Dissertations / Theses on the topic 'PSO'
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 'PSO.'
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.
Krézek, Vladimír. "Akcelerace částicových rojů PSO pomocí GPU." Master's thesis, Vysoké učení technické v Brně. Fakulta informačních technologií, 2012. http://www.nusl.cz/ntk/nusl-235471.
Full textZáň, Drahoslav. "Akcelerace částicových rojů PSO pomocí GPU." Master's thesis, Vysoké učení technické v Brně. Fakulta informačních technologií, 2013. http://www.nusl.cz/ntk/nusl-236374.
Full textSergio, Anderson Tenório. "Otimização de Reservoir Computing com PSO." Universidade Federal de Pernambuco, 2013. https://repositorio.ufpe.br/handle/123456789/11498.
Full textMade available in DSpace on 2015-03-09T14:34:23Z (GMT). No. of bitstreams: 2 Dissertaçao Anderson Sergio.pdf: 1358589 bytes, checksum: fdd2a84a1ce8a69596fa45676bc522e4 (MD5) license_rdf: 1232 bytes, checksum: 66e71c371cc565284e70f40736c94386 (MD5) Previous issue date: 2013-03-07
Reservoir Computing (RC) é um paradigma de Redes Neurais Artificiais com aplicações importantes no mundo real. RC utiliza arquitetura similar às Redes Neurais Recorrentes para processamento temporal, com a vantagem de não necessitar treinar os pesos da camada intermediária. De uma forma geral, o conceito de RC é baseado na construção de uma rede recorrente de maneira randômica (reservoir), sem alteração dos pesos. Após essa fase, uma função de regressão linear é utilizada para treinar a saída do sistema. A transformação dinâmica não-linear oferecida pelo reservoir é suficiente para que a camada de saída consiga extrair os sinais de saída utilizando um mapeamento linear simples, fazendo com que o treinamento seja consideravelmente mais rápido. Entretanto, assim como as redes neurais convencionais, Reservoir Computing possui alguns problemas. Sua utilização pode ser computacionalmente onerosa, diversos parâmetros influenciam sua eficiência e é improvável que a geração aleatória dos pesos e o treinamento da camada de saída com uma função de regressão linear simples seja a solução ideal para generalizar os dados. O PSO é um algoritmo de otimização que possui algumas vantagens sobre outras técnicas de busca global. Ele possui implementação simples e, em alguns casos, convergência mais rápida e custo computacional menor. Esta dissertação teve o objetivo de investigar a utilização do PSO (e duas de suas extensões – EPUS-PSO e APSO) na tarefa de otimizar os parâmetros globais, arquitetura e pesos do reservoir de um RC, aplicada ao problema de previsão de séries temporais. Os resultados alcançados mostraram que a otimização de Reservoir Computing com PSO, bem como com as suas extensões selecionadas, apresentaram desempenho satisfatório para todas as bases de dados estudadas – séries temporais de benchmark e bases de dados com aplicação em energia eólica. A otimização superou o desempenho de diversos trabalhos na literatura, apresentando-se como uma solução importante para o problema de previsão de séries temporais.
Veselý, Filip. "Aplikace optimalizační metody PSO v podnikatelství." Master's thesis, Vysoké učení technické v Brně. Fakulta podnikatelská, 2010. http://www.nusl.cz/ntk/nusl-222445.
Full textScarpa, Giulia <1991>. "PSO for CVaR-based Portfolio Selection." Master's Degree Thesis, Università Ca' Foscari Venezia, 2016. http://hdl.handle.net/10579/8970.
Full textDuhain, Julien Georges Omer Louis. "Particle swarm optimisation in dynamically changing environments - an empirical study." Diss., University of Pretoria, 2012. http://hdl.handle.net/2263/25875.
Full textDissertation (MSc)--University of Pretoria, 2012.
Computer Science
unrestricted
Lång, Magnus. "Sound and Complete Reachability Analysis under PSO." Thesis, Uppsala universitet, Institutionen för informationsteknologi, 2013. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-213286.
Full textNěmeček, Patrik. "Optimalizační úlohy na bázi částicových hejn (PSO)." Master's thesis, Vysoké učení technické v Brně. Fakulta informačních technologií, 2014. http://www.nusl.cz/ntk/nusl-236036.
Full textAlmasiri, osamah A. "SKIN CANCER DETECTION USING SVM-BASED CLASSIFICATION AND PSO FOR SEGMENTATION." VCU Scholars Compass, 2018. https://scholarscompass.vcu.edu/etd/5489.
Full textPalangpour, Parviz Michael. "FFGA implementation of PSO algorithm and neural networks." Diss., Rolla, Mo. : Missouri University of Science and Technology, 2010. http://scholarsmine.mst.edu/thesis/pdf/Palangpour_09007dcc8078a58e.pdf.
Full textVita. The entire thesis text is included in file. Title from title screen of thesis/dissertation PDF file (viewed April 8, 2010) Includes bibliographical references (p. 76-78).
Jiang, Siyu. "A Comparison of PSO, GA and PSO-GA Hybrid Algorithms for Model-based Fuel Economy Optimization of a Hybrid-Electric Vehicle." The Ohio State University, 2019. http://rave.ohiolink.edu/etdc/view?acc_num=osu156612591067731.
