To see the other types of publications on this topic, follow the link: Graph-based neural network model.
Dissertations / Theses on the topic 'Graph-based neural network model'
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 'Graph-based neural network model.'
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
McMichael, Lonny D. (Lonny Dean). "A Neural Network Configuration Compiler Based on the Adaptrode Neuronal Model." Thesis, University of North Texas, 1992. https://digital.library.unt.edu/ark:/67531/metadc501018/.
Full textAbstract:
A useful compiler has been designed that takes a high level neural network specification and constructs a low level configuration file explicitly specifying all network parameters and connections. The neural network model for which this compiler was designed is the adaptrode neuronal model, and the configuration file created can be used by the Adnet simulation engine to perform network experiments. The specification language is very flexible and provides a general framework from which almost any network wiring configuration may be created. While the compiler was created for the specialized adaptrode model, the wiring specification algorithms could also be used to specify the connections in other types of networks.
2
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.
3
Calvert, David. "A distance-based neural network model for sequence processing." Thesis, National Library of Canada = Bibliothèque nationale du Canada, 1998. http://www.collectionscanada.ca/obj/s4/f2/dsk2/tape17/PQDD_0010/NQ30591.pdf.
Full text
4
Ozkok, Yusuf Ibrahim. "Web Based Ionospheric Forecasting Using Neural Network And Neurofuzzy Models." Master's thesis, METU, 2005. http://etd.lib.metu.edu.tr/upload/3/12606031/index.pdf.
Full textAbstract:
This study presents the implementation of Middle East Technical University Neural Network (METU-NN) models for the ionospheric forecasting together with worldwide usage capability of the Internet. Furthermore, an attempt is made to include expert information in the Neural Network (NN) model in the form of neurofuzzy network (NFN). Middle East Technical University Neurofuzzy Network (METU-NFN) modeling approach is developed which is the first attempt of using a neurofuzzy model in the ionospheric forecasting studies. The Web based applications developed in this study have the ability to be customized such that other NN and NFN models including METU-NFN can also be adapted.
The NFN models developed in this study are compared with the previously developed and matured METU-NN models. At this very early stage of employing neurofuzzy models in this field, ambitious objectives are not aimed. Applicability of the neurofuzzy systems on the ionospheric forecasting studies is only demonstrated. Training and operating METU-NN and METU-NFN models under equal conditions and with the same data sets, the cross correlation of obtained and measured values are 0.9870 and 0.9086 and the root mean square error (RMSE) values of 1.7425 TECU and 4.7987 TECU are found by operating METU-NN and METU-NFN models respectively. The results obtained by METU-NFN model is close to those found by METU-NN model. These results are reasonable enough to encourage further studies on neurofuzzy models to benefit from expert information.
Availability of these models which already attracted intense international attention will greatly help the related scientific circles to use the models. The models can be architecturally constructed, trained and operated on-line. To the best of our knowledge this is the first application that gives the ability of on-line model usage with these features.
Applicability of NFN models to the ionospheric forecasting is demonstrated. Having ample flexibility the constructed model enables further developments and improvements. Other neurofuzzy systems in the literature might also lead to better achievements.
5
FUTIA, GIUSEPPE. "Neural Networks forBuilding Semantic Models and Knowledge Graphs." Doctoral thesis, Politecnico di Torino, 2020. http://hdl.handle.net/11583/2850594.
Full text
6
Thiruvengadachari, Sathish. "Experimental and neural network-based model for human-machine systems reliability." Diss., Online access via UMI:, 2006.
Find full text
7
Zorzetto, Luiz Flavio Martins. "Bioprocess monitoring with hybrid neural network/mechanistic model based state estimators." Thesis, University of Nottingham, 1995. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.283350.
Full text
8
Wang, Feng. "Neural network model of memory reinforcement for text-based intelligent tutoring system." Thesis, National Library of Canada = Bibliothèque nationale du Canada, 1997. http://www.collectionscanada.ca/obj/s4/f2/dsk2/tape16/PQDD_0021/NQ30122.pdf.
Full text
9
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.
10
Dai, Jing. "Reservoir-computing-based, biologically inspired artificial neural networks and their applications in power systems." Diss., Georgia Institute of Technology, 2013. http://hdl.handle.net/1853/47646.
Full textAbstract:
Computational intelligence techniques, such as artificial neural networks (ANNs), have been widely used to improve the performance of power system monitoring and control. Although inspired by the neurons in the brain, ANNs are largely different from living neuron networks (LNNs) in many aspects. Due to the oversimplification, the huge computational potential of LNNs cannot be realized by ANNs. Therefore, a more brain-like artificial neural network is highly desired to bridge the gap between ANNs and LNNs.
The focus of this research is to develop a biologically inspired artificial neural network (BIANN), which is not only biologically meaningful, but also computationally powerful. The BIANN can serve as a novel computational intelligence tool in monitoring, modeling and control of the power systems.
A comprehensive survey of ANNs applications in power system is presented. It is shown that novel types of reservoir-computing-based ANNs, such as echo state networks (ESNs) and liquid state machines (LSMs), have stronger modeling capability than conventional ANNs. The feasibility of using ESNs as modeling and control tools is further investigated in two specific power system applications, namely, power system nonlinear load modeling for true load harmonic prediction and the closed-loop control of active filters for power quality assessment and enhancement. It is shown that in both applications, ESNs are capable of providing satisfactory performances with low computational requirements.
A novel, more brain-like artificial neural network, i.e. biologically inspired artificial neural network (BIANN), is proposed in this dissertation to bridge the gap between ANNs and LNNs and provide a novel tool for monitoring and control in power systems. A comprehensive survey of the spiking models of living neurons as well as the coding approaches is presented to review the state-of-the-art in BIANN research. The proposed BIANNs are based on spiking models of living neurons with adoption of reservoir-computing approaches. It is shown that the proposed BIANNs have strong modeling capability and low computational requirements, which makes it a perfect candidate for online monitoring and control applications in power systems.
BIANN-based modeling and control techniques are also proposed for power system applications. The proposed modeling and control schemes are validated for the modeling and control of a generator in a single-machine infinite-bus system under various operating conditions and disturbances. It is shown that the proposed BIANN-based technique can provide better control of the power system to enhance its reliability and tolerance to disturbances.
