Content uploaded by Hui Wei
Author content
All content in this area was uploaded by Hui Wei on Mar 19, 2015
Content may be subject to copyright.
A preview of the PDF is not available
A Genetic-Algorithm-Based Explicit Description of Object Contour and its Ability to Facilitate Recognition
Abstract and Figures
Shape representation is an extremely important and longstanding problem in the field of pattern recognition. Closed contour, which refers to shape contour, plays a crucial role in the comparison of shapes. Because shape contour is the most stable, distinguishable, and invariable feature of an object, it is useful to incorporate it into the recognition process. This paper proposes a method based on genetic algorithms. The proposed method can be used to identify the most common contour fragments, which can be used to represent the contours of a shape category. The common fragments clarify the particular logics included in the contours. This paper shows that the explicit representation of the shape contour contributes significantly to shape representation and object recognition.
Figures - uploaded by Hui Wei
Author content
All figure content in this area was uploaded by Hui Wei
Content may be subject to copyright.
... Unfortunately, the parameters of PMSG are different under different operating conditions [4], and this will prevent the controller from working well and may even cause malfunctions, therefore, the precise estimation of the parameters is essential. Online parameter estimation methods mainly include: extended Kalman filter algorithm [5,6], model reference adaptive system [7,8], least square method [9,10], neural network [11,12], genetic algorithm [13,14], observer-based method [15], etc. In [5], the extended Kalman filter method (EKF) is often satisfied. ...
... Refs. [13,14] proposed genetic algorithm (GA) to estimate parameters, this method has smaller error and eliminates the need for a priori knowledge of machine parameters, but it suffers from premature and computational problems, moreover, the problem of the equation being underranked is ignored. The observer-based method in [15] has better performance in estimating parameters, however, the robustness is not enough when dealing with strongly coupled problems with parameters. ...
... where μ and ν follow a Gaussian distribution, they can be expressed as (14) ∼ ...
A novel parameter estimation method is proposed for the permanent magnet synchronous generator (PMSG), which is implemented by an enhanced self‐learning particle swarm optimization algorithm with Levy flight (SLPSO), and the problem of lower parameter estimation precision of standard PSO is obviated. This method injects currents of different intensities into the d‐axis in a time‐sharing manner to solve the problem of equation under‐ranking, and the mathematical model for full‐rank parameter estimation is developed. The speed term of PSO is simplified to expedite the convergence of PSO, and a strategy with chaotic decline for the inertia weight of PSO is adopted to strengthen its ability to jump out of the local optimum. Moreover, the self‐learning dense fleeing strategy (SLDF) is proposed where particles perform diffusion learning based on population density information and Levy flight, the evolutionary unitary problem and human intervention in the evolutionary process is averted. Furthermore, the memory tempering annealing algorithm (MTA) and greedy algorithm (GA) is integrated into the algorithm, MTA can facilitate the exploration of potentially better regions, and GA for local optimization enhances the convergence speed and accuracy in late stage of the algorithm. Comparing the proposed method with several existing PSO algorithms through simulation and experiments, the experimental data show that the proposed method can effectively track variable parameters under different working conditions and has better robustness.
... Ω is the full space of system state x. By substituting Equations (22) and (23) into Equation (25) taking the derivatives of continuous random variable x i and parameters i and i of the OS-PDF, and setting these derivatives to zero, the following solution can be obtained: ...
... The genetic algorithm (GA) is a kind of random optimization algorithm that was first proposed by American computer expert John Holland in the early 1960s [22]. Genetic algorithms are based on the principles of natural selection and genetics and can effectively obtain the global optimal solutions of general optimization problems. ...
Ice storm disasters pose great challenges to the safe and stable operation of transmission systems, especially in high‐renewable‐integration scenarios. However, as one of the major types of natural disasters that can have severe consequences, ice storm disasters are much less studied than hurricanes and earthquakes. Ice storm disasters are characterized by a long duration and wide scope, which affect the source, network, and load side of the power grid. It is difficult to formulate a quantitative evaluation of resilience and establish effective planning strategies. Here, a resilient planning method considering the interactive effects of ice disasters on sources, networks, and loads is therefore proposed. First, the two‐stage Monte Carlo method is used to generate multiple grid fault scenarios for different levels of ice storm disasters. Then, an index is proposed to quantify the grid resilience as the total amount of system power loss caused by ice storm disasters. Based on this approach, a two‐layer mathematical model is established with grid resilience and total investment cost objectives in each fault scenario. Hierarchical reinforcement and the protection of generating units and transmission lines are selected as investment strategies to mitigate the impact of ice storm disasters. Finally, the IEEE‐24 node transmission system is used to verify the feasibility and effectiveness of the proposed method. Optimizing the planning strategy can significantly improve system resilience with minimal investment cost.
