Understanding the biomechanical behavior of the human body in different conditions of locomotion can be very advantageous for many purposes, such as developing the humanoid robots. With this approach, the aim of this ...
详细信息
ISBN:
(纸本)9781538657034
Understanding the biomechanical behavior of the human body in different conditions of locomotion can be very advantageous for many purposes, such as developing the humanoid robots. With this approach, the aim of this study is investigating the nonlinear stiffness behavior of the calf muscle and the exerted ground reaction force (GRF) during running. For this purpose, a new active model of human body is proposed, which the distinctive features of this model are as follows: 1) The simulation model is considered to be five degrees of freedom (5-DOF) by using the standard solid model to simulate the calf muscle;2) The optimum values of the considered mechanical parameters are obtained using the particleswarmoptimization (PSO) algorithm;3) The stiffness of the calf muscle is considered to be nonlinear and active, which is appropriately formulated with regard to the viscoelasticity nature of the calf muscle. This model is tested for two types of hard and soft shoes, and validated by the results of previous studies. Then the effects of different conditions of body mass distribution, touchdown velocities, and different types of shoes on the GRF are investigated and discussed. The results of this study can be used in producing and development of humanoid robots, artificial limbs, etc.
In this paper a new approach to selection of the optimal parameters values for the SMOTE (Synthetic Minority Over-sampling Technique) algorithm in the problem of the SVM (Support Vector Machine) classification of imba...
详细信息
ISBN:
(纸本)9781509067428
In this paper a new approach to selection of the optimal parameters values for the SMOTE (Synthetic Minority Over-sampling Technique) algorithm in the problem of the SVM (Support Vector Machine) classification of imbalanced datasets has been suggested. This approach allows reducing the time expenditures for the search of the optimum parameters values of the SMOTE algorithm. The experimental results show that the offered approach allows increasing the classification quality of the SVM classifier.
Aiming at the problem that path planning for automatic handling robot in an environment with obstacles, the working environment model of the handling robot is analyzed. And then a path optimizationalgorithm based on ...
详细信息
ISBN:
(纸本)9781614997856;9781614997849
Aiming at the problem that path planning for automatic handling robot in an environment with obstacles, the working environment model of the handling robot is analyzed. And then a path optimizationalgorithm based on fusing ant colony and particle swarm optimization algorithm is proposed. First of all, this algorithm uses the global search ability of particleswarm to go on a rough search and quickly plans the starting point to the end of the initial path. Then, the pheromone distribution is performed on the initial path. Finally, the ant colony algorithm is used to search the path carefully to get the optimal path. Experimental verification shows that compared with a single ant colony or particle swarm optimization algorithm, fused algorithm about ant colony and particleswarmoptimization has a significant improvement in the number of iterations and path planning.
Recently, fault indicators with communication function have been increasingly used in fault diagnosis of distribution networks. In this paper, an objective function which considers the reliability index of the distrib...
详细信息
ISBN:
(纸本)9781538611272
Recently, fault indicators with communication function have been increasingly used in fault diagnosis of distribution networks. In this paper, an objective function which considers the reliability index of the distribution network and economic factors synthetically has been proposed for optimal placement of fault indicators in distribution networks, and binary particle swarm optimization algorithm is used for solving the optimization problem. The validity of the proposed model is verified by testing on the IEEE-33 node distribution system. The test results show that there is no need to install too many fault indicators in distribution networks and reasonable choice of the number and location of the fault indicator can achieve the comprehensive optimization of distribution network reliability and economy. At the same time, the results and processes of optimization are compared with those obtained by immune algorithm, the result shows that binary particle swarm optimization algorithm is better because of its fast convergence speed and less iteration times, which is an advantage for solving this optimal allocation problem.
This paper proposes a new intelligent particleswarmoptimization (PSO) based method for design of optimal fractional order fuzzy PID (FOFPID) controller with simultaneous auto-tuned fuzzy control rules and membership...
详细信息
ISBN:
(纸本)9781509043309
This paper proposes a new intelligent particleswarmoptimization (PSO) based method for design of optimal fractional order fuzzy PID (FOFPID) controller with simultaneous auto-tuned fuzzy control rules and membership functions. In the proposed method the parameters of FOFPID controller including input scaling factors, output scaling factors, fractional order of derivative and integrator, fuzzy rule base and membership functions are considered as tuning parameters and optimized simultaneously using PSO algorithm. Moreover, to reduce the fuzzy system design effort and computational complexity, a novel simultaneous tuning approach is proposed for determining the membership functions and fuzzy rule base. The newly suggested design approach provides a flexible controller with simple structure and straightforward algorithm. To evaluate the effectiveness of the proposed method, the proposed FOFPID controller is applied to solve the Load Frequency Control (LFC) problem in a representative power system with considerations governor saturation and the results are compared to the one obtained by a FOFPID controller with fixed fuzzy part and a fractional order PID (FOPID) controller. Simulation results indicate the superiority of proposed method.
