Kohonen Self-organizing Map Network Research Articles

Modeling and simulation of cooperative transport of an object by two mobile manipulators on an uneven terrain using KSOM network

ABSTRACT In this paper, a learning-based method for cooperative load transport by two 16 DOF wheeled mobile manipulators (MM) on a rough surface is proposed. Each MM has a 10 DOF mobile platform with a six DOF manipulator on top of it. As the MM system is redundant, the standard pseudo inverse or Jacobian methods for finding the inverse kinematics solution cannot be used in real time. Thus, an advanced Kohonen self-organizing map (KSOM) network is used to learn the inverse kinematic mapping and resolve the redundancy of the MMs. Considering the nonholonomic constraints of the vehicle and manipulability measure of the manipulator, the forward kinematic model of the MM system is used to train the network. A user defined object path governs the end effector paths of the two MMs for carrying the object and the trained network resolves the redundancy of the MMs to follow the respective end effector paths. The advantage of the proposed method is that once a terrain is learned, multiple MMs can be simulated to carry an object together in real time, without complex inverse kinematics. Simulation results show the usefulness of the proposed method.

Hepatitis B Diagnosis Using Logical Inference and Self-Organizing Map

Despite all the standardization efforts made, medical diagnosis is still regarded as an art owing to the fact that that medical diagnosis requires an expertise in handling the uncertainty which is unavailable in today's computing machinery. Though artificial intelligence is not a new concept it has been widely recognized as a new technology in computer science. Numerous areas such as education, business, medical and manufacturing have made use of artificial intelligence. Problem statement: The proposed study investigated the potential of artificial intelligence techniques principally for medical applications. Neural network algorithms could possible provide an enhanced solution for medical problems. This study analyzed the application of artificial intelligence in conventional hepatitis B diagnosis. Approach: In this research, an intelligent system that worked on basis of logical inference utilized to make a decision on the type of hepatitis that is likely to appear for a patient, if it is hepatitis B or not. Then kohonen's self-organizing map network was applied to hepatitis data for predictions regarding the Hepatitis B which gives severity level on the patient. Results: SOM which is a class of unsupervised network was used as a classifier to predict the accuracy of Hepatitis B. Conclusion: We concluded that the proposed model gives faster and more accurate prediction of hepatitis B and it works as promising tool for predicting of routine hepatitis B from the clinical laboratory data.

Parts clustering by self-organizing map neural network in a fuzzy environment

The description of the attributes or characteristics of the individual parts in a feature-based clustering system is frequently vague, and linguistic, fuzzy number or fuzzy coding is ideally suited to represent these attributes. However, due to the vagueness of the description, the resulting fuzzy membership functions are usually very approximate. Neural network learning to improve the fuzzy representation was used in this investigation to overcome these difficulties. In particular, Kohonen's self-organizing map network combined with fuzzy membership functions was used to classify the different parts based on their various attributes. The network can simultaneously deal with crisp attributes, interval attributes, and fuzzy attributes. Due to the fuzzy input and fuzzy weights, a revised weight updating rule was proposed. Various approaches have been proposed to define the distance or ranking of fuzzy numbers, which is essential in order to use the Kohonen map. The overall existence measurement was used in the present investigation. To illustrate the approach, parts based on two attributes were classified and discussed.