Kliknij ten link, aby zobaczyć inne rodzaje publikacji na ten temat: Radial Basis Function Neural Network Classifier.
Rozprawy doktorskie na temat „Radial Basis Function Neural Network Classifier”
Utwórz poprawne odniesienie w stylach APA, MLA, Chicago, Harvard i wielu innych
Sprawdź 50 najlepszych rozpraw doktorskich naukowych na temat „Radial Basis Function Neural Network Classifier”.
Przycisk „Dodaj do bibliografii” jest dostępny obok każdej pracy w bibliografii. Użyj go – a my automatycznie utworzymy odniesienie bibliograficzne do wybranej pracy w stylu cytowania, którego potrzebujesz: APA, MLA, Harvard, Chicago, Vancouver itp.
Możesz również pobrać pełny tekst publikacji naukowej w formacie „.pdf” i przeczytać adnotację do pracy online, jeśli odpowiednie parametry są dostępne w metadanych.
Przeglądaj rozprawy doktorskie z różnych dziedzin i twórz odpowiednie bibliografie.
1
Kamat, Sai Shyamsunder. "Analyzing Radial Basis Function Neural Networks for predicting anomalies in Intrusion Detection Systems". Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-259187.
Pełny tekst źródłaStreszczenie:
In the 21st century, information is the new currency. With the omnipresence of devices connected to the internet, humanity can instantly avail any information. However, there are certain are cybercrime groups which steal the information. An Intrusion Detection System (IDS) monitors a network for suspicious activities and alerts its owner about an undesired intrusion. These commercial IDS’es react after detecting intrusion attempts. With the cyber attacks becoming increasingly complex, it is expensive to wait for the attacks to happen and respond later. It is crucial for network owners to employ IDS’es that preemptively differentiate a harmless data request from a malicious one. Machine Learning (ML) can solve this problem by recognizing patterns in internet traffic to predict the behaviour of network users. This project studies how effectively Radial Basis Function Neural Network (RBFN) with Deep Learning Architecture can impact intrusion detection. On the basis of the existing framework, it asks how well can an RBFN predict malicious intrusive attempts, especially when compared to contemporary detection practices.Here, an RBFN is a multi-layered neural network model that uses a radial basis function to transform input traffic data. Once transformed, it is possible to separate the various traffic data points using a single straight line in extradimensional space. The outcome of the project indicates that the proposed method is severely affected by limitations. E.g. the model needs to be fine tuned over several trials to achieve a desired accuracy. The results of the implementation show that RBFN is accurate at predicting various cyber attacks such as web attacks, infiltrations, brute force, SSH etc, and normal internet behaviour on an average 80% of the time. Other algorithms in identical testbed are more than 90% accurate. Despite the lower accuracy, RBFN model is more than 94% accurate at recording specific kinds of attacks such as Port Scans and BotNet malware. One possible solution is to restrict this model to predict only malware attacks and use different machine learning algorithm for other attacks.I det 21: a århundradet är information den nya valutan. Med allnärvaro av enheter anslutna till internet har mänskligheten tillgång till information inom ett ögonblick. Det finns dock vissa grupper som använder metoder för att stjäla information för personlig vinst via internet. Ett intrångsdetekteringssystem (IDS) övervakar ett nätverk för misstänkta aktiviteter och varnar dess ägare om ett oönskat intrång skett. Kommersiella IDS reagerar efter detekteringen av ett intrångsförsök. Angreppen blir alltmer komplexa och det kan vara dyrt att vänta på att attackerna ska ske för att reagera senare. Det är avgörande för nätverksägare att använda IDS:er som på ett förebyggande sätt kan skilja på oskadlig dataanvändning från skadlig. Maskininlärning kan lösa detta problem. Den kan analysera all befintliga data om internettrafik, känna igen mönster och förutse användarnas beteende. Detta projekt syftar till att studera hur effektivt Radial Basis Function Neural Networks (RBFN) med Djupinlärnings arkitektur kan påverka intrångsdetektering. Från detta perspektiv ställs frågan hur väl en RBFN kan förutsäga skadliga intrångsförsök, särskilt i jämförelse med befintliga detektionsmetoder.Här är RBFN definierad som en flera-lagers neuralt nätverksmodell som använder en radiell grundfunktion för att omvandla data till linjärt separerbar. Efter en undersökning av modern litteratur och lokalisering av ett namngivet dataset användes kvantitativ forskningsmetodik med prestanda indikatorer för att utvärdera RBFN: s prestanda. En Random Forest Classifier algorithm användes också för jämförelse. Resultaten erhölls efter en serie finjusteringar av parametrar på modellerna. Resultaten visar att RBFN är korrekt när den förutsäger avvikande internetbeteende i genomsnitt 80% av tiden. Andra algoritmer i litteraturen beskrivs som mer än 90% korrekta. Den föreslagna RBFN-modellen är emellertid mycket exakt när man registrerar specifika typer av attacker som Port Scans och BotNet malware. Resultatet av projektet visar att den föreslagna metoden är allvarligt påverkad av begränsningar. T.ex. så behöver modellen finjusteras över flera försök för att uppnå önskad noggrannhet. En möjlig lösning är att begränsa denna modell till att endast förutsäga malware-attacker och använda andra maskininlärnings-algoritmer för andra attacker.
2
Koudelka, Vlastimil. "Neuronové sítě pro modelování EMC malých letadel". Master's thesis, Vysoké učení technické v Brně. Fakulta elektrotechniky a komunikačních technologií, 2009. http://www.nusl.cz/ntk/nusl-217813.
Pełny tekst źródłaStreszczenie:
This thesis deals with neural modeling of electromagnetic field inside small aircrafts, witch can contain composite materials in their construction. Introduction to neural networks and its application in EMC of small airplanes is discussed in the first part of the text. In the second part of this thesis we design a simple EM model of small airplane. The airplane is simulated by two parallel dielectric layers (the left-hand side wall and the right hand side wall of the airplane). The layers are put into a rectangular metallic waveguide terminated by the absorber in order to simulate the illumination of the airplane by the external wave (both of the harmonic nature and pulse one). Numerical analyses are performed to search the relations between the distribution of an electromagnetic field inside the aircraft and electric parameters of model walls. The results of numerical analyses are used to train two types of neural network. In this way we can obtain accurate continuous model of electromagnetic field inside the aircraft. For the comparison with neural networks a multi-dimensional cubic spline interpolation is provided also. Neural classifiers are also investigated. We use them for classification of imaginary composite materials in terms of EMC. The nearest neighbour algorithm is applied as a classic approach to problem of classification.
3
Murphy, Ethan Kane. "Radial-Basis-Function Neural Network Optimization of Microwave Systems". Digital WPI, 2003. https://digitalcommons.wpi.edu/etd-theses/77.
Pełny tekst źródłaStreszczenie:
An original approach in microwave optimization, namely, a neural network procedure combined with the full-wave 3D electromagnetic simulator QuickWave-3D implemented a conformal FDTD method, is presented. The radial-basis-function network is trained by simulated frequency characteristics of S-parameters and geometric data of the corresponding system. High accuracy and computational efficiency of the procedure is illustrated for a waveguide bend, waveguide T-junction with a post, and a slotted waveguide as a radiating element.
4
Murphy, Ethan Kane. "Radial-Basis-Function Neural Network Optimization of Microwave Systems". Link to electronic thesis, 2002. http://www.wpi.edu/Pubs/ETD/Available/etd-0113103-121206/.
Pełny tekst źródłaStreszczenie:
Master's Project (M.S.) -- Worcester Polytechnic Institute.Keywords: optimization technique; microwave systems; optimization technique; neural networks; QuickWave 3D. Includes bibliographical references (p. 68-71).
5
Aguilar, David P. "A radial basis neural network for the analysis of transportation data". [Tampa, Fla.] : University of South Florida, 2004. http://purl.fcla.edu/fcla/etd/SFE0000515.
Pełny tekst źródła
6
Fathala, Giuma Musbah. "Analysis and implementation of radial basis function neural network for controlling non-linear dynamical systems". Thesis, University of Newcastle upon Tyne, 1998. http://hdl.handle.net/10443/3114.
Pełny tekst źródłaStreszczenie:
Modelling and control of non-linear systems are not easy, which are now being solved by the application of neural networks. Neural networks have been proved to solve these problems as they are described by adjustable parameters which are readily adaptable online. Many types of neural networks have been used and the most common one is the backpropagation algorithm. The algorithm has some disadvantages, such as slow convergence and construction complexity. An alternative neural networks to overcome the limitations associated with the backpropagation algorithm is the Radial Basis Function Network which has been widely used for solving many complex problems. The Radial Basis Function Network is considered in this theses, along with a new adaptive algorithm which has been developed to overcome the problem of the optimum parameter selection. Use of the new algorithm reduces the trial and error of selecting the minimum required number of centres and guarantees the optimum values of the centres, the widths between the centres and the network weights. Computer simulation usmg SimulinklMatlab packages, demonstrated the results of modelling and control of non-linear systems. Moreover, the algorithm is used for selecting the optimum parameters of a non-linear real system 'Brushless DC Motor'. In the laboratory implementation satisfactory results have been achieved, which show that the Radial Basis Function may be used for modelling and on-line control of such real non-linear systems.
