Improved extreme learning machine for spectra classification of Covid-19
In recent years, the novel coronavirus has had profound impacts on various countries and industries worldwide. This study aims to investigate the novel coronavirus first identified in 2019, characterized as a novel single-stranded RNA virus that easily infects the human respiratory system. Currently...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis-Master by Coursework |
| Language: | English |
| Published: |
Nanyang Technological University
2024
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/173689 |
| _version_ | 1811697601088585728 |
|---|---|
| author | Wang, Changyang |
| author2 | Lin Zhiping |
| author_facet | Lin Zhiping Wang, Changyang |
| author_sort | Wang, Changyang |
| collection | NTU |
| description | In recent years, the novel coronavirus has had profound impacts on various countries and industries worldwide. This study aims to investigate the novel coronavirus first identified in 2019, characterized as a novel single-stranded RNA virus that easily infects the human respiratory system. Currently, the screening and diagnosis of the novel coronavirus primarily rely on nucleic acid testing, and the machine learning-based classification screening often employs traditional convolutional neural networks. However, this approach is not suitable for real-time rapid virus detection. In this dissertation, we meticulously compare three sets of preprocessing methods and seven feature selection and extraction methods to determine the optimal data preprocessing and feature extraction techniques. Simultaneously, based on the traditional Extreme Learning Machine (ELM), we propose a two-layer classification network combining the Extreme Learning Machine-Radial Basis Function (ELM-RBF) and Sparse Representation Classification (SRC). Compared to traditional ELM classification networks, our method exhibits superior performance. Ultimately, the comprehensive neural network classification system proposed in this study (employing SNV+second-order derivative preprocessing, Relief algorithm for feature extraction, and ELMRBF-SRC as the classifier) achieves impressive accuracy, sensitivity, and specificity, reaching 94.27%, 88.19%, and 97.64%, respectively. This study demonstrates the feasibility of using near-infrared spectroscopy based on throat swab sample extracts for the relatively straightforward system classification of COVID-19. |
| first_indexed | 2024-10-01T07:57:51Z |
| format | Thesis-Master by Coursework |
| id | ntu-10356/173689 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T07:57:51Z |
| publishDate | 2024 |
| publisher | Nanyang Technological University |
| record_format | dspace |
| spelling | ntu-10356/1736892024-02-23T15:44:24Z Improved extreme learning machine for spectra classification of Covid-19 Wang, Changyang Lin Zhiping School of Electrical and Electronic Engineering EZPLin@ntu.edu.sg Engineering Machine Learning ELM Spectrum classification Feature selection In recent years, the novel coronavirus has had profound impacts on various countries and industries worldwide. This study aims to investigate the novel coronavirus first identified in 2019, characterized as a novel single-stranded RNA virus that easily infects the human respiratory system. Currently, the screening and diagnosis of the novel coronavirus primarily rely on nucleic acid testing, and the machine learning-based classification screening often employs traditional convolutional neural networks. However, this approach is not suitable for real-time rapid virus detection. In this dissertation, we meticulously compare three sets of preprocessing methods and seven feature selection and extraction methods to determine the optimal data preprocessing and feature extraction techniques. Simultaneously, based on the traditional Extreme Learning Machine (ELM), we propose a two-layer classification network combining the Extreme Learning Machine-Radial Basis Function (ELM-RBF) and Sparse Representation Classification (SRC). Compared to traditional ELM classification networks, our method exhibits superior performance. Ultimately, the comprehensive neural network classification system proposed in this study (employing SNV+second-order derivative preprocessing, Relief algorithm for feature extraction, and ELMRBF-SRC as the classifier) achieves impressive accuracy, sensitivity, and specificity, reaching 94.27%, 88.19%, and 97.64%, respectively. This study demonstrates the feasibility of using near-infrared spectroscopy based on throat swab sample extracts for the relatively straightforward system classification of COVID-19. Master's degree 2024-02-23T02:39:23Z 2024-02-23T02:39:23Z 2024 Thesis-Master by Coursework Wang, C. (2024). Improved extreme learning machine for spectra classification of Covid-19. Master's thesis, Nanyang Technological University, Singapore. https://hdl.handle.net/10356/173689 https://hdl.handle.net/10356/173689 en application/pdf Nanyang Technological University |
| spellingShingle | Engineering Machine Learning ELM Spectrum classification Feature selection Wang, Changyang Improved extreme learning machine for spectra classification of Covid-19 |
| title | Improved extreme learning machine for spectra classification of Covid-19 |
| title_full | Improved extreme learning machine for spectra classification of Covid-19 |
| title_fullStr | Improved extreme learning machine for spectra classification of Covid-19 |
| title_full_unstemmed | Improved extreme learning machine for spectra classification of Covid-19 |
| title_short | Improved extreme learning machine for spectra classification of Covid-19 |
| title_sort | improved extreme learning machine for spectra classification of covid 19 |
| topic | Engineering Machine Learning ELM Spectrum classification Feature selection |
| url | https://hdl.handle.net/10356/173689 |
| work_keys_str_mv | AT wangchangyang improvedextremelearningmachineforspectraclassificationofcovid19 |