Flexible Wolf Pack Algorithm for Dynamic Multidimensional Knapsack Problems

Wu, Husheng; Xiao, Renbin

doi:10.34133/2020/1762107

Cited by 17 publications

(9 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Extract the principal components of data based on the feature matrix of principal component analysis. 31,32 When 12 principal components were selected, the cumulative variance contribution rate reached 90.5%. Therefore, this experiment selected the first 12 principal components of the PCA feature matrix as the original input of the subsequent DPC-SNA algorithm clustering, thereby reducing the data dimension from 48 to 12.…”

Section: Analysis Of Clustering Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Analysis of user electricity consumption behavior based on density peak clustering with shared neighbors and attractiveness

Li¹,

Wang

Zhang³

et al. 2022

Concurrency and Computation

View full text Add to dashboard Cite

Summary User behavior analysis is the research foundation of power load forecasting and power abnormal detection, and it is the theoretical support for smart grid planning and the construction of energy internet. Aiming at the complex characteristics of high‐dimensional, noisy, and multi‐redundant of power load data, this article used the principal component analysis (PCA) to reduce the dimensionality of power data. The density peaks clustering algorithm with shared neighbor and attractiveness (DPC‐SNA) was then used to cluster the data with reduced dimensionality to extract the user's electricity consumption characteristics. The DPC‐SNA algorithm first constructs a sample similarity measurement criterion that shares the similarity of neighbors, on which the local density is defined accordingly. The new local density can effectively distinguish the contributions of local samples and global samples. Incorporating the idea of universal gravitation, a new calculation method of sample attractiveness was defined, and the remaining samples were allocated by the attractiveness matrix. Experiment was performed using the actual load data of special transformer users in a certain area. The results show that there were five typical electricity consumption behavior characteristics in this area, namely, the evening‐peak production type, all‐day production type, multi‐peak production type, daytime production type, and night production type. The corresponding load peak time periods were also obtained.

show abstract

Section: Analysis Of Clustering Resultsmentioning

confidence: 99%

“…Extract the principal components of data based on the feature matrix of principal component analysis 31,32 . When 12 principal components were selected, the cumulative variance contribution rate reached 90.5%.…”

Section: Analysis Of User Power Consumption Based On Dpc‐sna Algorithmmentioning

confidence: 99%

Analysis of user electricity consumption behavior based on density peak clustering with shared neighbors and attractiveness

Li¹,

Wang

Zhang³

et al. 2022

Concurrency and Computation

View full text Add to dashboard Cite

show abstract

“…As the number of objectives increases, the computational cost of such algorithms becomes very expensive, so the computational cost needs to be considered when designing such algorithms. MOEAs based on swarm intelligence . This kind of MOEAs extends some swarm intelligence techniques with good performance to the field of multi‐objective optimization, 21–23 and swarm intelligence algorithms have unique optimization methods and strong adaptability 24,25 The optimization method of swarm intelligence algorithm is novel and unique, and has strong adaptability. Such as MOPSO, 26 MOFA, 27 CFMOFA, 28 MOFA‐HL, 29 all based on swarm intelligence algorithm is extended.…”

Section: Introductionmentioning

confidence: 99%

Multi‐objective firefly algorithm with multi‐strategy integration

Zhou

Tan

et al. 2022

Concurrency and Computation

View full text Add to dashboard Cite

In the optimization process of multi-objective firefly algorithm, population is easy to fall into local optimum, which leads to poor population distribution and convergence. In order to solve this problem, this article proposes a multi-objective firefly algorithm with multi-strategy integration (MOFA-MSI). First, in order to improve the distribution of population, MOFA-MSI proposes a cloning strategy, which calculates the distribution degree of individuals in population, clones them according to their distribution degree, and local mutation in the cloned individual produce a new population with good distribution. Then, in order to maintain the convergence of population, a position updating strategy based on non-dominated sorting is proposed. The new population after local mutation are performed by non-dominated sorting, and the fireflies with higher rank guide the fireflies with lower rank to fly, and then new population are generated by global mutation after position updated. Finally, the greedy strategy is adopted to select solutions with better distribution and convergence and store them in external files. In the experimental part, different types of test problems are used to test the performance of each algorithm, and MOFA-MSI is compared with three classical and four new multi-objective evolutionary algorithms. The results show that MOFA-MSI is superior to other seven algorithms in terms of the distribution and convergence of population.

show abstract

“…Traditional NID techniques achieve intrusion detection by comparing attacks identified in the feature code database, but this method has a high leakage rate and lag [1]. Recently, with the rapid development of artificial intelligence [2][3][4][5] and machine learning technologies [6][7][8], machine learning-based NID methods are gradually becoming a research hotspot.…”

Section: Introductionmentioning

confidence: 99%

Tri-training algorithm based on cross entropy and K-nearest neighbors for network intrusion detection

2022

KSII TIIS

View full text Add to dashboard Cite

To address the problem of low detection accuracy due to training noise caused by mislabeling when Tri-training for network intrusion detection (NID), we propose a Tri-training algorithm based on cross entropy and K-nearest neighbors (TCK) for network intrusion detection. The proposed algorithm uses cross-entropy to replace the classification error rate to better identify the difference between the practical and predicted distributions of the model and reduce the prediction bias of mislabeled data to unlabeled data; K-nearest neighbors are used to remove the mislabeled data and reduce the number of mislabeled data. In order to verify the effectiveness of the algorithm proposed in this paper, experiments were conducted on 12 UCI datasets and NSL-KDD network intrusion datasets, and four indexes including accuracy, recall, F-measure and precision were used for comparison. The experimental results revealed that the TCK has superior performance than the conventional Tri-training algorithms and the Tritraining algorithms using only cross-entropy or K-nearest neighbor strategy.

show abstract

Flexible Wolf Pack Algorithm for Dynamic Multidimensional Knapsack Problems

Cited by 17 publications

References 49 publications

Analysis of user electricity consumption behavior based on density peak clustering with shared neighbors and attractiveness

Analysis of user electricity consumption behavior based on density peak clustering with shared neighbors and attractiveness

Multi‐objective firefly algorithm with multi‐strategy integration

Tri-training algorithm based on cross entropy and K-nearest neighbors for network intrusion detection

Contact Info

Product

Resources

About