7
Lee, Hee Eun. "Hierarchical modeling of multi-scale dynamical systems using adaptive radial basis function neural networks: application to synthetic jet actuator wing". Thesis, Texas A&M University, 2003. http://hdl.handle.net/1969.1/230.
Pełny tekst źródłaStreszczenie:
To obtain a suitable mathematical model of the input-output behavior of highly nonlinear, multi-scale, nonparametric phenomena, we introduce an adaptive radial basis function approximation approach. We use this approach to estimate the discrepancy between traditional model areas and the multiscale physics of systems involving distributed sensing and technology. Radial Basis Function Networks offers the possible approach to nonparametric multi-scale modeling for dynamical systems like the adaptive wing with the Synthetic Jet Actuator (SJA). We use the Regularized Orthogonal Least Square method (Mark, 1996) and the RAN-EKF (Resource Allocating Network-Extended Kalman Filter) as a reference approach. The first part of the algorithm determines the location of centers one by one until the error goal is met and regularization is achieved. The second process includes an algorithm for the adaptation of all the parameters in the Radial Basis Function Network, centers, variances (shapes) and weights. To demonstrate the effectiveness of these algorithms, SJA wind tunnel data are modeled using this approach. Good performance is obtained compared with conventional neural networks like the multi layer neural network and least square algorithm. Following this work, we establish Model Reference Adaptive Control (MRAC) formulations using an off-line Radial Basis Function Networks (RBFN). We introduce the adaptive control law using a RBFN. A theory that combines RBFN and adaptive control is demonstrated through the simple numerical simulation of the SJA wing. It is expected that these studies will provide a basis for achieving an intelligent control structure for future active wing aircraft.
8
Kattekola, Sravanthi. "Weather Radar image Based Forecasting using Joint Series Prediction". ScholarWorks@UNO, 2010. http://scholarworks.uno.edu/td/1238.
Pełny tekst źródłaStreszczenie:
Accurate rainfall forecasting using weather radar imagery has always been a crucial and predominant task in the field of meteorology [1], [2], [3] and [4]. Competitive Radial Basis Function Neural Networks (CRBFNN) [5] is one of the methods used for weather radar image based forecasting. Recently, an alternative CRBFNN based approach [6] was introduced to model the precipitation events. The difference between the techniques presented in [5] and [6] is in the approach used to model the rainfall image. Overall, it was shown that the modified CRBFNN approach [6] is more computationally efficient compared to the CRBFNN approach [5]. However, both techniques [5] and [6] share the same prediction stage. In this thesis, a different GRBFNN approach is presented for forecasting Gaussian envelope parameters. The proposed method investigates the concept of parameter dependency among Gaussian envelopes. Experimental results are also presented to illustrate the advantage of parameters prediction over the independent series prediction.
9
Matta, Mariel Cadena da. "Processamento de imagens em dosimetria citogenética". Universidade Federal de Pernambuco, 2013. https://repositorio.ufpe.br/handle/123456789/10141.
Pełny tekst źródłaStreszczenie:
Submitted by Amanda Silva (amanda.osilva2@ufpe.br) on 2015-03-03T14:16:54Z
No. of bitstreams: 2
Dissertação Mariel Cadena da Matta.pdf: 2355898 bytes, checksum: 9c0530af680cf965137a2385d949b799 (MD5)
license_rdf: 1232 bytes, checksum: 66e71c371cc565284e70f40736c94386 (MD5)Made available in DSpace on 2015-03-03T14:16:54Z (GMT). No. of bitstreams: 2 Dissertação Mariel Cadena da Matta.pdf: 2355898 bytes, checksum: 9c0530af680cf965137a2385d949b799 (MD5) license_rdf: 1232 bytes, checksum: 66e71c371cc565284e70f40736c94386 (MD5) Previous issue date: 2013
FACEPE
A Dosimetria citogenética empregando análise de cromossomos dicêntricos é o “padrão ouro” para estimativas da dose absorvida após exposições acidentais às radiações ionizantes. Todavia, este método é laborioso e dispendioso, o que torna necessária a introdução de ferramentas computacionais que dinamizem a contagem dessas aberrações cromossômicas radioinduzidas. Os atuais softwares comerciais, utilizados no processamento de imagens em Biodosimetria, são em sua maioria onerosos e desenvolvidos em sistemas dedicados, não podendo ser adaptados para microscópios de rotina laboratorial. Neste contexto, o objetivo da pesquisa foi o desenvolvimento do software ChromoSomeClassification para processamento de imagens de metáfases de linfócitos (não irradiados e irradiados) coradas com Giemsa a 5%. A principal etapa da análise citogenética automática é a separação correta dos cromossomos do fundo, pois a execução incorreta desta fase compromete o desenvolvimento da classificação automática. Desta maneira, apresentamos uma proposta para a sua resolução baseada no aprimoramento da imagem através das técnicas de mudança do sistema de cores, subtração do background e aumento do contraste pela modificação do histograma. Assim, a segmentação por limiar global simples, seguida por operadores morfológicos e pela técnica de separação de objetos obteve uma taxa de acerto de 88,57%. Deste modo, os cromossomos foram enfileirados e contabilizados, e assim, a etapa mais laboriosa da Dosimetria citogenética foi realizada. As características extraídas dos cromossomos isolados foram armazenadas num banco de dados para que a classificação automática fosse realizada através da Rede Neural com Funções de Ativação de Base Radial (RBF). O software proposto alcançou uma taxa de sensibilidade de 76% e especificidade de 91% que podem ser aprimoradas através do acréscimo do número de objetos ao banco de dados e da extração de mais características dos cromossomos.
10
Ringienė, Laura. "Hybrid neural network for multidimensional data visualization". Doctoral thesis, Lithuanian Academic Libraries Network (LABT), 2014. http://vddb.library.lt/obj/LT-eLABa-0001:E.02~2014~D_20140912_140117-42267.
Pełny tekst źródłaStreszczenie:
The area of research is data mining based on multidimensional data visual analysis. This allows researcher to participate in the process of data analysis directly, to understand the complex data better and to make the best decisions. The objective of the dissertation is to create a method for making a multidimensional data projection on the plane such that the researcher could see and assess the intergroup similarities and differences of multidimensional points. In order to achieve the target, a new hybrid neural network is proposed and investigated. This neural network integrates the ideas both of the radial basis function neural network and that of a multilayer perceptron, which has the properties of a ''bottleneck'' neural network. The new network is used for the visual analysis of multidimensional data in such a way that the output values of the neurons of the last hidden layer are the two-dimensional or three-dimensional projections of the multidimensional data, when the multidimensional data is given to the network. A peculiarity of the network is that the visualization results on the plane reflect the general structure of the data (clusters, proximity between clusters, intergroup similarities of points) rather than the location of multidimensional points.Šio darbo tyrimų sritis yra duomenų tyryba remiantis daugiamačių duomenų vizualia analize. Tai leidžia tyrėjui betarpiškai dalyvauti duomenų analizės procese, geriau pažinti sudėtingus duomenis ir priimti geriausius sprendimus. Disertacijos tikslas yra sukurti metodą tokios duomenų projekcijos radimui plokštumoje, kad tyrėjas galėtų pamatyti ir įvertinti daugiamačių taškų tarpgrupinius panašumus/skirtingumus. Šiam tikslui pasiekti yra pasiūlytas radialinių bazinių funkcijų ir daugiasluoksnio perceptrono, turinčio ,,butelio kaklelio“ neuroninio tinklo savybes, junginys. Naujas tinklas naudojamas vizualiai daugiamačių duomenų analizei, kai atidėjimui plokštumoje arba trimatėje erdvėje taškai gaunami paskutinio paslėpto neuronų sluoksnio išėjimuose, kai į tinklo įėjimą paduodami daugiamačiai duomenys. Šio tinklo ypatybė yra ta, kad gautas vaizdas plokštumoje labiau atspindi bendrą duomenų struktūrą (klasteriai, klasterių tarpusavio artumas, taškų tarpklasterinis panašumas) nei daugiamačių taškų tarpusavio išsidėstymą.
11
Lee, Jun won. "Relationships Among Learning Algorithms and Tasks". BYU ScholarsArchive, 2011. https://scholarsarchive.byu.edu/etd/2478.
