In the digital economy, knowledge is regarded as an asset in an organization, and knowledge management (KM) implementation supports a company in developing innovative products and making critical management strategic decisions for business excellence. Customer relationship management (CRM) is an information-technology-enabling management tool, which manages the relationship with customers to understand, target, and attract them, with the objective of satisfying and retaining customers. Their synergy potential draws attention in the academic community and has led to the emergence of the customer knowledge management (CKM) model. In a knowledge management domain, an important task is the conversion of tacit knowledge into explicit knowledge, whereby the well-established Kano's Method has come up to demand and extract customer knowledge for attractive quality creation in new product development projects. As a consequence, this study proposes a Kano-CKM model with a methodology to delineate precisely the process of customer knowledge discovery for innovative product development. An industry level market research project applying the Kano-CKM model has been accomplished to present a satisfactory justification and will be described in the case study part of this article.
Mura defect classification is a critical concern for thin-film transistor liquid crystal display (TFT-LCD) manufacturers. In recent years, artificial intelligence technologies have been successfully applied in numerous areas. However, such approaches require large amounts of training image data. Simultaneously, product differentiation and customization strategies have forced the TFT-LCD manufacturing industry to shift from mass production to high-mix, low-volume, and short-life-cycle production. In this environment, collecting a large amount of training data is difficult. Moreover, images with Mura defects captured at inspection stations remain challenging because they are often contaminated with moiré patterns. Moiré patterns severely affect the visual quality of images and cause difficulty in determining Mura defects. This study proposes an approach to eliminate moiré patterns from defect images using a conditional generative adversarial network. In addition, we develop a transfer learning ensemble model that aggregates multiple convolutional neural networks based on a denoising network for defect classification in a limited training data set. The results from an industrial case study demonstrate that the proposed method provides improved accuracy for Mura defect classification. This method can therefore become a viable alternative to manual classification in the TFT-LCD manufacturing industry.
1 March 2006 in Computers & Mathematics with Applications