|
|
Bimonthly Since 1986 |
ISSN 1004-9037
|
|
|
|
|
Publication Details |
Edited by: Editorial Board of Journal of Data Acquisition and Processing
P.O. Box 2704, Beijing 100190, P.R. China
Sponsored by: Institute of Computing Technology, CAS & China Computer Federation
Undertaken by: Institute of Computing Technology, CAS
Published by: SCIENCE PRESS, BEIJING, CHINA
Distributed by:
China: All Local Post Offices
|
|
|
|
|
|
|
|
|
|
Abstract
Deep learning techniques utilize numerous layers of processing to acquire hierarchical data representations and have demonstrated exceptional outcomes in various fields. Lately, within the domain of natural language processing (NLP), there has been an explosion of various model designs and methodologies. The present study employs R-CNN ResNet-50FPN and artificial neural networks for an NLP task and illustrates their progression in automatically detecting faults in SMPS by extracting data from an image. This model enables an individual to input an image of a faulty SMPS, for which Deep learning and Natural Language Processing is used to generate image-based questions and image captions. Using Polling mechanism, the majority of hits will be calculated and based on that the problem identification is fine tuned to top 3 problem category. Then by further questionaries the fault is identified and solution is given.
Keyword
#
PDF Download (click here)
|
|
|
|
|