To sum up, a novel, more brain-like artificial neural network, i.e. biologically inspired artificial neural network (BIANN), is proposed in this dissertation to bridge the gap between ANNs and LNNs and provide a novel tool for monitoring and control in power systems. It is clearly shown that the proposed BIANN-based modeling and control schemes can provide faster and more accurate control for power system applications.
The conclusions, the recommendations for future research, as well as the major contributions of this research are presented at the end.
11
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.
12
Boetticher, Gary. "A neural network-based bottom-up approach for building a software reuse economic model." Morgantown, W. Va. : [West Virginia University Libraries], 1999. http://etd.wvu.edu/templates/showETD.cfm?recnum=994.
Full textAbstract:
Thesis (Ph. D.)--West Virginia University, 1999.Title from document title page. Document formatted into pages; contains viii, 226 p. : ill. (some col.) Includes abstract. Includes bibliographical references (p. 152-159).
13
Öberg, Oskar. "Critical Branching Regulation of the E-I Net Spiking Neural Network Model." Thesis, Luleå tekniska universitet, Institutionen för teknikvetenskap och matematik, 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:ltu:diva-76770.
Full textAbstract:
Spiking neural networks (SNN) are dynamic models of biological neurons, that communicates with event-based signals called spikes. SNN that reproduce observed properties of biological senses like vision are developed to better understand how such systems function, and to learn how more efficient sensor systems can be engineered. A branching parameter describes the average probability for spikes to propagate between two different neuron populations. The adaptation of branching parameters towards critical values is known to be important for maximizing the sensitivity and dynamic range of SNN. In this thesis, a recently proposed SNN model for visual feature learning and pattern recognition known as the E-I Net model is studied and extended with a critical branching mechanism. The resulting modified E-I Net model is studied with numerical experiments and two different types of sensory queues. The experiments show that the modified E-I Net model demonstrates critical branching and power-law scaling behavior, as expected from SNN near criticality, but the power-laws are broken and the stimuli reconstruction error is higher compared to the error of the original E-I Net model. Thus, on the basis of these experiments, it is not clear how to properly extend the E-I Net model properly with a critical branching mechanism. The E-I Net model has a particular structure where the inhibitory neurons (I) are tuned to decorrelate the excitatory neurons (E) so that the visual features learned matches the angular and frequency distributions of feature detectors in visual cortex V1 and different stimuli are represented by sparse subsets of the neurons. The broken power-laws correspond to different scaling behavior at low and high spike rates, which may be related to the efficacy of inhibition in the model.
14
Bahremand, Saeid. "Blood Glucose Management Streptozotocin-Induced Diabetic Rats by Artificial Neural Network Based Model Predictive Control." Thesis, Southern Illinois University at Edwardsville, 2017. http://pqdtopen.proquest.com/#viewpdf?dispub=10249804.
Full textAbstract:
Diabetes is a group of metabolic diseases where the body’s pancreas does not produce enough insulin or does not properly respond to insulin produced, resulting in high blood sugar levels over a prolonged period. There are several different types of diabetes, but the most common forms are type 1 and type 2 diabetes. Type 1 diabetes Mellitus (T1DM) can occur at any age, but is most commonly diagnosed from infancy to late 30s. If a person is diagnosed with type 1 diabetes, their pancreas produces little to no insulin, and the body’s immune system destroys the insulin-producing cells in the pancreas. Those diagnosed with type 1 diabetes must inject insulin several times every day or continually infuse insulin through a pump, as well as manage their diet and exercise habits. If not treated appropriately, it can cause serious complications such as cardiovascular disease, stroke, kidney failure, foot ulcers, and damage to eyes.
During the past decade, researchers have developed artificial pancreas (AP) to ease management of diabetes. AP has three components: continuous glucose monitor (CGM), insulin pump, and closed-loop control algorithm. Researchers have developed algorithms based on control techniques such as Proportional Integral Derivative (PID) and Model Predictive Control (MPC) for blood glucose level (BGL) control; however, variability in metabolism between or within individuals hinders reliable control.
This study aims to develop an adaptive algorithm using Artificial Neural Networks (ANN) based Model Predictive Control (NN-MPC) to perform proper insulin injections according to BGL predictions in diabetic rats. This study is a ground work to implement NN-MPC algorithm on real subjects. BGL data collected from diabetic rats using CGM are used with other inputs such as insulin injection and meal information to develop a virtual plant model based on a mathematical model of glucose–insulin homeostasis proposed by Lombarte et al. Since this model is proposed for healthy rats; a revised version on this model with three additional equations representing diabetic rats is used to generate data for training ANN which is applicable for the identi?cation of dynamics and the glycemic regulation of rats. The trained ANN is coupled with MPC algorithm to control BGL of the plant model within the normal range of 100 to 130 mg/dl by injecting appropriate amount of insulin. The ANN performed well with less than 5 mg/dl error (2%) for 5-minute prediction and about 15 mg/dl error (7%) for 30-minute prediction. In ¬¬addition, the NN-MPC algorithm kept BGL of diabetic rats more than 90 percent of the time within the normal range without hyper/hypo-glycaemia.
15
Pracný, Vladislav. "Neural network based shock absorber model with a thermodynamical coupling : experiment, modeling and vehicle simulation /." Aachen : Shaker, 2009. http://d-nb.info/994209967/04.
Full text
16
Figueroa, Barraza Joaquín Eduardo. "A capsule neural network based model for structural damage localization and quantification using transmissibilty data." Tesis, Universidad de Chile, 2019. http://repositorio.uchile.cl/handle/2250/170185.