Full textMelo, Leonardo Alves Moreira de. "Comparação de algoritmos de enxame de partículas para otimização de problemas em larga escala." Universidade Federal de Goiás, 2018. http://repositorio.bc.ufg.br/tede/handle/tede/9108.
Full textApproved for entry into archive by Luciana Ferreira (lucgeral@gmail.com) on 2018-11-29T11:09:58Z (GMT) No. of bitstreams: 2 Dissertação - Leonardo Alves Moreira de Melo - 2018.pdf: 2693689 bytes, checksum: 850fbad5a82099825d2478ba3415dcac (MD5) license_rdf: 0 bytes, checksum: d41d8cd98f00b204e9800998ecf8427e (MD5)
Made available in DSpace on 2018-11-29T11:09:58Z (GMT). No. of bitstreams: 2 Dissertação - Leonardo Alves Moreira de Melo - 2018.pdf: 2693689 bytes, checksum: 850fbad5a82099825d2478ba3415dcac (MD5) license_rdf: 0 bytes, checksum: d41d8cd98f00b204e9800998ecf8427e (MD5) Previous issue date: 2018-10-26
Fundação de Amparo à Pesquisa do Estado de Goiás - FAPEG
In order to address an issue concerning the increasing number of algorithms based on particle swarm optimization (PSO) applied to solve large-scale optimization problems (up to 2000 variables), this article presents analysis and comparisons among five state- of-the-art PSO algorithms (CCPSO2, LSS- PSO, OBL-PSO, SPSO and VCPSO). Tests were performed to illustrate the e ciency and feasibility of using the algorithms for this type of problem. Six benchmark functions most commonly used in the literature (Ackley 1, Griewank, Rastrigin, Rosenbrock, Schwefel 1.2 and Sphere) were tested. The experiments were performed using a high-dimensional problem (500 variables), varying the number of particles (50, 100 and 200 particles) in each algorithm, thus increasing the computational complexity. The analysis showed that the CCPSO2 and OBL-PSO algorithms found significantly better solutions than the other algorithms for more complex multimodal problems (which most resemble realworld problems). However, considering unimodal functions, the CCPSO2 algorithm stood out before the others. Our results and experimental analysis suggest that CCPSO2 and OBL- PSO seem to be highly competitive optimization algorithms to solve complex and multimodal optimization problems.
O número de algoritmos baseados na otimização por enxame de partículas (PSO) aplicados para resolver problemas de otimização em grande escala (até 2.000 variáveis) aumentou significativamente. Este trabalho apresenta análises e comparações entre cinco algoritmos (CCPSO2, LSSPSO, OBL-CPSO, SPSO e VCPSO). Testes foram realizados para ilustrar a eficiência e viabilidade de usar os algoritmos para resolver problemas em larga escala. Seis funções de referência que são comumente utilizadas na literatura (Ackley 1, Griewank, Rastrigin, Rosenbrock, Schwefel 1.2 e Sphere) foram utilizadas para testar a performancedesses algoritmos. Os experimentos foram realizados utilizando um problema de alta dimensionalidade (500 variáveis), variando o número de partículas (50, 100 e 200 partículas) em cada algoritmo, aumentando assim a complexidade computacional. A análise mostrou que os algoritmos CCPSO2 e OBL-CPSO mostraram-se significativamente melhores que os outros algoritmos para problemas multimodais mais complexos (que mais se assemelham a problemas reais). No entanto, considerando as funções unimodais, o algoritmo CCPSO2 destacou-se perante os demais. Nossos resultados e análises experimentais sugerem que o CCPSO2 e o OBL-CPSO são algoritmos de otimização altamente competitivos para resolver problemas de otimização complexos e multimodais em larga escala.
Urade, Hemlata S., and Rahila Patel. "Performance Evaluation of Dynamic Particle Swarm Optimization." IJCSN, 2012. http://hdl.handle.net/10150/283597.
Full textIn this paper the concept of dynamic particle swarm optimization is introduced. The dynamic PSO is different from the existing PSO’s and some local version of PSO in terms of swarm size and topology. Experiment conducted for benchmark functions of single objective optimization problem, which shows the better performance rather the basic PSO. The paper also contains the comparative analysis for Simple PSO and Dynamic PSO which shows the better result for dynamic PSO rather than simple PSO.
LIMA, Natália Flora De. "Frankenstein PSO na definição das arquiteturas e ajustes dos pesos e uso de PSO heterogêneo no treinamento de redes neurais feed-forward." Universidade Federal de Pernambuco, 2011. https://repositorio.ufpe.br/handle/123456789/17738.