... Online parameter estimation methods mainly include: extended Kalman filter algorithm [5][6], model reference adaptive system [7][8], least square method [9][10], neural network [11][12], genetic algorithm [13][14], observer-based method [15], etc. In [5][6], the extended Kalman filter method (EKF) is often used to estimate the resistance and flux linkage parameters of the generator, but its computation of matrix is relatively larger and the appropriate Q and R matrices are not easy to choose. ...
... The algorithm has high accuracy, but if the tuning criterion is not implemented properly, the method will fall into a local minimum or overfitting. [13][14] proposed genetic algorithm (GA) to estimate parameters, this method has smaller error, but suffers from premature and computational problems. Moreover, the problem of the equation being under-ranked is ignored. ...
A novel parameter estimation method is proposed for the permanent magnet synchronous generator (PMSG), which is implemented by an enhanced self-learning particle swarm optimization algorithm with Levy flight (SLPSO), and the problem of lower parameter estimation precision of standard PSO is obviated. This method injects currents of different intensities into the d-axis in a time-sharing manner to solve the problem of equation under-ranking, and the mathematical model for full-rank parameter estimation is developed. The speed term of PSO is simplified to expedite the convergence of PSO, and a strategy with Chaotic decline for the inertia weight of PSO is adopted to strengthen its ability to jump out of the local optimum. Moreover, the self-learning dense fleeing strategy (SLDF) is proposed where particles perform diffusion learning based on population density information and Levy flight, the evolutionary unitary problem and human intervention in the evolutionary process is averted. Furthermore, the memory tempering annealing algorithm (MTA) and greedy algorithm (GA) is integrated into the algorithm, MTA can facilitate the exploration of potentially better regions, and GA for local optimization enhances the convergence speed and accuracy in late stage of the algorithm. Comparing the proposed method with several existing PSO algorithms through simulation and experiments, the experimental data show that the proposed method can effectively track variable parameters under different working conditions and has better robustness.
... As a global optimization algorithm, a genetic algorithm [32][33][34] does not easily fall into the trap of a local minimum. erefore, a genetic algorithm is used as an optimization tool to optimize the SLL of the antenna pattern. ...
The sidelobe level (SLL) is an essential performance factor for satellite communication antennas. A low-SLL design can effectively suppress adjacent satellite interference. A low-SLL design method for a variable inclination continuous transverse stub (VICTS) antenna is proposed in this paper. The VICTS antenna is composed of three rotatable parts: a feeding plate, a radiation plate, and a polarization plate. The radiation plate comprises two groups of stubs with different radiation ratios. Combined with the nonlinear slow-wave structure attached to the feeding plate, the radiation ratio of the unit can be adjusted. The aperture field of the VICTS antenna using this method can be tapered in order to suppress the SLL. To verify the effectiveness of this method, the antenna prototype is fabricated and measured in a microwave anechoic chamber. The simulation and the measurement are in good agreement. The reflection coefficient of the antenna is kept below −15 dB and between 13.75 GHz and 14.5 GHz. When the radiation plate and the feeding plate rotate relative to each other, the pattern beam can be scanned from 5° to 70°. In the scanning range, the typical SLL can reach −18 dB.