Pełny tekst źródłaStreszczenie:
Metalearning aims to obtain knowledge of the relationship between the mechanism of learning and the concrete contexts in which that mechanisms is applicable. As new mechanisms of learning are continually added to the pool of learning algorithms, the chances of encountering behavior similarity among algorithms are increased. Understanding the relationships among algorithms and the interactions between algorithms and tasks help to narrow down the space of algorithms to search for a given learning task. In addition, this process helps to disclose factors contributing to the similar behavior of different algorithms. We first study general characteristics of learning tasks and their correlation with the performance of algorithms, isolating two metafeatures whose values are fairly distinguishable between easy and hard tasks. We then devise a new metafeature that measures the difficulty of a learning task that is independent of the performance of learning algorithms on it. Building on these preliminary results, we then investigate more formally how we might measure the behavior of algorithms at a ner grained level than a simple dichotomy between easy and hard tasks. We prove that, among all many possible candidates, the Classifi er Output Difference (COD) measure is the only one possessing the properties of a metric necessary for further use in our proposed behavior-based clustering of learning algorithms. Finally, we cluster 21 algorithms based on COD and show the value of the clustering in 1) highlighting interesting behavior similarity among algorithms, which leads us to a thorough comparison of Naive Bayes and Radial Basis Function Network learning, and 2) designing more accurate algorithm selection models, by predicting clusters rather than individual algorithms.
12
Ignatavičienė, Ieva. "Tiesioginio sklidimo neuroninių tinklų sistemų lyginamoji analizė". Master's thesis, Lithuanian Academic Libraries Network (LABT), 2012. http://vddb.laba.lt/obj/LT-eLABa-0001:E.02~2012~D_20120801_133809-03141.
Pełny tekst źródłaStreszczenie:
Pagrindinis darbo tikslas – atlikti kelių tiesioginio sklidimo neuroninių tinklų sistemų lyginamąją analizę siekiant įvertinti jų funkcionalumą.
Šiame darbe apžvelgiama: biologinio ir dirbtinio neuronų modeliai, neuroninių tinklų klasifikacija pagal jungimo konstrukciją (tiesioginio sklidimo ir rekurentiniai neuroniniai tinklai), dirbtinių neuroninių tinklų mokymo strategijos (mokymas su mokytoju, mokymas be mokytojo, hibridinis mokymas). Analizuojami pagrindiniai tiesioginio sklidimo neuroninių tinklų metodai: vienasluoksnis perceptronas, daugiasluoksnis perceptronas realizuotas „klaidos skleidimo atgal” algoritmu, radialinių bazinių funkcijų neuroninis tinklas.
Buvo nagrinėjama 14 skirtingų tiesioginio sklidimo neuroninių tinklų sistemos. Programos buvo suklasifikuotos pagal kainą, tiesioginio sklidimo neuroninių tinklo mokymo metodų taikymą, galimybę vartotojui keisti parametrus prieš apmokant tinklą ir techninį programos įvertinimą. Programos buvo įvertintos dešimtbalėje vertinimo sistemoje pagal mokymo metodų įvairumą, parametrų keitimo galimybes, programos stabilumą, kokybę, bei kainos ir kokybės santykį. Aukščiausiu balu įvertinta „Matlab” programa (10 balų), o prasčiausiai – „Sharky NN” (2 balai).
Detalesnei analizei pasirinktos keturios programos („Matlab“, „DTREG“, „PathFinder“, „Cortex“), kurios buvo įvertintos aukščiausiais balais, galėjo apmokyti tiesioginio sklidimo neuroninį tinklą daugiasluoksnio perceptrono metodu ir bent dvi radialinių bazinių funkcijų... [toliau žr. visą tekstą]The main aim – to perform a comparative analysis of several feedforward neural system networks in order to identify its functionality. The work presents both: biological and artificial neural models, also classification of neural networks, according to connections’ construction (of feedforward and recurrent neural networks), studying strategies of artificial neural networks (with a trainer, without a trainer, hybrid). The main methods of feedforward neural networks: one-layer perceptron, multilayer perceptron, implemented upon “error feedback” algorithm, also a neural network of radial base functions have been considered. The work has included 14 different feedforward neural system networks, classified according its price, application of study methods of feedforward neural networks, also a customer’s possibility to change parameters before paying for the network and a technical evaluation of a program. The programs have been evaluated from 1 point to 10 points according to the following: variety of training systems, possibility to change parameters, stability, quality and ratio of price and quality. The highest evaluation has been awarded to “Matlab” (10 points), the lowest – to “Sharky NN” (2 points). Four programs (”Matlab“, “DTREG“, “PathFinder“,”Cortex“) have been selected for a detail analysis. The best evaluated programs have been able to train feedforward neural networks using multilayer perceptron method, also at least two radial base function networks. “Matlab“ and... [to full text]
13
Ringienė, Laura. "Hibridinis neuroninis tinklas daugiamačiams duomenims vizualizuoti". Doctoral thesis, Lithuanian Academic Libraries Network (LABT), 2014. http://vddb.library.lt/obj/LT-eLABa-0001:E.02~2014~D_20140912_140105-52586.
Pełny tekst źródłaStreszczenie:
Šio darbo tyrimų sritis yra duomenų tyryba remiantis daugiamačių duomenų vizualia analize. Tai leidžia tyrėjui betarpiškai dalyvauti duomenų analizės procese, geriau pažinti sudėtingus duomenis ir priimti geriausius sprendimus. Disertacijos tikslas yra sukurti metodą tokios duomenų projekcijos radimui plokštumoje, kad tyrėjas galėtų pamatyti ir įvertinti daugiamačių taškų tarpgrupinius panašumus/skirtingumus. Šiam tikslui pasiekti yra pasiūlytas radialinių bazinių funkcijų ir daugiasluoksnio perceptrono, turinčio ,,butelio kaklelio“ neuroninio tinklo savybes, junginys. Naujas tinklas naudojamas vizualiai daugiamačių duomenų analizei, kai atidėjimui plokštumoje arba trimatėje erdvėje taškai gaunami paskutinio paslėpto neuronų sluoksnio išėjimuose, kai į tinklo įėjimą paduodami daugiamačiai duomenys. Šio tinklo ypatybė yra ta, kad gautas vaizdas plokštumoje labiau atspindi bendrą duomenų struktūrą (klasteriai, klasterių tarpusavio artumas, taškų tarpklasterinis panašumas) nei daugiamačių taškų tarpusavio išsidėstymą.The area of research is data mining based on multidimensional data visual analysis. This allows researcher to participate in the process of data analysis directly, to understand the complex data better and to make the best decisions. The objective of the dissertation is to create a method for making a multidimensional data projection on the plane such that the researcher could see and assess the intergroup similarities and differences of multidimensional points. In order to achieve the target, a new hybrid neural network is proposed and investigated. This neural network integrates the ideas both of the radial basis function neural network and that of a multilayer perceptron, which has the properties of a ''bottleneck'' neural network. The new network is used for the visual analysis of multidimensional data in such a way that the output values of the neurons of the last hidden layer are the two-dimensional or three-dimensional projections of the multidimensional data, when the multidimensional data is given to the network. A peculiarity of the network is that the visualization results on the plane reflect the general structure of the data (clusters, proximity between clusters, intergroup similarities of points) rather than the location of multidimensional points.
14
Ghosh, Dastidar Samanwoy. "Models of EEG data mining and classification in temporal lobe epilepsy: wavelet-chaos-neural network methodology and spiking neural networks". Columbus, Ohio : Ohio State University, 2007. http://rave.ohiolink.edu/etdc/view?acc%5Fnum=osu1180459585.
Pełny tekst źródła
15
Gao, Zhiyuan, i Likai Qi. "Predicting Stock Price Index". Thesis, Halmstad University, Applied Mathematics and Physics (CAMP), 2010. http://urn.kb.se/resolve?urn=urn:nbn:se:hh:diva-3784.
Pełny tekst źródłaStreszczenie:
This study is based on three models, Markov model, Hidden Markov model and the Radial basis function neural network. A number of work has been done before about application of these three models to the stock market. Though, individual researchers have developed their own techniques to design and test the Radial basis function neural network. This paper aims to show the different ways and precision of applying these three models to predict price processes of the stock market. By comparing the same group of data, authors get different results. Based on Markov model, authors find a tendency of stock market in future and, the Hidden Markov model behaves better in the financial market. When the fluctuation of the stock price index is not drastic, the Radial basis function neural network has a nice prediction.
16
Guo, Zhihao. "Intelligent multiple objective proactive routing in MANET with predictions on delay, energy, and link lifetime". online version, 2008. http://rave.ohiolink.edu/etdc/view?acc%5Fnum=case1195705509.
Pełny tekst źródła
17
Paduru, Anirudh. "Fast Algorithm for Modeling of Rain Events in Weather Radar Imagery". ScholarWorks@UNO, 2009. http://scholarworks.uno.edu/td/1097.
