Дисертації з теми "BACTERIA FORAGING"
Оформте джерело за APA, MLA, Chicago, Harvard та іншими стилями
Ознайомтеся з топ-32 дисертацій для дослідження на тему "BACTERIA FORAGING".
Біля кожної праці в переліку літератури доступна кнопка «Додати до бібліографії». Скористайтеся нею – і ми автоматично оформимо бібліографічне посилання на обрану працю в потрібному вам стилі цитування: APA, MLA, «Гарвард», «Чикаго», «Ванкувер» тощо.
Також ви можете завантажити повний текст наукової публікації у форматі «.pdf» та прочитати онлайн анотацію до роботи, якщо відповідні параметри наявні в метаданих.
Переглядайте дисертації для різних дисциплін та оформлюйте правильно вашу бібліографію.
Vetter, Yves-Alain. "Bacterial foraging with cell-free enzymes /." Thesis, Connect to this title online; UW restricted, 1998. http://hdl.handle.net/1773/11033.
Повний текст джерелаLadevèze, Simon. "Functional and structural insights into Glycoside Hydrolase family 130 enzymes : implications in carbohydrate foraging by human gut bacteria." Thesis, Toulouse, INSA, 2015. http://www.theses.fr/2015ISAT0010/document.
Повний текст джерелаThe interplay between gut bacteria, food and host play a key role in human health. Thefunctional characterization of Uhgb_MP, an enzyme belonging to the family 130 of glycosidehydrolases, discovered by functional metagenomics, revealed novel functions of plant cellwall polysaccharide and host glycan degradation by phosphorolysis. The moleculardeterminants of Uhgb_MP specificity towards mannosides were identified by solving itscrystal structure, in apo form and in complex with its ligands. A new process of high addedvalue mannosylated oligosaccharide synthesis by reverse-phosphorolysis was alsodeveloped. Finally, the functional characterization of the BACOVA_03624 protein fromBacteroides ovatus ATCC 8483, a highly prevalent gut bacterium, revealed that GH130 familyboth contains glycoside phosphorylases and glycoside hydrolases, which are able to degrademannosides and galactosides, and to synthesize them by reverse-phosphorolysis and/ortransglycosylation. All these results, together with the identification of GH130 enzymeinhibitors, open new perspectives for studying, and potentially also for controlling,interactions between host and gut microbes
Harso, Wahyu [Verfasser], Eckhard [Gutachter] George, Christof [Gutachter] Engels, and Klaus [Gutachter] Dittert. "The mycorrhizal plant root system : foraging activities and interaction with soil bacteria in heterogeneous soil environments / Wahyu Harso. Gutachter: Eckhard George ; Christof Engels ; Klaus Dittert." Berlin : Lebenswissenschaftliche Fakultät, 2016. http://d-nb.info/1112193022/34.
Повний текст джерелаTang, W. J. "Optimisation algorithms inspired from modelling of bacterial foraging patterns and their applications." Thesis, University of Liverpool, 2008. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.490623.
Повний текст джерелаNasir, Ahmad. "Bacterial foraging and spiral dynamics based metaheuristic algorithms for global optimisation with engineering applications." Thesis, University of Sheffield, 2014. http://etheses.whiterose.ac.uk/7068/.
Повний текст джерелаSupriyono, Heru. "Novel bacterial foraging optimisation algorithms with application to modelling and control of flexible manipulator systems." Thesis, University of Sheffield, 2012. http://etheses.whiterose.ac.uk/2122/.
Повний текст джерелаTIWARI, RAM MUKUND. "FUZZY EDGE DETECTION OF BLURRED IMAGE USING BACTERIA FORAGING." Thesis, 2012. http://dspace.dtu.ac.in:8080/jspui/handle/repository/14020.
Повний текст джерелаKUMAR, AJAY. "EDGE DETECTION USING BACTERIA FORAGING & FUZZY SIMILARITY MEASURE." Thesis, 2012. http://dspace.dtu.ac.in:8080/jspui/handle/repository/14024.
Повний текст джерелаDas, Saikishan, and K. Prasanna. "Multiple robot co-ordination using particle swarm optimisation and bacteria foraging algorithm." Thesis, 2010. http://ethesis.nitrkl.ac.in/1886/1/B.Tech_Project_Thesis_Saikishan_Das(10603062).pdf.
