Defect Detection Using Unanimous Vote Among Mahalanobis Classifiers for Each Color Component

In manufacturing industries, product inspection is automated and the use of image data is increasingly being employed for defect detection. A manufacturing company in Japan produces an item and inspects the produced products using image data. Reducing the error rate is important in product inspection because poor inspection of products might lead to the delivery of defective products to consumers (consumer’s risk) and strict inspection increases production cost (producer’s risk). To reduce the error rate, we highlighted fault points using a two-dimensional moving range filter and discriminated defect production through a unanimous vote among Mahalanobis classifiers for each color component. For results, we achieved a lower error rate than the current system. This research is an empirical study of how to use image data in defect detection.     

Broadband Demand Analysis for Network Building

An increase of broadband demand is forecasted by transitional methods that consider the effect of this increase through many factors, such as customer requirement diversification, and new service introduction and deployment under competition. Broadband demand forecasting has become important for closing the digital divide, promoting regional developments, and constructing networks economically; therefore, a demand forecast model that considers the mechanisms of market structure is necessary. In this paper, a demand analysis method for broadband access combining macro- and micro-data mining is proposed, and the service choice behaviour of customers is introduced as a customer model not only to express the macro trend of market structure, but also to consider area marketing. The proposed method can estimate the potential demand, determine the point at which broadband demand growth peaks in a specified area, and support a decision for ultra high-speed broadband access facility installation.