Full textAbstract:
Tesis para optar al grado de Magíster en Ciencias de la Ingeniería Mención MecánicaMemoría para optar al título de Ingeniero Civil Mecánico
Dentro de la ingeniería estructural, el monitoreo de condición usando diferentes tipos de sensores ha sido importante en la prevención de fallas y diagnóstico del estado de salud. El desafío actual es aprovechar al máximo las grandes cantidades de datos para entregar mediciones y predicciones precisas. Los algoritmos de aprendizaje profundo abordan estos problemas mediante el uso de datos para encontrar relaciones complejas entre ellos. Entre estos algoritmos, las redes neuronales convolucionales (CNN) han logrado resultados de vanguardia, especialmente cuando se trabaja con imágenes. Sin embargo, existen dos problemas principales: la incapacidad de reconocer imágenes rotadas como tales, y la inexistencia de jerarquías dentro de las imágenes. Para resolver estos problemas, se desarrollaron las redes de cápsulas (Capsule Networks), logrando resultados prometedores en problemas de tipo benchmark. En esta tesis, las Capsule Networks se modifican para localizar y cuantificar daños estructurales. Esto implica una tarea doble de clasificación y regresión, lo que no se ha realizado anteriormente. El objetivo es generar modelos para dos casos de estudio diferentes, utilizando dos algoritmos de routing diferentes. Se analizan y comparan los resultados entre ellos y con el estado del arte. Los resultados muestran que las Capsule Networks con Dynamic routing logran mejores resultados que las CNN, especialmente cuando se trata de valores falsos positivos. No se observa sobreajuste en el conjunto de validación sino en el conjunto de prueba. Para resolver esto, se implementa la técnica de dropout, mejorando los resultados obtenidos en este último conjunto.
17
Rockney, Alissa Ann. "A Predictive Model Which Uses Descriptors of RNA Secondary Structures Derived from Graph Theory." Digital Commons @ East Tennessee State University, 2011. https://dc.etsu.edu/etd/1300.
Full textAbstract:
The secondary structures of ribonucleic acid (RNA) have been successfully modeled with graph-theoretic structures. Often, simple graphs are used to represent secondary RNA structures; however, in this research, a multigraph representation of RNA is used, in which vertices represent stems and edges represent the internal motifs. Any type of RNA secondary structure may be represented by a graph in this manner. We define novel graphical invariants to quantify the multigraphs and obtain characteristic descriptors of the secondary structures. These descriptors are used to train an artificial neural network (ANN) to recognize the characteristics of secondary RNA structure. Using the ANN, we classify the multigraphs as either RNA-like or not RNA-like. This classification method produced results similar to other classification methods. Given the expanding library of secondary RNA motifs, this method may provide a tool to help identify new structures and to guide the rational design of RNA molecules.
18
Keisala, Simon. "Using a Character-Based Language Model for Caption Generation." Thesis, Linköpings universitet, Interaktiva och kognitiva system, 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-163001.
Full textAbstract:
Using AI to automatically describe images is a challenging task. The aim of this study has been to compare the use of character-based language models with one of the current state-of-the-art token-based language models, im2txt, to generate image captions, with focus on morphological correctness. Previous work has shown that character-based language models are able to outperform token-based language models in morphologically rich languages. Other studies show that simple multi-layered LSTM-blocks are able to learn to replicate the syntax of its training data. To study the usability of character-based language models an alternative model based on TensorFlow im2txt has been created. The model changes the token-generation architecture into handling character-sized tokens instead of word-sized tokens. The results suggest that a character-based language model could outperform the current token-based language models, although due to time and computing power constraints this study fails to draw a clear conclusion. A problem with one of the methods, subsampling, is discussed. When using the original method on character-sized tokens this method removes characters (including special characters) instead of full words. To solve this issue, a two-phase approach is suggested, where training data first is separated into word-sized tokens where subsampling is performed. The remaining tokens are then separated into character-sized tokens. Future work where the modified subsampling and fine-tuning of the hyperparameters are performed is suggested to gain a clearer conclusion of the performance of character-based language models.
19
McKinnell, L. A. "A neural network based ionospheric model for the bottomside electron density profile over Grahamstown, South Africa." Thesis, Rhodes University, 2003. http://hdl.handle.net/10962/d1005262.
Full textAbstract:
This thesis describes the development and application of a neural network based ionospheric model for the bottomside electron density profile over Grahamstown, South Africa. All available ionospheric data from the archives of the Grahamstown (33.32ºS, 26.50ºE) ionospheric station were used for training neural networks (NNs) to predict the parameters required to produce the final profile. Inputs to the model, called the LAM model, are day number, hour, and measures of solar and magnetic activity. The output is a mathematical description of the bottomside electron density profile for that particular input set. The two main ionospheric layers, the E and F layers, are predicted separately and then combined at the final stage. For each layer, NNs have been trained to predict the individual ionospheric characteristics and coefficients that were required to describe the layer profile. NNs were also applied to the task of determining the hours between which an E layer is measurable by a groundbased ionosonde and the probability of the existence of an F1 layer. The F1 probability NN is innovative in that it provides information on the existence of the F1 layer as well as the probability of that layer being in a L-condition state - the state where an F1 layer is present on an ionogram but it is not possible to record any F1 parameters. In the event of an L-condition state being predicted as probable, an L algorithm has been designed to alter the shape of the profile to reflect this state. A smoothing algorithm has been implemented to remove discontinuities at the F1-F2 boundary and ensure that the profile represents realistic ionospheric behaviour in the F1 region. Tests show that the LAM model is more successful at predicting Grahamstown electron density profiles for a particular set of inputs than the International Reference Ionosphere (IRI). It is anticipated that the LAM model will be used as a tool in the pin-pointing of hostile HF transmitters, known as single-site location.
20
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.
21
Paradza, Masimba Wellington. "Development of a neural network based model for predicting the occurrence of spread F within the Brazilian sector." Thesis, Rhodes University, 2009. http://hdl.handle.net/10962/d1005245.
Full textAbstract:
Spread F is a phenomenon of the ionosphere in which the pulses returned from the ionosphere are of a much greater duration than the transmitted ones. The occurrence of spread F can be predicted using the technique of Neural Networks (NNs). This thesis presents the development and evaluation of NN based models (two single station models and a regional model) for predicting the occurrence of spread F over selected stations within the Brazilian sector. The input space for the NNs included the day number (seasonal variation), hour (diurnal variation), sunspot number (measure of the solar activity), magnetic index (measure of the magnetic activity) and magnetic position (latitude, magnetic declination and inclination). Twelve years of spread F data measured during 1978 to 1989 inclusively at the equatorial site Fortaleza and low latitude site Cachoeira Paulista are used in the development of an input space and NN architecture for the NN models. Spread F data that is believed to be related to plasma bubble developments (range spread F) were used in the development of the models while those associated with narrow spectrum irregularities that occur near the F layer (frequency spread F) were excluded. The results of the models show the dependency of the probability of spread F as a function of local time, season and latitude. The models also illustrate some characteristics of spread F such as the onset and peak occurrence of spread F as a function of distance from the equator. Results from these models are presented in this thesis and compared to measured data and to modelled data obtained with an empirical model developed for the same purpose.
