scholarly journals Software Defect Prediction Based on Hybrid Swarm Intelligence and Deep Learning

2021 ◽  
Vol 2021 ◽  
pp. 1-17
Author(s):  
Zhen Li ◽  
Tong Li ◽  
YuMei Wu ◽  
Liu Yang ◽  
Hong Miao ◽  
...  
Keyword(s):  
Deep Learning ◽  
Swarm Intelligence ◽  
Hybrid Algorithm ◽  
Fitness Function ◽  
Optimal Solution ◽  
Particle Swarm Algorithm ◽  
Hybrid Swarm ◽  
Hyperparameter Optimization ◽  
Advantages And Disadvantages ◽  
Swarm Algorithm

In order to improve software quality and testing efficiency, this paper implements the prediction of software defects based on deep learning. According to the respective advantages and disadvantages of the particle swarm algorithm and the wolf swarm algorithm, the two algorithms are mixed to realize the complementary advantages of the algorithms. At the same time, the hybrid algorithm is used in the search of model hyperparameter optimization, the loss function of the model is used as the fitness function, and the collaborative search ability of the swarm intelligence population is used to find the global optimal solution in multiple local solution spaces. Through the analysis of the experimental results of six data sets, compared with the traditional hyperparameter optimization method and a single swarm intelligence algorithm, the model using the hybrid algorithm has higher and better indicators. And, under the processing of the autoencoder, the performance of the model has been further improved.

Analog Circuit Fault Diagnosis Based on Particle Swarm Neural Network Hybrid Algorithm

2013 ◽  
Vol 373-375 ◽  
pp. 1049-1052
Author(s):  
Bao Ru Han ◽  
Jing Bing Li
Keyword(s):  
Fault Diagnosis ◽  
Hybrid Algorithm ◽  
Analog Circuit ◽  
Particle Swarm ◽  
Bp Algorithm ◽  
Particle Swarm Algorithm ◽  
Inertia Weight ◽  
High Convergence Rate ◽  
Swarm Algorithm ◽  
Circuit Fault Diagnosis

Base on improved particle swarm algorithm, this paper proposes a linear decreasing inertia weight particle swarm algorithm and error back propagation algorithm based on hybrid algorithm combining. The linear decreasing inertia weight particle swarm algorithm and momentum-adaptive learning rate BP algorithm interchangeably adjust the network weights, so that the two algorithms are complementary. It gives full play to the PSO's global optimization ability and the BP algorithm local search advantage, to overcome the slow convergence speed and easily falling into local weight problems. Simulation results show that this diagnostic method can be used for tolerance analog circuit fault diagnosis, with a high convergence rate and diagnostic accuracy.

Artificial Fish Swarm Algorithm Based on Fast Image Matching

2011 ◽  
Vol 271-273 ◽  
pp. 297-302
Author(s):  
Miao Ma ◽  
Jiao He ◽  
Min Guo
Keyword(s):  
Image Matching ◽  
Feature Matching ◽  
Fitness Function ◽  
Optimal Solution ◽  
Fast Method ◽  
Artificial Fish Swarm Algorithm ◽  
Template Image ◽  
Artificial Fish Swarm ◽  
Swarm Algorithm ◽  
Exclusive Or

Due to the large amount of calculation and high time-consuming in traditional grayscale matching, this paper combines artificial fish algorithm of swarm intelligence with edge detection and the operation of bitwise exclusive or, and presents a fast method on feature matching. The method regards the problem of image matching as a process of searching the optimal solution. In order to provide artificial fish swarm algorithm with an appropriate fitness function, the operation of bitwise exclusive or and addition is employed to deal with the edge information extracted from the template image and the searching image. Then the best matching position is gradually approaching by swarming, following and other behaviors of artificial fish. Experimental results show that the proposed method not only significantly shortens the matching time and guarantees the matching accuracy, but also is robust to noise disturbance.

The Application of Quantum-Behaved Particle Swarm Algorithm in Intelligent Test Paper Generation

2013 ◽  
Vol 694-697 ◽  
pp. 2378-2382 ◽  
Author(s):  
Xin Ran Li
Keyword(s):  
Particle Swarm ◽  
Optimal Solution ◽  
Particle Aggregation ◽  
Particle Swarm Algorithm ◽  
Test Paper ◽  
Inertia Weight ◽  
Local Optimal Solution ◽  
Swarm Algorithm ◽  
Low Efficiency

Aiming at solving the low efficiency and low quality of the existing test paper generation algorithm, this paper proposes an improved particle swarm algorithm, a new algorithm for intelligent test paper generation. Firstly, the paper conducts mathematically modeling based on item response theory. Secondly, in the new algorithm, the inertia weight is expressed as functions of particle evolution velocity and particle aggregation by defining particle evolution velocity and particle aggregation so that the inertia weight has adaptability. At the same time, slowly varying function is introduced to the traditional location updating formula so that the local optimal solution can be effectively overcome. Finally, simulation results show that compared with the quantum-behaved particle swarm algorithm, the proposed algorithm has better performance in success rate and composing efficiency.

