An Improvised Machine Learning Model Based on Mutual Information Feature Selection Approach for Microbes Classification

Entropy

Balwinder Singh Sohi¹  Anaahat Dhindsa²  Sanjay Bhatia³  Sunil Agrawal⁴ 

[1] Department of ECE, Chandigarh University, Gharuan, Punjab 140413, India;Department of Electronics and Communication Engineering, Chandigarh University, Gharuan, Punjab 140413, India;P.G Department of Zoology, University of Jammu, Kashmir 180006, India;University Institute of Engineering and Technology, Panjab University, Chandigarh 160014, India;

关键词: mutual information;    classification;    k-fold cross validation;    machine learning modeling;    image segmentation;    microorganisms;   

DOI  :  10.3390/e23020257

来源: DOAJ

【 摘 要 】

The accurate classification of microbes is critical in today’s context for monitoring the ecological balance of a habitat. Hence, in this research work, a novel method to automate the process of identifying microorganisms has been implemented. To extract the bodies of microorganisms accurately, a generalized segmentation mechanism which consists of a combination of convolution filter (Kirsch) and a variance-based pixel clustering algorithm (Otsu) is proposed. With exhaustive corroboration, a set of twenty-five features were identified to map the characteristics and morphology for all kinds of microbes. Multiple techniques for feature selection were tested and it was found that mutual information (MI)-based models gave the best performance. Exhaustive hyperparameter tuning of multilayer layer perceptron (MLP), k-nearest neighbors (KNN), quadratic discriminant analysis (QDA), logistic regression (LR), and support vector machine (SVM) was done. It was found that SVM radial required further improvisation to attain a maximum possible level of accuracy. Comparative analysis between SVM and improvised SVM (ISVM) through a 10-fold cross validation method ultimately showed that ISVM resulted in a 2% higher performance in terms of accuracy (98.2%), precision (98.2%), recall (98.1%), and F1 score (98.1%).

【 授权许可】

Unknown