22
Pracný, Vladislav [Verfasser]. "Neural network-based shock absorber model with a thermodynamical coupling : Experiment, modeling and vehicle simulation / Vladislav Pracny." Aachen : Shaker, 2009. http://d-nb.info/1161302549/34.
Full text
23
Kadlec, Jakub. "Creating a prediction model for weather forecasting based on artificial neural network supported by association rules mining." Master's thesis, Vysoká škola ekonomická v Praze, 2016. http://www.nusl.cz/ntk/nusl-203981.
Full textAbstract:
This diploma thesis introduces three different methods of creating a neural network binary classifier for the purpose of automated weather prediction with attribute pre-selection using association rules and correlation patters mining by the LISp-Miner system. First part of the thesis consists of collection of theoretical knowledge enabling the creation of such predictive model, whereas the second part describes the creation of the model itself using the CRISP-DM methodology. Final part of the thesis analyses the performance of created classifiers and concludes the proposed methods and their possible benefits over training the network without attribute pre-selection.
24
Garagnani, Max. "Understanding language and attention : brain-based model and neurophysiological experiments." Thesis, University of Cambridge, 2009. https://www.repository.cam.ac.uk/handle/1810/243852.
Full textAbstract:
This work concerns the investigation of the neuronal mechanisms at the basis of language acquisition and processing, and the complex interactions of language and attention processes in the human brain. In particular, this research was motivated by two sets of existing neurophysiological data which cannot be reconciled on the basis of current psycholinguistic accounts: on the one hand, the N400, a robust index of lexico-semantic processing which emerges at around 400ms after stimulus onset in attention demanding tasks and is larger for senseless materials (meaningless pseudowords) than for matched meaningful stimuli (words); on the other, the more recent results on the Mismatch Negativity (MMN, latency 100-250ms), an early automatic brain response elicited under distraction which is larger to words than to pseudowords. We asked what the mechanisms underlying these differential neurophysiological responses may be, and whether attention and language processes could interact so as to produce the observed brain responses, having opposite magnitude and different latencies. We also asked questions about the functional nature and anatomical characteristics of the cortical representation of linguistic elements. These questions were addressed by combining neurocomputational techniques and neuroimaging (magneto-encephalography, MEG) experimental methods. Firstly, a neurobiologically realistic neural-network model composed of neuron-like elements (graded response units) was implemented, which closely replicates the neuroanatomical and connectivity features of the main areas of the left perisylvian cortex involved in spoken language processing (i.e., the areas controlling speech output – left inferior-prefrontal cortex, including Broca’s area – and the main sensory input – auditory – areas, located in the left superior-temporal lobe, including Wernicke’s area). Secondly, the model was used to simulate early word acquisition processes by means of a Hebbian correlation learning rule (which reflects known synaptic plasticity mechanisms of the neocortex). The network was “taught” to associate pairs of auditory and articulatory activation patterns, simulating activity due to perception and production of the same speech sound: as a result, neuronal word representations distributed over the different cortical areas of the model emerged. Thirdly, the network was stimulated, in its “auditory cortex”, with either one of the words it had learned, or new, unfamiliar pseudoword patterns, while the availability of attentional resources was modulated by changing the level of non-specific, global cortical inhibition. In this way, the model was able to replicate both the MMN and N400 brain responses by means of a single set of neuroscientifically grounded principles, providing the first mechanistic account, at the cortical-circuit level, for these data. Finally, in order to verify the neurophysiological validity of the model, its crucial predictions were tested in a novel MEG experiment investigating how attention processes modulate event-related brain responses to speech stimuli. Neurophysiological responses to the same words and pseudowords were recorded while the same subjects were asked to attend to the spoken input or ignore it. The experimental results confirmed the model’s predictions; in particular, profound variability of magnetic brain responses to pseudowords but relative stability of activation to words as a function of attention emerged. While the results of the simulations demonstrated that distributed cortical representations for words can spontaneously emerge in the cortex as a result of neuroanatomical structure and synaptic plasticity, the experimental results confirm the validity of the model and provide evidence in support of the existence of such memory circuits in the brain. This work is a first step towards a mechanistic account of cognition in which the basic atoms of cognitive processing (e.g., words, objects, faces) are represented in the brain as discrete and distributed action-perception networks that behave as closed, independent systems.
25
Kim, Jun Ha. "Artificial neural network (ANN) based decision support model for alternative workplace arrangements (AWA) readiness assessment and type selection." Diss., Atlanta, Ga. : Georgia Institute of Technology, 2009. http://hdl.handle.net/1853/31830.
Full textAbstract:
Thesis (Ph.D)--Building Construction, Georgia Institute of Technology, 2010.Committee Chair: Roper, Kathy; Committee Co-Chair: Kangari, Roozbeh; Committee Member: Ashuri, Baabak; Committee Member: Castro, Daniel; Committee Member: Rouse, William. Part of the SMARTech Electronic Thesis and Dissertation Collection.
26
Thanikasalam, Kokul. "Appearance based online visual object tracking." Thesis, Queensland University of Technology, 2019. https://eprints.qut.edu.au/130875/1/Kokul_Thanikasalam_Thesis.pdf.
Full textAbstract:
This thesis presents research contributions to the field of computer vision based visual object tracking. This study investigates appearance based object tracking by using traditional hand-crafted and deep features. The thesis proposes a real-time tracking framework with high accuracy which follows a deep similarity tracking strategy. This thesis also proposes several deep tracking frameworks for high-accuracy tracking and to manage the spatial information loss. The research findings of the study would be able to be used in a range of applications including visual surveillance systems.
27
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
28
Biruk, David D. "Neural Network Based Control of Integrated Recycle Heat Exchanger Superheaters in Circulating Fluidized Bed Boilers." UNF Digital Commons, 2013. http://digitalcommons.unf.edu/etd/470.
