Automatic Landmarking of 2D Medical Shapes Using the Growing Neural Gas Network

2005 ◽  
pp. 210-219 ◽  
Author(s):  
Anastassia Angelopoulou ◽  
Alexandra Psarrou ◽  
José García Rodríguez ◽  
Kenneth Revett
Keyword(s):  
Growing Neural Gas ◽  
Gas Network ◽  
Neural Gas

scholarly journals Evaluation of different chrominance models in the detection and reconstruction of faces and hands using the growing neural gas network

2019 ◽  
Vol 22 (4) ◽  
pp. 1667-1685 ◽  
Author(s):  
Anastassia Angelopoulou ◽  
Jose Garcia-Rodriguez ◽  
Sergio Orts-Escolano ◽  
Epaminondas Kapetanios ◽  
Xing Liang ◽  
...  
Keyword(s):  
Growing Neural Gas ◽  
Gas Network ◽  
Neural Gas

scholarly journals Hierarchical Growing Neural Gas Network (HGNG)-Based Semicooperative Feature Classifier for IDS in Vehicular Ad Hoc Network (VANET)

2018 ◽  
Vol 7 (3) ◽  
pp. 41 ◽  
Author(s):  
Ayoob Ayoob ◽  
Gang Su ◽  
Gaith Al
Keyword(s):  
Ad Hoc Network ◽  
Ad Hoc ◽  
Detection System ◽  
Vehicular Ad Hoc Network ◽  
Location Information ◽  
Detection Accuracy ◽  
Processing Efficiency ◽  
Growing Neural Gas ◽  
Gas Network ◽  
Neural Gas

In this research, new modeling strategy based hierarchical growing neural gas network (HGNG)-semicooperative for feature classifier of intrusion detection system (IDS) in a vehicular ad hoc network (VANET). The novel IDS mainly presents a new design feature for an extraction mechanism and a HGNG-based classifier. Firstly, the traffic flow features and vehicle location features were extracted in the VANET model. In order to effectively extract location features, a semicooperative feature extraction is used for collecting the current location information for the neighboring vehicles through a cooperative manner and the location features of the historical location information. Secondly, the HGNG-based classifier was designed for evaluating the IDS by using a hierarchy learning process without the limitation of the fix lattice topology. Finally, an additional two-step confirmation mechanism is used to accurately determine the abnormal vehicle messages. In the experiment, the proposed IDS system was evaluated, observed, and compared with the existing IDS. The proposed system performed a remarkable detection accuracy, stability, processing efficiency, and message load.

Writing in the Air Using Kinect and Growing Neural Gas Network

2015 ◽  
Vol 72 (5) ◽  
Author(s):  
Mohammad Reza Aminian Heidari ◽  
Azrulhizam Shapi’i ◽  
Riza Sulaiman
Keyword(s):  
Character Recognition ◽  
English Language ◽  
Noise Tolerance ◽  
Recognition Method ◽  
Accuracy Rate ◽  
Growing Neural Gas ◽  
Gas Network ◽  
Neural Gas ◽  
Kinect Camera ◽  
Lower Case

This paper discusses an approach which helps us to recognize English language characters which are written in the air by hands. This method is done by using Kinect camera and growing neural gas network. The proposed character recognition method has three main steps: preprocessing, training and recognition. The system and the proposed method can be considered from two aspects: (a) runtime, and (b) accuracy. One of the main goals in this method is to provide noise tolerance which is necessary for these kinds of methods. IN addition, it has influence upon accuracy rate because the proposed method can remove more outliers. The results show that the proposed method provides good results with the accuracy rate of 95.54%, 97.86% and 99.08% for lower case letters, upper case letters and digits respectively.

A new neural gas network approach for obtaining the singularity-free workspace of 3-DOF planar parallel manipulators

2016 ◽  
Vol 232 (1) ◽  
pp. 174-189 ◽  
Author(s):  
Roya Sabbagh Novin ◽  
Mehdi Tale Masouleh ◽  
Mojtaba Yazdani
Keyword(s):  
Parallel Manipulators ◽  
Performance Criterion ◽  
Easy Access ◽  
Data Generation ◽  
Parallel Mechanisms ◽  
Growing Neural Gas ◽  
Gas Network ◽  
Neural Gas ◽  
Highly Nonlinear ◽  
Three Degree Of Freedom

This paper proposes a new extension of the Growing Neural Gas Network, called the Progressive Growing Neural Gas Network (PGNGN), for the application of kinematic investigation of parallel mechanisms, with more emphasis on the singularity-free workspace determination. In fact, PGNGN leads to a general approach in order to obtain the topology of the workspace. In this algorithm, the network starts to grow by taking into account new data points close to its border neurons by resorting to the so-called boundary data generation procedure. By considering singularity loci expression, the separated parts are detected and each part will pursue learning, adding units and connections, until a given performance criterion will be reached. Finally, after finding cavities, if any exists, the maximal circle for each part of the workspace is found. A graphical user interface (GUI) is developed providing the users with easy access to the important parameters in which the singularity-free workspace of three planar three-degree-of-freedom (3-DOF) parallel mechanisms are investigated in which two of them, namely, 3-RRR and 3-PRR parallel mechanisms, are among the most complicated parallel mechanisms due to their highly nonlinear and complicated singularity loci expressions. Results reveal the applicability and reliability of the proposed PGNGN-based approach for obtaining the singularity-free workspace of planar parallel mechanisms.

Sign in / Sign up

Export Citation Format

Share Document