Toward cognitive support for automated defect detection

Essa, Ehab; Hossain, M. Shamim; Tolba, A. S.; Raafat, Hazem M.; Elmogy, Samir; Muahmmad, Ghulam

doi:10.1007/s00521-018-03969-x

Cited by 11 publications

(2 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Martins Sampaio et al [8] discussed the challenges of collecting data from multiple complex systems and the process of decision making in a complex industrial environment and how business logic changes impacts the learning of the model. Essa et al [9] used machine learning, and big data processing to inspect industrial products in a fast and effective way using neighborhood maintaining approach. Burns et al [12] discussed modeling automation along with intelligent work analysis to assist the process of human-automation and coordination between human and machines in a complex industrial environment.…”

Section: Related Workmentioning

confidence: 99%

Building Cognitive Intelligence In Conveyor Systems using Intermediary Anomaly Detection And Handling (IADH) Technique

Poosapati*,

Manda,

Katneni

2019

IJITEE

View full text Add to dashboard Cite

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..

show abstract

Section: Related Workmentioning

confidence: 99%

Building Cognitive Intelligence In Conveyor Systems using Intermediary Anomaly Detection And Handling (IADH) Technique

Poosapati*,

Manda,

Katneni

2019

IJITEE

View full text Add to dashboard Cite

show abstract

“…The approach aims to detect both real (scratches and pits) and fake (stains, long dust and circular dust). Essa et al [401] proposed a defect detection approach (E-MR-ELM) for textile fabric surface inspection with extreme learning machine (ELM) and similarity measure (a kind of minimum ratio between local neighbourhood sliding window). The approach achieved 90.07% accuracy, 91.29% sensitivity and 99.67% specificity.…”

Section: Non-uniform Illuminationmentioning

confidence: 99%

Novel techniques for sparse representation problems

Chai¹

View full text Add to dashboard Cite

This thesis contains material from papers published in the following peer-reviewed conferences and publication drafts under preparation for the publications in the following peer-reviewed journals where I was the first and corresponding author. Chapter 3 is prepared as W.H. Chai, and C. Quek. A novel Quasi-Newton Technique for Composite Convex Minimization. Pattern Recognition (Under revision) The contributions of the co-authors are as follows:  I defined the initial project direction  Assoc Prof Quek edited the manuscript drafts.  The manuscript was revised by Assoc Prof Quek.  I generated the idea, derived the theory, designed the study and the algorithm, performed all the experimental works, and analyzed the results at the School of Computer Science and Rolls-Royce@NTU Corporate Lab. Chapter 4 is prepared as W.H. Chai, and C. Quek. Representation Recovery via -norm Minimization with Corrupted Data. Information Sciences (Submitted)The contributions of the co-authors are as follows: Assoc Prof Quek provided the initial project direction and edited the manuscript drafts. The manuscript was revised by Assoc Prof Quek. I generated the idea, derived the theory, designed the study and the algorithm, performed all the experimental works, and analyzed the results at the School of Computer Science and Rolls-Royce@NTU Corporate Lab.Chapter 5 is prepared as W.H. Chai, and C. Quek. Feature Selection for Dictionary Transfer. Pattern Recognition Letters (Under preparation for publication)The contributions of the co-authors are as follows:x  I defined the initial project direction  Assoc Prof Quek edited the manuscript drafts. The manuscript was revised by Assoc Prof Quek. I generated the idea, derived the theory, designed the study and the algorithm, performed all the experimental works, and analyzed the results at the School of Computer Science and Rolls-Royce@NTU Corporate Lab.

show abstract