Full textAbstract:
The focus of this thesis is the development and implementation of a neural network model predictive controller to be used for controlling the integrated recycle heat exchanger (Intrex) in a 300MW circulating fluidized bed (CFB) boiler. Discussion of the development of the controller will include data collection and preprocessing, controller design and controller tuning. The controller will be programmed directly into the plant distributed control system (DCS) and does not require the continuous use of any third party software.
The intrexes serve as the loop seal in the CFB as well as intermediate and finishing superheaters. Heat is transferred to the steam in the intrex superheaters from the circulating ash which can vary in consistency, quantity and quality. Fuel composition can have a large impact on the ash quality and in turn, on intrex performance. Variations in MW load and airflow settings will also impact intrex performance due to their impact on the quantity of ash circulating in the CFB. Insufficient intrex heat transfer will result in low main steam temperature while excessive heat transfer will result in high superheat attemperator sprays and/or loss of unit efficiency.
This controller will automatically adjust to optimize intrex ash flow to compensate for changes in the other ash properties by controlling intrex air flows. The controller will allow the operator to enter a target intrex steam temperature increase which will cause all of the intrex air flows to adjust simultaneously to achieve the target temperature. The result will be stable main steam temperature and in turn stable and reliable operation of the CFB.
29
Chin-Lang, Huang, and 黃錦郎. "Neural Network Based Model Reference Adaptive Control." Thesis, 2002. http://ndltd.ncl.edu.tw/handle/25112423970598183022.
Full textAbstract:
碩士義守大學
電機工程學系
90
Adaptive controllers have been used in industrial field for many years. The Model Reference Adaptive Control is an important control method in adaptive control field. The key problem with MRAS (Model Reference Adaptive System) is to determine the adjustment mechanism. The Mechanism for adjusting the parameters in a MRAC can be obtained in two ways: one is using a gradient method (also called MIT rule), the other is applying Lyapunov stability theory. The MIT rule has one parameter, the adaptation gain, that must be chosed by the user. It is difficult to find a Lyapunov function. So it is not convenient to use a Model Reference adaptive controller. A new method of MRAS is proposed in this thesis. It combines the Back-Propagation Network (BPN) and the Model Reference Adaptive Control (MRAC). The BPN can provide a forecasting value of a plant. The adjustment mechanism adjusts the controller parameters in such a way that the error, which is the difference between BPN forecasting value and model output, is small. This method can control MRAS in a good response without finding adaptation gain or Lyapunov function. Computer simulation results show that the new method can achieve good transient response.
30
Huang, Ming-Hung, and 黃明宏. "Grid based Artificial Neural Network Typhoon Rainfall Model." Thesis, 2008. http://ndltd.ncl.edu.tw/handle/71095795825027771927.
Full textAbstract:
碩士國立成功大學
水利及海洋工程學系碩博士班
97
Typhoon is one of the most important source of water resources of Taiwan. Typhoon brought abundant rainfall to its covering area. It is generally regarded moving path, characteristics of typhoon, local terrain and meteorological factors of a gage station as major factors affect rainfall depth. There are many approaches were developed to simulated the complicated non-linear process of typhoon rainfall. However, the accuracy of simulation may be improved. A back-propagation artificial neural network model (BPN) was adopted in this thesis to simulate typhoon rainfall. BPN records complex rainfall mechanism to simulate rainfall depth. It takes center location of typhoon, maximum center wind speed of typhoon, storm radius of the tenth-level wind speed, storm radius of the seventh-level wind speed, center atmospheric pressure of typhoon, characteristic parameters, wind speed and direction of high altitude and ground, atmospheric pressure and temperature of local rain gauge station etc. as input of BPN model. This thesis divides the study area of Taiwan and its offshore area into 16 grids. It is the major difference between this thesis and its precedent research. An individual BPN model was developed for each grid. This thesis established and compared two BPN models. Both models have two hidden layers to increase the ability of description. Model I adopted all meteorologic data as inputs to train BPN, however the Model II only included those events with rainfall. The results showed that Model I is better then Model II in general, but Model II has better estimate of peak-time. Simulating rainfall hyetograph of typhoon AERE of 2004 with Model I, after deleting a few meteorological factors, the coefficient of efficiency (CE) is 0.99 and root mean square error (RMSE) is 6.5. The CE is 0.41 and RMSE is 6.6 after simulating with Wang’s model (2007). Generally speaking, the model I developed in this thesis gains better CE and RMSE.
31
高正一. "A neural network model based on fuzzy classification concept." Thesis, 1992. http://ndltd.ncl.edu.tw/handle/52510456915064071054.
Full text
32
Yu, Hong-Kai, and 游弘凱. "Prediction of PID Phenomenon based on Neural Network Model." Thesis, 2016. http://ndltd.ncl.edu.tw/handle/76823974246043135494.
Full textAbstract:
碩士國立宜蘭大學
電機資訊學院碩士在職專班
104
Potential Induced Degradation (PID) is a kind of induced attenuation phenomenon which makes solar module panels to withstand the impact from the terminal voltage when solar cell is packaged into the PV modules and work at outdoors in sunlight to generate electricity. It will cause serious solar module panels’ power attenuation, and result in lower power generation efficiency and more serious problems when the terminal voltage is applied on solar modules, due to this phenomenon. In this study, we prepare the three kind cell of different Reflection Index, compare the standard module and mini-module test result base on the IEC 62804 test condition; We also compare the mini-module and signal cell PID test result. The result was show positive correlation between mini-module and signal cell. In addition, settling time method was applied to PID issue forecast. The average prediction hit rate is 94% at 14th hour test. At last, a data analysis method is by neural network theory and predict the cell whether the occurrence PID issue on PV module. Base on the neural network black box and no need the detail math mode characteristic for data analyze, it will be occur more than 80% hit rate at 2hr. If we predict the PID issue on cell level, that we can reduce the cost, and increase the quality and reliability at outside.
33
Tsai, Jui-Ju, and 蔡睿儒. "Process Optimization Based on Neural Network Model and Orthogonal Arrays." Thesis, 2008. http://ndltd.ncl.edu.tw/handle/89636932994073794808.
