the safety and efficiency of the operations in airspaces, which, however, could lead to an increased workload for Air Traffic Controllers (ATCs) and delays in their decision-making processes. Although terminal airspaces are highly structured with the flight procedures such as standard terminal arrival routes and standard instrument departures, the aircraft are frequently instructed to deviate from such procedures by ATCs to accommodate given traffic situations, e.g., maintaining the separation from neighboring aircraft or taking shortcuts to meet scheduling requirements. Such deviation, called vectoring, could even increase the delays and workload of ATCs. This thesis focuses on developing a framework for trajectory pattern identification and classification that can provide ATCs, in vectored airspace, with real-time information of which possible vectoring pattern a new incoming aircraft could take so that such delays and workload could be reduced. This thesis consists of two parts, trajectory pattern identification and trajectory pattern classification.
In the first part, a framework for trajectory pattern identification is proposed based on agglomerative hierarchical clustering, with dynamic time warping and squared Euclidean distance as the dissimilarity measure between trajectories. Binary trees with fixes that are provided in the aeronautical information publication data are proposed in order to catego- rize the trajectory patterns. In the second part, multiple recurrent neural network based binary classification models are trained and utilized at the nodes of the binary trees to compute the possible fixes an incoming aircraft could take. The trajectory pattern identifi- cation framework and the classification models are illustrated with the automatic dependent surveillance-broadcast data that were recorded between January and December 2019 in In- cheon international airport, South Korea .
45
Hung, Yu-Min, and 洪鈺敏. "Novel Bayer CFA Module-Based Camera Model Identification Using Convolutional Neural Networks." Thesis, 2019. http://ndltd.ncl.edu.tw/handle/2a44gx.
Full text
46
Kumari, K., J. P. Singh, Y. K. Dwivedi, and Nripendra P. Rana. "Multi-modal Aggression Identification Using Convolutional Neural Network and Binary Particle Swarm Optimization." 2021. http://hdl.handle.net/10454/18300.
Full textAbstract:
YesAggressive posts containing symbolic and offensive images, inappropriate gestures along with provocative textual comments are growing exponentially in social media with the availability of inexpensive data services. These posts have numerous negative impacts on the reader and need an immediate technical solution to filter out aggressive comments. This paper presents a model based on a Convolutional Neural Network (CNN) and Binary Particle Swarm Optimization (BPSO) to classify the social media posts containing images with associated textual comments into non-aggressive, medium-aggressive and high-aggressive classes. A dataset containing symbolic images and the corresponding textual comments was created to validate the proposed model. The framework employs a pre-trained VGG-16 to extract the image features and a three-layered CNN to extract the textual features in parallel. The hybrid feature set obtained by concatenating the image and the text features were optimized using the BPSO algorithm to extract the more relevant features. The proposed model with optimized features and Random Forest classifier achieves a weighted F1-Score of 0.74, an improvement of around 3% over unoptimized features.
The full-text of this article will be released for public view at the end of the publisher embargo on 13 Jan 2022.
47
Hsia, Chi-Yuan, and 夏啟元. "Model Construction and Real-Time Analysis of Personal EEG Identification Based on Machine Learning and Convolutional Neural Network." Thesis, 2019. http://ndltd.ncl.edu.tw/cgi-bin/gs32/gsweb.cgi/login?o=dnclcdr&s=id=%22107NCHU5396049%22.&searchmode=basic.
Full textAbstract:
碩士國立中興大學
資訊管理學系所
107
Under the development trend of artificial intelligence, biometrics has become a popular technology, which could be applied to various situations, such as finance, public institutions, and customs. Electroencephalography (EEG), a method for research on biometrics, collects electromagnetic waves on specific positions on the scalp and reflects individual brain activity. Much research proved that α band in EEG could distinguish individual differences, and the significance was proven in clinical neurophysiology. In EEG biometrics, complicated electrode channels were used in most research to cover the entire head for collecting brainwave records. Such equipment could not satisfy the requirement for collectability in the application of biometrics. This study mainly develops the verification model with brainwave through Convolutional Neural Network (CNN). A handy EEG collects the static brainwave of participants for 2 minutes. With the Butterworth Low Pass Filter (BLPF) and Short-time Fourier Transform (STFT), brainwave features are selected from the source brainwave signals, and the verification evaluation model is developed with the comparison between several machine learning classifiers and the deep learning CNN model. Two authentication models of individual specific and general models are proposed in this study and Synthetic Minority Oversampling Technique (SMOTE) is used for solving the imbalance problem between personal data and general data so that the research results show favorable effects in various model evaluation indicators. In individual specific model, the selection of brainwave features at 2 second reveals the accuracy 96.80%. In general model, it is necessary to select brainwave for 20 seconds, which is longer than it in individual specific model, but the accuracy is up to 98.58%. The two models show the advantages and disadvantage, but could be chosen the suitable one for verification systems in distinct application.
