FOUR-LAYER SPHERICAL SELF-ORGANIZED MAPS NEURAL NETWORKS TRAINED BY RECIRCULATION TO SIMULATE PERCEPTION AND ABSTRACTION ACTIVITY - APPLICATION TO PATTERNS OF RAINFALL GLOBAL REANALYSIS
Journal Title: ICTACT Journal on Soft Computing - Year 2018, Vol 8, Issue 4
Abstract
This work is intended to organize a big set of time series. To do that a self-organized map is implemented in four spherical layers trained by recirculation. This way tries to simulate aspects of perception and abstraction. The methodology and the fundamentals are described. About the fundamentals, both from the problem point of view and the neural aspects as brain functioning, perception and abstraction concepts, psycho genetics and grouping ideas, and from the architecture of the network, scheme of training, spherical layers of the maps and algorithms involved in the iterative training. Then, it is used to organize a big set of time series of rainfall reanalysis on grid point around the Earth to show how it functions. After removing the average from the series, the annual cycle in shape and amplitude is the main criterion for organization. It is shown how the successive layers contain more general abstractions, their representativeness around the Globe and in regional scale. It is compared with individual series in some points of grid. A possible change of behaviour is found in global scale around 1973 and with a variant in the methodology a possible change in the annual cycle the same year.
Authors and Affiliations
Dario Alberto Huggenberger
Keywords
Related Articles
- EP ID EP532595
- DOI 10.21917/ijsc.2018.0243
- Views 48
- Downloads 0
MULTI-DOCUMENT TEXT SUMMARIZATION USING CLUSTERING TECHNIQUES AND LEXICAL CHAINING
This paper investigates the use of clustering and lexical chains to produce coherent summaries of multiple documents in text format to generate an indicative, less redundant summary. The summary is designed as per user’s...
ENHANCED HYBRID PSO – ACO ALGORITHM FOR GRID SCHEDULING
Grid computing is a high performance computing environment to solve larger scale computational demands. Grid computing contains resource management, task scheduling, security problems, information management and so on. T...
OPTIMIZATION OF GRID RESOURCE SCHEDULING USING PARTICLE SWARM OPTIMIZATION ALGORITHM
Job allocation process is one of the big issues in grid environment and it is one of the research areas in Grid Computing. Hence a new area of research is developed to design optimal methods. It focuses on new heuristic...
AN APPROACH FOR AUTO-GENERATING SOLUTION TO USER-GENERATED MEDICAL CONTENT USING DEEP LEARNING TECHNIQUES
One of many things humans are obsessive about is health. Presently, when faced with a health-related issue one goes to the web first, to find closure to his/her problem. The community Question Answering (cQA) forum allow...
AN QUALITY BASED ENHANCEMENT OF USER DATA PROTECTION VIA FUZZY RULE BASED SYSTEMS IN CLOUD ENVIRONMENT
So far, in cloud computing distinct customer is accessed and consumed enormous amount of services through web, offered by cloud service provider (CSP). However cloud is providing one of the services is, security-as-a-ser...