Search results for: Ian P. McCarthy
2 Modeling the Uncertainty of the Remanufacturing Process for Consideration of Extended Producer Responsibility (EPR)
Authors: Michael R. Johnson, Ian P. McCarthy
Abstract:
There is a growing body of evidence to support the proposition of product take back for remanufacturing particularly within the context of Extended Producer Responsibility (EPR). Remanufacturing however presents challenges unlike that of traditional manufacturing environments due to its high levels of uncertainty which may further distract organizations from considering its potential benefits. This paper presents a novel modeling approach for evaluating the uncertainty of part failures within the remanufacturing process and its impact on economic and environmental performance measures. This paper presents both the theoretical modeling approach and an example of its use in application.Keywords: Remanufacturing, Demanufacturing, Extended Producer Responsibility, Sustainability, Uncertainty.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 17301 The Relationship between Representational Conflicts, Generalization, and Encoding Requirements in an Instance Memory Network
Authors: Mathew Wakefield, Matthew Mitchell, Lisa Wise, Christopher McCarthy
Abstract:
This paper aims to provide an interpretation of artificial neural networks (ANNs) and explore some of its implications. The interpretation views ANNs as a memory which encodes instances of experience. An experiment explores the behavior of encoding and retrieval of instances from memory. A localised representation ANN is created that allows control over encoding and retrieved memory sample size and is experimented with using the MNIST digits dataset. The relationship between input familiarity, conflict within retrieved samples, and error rates is described and demonstrated to be an effective driver for memory encoding. Results indicate that selective encoding and retrieval samples that allow detection of memory conflicts produce optimal performance, and that error rates are normally distributed with input familiarity and conflict. By using input familiarity and sample consistency to guide memory encoding, the number of encoding trials on the dataset were reduced to 18.33% of the training data while maintaining good recognition performance on the test data.
Keywords: Artificial Neural Networks, ANNs, representation, memory, conflict monitoring, confidence.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 475