Повний текст джерелаLee, Kuo-Wei, and 李國維. "Improved Bacterial Foraging Optimization." Thesis, 2013. http://ndltd.ncl.edu.tw/handle/22851452298832117486.
Повний текст джерела大同大學
資訊經營學系(所)
101
This paper proposes an improved approach involving bacterial foraging optimization algorithm (BFOA) behavior. The new algorithm is called improved bacterial foraging optimization (IBFO). BFOA is a new swarm intelligence technique. Three main BFOA operation are chemotaxis, reproduction and elimination-dispersal, which are applied to global and local random searches. This powerful and effective algorithm has been used to solve various real-world optimization problem. However , BFOA has several shortages: many parameters needed to be set ; tumble angles are generated randomly and a fixed chemotactic step size causing poor convergence. In this paper, we try to improve these shortages of BFOA base on reduce setting parameters. Finally, we compare the performance of IBFO with the classical BFOA, testing them on seven widely-used benchmark functions. The experimental result shows that the IBFO is very competitive and outperforms the BFOA.
Lin, Guan-Yu, and 林冠喻. "Bacterial foraging for watermarkings applications." Thesis, 2009. http://ndltd.ncl.edu.tw/handle/66p8px.
Повний текст джерела國立高雄大學
電機工程學系碩士班
97
In recent years, along with the booming application of the Internet, digital files and associated multimedia contents can be easily acquired in our daily lives. With the inherent characteristics of lossless copying and easy spreading, the intellectual property or ownerships of the multimedia contents have become a rising problem. Data hiding and watermarking techniques aiming at protecting copyright-related issues are of considerable interest in academia and industry. In this thesis, we mainly focus on improving the requirements of watermarking applications, including the watermark robustness and the invisibility in the frequency domain. Since the requirements tend to have conflicts, we employ bacterial foraging for training the watermarking algorithm and obtain the optimized solution. With the simulations presented, bacterial foraging provides a systematic way to balance the contributions by the watermarking requirements, and to offer another scope for designing an effective algorithm for watermarking.
Allemneny, Raghuveer. "Bacterial Foraging Based Channel Equalizers." Thesis, 2006. http://ethesis.nitrkl.ac.in/24/1/raghuveer.pdf.
Повний текст джерелаCheng, Hsiu-Tzu, and 鄭秀姿. "Bacterial Foraging Optimization for Portfolio Optimizations." Thesis, 2012. http://ndltd.ncl.edu.tw/handle/79562681397598793645.
Повний текст джерела大同大學
資訊經營學系(所)
100
Portfolio optimization (PO) is a mixed quadratic and integer programming problem, and an effective solution approach is essential for most investors in order to raise expected returns and reduce investment risks. To solve this problem, various heuristic algorithms, such as genetic algorithms and particle swarm optimization, have been proposed in the past. This paper aims to examine the potential of bacterial foraging optimization algorithms (BFO) for solving the portfolio optimization problem. Bacterial foraging optimization algorithm is a new swarm intelligence technique and has successfully applied to some real world problems. Through three operations, chemotaxis, reproduction, and elimination and dispersal, the proposed BFO algorithm can effectively solve a PO problem with cardinality and bounding constraints. The performance of BFO approach was evaluated by performing computational tests on five benchmark data sets, and the computational results were compared to those obtained with existing heuristic algorithms. Experimental results demonstrate that the proposed algorithm is very competitive in portfolio optimization.
KUMARI, TANYA. "EDGE DETECTION USING BACTERIAL FORAGING AND UNIVERSAL LAW OF GRAVITY." Thesis, 2016. http://dspace.dtu.ac.in:8080/jspui/handle/repository/15059.
Повний текст джерелаYu, Chia-Jung, and 余家榮. "Design of Fuzzy PID Controllers Based on Modified Bacterial Foraging Optimization." Thesis, 2010. http://ndltd.ncl.edu.tw/handle/21557765565511079873.
