Data and feature mixed ensemble based extreme learning machine for medical object detection and segmentation
Extreme learning machine (ELM) is a single-hidden layer feed-forward neural network with an efficient learning algorithm. Conventionally an ELM is trained using all the data based on the least square solution, and thus it may suffer from overfitting. In this final year project paper, we present a ne...
| מחבר ראשי: | |
|---|---|
| מחברים אחרים: | |
| פורמט: | Final Year Project (FYP) |
| שפה: | English |
| יצא לאור: |
2015
|
| נושאים: | |
| גישה מקוונת: | http://hdl.handle.net/10356/63600 |
| _version_ | 1826112828678864896 |
|---|---|
| author | Zhu, Wan Zheng |
| author2 | Huang Weimin |
| author_facet | Huang Weimin Zhu, Wan Zheng |
| author_sort | Zhu, Wan Zheng |
| collection | NTU |
| description | Extreme learning machine (ELM) is a single-hidden layer feed-forward neural network with an efficient learning algorithm. Conventionally an ELM is trained using all the data based on the least square solution, and thus it may suffer from overfitting. In this final year project paper, we present a new method of data and feature mixed ensemble based extreme learning machine (DFEN-ELM). DFEN-ELM combines data ensemble and feature subspace ensemble to tackle the overfitting problem and it takes advantage of the fast speed of ELM when building ensembles of classifiers. Both one-class and two-class ensemble based ELM have been studied. Experiments were conducted on computed tomography (CT) data for liver tumor detection and segmentation as well as magnetic resonance imaging (MRI) data for rodent brain segmentation. To improve the ensembles with new training data, sequential kernel learning is adopted further in the experiments on CT data for speedy retraining and iteratively enhancing the image segmentation performance. Experiment results on different testing cases and various testing datasets demonstrate that DFEN-ELM is a robust and efficient algorithm for medical object detection and segmentation. |
| first_indexed | 2024-10-01T03:13:12Z |
| format | Final Year Project (FYP) |
| id | ntu-10356/63600 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T03:13:12Z |
| publishDate | 2015 |
| record_format | dspace |
| spelling | ntu-10356/636002023-07-07T16:10:55Z Data and feature mixed ensemble based extreme learning machine for medical object detection and segmentation Zhu, Wan Zheng Huang Weimin Lin Zhiping School of Electrical and Electronic Engineering A*STAR Institute for Infocomm Research DRNTU::Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision Extreme learning machine (ELM) is a single-hidden layer feed-forward neural network with an efficient learning algorithm. Conventionally an ELM is trained using all the data based on the least square solution, and thus it may suffer from overfitting. In this final year project paper, we present a new method of data and feature mixed ensemble based extreme learning machine (DFEN-ELM). DFEN-ELM combines data ensemble and feature subspace ensemble to tackle the overfitting problem and it takes advantage of the fast speed of ELM when building ensembles of classifiers. Both one-class and two-class ensemble based ELM have been studied. Experiments were conducted on computed tomography (CT) data for liver tumor detection and segmentation as well as magnetic resonance imaging (MRI) data for rodent brain segmentation. To improve the ensembles with new training data, sequential kernel learning is adopted further in the experiments on CT data for speedy retraining and iteratively enhancing the image segmentation performance. Experiment results on different testing cases and various testing datasets demonstrate that DFEN-ELM is a robust and efficient algorithm for medical object detection and segmentation. Bachelor of Engineering 2015-05-15T07:15:03Z 2015-05-15T07:15:03Z 2015 2015 Final Year Project (FYP) http://hdl.handle.net/10356/63600 en Nanyang Technological University 50 p. application/pdf |
| spellingShingle | DRNTU::Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision Zhu, Wan Zheng Data and feature mixed ensemble based extreme learning machine for medical object detection and segmentation |
| title | Data and feature mixed ensemble based extreme learning machine for medical object detection and segmentation |
| title_full | Data and feature mixed ensemble based extreme learning machine for medical object detection and segmentation |
| title_fullStr | Data and feature mixed ensemble based extreme learning machine for medical object detection and segmentation |
| title_full_unstemmed | Data and feature mixed ensemble based extreme learning machine for medical object detection and segmentation |
| title_short | Data and feature mixed ensemble based extreme learning machine for medical object detection and segmentation |
| title_sort | data and feature mixed ensemble based extreme learning machine for medical object detection and segmentation |
| topic | DRNTU::Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision |
| url | http://hdl.handle.net/10356/63600 |
| work_keys_str_mv | AT zhuwanzheng dataandfeaturemixedensemblebasedextremelearningmachineformedicalobjectdetectionandsegmentation |