An Improvised Machine Learning Model Based on Mutual Information Feature Selection Approach for Microbes Classification
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 ge...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-02-01
|
| Series: | Entropy |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1099-4300/23/2/257 |
| id |
doaj-d2795d33e0ce48a49264ea89aacfb8b6 |
|---|---|
| record_format |
Article |
| spelling |
doaj-d2795d33e0ce48a49264ea89aacfb8b62021-02-24T00:03:23ZengMDPI AGEntropy1099-43002021-02-012325725710.3390/e23020257An Improvised Machine Learning Model Based on Mutual Information Feature Selection Approach for Microbes ClassificationAnaahat Dhindsa0Sanjay Bhatia1Sunil Agrawal2Balwinder Singh Sohi3Department of Electronics and Communication Engineering, Chandigarh University, Gharuan, Punjab 140413, IndiaP.G Department of Zoology, University of Jammu, Kashmir 180006, IndiaUniversity Institute of Engineering and Technology, Panjab University, Chandigarh 160014, IndiaDepartment of ECE, Chandigarh University, Gharuan, Punjab 140413, IndiaThe 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%).https://www.mdpi.com/1099-4300/23/2/257mutual informationclassificationk-fold cross validationmachine learning modelingimage segmentationmicroorganisms |
| collection |
DOAJ |
| language |
English |
| format |
Article |
| sources |
DOAJ |
| author |
Anaahat Dhindsa Sanjay Bhatia Sunil Agrawal Balwinder Singh Sohi |
| spellingShingle |
Anaahat Dhindsa Sanjay Bhatia Sunil Agrawal Balwinder Singh Sohi An Improvised Machine Learning Model Based on Mutual Information Feature Selection Approach for Microbes Classification Entropy mutual information classification k-fold cross validation machine learning modeling image segmentation microorganisms |
| author_facet |
Anaahat Dhindsa Sanjay Bhatia Sunil Agrawal Balwinder Singh Sohi |
| author_sort |
Anaahat Dhindsa |
| title |
An Improvised Machine Learning Model Based on Mutual Information Feature Selection Approach for Microbes Classification |
| title_short |
An Improvised Machine Learning Model Based on Mutual Information Feature Selection Approach for Microbes Classification |
| title_full |
An Improvised Machine Learning Model Based on Mutual Information Feature Selection Approach for Microbes Classification |
| title_fullStr |
An Improvised Machine Learning Model Based on Mutual Information Feature Selection Approach for Microbes Classification |
| title_full_unstemmed |
An Improvised Machine Learning Model Based on Mutual Information Feature Selection Approach for Microbes Classification |
| title_sort |
improvised machine learning model based on mutual information feature selection approach for microbes classification |
| publisher |
MDPI AG |
| series |
Entropy |
| issn |
1099-4300 |
| publishDate |
2021-02-01 |
| description |
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%). |
| topic |
mutual information classification k-fold cross validation machine learning modeling image segmentation microorganisms |
| url |
https://www.mdpi.com/1099-4300/23/2/257 |
| work_keys_str_mv |
AT anaahatdhindsa animprovisedmachinelearningmodelbasedonmutualinformationfeatureselectionapproachformicrobesclassification AT sanjaybhatia animprovisedmachinelearningmodelbasedonmutualinformationfeatureselectionapproachformicrobesclassification AT sunilagrawal animprovisedmachinelearningmodelbasedonmutualinformationfeatureselectionapproachformicrobesclassification AT balwindersinghsohi animprovisedmachinelearningmodelbasedonmutualinformationfeatureselectionapproachformicrobesclassification AT anaahatdhindsa improvisedmachinelearningmodelbasedonmutualinformationfeatureselectionapproachformicrobesclassification AT sanjaybhatia improvisedmachinelearningmodelbasedonmutualinformationfeatureselectionapproachformicrobesclassification AT sunilagrawal improvisedmachinelearningmodelbasedonmutualinformationfeatureselectionapproachformicrobesclassification AT balwindersinghsohi improvisedmachinelearningmodelbasedonmutualinformationfeatureselectionapproachformicrobesclassification |
| _version_ |
1724253647381987328 |