Повний текст джерела國立高雄應用科技大學
電子工程系
98
In this thesis, we propose a modified bacterial foraging optimization (MBFO) approach, to include the synchronous bacterial foraging optimization (SBFO) and self adaptive bacterial foraging optimization (SABFO), to update the fuzzy proportional, integral, and derivative (FPID) gains which are optimized. Because of the genetic algorithm (GA) finds out the local optimal solution can not the global optimal solution for processing the complex problems. The bacterial foraging optimization (BFO) possesses chemotactic, swarming, reproduction, elimination and dispersal features to move the bacterial populations to the same environment, so this behavior avoid to get the local optimal solution. The modified bacterial foraging optimization by improving the moved length, position and objection function enhances the convergence speed of BFO. Hence, the modified bacterial foraging optimization gives more powerful improvements for the performance of control systems. Finally, from the demonstrating examples, the simulated results are presented to illustrate the better performance of the proposed methodology of (MBFO-FPID) approach compared with other approaches.
Chen, Kuan-Yu, and 陳冠宇. "Design of Adaptive Channel Equalizer Based on Modified Bacterial Foraging Optimization." Thesis, 2011. http://ndltd.ncl.edu.tw/handle/62046402260337701178.
Повний текст джерела國立高雄應用科技大學
電子工程系
99
In the communication systems, due to noise interference of signal transmission through channel, so the signal will need to be handled at the receiver, applying an equalizer recovering the received signal should be considered. Inter-symbol interference (ISI) is an important factor which affects the performance of communication systems, so that the originally transmitted symbols can be recovered correctly at the receiver, an equalizer can effectively eliminate ISI caused by band-limited channel or multipath. In this thesis, we propose a self adaptive bacterial foraging oriented by particle swarm optimization (SABF-PSO) approach, to update the adaptive channel equalizer weights which are optimized. Finally, from the simulation results are given to verify the effectiveness of the proposed method.
BANSAL, MINAL. "APPLICATION OF TYPE-2 FUZZY LOGIC TO REMOVE NOISE FROM COLOUR IMAGES BY USING BACTERIAL FORAGING." Thesis, 2016. http://dspace.dtu.ac.in:8080/jspui/handle/repository/14484.
Повний текст джерелаChien, You-Ming, and 簡佑銘. "Application of Bacterial Foraging Algorithm for Fault Section Estimation of Power Systems." Thesis, 2008. http://ndltd.ncl.edu.tw/handle/86489363430766542072.
Повний текст джерела國立成功大學
電機工程學系碩博士班
96
The problem of fault section estimation is very important in power systems because effective fault section estimation will help facilitate the power restoration. Therefore, in this thesis, a Bacterial Foraging Algorithm (BFA) is proposed to solve the fault section estimation problem. The theme of this method is to simulate Escherichia coli such that the nutrients in the intestine can be better searched, with such a concept it is further employed to solve the fault section estimation problems. In order to validate the effectiveness of this approach, the method has been tested through different test scenarios with comparison to other methods. From the test results, they revealed the satisfactory computation performance of justifying the section of faults in a distribution system, thereby providing a useful reference as maintenance forewarning as well.
Chou, hsiaoping, and 周小萍. "Bacterial Foraging Particle Swarm Optimization Algorithm Time-Serial Fuzzy Prediction System Design." Thesis, 2012. http://ndltd.ncl.edu.tw/handle/67897026614561251690.
Повний текст джерела國立金門大學
觀光管理學系
100
This study presents Particle Swarm Optimization (PSO) and Bacterial Foraging Particle Swarm Optimization (BFPSO) to develop the financial time-series prediction system. The dynamic clustering-based learning algorithm is first to determine the number of Radial Basis Function Networks (RBFN) and select the center positions of Radial Basis Function. Thus, the initial system model is fast determined. The particle swarm optimization (PSO) and recursive least square (RLS) learning machines are proposed to acquire the appropriate parameters of model system to predict the behavior of the identified stock data set. In this article, the novel BFPSO learning algorithm is proposed to efficiently achieve the fuzzy system to create the accurate prediction model. The identified model can actually forecast the stock data. The real Taiwan Stock Price Index serial data between 2000 and 2004 illustrate the efficiency of the proposed learning scheme. Several experiments in the stock price prediction examples can present the powerful of our illustrated learning algorithms.
Lu, Wei-Cheng, and 呂偉誠. "Fuzzy Bacterial Foraging System and its Applications in Control of Servo Motors." Thesis, 2011. http://ndltd.ncl.edu.tw/handle/72551615407317176764.