Full textAbstract:
碩士中原大學
機械工程研究所
96
This thesis presents a systematic and cost-effective approach for process optimization with minimal experimental runs. Based on the experimental design scheme of orthogonal arrays, artificial neural network is used to establish the process model. Moreover, Taguchi-genetic algorithm (TGA) is used to search for the global optimum of the fabrication conditions. The procedure starts planning and conducting the initial experiment with fewer levels. By adding experimental points selected from augmented orthogonal arrays, the process model is corrected. This step is continued until the termination condition has been reached. Then, the optimum given by Taguchi-genetic algorithm is the final solution. This proposed approach provides an effective and economical solution for process optimization. In this research, we chose copper CMP process for verifying the effectiveness of hybrid optimization algorithm. The controllable factors of CMP machine includes back pressure, platen speed, carrier speed, and polishing time. We used orthogonal array (OA) experiments to train a neural network (NN) for creating the process model. Then we used Taguchi-genetic algorithm to find the global optimum of the control parameters. The removal rate target of the Cu film was 5500 Å. Applying the optimal parameters to the CMP machine, we got an average removal rate of 5431 Å. The result approved that the approach in this research was able to get a set of optimal parameters with better accuracy than Taguchi method.
34
Hsiao, Chih-kai, and 蕭志凱. "A neural network based model for controlling smart building skins." Thesis, 2008. http://ndltd.ncl.edu.tw/handle/53741826763028181414.
Full textAbstract:
碩士國立臺灣科技大學
建築系
96
Building skin defines the relation of people and natural environment. It should be adjustable to the changes of people needs and natural environment. Building skins need the ability of learning for the adaptation to different situations under variations of spatial functions, opening, surroundings and occupants of the building. This research advances a feasible framework which can realize smart building skins by providing the ability of learning and automatic controlling to satisfy the demands of people for a comfortable environment by adjusting parameters of the smart building skin. A neural network is used as the control system. We use a set of virtual data to evaluate the system. The result shows that the average accuracy of the system output control increases when the volume of training data increases and shows the system can learn effectively. Furthermore, the standard deviation of the distance between forecast output and target output decreases gradually when the volume of training data increases, and it shows that the output control of the system becomes more stable by continuously learning.
35
Lee, Hsin-Ni, and 李心妮. "An Integrated Neural Network Based Inspection Model of Financial Distress." Thesis, 2006. http://ndltd.ncl.edu.tw/handle/88983574117257721857.
Full text
36
Peng, Chi-Wei, and 彭志煒. "A Neural Network Based Model for Hysteresis Loop of Transformers." Thesis, 1995. http://ndltd.ncl.edu.tw/handle/63127790094797053606.
Full text
37
Wang, Hao-Cheng, and 王浩丞. "An Attention-based Neural Network Model for Interest Shift Prediction." Thesis, 2016. http://ndltd.ncl.edu.tw/handle/j879jw.
Full textAbstract:
碩士國立臺灣大學
資訊工程學研究所
105
Recommendation systems have mainly dealt with the problem of recommending items to fit user preferences, while the dynamicity of user interest is not fully considered. We observe that music streaming platforms like YouTube always recommend songs that either from the same artist or with the same title, assuming that users have a static interest in similar items, but ignore the fact that we get satiated easily with repeated consumptions. To provide a more appealing user experience, recent developments in recommendation system have focused on introducing novelty in the recommendation list; however, none of these works try to discuss ``when will the users shift their interest?", the key problem that determines our strategies to recommend new items or similar items. In this work, we present a novel model for interest shift prediction. By the state-of-the-art deep learning techniques that excel in extracting high-level knowledge, we try to construct the latent representations of mental states, and apply the attention mechanism on our model to automatically detect the shifting patterns in the listening records. Experiments and case studies show that our models can achieve good accuracy as well as interpretability.
38
Wu, Chao-Chung, and 吳肇中. "An Attention Based Neural Network Model for Unsupervised Lyrics Rewriting." Thesis, 2018. http://ndltd.ncl.edu.tw/handle/w4bcnv.
Full textAbstract:
碩士國立臺灣大學
資訊工程學研究所
106
Creative writing has become a standard task to showcase the power of artificial intelligence. This work tackles a challenging task in this area, the lyrics rewriting. This task possesses several unique challenges. First, we require the outputs to be not only semantically correlated with the original lyrics, but also coherent in segmentation structure, rhyme as the rewritten lyrics must be performed by the artist with the same music. Second, there is no parallel rewriting lyrics corpus available for supervised training. We propose a deep neural network based model for this task and exploit both general evaluation metrics such as ROUGE and human study to evaluate the effectiveness of the model.
39
LAI, WEI-CHENG, and 賴偉程. "Building Children Emotion Recognition Model Based on Convolutional Neural Network." Thesis, 2019. http://ndltd.ncl.edu.tw/handle/88wp5c.
Full textAbstract:
碩士國立臺北科技大學
資訊工程系
107
In daily life, people often express emotions through ways other than language. Among them, people’s facial expression is the most common way to express their emotion, people can take corresponding actions to achieve their goals via facial expression. Thus the emotion recognition has become an important technology in the artificial intelligence industry, the related work including Safe Driving, Commercial Advertising Evaluation, etc. Although there are several emotion recognition models for adult appeared in recent years, they didn’t have better performance on children facial expression through children has different facial features from adult’s. To solve this problem, this research takes four different classes in the kindergarten as the dataset, building children emotion recognition model based on Convolutional Neural Network. First, this research cropped and converted the dataset picture to grayscale, and labeled an emotion in seven classes as the right result for the picture, including angry, disgust, fear, happiness, sadness, surprise, neutral, contempt. Then input these data into the Convolutional Neural Network. Since Convolutional Neural Network is different from the neural network based on traditional feature engineering, it can learn the emotional features for the classes itself without manual setting, At the same time, this research added residual modules and depth-wise separable convolutions to reduce the depth and parameter in the Convolutional Neural Network. At last, this research used a support vector machine to classify the result. After finishing the training, this research used the test data to evaluate the accuracy of the model, to prove the model can effectively recognize children's expression emotions.
40
盧嘉弘. "An internal model control-based neural network ship steering autipilot design." Thesis, 2002. http://ndltd.ncl.edu.tw/handle/05964257685286522082.
