Expectation-Maximization Method for EEG-Based Continuous Cursor Control
<p/> <p>To develop effective learning algorithms for continuous prediction of cursor movement using EEG signals is a challenging research issue in brain-computer interface (BCI). In this paper, we propose a novel statistical approach based on expectation-maximization (EM) method to learn...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2007-01-01
|
| Series: | EURASIP Journal on Advances in Signal Processing |
| Online Access: | http://asp.eurasipjournals.com/content/2007/049037 |
| _version_ | 1819026066265604096 |
|---|---|
| author | Guan Cuntai Wu Jiankang Zhu Xiaoyuan Cheng Yimin Wang Yixiao |
| author_facet | Guan Cuntai Wu Jiankang Zhu Xiaoyuan Cheng Yimin Wang Yixiao |
| author_sort | Guan Cuntai |
| collection | DOAJ |
| description | <p/> <p>To develop effective learning algorithms for continuous prediction of cursor movement using EEG signals is a challenging research issue in brain-computer interface (BCI). In this paper, we propose a novel statistical approach based on expectation-maximization (EM) method to learn the parameters of a classifier for EEG-based cursor control. To train a classifier for continuous prediction, trials in training data-set are first divided into segments. The difficulty is that the actual intention (label) at each time interval (segment) is unknown. To handle the uncertainty of the segment label, we treat the unknown labels as the hidden variables in the lower bound on the log posterior and maximize this lower bound via an EM-like algorithm. Experimental results have shown that the averaged accuracy of the proposed method is among the best.</p> |
| first_indexed | 2024-12-21T05:20:40Z |
| format | Article |
| id | doaj.art-bee14f093a7844bd9424cb021cefd002 |
| institution | Directory Open Access Journal |
| issn | 1687-6172 1687-6180 |
| language | English |
| last_indexed | 2024-12-21T05:20:40Z |
| publishDate | 2007-01-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | EURASIP Journal on Advances in Signal Processing |
| spelling | doaj.art-bee14f093a7844bd9424cb021cefd0022022-12-21T19:14:49ZengSpringerOpenEURASIP Journal on Advances in Signal Processing1687-61721687-61802007-01-0120071049037Expectation-Maximization Method for EEG-Based Continuous Cursor ControlGuan CuntaiWu JiankangZhu XiaoyuanCheng YiminWang Yixiao<p/> <p>To develop effective learning algorithms for continuous prediction of cursor movement using EEG signals is a challenging research issue in brain-computer interface (BCI). In this paper, we propose a novel statistical approach based on expectation-maximization (EM) method to learn the parameters of a classifier for EEG-based cursor control. To train a classifier for continuous prediction, trials in training data-set are first divided into segments. The difficulty is that the actual intention (label) at each time interval (segment) is unknown. To handle the uncertainty of the segment label, we treat the unknown labels as the hidden variables in the lower bound on the log posterior and maximize this lower bound via an EM-like algorithm. Experimental results have shown that the averaged accuracy of the proposed method is among the best.</p>http://asp.eurasipjournals.com/content/2007/049037 |
| spellingShingle | Guan Cuntai Wu Jiankang Zhu Xiaoyuan Cheng Yimin Wang Yixiao Expectation-Maximization Method for EEG-Based Continuous Cursor Control EURASIP Journal on Advances in Signal Processing |
| title | Expectation-Maximization Method for EEG-Based Continuous Cursor Control |
| title_full | Expectation-Maximization Method for EEG-Based Continuous Cursor Control |
| title_fullStr | Expectation-Maximization Method for EEG-Based Continuous Cursor Control |
| title_full_unstemmed | Expectation-Maximization Method for EEG-Based Continuous Cursor Control |
| title_short | Expectation-Maximization Method for EEG-Based Continuous Cursor Control |
| title_sort | expectation maximization method for eeg based continuous cursor control |
| url | http://asp.eurasipjournals.com/content/2007/049037 |
| work_keys_str_mv | AT guancuntai expectationmaximizationmethodforeegbasedcontinuouscursorcontrol AT wujiankang expectationmaximizationmethodforeegbasedcontinuouscursorcontrol AT zhuxiaoyuan expectationmaximizationmethodforeegbasedcontinuouscursorcontrol AT chengyimin expectationmaximizationmethodforeegbasedcontinuouscursorcontrol AT wangyixiao expectationmaximizationmethodforeegbasedcontinuouscursorcontrol |