Random Global and Local Optimal Search Algorithm Based Subset Generation for Diagnosis of Cancer

Meenachi, L.; Ramakrishnan, S.

doi:10.2174/1573405614666180720152838

Cited by 8 publications

(3 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Table 7. Comparison of percentage of features used by the proposed method and existing feature-selection algorithms Propos method GATFRO [50] ACTFRO [50] GSFR [51] GLO [52] DEGR [53] FS-JMIE [54] PSO […”

Section: Evaluation Of the Results And Comparison Of Functionsmentioning

confidence: 99%

A New Evolutionary Ensemble Learning of Multimodal Feature Selection from Microarray Data

Nekouie

Romoozi

Esmaeili

2023

Neural Process Lett

View full text Add to dashboard Cite

In the last decades, data has grown exponentially with respect to the number of samples and features, which makes feature selection more challenging. An optimization method called multimodal optimization techniques is employed to nd several optimal solutions. The main contribution of multimodal optimization techniques is providing several optimal solutions instead of a single solution. Since multimodal optimization algorithm naturally provides several answers, in this paper the potential and information of several answers are used to address the issues of selecting features from microarray data, using hidden information in the data, and creating an ensemble of classi ers. After pre-processing of data, several optimal feature subsets are obtained by re ybased multimodal optimization algorithm to tap the potential of and information in several answers. The mutual information method is used as the tness function to evaluate the suggested subset of features. Then, each subset of features is used to learn a classi er and such classi ers are learned on data whose features are presented by a multimodal optimization algorithm, and these classi ers are combined. To select a proper combination, a particle swarm optimization algorithm is used. Finally, the algorithm for the datasets of the microarray is evaluated in terms of cancer diagnosis. The algorithmic method e ciency is evaluated by applying it on 11 datasets. The results suggested the superiority and proper function of the multimodal feature selection method compared with other methods.

show abstract

Section: Evaluation Of the Results And Comparison Of Functionsmentioning

confidence: 99%

A New Evolutionary Ensemble Learning of Multimodal Feature Selection from Microarray Data

Nekouie

Romoozi

Esmaeili

2023

Neural Process Lett

View full text Add to dashboard Cite

show abstract

“…Clinically, the computational complexity of the block matching algorithm makes it difficult to meet the needs of timeliness. Journal of Healthcare Engineering erefore, first, the impact of global search [17] and logarithmic search [18] on the efficiency of the algorithm was analyzed. It was found the tracking accuracy of the two search methods was both higher than 93%.…”

Section: Discussionmentioning

confidence: 99%

Block Matching Pyramid Algorithm-Based Analysis on Efficacy of Shexiang Baoxin Pills Guided by Echocardiogram (ECG) on Patients with Angina Pectoris in Coronary Heart Disease

Gao

Wang

et al. 2021

Journal of Healthcare Engineering

View full text Add to dashboard Cite

This paper was aimed to explore the application of the block matching pyramid (BMP) algorithm in echocardiographic spot tracking in patients with coronary heart disease (CHD) and angina pectoris, as well as the effect of Shexiang Baoxin pills (a kind of drug containing musk, which is good for cardiac diseases) on blood lipids, cardiac function, and curative effect. 206 patients with CHD angina pectoris in the hospital from July 2018 to May 2020 were selected as the research subjects and were enrolled into the control (Ctrl) group (conventional treatment, n = 103) and the observation group (the Shexiang Baoxin pill was given on the basis of conventional treatment, n = 103) in random. Then, the patients’ echocardiograms were obtained, and the BMP algorithm was used to track the echocardiograms. At 12 months after treatment, the total cholesterol (TC), triglycerides (TG), low-density lipoprotein cholesterol (LDL-C), and high-density lipoprotein cholesterol (HDL-C) were compared. Besides, the differences between left ventricular end-systolic volume (LVESV), left ventricular end-systolic diameter (LVESD), left ventricular end-diastolic volume (LVEDV), left ventricular end-diastolic dimension (LVEDD), cardiac index (CI), cardiac output (CO), and LVEF were observed. Finally, the efficacy of angina pectoris and electrocardiogram was calculated. It was found that the BMP algorithm can track the echocardiograms and display the movement and displacement of the patients’ left ventricle. After treatment, in contrast with the Ctrl, the levels of TC, TG, and LDL-C in the observation group were obviously lower ( P < 0.05 ); the LVESV, LVEDV, and LVEF were obviously lower ( P < 0.05 ), the LVESD, LVEDD, CO, and CI were obviously higher ( P < 0.05 ), the total score of angina after treatment was obviously lower ( P < 0.05 ), and the total effective rates of angina pectoris and echocardiogram were obviously higher ( P < 0.05 ). In conclusion, echocardiographic spot tracking can realize the diagnosis of patients with CHD angina pectoris, and Shexiang Baoxin pill can regulate the blood lipid level and improve the echocardiographic indicators and the clinical efficacy is obvious.

show abstract

“…Great progress has been achieved. However, in the course of performing the training algorithm of the classifier, they all face the situation of either falling into the local optimal [8,9] or failing to reach the global optimal.…”

Section: Introductionmentioning

confidence: 99%

Diagnosis of COVID-19 by Wavelet Renyi Entropy and Three-Segment Biogeography-Based Optimization

Wang¹,

Wu²,

Zhang³

et al. 2020

IJCIS

View full text Add to dashboard Cite

Corona virus disease 2019 (COVID-19) is an acute infectious pneumonia and its pathogen is novel and was not previously found in humans. As a diagnostic method for COVID-19, chest computed tomography (CT) is more sensitive than reverse transcription polymerase chain reaction. However, the interpretation of COVID-19 based on chest CT is mainly done manually by radiologists and takes about 5 to 15 minutes for one patient. To shorten the time of interpreting the CT image and improve the reliability of identification of COVID-19. In this paper, a novel chest CT-based method for the automatic detection of COVID-19 was proposed. Our algorithm is a hybrid method composed of (i) wavelet Renyi entropy, (ii) feedforward neural network, and (iii) a proposed three-segment biogeography-based optimization (3SBBO) algorithm. The wavelet Renyi entropy is used to extract the image features. The novel optimization method of 3SBBO can optimize weights, biases of the network, and Renyi entropy order. Finally, we used 296 chest CT images to evaluate the detection performance of our proposed method. In order to reduce randomness and get unbiased result, the 10 runs of 10-fold cross validation are introduced. Experimental outcomes show that our proposed method is superior to state-of-the-art approaches in terms of sensitivity, specificity, precision, accuracy, and F1.

show abstract

Random Global and Local Optimal Search Algorithm Based Subset Generation for Diagnosis of Cancer

Cited by 8 publications

References 0 publications

A New Evolutionary Ensemble Learning of Multimodal Feature Selection from Microarray Data

A New Evolutionary Ensemble Learning of Multimodal Feature Selection from Microarray Data

Block Matching Pyramid Algorithm-Based Analysis on Efficacy of Shexiang Baoxin Pills Guided by Echocardiogram (ECG) on Patients with Angina Pectoris in Coronary Heart Disease

Diagnosis of COVID-19 by Wavelet Renyi Entropy and Three-Segment Biogeography-Based Optimization

Contact Info

Product

Resources

About