Concrete is indispensable in contemporary industry, and the weighing of aggregates directly determines the quality of concrete preparation. In response to the difficulty of traditional methods in meeting the industrial requirements for accuracy, efficiency, and cost of measurement, this paper proposes a non-contact bone pile weight measurement method based on binocular vision. Firstly, the on-site image is obtained through a binocular camera, and the camera parameters are used to improve the image edge information and preprocess the image. Then, the improved semi global matching (SGM) algorithm is used to improve computational efficiency, obtaining three-dimensional information of the aggregate pile for volume calculation. Based on the watershed algorithm and T-S inference, the aggregate clearance rate is calculated, and the initial volume is corrected. Finally, a linear relationship is established between the density of the aggregate pile and the clearance rate, and the weight of the aggregate pile can be obtained by the density formula. The experimental results on different sizes of aggregate piles shows that the average error of the experiment is less than 4%. Efficiency of improved SGM matching algorithm has increased several times compared to the original algorithm, providing a low-cost and efficient measurement method for industrial aggregate weighing.
Multilevel inverters are increasingly being employed for industrial applications, such as speed control of motors and grid integration of distributed generation systems. The focus is on developing topologies that utilize fewer lower-rating switches and power sources while working efficiently and reliably. This work pertains to developing a three-phase multilevel inverter that employs switching capacitors and a single DC power supply that produces a nine-stage, three-phase voltage output. A recently proposed powerful meta-heuristic technique called symbiotic organism search (SOS) has been applied to identify the optimum switching angles for Selective Harmonic Elimination (SHE) from the output voltage waveform. A thorough converter analysis has also been done in the MATLAB/SIMULINK environment and is validated with the real-time hardware-in-the-loop (HIL) experiment results.
This paper proposes a new reconfigurable intelligent surface based three-dimensional beam tracking method to solve the beam tracking problems for the unmanned aerial vehicle with obstacles in communication channels. The proposed beam tracking method can not only regulate the reconfigurable intelligent surfaces to achieve the beam tracking of the obstructed communications, but also optimize the transmission efficiency of the communication. Firstly, a reconfigurable intelligent surface is proposed, which can correlate the transmission signals by adjusting the phase-shift matrix. Meanwhile, a new communication channel is constructed according to the reconfigurable intelligent surface, which consists of two parts. The first one is the channel between the unmanned aerial vehicle and the reconfigurable intelligent surface, the other is the channel between the reconfigurable intelligent surface and the ground base station. Note that the transmission performance of the communications can be optimized by adjusting the phase shift of each uniform linear array on the reconfigurable intelligent surface. Then, a new beam tracking method for the unmanned aerial vehicle with obstructed communications is proposed on the basis of the reconfigurable intelligent surface. By proposing the mixed genetic algorithm, the estimation accuracy of the azimuth and elevation angles is improved to enhance the performance of the beam tracking. Finally, the simulations are provided to verify the effectiveness of the proposed three-dimensional beam tracking method with reconfigurable intelligent surface.
Orientation detection is an important step in image understanding. Simple cells in the primary visual cortex are sensitive to stimuli of specific orientation. Hubel and Wiesel's classical theory attributes orientation selection in a simple cell to the aligned receptive fields of the retinal ganglion cells and the lateral geniculate nucleus cells. It is hypothesized that these receptive fields are similar in size and sub-structure. Current anatomical and electrophysiological evidence is not sufficient to support this geometric-arrangement-based model. Additionally, this feedforward model is incomplete in the implementation details of neural computation. The proposed algebraic model satisfies local constraints from afferent neurons and estimates the orientation of the stimulus. This constraint satisfaction based approach achieves desirable results on challenging image dataset, and can also be used to explain visual illusions.
The feedforward model proposed by Hubel and Wiesel partially explained orientation selectivity in simple cells. This classical hypothesis attributed orientation preference to idealized alignment of geniculate cell receptive fields. Many scholars have been either revising this model or putting forward new theories to account for more related phenomenon such as contrast invariant tuning. None of the previous neural models is complete in implementation details or involves strict computational strategies. This paper mathematically studied a detailed but vital question which has long been neglected: the possibility of massive variable-sized, unaligned geniculate cell receptive fields producing the orientation selectivity of a simple cell. The response curve of each afferent neuron is fully utilized to obtain a local constraint and a group-decision making approach is then applied to solve the constraint satisfaction problem. Our new model does not achieve just consistent experimental results with physiological data, but consistent interpretations of several illusions with observers' perceptions. The current work, which supplemented the previous models with necessary computational details, is based on ensemble coding in essence. This underlying mechanism helps to understand how visual information is processed in from the retina to the cortex.