CENTROID NEURAL NETWORK WITH WEIGHTED FEATURES

2009 ◽  
Vol 18 (08) ◽  
pp. 1353-1367 ◽  
Author(s):  
DONG-CHUL PARK
Keyword(s):  
Neural Network ◽  
Image Compression ◽  
Objective Function ◽  
Lagrange Multiplier ◽  
Synthetic Data ◽  
Feature Weighting ◽  
The Self ◽  
Self Organizing Map ◽  
Data Set ◽  
Self Organizing

A Centroid Neural Network with Weighted Features (CNN-WF) is proposed and presented in this paper. The proposed CNN-WF is based on a Centroid Neural Network (CNN), an effective clustering tool that has been successfully applied to various problems. In order to evaluate the importance of each feature in a set of data, a feature weighting concept is introduced to the Centroid Neural Network in the proposed algorithm. The weight update equations for CNN-WF are derived by applying the Lagrange multiplier procedure to the objective function constructed for CNN-WF in this paper. The use of weighted features makes it possible to assess the importance of each feature and to reject features that can be considered as noise in data. Experiments on a synthetic data set and a typical image compression problem show that the proposed CNN-WF can assess the importance of each feature and the proposed CNN-WF outperforms conventional algorithms including the Self-Organizing Map (SOM) and CNN in terms of clustering accuracy.

scholarly journals SYNTHESIS OF SELF-ORGANIZING MAP AND FEEDFORWARD NEURAL NETWORK FOR BETTER FORECASTING

2014 ◽  
pp. 68-75
Author(s):  
Oles Hodych ◽  
Yuriy Shcherbyna ◽  
Michael Zylan
Keyword(s):  
Neural Network ◽  
Feedforward Neural Network ◽  
Share Price ◽  
Data Sets ◽  
Self Organizing Map ◽  
Data Set ◽  
Price Fluctuation ◽  
Price Data ◽  
Comparison Results ◽  
Self Organizing

In this article the authors propose an approach to forecasting the direction of the share price fluctuation, which is based on utilization of the Feedforward Neural Network in conjunction with Self-Organizing Map. It is proposed to use the Self-Organizing Map for filtration of the share price data set, whereas the Feedforward Neural Network is used to forecast the direction of the share price fluctuation based on the filtered data set. The comparison results are presented for filtered and non-filtered share price data sets.

scholarly journals A HYBRID KANSEI ENGINEERING SYSTEM USING THE SELF-ORGANIZING MAP NEURAL NETWORK

2016 ◽  
Vol 2 (1) ◽  
pp. 23-38
Author(s):  
C.S. Teh ◽  
C.P. Lim
Keyword(s):  
Neural Network ◽  
Decision Making ◽  
Product Design ◽  
The Self ◽  
Design Parameters ◽  
Decision Making Process ◽  
Engineering System ◽  
Self Organizing Map ◽  
Kansei Engineering ◽  
Self Organizing

Kansei Engineering (KE), a technology founded in Japan initially for product design, translates human feelings into design parameters. Although various intelligent approaches to objectively model human functions and the relationships with the product design decisions have been introduced in KE systems, many of the approaches are not able to incorporate human subjective feelings and preferences into the decision-making process. This paper proposes a new hybrid KE system that attempts to make the machine-based decision-making process closely resembles the real-world practice. The proposed approach assimilates human perceptive and associative abilities into the decision-making process of the computer. A number of techniques based on the Self-Organizing Map (SOM) neural network are employed in the backward KE system to reveal the underlying data structures that are involved in the decision-making process. A case study on interior design is presented to evaluate the efficacy of the proposed approach. The results obtained demonstrate the effectiveness of the proposed approach in developing an intelligent KE system which is able to combine human feelings and preferences into its decision making process.

scholarly journals Haptic Perception with Self-Organizing ANNs and an Anthropomorphic Robot Hand

2010 ◽  
Vol 2010 ◽  
pp. 1-9 ◽  
Author(s):  
Magnus Johnsson ◽  
Christian Balkenius
Keyword(s):  
Neural Network ◽  
Haptic Perception ◽  
Cell Structure ◽  
The Self ◽  
Robot Hand ◽  
Self Organizing Map ◽  
Training Set ◽  
Input Space ◽  
Growing Cell ◽  
Self Organizing

We have implemented and compared four biologically motivated self-organizing haptic systems based on proprioception. All systems employ a 12-d.o.f. anthropomorphic robot hand, the LUCS Haptic Hand 3. The four systems differ in the kind of self-organizing neural network used for clustering. For the mapping of the explored objects, one system uses a Self-Organizing Map (SOM), one uses a Growing Cell Structure (GCS), one uses a Growing Cell Structure with Deletion of Neurons (GCS-DN), and one uses a Growing Grid (GG). The systems were trained and tested with 10 different objects of different sizes from two different shape categories. The generalization abilities of the systems were tested with 6 new objects. The systems showed good performance with the objects from the training set as well as in the generalization experiments. Thus the systems could discriminate individual objects, and they clustered the activities into small cylinders, large cylinders, small blocks, and large blocks. Moreover, the self-organizing ANNs were also organized according to size. The GCS-DN system also evolved disconnected networks representing the different clusters in the input space (small cylinders, large cylinders, small blocks, large blocks), and the generalization samples activated neurons in a proper subnetwork in all but one case.

