Feature spaces optimization plays a very important role in object recognition and categorization. After analyzing of several fashionable local features at present, some optimization algorithms based on the information...
详细信息
ISBN:
(纸本)9783037851036
Feature spaces optimization plays a very important role in object recognition and categorization. After analyzing of several fashionable local features at present, some optimization algorithms based on the information theory are proposed. In this paper, we describe the approaches to recognize generic objects using these features which have been optimized. As baselines for comparison, we also implemented some additional recognition systems using other optimization algorithms. The performance analysis on the obtained experimental results demonstrates that the proposed optimization algorithms are effective and efficient.
This paper first presents theoretical research on direct optimization using the Rotate-Vector (RV) algorithm which is suitable for the complex objects and valuable in engineering applications with global optimization ...
详细信息
ISBN:
(纸本)9780769547923
This paper first presents theoretical research on direct optimization using the Rotate-Vector (RV) algorithm which is suitable for the complex objects and valuable in engineering applications with global optimization ability. The derivation of the RV algorithm is illustrated in three-dimensional space and subsequently extended into multidimensional space. The numerical simulation utilizes this RV algorithm to optimize the parameters of a Proportional-Integral-Differential (PID) controller for an electro-hydraulic system. Simulation results show that the RV algorithm can solve optimization problems without calculating the function gradient.
According to research on the leveling principle of the telescopic handler fork, establishing relevant mathematical model to optimize the position of master cylinder with the optimization algorithm of accumulated error...
详细信息
ISBN:
(纸本)9783037852866
According to research on the leveling principle of the telescopic handler fork, establishing relevant mathematical model to optimize the position of master cylinder with the optimization algorithm of accumulated error, least square method, and multi-objective programming of method of weighting by using the computer language of VB. Then the position of fork got optimization that stabilizes the level of fork of telescopic handler.
Based on the standard particle swarm optimization, introduce the information about negative gradient to influence the update of velocities of the particles, proposed the particles swarm optimization with negative grad...
详细信息
ISBN:
(纸本)9783037853696
Based on the standard particle swarm optimization, introduce the information about negative gradient to influence the update of velocities of the particles, proposed the particles swarm optimization with negative gradient, and make the movement of particles more pertinent. The result of computer simulation about several test functions indicates that the particle swarm optimization with negative gradient can improve optimization efficiency and get better results.
In this paper we investigate capacity optimization mechanisms for multi-beam satellite systems built on a realistic payload model. The first proposed mechanism deals with long term traffic variations, for which capaci...
详细信息
ISBN:
(纸本)9781457720536
In this paper we investigate capacity optimization mechanisms for multi-beam satellite systems built on a realistic payload model. The first proposed mechanism deals with long term traffic variations, for which capacity optimization algorithms are proposed based on per-beam traffic requests. Due to the high asymmetry of the traffic, our algorithms provide time and spatial flexibility illuminating a specific set of beams within a window of several time-slots. Our algorithms maximize the amount of capacity actually offered while providing reduced power consumption. The second proposed mechanism deals with short-term traffic variations, for which we propose Network Coding (NC) based techniques at the link layer. The aim is to increase the offered capacity taking advantage of overlapping beam coverage, usually considered as a source of interference. This technique is meant to be applied not only in classical multi-beam systems, but also on top of the per-beam capacity optimization as a method to deal with fast traffic unbalances not evaluated in the first mechanism. Analysis and simulations results show that system capacity can be increased up to 13% in the first case and up to 90% in the second case.
This paper presents a comparative study of two popular Evolutionary algorithms (EA): Genetic algorithms (GA) and Particle Swarm optimization (PSO) for optimal tuning of Proportional Integral (PI) speed controller in P...
详细信息
ISBN:
(纸本)9783037852866
This paper presents a comparative study of two popular Evolutionary algorithms (EA): Genetic algorithms (GA) and Particle Swarm optimization (PSO) for optimal tuning of Proportional Integral (PI) speed controller in Permanent Magnet Synchronous Motor (PMSM) drives. Comparisons between the results obtained by GA method and those by improved PSO method are made. The experimental results show that the PSO method can locate the optimal or near optimal parameter space and achieve a higher quality solution than the GA method.
With the continuous development of Internet technology, accurate classification of network traffic becomes more and more important. Statistics-based traffic classification with extremely accuracy and high expansibilit...
详细信息
ISBN:
(纸本)9780769548524;9781467330930
With the continuous development of Internet technology, accurate classification of network traffic becomes more and more important. Statistics-based traffic classification with extremely accuracy and high expansibility has become the mainstream of this domain. However, this method also has some shortcomings, such as, overabundance of statistical features, and insufficient flexibility of feature vector. We propose an optimal feature vector extraction algorithm, which first extracts the optimal feature vector from original feature set before the classifier executes machine learning and classification, so as to achieve the objective of reducing the dimension of feature vector, saving the classifier's overhead of memory and computation, and improving the classifier's flexibility. Experimental results show that this algorithm can significantly decrease the dimension of original feature vector, while endowing classifier with more flexibility.
To decrease short-circuit current, adjusting the power network operation by breaking transmission lines is the most economic and convenient measure. For large power grid, breaking transmission lines has thousands of c...
详细信息
ISBN:
(纸本)9783037854969
To decrease short-circuit current, adjusting the power network operation by breaking transmission lines is the most economic and convenient measure. For large power grid, breaking transmission lines has thousands of combinations, so ifs very difficult to find the best combination in a short time. Firstly, this paper formulated the sensitivity relationship between transmission line outage and impedance change. Then preliminary combinations schemes of transmission line outage were selected according to the sensitivity. Index values of factors were given using the fuzzy control evaluation. Finally, this paper determined optimal scheme from maximum priority and accomplished the accessorial intelligent optimize system of limiting short-circuit current. The rapidity and rapidity of the proposed control strategy was verified by calculating the actual power grid.
The main steam temperature is always an important indicator of the boiler operation quality, high or low will affect the quality of boiler operation. At first, introduce a algorithm PSO, which can used to optimize the...
详细信息
ISBN:
(纸本)9783037855300
The main steam temperature is always an important indicator of the boiler operation quality, high or low will affect the quality of boiler operation. At first, introduce a algorithm PSO, which can used to optimize the PID parameters of a main steam temperature control system. Then, improved the PSO, and studied a kind of improved particle swarm algorithm quantum apply quantum-behaved particle swarm optimization (QPSO). And this algorithm is used to optimize the PID parameters of a main steam temperature control system, got the best parameters. In the end, simulation result shows that, compared with basic particle swarm optimization (PSO),QPSO can make main steam temperature control system has a better control of quality, and improves the system of static and dynamic characteristics.
This paper describes a theoretical approach to evaluate the uncertainty on the series and shunt resistances estimated by the seven-parameter (double diode) model of a photovoltaic (PV) cell using data commonly provide...
详细信息
This paper describes a theoretical approach to evaluate the uncertainty on the series and shunt resistances estimated by the seven-parameter (double diode) model of a photovoltaic (PV) cell using data commonly provided by panel manufacturers, measured environmental parameters, and semiempirical equations. After a brief survey on the state of the art and the treatment of the double-diode model, the procedure proposed by the authors, to estimate the unknown parameters, is illustrated. The theoretical expression of the uncertainty, which affects the estimation of the series and shunt resistances (namely, R-s and R-sh) of a PV cell, is then derived. A statistical analysis performed by means of a Monte Carlo simulation is in agreement with the theoretical expression of the uncertainty.
暂无评论