Full textMade available in DSpace on 2016-08-24T17:35:05Z (GMT). No. of bitstreams: 2 license_rdf: 1232 bytes, checksum: 66e71c371cc565284e70f40736c94386 (MD5) Dissertacao-Natalia_Flora_de_Lima.pdf: 2000980 bytes, checksum: 107f0691d21b9d94e253d08f06a4fbdd (MD5) Previous issue date: 2011-08-29
Facepe
Este trabalho apresenta dois novos algoritmos, PSO-FPSO e FPSO-FPSO, para a otimização global de redes neurais MLP (do inglês Multi Layer Perceptron) do tipo feed-forward. O propósito destes algoritmos é otimizar de forma simultânea as arquiteturas e pesos sinápticos, objetivando melhorar a capacidade de generalização da rede neural artificial (RNA). O processo de otimização automática das arquiteturas e pesos de uma rede neural vem recebendo grande atenção na área de aprendizado supervisionado, principalmente em problemas de classificação de padrões. Além dos Algoritmos Genéticos, Busca Tabu, Evolução Diferencial, Recozimento simulado que comumente são empregados no treinamento de redes neurais podemos citar abordagens populacionais como a otimização por colônia de formigas, otimização por colônia de abelhas e otimização por enxame de partículas que vêm sendo largamente utilizadas nesta tarefa. A metodologia utilizada neste trabalho trata da aplicação de dois algoritmos do tipo PSO, sendo empregados na otimização das arquiteturas e na calibração dos pesos das conexões. Nesta abordagem os algoritmos são executados de forma alternada e por um número definido de vezes. Ainda no processo de ajuste dos pesos de uma rede neural MLP foram realizados experimentos com enxame de partículas heterogêneos, que nada mais é que a junção de dois ou mais PSOs de tipos diferentes. Para validar os experimentos com os enxames homogêneos foram utilizadas sete bases de dados para problemas de classificação de padrões, são elas: câncer, diabetes, coração, vidros, cavalos, soja e tireóide. Para os experimentos com enxames heterogêneos foram utilizadas três bases, a saber: câncer, diabetes e coração. O desempenho dos algoritmos foi medido pela média do erro percentual de classificação. Algoritmos da literatura são também considerados. Os resultados mostraram que os algoritmos investigados neste trabalho obtiveram melhor acurácia de classificação quando comparados com os algoritmos da literatura mencionados neste trabalho.
This research presents two new algorithms, PSO-FPSO e FPSO-FPSO, that can be used in feed-forward MLP (Multi Layer Perceptron) neural networks for global optimization. The purpose of these algorithms is to optimize architectures and synaptic weight, at same time, to improve the capacity of generalization from Artificial Neural Network (ANN). The automatic optimization process of neural network’s architectures and weights has received much attention in supervised learning, mainly in pattern classification problems. Besides the Genetic Algorithms, Tabu Search, Differential Evolution, Simulated Annealing that are commonly used in the training of neural networks we can mentioned population approaches such Ant Colony Optimization, Bee Colony Optimization and Particle Swarm Optimization that have been widely used this task. The methodology applied in this research reports the use of two PSO algorithms, used in architecture optimization and connection weight adjust. In this approach the algorithms are performed alternately and by predefined number of times. Still in the process of adjusting the weights of a MLP neural network experiments were performed with swarm of heterogeneous particles, which is nothing more than the joining of two or more different PSOs. To validate the experiments with homogeneous clusters were used seven databases for pattern classification problems, they are: cancer, diabetes, heart, glasses, horses, soy and thyroid. For the experiments with heterogeneous clusters were used three bases, namely cancer, diabetes and heart. The performance of the algorithms was measured by the average percentage of misclassification, literature algorithms are also considered. The results showed that the algorithms investigated in this research had better accuracy rating compared with some published algorithms.
Toleikytė, Lina. "PSO sveikatą stiprinančių iniciatyvų įgyvendinimo galimybių Lietuvos ligoninėse tyrimas." Master's thesis, Lithuanian Academic Libraries Network (LABT), 2005. http://vddb.library.lt/obj/LT-eLABa-0001:E.02~2005~D_20050608_132323-99989.
Full textMoret, Cristina <1992>. "GAs and PSO: two metaheuristic methods for portfolio optimization." Master's Degree Thesis, Università Ca' Foscari Venezia, 2018. http://hdl.handle.net/10579/13319.
Full textMARINHO, Pedro Rafael Diniz. "Some new families of continuos distributions." Universidade Federal de Pernambuco, 2016. https://repositorio.ufpe.br/handle/123456789/18862.