Pełny tekst źródłaStreszczenie:
Weather radar imagery is important for several remote sensing applications including tracking of storm fronts and radar echo classification. In particular, tracking of precipitation events is useful for both forecasting and classification of rain/non-rain events since non-rain events usually appear to be static compared to rain events. Recent weather radar imaging-based forecasting approaches [3] consider that precipitation events can be modeled as a combination of localized functions using Radial Basis Function Neural Networks (RBFNNs). Tracking of rain events can be performed by tracking the parameters of these localized functions. The RBFNN-based techniques used in forecasting are not only computationally expensive, but also moderately effective in modeling small size precipitation events. In this thesis, an existing RBFNN technique [3] was implemented to verify its computational efficiency and forecasting effectiveness. The feasibility of modeling precipitation events using RBFNN effectively was evaluated, and several modifications to the existing technique have been proposed.
18
Rodríguez, Martínez Cecilia. "Software quality studies using analytical metric analysis". Thesis, KTH, Kommunikationssystem, CoS, 2013. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-120325.
Pełny tekst źródłaStreszczenie:
Today engineering companies expend a large amount of resources on the detection and correction of the bugs (defects) in their software. These bugs are usually due to errors and mistakes made by programmers while writing the code or writing the specifications. No tool is able to detect all of these bugs. Some of these bugs remain undetected despite testing of the code. For these reasons, many researchers have tried to find indicators in the software’s source codes that can be used to predict the presence of bugs. Every bug in the source code is a potentially failure of the program to perform as expected. Therefore, programs are tested with many different cases in an attempt to cover all the possible paths through the program to detect all of these bugs. Early prediction of bugs informs the programmers about the location of the bugs in the code. Thus, programmers can more carefully test the more error prone files, and thus save a lot of time by not testing error free files. This thesis project created a tool that is able to predict error prone source code written in C++. In order to achieve this, we have utilized one predictor which has been extremely well studied: software metrics. Many studies have demonstrated that there is a relationship between software metrics and the presence of bugs. In this project a Neuro-Fuzzy hybrid model based on Fuzzy c-means and Radial Basis Neural Network has been used. The efficiency of the model has been tested in a software project at Ericsson. Testing of this model proved that the program does not achieve high accuracy due to the lack of independent samples in the data set. However, experiments did show that classification models provide better predictions than regression models. The thesis concluded by suggesting future work that could improve the performance of this program.Idag spenderar ingenjörsföretag en stor mängd resurser på att upptäcka och korrigera buggar (fel) i sin mjukvara. Det är oftast programmerare som inför dessa buggar på grund av fel och misstag som uppkommer när de skriver koden eller specifikationerna. Inget verktyg kan detektera alla dessa buggar. Några av buggarna förblir oupptäckta trots testning av koden. Av dessa skäl har många forskare försökt hitta indikatorer i programvarans källkod som kan användas för att förutsäga förekomsten av buggar. Varje fel i källkoden är ett potentiellt misslyckande som gör att applikationen inte fungerar som förväntat. För att hitta buggarna testas koden med många olika testfall för att försöka täcka alla möjliga kombinationer och fall. Förutsägelse av buggar informerar programmerarna om var i koden buggarna finns. Således kan programmerarna mer noggrant testa felbenägna filer och därmed spara mycket tid genom att inte behöva testa felfria filer. Detta examensarbete har skapat ett verktyg som kan förutsäga felbenägen källkod skriven i C ++. För att uppnå detta har vi utnyttjat en välkänd metod som heter Software Metrics. Många studier har visat att det finns ett samband mellan Software Metrics och förekomsten av buggar. I detta projekt har en Neuro-Fuzzy hybridmodell baserad på Fuzzy c-means och Radial Basis Neural Network använts. Effektiviteten av modellen har testats i ett mjukvaruprojekt på Ericsson. Testning av denna modell visade att programmet inte Uppnå hög noggrannhet på grund av bristen av oberoende urval i datauppsättningen. Men gjordt experiment visade att klassificering modeller ger bättre förutsägelser än regressionsmodeller. Exjobbet avslutade genom att föreslå framtida arbetet som skulle kunna förbättra detta program.
Actualmente las empresas de ingeniería derivan una gran cantidad de recursos a la detección y corrección de errores en sus códigos software. Estos errores se deben generalmente a los errores cometidos por los desarrolladores cuando escriben el código o sus especificaciones. No hay ninguna herramienta capaz de detectar todos estos errores y algunos de ellos pasan desapercibidos tras el proceso de pruebas. Por esta razón, numerosas investigaciones han intentado encontrar indicadores en los códigos fuente del software que puedan ser utilizados para detectar la presencia de errores. Cada error en un código fuente es un error potencial en el funcionamiento del programa, por ello los programas son sometidos a exhaustivas pruebas que cubren (o intentan cubrir) todos los posibles caminos del programa para detectar todos sus errores. La temprana localización de errores informa a los programadores dedicados a la realización de estas pruebas sobre la ubicación de estos errores en el código. Así, los programadores pueden probar con más cuidado los archivos más propensos a tener errores dejando a un lado los archivos libres de error. En este proyecto se ha creado una herramienta capaz de predecir código software propenso a errores escrito en C++. Para ello, en este proyecto se ha utilizado un indicador que ha sido cuidadosamente estudiado y ha demostrado su relación con la presencia de errores: las métricas del software. En este proyecto un modelo híbrido neuro-disfuso basado en Fuzzy c-means y en redes neuronales de función de base radial ha sido utilizado. La eficacia de este modelo ha sido probada en un proyecto software de Ericsson. Como resultado se ha comprobado que el modelo no alcanza una alta precisión debido a la falta de muestras independientes en el conjunto de datos y los experimentos han mostrado que los modelos de clasificación proporcionan mejores predicciones que los modelos de regresión. El proyecto concluye sugiriendo trabajo que mejoraría el funcionamiento del programa en el futuro.
19
Kotol, Martin. "Neuronové modelování elektromegnetických polí uvnitř automobilů". Doctoral thesis, Vysoké učení technické v Brně. Fakulta elektrotechniky a komunikačních technologií, 2018. http://www.nusl.cz/ntk/nusl-390291.
Pełny tekst źródłaStreszczenie:
Disertační práce se věnuje využití umělých neuronových sítí pro modelování elektromagnetických polí uvnitř automobilů. První část práce je zaměřena na analytický popis šíření elektromagnetických vlny interiérem pomocí Nortonovy povrchové vlny. Následující část práce se věnuje praktickému měření a ověření analytických modelů. Praktická měření byla zdrojem trénovacích a verifikačních dat pro neuronové sítě. Práce se zaměřuje na kmitočtová pásma 3 až 11 GHz a 55 až 65 GHz.
20
Martínez, Brito Izacar Jesús. "Quantitative structure fate relationships for multimedia environmental analysis". Doctoral thesis, Universitat Rovira i Virgili, 2010. http://hdl.handle.net/10803/8590.
Pełny tekst źródłaStreszczenie:
Key physicochemical properties for a wide spectrum of chemical pollutants are unknown. This thesis analyses the prospect of assessing the environmental distribution of chemicals directly from supervised learning algorithms using molecular descriptors, rather than from multimedia environmental models (MEMs) using several physicochemical properties estimated from QSARs. Dimensionless compartmental mass ratios of 468 validation chemicals were compared, in logarithmic units, between: a) SimpleBox 3, a Level III MEM, propagating random property values within statistical distributions of widely recommended QSARs; and, b) Support Vector Regressions (SVRs), acting as Quantitative Structure-Fate Relationships (QSFRs), linking mass ratios to molecular weight and constituent counts (atoms, bonds, functional groups and rings) for training chemicals. Best predictions were obtained for test and validation chemicals optimally found to be within the domain of applicability of the QSFRs, evidenced by low MAE and high q2 values (in air, MAE≤0.54 and q2≥0.92; in water, MAE≤0.27 and q2≥0.92).Las propiedades fisicoquímicas de un gran espectro de contaminantes químicos son desconocidas. Esta tesis analiza la posibilidad de evaluar la distribución ambiental de compuestos utilizando algoritmos de aprendizaje supervisados alimentados con descriptores moleculares, en vez de modelos ambientales multimedia alimentados con propiedades estimadas por QSARs. Se han comparado fracciones másicas adimensionales, en unidades logarítmicas, de 468 compuestos entre: a) SimpleBox 3, un modelo de nivel III, propagando valores aleatorios de propiedades dentro de distribuciones estadísticas de QSARs recomendados; y, b) regresiones de vectores soporte (SVRs) actuando como relaciones cuantitativas de estructura y destino (QSFRs), relacionando fracciones másicas con pesos moleculares y cuentas de constituyentes (átomos, enlaces, grupos funcionales y anillos) para compuestos de entrenamiento. Las mejores predicciones resultaron para compuestos de test y validación correctamente localizados dentro del dominio de aplicabilidad de los QSFRs, evidenciado por valores bajos de MAE y valores altos de q2 (en aire, MAE≤0.54 y q2≥0.92; en agua, MAE≤0.27 y q2≥0.92).
21
Lin, Kung-Ting, i 林冠廷. "Radial Basis Function Neural Network Based Bayesian Classifier Design for Data Fusion". Thesis, 2012. http://ndltd.ncl.edu.tw/handle/29789234839137298174.
