A FEEDFORWARD NEURAL NETWORK CLASSIFIER MODEL: MULTIPLE CLASSES, CONFIDENCE OUTPUT VALUES, AND IMPLEMENTATION

1992 ◽  
Vol 06 (04) ◽  
pp. 539-569
Author(s):  
CRIS KOUTSOUGERAS ◽  
GEORGE GEORGIOU ◽  
CHRISTOS PAPACHRISTOU
Keyword(s):  
Neural Network ◽  
Pattern Classification ◽  
Adaptive Algorithm ◽  
Difficult Problem ◽  
Feedforward Neural Network ◽  
Neural Network Classifier ◽  
Optical Processing ◽  
Internal Representations ◽  
Processing Elements ◽  
And Function

The Athena model is a tree-like net for pattern classification. This paper presents the formalisms on which the model's internal representations and function are based. It also presents an adaptive algorithm to be used with this model. The adaptation is based on entropy optimization. The difficult problem of the optimization is handled by use of Fisher's multiple discriminants method. A method is also presented by which confidence values are produced for the overall classification decision. Finally, a data flow architecture using optical processing elements is considered for the model's implementation.

MULTICHANNEL DECODING FOR PHASE-CODED SSVEP BRAIN–COMPUTER INTERFACE

2012 ◽  
Vol 22 (05) ◽  
pp. 1250022 ◽  
Author(s):  
NIKOLAY V. MANYAKOV ◽  
NIKOLAY CHUMERIN ◽  
MARC M. VAN HULLE
Keyword(s):  
Neural Network ◽  
Single Channel ◽  
Brain Computer Interface ◽  
Feedforward Neural Network ◽  
Computer Interface ◽  
Neural Network Classifier ◽  
Selection Strategies ◽  
Multilayer Feedforward Neural Network ◽  
The One ◽  
Complex Valued

We propose a complex-valued multilayer feedforward neural network classifier for decoding of phase-coded information from steady-state visual evoked potentials. To optimize the performance of the classifier we supply it with two filter-based feature selection strategies. The proposed approaches could be used for a phase-coded brain–computer interface, enabling to encode several targets using only one stimulation frequency. The proposed classifier is a multichannel one, which distinguishes our approach from the existing single-channel ones. We show that the proposed approach outperforms others in terms of accuracy and length of the data segments used for decoding. We show that the decoding based on one optimally selected channel yields an inferior performance compared to the one based on several features, which supports our argument for a multichannel approach.

scholarly journals A Novel Neural Network Classifier Using Beetle Antennae Search Algorithm for Pattern Classification

IEEE Access ◽  
2019 ◽  
Vol 7 ◽  
pp. 64686-64696 ◽  
Author(s):  
Qing Wu ◽  
Zheping Ma ◽  
Gang Xu ◽  
Shuai Li ◽  
Dechao Chen
Keyword(s):  
Neural Network ◽  
Pattern Classification ◽  
Search Algorithm ◽  
Neural Network Classifier

Image Recognition and Counting for the Bacilli Cell Based on the Microscopic Image

2014 ◽  
Vol 651-653 ◽  
pp. 2318-2321
Author(s):  
Min Tan ◽  
Ji Kang Zhong ◽  
Guo Zhao Zhang ◽  
Zhi Xiang Hu
Keyword(s):  
Neural Network ◽  
Small Area ◽  
Object Segmentation ◽  
Single Layer ◽  
Difficult Problem ◽  
Microscopic Image ◽  
Neural Network Classifier ◽  
Recognition Method ◽  
Accurate Identification ◽  
Intelligent Recognition

In order to automatically detect bacilli in sputum image with microscopy, an intelligent recognition method based on machine vision is presented. Firstly, a novel background filter was designed based on the single layer perceptron to realize object segmentation from background. After eliminating the short twig and small area noise, the suspicious goals and the image noise are separated. In the feature extraction, besides the base features of single bacillus two important features are presented to solve the difficult problem of identification and counting for the overlapping and winding bacilli cells. Finally, an EBP neural network classifier is designed for the accurate identification and counting of the bacilli cells. Experimental results verified the effectiveness of the presented method.

Sign in / Sign up

Export Citation Format

Share Document