Runtime Calibration of Online EEG based Movement Prediction using EMG Signals

In recent years Extreme Learning Machine (ELM) has gained the interest of various researchers due to its superior generalization and approximation capability. The network architecture and type of activation functions are the two important factors that influence the performance of an ELM. Hence in this study, a Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) oriented multi-criteria decision making (MCDM) framework is suggested for analyzing various ELM models developed with distinct activation functions with respect to sixteen evaluation criteria. Evaluating the performance of the ELM with respect to multiple criteria instead of single criterion can help in designing a more robust network. The proposed framework is used as a binary classification system for pursuing the problem of stock index price movement prediction. The model is empirically evaluated by using historical data of three stock indices such as BSE SENSEX, S&P 500 and NIFTY 50. The empirical study has disclosed promising results by evaluating ELM with different activation functions as well as multiple criteria.

Download Full-text

Eye movement prediction and variability on natural video data sets

Visual Cognition ◽

10.1080/13506285.2012.667456 ◽

2012 ◽

Vol 20 (4-5) ◽

pp. 495-514 ◽

Cited By ~ 9

Author(s):

Michael Dorr ◽

Eleonora Vig ◽

Erhardt Barth

Keyword(s):

Eye Movement ◽

Video Data ◽

Data Sets ◽

Movement Prediction

Download Full-text

Comprehensive Analysis of Automatic Identification System (AIS) Data in Regard to Vessel Movement Prediction

Journal of Navigation ◽

10.1017/s0373463314000253 ◽

2014 ◽

Vol 67 (5) ◽

pp. 791-809 ◽

Cited By ~ 32

Author(s):

Philipp Last ◽

Christian Bahlke ◽

Martin Hering-Bertram ◽

Lars Linsen

Keyword(s):

Large Data ◽

Automatic Identification ◽

Identification System ◽

Very High Frequency ◽

Database Queries ◽

Related Data ◽

Movement Prediction ◽

Time Period ◽

Current Usage ◽

Exchange Vessel

AIS was primarily developed to exchange vessel-related data among vessels or AIS stations by using very-high frequency (VHF) technology to increase safety at sea. This study evaluates the formal integrity, availability, and the reporting intervals of AIS data with a focus on vessel movement prediction. In contrast to former studies, this study is based on a large data collection of over 85 million AIS messages, which were continuously received within a time period of two months. Thus, the evaluated data represent a comprehensive and up-to-date view of the current usage of AIS systems installed on vessels. Results of previous studies concerning the availability of AIS data are confirmed and extended. New aspects such as reporting intervals are additionally evaluated. Received messages are stored in a database, which allows for performing database queries to evaluate the obtained data in an automatic way. This study shows that almost ten years after becoming mandatory for professional operating vessels, AIS still lacks availability for both static and dynamic data and that the reporting intervals are not as reliable as specified within the technical AIS standard.

Download Full-text