A new fruit fly optimization algorithm enhanced support vector machine for diagnosis of breast cancer based on high-level features

Abstract

Background It is of great clinical significance to develop an accurate computer aided system to accurately diagnose the breast cancer. In this study, an enhanced machine learning framework is established to diagnose the breast cancer. The core of this framework is to adopt fruit fly optimization algorithm (FOA) enhanced by Levy flight (LF) strategy (LFOA) to optimize two key parameters of support vector machine (SVM) and build LFOA-based SVM (LFOA-SVM) for diagnosing the breast cancer. The high-level features abstracted from the volunteers are utilized to diagnose the breast cancer for the first time. Results In order to verify the effectiveness of the proposed method, 10-fold cross-validation method is used to make comparison among the proposed method, FOA-SVM (model based on original FOA), PSO-SVM (model based on original particle swarm optimization), GA-SVM (model based on genetic algorithm), random forest, back propagation neural network and SVM. The main novelty of LFOA-SVM lies in the combination of FOA with LF strategy that enhances the quality for FOA, thus improving the convergence rate of the FOA optimization process as well as the probability of escaping from local optimal solution. Conclusions The experimental results demonstrate that the proposed LFOA-SVM method can beat other counterparts in terms of various performance metrics. It can very well distinguish malignant breast cancer from benign ones and assist the doctor with clinical diagnosis.

Chaotic Arc Adaptive Grasshopper Optimization

“…Additionally, its convergence and overall searching behavior were enriched due to the better balance between the diversification and intensification trends. Moreover, with those properties we described, the AGOA can be applied to more scenarios, such as energy optimization problems, image segmentation problems, and the optimization of support vector machines [17], [27], [125]- [127], extreme learning machines [19], [20], [34], [128]- [130], and convolutional neural networks [131][132][133] that involve parameter optimization. Besides, the binary version of the AGOA can be used in feature selection problems [134]- [137] to cope with feature selection problems in the field of data mining.…”

Diagnosing Coronavirus Disease 2019 (COVID-19): Efficient Harris Hawks-Inspired Fuzzy K-Nearest Neighbor Prediction Methods

“…FKNN [83], [84] classifier is developed based on the traditional k-nearest neighbor (KNN) classifier and has been widely considered from the time when it was initially suggested [85], [86], [86]- [88]. Compared with procedures such as extreme learning machines [89]- [94], deep learning methods [95]- [97], and support vector machines [70], [17], [98]- [103], FKNN is much simpler and can return outcomes that can be more easily understood.…”

“…It is almost possible to reach any form according to the decision-makers preferences. These problems can be modeled as many-objective [10], [11], memetic [12], robust [13], multiobjective [14], large scale [15], [16], fuzzy [17], and single-objective optimization. These forms and the growing demand for their solvers have raised many challenges in data science.…”

Predicting Coronary Atherosclerotic Heart Disease: An Extreme Learning Machine with Improved Salp Swarm Algorithm

“…In the future, it is our goal to utilize the STSSA-KELM model to diagnose other diseases, such as pleural effusion, diabetes, appendicitis, and so on. Additionally, the core method STSSA can also be used for parameter tuning for the artificial intelligence models, such as support vector machines [40][41][42][43][44], and convolutional neural networks [45][46][47][48][49]. Moreover, it can also be applied to tackle the feature selection problems [28,41,50,51].…”