Pełny tekst źródłaStreszczenie:
碩士育達商業科技大學
資訊管理所
100
A neural-network-based classifier design for adaptive Kalman filtering is introduced to fuse the measurements extracted from multiple sensors to improve tracking accuracy. The proposed method consists of a group of parallel Kalman filters and a classifier based on Radial Basis Function Neural Network (RBFNN). By incorporating Markov chain into Bayesian estimation scheme, a RBFNN is used as a probabilistic neural network for classification. Based upon data compression technique and on-line classification algorithm, an adaptive estimator to measurement fusion is developed that can handle the switching plant in the multi-sensor environment. The Monte Carlo simulation is employed to demonstrate the effectiveness of the proposed method.
22
Tsai, Jea-Rong, i 蔡至榮. "Robust construction of radial basis function neural network". Thesis, 1995. http://ndltd.ncl.edu.tw/handle/52461067853672588056.
Pełny tekst źródłaStreszczenie:
碩士國立成功大學
電機工程研究所
83
There are many applications for function approximation. Neural network is proposed as a new scheme for the sort of problems. Among them, Radial basis function network is considered as a good candidate because of its faster learing capacity compared with miltilayer proceptron. A conventional RBF network takes Gaussian function as its basis function and the least mean square criterion as the objective function. However, the above approach suffers from two major problems. First, it is difficult for Gaussian function to approximate contant values. If a function contains nearly unchangeable value in some inverals, the RBF network will be found inefficient in approximating the contant value. Second, when the training patterns incur gross error, the network will inaccurately interpolate these training patterns with gross errors. In the paper, we propose to design the RBF network based on sequences of sigmoidal functions and a robust objective function. The fromer is taken as the basis function of the network and the latter resists influence of gross errors. Compared with traditional RBF networks, Our network is demonstrated to posses the following characteristers:(1) it has better capacity of approximation for underlying functions;(2)it has faster learning speed and better size of network.
23
Shih, Siou-Hao, i 石修豪. "Application of Radial Basis Function NeuralApplication of Radial Basis Function Neural Network for Image Recovering". Thesis, 2010. http://ndltd.ncl.edu.tw/handle/70806405025187459328.
Pełny tekst źródłaStreszczenie:
碩士南台科技大學
資訊工程系
98
Image inpainting is a wide range of technology, how to properly fix the value generated is not easy to judge, therefore, this study, the component units of the logic and structure are very similar to the biological neural network, artificial neural networks. In this paper, we propose the application of radial basis function neural network for learning image changes of neighboring pixels, and then be able to guess the repair area should be repaired value. For two-dimensional images corresponding to the direction between pixels and strengthen convergence, network architecture, two additional special parameters as network input, to represent the input and output pixel value between the pixel value. The first parameter represents the input pixel intensity value and the output pixel value changes, a similar image pixels not unusual, and in the vicinity of the pixel value changes are more numerous, increasing intensity of the input parameters can do the exact make and fast network convergence; second parameter represents the input pixel value and the relative position of the output pixel value and position in the network hidden layer will be converted to real values for differential operation. As the repair time, because strength parameter uncertainty, there will be other collisions output through data clustering approach, to isolate the exact image of the network output value and get a complete image recovery. Experimental results, the proposed method, makes use of the image restoration of neural network, the same pixel in the Input can correspond to a variety of output meant that image can recover the situation, all in one class neural networks. Another addition to the image inpainting between similar colors, but also be able to effectively deal with the border color conversions, will not produce blurred boundaries. Compare with the average repair mode image, and get better PSNR.
24
"Radial basis function of neural network in performance attribution". 2003. http://library.cuhk.edu.hk/record=b5891681.
Pełny tekst źródłaStreszczenie:
Wong Hing-Kwok.Thesis (M.Phil.)--Chinese University of Hong Kong, 2003.
Includes bibliographical references (leaves 34-35).
Abstracts in English and Chinese.
Abstract --- p.i
Acknowledgement --- p.iii
Chapter 1 --- Introduction --- p.1
Chapter 2 --- Radial Basis Function (RBF) of Neural Network --- p.5
Chapter 2.1 --- Neural Network --- p.6
Chapter 2.2 --- Radial Basis Function (RBF) Network --- p.8
Chapter 2.3 --- Model Specification --- p.10
Chapter 2.4 --- Estimation --- p.12
Chapter 3 --- RBF in Performance Attribution --- p.17
Chapter 3.1 --- Background of Data Set --- p.18
Chapter 3.2 --- Portfolio Construction --- p.20
Chapter 3.3 --- Portfolio Rebalance --- p.22
Chapter 3.4 --- Result --- p.23
Chapter 4 --- Comparison --- p.26
Chapter 4.1 --- Standard Linear Model --- p.27
Chapter 4.2 --- Fixed Additive Model --- p.28
Chapter 4.3 --- Refined Additive Model --- p.29
Chapter 4.4 --- Result --- p.30
Chapter 5 --- Conclusion --- p.32
Bibliography --- p.34
25
Liou, Shiue-Ru, i 劉學汝. "Radial Basis Function Neural Network for Losses of Rice". Thesis, 2017. http://ndltd.ncl.edu.tw/handle/9485ps.
Pełny tekst źródłaStreszczenie:
碩士國立交通大學
統計學研究所
105
Taiwan is located in the path of typhoon and there is huge agricultural losses caused by typhoons every year. Even though there are agricultural technological progress and variety improvement, we can’t completely avoid the damage. So, we want to discuss how typhoon factors affect agricultural loss. Taiwan has developed the rice industry since Japanese occupation period, and it becomes one of the most important crops in Taiwan. In this paper, we focus on the research of the losses of rice. We apply radial basis function neural network to build the model, combined with three different ways including K-means, self-organizing map network and orthogonal least squares to find the centers of neurons in the hidden layer. And then, we compare the effects of three different models.
26
YEH, TZU-CHUAN, i 葉紫泉. "Radial basis function neural-network controller for robotic manipulators". Thesis, 2019. http://ndltd.ncl.edu.tw/handle/c2vpud.
Pełny tekst źródłaStreszczenie:
碩士華夏科技大學
智慧型機器人研究所
107
The difficulty of the control of multiple-input multiple-output (MIMO) systems is to eliminate the coupling effects between the degrees (DOFs) of free for MIMO systems. A robotic manipulator is one of MIMO systems, which possesses complicated and nonlinear dynamics characteristics. Therefore, it is difficult to design model-based to control robotic manipulators. This study developed a model-free radial basis function neural-network controller (RBFNC), which has characteristics of the coupling weighting, for the control of robotic manipulators. Simulation results demonstrated that the control performance of the RBFN exceeds that of the traditional proportional-integral-derivative (PID) controller for a two-DOF robotic manipulator.
27
CHENG, CHE-MIN, i 鄭哲民. "On The Basis Of Radial Basis Function Neural Network For Image Compress". Thesis, 2003. http://ndltd.ncl.edu.tw/handle/81207020447931238716.
Pełny tekst źródłaStreszczenie:
碩士中華大學
科技管理研究所
91
Recently, image compression is a hot topic in related image processing studies. Along with the popularity of Internet and mobile technology, images have been the most used media among a variety of multimedia services. Image compression then plays a significant factor. Due the inherent feature of huge data amounts, images need to be compressed before delivering or storing. A compressed image cannot only save disk space but can also reduce transmission time. In order to improve the encoding efficiency of conventional image compression, we have proposed an intelligent image compression method. With the proposed system, location and gray-level features of the pixels will be exploited and applied to Radial Basis Function (RBF) Neural Network algorithm, which is used in the compression process. It is expected that the compression ratio and quality of the reconstructed image will be improved. It has been proved that the proposed Radial Basis Function Neural Network algorithm has very good results in compression ratio and visual effects, for the multi dimensional huge data amounts of still image. This algorithm overcomes the complexity of small block encoding used in conventional image compression.
28
Wang, Fu-Lu, i 王富祿. "Real-Time Power Dispatch Using Radial Basis Function Neural Network". Thesis, 2003. http://ndltd.ncl.edu.tw/handle/7npg92.
Pełny tekst źródłaStreszczenie:
碩士崑山科技大學
電機工程研究所
91
In general, the strategy of operating dispatch in power system is mainly concerned with the economic dispatch. However, as a result of public awareness of the environmental protection, the strategy of operating dispatch considering economic and emissions deserves gradually attention. After the private power generators entering the electricity market, the amounts of thermal plant as well as the degree of emissions are increased that leads to the difficulty in reducing the emissions. Therefore, it is an important topic on how to reduce the emissions while generating power outputs. It is an effective method to reduce the emissions by way of power dispatch. In general, the emission can be expressed as a non-linear function of power generation. This thesis thus integrates the emission model into the traditional power dispatch approach. Through the power dispatch of various generating units, the target of reducing emissions can be reached. Based on diverse load levels, the single objective optimization approach is used to optimize each objective separately to obtain respective minimum attainable cost and emission levels and corresponding maximum values of the other objective. To have the power dispatch more adequate to the electricity market, the weighted-sum method is relied on to collect the training sets of power dispatch considering fuel cost and emissions for the off-line circumstance. The proposed radial basis function neural network (RBFNN) is then adopted to search for the optimal parameters of network. Once the networks are trained properly, it can produce the required outputs as soon as the inputs are given. The effectiveness of the proposed approach has been demonstrated by the IEEE 30-bus 6-generator system and the simplified Taiwan Power Company (TPC) 345kV system. Testing results reveal that the proposed RBFNN outperforms the artificial neural networks (ANN) method, in both learning speed and estimating the outputs of the generating units according to the input load demands. Although this thesis focuses on one emitted pollutant, the proposed approach can be extended to multiple emitted pollutants by appropriately formulating the emission function.