Повний текст джерела國立臺灣師範大學
應用電子科技學系
99
This thesis proposes a modified bacterial foraging algorithm to adjust the design of fuzzy systems. Since traditional bacterial foraging algorithms require complicated operations and extremely time-consuming, the modified bacterial foraging algorithm utilize some simplified procedures to reduce the computation time and increase the operation efficiency. The simplified procedures include five parts that include: 1) modified Swarm Behavior, 2) electrification bacterium hover ability, 3) modified bacterium location, 4) adjustment of bacteria source, and 5) the best bacterium source evolution mechanism. The modified bacterial foraging algorithm is applied to update the parameters of fuzzy systems that approximate nonlinear functions, and to on-line tune the parameters of fuzzy controllers. The DC servo motor experiment and simulation results demonstrate the feasibility and applicability of the proposed methods.
Lin, Chih-chung, and 林志忠. "A probability matrix-based Discrete Bacterial Foraging Optimization for Capacity Vehicle Routing Problems." Thesis, 2016. http://ndltd.ncl.edu.tw/handle/27872835340646727824.
Повний текст джерела大同大學
資訊經營學系(所)
104
Vehicle routing problem (VRP) becomes more important in the distribution industry. Capacitated vehicle routing problems (CVRP) are a combinatorial optimization problem. It has been proved that CVRP is an NP-hard problem. Therefore it is hard to find optimal solutions for large-sized problems. This paper proposes a Discrete Bacterial Foraging Optimization with Probability Matrix (DBFOMAT) approach to solve the CVRP. The proposed approach uses a probability matrix as the main mechanism for solution matrix decoding. The algorithm first uses DBFO for assigning customers to routes and then uses probability matrices to arrange customer visiting sequences for each vehicle. This approach also uses another probability matrix to memorize customer sequences, which are used to guide customer sequencing in next iteration. The experimental results show that the proposed algorithm is an effective approach for solving the CVRP.
Lin, Yu-Sheng, and 林裕勝. "Bacterial Foraging Fuzzy Controllers and Its Application Study in Control of Two-Wheeled Vehicles." Thesis, 2013. http://ndltd.ncl.edu.tw/handle/50443605853871296346.
Повний текст джерела國立臺灣師範大學
應用電子科技研究所
101
This thesis focuses on adjusting the design of fuzzy control systems through a combination of the fuzzy control theory and the bacterial foraging algorithm. In addition, for a self-designed two wheeled vehicle, because of the reason that two-wheeled vehicle is unable to be self-balancing, a controller is required for forming a control system. The control system kernel is Megawin 82G516 single chip. The real-time data of angle and angular velocity are transmitted respectively from 3-axis accelerometer and gyroscope to the control kernel. Through the measurement amplifier processes analog signal, along with the construction of digital filter (Kalman filter) and fuzzy controller in the single chip, the control system kernel outputs a suitable pulse width modulation (PWM) to control the two-wheeled vehicles to go forward and backward, and even to make it self-balancing. The simulation results indicate that the two-wheeled unstable vehicle becomes stable immediately through the bacterial evolution. Moreover, the experiment results show that the two-wheeled vehicle with fuzzy bacterial evolution system can detect the gravity center of body such that the two-wheeled vehicle can move forward and backward.
Huang, Chun-Yu, and 黃均瑜. "Design of Optimal Motion Controller for a Mecanum Wheeled Robot Using Bacterial Foraging Optimization." Thesis, 2015. http://ndltd.ncl.edu.tw/handle/89209368293691613098.
Повний текст джерела國立宜蘭大學
電機工程學系碩士班
103
This paper presents a bacterial foraging optimization algorithm (BFO) motion control method and its application to a four-wheeled Mecanum omnidirectional mobile robot. The optimal parameters of motion controller are auto-tuned by using the proposed BFO computing. By using Lyapunov stability theory, the closed-loop system has been proven stable. The convergent behavior of tracking errors provides better performance of the Mecanum omnidirectional mobile robot to achieve stability and trajectory tracking. The kinematic model is derived via the geometric architecture of Mecanum omnidirectional mobile robots and the BFO-based kinematic controller is developed. This efficient BFO-based intelligent motion controller is then implemented in a field programmable gate array (FPGA) chip by using the system-on-a-programmable-chip (SoPC) technology and hardware/software codesign to achieve stabilization and trajectory tracking. Simulations and experimental results demonstrate the effectiveness and merits of the proposed methods.
