Remote sensing image classification based on optimized support vector machine

An improved hybrid particle swarm optimization algorithm based on adaptive inertia weight is proposed for job shop scheduling problem(JSSP). In order to overcome the shortcomings of the standard particle swarm optimization algorithm(PSO) in the optimization process, such as slow iteration speed, low precision and easy to fall into local optimal, simulated annealing algorithm(SA) and PSO are combined(SAPSO); In order to balance the global search ability and local search ability of particles, the adaptive weight of each particle is dynamically adjusted in this paper. The improved hybrid algorithm utilizes the probabilistic mutation capability of SA, which can accept both the good solution and the bad solution with a certain probability when accepting the new solution, and can get rid of the local optimal solution of the algorithm, which not only improves the flexibility and diversity of the algorithm, but also improves the diversity of particles. Adding adaptive weight to improve inertia weight in PSO makes it possible to dynamically adjust parameter factors according to fitness. Finally, the feasibility and efficiency of the improved algorithm are verified by the standard examples of JSSP.

In order to improve the stability and sensitivity of particle swarm optimization (PSO) algorithm and to solve the problem of premature convergence, in this re-search, a computer PSO algorithm based on thermodynamic motion mechanism is proposed based on the principle of thermodynamic motion mechanism. Firstly, the thermodynamic motion phenomenon, the diffusion law in kinematics and the standard PSO algorithm are introduced. Then, according to the basic idea of thermodynamic motion mechanism, the standardized PSO algorithm is optimized and its optimization process is introduced. Finally, the experimental results are analysed by setting the test function. The results show that among the five test functions, the computer PSO algorithm based on thermodynamic motion mechanism has a higher probability of jumping out of the local optimal solution. Its robustness and stability are much better than standard PSO algorithms. The evolution ability of the computer PSO algorithm based on thermodynamic motion mechanism is better than that of the standard PSO algorithm. The standard PSO algorithm is superior because it is based on thermodynamic motion mechanism. The research in this paper can provide good guidance for improving the performance of PSO algorithm.

This paper proposes two improved algorithms, the DE-PSO algorithm, which combines differential evolution and phased strategy, and the hybrid particle swarm optimization algorithm integrating whale algorithm (WOAPSO), which combines the whale optimization mechanism. Compared to traditional calibration methods (such as the Newmark three- and two-parameter methods), which rely on empirical simplified models, adapting them to the complex seismic nonstationarity and multipeak characteristics is difficult. However, although intelligent optimization algorithms, such as particle swarm optimization (PSO) and differential evolution (DE) have improved calibration accuracy in recent years, insufficient convergence stability and low computational efficiency, among other problems, persist. Therefore, based on experiments, the performances of these algorithms were compared with those of standard PSO, traditional DE, and other algorithms. The results demonstrate the significant superiority of DE-PSO and WOAPSO. In 50 repeated experiments, the fitness standard deviation (STD) was significantly reduced, and the algorithms achieved rapid convergence by the mid-iteration stage, which effectively resolves the issues of premature convergence and local oscillation tendencies inherent in the standard Particle Swarm Optimization algorithm. Regarding the key parameters (Tg, βmax, γ) of the standard, the STD of the improved algorithm approached zero, verifying its strong adaptability to multimodal optimization problems. Furthermore, the DE-PSO algorithm had the best performance in balancing computational efficiency and stability, with a convergence speed that is three times faster than that of standard DE algorithm while maintaining the lowest parameter volatility. This study provides an efficient algorithmic tool for the rapid analysis of strong motion records and the efficient calibration of design response spectra, which has implications for the seismic optimization design of complex structures and can be guided by regulations, contributing to engineering seismic practice.

Aiming at the problem that the standard particle swarm optimization algorithm (PSO) is easy to fall into local convergence so quickly, and the convergence speed is slow, a new optimization algorithm combining PSO, Beetle Antennae Search Algorithm and Genetic Algorithm is proposed in this paper First, the improved sigmoid function is introduced to form a nonlinear function relation between the learning factor and the step size of the particle swarm optimization algorithm, which can effectively increase the convergence speed. Second, in order to maintain the diversity of the population, the crossover operation and mutation operation of genetic algorithm are introduced to improve the global search ability of the algorithm. In order to verify the performance of the new optimization algorithm, the average fitness values of the four standard test functions in different dimensions are compared to and the corresponding optimal values. The simulation results show that the new algorithm not only improves the premature convergence of the traditional particle swarm optimization algorithm, but also improves the optimization efficiency.KeywordsParticle swarm optimizationBeetle antennae search algorithmLearning factorCrossover and mutation