Full textMade available in DSpace on 2017-05-23T12:23:58Z (GMT). No. of bitstreams: 2 license_rdf: 811 bytes, checksum: e39d27027a6cc9cb039ad269a5db8e34 (MD5) SOME NEW FAMILIES OF CONTINUOUS DISTRIBUTIONS.pdf: 5612905 bytes, checksum: 3fd32464f68606705a4b23070897a8e2 (MD5) Previous issue date: 2016-06-27
FACEPE
The area of survival analysis is important in Statistics and it is commonly applied in biological sciences, engineering, social sciences, among others. Typically, the time of life or failure can have different interpretations depending on the area of application. For example, the lifetime may mean the life itself of a person, the operating time of equipment until its failure, the time of survival of a patient with a severe disease from the diagnosis, the duration of a social event as a marriage, among other meanings. The time of life or survival time is a positive continuous random variable, which can have constant, monotonic increasing, monotonic decreasing or non-monotonic (for example, in the form of a U) hazard function. In the last decades, several families of probabilistic models have been proposed. These models can be constructed based on some transformation of a parent distribution, commonly already known in the literature. A given linear combination or mixture of G models usually defines a class of probabilistic models having G as a special case. This thesis is composed of independent chapters. The first and last chapters are short chapters that include the introduction and conclusions of the study developed. Two families of distributions, namely the exponentiated logarithmic generated (ELG) class and the geometric Nadarajah-Haghighi (NHG) class are studied. The last one is a composition of the Nadarajah-Haghighi and geometric distributions. Further, we develop a statistical library for the R programming language called the AdequacyModel. This is an improvement of the package that was available on CRAN (Comprehensive R Archive Network) and it is currently in version 2.0.0. The two main functions of the library are the goodness.fit and pso functions. The first function allows to obtain the maximum likelihood estimates (MLEs) of the model parameters and some goodness-of-fit of the fitted probabilistic models. It is possible to choose the method of optimization for maximizing the log-likelihood function. The second function presents the method meta-heuristics global search known as particle swarm optimization (PSO) proposed by Eberhart and Kennedy (1995). Such methodology can be used for obtaining the MLEs necessary for the calculation of some measures of adequacy of the probabilistic models.
A área de análise de sobrevivência é importante na Estatística e é comumente aplicada às ciências biológicas, engenharias, ciências sociais, entre outras. Tipicamente, o tempo de vida ou falha pode ter diferentes interpretações dependendo da área de aplicação. Por exemplo, o tempo de vida pode significar a própria vida de uma pessoa, o tempo de funcionamento de um equipamento até sua falha, o tempo de sobrevivência de um paciente com uma doença grave desde o diagnóstico, a duração de um evento social como um casamento, entre outros significados. O tempo de vida é uma variável aleatória não negativa, que pode ter a função de risco na forma constante, monótona crescente, monótona decrescente ou não monótona (por exemplo, em forma de U). Nas últimas décadas, várias famílias de modelos probabilísticos têm sido propostas. Esses modelos podem ser construídos com base em alguma transformação de uma distribuição padrão, geralmente já conhecida na literatura. Uma dada combinação linear ou mistura de modelos G normalmente define uma classe de modelos probabilísticos tendo G como caso especial. Esta tese é composta de capítulos independentes. O primeiro e último são curtos capítulos que incluem a introdução e as conclusões do estudo desenvolvido. Duas famílias de distribuições, denominadas de classe “exponentiated logarithmic generated” (ELG) e a classe “geometric Nadarajah-Haghighi” (NHG) s˜ao estudadas. A ´ultima ´e uma composi¸c˜ao das distribuições de Nadarajah-Haghighi e geométrica. Além disso, desenvolvemos uma biblioteca estatística para a linguagem de programação R chamada AdequacyModel. Esta é uma melhoria do pacote que foi disponibilizado no CRAN (Comprehensive R Archive Network) e está atualmente na versão 2.0.0. As duas principais funções da biblioteca são as funções goodness.fit e pso. A primeira função permite obter as estimativas de máxima verossimilhança (EMVs) dos parâmetros de um modelo e algumas medidas de bondade de ajuste dos modelos probabilísticos ajustados. E possível escolher o método de otimização para maximizar a função de log-verossimilhan¸ca. A segunda função apresenta o método meta-heurístico de busca global conhecido como Particle Swarm Optimization (PSO) proposto por Eberhart e Kennedy (1995). Algumas metodologias podem ser utilizadas para obtenção das EMVs necessárias para o cálculo de algumas medidas de adequação dos modelos probablísticos ajustados.
Gustavsson, Carina, and Ida Lübking. "Feminismens intåg i politiken – Partiers strategier och bemötande av Feministiskt Initiativ." Thesis, Högskolan i Borås, Akademin för vård, arbetsliv och välfärd, 2016. http://urn.kb.se/resolve?urn=urn:nbn:se:hb:diva-8852.
Full textThis essay is about how some of the already established parties have responded to the Feminist Initiative and it’s entry into politics and the parties' views on gender equality and feminism.We have used qualitative methods in the form of interviews and data collection. We interviewed the parties regarding their ideology and attitude as well as the strategies they have adopted to address niche party Feminist Initiative. We have looked at Position, salience and ownership, PSO-theory to see if the parties have used out the strategies significantly in theory. We also studied how the advent of the Feminist Initiative has affected the established parties' priorities and profiling the issues of gender equality and feminism. We also focus on earlier research on feminism.Parties look different on feminism and gender equality. After interviewing the desired parties it will show clear links with PSO-theory. We also studied whether the parties have put feminism and gender equality higher up on the political agenda since the Feminist Initiative's entry into politics.The original text is in Swedish.
SINGH, BHUPINDER. "A HYBRID MSVM COVID-19 IMAGE CLASSIFICATION ENHANCED USING PARTICLE SWARM OPTIMIZATION." Thesis, DELHI TECHNOLOGICAL UNIVERSITY, 2021. http://dspace.dtu.ac.in:8080/jspui/handle/repository/18864.
Full textOlekas, Patrick T. "Characterization and Heuristic Optimization of Complex Networks." University of Cincinnati / OhioLINK, 2008. http://rave.ohiolink.edu/etdc/view?acc_num=ucin1224187184.
