Evaluation and Exploration of Machine Learning and Convolutional Neural Network Classifiers in Detection of Lung Cancer from Microarray Gene—A Paradigm Shift
Microarray gene expression-based detection and classification of medical conditions have been prominent in research studies over the past few decades. However, extracting relevant data from the high-volume microarray gene expression with inherent nonlinearity and inseparable noise components raises...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-08-01
|
| Series: | Bioengineering |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2306-5354/10/8/933 |
| _version_ | 1797585432349769728 |
|---|---|
| author | Karthika M S Harikumar Rajaguru Ajin R. Nair |
| author_facet | Karthika M S Harikumar Rajaguru Ajin R. Nair |
| author_sort | Karthika M S |
| collection | DOAJ |
| description | Microarray gene expression-based detection and classification of medical conditions have been prominent in research studies over the past few decades. However, extracting relevant data from the high-volume microarray gene expression with inherent nonlinearity and inseparable noise components raises significant challenges during data classification and disease detection. The dataset used for the research is the Lung Harvard 2 Dataset (LH2) which consists of 150 Adenocarcinoma subjects and 31 Mesothelioma subjects. The paper proposes a two-level strategy involving feature extraction and selection methods before the classification step. The feature extraction step utilizes Short Term Fourier Transform (STFT), and the feature selection step employs Particle Swarm Optimization (PSO) and Harmonic Search (HS) metaheuristic methods. The classifiers employed are Nonlinear Regression, Gaussian Mixture Model, Softmax Discriminant, Naive Bayes, SVM (Linear), SVM (Polynomial), and SVM (RBF). The two-level extracted relevant features are compared with raw data classification results, including Convolutional Neural Network (CNN) methodology. Among the methods, STFT with PSO feature selection and SVM (RBF) classifier produced the highest accuracy of 94.47%. |
| first_indexed | 2024-03-11T00:06:01Z |
| format | Article |
| id | doaj.art-0bfb36baa4d2499d9de460b13b84a7db |
| institution | Directory Open Access Journal |
| issn | 2306-5354 |
| language | English |
| last_indexed | 2024-03-11T00:06:01Z |
| publishDate | 2023-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Bioengineering |
| spelling | doaj.art-0bfb36baa4d2499d9de460b13b84a7db2023-11-19T00:18:02ZengMDPI AGBioengineering2306-53542023-08-0110893310.3390/bioengineering10080933Evaluation and Exploration of Machine Learning and Convolutional Neural Network Classifiers in Detection of Lung Cancer from Microarray Gene—A Paradigm ShiftKarthika M S0Harikumar Rajaguru1Ajin R. Nair2Department of Information Technology, Bannari Amman Institute of Technology, Sathyamangalam 638401, IndiaDepartment of Electronics and Communication Engineering, Bannari Amman Institute of Technology, Sathyamangalam 638401, IndiaDepartment of Electronics and Communication Engineering, Bannari Amman Institute of Technology, Sathyamangalam 638401, IndiaMicroarray gene expression-based detection and classification of medical conditions have been prominent in research studies over the past few decades. However, extracting relevant data from the high-volume microarray gene expression with inherent nonlinearity and inseparable noise components raises significant challenges during data classification and disease detection. The dataset used for the research is the Lung Harvard 2 Dataset (LH2) which consists of 150 Adenocarcinoma subjects and 31 Mesothelioma subjects. The paper proposes a two-level strategy involving feature extraction and selection methods before the classification step. The feature extraction step utilizes Short Term Fourier Transform (STFT), and the feature selection step employs Particle Swarm Optimization (PSO) and Harmonic Search (HS) metaheuristic methods. The classifiers employed are Nonlinear Regression, Gaussian Mixture Model, Softmax Discriminant, Naive Bayes, SVM (Linear), SVM (Polynomial), and SVM (RBF). The two-level extracted relevant features are compared with raw data classification results, including Convolutional Neural Network (CNN) methodology. Among the methods, STFT with PSO feature selection and SVM (RBF) classifier produced the highest accuracy of 94.47%.https://www.mdpi.com/2306-5354/10/8/933lung cancer classificationdimensionality reductionfeature selection techniquesShort Term Fourier TransformParticle Swarm OptimizationHarmonic Search |
| spellingShingle | Karthika M S Harikumar Rajaguru Ajin R. Nair Evaluation and Exploration of Machine Learning and Convolutional Neural Network Classifiers in Detection of Lung Cancer from Microarray Gene—A Paradigm Shift Bioengineering lung cancer classification dimensionality reduction feature selection techniques Short Term Fourier Transform Particle Swarm Optimization Harmonic Search |
| title | Evaluation and Exploration of Machine Learning and Convolutional Neural Network Classifiers in Detection of Lung Cancer from Microarray Gene—A Paradigm Shift |
| title_full | Evaluation and Exploration of Machine Learning and Convolutional Neural Network Classifiers in Detection of Lung Cancer from Microarray Gene—A Paradigm Shift |
| title_fullStr | Evaluation and Exploration of Machine Learning and Convolutional Neural Network Classifiers in Detection of Lung Cancer from Microarray Gene—A Paradigm Shift |
| title_full_unstemmed | Evaluation and Exploration of Machine Learning and Convolutional Neural Network Classifiers in Detection of Lung Cancer from Microarray Gene—A Paradigm Shift |
| title_short | Evaluation and Exploration of Machine Learning and Convolutional Neural Network Classifiers in Detection of Lung Cancer from Microarray Gene—A Paradigm Shift |
| title_sort | evaluation and exploration of machine learning and convolutional neural network classifiers in detection of lung cancer from microarray gene a paradigm shift |
| topic | lung cancer classification dimensionality reduction feature selection techniques Short Term Fourier Transform Particle Swarm Optimization Harmonic Search |
| url | https://www.mdpi.com/2306-5354/10/8/933 |
| work_keys_str_mv | AT karthikams evaluationandexplorationofmachinelearningandconvolutionalneuralnetworkclassifiersindetectionoflungcancerfrommicroarraygeneaparadigmshift AT harikumarrajaguru evaluationandexplorationofmachinelearningandconvolutionalneuralnetworkclassifiersindetectionoflungcancerfrommicroarraygeneaparadigmshift AT ajinrnair evaluationandexplorationofmachinelearningandconvolutionalneuralnetworkclassifiersindetectionoflungcancerfrommicroarraygeneaparadigmshift |