Tung, Chih-Hauan, and 董至軒. "Automatic clustering for cell formation with alternative process routings using a Discrete Bacterial Foraging Optimization." Thesis, 2014. http://ndltd.ncl.edu.tw/handle/4e62s3.
Повний текст джерела大同大學
資訊經營學系(所)
102
The use of data clustering methods is one of the most popular approaches of designing cellular manufacturing systems (CMS). The aim of cell formation is to classify similar parts into part families and to group machines into manufacturing cells. In most past studies, the number of machine cells is known beforehand, but in practice there are many restrictions to obtain the number in advance. This study proposed an automatic clustering approach based on discrete bacterial foraging optimization (DBFO) algorithms to solve cell formation problems with alternative process routings. That is, the best number of machine cells is searched during the cell formation process, not given in advance. To enhance the searching ability of DBFO, the concept of gbest and pbest adopted from particle swarm optimization (PSO) is embedded into the proposed algorithm. Two types of generalized cell formation problems are tested: considering operation sequences and not considering operation sequences. The experimental results show that the proposed DBFO algorithm performs well for solving cell formation problems, particularly when the cell numbers are not given beforehand.
Ting, Tsai You, and 蔡侑庭. "Application of Bacterial Foraging Optimization and GeneralRegression Neural Network on Taipei City House Prices Forecast." Thesis, 2014. http://ndltd.ncl.edu.tw/handle/69331874993757814549.
Повний текст джерела東吳大學
經濟學系
102
Abstract Having a warm home is the goal that we have to pursue, but the limited supply of land, susceptible to fluctuations in the impact of various external factors, but when faced with sudden upheaval, as previously the U.S. housing loan crisis or the Japanese real estate bubble event so big its influence can not be careless, so understanding the future trend of prices, has become the subject of government policy and people's lives are sustained attention. Known from research to explore existing literature, the use of artificial intelligence methods of forecasting models, often compared to traditional measurement methods alone can achieve better prediction. This article will introduce a new evolutionary computation method - bacterial foraging algorithm, hoping by bacterial foraging algorithm combined with generalized regression neural networks and other artificial intelligence methods to construct more effective predictive models. Empirical results indicate bacterial foraging algorithm model, in a small sample of prices in Taipei prediction model has better predictive ability; bacterial foraging algorithm to fine-tune and optimize through generalized regression neural network model parameters, Its predictions than other models available to smaller error rate, and effectively improve the accuracy of predictions. The study screened regularly post office savings variable is the one-year floating rate, M2, the consumer price index, the number of households and domiciled stock index and other five. And after training in the above model, can get good predictive value. This also explained the ups and downs of Taipei prices, mainly affected by the overall economic indicators. Keywords: house prices, artificial intelligence, neural networks, Bacterial
Chen, Chieh-Han, and 陳玠含. "A Novel Strategy-adaptation-based Bacterial Foraging Optimization for FCMAC Model and Its Applications in Classification." Thesis, 2013. http://ndltd.ncl.edu.tw/handle/06701788743677371159.
Повний текст джерела國立勤益科技大學
資訊工程系
101
In this thesis, we propose a fuzzy cerebellar model articulation controller (FCMAC) model with improved bacterial foraging optimization (BFO). The proposed modified bacterial foraging optimization is called Strategy-adaptation-based Bacterial Foraging Optimization (SABFO). The SABFO is use to adjust the weights of FCMAC model and facilitate the actual output of the FCMAC model approximating the desired output for classifications. This thesis consisted of two major parts. In the first part, we propose a new Strategy-adaptation-based Bacterial Foraging Optimization. The main contribution of this study is adding the strategic approach into traditional bacterial foraging optimization. The propose method makes each bacterium perform different run-lengths, and increased bacterial diversity as well. We use nonlinear benchmark functions for verifying our propose SABFO to achieve the global optimal solution more easily than other methods. In the second part, we apply the propose SABFO to adjust the parameters of FCMAC model. Although back-propagation (BP) algorithm is commonly used to adjust the parameters of FCMAC model, it is easy to fall into the local optimal solution. Therefore, our proposed evolutionary algorithms can solve the above-mentioned optimal parameter problems successfully. Finally, the propose FCMAC model with SABFO learning algorithm is applied in classification problems. Experimental results demonstrate the convergence effectiveness of the proposed methods.