Full textCleghorn, Christopher Wesley. "A Generalized theoretical deterministic particle swarm model." Diss., University of Pretoria, 2013. http://hdl.handle.net/2263/33333.
Full textDissertation (MSc)--University of Pretoria, 2013.
gm2014
Computer Science
Unrestricted
Mazin, Asim Mohamed. "REDUCING THE PEAK TO AVERAGE POWER RATIO OF MIMO-OFDM USING Particle SWARM OPTIMIZATION BASED PTS." OpenSIUC, 2013. https://opensiuc.lib.siu.edu/theses/1130.
Full textREIS, Felipe Andery. "Procedimento de Ajuste de Parâmetros de Redes RBF via PSO." reponame:Repositório Institucional da UNIFEI, 2014. http://repositorio.unifei.edu.br:8080/xmlui/handle/123456789/292.
Full textMade available in DSpace on 2016-01-20T12:46:13Z (GMT). No. of bitstreams: 1 dissertacao_reis_2014.pdf: 1856078 bytes, checksum: 33fce3e106740e6125c35aa6b2e14fed (MD5) Previous issue date: 2014-12
As redes neurais de funções de base radial (RBF - Radial Basis Function) têm sido utilizadas para a resolução de vários problemas em diversos contextos. Os parâmetros de uma rede de base radial (valores de centros, larguras e pesos) têm grande influência na sua capacidade de mapear relações entre seus dados de entrada e saída. Algumas abordagens apresentam procedimentos diversificados para determinar e otimizar estes parâmetros. Este trabalho aborda a combinação de métodos não supervisionados com o algoritmo de enxame de partículas (PSO - Particle Swarm Optimization) para a determinação de parâmetros em redes RBF. O algoritmo de otimização realiza um refinamento nos valores das larguras das funções de base radial a partir de um procedimento prévio de seleção de parâmetros. Utilizando valores pré-ajustados, o algoritmo converge em um menor número de passos em relação aos parâmetros inicializados aleatoriamente. O uso da abordagem proposta proporciona uma boa melhoria na exatidão de modelos de redes RBF em aplicações de aproximação de funções, previsão de série temporal e classificação de padrões.
Gobbo, Ilaria <1994>. "PSO per problemi di tracking error: selezione di piccoli portafogli." Master's Degree Thesis, Università Ca' Foscari Venezia, 2019. http://hdl.handle.net/10579/14220.
Full textMazzucato, Nicolo' <1992>. "PSO and BFO: two alternative metaheuristics for portfolio optimization problem." Master's Degree Thesis, Università Ca' Foscari Venezia, 2019. http://hdl.handle.net/10579/14538.
Full textHenniges, Philippe. "PSO pour l'apprentissage supervisé des réseaux neuronaux de type fuzzy ARTMAP." Mémoire, École de technologie supérieure, 2006. http://espace.etsmtl.ca/508/1/HENNIGES_Pihilippe.pdf.
Full textFranz, Wayne. "Multi-population PSO-GA hybrid techniques: integration, topologies, and parallel composition." Springer, 2013. http://hdl.handle.net/1993/23842.
Full textChi, Wen-Chun, and 紀玟君. "Parallel QBL-PSO Using MapReduce." Thesis, 2014. http://ndltd.ncl.edu.tw/handle/42584912905270860447.
Full textFranken, Cornelis J. "PSO-based coevolutionary Game Learning." Diss., 2004. http://hdl.handle.net/2263/30166.
Full textDissertation (MSc)--University of Pretoria, 2005.
Computer Science
unrestricted
Lai, Yi-fong, and 賴易烽. "PSO Algorithm for Speaker Verification." Thesis, 2012. http://ndltd.ncl.edu.tw/handle/19867975602889928362.
Full text國立中央大學
電機工程研究所
100
This thesis proposed method uses PSO algorithm to develop the VQ algorithm and determinate the parameter of SVM. Particle swarm optimization (PSO) simulates social behavior such as birds flocking to a promising position to achieve precise objectives in a multi-dimensional space. PSO performs searches using a population (called swarm) of individuals (called particles) that are updated from iteration to iteration. The vector quantization (VQ) was a powerful technique in the applications of digital speech compression. The traditionally widely used method such as the Linde-Buzo-Gray (LBG) algorithm always generated local optimal codebook. This thesis proposed method uses PSO algorithm to develop the VQ algorithm. Experimental results showed that the PSO algorithm can provide a better codebook with smaller mean square error (MSE) and less computation time than LBG algorithm. In the support vector machines (SVM), the model for classification is generated from the training process with the training data. Later on, classification is executed based on trained model. The largest problems encountered in setting up the SVM model are how to select the kernel function and its parameter values. This thesis proposed a method uses PSO algorithm to determinate the SVM parameter. Experimental results showed that the proposed system obtains a 2.26% EER and 0.0275 DCF improvement over the system with grid search.
Kao, Chih-Chieh, and 高志杰. "PSO Algorithm for Mel- Filterbank." Thesis, 2013. http://ndltd.ncl.edu.tw/handle/80671820970339415326.