Genetic algorithms all the methods used to solve the Traveling Agent (TSP) problem, the use of genetic algorithms on TSP problems is more common than other methods, and it is also possible to achieve global search and obtain the best values. Compared with the traditional genetic algorithm, the particle swarm algorithm is not only easy to be applied, but also can be widely used because of the function of rapid search, but at the same time, the shortcomings of the traditional standard particle swarm algorithm are more prominent, and it is easy to fall into the situation of optimal solution of local problems. So first of all, we use the classical TSP algorithm to propose a mixed particle swarm algorithm, which solves the TSP problem by using the selection, crossover, variation and other operators of the traditional genetic algorithm, and through the conclusion of the solution, it can be shown that the method not only greatly improves the search function of the traditional standard particle swarm, but also greatly improves the convergence speed while obtaining the approximate optimal solution.

In order to overcome the drawbacks of falling into local extremum and lower optimization precision of standard particle swarm optimization (PSO) algorithm, multipopulation strategy, adaptive dynamic adjustment strategy and co-evolution mode are introduced into the standard PSO algorithm in order to propose an improved coevolutionary PSO(MPACEPSO) algorithm based on multi-strategy evolution mode and multi-population co-evolutionary mechanism. In the evolutionary process of MPACEPSO algorithm, the multi-population strategy is used to divide the population into several subpopulations, which use different co-evolutionary model to evolve. These sub-populations are influenced and promoted each other in order to realize the exchange of information and co-evolution among the sub-populations, improve the convergence speed and search precision of MPACEPSO algorithm, and effectively suppress the appearance of the local optimum. The adaptive dynamic adjustment strategy of inertia weight is used to keep the diversity of population, reduce the probability of falling into the local extremum. Finally, the ZDT functions are selected to test the optimization performance of proposed MPACEPSO algorithm. The experimental results show that the proposed MPACEPSO algorithm has faster convergence speed, stronger global search ability, higher solving precision and better dynamic optimization performance. The experimental result analysis shows that the proposed MPACEPSO algorithm is insensitive to parameters and easy to be used in solving the complex optimization problems.

Recently, the issue of food authentication has gained attention, especially halal authentication, because of cases of pork adulteration in beef. Many studies have developed rapid detection for adulterated meat. However, these studies are not yet practical and economical methods and instruments and a faster analysis process. In this context, this paper proposes the Optimized Electronic Nose System (OENS) for more accurately detecting pork adulteration in beef. OENS has advantages such as proper noise filtering, an optimized sensor array, and optimized support vector machine (SVM) parameters. Noise filtering is carried out by cross-validation with different mother wavelets, i.e., Haar, dmey, coiflet, symlet, and Daubechies. The sensor array was optimized by dimension reduction using principal component analysis (PCA). An algorithm is proposed for the optimization of the SVM parameters. An experiment was conducted by analyzing seven classes of meat, comprising seven different mixtures of beef and pork. The first and seventh classes were 100% beef and 100% pork, respectively, while the second, third, fourth, fifth, and sixth classes contained 10%, 25%, 50%, 75%, and 90% of beef in a sample of 100 grams, respectively. Sample testing was carried out for 15 minutes for each sample. The classification test results to detect beef and pork had an accuracy of 98.10% using the optimized support vector machine. Thus, OENS has a favorable performance to detect pork adulteration in beef for halal authentication.

In this paper, we present a Hybrid Particle Swarm Optimization (HPSO) algorithm that combines the Particle Swarm Optimization (PSO) algorithm with the Genetic Algorithm (GA) method. The algorithm is used for investigating the plastic deformation behavior of titanium alloy (Ti-6Al-4V) in a multi-hole extrusion process. The simulation used rigid-plastic finite element (FE) DEFORMTM-3D software to obtain the minimum mandrel bias angle and exit tube bending angle. Results of the simulation indicate that these two angles were significantly less than 0.3 degrees, suggesting that metaheuristic algorithms based on HPSO and FE analysis could be used for general multi-hole extrusion processes.KeywordsMulti-hole extrusionParticle Swarm OptimizationFinite elementGenetic Algorithm

As peer-to-peer (P2P) technology booms lots of problems arise such as rampant piracy, congestion, low quality etc. Thus, accurate identification of P2P traffic makes great sense for efficient network management. As one of the optimal classifiers, support vector machine (SVM) has been successfully used in P2P traffic identification. However, the performance of SVM is largely dependent on its parameters and the traditional tuning methods are inefficient. In the paper, a novel hybrid method to optimize parameters of SVM based on cuckoo search algorithm combined with particle swarm optimization algorithm is proposed. The first stage of the proposed approach is to tune the best parameters for SVM with training data. Subsequently, the SVM configured with the best parameters is employed to identify P2P traffic. In the end, we demonstrate the effectiveness of our approach on-campus traffic traces. Experimental results indicate that the proposed method outperforms SVM based on genetic algorithm, particle swarm optimization algorithm and cuckoo search algorithm.

