Application in Disease Classification based on KPCA-IBA-LSSVM

Jiang, Jin Long; Li, Shao Yi; Liao, Ming Liang; Jiang, Yan

doi:10.1016/j.procs.2019.06.017

Cited by 5 publications

(4 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In a dataset of 400 samples, 320 samples are used as the training set, and 80 samples are used as the test set. IPSO-LSSVM, 38 COA-LSSVM, 39 IBA-LSSVM 40 are used for comparison to verify the superiority of the proposed method.…”

Section: Application Of Pca-hsida-lssvm On Escc Datasetmentioning

confidence: 99%

“…39 Jiang et al combined LSSVM optimized by improved bat algorithm (IBA)with kernelized principal component analysis (KPCA) for disease classification. 40 Ahmed et al proposed an improved Barnacle Mating Optimizer and combined with LSSVM to predict COVID-19 confirmed cases with total vaccination. 41 Rashid and Miften utilized the discrete wavelet transform (DWT) statistical attributes and LSSVM to detect seizure, which can in real time to enhance healthcare and life quality.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

A survival prediction model based on PCA-HSIDA-LSSVM for patients with esophageal squamous cell carcinoma

Wang,

Xia,

Ling

et al. 2023

Proc Inst Mech Eng H

View full text Add to dashboard Cite

Esophageal squamous cell carcinoma (ESCC) is a type of cancer and has some of the highest rates of both incidence and mortality globally. Developing accurate models for survival prediction provides a basis clinical judgment and decision making, improving the survival status of ESCC patients. Although many predictive models have been developed, there is still lack of highly accurate survival prediction models for ESCC patients. This study proposes a novel survival prediction model for ESCC patients based on principal component analysis (PCA) and least-squares support vector machine (LSSVM) optimized by an improved dragonfly algorithm with hybrid strategy (HSIDA). The original 17 blood indicators are condensed into five new variables by PCA, reducing data dimensionality and redundancy. An improved dragonfly algorithm based on hybrid strategy is proposed, which addresses the limitations of dragonfly algorithm, such as slow convergence, low search accuracy and insufficient vitality of late search. The proposed HSIDA is used to optimize the regularization parameter and kernel parameter of LSSVM, improving the prediction accuracy of the model. The proposed model is validated on the dataset of 400 patients with ESCC in the clinical database of First Affiliated Hospital of Zhengzhou University and the State Key Laboratory of Esophageal Cancer Prevention and Control of Henan Province. The experiment results demonstrate that the proposed HSIDA-LSSVM has the best prediction performance than LSSVM, HSIDA-BP, IPSO-LSSVM, COA-LSSVM and IBA-LSSVM. The proposed model achieves the accuracy of 96.25%, sensitivity of 95.12%, specificity of 97.44%, precision of 97.50%, and F1 score of 96.30%.

show abstract

Section: Application Of Pca-hsida-lssvm On Escc Datasetmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

A survival prediction model based on PCA-HSIDA-LSSVM for patients with esophageal squamous cell carcinoma

Wang,

Xia,

Ling

et al. 2023

Proc Inst Mech Eng H

View full text Add to dashboard Cite

show abstract

“…BA was applied to optimize the parameters of a least square support vector machine (SVM) for disease classification in (J. L. Jiang, Li, Liao, & Jiang, 2019 ). This work developed BA to avoid premature convergence and avoiding trapping in local optima by calling chaotic functions for population initialization and using a decreasing weight parameter.…”

Section: Literature Reviewmentioning

confidence: 99%

“…This work developed BA to avoid premature convergence and avoiding trapping in local optima by calling chaotic functions for population initialization and using a decreasing weight parameter. The validation of this algorithm in (J. L. Jiang et al, 2019 ) was performed on a Hear disease (Statlog) and Breast cancer dataset. Besides, many other applications made use of BA, such as MR brain image segmentation ( Alagarsamy, Kamatchi, Govindaraj, Zhang, & Thiyagarajan, 2019 ), human diseases prediction ( Enireddy et al, 2021 ), and pathological brain detection ( Lu, Wang, & Zhang, 2020 ).…”

Section: Literature Reviewmentioning

confidence: 99%