Full text國立中央大學
電機工程學系
101
In this thesis, a study for feature extraction using filter bank applied to mel frequency cepstrum coefficients (MFCC) is presented. We propose a novel approach to use particle swarm optimization (PSO) to optimize the parameters of MFCC filterbank, such as the central and side frequencies. The proposed PSO algorithm utilizes filter similarity between statistical curve and filterbank’s envelope as fitness function. According to the energy and energy difference statistical charts that comply with characteristics of the speech signal in the energy spectrum, we obtained two optimal results by PSO. Then keyword recognization and three noisy environments are considered for tests. The results of our experiments show that the proposed method improves the recognition rate of keyword spotting system and the robustness against the testing noisy environments.
Liu, Te-chen, and 劉德誠. "A PSO Based Face Detection System." Thesis, 2006. http://ndltd.ncl.edu.tw/handle/89072898476870568717.
Full text長庚大學
資訊管理研究所
94
This paper proposes a Particle Swarm Optimization (PSO) based human face detection system. The system integrates PSO and neural networks. It can provide a more accurate face detection service by gaining faces’ position, size and angle. Engineers have interested in the face detection technologies for a very long time. At present, there are many applied face detection methodologies. The machine learning methods are one kind of these methodologies that need fewer man-made definitions. Only if there are enough training data collections, machine learning technologies can perform as a reliable face detector. And, the neural network classifier is one of these successful cases. In the pass, most of the pure machine learning based face detection system could only detect faces’ position, but not included their size and angle. This system integrates PSO and neural networks, and it can keep the advantage of the machine learning and moreover aware the faces’ size and angle. Besides proposing the framework of the PSO face detection system, this research also provide two PSO parameter setting formula. The Variable Confidence (VC) and Fast Variable Confidence (FVC) are two simple formulas that can promote the performance of the PSO face detection. These two methods improve both the detect rate and error rate substantially. We used the “Taiwanese Facial Dataset” and JAFFE image database as the experiment data, and tested tree PSO detection methods and different population size. The result shows that the VCPSO can meet the detect rate at 97.5%. The FVCPSO can save almost 50% of the iteration time, but only have accuracy down about 5%. These results point out that the detection methods we proposed are practical for the reality world. They provide a feasible way for the applications which need the detail of the faces’ information.
Lin, Shu-Yu, and 林書宇. "Improving PSO by Query-Based Learning." Thesis, 2007. http://ndltd.ncl.edu.tw/handle/34kyp3.
Full text國立臺灣大學
工程科學及海洋工程學研究所
95
Motivation: PSO (particle swarm optimization) is one of the most important research topics on artificial intelligence. PSO still remain some disadvantages. This paper tries to discuss the disadvantages of PSO and to find a solution for improving its performance. Method: We apply the query-based learning method proposed in our previous papers to PSO. It leads the particles to extend their search area. Thus, not only the precision of solution but also the time consumed is improved. We visualize the mechanism through a two-dimension PSO and verify the mechanism by several functions. Conventional PSO usually leads the particles go into the wrong direction of evolution. To resolve this drawback, when particles tend to converge, we spread some particles into ambiguous solution space. Furthermore, PSO has been well improved. Achievement: This thesis, in our knowledge, is the first study that applies the QBL concept in Particle Swarm Optimization. The experiment results show the proposed approach is able to prevent the system from falling into local optimal and improve the performance of PSO.
Chen, WeiRen, and 陳韋任. "PSO-based Fuzzy Image Filter Design." Thesis, 2011. http://ndltd.ncl.edu.tw/handle/29702015981924462606.
Full text國立宜蘭大學
電子工程學系碩士班
99
In this paper, we employ a fuzzy image filter (FIF) to reducing noise for gray-level image and the parameters of the FIF are adjusted by using the Particle Swarm Optimization (PSO) technique. It is well known that PSO has fast convergence speed to find the global optimal parameters of FIF and thus it will have better performance for removing the impulse noise even from highly corrupted images. The filter consists of a fuzzy number construction process, a fuzzy filtering process, a PSO searching process and an image knowledge base. First, we construct the image knowledge base for the fuzzy filtering process as that in [30]. Then, we can collect data when training noised images pass through the fuzzy filtering process and adjust each of the parameters to global optimum value by PSO. Thus, the proposed FIF can be constructed more efficient and powerful. In order to show the ability of this FIF, we compare with some denoising methods in the experimental results. At last, applying the same framework again, we will utilize a metric Q who was proposed by Zhu[29] and when it was without knowledge of the noise-free image and provides a quantitative measure of true image content from the noise image, to reduction Impulse noise.
Li, zeyou, and 李則佑. "Applying PSO-SVM For Channel Equalization." Thesis, 2012. http://ndltd.ncl.edu.tw/handle/21964865425522112791.
Full text國立宜蘭大學
電機工程學系碩士班
100
The support vector machine (SVM) is a powerful tool for solving problems with high dimensional, nonlinearly, and is of excellent performance in classification. In this study, we propose SVM as channel equalization. To reconstruct the signal that has the inter symbol interference (ISI) and white Gaussian noise which in high speed communications environments. The SVM parameters will affect the identification of the result. Therefore, we use particle swarm optimization (PSO) to find the suit parameters in SVM. To obtain the channel equalization model and reconstruct the signal. The PSO-SVM equalizer to realize the Bayesian equalizer solution can be achieved efficiently. The performance degradation was nearly 1dB at SNR increased.