Wei, Shih-Min, and 魏世旻. "Mobile Robot Wall-following Control Using a Fuzzy CMAC with Group-based Strategy Bacterial Foraging Optimization." Thesis, 2015. http://ndltd.ncl.edu.tw/handle/20707906136341859210.
Повний текст джерела國立勤益科技大學
資訊工程系
103
In this paper, a fuzzy cerebellar model articulation controller (FCMAC) with group-based strategy bacterial foraging optimization (GSBFO) for mobile robot wall-following control is proposed. In the proposed FCMAC controller, the inputs are the distance between the sonar and the wall, the outputs are the angular velocity of two wheels. Through using the GSBFO to adjust parameters of FCMAC. A new fitness function is defined to evaluate the evolution of mobile robot wall-following. The fitness function includes four assessment factors which are defined as follows: maintaining safe distance between the mobile robot and the wall, ensuring successfully running a cycle, avoiding mobile robot collisions, and mobile robot running at a maximum speed. The simulation results show that the improved BFO is better than the traditional BFO. After learning, mobile robot travels wall-following successfully in unknown environment.
Farhat, Ibrahim A. "Economic and Economic-Emission Operation of All-Thermal and Hydro-Thermal Power Generation Systems Using Bacterial Foraging Optimization." 2012. http://hdl.handle.net/10222/14865.
Повний текст джерелаShih, Po-Lin, and 施伯霖. "Integrated Optimal Energy Management/Gear Shifting Strategy Using Bacterial Foraging Algorithm for a Three-Power-Source Hybrid Powertrain." Thesis, 2017. http://ndltd.ncl.edu.tw/handle/wdaw58.
Повний текст джерела國立臺灣師範大學
工業教育學系
105
The purpose of this study is to develop the bacterial foraging algorithm (BFA) by applying it to the energy management/gear shifting strategy system of a three-power-source hybrid powertrain. Furthermore, this study was practical in nature, as it used the real-time simulation Hardware-in-the-Loop (HIL) to verify the algorithm’s feasibility. This study employs HIL to assess the influence that using BFA will have on the energy management and gear shifting strategy control of a three-power-source hybrid powertrain. The vehicle weighs 1,368 kilograms and its subsystems include a 43kW internal combustion engine, 30kW motor, 15kW integrated starter generator, and a 1.872kW-h Ah lithium battery. There are three primary steps for the energy management system and BFA energy management control: 1) chemotaxis, 2) reproduction, and 3) elimination-dispersal. The overall number of iterations was 30, and 80 bacteria were used carry out optimal energy management. BFA and two control strategies were used to carry out a comparison of fuel consumption with the NEDC (New European Driving Cycle) driving pattern. 1) Rule-based management: There are five control modes, which are system preparation, battery charging mode, electric mode, hybrid power mode, and extended range mode; the engineer used his experience to determine when to set and change modes. 2) Equivalent consumption minimization strategy (ECMS): By incorporating the global search algorithm (GSA), we searched for all the scope’s possibilities in order to find the most minimal fuel consumption for power distribution ratio and gear shifting strategy. At the end of the study, we used HIL to simulate the feasibility and verify fuel consumption benefits of BFA on vehicle control units (VCU) in real time. A basic rule base, ECMS, BFA, and real-time were the four conditions for the equivalent consumption with the NEDC driving pattern: 538.9g, 209.6g, 248.9g, and 253.6g were their respective values. The equivalent consumption values with a FTP-72 driving cycle were 579.2g, 291g, 316.3g, and 320.38g. ECMS, BFA, and real-time were compared with a basic rule base when using a NEDC driving pattern to determine percentage values for improvement in energy consumption: 61%, 53.8%, and 52.9%. Percentage values for improvement in energy consumption for a FTP-72 driving cycle were 49.7%, 45.3%, and 44.6%. The improvement in equivalent consumption values for BFA and real-time for the NEDC driving pattern and FTP-72 driving cycle were 98% similar, and they were only outperformed by ECMS, which was the optimal solution. In the future, this experiment will be used to test a three-power-source e-CVT hybrid-powered vehicle.