29
Wang, Yuan-Peng, i 王元鵬. "Optimizing the Radial Basis Function Neural Network by Heuristic Algorithms". Thesis, 2006. http://ndltd.ncl.edu.tw/handle/02148362820392789232.
Pełny tekst źródła
30
Shih, Cheng-Yuan, i 施正遠. "An Improved Radial Basis Function Neural Network and Its Applications". Thesis, 2011. http://ndltd.ncl.edu.tw/handle/40102742216357916407.
Pełny tekst źródłaStreszczenie:
博士元智大學
通訊工程學系
99
The radial basis function (RBF) neural network is regarded as a good method in many kinds of applications, including function approximation, classification, and prediction. However, there still exist some unsolved problems, including the inability of flat function approximation, the weakness for noise, and the tradeoff between the network performance and the network size. In this thesis, RBF neural networks are improved by sigmoid function, M-estimator, and the growing and pruning algorithm (GAP). The proposed improved RBF networks adopt the sigmoid function as their kernel due to its increased flexibility over the Gaussian kernel. Furthermore, this thesis presents an M-estimator based RBF learning algorithm. The Welsch M-estimator and median scale estimator are employed to get rid of the influence from the noise. Finally, the GAP adjusts the network size dynamically according to the neuron’s significance. To evaluate the network performance, the improved RBF neural networks were applied to three applications, noisy time series prediction, liver mass classification, and vision-based handwriting recognition system. The experimental results show the proposed GAP algorithm is able to dynamically adjust the number of neurons to approach an appropriate size of the network. Moreover, for the noisy time series prediction, the M-estimator based RBF learning algorithm eliminates the influence of noise. For other applications, the experimental results show that the proposed sigmoid kernel is efficient for classification problems.
31
Teng, Yu-Feng, i 鄧淯峰. "Radial Basis Function Based Neural Network for Power System Harmonics Detection". Thesis, 2008. http://ndltd.ncl.edu.tw/handle/84138162303661949127.
Pełny tekst źródłaStreszczenie:
碩士國立中正大學
電機工程所
96
With the widespread use of nonlinear loads in the power system, harmonic distortion causes a serious deterioration of power quality. Excessive harmonics may introduce over-voltage or over-current problems that will reduce the life of power system equipment. The equipment performance also will become inaccurate due to harmonic disturbances. Therefore, mitigating harmonics has become a great concern for both utilities and customers. The fast Fourier transform (FFT) has been widely used for the signal processing because of its computational efficiency. In addition, most power meters adopt FFT-based algorithm to analyze the harmonics and to show the frequency spectra. However, the FFT-based algorithm is less accurate if the system frequency varies and the frequency resolution decreases, and the analytic results will be inaccurate caused by the leakage and picket-fence effects. Although increasing the sampling frequency can mitigate the undesired effects, this will impede the computational efficiency. Therefore, how to achieve both the high resolution and efficiency is worth investigating. In recent years, the Artificial Neural Network (ANN) based methods, adaptive linear element (ADALINE) and back propagation neural network (BPN), have been widely used for the signal processing. The time-domain methods not only reduce the calculation time, but also avoid the restriction of the frequency domain methods. For this reason, this thesis proposes the RBFNN (radial basis function neural network) based algorithm for harmonics detection. Finally, the thesis applies LabVIEW and the dedicated hardware setup to validate the performance of proposed methods by testing the synthesized and actual signals.
32
Yu-KuanLin i 林祐寬. "Variable-Size Block Texture Compression Using Radial Basis Function Neural Network". Thesis, 2017. http://ndltd.ncl.edu.tw/handle/7tjtwt.
Pełny tekst źródła
33
Lin, Chin-Yeu, i 林俊宇. "A Fuzzy-Reasoning Radial Basis Function Neural Network with Reinforcement Learning Method". Thesis, 1999. http://ndltd.ncl.edu.tw/handle/79704454118479961197.
Pełny tekst źródłaStreszczenie:
碩士國立臺灣科技大學
電機工程系
87
A rule-based fuzzy system with learning capability has excellent features to solve many difficult problems in real-world applications. A self-constructing rule-based fuzzy system based on reinforcement learning with Temporal Difference TD(l) method, where l is non-zero values, is created in this thesis. The reinforcement learning with TD(l) method is one of the powerful learning methods, specially for ill-defined or some situations to which supervised learning method is not applicable. In this thesis, the rule-based fuzzy system is represented by radial basis function neural network (RBFN) for learning and tuning facilities. The network architecture, which is called Fuzzy-Reasoning Radial Basis Function Neural Network (FRBFN), is composed of two sub-networks: Action Critic Network (ACN) and Action Selection Network (ASN). There are only three neural layers in each sub-network. The function of ASN is equivalent to that of fuzzy reasoning to generate the output of fuzzy system. Due to the equivalence between RBFN and fuzzy system, the need of fuzzification and defuzzification can be eliminated. The function of ACN is to generate credits at each time step for reinforcement learning procedure. The proposed FRBFN is proved having the ability to learning from experience. The system can not only generate but also tune the rules on-line as environment or controlled plant is changed.
34
CHENG-HSUN, LU, i 呂承勳. "Self-Organizing Fuzzy Radial Basis-Function Neural-Network Controller for Robotic Systems". Thesis, 2017. http://ndltd.ncl.edu.tw/handle/35094652486239930551.
Pełny tekst źródłaStreszczenie:
碩士華夏科技大學
智慧型機器人研究所
105
This study developed intelligent controllers for the control of robotic systems. The application of model based classical control theories needs accurate system’s mathematical model for the design of controllers. However, the mathematical mod- els of robotic systems with nonlinearities and dynamic uncertain characteristics are difficult to establish or estimate accurately. This study proposed model-free in- telligent control strategies to control robotic systems. The theoretical analysis and simulation for the control of a robotic system was performed to verify the availability of the proposed intelligent control strategies. This study employed three different intelligent control strategies, (1) self-organizing fuzzy controller (SOFC) (2) self-organizing fuzzy radial basis-function neural-network with steepest descent method(SFRBNC S ) (3) self-organizing fuzzy radial basis-function neural-network with Levenberg-Marquardt algorithm (SFRBNC L ) for the control of robotic systems. Simulation results showed that the proposed intelligent controllers achieved satis- factory control performance for the trajectory tracking control of a robotic system.
35
Wang, Ting-hua, i 王廷華. "PREDICTION BY MOVABLE-RATE GRADIENT RADIAL BASIS FUNCTION NEURAL NETWORK WITH FUZZY CURVES". Thesis, 1997. http://ndltd.ncl.edu.tw/handle/25051127833995293341.
Pełny tekst źródłaStreszczenie:
碩士大同工學院
電機工程學系
85
This thesis will provide a faster and simpler radial basis function neuralnetwork from an efficient classifier, a variable learning and a gradient algor-ithm. Its advantage is that we know nothing about the system unless its input-output pairs and use less time learning well. The fuzzy-side view will help usfind the character more simply and quickly. The proposed method will further improve the power and/or the speed of the learning of the Neural Network whichis not bounded with smooth system. In examples, we will know that it can be used in the predict problem very well with both stationary and nonstationary time series. In the similar way, we can still use this proposed method in otherinput-output pairs' problem.
36
Huang, Cheng-Tung, i 黃正同. "Prediction of Storm-Built Beach Profile Using Radial Basis Function Artificial Neural Network". Thesis, 2006. http://ndltd.ncl.edu.tw/handle/70202129058487461760.
Pełny tekst źródłaStreszczenie:
碩士中興大學
土木工程學系所
94
This study aims to investigate the applicability of the Radial-Basis Function neural network (RBFN) for predicting the major pertinent parameters of a storm-built beach profile. The prediction model is performed from learning 18 model bar profiles selected from previous large wave tank test. A Radial-Basis Function network procedure was used to adjust the weights of the connections in the neural network and to minimize the error between the desired outputs and the observed values. Base on the proposed RBFN model that it has curve fitting capability, the major geometric parameters for a storm-built bar are predicted well as the nondimensional wave condition is given. The results show that the neural network model works better then the previous empirical predictions of Silvester and Hsu (1993) and back-propagation neural network..