Full textAbstract:
碩士國立海洋大學
航運技術研究所
90
It is well known that the ship steering dynamics is characterized by a highly complicated nonlinear behavior. For simplicity, a linear model is often adopted in the design of the steering autopilot to facilitate the design and implementation. However, to make the autopilot of practical use, the modeling error between the model and the plant under control has to be monitored and the controller parameters should be adjusted accordingly. In this work, the internal model control (IMC) configuration is adopted and the neural network (NN） is employed in describing the model and the controller, which is essentially the model inverse under the IMC structure. Two important features are combined in this study, specifically, the IMC has a clear connection between the model and the controller and the NN is capable of learning adaptively. In this work, both two-layer and three-layer feedforward networks are considered in the design of a heading control autopilot and a yaw rate control autopilot. Numerical simulations indicate that very good tracking performance is achieved for the square wave, saw-tooth and sine wave reference inputs.
41
Ke, Ching-Shun, and 柯清順. "The Predicting and Identifying of system model based on Neural Network." Thesis, 2005. http://ndltd.ncl.edu.tw/handle/98348418393663863026.
Full textAbstract:
碩士國立臺灣海洋大學
電機工程學系
93
For the analysis and application of control-theory, It is necessary to model the system to a mathematic platform, according to the physical, input and output characteristic of the system. Unfortunately, the complexity of the system and uncertainty of environment cause that the model cannot exactly and accurately performs all the behavior of the target system. Therefore, the implementation cannot achieve our expected performance due to inaccurate modeling. This paper will apply the advantages of simple architecture and operation of backpropagation to setup the system. It avoids the complexity of the mathematic modeling. the implementation of nervous-network model, whose response completely follows up the reference model, is applied to the model reference adaptive controller.
42
Huang, Teng Yu, and 黃登宇. "The Research of Gold Price Forecasting Model based on Neural Network." Thesis, 2012. http://ndltd.ncl.edu.tw/handle/23183123048808260533.
Full textAbstract:
碩士臺北城市科技大學
電子商務研究所
100
It's volatile times to international finance situation . Since the U.S. investment bank Lehman Brothers went bankrupt in 2008, the following are debt crisis in Europe and the risk of US national debt. Certainly, the events cause USD devaluation. We found that LIBOR rate & TED spread have been raised while the stock price were go down in the market. In this study, we propose two hypotheses. First, MA, RSI, two indicators help to improve the forecasting performance of gold. Second, TED spread will help enhance the performance of the gold price forecast. The experimental results show that MA, RSI, and the TED spread factor are main impact to effect the factor price of gold. The prediction model of the proposed structure has been maintained to predict the stability of the performance, thus, the gold price prediction model can be confirm.
43
Hsu, Chia-Ming, and 許家銘. "Emotional and Conditional Model for Pet Robot based on Neural Network." Thesis, 2014. http://ndltd.ncl.edu.tw/handle/62567712120856301898.
Full textAbstract:
碩士中原大學
資訊工程研究所
102
Recently more and more pet robot products are launched, which showing the increasing market demand for pet robots, and a plenty of researches have pointed out that the product innovativeness can encourage consumers’ acceptance, the pet robot will be made with more variability, more versatility, and more interesting in each generation. To make the robots do common activities in the same environment with human and integrate it to human’ life is the target of those researchers who were studying in the field of intelligent robot. As a matter of fact, all traditional robots have to face with two major issues: one is the user limitation of patience and passion, and the other is the users cannot escape from the thought of “interacting with a hard and cold robot machine”. This research is aimed at making the pet robots perform more naturally; therefore a simplified prototype system has been designed, it is composed of conditional model and emotional model. The conditional model can make every pet robot have unique interactive style, its theoretical foundation of learning method is based on classical conditioning. And the computational model is binding up with associative neural network and Hebbian learning rule, it can implements acquisition, extinction, and reacquisition effects as basic characteristics, and other extensive characteristics, such as blocking and secondary conditioning. On the other hand, the emotional model was modeled on the impact of the actual biological relationship between endocrine and emotion, which was built up eight basic emotions; apart from this, the concepts of emotion and feeling have also been adopted, thus determine the final performance behavior by using mood-driven approach. In this research, two aspects of achievement will be demonstrated: the first is how the learning method affects the emotion of pet robot, and the second is how the emotion affects the behavior of pet robot. Hopefully, the pet robot can learn like a human, performing biological self-expression, making people think the pet robot is animated machine, and people will get more trusting experience while they are interacting with each other.
44
Tsung-ChiehWen and 溫淙傑. "Implementation of Text Classification Model Based on Recurrent Convolutional Neural Network." Thesis, 2017. http://ndltd.ncl.edu.tw/handle/qq5p25.
Full textAbstract:
碩士國立成功大學
工程科學系碩士在職專班
105
In a variety of community media types of network platform have on-line operation, and the popularity of smart phones, these changes have changed the way people use the web. Over the past years, users only can search and get the information from the website, but now the user can be an information provider. Many Internet users began to be willing and keen to share their views out, so there is a lot of text data on the Internet. Ten years ago people have heard this sentence:「This is an era of information explosion」, and now because everyone can be the provider of messages, as compared to a decade ago, the current amount of information on the Internet is more larger. These content generated by the user often contains some opinion, evaluation and other information, and these messages can often be converted into valuable information, and this information can be used by individuals or corporate groups. But the text on the Internet is too much, cannot be man-made to collect and analyze. So how to use the machine to help users analyze these texts is one of the important topics in the field of information capture in recent years. In this research, we implemented a deep learning network architecture, which combined with the architecture of convolutional neural network and the architecture of recurrent neural network. And use to complete the goal of text classification with the pre-trained word vectors. The difficulty is that the word vector should be used as a static lookup table without updating, but the network still can ignore the noise which caused by missing words to complete the task. The experimental results show that the accuracy of this study is consistent with the accuracy of other studies, proved the feasibility of this architecture. And has the following advantages: 1. The accuracy rate of this architecture is higher than that of recurrent neural network, 2. Compared with the convolution neural network, the accuracy results are more stable, 3. Use less epoch to get stable results. But the shortcoming of this research architecture is that training time is too long.
45
Huang, Chun-Chieh, and 黃駿杰. "A TFT-LCD Defect Classification Model Based on Convolutional Neural Network." Thesis, 2018. http://ndltd.ncl.edu.tw/handle/25awgz.