scholarly journals Improved Fitness-Dependent Optimizer Algorithm

2020 ◽  
Author(s):  
Danial A. Muhammed ◽  
Soran AM. Saeed ◽  
Tarik A. Rashid
Keyword(s):  
Optimization Problems ◽  
Optimal Solution ◽  
Standard Test ◽  
Particle Swarm Algorithm ◽  
Test Function ◽  
Dragonfly Algorithm ◽  
Whale Optimization ◽  
Real World Applications ◽  
Swarm Algorithm ◽  
Benchmark Test Functions

<div> <table> <tr> <td> <p>The fitness-dependent optimizer (FDO) algorithm was recently introduced in 2019. An improved FDO (IFDO) algorithm is presented in this work, and this algorithm contributes considerably to refining the ability of the original FDO to address complicated optimization problems. To improve the FDO, the IFDO calculates the alignment and cohesion and then uses these behaviors with the pace at which the FDO updates its position. Moreover, in determining the weights, the FDO uses the weight factor ( ), which is zero in most cases and one in only a few cases. Conversely, the IFDO performs randomization in the [0-1] range and then minimizes the range when a better fitness weight value is achieved. In this work, the IFDO algorithm and its method of converging on the optimal solution are demonstrated. Additionally, 19 classical standard test function groups are utilized to test the IFDO, and then the FDO and three other well-known algorithms, namely, the particle swarm algorithm (PSO), dragonfly algorithm (DA), and genetic algorithm (GA), are selected to evaluate the IFDO results. Furthermore, the CECC06 2019 Competition, which is the set of IEEE Congress of Evolutionary Computation benchmark test functions, is utilized to test the IFDO, and then, the FDO and three recent algorithms, namely, the salp swarm algorithm (SSA), DA and whale optimization algorithm (WOA), are chosen to gauge the IFDO results. The results show that IFDO is practical in some cases, and its results are improved in most cases. Finally, to prove the practicability of the IFDO, it is used in real-world applications.</p> </td> </tr> </table> </div> <br>

scholarly journals Optimization design based on hierarchic genetic algorithm and particles swarm algorithm

2018 ◽  
Vol 12 (3) ◽  
pp. 217-222 ◽  
Author(s):  
Lin DengWei
Keyword(s):  
Genetic Algorithm ◽  
Optimization Design ◽  
Fitness Function ◽  
Particle Swarm ◽  
Trust Model ◽  
Particle Swarm Algorithm ◽  
Time Model ◽  
Similarity Algorithm ◽  
Swarm Algorithm ◽  
Hierarchical Genetic Algorithm

For a lot of data, it is time-consuming and unpractical to get the best combination by manual tests. The genetic algorithm can make up for this shortcoming through the optimization of parameters. In this paper, the advantages of traditional similarity algorithm is studied, the time model and the trust model for further filtering are introduced, and the parameters with the combination of hierarchical genetic algorithm and particle swarm algorithm are optimized. In the collaborative filtering algorithm, genetic algorithm is improved with hierarchical algorithm, and the user model and the algorithm process are optimized using the fitness function of selection, crossover, and variation, along with the optimization of recommendation result set. In the algorithm, the global optimal parameters can be calculated with the optimization of the obtained initial data, and the accuracy of the similarity calculation can also be improved. This study does the recommendation and comparison experiment in the MovieLens Dataset, and the results show that, on the basis of obtaining the nearest neighbor user group, the mixing use of the hierarchical genetic algorithm and the particle swarm algorithm can make more improvement in the recommendation quality than that of the traditional similarity algorithm.

scholarly journals Joint Transmit and Receive Antenna Selection in MIMO Systems Based on Swarm Intelligence Algorithm

2021 ◽  
Author(s):  
Zhang Yiwen ◽  
Su Sunqing ◽  
Liao Wenliang ◽  
Lei Guowei ◽  
Yang Guangsong
Keyword(s):  
Mimo Systems ◽  
Antenna Selection ◽  
Multiple Input Multiple Output ◽  
Optimal Solution ◽  
System Capacity ◽  
Particle Swarm Algorithm ◽  
Input Multiple Output ◽  
Swarm Algorithm ◽  
Speed Accuracy ◽  
Receive Antenna

Abstract In multiple-input-multiple-output (MIMO) systems, the selection of receive and transmit antennas is not just effective in increasing system capacity, but also in reducing RF link costs and system complexity. The exhaustive algorithm, i.e. the joint transmit and receive antenna selection (JTRAS) with the best accuracy, can search all the subsets of both transmit and receive antennas in order to find the optimal solution. However, with the increase of the number of antennas, the computational complexity is too large and its applicability is limited. In this paper, the antennas are coded by fractional coding with the maximization of channel capacity as the basic criterion, and three intelligent algorithms, namely genetic algorithm, cat swarm algorithm and particle swarm algorithm, are applied for antenna selection. The simulation results demonstrate that all three algorithms can efficiently accomplish the antenna selection. In the end, we compare them in terms of speed, accuracy and complexity of the search in MIMO systems.

scholarly journals Parallel Hybrid Particle Swarm Algorithm for Workshop Scheduling Based on Spark