37
Yang, Zhi-Ting, i 楊之廷. "Application of Hybrid Self-organizing Fuzzy and Radial Basis-function Neural-network Controller". Thesis, 2009. http://ndltd.ncl.edu.tw/handle/5xz46b.
Pełny tekst źródłaStreszczenie:
碩士國立臺北科技大學
機電整合研究所
97
A self-organizing fuzzy controller (SOFC) has been proposed for control engineering applications. During the control process, it continually updates the learning strategy in the form of fuzzy rules, beginning with empty fuzzy rules, to eliminate the difficulty of finding appropriate membership functions and fuzzy rules when using a fuzzy logic controller. However, it is intricate to select appropriate parameters for both the learning rate and weighting distribution in the SOFC for control engineering applications. This study developed a hybrid self-organizing fuzzy and radial basis-function neural network controller (HSFRBNC), which applied a radial basis function neural-network (RBFN) to regulate in real-time these parameters of the SOFC to gain optimal values and overcome the problem when the SOFC was employed. To confirm the applicability of the proposed HSFRBNC, it was applied in manipulating a turning system and an active suspension system, and then their control performance was evaluated. Simulation results demonstrated that the HSFRBNC has better control performance than the SOFC in improving the performance of the constant cutting force operation of the turning system, service life of the suspension system, and ride comfort of a car.
38
Hsu, Wen-Yen, i 徐文彥. "RADIAL BASIS FUNCTION NETWORK BASED AUTOMATIC GENERATION FUZZY NEURAL NETWORK CONTROLLER FOR PERMANENT MAGNET LINEAR SYNCHRONOUSMOTOR". Thesis, 2007. http://ndltd.ncl.edu.tw/handle/8u99fa.
Pełny tekst źródłaStreszczenie:
碩士大同大學
電機工程學系(所)
95
In this thesis, a radial basis function network (RBFN) based automatic generation fuzzy neural network (AGFNN) is proposed to control the rotor position of the permanent magnet linear synchronous motor (PMLSM) to track the period reference trajectories. The proposed RBFN based AGFNN not only has the advantages of the back-propagation algorithm, in which the parameter of the connected weights are adjusted but also has the advantages of the switching law, momentum term and RBFN, in which the tracking error and steady state responses will be betterment. The structure learning is based on the Mahalanobis distance and the parameter learning is based on the back-propagation algorithm. The simulation results of the proposed RBFN-based AGFNN with the periodic reference trajectories show that the tracking error and steady state responses have better performance, own the robustness performance under the parameter variation and external load disturbance.
39
Chiu, Chih-sheng, i 邱志聖. "DESIGN OF RADIAL BASIS FUNCTION NEURAL NETWORK WITH SLIDING MODE CONTROL FOR ROBOTIC MANIPULATORS". Thesis, 2007. http://ndltd.ncl.edu.tw/handle/j9dmbg.
Pełny tekst źródłaStreszczenie:
碩士大同大學
電機工程學系(所)
95
In this thesis, radial basis function network (RBFN) with sliding-mode controller (SMC) is designed to the joint position control of two-link robot manipulators for periodic motion and predefined trajectory tracking control. Radial basis function uses curve fitting mode to obtain the nonlinear mapping. The unavoidable learning procedure degrades its transient performance in the existence of disturbance. Sliding-mode control is effective in overcoming uncertainties and has a fast transient response, while the control effort is discontinuous and creates chattering. For this defect, a saturation function is utilized to improve it. The back-propagation (BP) algorithm and Lyapunov stability theorem are used to decide a suitable update law and sliding-mode switch gain, respectively. Thus, the satisfactory performance will be obtained, which better than the controller with single RBFN controller or SMC. The simulated results of a two-link robotic manipulator for the joint frictions, changing link masses and adding external disturbances are provided to show that the effectiveness of the proposed control scheme.
40
Chen, Zhen-Yao, i 陳振耀. "Application of Evolutionary Computation-Based Radial Basis Function Neural Network to IPC Sales Forecasting". Thesis, 2010. http://ndltd.ncl.edu.tw/handle/d83vya.
Pełny tekst źródłaStreszczenie:
博士國立臺北科技大學
工商管理研究所
98
Forecasting is one of the crucial factors in practical application since it ensures the effective allocation of capacity and proper amount of inventory. Since auto-regressive integrated moving average (ARIMA) models which are more suitable for linear data have their constraints in predicting complex data for the real-world problems, some approaches have been developed to conquer the challenge of nonlinear forecasting. Therefore, for the purpose of forecasting nonlinear data, this study intends to develop three integrated evolutionary computation (EC)-based algorithms for training radial basis function neural network (RBFnn). The EC-based algorithms include genetic algorithm (GA), particle swarm optimization (PSO), and artificial immune system (AIS). In order to verify these three developed integrated EC-based algorithms, three benchmark continuous test functions were employed. The experimental results of three integrated EC-based algorithms are really very promising. In addition, industrial personal computer (IPC) sales data provided by an international well-known IPC manufacturer in Taiwan is also applied to further assess these developed algorithms. The model evaluation results indicated that the developed algorithms really can forecast more accurately. Furthermore, if foreign exchange (FX) factor is considered, the forecasting results can be improved.
41
Tsao, Hsin-Cheng, i 曹新晟. "Self-Organizing Fuzzy Sliding-Mode Radial Basis-Function Neural-Network Controller for Turning Systems". Thesis, 2013. http://ndltd.ncl.edu.tw/handle/2y2yky.
Pełny tekst źródłaStreszczenie:
碩士國立臺北科技大學
機電整合研究所
101
Turning systems generally have nonlinear and complex characteristics, so the design of model-based controllers to manipulate such systems to improve their control performances is impractical. To address this problem, this study developed a self-organizing fuzzy sliding-mode radial basis-function neural-network controller (SFSRBNC) for the control of turning systems. The SFSRBNC not only eliminates the problem caused by the inappropriate selection of parameters in both a self-organizing fuzzy controller (SOFC) and a self-organizing fuzzy sliding-mode controller (SFSC) and by the determination of the inappropriate membership functions and fuzzy rules for the design of a fuzzy logic controller, but also solves the stability problem of a self-organizing fuzzy radial basis-function neural-network controller (SFRBNC) application. Simulation results indicated that the SFSRBNC achieved better control performance than the SFSC, SFRBNC, and SOFC for the control of the constant cutting force, with or without fixed material removal rate, in turning.
42
Chen, Bo-Yan, i 陳伯彥. "Self-Organizing Fuzzy Sliding-Mode Radial Basis-Function Neural-Network Controller for Nonlinear Systems". Thesis, 2013. http://ndltd.ncl.edu.tw/handle/5brywj.
Pełny tekst źródłaStreszczenie:
碩士國立臺北科技大學
機電整合研究所
101
This study developed a self-organizing fuzzy sliding-mode radial basis-function neural-network controller (SFSRBNC) for nonlinear systems. The sliding surface and its differential, rather than the error and error change of the system,are used as input variables of a fuzzy logic controller (FLC) in the SFSRBNC, which guarantees the stability of the system operation. The SFSRBNC not only eliminates the stability problem of a self-organizing fuzzy radial basis-function neural-network controller (SFRBC) application,but also overcomes the problem caused by the inappropriate selection of parameters in both a self-organizing fuzzy controller (SOFC) and a self-organizing fuzzy sliding-mode controller (SFSC), and by the determination of unsuitable membership functions and fuzzy rules in an FLC.To demonstrate the feasibility of the proposed method, the SFSRBNC was applied to controlling nonlinear systems which are a microactuator system and a robotic system to determine their control performances. Simulation results verified that the SFSRBNC gained better control performance than the SFRBC, SFSC, and SOFC for the control of the nonlinear systems.
43
Li, Mu, i 李穆. "Using Radial Basis Function Neural Network to establish displacement field of simply supported beam". Thesis, 2009. http://ndltd.ncl.edu.tw/handle/41320460504797397728.
Pełny tekst źródłaStreszczenie:
碩士國立臺灣科技大學
營建工程系
97
The main objective of this article is to test and try to using Radial Basis Function Neural Network to conduct the simulation of displacement field of simply supported beam. Because of the inconvenience of Element Free Galerkin Method in multiple variable inputing, this study use Radial Basis Function Neural Network to learn the simulation of displacement field of simply supported beam.
44
Ho, Cheng-Hsuan, i 何承軒. "Using Radial Basis Function Neural Network to Build the Rating Curve of Irrigation Channel". Thesis, 2018. http://ndltd.ncl.edu.tw/handle/a34448.