48
Hsu, Zeng-Wei, and 許增尉. "Identification of Instantaneous Modal Parameters of A Time Varying Structure via A Neural Network." Thesis, 2007. http://ndltd.ncl.edu.tw/handle/smfu6h.
Full textAbstract:
碩士國立交通大學
土木工程系所
96
Time varying systems find many applications in various fields. In mechanical and civil engineering, a system with active control devices of modifying stiffness or damping of the system is a time varying system. When a structure is damaged under dynamic loading, the structure normally displays changes in stiffness and damping with time. The changes with time in stiffness and damping of a system result in time varying instantaneous model parameters is an important issue in damage assessment of a structure. The present work develops a novel procedure of establishing BP neural network of a time varying system and estimating instantaneous model parameters of the system from established neural network. The connective weights and thresholds in a neural network are assumed as functions of time and are expanded by polynomials. A weighted least-squares approach is applied to determine the coefficients of the polynomials. Because of using the weighted least-squares approach, the coefficients of the polynomials also depend on time. Consequently, only low orders of polynomials are needed to expand the connective weights and thresholds. The feasibility of the proposed procedure is demonstrated by processing numerically simulated dynamic responses of a nonlinear system and a time-varying linear system. It is also performed to investigate the effects of weighting function in the weighted least-square approach, polynomial order, and noise on establishing a suitable neural network and determining instantaneous model parameters. Finally, the proposed procedure is applied to process measured dynamics responses of a RC structure under shaking table tests. The experimental structure has been shaken to perform nonlinear behaviors. When dramatic changes are observed in the slope of the measured relationship between force and displacement for the experimental structure, the identified instantaneous model parameters also show significant changes.
49
Vaidya, Anil Pralhad. "A Model Study For The Application Of Wavelet And Neural Network For Identification And Localization Of Partial Discharges In Transformers." Thesis, 2004. http://etd.iisc.ernet.in/handle/2005/1183.
Full text
50
Corredor, Edward Alexis Baron. "Assessment and identification of concrete box-girder bridges properties using surrogate model calibration: case study: El Tablazo bridge." Master's thesis, 2017. http://hdl.handle.net/1822/70634.
Full textAbstract:
Dissertação de mestrado integrado em Engenharia CivilThis work consists in identifying and assessing the properties in a pre-stressed concrete bridge related to material, geometry and physic sources, through a surrogate model. The participation of this mathematical model allows to generate a relationship between bridge properties and its dynamic response, with the purpose of creating a tool to predict the analytical values of the studied properties from measured eigenfrequencies; in this case, it is introduced the identification of damage scenarios, giving the application for validate the generated metamodel (Artificial Neural Network - ANN). A FE model is developed to simulate the studied structure, a Colombian bridge called El Tablazo, one of the higher in the country of this type (box-girder bridge), with a total length of 560 meters, located on the Sogamoso riverbed in the region of Santander - Colombia. Once the damage scenarios are defined, this work allows to indicate the basis for futures plans of structural health monitoring.
Este trabalho consiste em identificar e avaliar as propriedades de uma ponte em betão pré-esforçado em relação ao material, geometria e características físicas através de um metamodelo. A participação deste modelo matemático permite gerar uma relação entre as propriedades da ponte e sua resposta dinâmica, com o objetivo de criar uma ferramenta para prever os valores analíticos das propriedades estudadas a partir de frequências próprias medidas; neste caso, é introduzida a identificação de cenários de dano, dando uma aplicação para validar o metamodelo (Rede Neural Artificial - ANN). Um modelo de elemento finito é desenvolvido para simular a estrutura estudada, uma ponte colombiana chamada El Tablazo, uma das que apresenta maior altura do país em seu tipo (pontes em viga-caixão), com um comprimento total de 560 metros, localizada no rio Sogamoso, na região de Santander - Colômbia. Uma vez que os cenários de dano são definidos, a tese permite indicar a base para os planos futuros de monitoramento da saúde estrutural.