Particle swarm optimization for bandwidth determination and feature selection of kernel density estimation based classifiers in diagnosis of breast cancer

Sheikhpour, Razieh; Sarram, Mehdi Agha; Sheikhpour, Robab

doi:10.1016/j.asoc.2015.10.005

Cited by 143 publications

(47 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The correct and early detection of breast cancer can ensure a long survival of the patients. Early detection of breast cancer with an accurate and reliable diagnosis procedure causes physicians distinguish benign breast tumors from malignant tumors (2). Breast cancer involved different signaling cascade deregulation (3), and early prognostic markers can could be used for routine diagnosis and patient survival.…”

Section: Contextmentioning

confidence: 99%

See 1 more Smart Citation

The Role of Interleukin-8 and Its Mechanism in Patients with Breast Cancer: Its Relation with Oxidative Stress and Estrogen Receptor

Sheikhpour

2017

Int J Cancer Manag

Self Cite

View full text Add to dashboard Cite

Context: Breast cancer is one of the leading causes of death among women all over the world. Prognostic markers can be used for patient survival. Likewise, these biomarkers are able to generate main information related to clinical manner of breast gland tumors. Interleukin-8 (IL-8) is a chemotactic cytokines caused initiation of an inflammatory response. Evidence Acquisition: We performed a computerized search in Medline/PubMed databases with key words: IL-8, breast cancer, and oxidative stress. Results: IL-8 secretion motivates the expression of adhesion molecule, including fibronectin in human inflammatory breast cancer cells. IL-8 activates PI3K/Akt pathway, which in turn activates NF-κB resulted up-regulation of integrin β3 expression and increases the invasion of breast cancer cells. Therefore, it seems that IL-8/PI3K/Akt/NF-κB/integrin β3 axis may be used for therapeutic intervention of breast cancer with metastasis status. NF-κB plays an important role in IL-8 gene transcription via several signals, such as LPS, TNF-alpha, and oxidative stress. Oxidative stress caused angiogenic factor production, such as vascular endothelial growth factor and IL-8 via cancer cells. Moreover, there is inverse relation between ER level and IL-8, but the mechanism of IL-8 action in estrogen receptor-negative breast cancer is largely unknown. Estrogen receptor and growth factor in breast cancer cells is influenced by mitogen activated protein kinase (MAPK) cascade, as a part of IL-8 signaling pathway. Conclusions: According to these studies, interleukin-8 may be as a main biomarker for breast cancer. It seems that signaling pathway of IL-8 may be used for therapeutic intervention of breast cancer. Also oxidative stress and breast cancer cells with lacking estrogen receptor generate more interleukin-8.

show abstract

Section: Contextmentioning

confidence: 99%

“…It affects 1 of every 8 women in the United States (2). Also, it is one of the most frequent malignancies among Iranian women (1).…”

Section: Contextmentioning

confidence: 99%

The Role of Interleukin-8 and Its Mechanism in Patients with Breast Cancer: Its Relation with Oxidative Stress and Estrogen Receptor

Sheikhpour

2017

Int J Cancer Manag

Self Cite

View full text Add to dashboard Cite

show abstract

“…During the past decades, many feature selection algorithms have been proposed in the literature, which can be divided into three categories [1]: filter methods [8], embedded methods [9] and wrapper methods [10]. In filter methods, selecting or removing a feature component is decided by a criteria function, such as the mutual information, interclass distance or statistical measures.…”

Section: Introductionmentioning

confidence: 99%

“…Sheikhpour et al [10] proposed the PSO-KDE model, which combines PSO with a non-parametric kernel density estimation (KDE) based classifier to distinguish benign breast tumors from malignant ones. In this model, PSO simultaneously optimizes the selected feature subset and the kernel bandwidth in the KDE-based classifier.…”

Section: Introductionmentioning

confidence: 99%

A tribe competition-based genetic algorithm for feature selection in pattern classification

Xia

2017

Applied Soft Computing

View full text Add to dashboard Cite

Abstract-Feature selection has always been a critical step in pattern recognition, in which evolutionary algorithms, such as the genetic algorithm (GA), are most commonly used. However, the individual encoding scheme used in various GAs would either pose a bias on the solution or require a pre-specified number of features, and hence may lead to less accurate results. In this paper, a tribe competition-based genetic algorithm (TCbGA) is proposed for feature selection in pattern classification. The population of individuals is divided into multiple tribes, and the initialization and evolutionary operations are modified to ensure that the number of selected features in each tribe follows a Gaussian distribution. Thus each tribe focuses on exploring a specific part of the solution space. Meanwhile, tribe competition is introduced to the evolution process, which allows the winning tribes, which produce better individuals, to enlarge their sizes, i.e. having more individuals to search their parts of the solution space. This algorithm, therefore, avoids the bias on solutions and requirement of a pre-specified number of features. We have evaluated our algorithm against several state-of-the-art feature selection approaches on 20 benchmark datasets. Our results suggest that the proposed TCbGA algorithm can identify the optimal feature subset more effectively and produce more accurate pattern classification.

show abstract

“…It has good adaptation and gains wide concern. It is applied in many fields such as decision feedback equalizer [3,4], parameter identification [5,6], power dispatch [7] and mechanical control [8,9], etc.…”

mentioning

confidence: 99%

The Particle Swarm Optimization Algorithm with Adaptive Chaos Perturbation

Li¹,

Liao

Yang

2016

INT J COMPUT COMMUN

View full text Add to dashboard Cite

Aiming at the two characteristics of premature convergence of particle swarm optimization that the particle velocity approaches 0 and particle swarm congregate, this paper learns from the annealing function of the simulated annealing algorithm and adaptively and dynamically adjusts inertia weights according to the velocity information of particles to avoid approaching 0 untimely. This paper uses the good uniformity of Anderson chaotic mapping and performs chaos perturbation to part of particles based on the information of variance of the population's fitness to avoid the untimely aggregation of particle swarm. The numerical simulations of five test functions are performed and the results are compared with several swarm intelligence heuristic algorithms. The results shows that the modified algorithm can keep the population diversity well in the middle stage of the iterative process and it can improve the mean best of the algorithm and the success rate of search.

show abstract

Particle swarm optimization for bandwidth determination and feature selection of kernel density estimation based classifiers in diagnosis of breast cancer

Cited by 143 publications

References 53 publications

The Role of Interleukin-8 and Its Mechanism in Patients with Breast Cancer: Its Relation with Oxidative Stress and Estrogen Receptor

The Role of Interleukin-8 and Its Mechanism in Patients with Breast Cancer: Its Relation with Oxidative Stress and Estrogen Receptor

A tribe competition-based genetic algorithm for feature selection in pattern classification

The Particle Swarm Optimization Algorithm with Adaptive Chaos Perturbation

Contact Info

Product

Resources

About