Because the network intrusion behaviors are characterized with uncertainty, complexity and diversity, an intrusion detection method based on neural network and particle swarm optimization algorithm (PSOA) is presented...
详细信息
ISBN:
(纸本)9781424451821
Because the network intrusion behaviors are characterized with uncertainty, complexity and diversity, an intrusion detection method based on neural network and particle swarm optimization algorithm (PSOA) is presented in this paper. The novel structure model has higher accuracy and faster convergence speed. We construct the network structure, and give the algorithm flow. We discussed and analyzed the impact factor of intrusion behaviors. With the ability of strong self-learning and faster convergence, this intrusion detection method can detect various intrusion behaviors rapidly and effectively by learning the typical intrusion characteristic information. Utilizing the character that rough set can keep the discern ability of original dataset after reduction, the reduces of the original dataset arc calculated and used to train neural network, which increase the detection accuracy. We apply this technique on KDD99 data set and get satisfactory results. The experimental result shows that this intrusion detection method is feasible and effective.
The last decade has witnessed a great interest in using evolutionary algorithms, such as genetic algorithms, evolutionary strategies and particleswarmoptimization (PSO), for multivariate optimization. This paper pre...
详细信息
ISBN:
(纸本)9781424481262
The last decade has witnessed a great interest in using evolutionary algorithms, such as genetic algorithms, evolutionary strategies and particleswarmoptimization (PSO), for multivariate optimization. This paper presents a hybrid algorithm for searching a complex domain space, by combining the PSO and orthogonal design. In the standard PSO, each particle focuses only on the error propagated back from the best particle, without "communicating" with other particles. In our approach, this limitation of the standard PSO is overcome by using a novel crossover operator based on orthogonal design. Furthermore, instead of the "generating-and-updating" model in the standard PSO, the elitism preservation strategy is applied to determine the possible movements of the candidate particles in the subsequent iterations. Experimental results demonstrate that our algorithm has a better performance compared to existing methods, including five PSO algorithms and three evolutionary algorithms.
In this paper, a Two Sub-swarms Quantum-behaved particle swarm optimization algorithm Based on Exchange Strategy (TS-QPSO) is proposed. Two sub-swarms of particles with quantum Behavior are set up in TS-QPSO. Once the...
详细信息
ISBN:
(纸本)9780769540207
In this paper, a Two Sub-swarms Quantum-behaved particle swarm optimization algorithm Based on Exchange Strategy (TS-QPSO) is proposed. Two sub-swarms of particles with quantum Behavior are set up in TS-QPSO. Once the whole swarm falls into local optima and the best value of the global swarm is not improved after the allowable iterations, the exchange strategy will be carried out. The amount of exchange particles is different in each searching phase. In this way, the population diversity can be improved greatly and the problem that falling into local optima can be avoided effectively. Experiment results show that the overall performance of TS-QPSO is superior to QPSO algorithm and TSPSO algorithm.
Existing virtual network mapping algorithms does not consider resource consumption of intermediate node on communication path usually. Minimum resource consumption or shortest path of physical network is regarded as o...
详细信息
ISBN:
(纸本)9781510821279
Existing virtual network mapping algorithms does not consider resource consumption of intermediate node on communication path usually. Minimum resource consumption or shortest path of physical network is regarded as objective, thereby leading to bottleneck due to insufficient resource of intermediate node on communication path, and affecting performance of the whole physical network and subsequent success rate of virtual network. A virtual network mapping algorithm based on load balancing multi-objective particleswarmoptimization is proposed in the paper aiming at the problem. Resource consumption of intermediate node is sufficiently considered in the algorithm, double balance of node load and link load is regarded as objective. Meanwhile, the optimal path of particle swarm optimization algorithm is adopted. Experiments show that the algorithm proposed in the paper can not only realize double balance of node load and link load, but also effectively improve request receiving success rate, overall resource load balance and long-term operation income.
in this paper,through the research of the existing particle swarm optimization algorithm and its improved algorithm,a particle swarm optimization algorithm improvement program is proposed,and the experimental results ...
详细信息
in this paper,through the research of the existing particle swarm optimization algorithm and its improved algorithm,a particle swarm optimization algorithm improvement program is proposed,and the experimental results show that this improved algorithm not only does not increase the complexity,but also has greater improvement in the convergence speed and stability comparing with the original algorithm.
暂无评论