A fully adaptive image classification approach for industrial revolution 4.0

Syed Muslim Jameel, Manzoor Ahmed Hashmani, Hitham Alhussain, Arif Budiman

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

7 Citations (Scopus)

Abstract

Industrial Revolution (IR) improves the way we live, work and interact with each other by using state of the art technologies. IR-4.0 describes a future state of industry which is characterized through the digitization of economic and production flows. The nine pillars of IR-4.0 are dependent on Big Data Analytics, Artificial Intelligence, Cloud Computing Technologies and Internet of Things (IoT). Image datasets are most valuable among other types of Big Data. Image Classification Models (ICM) are considered as an appropriate solution for Business Intelligence. However, due to complex image characteristics, one of the most critical issues encountered by the ICM is the Concept Drift (CD). Due to CD, ICM are not able to adapt and result in performance degradation in terms of accuracy. Therefore, ICM need better adaptability to avoid performance degradation during CD. Adaptive Convolutional ELM (ACNNELM) is one of the best existing ICM for handling multiple types of CD. However, ACNNELM does not have sufficient adaptability. This paper proposes a more autonomous adaptability module, based on Meta-Cognitive principles, for ACNNELM to further improve its performance accuracy during CD. The Meta-Cognitive module will dynamically select different CD handling strategies, activation functions, number of neurons and restructure ACNNELM as per changes in the data. This research contribution will be helpful for improvement in various practical applications areas of Business Intelligence which are relevant to IR-4.0 and TN50 (e.g., Automation Industry, Autonomous Vehicle, Expert Agriculture Systems, Intelligent Education System, and Healthcare etc.).

Original languageEnglish
Title of host publicationRecent Trends in Data Science and Soft Computing - Proceedings of the 3rd International Conference of Reliable Information and Communication Technology IRICT 2018
EditorsFathey Mohammed, Faisal Saeed, Nadhmi Gazem, Abdelsalam Busalim
PublisherSpringer Verlag
Pages311-321
Number of pages11
ISBN (Print)9783319990064
DOIs
Publication statusPublished - 2019
Event3rd International Conference of Reliable Information and Communication Technology, IRICT 2018 - Kuala Lumpur, Malaysia
Duration: 23 Jun 201824 Jun 2018

Publication series

NameAdvances in Intelligent Systems and Computing
Volume843
ISSN (Print)2194-5357

Conference

Conference3rd International Conference of Reliable Information and Communication Technology, IRICT 2018
Country/TerritoryMalaysia
CityKuala Lumpur
Period23/06/1824/06/18

Keywords

  • Concept Drift
  • Image Classification
  • Industrial Revolution 4.0
  • Self Adaptability

Fingerprint

Dive into the research topics of 'A fully adaptive image classification approach for industrial revolution 4.0'. Together they form a unique fingerprint.

Cite this