Su, Hua, and 蘇樺. "PSO Algorithm for Speaker Verification Systems." Thesis, 2014. http://ndltd.ncl.edu.tw/handle/64080634241659055321.
Full text國立中央大學
電機工程學系
102
This thesis focused on speaker verification between test corpus and registered speaker models. First of all, the thesis introduces score normalization approaches to the speaker verification system. Then, we apply Particle Swarm Optimization algorithm to optimize model parameters. The main idea of PSO method is like fish foraging behavior. All particles of PSO have memories. The algorithm has simple calculation and fast convergence. With its optimized features to build a more accurate speaker model, the system is more discernment. In addition, the thesis also introduces a regression analysis method to speaker verification system. Regression analysis is a useful statistics analysis method. We build the regression model for each speaker by ordinary least squares estimation and the coefficients of determination analysis. Experiments showed that the proposed method can improve performance of the speaker verification system.
Tang, Chung-Hao, and 唐中浩. "Applying Adaptive PSO on Roundness Measurement." Thesis, 2009. http://ndltd.ncl.edu.tw/handle/8eqku6.
Full text國立臺北科技大學
工業工程與管理研究所
97
Inspection on silicon wafers is a complex and important process for semiconductor manufacturers. Optimally manufacturing each wafer to overcome the quartz shortages is tantamount to achieve maximum total profit in practice. Roundness, particularly the roundness of silicon wafers remaining a bottleneck for reclaiming wafer, is a very costly and crucial step for increasing yield. In particular, inspecting post-slicing process of wafers can be considered as a non-linear problem with a specified roundness measure. Therefore, this study proposes heuristic and adaptive methods that rapidly converge with high accuracy and low cost. The proposed methods incorporate the Hooke-Jeeves pattern search with Particle Swarm Optimization in comparison of convergent performance. A substantial amount of effort has been expended to alleviate the redundancy than the former [18] involved. This study primarily focuses on mixture algorithms for measuring roundness of silicon wafers and competes the performance with accuracy (efficiency) through visual inspection. A set of experiments is conducted to verify the feasibility under varied schemes. Definitively, experimental results reveal that the proposed method is superior in terms of execution time and solution quality.
Prasain, Hari. "A Parallel Particle Swarm Optimization Algorithm for Option Pricing." 2010. http://hdl.handle.net/1993/4033.
Full textSidhu, Manitpal S. "A PSO based load-rebalance algorithm for task-matching in large scale heterogeneous computing systems." 2013. http://hdl.handle.net/1993/21692.
Full textEmma and 蔣雅慈. "Multi-Objective Nurse Scheduling Using Scatter PSO." Thesis, 2009. http://ndltd.ncl.edu.tw/handle/64296188743774598841.
Full text國立暨南國際大學
資訊管理學系
97
It is time-consuming to generate nurse scheduling using traditional human-involved manner in order to account for administrative operations, business benefits, governmental regulations, and fairness perceived by nurses. Moreover, the objectives cannot be measured quantitatively even when the nurse scheduling is generated after a lengthy manual process. This paper presents a Multi-Objective Scatter PSO combined with Tabu Search to tackle the real-world nurse scheduling problem. By the proposed mathematical formulation, the hospital administrator can set up multiple objectives (such as cost reduction and nurse-satisfaction raising) and stipulate a set of scheduling constraints (such as operational practice and governmental regulations), and our system can automatically generate a set of solutions which nearly optimize the given objectives and meet the specified constraints. We used two kinds of problems to evaluate the performance of Scatter MOPSO, first is benchmark functions and second is nurse scheduling problem. The experimental results manifest that our method performs better than NSGA II and MOPSO on benchmark functions, and better than MOPSO on nurse scheduling problem.
Wu, Cheng-Pei, and 吳政沛. "PSO-based Localization in Wireless Sensor Networks." Thesis, 2008. http://ndltd.ncl.edu.tw/handle/09485581456766144695.
Full text淡江大學
電機工程學系碩士班
96
Localization in wireless sensor networks has developed two categories: range-free and range-based localization algorithms. The range-free algorithms don''t need any range techniques but use connectivity among the anchors to estimate the positions of unknown nodes. The range-based algorithms must need some range techniques such as TOA, TDOA, AOA and RSSI to measure the neighbors'' distance. And use these measurements to estimate the position of the unknown nodes. In order to add the coverage of anchor nodes, some range-based localization algorithms use iterative multilateration to solve low density problem of the anchor nodes. But the iterative multilateration algorithm suffers two drawbacks: first, some nodes still don''t have sufficient anchor nodes in their neighborhood; second, the use of localized unknown nodes as anchor nodes can bring the cumulative error. Therefore, we propose a PSO based localization algorithm using the distance of the closest neighbor to estimate the unknown node''s location. We use this algorithm to reduce the error accumulation effects and add the probability of the orphan nodes which can successfully calculate the locations. Compared with some localization algorithms, new method can be more effective performance for different environment in our computer simulations.