The Particle swarm optimization (PSO) algorithm is a population-based intelligent stochastic search technique encouraged from the intrinsic manner of bee swarm seeking for their food source. With flexibility for numerical experimentation, the PSO algorithm has been mostly used to resolve diverse kind of optimization problems. The PSO algorithm is frequently captured in local optima meanwhile handling the complex real-world problems. Many authors improved the standard PSO algorithm with different mutation strategies but an exhausted comprehensive overview about mutation strategies is still lacking. This article aims to furnish a concise and comprehensive study of problems and challenges that prevent the performance of the PSO algorithm. It has tried to provide guidelines for the researchers who are active in the area of the PSO algorithm and its mutation strategies. The objective of this study is divided into two sections: primarily to display the improvement of the PSO algorithm with mutation strategies that may enhance the performance of the standard PSO algorithm to great extent and secondly, to motivate researchers and developers to use the PSO algorithm to solve the complex real-world problems. This study presents a comprehensive survey of the various PSO algorithms based on mutation strategies. It is anticipated that this survey would be helpful to study the PSO algorithm in detail for researchers.

Parameters of support vector machines (SVM) which is optimized by standard genetic algorithm is easy to trap into the local minimum, in order to get the optimal parameters of support vector machine, this paper proposed a parameters optimization method for support vector machines based on improved genetic algorithm, the simulation experiment is carried out on 5 benchmark datasets. The simulation show that the proposed method not only can assure the classification precision, but also can reduce training time markedly compared with standard genetic algorithm. DOI : http://dx.doi.org/10.11591/telkomnika.v12i1.3182

A large project in a company is often divided to several subtasks, which would be assigned to different people with variant abilities to the same task. So whether the tasks are scheduled properly would determine the quality or the efficiency of team collaboration. A hybrid particle swarm optimization (PSO) algorithm is putted forward. Subtasks are disassembled from the project by using the task tree relations, and the tree structure is modeled into a task matrix. Moreover, task-time matrix is used to indicate the people abilities to complete the tasks. Then the hybrid algorithm was presented, in which simulated annealing method is added in particle swarm optimization to improve the capability of seeking the best allocating results. Finally, a simulation experiment is carried out by using the proposed algorithm, the comparing results show that the convergent velocity is fast and the optimizing ability is preferable.

In this paper, a hybrid algorithm based on Particle Swarm Optimization (PSO) and Cuckoo Search (CS) is detailed with the application of Optimal Reactive Power Dispatch (ORPD). The Levy flight and the elimination mechanism are introduced to the traditional PSO algorithm. Benchmark tests show that the hybrid algorithm has better optimization efficiency than original PSO and CS algorithms. In the application of the ORPD, the fitness function is the total real loss of the distribution network. Inequality constrains are handled by the limitation of searching space. The simulation results on the IEEE-14 bus standard system and a real distribution network illustrate the feasibility and effectiveness of the algorithm. The total real power losses decrease 7.1% and 8% in two applications. The mathematical tests and engineering applications demonstrate that the hybrid algorithm has better searching ability than the standard PSO algorithm, and it is suitable for the solution of ORPD problem.

Identifying protein arginine methylation sites using global features of protein sequence coupled with support vector machine optimized by particle swarm optimization algorithm

Neural Network system for SoC is one topic in the world. Recently, SoC began to combine AI technique by Python. When developers consider Intelligent system on SoC, the co-design software and hardware are significant. In this case, small devices and embedded system are target system. For IoT, those techniques will grow up in the world. Those cases, avoiding premature convergence while keeping performance is a challenge in training the neural network, especially in a case of large NNs or a large number of training data. In this case, one problem is a huge memory and processing power. For tiny memory and processing system as SoC, we propose an improved particle swarm optimization (PSO) algorithm called the PSOseed2 algorithm for training NN. The PSOseed2 algorithm solves the premature convergence of the standard PSO (SPSO) algorithm by slightly modifying the velocity update function without adding many computational tasks to the SPSO algorithm. We evaluated this algorithm on field programmable gate array (FPGA)-based NN and software-based NN and trained these NNs with different PSO algorithms that are SPSO, PSOseed, PSOseed2, and dissipative PSO. Experimental results with different datasets confirmed that the NNs trained by the proposed PSOseed2 algorithm had better recognition rates and lower global learning errors than the NN trained by other PSO algorithms. In this talk, I would like to talk those relational research in the world and our results and discussion.