Research article · 2017
ArticlePublished 26 Dec 2013
Improving Classification by Feature Discretization and Optimization for fNIRS-based BCI
State Key Laboratory of Robotics, Shenyang Institute of Automation (SIA), Chinese Academy of Sciences (CAS), Shenyang, P. R. China; University of Chinese Academy of Sciences, Beijing, P. R. China; School of Automation and Information Engineering, Kunming University of Science and Technology, Kunming, P. R. China; Department of Advanced Robotics, Chiba Institute of Technology, Chiba, Japan; School of Mechanical Engineering & Automation, Northeastern University, Shenyang, China
Abstract
Select any words in the title or abstract, or press this and choose a sentence.
In this paper, we present a signal discretization and feature selection method to improve classification accuracy for fNIRS based brain computer interface (BCI) system, which can classifiy right hand clench force motor imagery and clench speed motor imagery at an accuracy of 69%-81% through 5 fold cross validation in 6 subjects. Difference between oxyhemoglobin and deoxyhemoglobin (we abbreviate this difference as HbD) is proposed as a new feature type and shows outstanding performance in some subjects. Linear kernal support vector machine (SVM) classification between clench force motor imagery and clench speed motor imagery using four concentration feature types (oxyhemoglobin, deoxyhemoglobin, totalhemoglobin, and HbD) is implemented. Our results demonstrate that feature discretization using Chi2 algorighm and feature optimization using ‘MIFS’ (Mutual Information Feature Selection) criterion can improve the classification accuracy by more than 35%. Except total hemoglobin, all the other three feature types can be used as the optimum feature for different subjects. The results of this paper can also be used in online BCI applications.
Subjects
EngineeringMaterials ScienceAsk about this article
Answers come only from this article's title, abstract and keywords, each sentence pointing to where it comes from. Your question is sent to OpenAI to write the answer. Scholars Central does not store it.
Similar by topic
Conference abstract · 15 Jun 2015
Active vibration control of smart structures bonded with discrete piezoelectric sensors and actuators located optimally using a reduced genetic algorithm
Research article · 16 Apr 2016
Optimization Algorithms for Feature Selection in Classification: A Survey
Research article · Feb 2014
Classification of Microarray Data Based On Feature Selection Method
Conference abstract · 15 Jun 2020
Luminescence chemosensors based on polythiophene and Covalent Polymers Containing Discrete Heterocyclic Anion Receptors- Nanomaterials 2017, March 30-31, 2017, Madrid, Spain
More from this journal
The newest in Journal of Biomimetics Biomaterials and Tissue Engineering.
Article · 13 Feb 2014
Graft Materials in Oral Surgery: Revision
Article · 3 Feb 2014
Hydrogels as Biomaterials – How Long More is the Road Ahead?
Article · 28 Jan 2014
A Vague Set Based Model for Regional Blood Supply and Demand Balance Adjustment
Conferences in this field
Upcoming conferences in this field.
Follow
New articles from what you follow go into your email digest, once you agree to alert emails.
- JournalJournal of Biomimetics Biomaterials and Tissue Engineering
- SubjectEngineering
- SubjectMaterials Science
- BylineArticles whose byline prints “Baolei Xu”
- BylineArticles whose byline prints “Yunfa Fu”
- BylineArticles whose byline prints “Gang Shi”
- BylineArticles whose byline prints “Xuxian Yin”
- BylineArticles whose byline prints “Zhidong Wang”
- BylineArticles whose byline prints “Hongyi Li”
