In the present paper, a computationally effective method for system reliability is proposed and examined. Dimension reduction integration is applied to evaluate the first few moments of the system performance function of a structure from which the moment-based reliability index based on the fourth moment standardization function and failure probability can be evaluated without Monte Carlo simulations. The procedure does not require the computation of derivatives, nor the determination of the design point and computation of the mutual correlations among the failure modes; thus, it should be computationally effective for structural system reliability assessment.
The recommender system is an effective Web marketing tool that havve been used especially on electric commerce sites in recent years. The recommender system provides each user with a list of new recommended items that are predicted to be preferred by the user. Collaborative filtering is one of the most representative and powerful methods to predict user preference in the recommender system. Collaborative filtering measures the similarity of preference between users and uses it to decide items to be recommended. Based on previous researche on this method, user preference is considered to have two aspects: Purchasing interest for items and post-purchase satisfaction with items. However, the conventional methods do not consider the two different preferences at the same time. This paper suggests taking these two preferences into account and proposes a new method that allows users to choose the balance between them. The proposed method is evaluated through simulation experiments with MovieLens data. It demonstrates the effectiveness of our proposal in precision and average rating compared with a previous method.
This study was motivated by challenges facing inventory managers when deciding the ordering policy for various items. It is difficult to find an appropriate ordering policy for many types of items. We propose a model that changes conventional multi-criteria ABC analysis so that it is suitable for use by inventory managers. We indicate that categorizing items based on their statistical characteristics leads to an ordering policy suitable for each item. We propose a method for deciding the ordering policy based on important shipping statistics and a classification technique. For this method, we analyze the relation between shipping statistics and the ordering policy for searching important shipping statistics. We classify items by shipping statistics and then decide the ordering policy for each item. In the numerical experiment, we used actual shipment data to calculate many shipping statistics that represent the characteristics of each item. Next, we found the important shipping statistics from Random Forests and applied them to decide the ordering policy. Finally, for confirming the importance of important shipping statistics, we tested the performance of Random Forests and other classifying methods using the important shipping statistics. It was found that the performance of each classifying method was improved.
Supply chain management (SCM) utilizes lean, agile and hybrid (leagile) supply chain models to stimulate consequences of increased globalization and behavioral changes of information rich consumers. Although SCM conceptually inherits a holistic view, firm level analysis occupies the majority of research. This research work attempts to uncover a new approach for SCM, exploring leanness and agility of value networks. Through a case study of six different global apparel value networks, the research provides important insights to SCM. While providing evidence that SCM is more accurately measured in the value network level, results reveal that different value networks focus on different areas of SCM. Further, owing to lean-agile characteristics of value networks, they develop unique capabilities in SCM. The paper proposes and tests a framework with lean-agile filtration for customer segmentation in a B2B context.
Virtual private servers (VPSs) such as the Amazon EC2 are widely used throughout the world. It is necessary to use VPSs properly in terms of the users' usage patterns and the frequency of use. However, it is often only the cost that receives attention. Therefore, a VPS may not serve the user's purpose. Our proposed system evaluates a certain constant index so that the user can select the appropriate VPS. Moreover, automation is accomplished from verification to evaluation to rapidly and adequately verify the various VPSs that will be routinely offered in the future. We proposed the use of the system at Shizuoka University where hundreds of VPS were introduced. We constructed the system for an analytic hierarchy process using the score of each benchmark. With this system, we can easily propose the best server to clients.
In recent years, diversified market needs have led to the constant use of high-mix, low-volume production in the manufacturing industry. However, there has been little research on the development of Demand Forecasting models that appropriately consider everyday market needs or of product-mix decision making methodologies that strategically use such models. In this study, a new Demand Forecasting model was developed based on genetic programming (GP), using experimental forecasting factors derived from sales activities with customers in metropolitan areas as the decision variable. The authors identify the process used to achieve improved Demand Forecasting accuracy by solving product-mix decision-making and how it impacts the manufacturing industry using Profit Contribution Analysis. Furthermore, a method to quantitatively identify the need for introducing new technologies to realize product-mixes using the aforementioned method is examined. Finally, the effectiveness of this method is validated using actual data from small and medium-sized manufacturers located in a regional area.
Engineer-to-order production is an approach in which a firm designs and produces a product that matches the requests of its customers. Usually, at the inquiry stage, the product specification items provided by the design/engineering department are used for discussions between the sales staff and the customer. However, since the customers are not familiar with all the product specifications, commonly, the product specifications are proposed by the sales staff according to his/her experience. Therefore, sometimes a relatively complex product specification (implying high price) may be proposed because of which the customer may not be satisfied; then, extensive discussions are conducted among the customer and the sales, engineering, and even production departments of the firm. This inefficient process may lead to order loss. In contrast, even when the customer is satisfied, the specifications (price) may be underestimated when the product specification is designed in detail after the contract is signed, and may lead to financial loss for the particular order. Therefore, the ability to accurately grasp customer requirements at an early stage is an essential factor. To solve this problem, this paper focuses on the description of the customer requirements. Instead of product specifications, customer requirement specifications are proposed to be used at the inquiry stage. This study uses mixers and drilling machines as case studies. Detailed customer requirement specifications are designed for these two kinds of products. The results show that the proposed description models are practically useful and can be translated into accurate product specifications.
After the Great East Japan Earthquake of March 11, 2011, business continuity management (BCM) has attracted more attention as a way to enhance the resilience of organizations in Japan. In addition, the ISO 22301 international standard for BCM was established in 2012 . As a result, there are presently nineteen international standards for management systems (MS). Many organizations in Japan have already implemented multiple MS standards. Although there are many MS standards that require the implementation of risk assessment (RA), in reality, RA methods are not integrated and are individually conducted because their requirements differ from those of MS. The practice of applying RA methods for multiple MS standards often causes overlaps of a RA process and inconsistencies in RA results. A solution to these problems is the development of a “multi-purpose risk assessment system (MUPRAS).” This study aims to efficiently develop a MUPRAS by increasing the commonality between RA-required specifications of multiple MS standards on the basis of open architecture theory. This study proceeds as follows. First, types of the target MS standards are screened out. Second, the possession status of third-party certifications for MS standards is surveyed. Third, commonalities of RA-required specifications of MS standards are digitized. Fourth, assessment methods of commonality mentioned above are proposed. Fifth, a case study for a MUPRAS is conducted.