Wu, Tsan-Chan, and 吳讚展. "Self-adjusted Nonlinear inertia weight PSO algorithm." Thesis, 2012. http://ndltd.ncl.edu.tw/handle/26009556464934248971.
Full text國立中央大學
電機工程研究所
100
In this thesis we have presented an improved algorithm for Particle Swarm Optimization (PSO) named Self-adjusted Nonlinear inertia weight PSO algorithm (SNPSO). SNPSO algorithm is an improved method of the inertia weight, utilize nonlinear and self-modulation characteristics to improve PSO algorithm that is easy to trap into the local optimal solution, The thesis also presents a method of searching parameters in the SNPSO. Finally, The performance of SNPSO is fairly demonstrated by applying sixteen benchmark problems and comparing it with several popular PSO algorithm. The analysis of result shows that our proposed methods is effective and gain better performance than other popular PSO algorithms. Furthermore, our method can efficiently improve the performance of standard PSO and more ability to prevent the particle fall into some local optimal solutions.
Yan, Yu-shiang, and 顏淯翔. "Visual Tracking System Based on Improved PSO." Thesis, 2014. http://ndltd.ncl.edu.tw/handle/46901353322747813785.
Full text國立中央大學
電機工程學系
102
In this thesis, we propose a modified particle swarm optimization algorithm which is called particle swarm optimization with one dimension multi-modes (ODMPSO). The proposed ODMPSO which is different from standard PSO algorithm is moving functions. In ODMPSO method, the particles can be adaptively searched by their environment. There are five modes in ODMPSO method. Each mode has its own specific optimizations. Finally, these modes makes the particles more easily and quickly find the results. Afterwards, we propose a Gaussian mixture model based on ODMPSO (GMM-ODMPSO) method in a visual tracking system. The GMM-ODMPSO method will accelerate the convergence rate of creating the GMM background model and the system also improves the detection of moving targets. The experimental results show that the proposed GMM background model obtains better recognition rate. As seen in the experiments, the GMM-ODMPSO method is a 48% improvement over the computing time, 88% over the convergence rate, and the recognition rate is almost the same as the traditional GMM background model. In the results, we can see our proposed method is more effective.
KUMAR, ANURAG. "ECONOMIC LOAD DISPATCH STUDIES BASED ON PSO." Thesis, 2020. http://dspace.dtu.ac.in:8080/jspui/handle/repository/20135.
Full textVARSHNEY, PRATEEK KUMAR VARSHNEY. "IMPLEMENTING PARALLEL PSO ALGORITHM USING MAPREDUCE ARCHITECTURE." Thesis, 2016. http://dspace.dtu.ac.in:8080/jspui/handle/repository/14678.
Full textMishra, Mahesh Prasad. "Solution to economic load dispatch using PSO." Thesis, 2012. http://ethesis.nitrkl.ac.in/3711/1/FINALTHESIS.pdf.
Full textpal, Sushil, and Annwesh Barik. "PSO Based Deployment of Hybrid Sensor Networks." Thesis, 2015. http://ethesis.nitrkl.ac.in/6904/1/PSO_Pal_2015.pdf.
Full textChing-Yi, Chen. "PSO-Based Evolutionary Learning System Design and Applications /." 2006. http://www.cetd.com.tw/ec/thesisdetail.aspx?etdun=U0002-2505200615111100.
Full textWu, Shang-Tza, and 吳尚澤. "A Dynamic PSO ─ Black-Scholes Option Pricing Model." Thesis, 2014. http://ndltd.ncl.edu.tw/handle/76766122738842239555.
Full text國立屏東商業技術學院
資訊管理系(所)
102
In the financial market, to analyze the trends of price change is capable to predominate the investment opportunities. Therefore, many scholars and researchers focused on the pricing theories of financial commodity, for example, the Black-Scholes option pricing model, but its arguments are predefined by some strongly assumptions. Because of those assumptions, it will be still difficult to evaluate the prices to real markets. Therefore, this research would give 4 different conditions and their impacts on option pricing to construct a hybrid-dynamic option pricing model (PSO-BS Option Pricing Model). By revising the controversial normal distribution assumption of traditional pricing model, the study has formed some new look up tables by several investment conditions. Without increasing pricing complexity of commodities, the result of the pricing model is obviously superior to traditional Black-Scholes option pricing model.
Wu, Chih-ping, and 吳致平. "PSO-based resource allocation in downlink LTE networks." Thesis, 2014. http://ndltd.ncl.edu.tw/handle/77029494192799872760.
Full text國立中央大學
通訊工程學系在職專班
102
In this thesis, the problem of resource allocation in downlink long term evolution (LTE) networks is investigated. To increase the spectral and power efficiency, we propose a subcarrier allocation scheme based on particle swarm optimization (PSO) algorithm. PSO can be easily implemented in discrete optimization problem and fast converge to an optimal solution, but the solution may be just a local optimum. In order to avoid trapping at local optima, the strategies of crossover and mutation are used in the proposed method. Simulation results show that the proposed algorithm can efficiently reduce the total transmission power.