Pełny tekst źródłaStreszczenie:
碩士國立臺北科技大學
土木工程系土木與防災碩士班
106
Agricultural farming in Taiwan has always been dominated by paddy fields, which is the main target of irrigation for the irrigation channels. The irrigation channels are spread throughout the planting of rice in Taiwan. If we can understand the rating curve of each channel, it is possible to adjust the flow of each channel to correspond to the amount of water needed for agricultural activities through the water conservancy facilities. Thereby reducing the waste of water resources. Therefore, it is an important goal to investigate the details of each channel. How to effectively and quickly obtain the required measurement data and establish a reliable rating curve in a large number of irrigation channels throughout Taiwan is the goal of this study. However, if the rating curve is to be perfected in the discharge measurement process, it is necessary to measure the flow field distribution under each water level as much as possible to calculate the velocity. Therefore,to construct a complete rating curve, multiple measurements are required to achieve Therefore, this study uses the Radial Basis Function Neural Network (RBFNN) model to train and characterize the parameters of the neural network only with the part of measured data, and the remaining data is used for verification. Very good results were obtained in the verification. The network constructed by this parameter is used to simulate the velocity distribution under each water level condition, and the velocity calculation is performed, and the velocity data construction rating curve calculated by the simulation result is performed, and then comparing with the rating curve established by the original measurement data.
45
Ji, Yun, i 紀昀. "Application of Radial Basis Function Neural Network combined with Genetic Algorithms for river stage prediction". Thesis, 2013. http://ndltd.ncl.edu.tw/handle/28747901720082785639.
Pełny tekst źródłaStreszczenie:
碩士中原大學
土木工程研究所
101
Recently, there are worried about the collapsed of bridges in Taiwan during Typhoons period. To ensure the safety of the people and vehicles on the bridges, it’s getting important to develop a safety warning system of bridges. Water level prediction is one of the most important parts in this system. Therefore, This study for establishing a systematic model of integrated performance for the water level forecasting models. In this study, choosing Xin-hai Bridge as study case. Collecting typhoon data in Taiwan during 1996 to 2010. Using Radial Basis Function Neural Network to create Xin-hai Bridge water level forecasting mode combined with Genetic Algorithms (GA-RBFNN) to forecast water level of Xin-hai Bridge after one to three hours. In GA-RBFNN mode, choosing water level of San-ying Bridge, Shi-men Reservoir releasing, three rainfall stations data of upstream and tidal at estuary of Tam-sui River as input data, and the output data are the prediction of water level for Xin-hai Bridge. The result of prediction at one hour later, the Correlation Coefficient is up to 0.984. And the results of prediction at three hours later, the Correlation Coefficient were higher than 0.7, the prediction data were nearly successful achievement. The result of study is expected to be used for safety warning system of bridges in the future.
46
Chiao, Kai-chieh, i 喬凱杰. "Compare the Behavior of Radial Basis Function Neural Network and Differential Reproducing kernel Approximation Method". Thesis, 2008. http://ndltd.ncl.edu.tw/handle/37138327103090944403.
Pełny tekst źródłaStreszczenie:
碩士國立臺灣科技大學
營建工程系
96
This study mainly examines the theory of Radial Basis Function (RBF) and Differential Reproducing kernel Approximation Method (DRKM), and compares the differences between them. The entire network calculation of RBF is controlled by the central points. There are two techniques to simulate the procedure: First, select the central point set randomly: to carry out the analysis by controlling the number of central points. Second, select the central points by Orthogonal Least Squares: to carry out the analysis by allocating the tolerance of errors. DKSM controls its accuracy by influencing the selection of radius. This study provides some examples to discuss the accuracy and suitability of this procedure in order to provide references for further studies. The results reveal that the approximate interpolation outcomes getting better if the RBF numbers of random selection of central points increase. When the numbers of central points go beyond specific percentage, its accuracy can surpass the result of DRKM. Although in the RBF we can control the selection of central points by the Orthogonal Least Squares, the efficiency of calculation is greatly affected by the amount of data. Therefore, it is time-consuming for complicated cases.
47
Kuei, Yu-Hsien, i 桂宇賢. "Application of Back Propagation and Radial Basis Function Artificial Neural Network to Velocity Profile Prediction". Thesis, 2014. http://ndltd.ncl.edu.tw/handle/72906033444689359511.
Pełny tekst źródłaStreszczenie:
碩士國立中興大學
土木工程學系所
102
Accuracy of the velocity measurements is related to the accuracy of discharge estimation, the practicality of the project design and planning, and the amount of losses caused by disasters. Because of many uncertainty conditions in Taiwan''s rivers, the velocity measuring technique still requires further improvement. In particular, due to the frequent flood disasters caused by the climate change, and the corresponding extreme rainfalls, the river velocity measurement becomes a challenge task. To avoid the exposure to the dangerous environment for the measuring persons, a large number of measured data is used for simulating the average velocity profile and finding the best model for the design and planning. This study aims to compare the accuracy of the radial basis function artificial neural network (RBFN) and back propagation artificial neural network (BPN) for simulating the average velocity profiles. Both Yang (1998) and Lin’s (1999) experimental data were adopted for the artificial neural network training, validation and testing. The correlation coefficient (C.C) and the root mean square error (RMSE) were used to determine the effectiveness of the simulation and estimation.
48
Chuang, Chih-Hsun, i 莊至勛. "Radial Basis Function Neural Network Assisted Ultra-Tighty Coupled GPS/INS Integration for Seamless Navigation". Thesis, 2012. http://ndltd.ncl.edu.tw/handle/89862858060966277779.
Pełny tekst źródłaStreszczenie:
碩士國立臺灣海洋大學
通訊與導航工程學系
100
In GPS/INS integration, the ultra-tightly coupled approach involves the integration of I (in-phase) and Q (quadrature) components from the correlator of a GPS receiver with the INS data. The principal advantages of the Ultra Tightly Couple (UTC) structure is that a Doppler frequency derived from the INS is integrated with the tracking loops to improve the receiver tracking capability. The Doppler frequency shift is calculated and fed to the GPS tracking loops for elimination of the effect of stochastic errors caused by the Doppler frequency. The navigation information from INS can be converted into the Doppler information, which can be integrated with the GPS tracking loops to mitigate the Doppler on the GPS signal, resulting in the threshold improvement, thereby improving the overall system performance. An algorithm for bridging GPS outages using the radial basis function neural network (RBFNN) for providing better prediction of measurement residual between GPS and prediction in order to maintain regular operation of the navigation system. The results demonstrate that the UTC with the assist of neural network can effectively improve the system robustness during GPS outages.
49
Tzeng, Ruei-Fu, i 曾瑞賦. "Defect Inspection of Optical Masks by Using Radial Basis Function Neural Network with Image Operations". Thesis, 2014. http://ndltd.ncl.edu.tw/handle/79643115123756708477.
Pełny tekst źródłaStreszczenie:
碩士明新科技大學
精密機電工程研究所
102
This research proposes self-learning methods to inspect defects of optical masks by using the radial basis function neural network with image operations. The research includes the automatic optical mask image alignment, neural network inspection methods, image processing, and system program development. In the automatic optical mask image alignment, the use high precision image measurement system (Nikon VMR-3020), and using centroid counterpoint to the four corners of the intersecting point of the optical mask image on the centroid, forming a central position, the optical mask image can be maintained to achieve consistency in the center of the image window capture, image processing to facilitate follow-up. In the aspect of neural network, the radial basis function neural network is an excellent feed-forward neural network. The research uses the neural network, because it can train in the classification with a high speed, better learning and approximate capacity. In the aspect of defect inspection, the image complexity of the background and noises of wafer surfaces and optical masks image can be reduced by image processing. Through calculating eight feature parameters for optical mask images, the feature parameters were also considered as the input parameters of the RBF neural network. Finally, the inspection systems of wafer surface and optical mask were successfully established and defects can be classified. Finally, the inspection systems of optical mask were successfully established and defects can be classified. Experimental results show that the developed method can successfully isolate and inspect the defects of optical masks.
50
TSUEI, TI-WEI, i 崔以威. "Adaptive Self-Organizing Fuzzy Sliding-Mode Radial Basis-Function Neural-Network Control for Robotic Manipulators". Thesis, 2019. http://ndltd.ncl.edu.tw/handle/egura5.
Pełny tekst źródłaStreszczenie:
碩士華夏科技大學
智慧型機器人研究所
107
A robotic manipulator has nonlinear with complex dynamic characteristic. It is one of multiple-input multiple-output systems, which has coupling dynamic effects between the degrees of free (DOFs). Therefore, it is difficult to design a model-based controller to manipulate the robot. This study developed a self-organizing fuzzy controller (SOFC), without mathematical model of the system, for the control of the robot. However, the design of the SOFC focuses mainly on controlling single-input single-output systems. It is arduous to eliminate the coupling dynamic effects between the DOFs for the control of the robot. In addition, the stability of the SOFC is difficult to prove using mathematical operation. This study designed an adaptive self-organizing fuzzy sling-mode radial basis-function neural-network controller (ASFSRBNC) to manipulate the robot, in order to overcome the .the above-mentioned problem. In this study, the stability of the proposed ASFSRBNC was proved by the Lyapunov theorem. Simulation results demonstrated that the control performance of the proposed ASFSRBNC is better than that of the SOFC for the control of the robotic manipulator.