Full textAbstract:
碩士國立交通大學
工業工程與管理系所
106
Since the ever-changing technology nowadays, people are increasing their request for skill and qualities as well as the display screens. As the level of the quality of display screens rise, the numbers of dead dots that used to be the inspection standard become a problem that can’t be ignored. Traditional inspection methods that inspected by humans may cause occupational injuries and fatigue and also harm the yield rate. Therefore, the trend of using Automatic Optical Inspection (AOI) instead of the traditional way is inevitable. This research is based on AOI, constructing a TFT-LCD defect classification model based on Convolutional Neural Network, evidenced with practical data provided by one well-known laptop brand in Taiwan. The related researches for dead dots recently are most thorough machine learning which processes images and calculates feature values first and finally classifies it with the algorithm. The breakthrough of this research is that there is no need to process images and calculate feature values. Besides, the distinguish rate is up to 99.4% so that we can say it’s effective to classify dead dots for TFT-LCD.
46
Hsiao, Chung-Ting, and 蕭仲廷. "A Policy-Based Reinforcement Learning Model for Neural Network Architecture Search." Thesis, 2019. http://ndltd.ncl.edu.tw/handle/vruep9.
Full textAbstract:
碩士國立中央大學
軟體工程研究所
107
The last few years, in the field of machine learning deep learning and its core – neural network has playing a very important role. Because of its high performance, and easy to implement, in addition to computing resource advancement such as GPU and TPU, these reason triggered a vigorous growth of deep learning and neural network. The most common problem user faced is when using deep learning which neural network structure should user use, and how can neural network structure be designed. Furthermore because of handcraft neural network need a great deal of knowledge and experience. Lately, a lot of studies has focused on this issue—how to automatically generate the finest neural network. There are several methods to implement the method, in this paper we use reinforcement learning based method, and Propose a special method call Hill Climbing Model (HCM), this model will find the finest structure for the user, and it is easy to train just cost few computing resource.
47
Tsai, Tzu-Han, and 蔡子涵. "A DQN-Based Reinforcement Learning Model for Neural Network Architecture Search." Thesis, 2019. http://ndltd.ncl.edu.tw/handle/qf2jk4.
Full textAbstract:
碩士國立中央大學
資訊管理學系
107
Designing neural network (NN) architectures requires both human expertise and labor. New architectures are handcrafted by careful experimentation or modified from a handful of existing networks. We introduce HCM, a meta-modeling algorithm based on reinforcement learning to automatically generate high-performing NN architectures for a given learning task. The learning agent is trained to sequentially choose NN layers using DQN with an ɛ-greedy exploration strategy and experience replay. The agent explores a large but finite space of possible architectures and iteratively discovers designs with improved performance on the learning task. Even on image classification benchmarks, the agent-designed networks can do good as existing networks designed but more efficient. We also outperform existing meta-modeling approaches for network design on image classification or regression tasks.
48
Chao, Lee-Chang, and 趙豊昌. "The Yield Prediction Model with Neural Network for Integrated Circuit --- Based on Poisson Model." Thesis, 1997. http://ndltd.ncl.edu.tw/handle/46233153779168204597.
Full textAbstract:
碩士國立交通大學
工業工程與管理學系
85
In integrated circuit (IC) manufacturing, a wafer''s defects tend to cluster. As the wafer size increases, the clustering phenomenon of the defects becomes increasingly apparent.When the conventional Poisson yield model is used, the clustered defects frequently cause false results. In this study, we propose a neural network-based modified Poisson yield model to predict the wafer yield in IC manufacturing. The proposed approach can reduce the phenomenon of the false predictions caused by the clustered defects. A case study is also presented, demonstrating the effectiveness of the proposed approach.Keywords: integrated circuit, defects, cluster, yield model, neural network
49
(8784458), Qin He. "Learning Lighting Models with Shader-Based Neural Networks." Thesis, 2020.
Find full textAbstract:
To correctly reproduce the appearance of different objects in computer graphics applications, numerous lighting models have been proposed over the past several decades. These models are among the most important components in the modern graphics pipeline since they decide the final pixel color shown in the generated images. More physically valid parameters and functions have been introduced into recent models. These parameters expanded the range of materials that can be represented and made virtual scenes more realistic, but they also made the lighting models more complex and dependent on measured data.
Artificial neural networks, or neural networks are famous for their ability to deal with complex data and to approximate arbitrary functions. They have been adopted by many data-driven approaches for computer graphics and proven to be effective. Furthermore, neural networks have also been used by the artists for creative works and proven to have the ability of supporting creation of visual effects, animation and computational arts. Therefore, it is reasonable to consider artificial neural networks as potential tools for representing lighting models. Since shaders are used for general-purpose computing, neural networks can be further combined with modern graphics pipeline using shader implementation.
In this research, the possibilities of shader-based neural networks to be used as an alternative to traditional lighting models are explored. Fully connected neural networks are implemented in fragment shader to reproduce lighting results in the graphics pipeline, and trained in compute shaders. Implemented networks are proved to be able to approximate mathematical lighting models. In this thesis, experiments are described to prove the ability of shader-based neural networks, to explore the proper network architecture and settings for different lighting models. Further explorations of possibilities of manually editing parameters are also described. Mean-square errors and runtime are taken as measurements of success to evaluate the experiments. Rendered images are also reported for visual comparison and evaluation.
50
Stewart, IAN. "A Modified Genetic Algorithm and Switch-Based Neural Network Model Applied to Misuse-Based Intrusion Detection." Thesis, 2009. http://hdl.handle.net/1974/1720.
Full textAbstract:
As our reliance on the Internet continues to grow, the need for secure, reliable networks also increases. Using a modified genetic algorithm and a switch-based neural network model, this thesis outlines the creation of a powerful intrusion detection system (IDS) capable of detecting network attacks.
The new genetic algorithm is tested against traditional and other modified genetic algorithms using common benchmark functions, and is found to produce better results in less time, and with less human interaction. The IDS is tested using the standard benchmark data collection for intrusion detection: the DARPA 98 KDD99 set. Results are found to be comparable to those achieved using ant colony optimization, and superior to those obtained with support vector machines and other genetic algorithms.Thesis (Master, Computing) -- Queen's University, 2009-03-03 13:28:23.787