Building Cognitive Intelligence In Conveyor Systems using Intermediary Anomaly Detection And Handling (IADH) Technique
Vijaya Ramaraju Poosapati1, Vijaya Killu Manda2, Vedavathi Katneni3
1Vijayaramaraju Poosapati*, Computer Science Department, GITAM Visakhapatnam, India.
2Vijaya Killu Manda, Computer, GITAM Visakhapatnam, India.
3Vedavathi Katneni, Computer Science Department, GITAM Visakhapatnam, India.
Manuscript received on September 15, 2019. | Revised Manuscript received on 24 September, 2019. | Manuscript published on October 10, 2019. | PP: 957-964 | Volume-8 Issue-12, October 2019. | Retrieval Number: J96670881019/2019©BEIESP | DOI: 10.35940/ijitee.J9667.1081219
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Industry 4.0 is characterized by the interconnection of industrial systems and automation to enable efficient and autonomous industrial operations. Automating the tasks done by humans involves processing a huge volume of data across multiple sources in the industry and incorporating intelligence into the machine from the insights extracted from the processed data. Classification techniques play a vital role in extracting the features and predicting the best possible action that can be taken based on the processed data. However in cases where the underlying business rules changes, the algorithms fail to detect these changes early, thereby impacting the overall accuracy of the model. In this paper, we presented the Intermediary Anomaly Detection and Handling (IADH) algorithm to overcome the problem mentioned above. IADH algorithm will help to quickly identify the changing business rules of the industry and alter the prediction of the model. The architecture of this model does not restrict to one specific industrial machine but enables it to be reusable across multiple industrial systems. The details of the test data collected, algorithm steps, prototype built and software modules built to develop the product with the IADH feature are discussed in this paper. The results of the model with IADH and without IADH are compared to notice the improvements of the proposed IADH Technique for the collected dataset..
Keywords: ]Industrial Automation, Cognitive Systems, Machine Learning, Classification, Cognitive Automation Software
Scope of the Article: Classification