Algorithms ◽  
2021 ◽  
Vol 14 (9) ◽  
pp. 262
Author(s):  
Tianhua Zheng ◽  
Jiabin Wang ◽  
Yuxiang Cai
Keyword(s):  
Particle Swarm ◽  
Optimal Solution ◽  
Particle Swarm Algorithm ◽  
Hybrid Particle ◽  
Algorithm Efficiency ◽  
Parallel Hybrid ◽  
Swarm Algorithm ◽  
Mass Assembly ◽  
Scheduling Plan ◽  
Algorithm Parallelization

In hybrid mixed-flow workshop scheduling, there are problems such as mass production, mass manufacturing, mass assembly and mass synthesis of products. In order to solve these problems, combined with the Spark platform, a hybrid particle swarm algorithm that will be parallelized is proposed. Compared with the existing intelligent algorithms, the parallel hybrid particle swarm algorithm is more conducive to the realization of the global optimal solution. In the loader manufacturing workshop, the optimization goal is to minimize the maximum completion time and a parallelized hybrid particle swarm algorithm is used. The results show that in the case of relatively large batches, the parallel hybrid particle swarm algorithm can effectively obtain the scheduling plan and avoid falling into the local optimal solution. Compared with algorithm serialization, algorithm parallelization improves algorithm efficiency by 2–4 times. The larger the batches, the more obvious the algorithm parallelization improves computational efficiency.

A Novel Particle Swarm Algorithm for Online Trading Customer Classification

2014 ◽  
Vol 644-650 ◽  
pp. 2181-2184
Author(s):  
Chen Chen
Keyword(s):  
Search Algorithm ◽  
Particle Swarm ◽  
Optimal Solution ◽  
Particle Swarm Algorithm ◽  
Computation Method ◽  
Original Algorithm ◽  
Online Trading ◽  
Customer Classification ◽  
Swarm Algorithm ◽  
Improved Algorithm

Particle swarm algorithm is an efficient evolutionary computation method and wildly used in various disciplines. But as a random global search algorithm, particle swarm algorithm easily falls into the local optimal solution for its rapid propagation in populations and in order to overcome these shortcomings, a novel particle swarm algorithm is presented and used in classifying online trading customers. The corresponding improvements include improving the speed update formula of particles and improving the balance between the development and detection capability of original algorithm and redesigning the calculation flow of the improved algorithm. Finally after designing 21 customer classification indicators, the improved algorithm is realized for customer classification of a certain E-commerce enterprise and experimental results show that the algorithm can improve classification accuracy and decreases the square errors.

Image Matching Based on Bacterial Foraging Algorithm

2011 ◽  
Vol 301-303 ◽  
pp. 859-863
Author(s):  
Hong Peng Tian
Keyword(s):  
Wavelet Transform ◽  
Swarm Intelligence ◽  
Image Matching ◽  
Fitness Function ◽  
Optimal Solution ◽  
Experimental Results ◽  
Matching Method ◽  
Bacterial Foraging ◽  
Template Image ◽  
Bacterial Foraging Algorithm

To increase the speed of image matching, this paper combines Bacterial Foraging Algorithm (BFA) of swarm intelligence with wavelet transform, and presents a fast matching method. The method regards the problem of image matching as a search for the optimal solution. To provide artificial bacterial swarm algorithm with an appropriate fitness function, the Normalized Product correlation (NPROD) is employed to measure the similarity between the template image and the searching image. Then the best coarse matching position is gradually approaching by chemotaxis, elimination and dispersal, and reproduction behaviors of artificial bacterial. Finally, the best matching position is found out according to the coarse matching position. Experimental results show that the proposed method is fast and efficient.

Chaotic Particle Swarm Optimization for Automatic Surface or Curve Localization

2014 ◽  
Vol 620 ◽  
pp. 324-328
Author(s):  
Jia Feng Wu ◽  
Dong Li Qin
Keyword(s):  
Particle Swarm Optimization ◽  
Particle Swarm ◽  
Optimal Solution ◽  
Particle Swarm Algorithm ◽  
Euler Angles ◽  
Swarm Optimization ◽  
Chaotic Mapping ◽  
Curve Detection ◽  
Swarm Algorithm ◽  
Chaotic Particle Swarm Optimization

In order to solve the automatic localization problem of the surface or curve detection, this paper presents a method for obtaining a global optimal solution, the method uses particle swarm algorithm to solve the position and orientation. To solve the problem of premature convergence and slow convergence in particle swarm algorithm, a chaotic mapping logistic model is presented to improve the performance of particle swarm algorithm and the shrinking chaotic mutation operator is applied into the method to increase the diversity and ergodicity of particle populations. In this paper, the objective matrix is separately described by quaternion and Euler angles, and the accuracy and convergence of the algorithm are analyzed taken into account these matrices. Simulation results demonstrate that two mentioned expressions can comply with the requirements of adaptive localization, and while Euler angles as optimization variables, chaotic particle swarm optimization have higher accuracy results. Finally, compared to Hong-Tan algorithms, the method is effective and reliable.

Sign in / Sign up

Export Citation Format

Share Document