WANG, CHUN-HUNG, and 王俊弘. "Adaptive Iterative Learning Control for Freeway Traffic Flow Systems Using Improved Bacterial Foraging Optimization based Desired Traffic Density Planning." Thesis, 2017. http://ndltd.ncl.edu.tw/handle/7d739m.
Повний текст джерела華梵大學
電子工程學系碩士班
105
For iterative learning control problem of unknown robotic systems with initial resetting errors, we propose a discrete fuzzy-neural adaptive iterative learning control (AILC) for freeway traffic flow systems with random initial resetting errors , iteration-varying desired traffic densities and random bounded off-ramp traffic volumes using traffic densities, space mean speeds and on-ramp waiting queues design. It is assumed that the system nonlinear functions and input gains are unknown for controller design. An adaptive fuzzy neural network (FNN) controller and an adaptive robust controller are applied to compensate for the unknown system nonlinearities and input gains, respectively. Moreover, to deal with the disturbances from random bounded off-ramp traffic volumes, a dead zone like auxiliary error with a time-varying boundary layer is introduced as a bounding parameter. This proposed auxiliary error is also utilized to construct the adaptive laws without using the bound of the input gain. The traffic density tracking error is shown to converge along the axis of learning iteration to a residual set whose level of magnitude depends on the width of boundary layer. Besides, since the nice desired traffic densities designed for the coordinated control objective of the AILC for freeway traffic flow systems are generally unknown, the improved bacterial forging optimization (IBFO) algorithm is used to optimize the fitness function, which is constructed by the coordinated control objective and includes (1) minimum total travel time, (2) minimum on-ramp average waiting time, and (3) minimum changes of desired traffic densities. Finally, a computer simulation example is used to verify the learning performance of the proposed fuzzy-neural AILC for freeway traffic flow systems using IBFO based desired traffic densities planning.
Huang, Jin-Yuan, and 黃進源. "The Study of hyperspectral imaging on Paddy Rice Image Classification through Comparison of Back-Propagation Neural Network and Bacterial Foraging Optimization." Thesis, 2016. http://ndltd.ncl.edu.tw/handle/cear4w.
Повний текст джерела嶺東科技大學
資訊管理系碩士班
104
The hyperspectral is an advanced material which render more accurately classification result. However, due to spectral information is very rich, the computation also takes more time. Therefore, if we can construct a decision system to accurately interpreting the surface of ground, it can be applied significantly to reduce manpower and time. This study focused on how to extract the important factors of hyperspectral image to classify the paddy rice area with applying supervised and unsupervised learning algorithm. In this study, back-propagation neural network and bacterial foraging optimization for hyperspectral image for image classification. The prior processing of image data used entropy-based classification to extract the influenced factors of image band properties. Then the two algorithms are applied into following four case studies: (a) the original band with a back-propagation neural network (b) entropy-base-classification filter out important information with back-propagation neural network (c) the original band with bacterial foraging optimization (d) entropy-base-classification filter out important information with bacterial foraging optimization. Finally, the error matrices are present and thematic maps are drawn among four cases and outcomes are compared.
YEN, HAN-TAO, and 顏翰濤. "The Study of Hyperspectral Imaging on Paddy Rice Image Classification through Particle Swarm Optimization with Linear Discriminant Analysis and Bacterial Foraging Optimization." Thesis, 2016. http://ndltd.ncl.edu.tw/handle/hdg4nb.
Повний текст джерела嶺東科技大學
資訊管理系碩士班
104
This study focused on how to extract the important from hyperspectral imaging spectral information. The techniques of image classification on paddy fields with supervised and unsupervised learning approaches. In this study, Linear Discriminant Analysis and bacterial foraging optimization for hyperspectral imagery for image classification. The preprocessing of Particle Swarm Optimization is used to extract the important influenced factor, and then design into the following four different case studies: ( a) the original band with Linear Discriminant Analysis (b) Particle Swarm Optimization filter out important information with Linear Discriminant Analysis (c) the original band with bacterial foraging optimization (d) Particle Swarm Optimization filter out important information with bacterial foraging optimization, finally using the error matrix and topic maps showing the results of the classification after comparison.