Task Allocation of Multiple Robotic Fishes Based on Self-Organizing Map Neural Network

2014 ◽  
Vol 563 ◽  
pp. 308-311 ◽  
Author(s):  
Yu Lian Jiang
Keyword(s):  
Neural Network ◽  
Task Allocation ◽  
Robotic Fish ◽  
The Self ◽  
Self Organizing Map ◽  
Ball Game ◽  
Target Task ◽  
Water Polo ◽  
Som Neural Network ◽  
Self Organizing

For a water polo ball game there are multiple water polos and multiple robotic fishes in each team, seeking a reasonable task allocation plan is the key point to win the game. To resolve the problem, this paper proposed a multi-target task allocation method based on the Self-organizing map (SOM) neural network. This method takes the position of the water polos as the input vector, competes and compares the position of the water polos and robotic fishes, outputs the corresponding robotic fish of each water polo. The robotic fish will move toward the target water polo when the weight was adjusted, and will finally reach the target water polo. Simulations show that the score of the team using this method is higher than another team. The results prove the correctness and reliability of this method.

scholarly journals Application of Supervised SOM Algorithms in Predicting the Hepatotoxic Potential of Drugs

2021 ◽  
Vol 22 (9) ◽  
pp. 4443
Author(s):  
Viktor Drgan ◽  
Benjamin Bajželj
Keyword(s):  
Neural Network ◽  
Development Process ◽  
The Self ◽  
Training Algorithms ◽  
Drug Development Process ◽  
Self Organizing Map ◽  
High Ability ◽  
Good Separation ◽  
Propagation Algorithm ◽  
Self Organizing

The hepatotoxic potential of drugs is one of the main reasons why a number of drugs never reach the market or have to be withdrawn from the market. Therefore, the evaluation of the hepatotoxic potential of drugs is an important part of the drug development process. The aim of this work was to evaluate the relative abilities of different supervised self-organizing algorithms in classifying the hepatotoxic potential of drugs. Two modifications of standard counter-propagation training algorithms were proposed to achieve good separation of clusters on the self-organizing map. A series of optimizations were performed using genetic algorithm to select models developed with counter-propagation neural networks, X-Y fused networks, and the two newly proposed algorithms. The cluster separations achieved by the different algorithms were evaluated using a simple measure presented in this paper. Both proposed algorithms showed a better formation of clusters compared to the standard counter-propagation algorithm. The X-Y fused neural network confirmed its high ability to form well-separated clusters. Nevertheless, one of the proposed algorithms came close to its clustering results, which also resulted in a similar number of selected models.

Convergence and Ordering of Kohonen's Batch Map

1997 ◽  
Vol 9 (8) ◽  
pp. 1667-1676 ◽  
Author(s):  
Yizong Cheng
Keyword(s):  
Objective Function ◽  
The Self ◽  
Self Organizing Map ◽  
Degenerate State ◽  
Batch Mode ◽  
Convergence Proof ◽  
Neighborhood Relation ◽  
Self Organizing

The convergence and ordering of Kohonen's batch-mode self-organizing map with Heskes and Kappen's (1993) winner selection are proved. Selim and Ismail's (1984) objective function for k-means clustering is generalized in the convergence proof of the self-organizing map. It is shown that when the neighborhood relation is doubly decreasing, order in the map is preserved. An unordered map becomes ordered when a degenerate state of ordering is entered, where the number of distinct winners is one or two. One strategy to enter this state is to run the algorithm with a broad neighborhood relation.

scholarly journals Using Self-Organizing Maps for Rural Territorial Typology

2011 ◽  
pp. 107-126 ◽  
Author(s):  
Marcos Santos da Silva ◽  
Edmar Ramos de Siqueira ◽  
Olívio Teixeira ◽  
Maria Manos ◽  
Antônio Monteiro
Keyword(s):  
Neural Network ◽  
Temporal Analysis ◽  
The Self ◽  
Self Organizing Map ◽  
Clustering Methods ◽  
Self Organizing Maps ◽  
Policy Makers ◽  
Spatial Temporal Analysis ◽  
Self Organizing

This work assessed the capacity of the self-organizing map, an unsupervised artificial neural network, to aid the process of territorial design through visualization and clustering methods applied to a multivariate geospatial temporal dataset. The method was applied in the case study of Sergipe‘s institutional regional partition (Territories of Identity). Results have shown that the proposed method can improve the exploratory spatial-temporal analysis capacity of policy makers that are interested in territorial typology. A new partition for rural planning was elaborated and confirmed the coherence of the Territories of Identity.

scholarly journals A Comparison Study: Clustering using Self-Organizing Map and K-means Algorithm

2016 ◽  
Vol 15 (1) ◽  
Author(s):  
Annisa Uswatun Khasanah
Keyword(s):  
Neural Network ◽  
Exact Solution ◽  
The Other ◽  
Self Organizing Map ◽  
Comparison Study ◽  
Comparison Result ◽  
Data Set ◽  
Neural Network Method ◽  
Network Method ◽  
Self Organizing

Nowadays clustering is applied in many different scopes of study. There are many methods that have been proposed, but the most widely used is K-means algorithm. Neural network has been also usedin clustering case, and the most popular neural network method for clustering is Self-Organizing Map (SOM). Both methods recently become the most popular and powerful one. Many scholarstry to employ and compare the performance of both mehods. Many papers have been proposed to reveal which one is outperform the other. However, until now there is no exact solution. Different scholar gives different conclusion. In this study, SOM and K-means are compared using three popular data set. Percent misclassified and output visualization graphs (separately and simultaneously with PCA) are presented to verify the comparison result.

Sign in / Sign up

Export Citation Format

Share Document