Investigating the performance improvement by sampling techniques in EEG data
Journal Title: International Journal on Computer Science and Engineering - Year 2010, Vol 2, Issue 6
Abstract
In this paper the performance of oversampling methods such as SMOTE (Synthetic Minority Over-sampling Technique) and PCA (Principal Component Analysis) which are used for preprocessing are applied for the Brain computer interface dataset. The pre-processed data is used for classification by SMO and Naïve Bayes. In the EEG recordings, the transient events are detected while predicting the conditions of Central Nervous System and are classified as epileptic spikes, muscle activity, eye blinking activity and sharp alpha activity. The Preprocessing technique SMOTE is an over-sampling method which combines the informed over-sampling of minority class with random under-sampling of the majority class. Principal Component Analysis (PCA) is an exploratory data analysis technique. It involves a mathematical procedure which transforms a number of possibly correlated variables into smaller number of uncorrelated variables called Principal Components. It is mostly used as a tool in data analysis and for making predictive models. Based on the experimental results derived through SMOTE and PCA when they are applied to SMO and Naïve Bayes, it is concluded that PCA can be a better option since its performance improvement is better than that of SMOTE.
Authors and Affiliations
Mrs. V. Baby Deepa , Dr. P. Thangaraj. , Dr. S. Chitra
Keywords
Related Articles
- EP ID EP129447
- DOI -
- Views 125
- Downloads 0
Handwritten Gurmukhi Character Recognition Using Statistical and Background Directional Distribution Features
In this manuscript handwritten Gurmukhi character recognition for isolated characters is proposed. We have used some statistical features like zonal density, projection histograms (horizontal, vertical and both diagonal)...
Hidden Web Data Extraction Using Dynamic Rule Generation
World Wide Web is a global information medium of interlinked hypertext documents accessed via computers connected to the internet. Most of the users rely on traditional search engines to search the information on the web...
Query Optimization on Compressed and Decompressed Object-Oriented Database Using Operators
In this paper, we present an approach using various database operators that permits to enrich technique of query ptimization existing in the objectoriented databases and the comparative analysis of query optimization of...
Energy Efficient Adaptive Clustering for Heterogeneous Sensor Networks with power control
Wireless sensor networks are energy constraint battery powered sensing, computing and communication infrastructure. Sensor nodes are randomly deployed and organized as clusters, and each node is responsible for transmitt...
Wirelss Security on Security Standard Policy: A Case Studty
Administrators of a network have a variety of different uthentication and encryption technologies to choose from. Administrators must also take into account a variety of organizational factors, not just of technical fac...