2022
DOI: 10.1007/s42235-022-00216-x
|View full text |Cite
|
Sign up to set email alerts
|

An Efficient Hybrid Model Based on Modified Whale Optimization Algorithm and Multilayer Perceptron Neural Network for Medical Classification Problems

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
4
0

Year Published

2023
2023
2024
2024

Publication Types

Select...
9

Relationship

0
9

Authors

Journals

citations
Cited by 11 publications
(4 citation statements)
references
References 72 publications
0
4
0
Order By: Relevance
“…Although this method can quickly extract the required features, these features may not have the best recognition effect. Because these feature extraction rules are all derived from experience, when faced with different background environments, the extracted features are good or bad [7][8]. Moreover, there is no unified strategy for how to combine these features to improve the IR effect.…”
Section: Comparison Of Image Recognition (Ir) Methodsmentioning
confidence: 99%
“…Although this method can quickly extract the required features, these features may not have the best recognition effect. Because these feature extraction rules are all derived from experience, when faced with different background environments, the extracted features are good or bad [7][8]. Moreover, there is no unified strategy for how to combine these features to improve the IR effect.…”
Section: Comparison Of Image Recognition (Ir) Methodsmentioning
confidence: 99%
“…An application of GA hybridization and back propagation showed a better result in breast cancer classification by AlShourbaji et al [48] compared to BP alone. In order to enhance the accuracy of MLPs, the authors of [49] proved that the differential evolution algorithm optimised by metaheuristics still shows better results in the classification of medical data.…”
Section: Literature Reviewmentioning
confidence: 99%
“…To sum up, the basis of the NNM inference on the side is the lightweight of the model, and the lightweight of the model depends on its own small amount of parameters and calculations. Therefore, the focus of this paper is to design the model around the two core tasks of reducing the complexity of the model's convolution kernel parameters and the calculation amount of participating in the NNM for image recognition, analyzing the main problems faced by the lightweight model, and designing an effective solution to solve [15,16].…”
Section: Analysis Of Research Significancementioning
confidence: 99%