Time filter

Source Type

Otsuka N.,1st Manufacturing Industries Solutions Division | Nishina M.,Manufacturing and Process Industries Systems Development Division | Higashihara K.,Global Products and Services Development Division | Umezu K.,Knowledge Discovery Research Laboratories | And 3 more authors.
NEC Technical Journal | Year: 2015

The optimization of spare parts inventories is an issue that is commonly found in the manufacturing industry. NEC Fielding, who are the subsidiary of the NEC Group and manage the maintenance business, also have similar concerns, because traditional statistical techniques have had limited accuracy in predicting the future demand for repair parts. The company therefore has decided to adopt NEC's big data analysis technology "heterogeneous mixture learning." This has enabled them to forecast demands with high accuracy. They have thereby succeeding in reducing by about 20% the inventory of the high-rotation parts that occupy a large share of the spare parts shipments. As the stockout risk is also estimated, this approach has allowed the company to challenge a more thorough optimization of the inventory. This paper describes the spare parts demand forecasting procedures performed at NEC Fielding by using the heterogeneous mixture learning engine and includes discussion of its resulting effects. Source

Machida F.,Knowledge Discovery Research Laboratories | Kohno S.,Knowledge Discovery Research Laboratories | Maebara K.,NEC Corp | Nakagawa M.,NEC Communication Systems LTD.
Proceedings of the 11th International Conference on Network and Service Management, CNSM 2015 | Year: 2015

Mobile thin-client services are gaining lots of attention from companies who concern about the security yet recognize the benefits of mobile computing in their businesses. The service is based on a private cloud system hosting virtual machines that can execute mobile OS instances. The owner of the private cloud needs to prepare sufficient server resources for hosting those virtual machines. In this paper, we propose a framework to guide server procurement decisions in a private cloud for mobile thin-client service, which aims to minimize the cost of unused servers while avoiding service level violation due to the lack of resources. To make a timely server procurement decision, the framework combines the techniques for workload estimation to individual VMs, demand estimation of newly created VMs and repetitive simulation of VM replacement algorithm. Through a simulation study, we show that the proposed framework can reduce the cost of unused servers by 25% while satisfying a service level, compared with a time-based heuristic decision method. © 2015 IFIP. Source

Fujimaki R.,NEC Laboratories America Inc. | Morinaga S.,Knowledge Discovery Research Laboratories
NEC Technical Journal | Year: 2012

Recently, the acquisition of knowledge from big data analysis is becoming an essential feature of business efficiency. However, the analysis of big data can be troublesome because it often involves the collection and storage of mixed data based on different patterns or rules (heterogeneous mixture data). This has made the heterogeneous mixture property of data a very important issue. This paper introduces "heterogeneous mixture learning," which is the most advanced heterogeneous mixture data analysis technology developed by NEC, together with details of some actual applications. The possibility of the utilization of data that has previously been collected without any specific aim is also discussed. Source

Ikegami T.,Knowledge Discovery Research Laboratories | Tanikawa Y.,Knowledge Discovery Research Laboratories
NEC Technical Journal | Year: 2014

In recent years, providing countermeasures to human error has become increasingly important among business operation systems. This trend is especially significant in the fields of aerospace and medical treatment, in which social solutions with high security and reliability are essential. We have developed a Color Combinations Evaluation Method to reduce human error and have applied it to an air traffic control system. This method quantifies three requirements for color combinations that are effective in reducing human error: "Harmony," "Visual attention of important information" and "Fatigue of eyes." It also quantifies "user's perceptual load" that users might receive from color combinations. Developers can determine the optimal color combinations based on calculated value. This paper introduces the Color Combinations Evaluation Method and its practical applications. Source

Tanikawa Y.,Knowledge Discovery Research Laboratories | Okubo R.,Knowledge Discovery Research Laboratories | Fukuzumi S.,Knowledge Discovery Research Laboratories
NEC Technical Journal | Year: 2014

Usability has recently been increasing in importance for business information systems. In response to this trend, NEC is developing a software engineer support method to enable the efficient development of systems with higher usability. The support method is being developed with the viewpoint that it is important to clarify usability-related customer needs during upstream processes of system development. This method consists of a procedure for deriving usability-related customer needs from the properties of the target system's users and tasks and connecting them to usability requirements. The verification experiments of this method succeeded in recognizing the validity of the output requirements and the effectiveness of the method. This paper introduces this method for supporting the clarification of customer needs. Source

Discover hidden collaborations