Design of a product quality control system based on the use of data mining techniques

In recent years industries have increasingly used customer relationship labor in management as a tool to improve their position in the marketplace. This research involves using a data warehouse, decision-tree-based data mining, and neural network pattern classification analysis to isolate the causes of non-conformity in IC packaging. The correctness of the classification analysis produced using the two methods is compared. Our objective is to establish an information analysis system, that is able to quickly identify the causes of problems thereby reducing the time taken to solve quality-related problems. It is shown that predictions made about the target group using decision tree analysis are more accurate than those made by neural network classification, indicating that decision tree analysis is an effective means of classification analysis of a company's quality problems.     

A study on the critical success factors for corporations embarking on knowledge community-based e-learning

Corporations have felt the pressure for fast-paced innovations and knowledge transfer as major driving forces in raising their sustainable competitive advantage and organizational total productivity. Thus, the development of the knowledge community through e-learning is an important strategy in implementing knowledge management policy. This paper illustrates an empirical study with which to conduct qualitative research of learning organization. From the case company’s real progress and practical experience, some core principles were extracted from four managerial aspects, such as: strategy, technology, process, and personnel. These aspects were analyzed in order to understand the value chain framework and the major concerns of knowledge community development. Further, the main benefits are addressed and certain critical factors are proposed and shown in this paper to ensure the success of corporations embarking on knowledge community-based e-learning.     

Role Negotiation and Interaction: An Exploratory Case Study of the Impact of Management Consultants on ERP System Implementation in SMEs in Taiwan

Abstract

With growing pressures for collaborative information systems (IS) partnerships, Enterprise Resource Planning (ERP) implementation has been an important activity for improving supply chains efficiency in Small and Medium-Sized Enterprises (SMEs). Historically ERP consultants usually take a product-selling approach in SMEs, providing limited management consultancy services. However, a more constructive role for management consultants has become an emerging and challenging issue. This study explored the involvement of management consultants in ERP implementation, particularly with internal managers, ERP consultants and other project members. Extensive interviews were conducted with management consultants as well as 47 project members from four different SMEs in Taiwan employing ERP consultants. Using a grounded theory methodology, prior literature was used to sensitize the findings to key concepts of importance. The results were then analyzed and we described how owner-managers regard management consultants and how the consultants use role negotiation skills to work with both internal managers and ERP consultants. The study found resistance toward management consultants primarily from managers in SMEs, and not owner-managers. The relationships between management consultants and SME managers also differed from similar relationships in large organizations. Suggestions are also provided for academics and practitioners along with areas for future research to extend these exploratory findings.     

A Web-based monitor and management system architecture for enterprise virtual private network

Virtual private network (VPN) not only possesses the low cost, inexpensive fees, and excellent support advantages of the Internet, it also has the benefit of the security as the leased line. How to properly manage the VPN is an issue in which the enterprise IT engineers have to take seriously.

This research is based on the new network management technologies such as policy-based network management, mobile agent, etc., to design a VPN monitor and management system architecture that contains high level management with low network traffic load. This system architecture integrates both VPN devices and general network devices, such the feature can integrate the monitor and manage the VPN and Intranet at the same time.

The result of this research provides enterprises with a VPN architecture for monitoring and managing the enterprises, as well as to establish a prototype for the enterprise VPN monitor and management system. Such system architecture can effectively assist the semiconductor companies to monitor and manage their enterprise VPN in order to utilize the Internet resources, and to reduce the possible operation off time. The prototype system could proof the feasibility of the systematic architecture, it can automatically detect and activate the backup mechanism according to the preset management policy, and to achieve the effective and fast solution for the enterprise network problems.     

An RFID-based enterprise application integration framework for real-time management of dynamic manufacturing processes

Enterprise application integration (EAI) is an important issue for a company trying to transform itself into a ubiquitous real-time organization. However, traditional techniques for EAI are only suitable for integrating the virtual information among different applications. The challenge of integrating physical objects with corresponding business processes and applications at the right time and location is a critical concern for companies building a real-time enterprise (RTE) information system. In this research, we proposed an EAI framework based on radio frequency identification (RFID) technology. On the basis of this framework, a prototype system is developed to demonstrate the applicability of the framework in a shop floor environment. This paper also presents a RFID-based standard operation procedure to configure a prototype system for a particular shop floor operation and an operator orientation for performing the corresponding tasks. The findings of this paper demonstrate that the proposed framework is more capable than most current industrial practices in both managing dynamic manufacturing processes and in providing real-time visibility of work-in-process information. Using this framework, an enterprise can easily integrate an RFID-based solution into its IT infrastructure and manufacturing environment to facilitate real-time management of dynamic production operations.     

Generating learning sequences for decision makers through data mining and competence set expansion

For each decision problem, there is a competence set, proposed by Yu (1990), consisting of ideas, knowledge, information, and skills required for solving the problem. Thus, it is reasonable that we view a set of useful patterns discovered from a relational database by data mining techniques as a needed competence set for solving one problem. Significantly, when decision makers have not acquired the competence set, they may lack confidence in making decisions. In order to effectively acquire a needed competence set to cope with the corresponding problem, it is necessary to find appropriate learning sequences for acquiring those useful patterns, the so-called competence set expansion. This paper thus proposes an effective method consisting of two phases to generate learning sequences. The first phase finds a competence set consisting of useful patterns by using a proposed data mining technique. The other phase expands that competence set with minimum learning cost by the minimum spanning table method (Feng and Yu (1998)). From a numerical example, we can see that it is possible to help decision makers to solve the decision problems by use of the data mining technique and the competence set expansion, enabling them to make better decisions.     

Using intelligent technology and real-time feedback algorithm to improve manufacturing process in IoT semiconductor industry

The Journal of Supercomputing - To enable the Internet of things, the semiconductor manufacturing process has progressed from the micron to the deep submicron level. Quality improvement is one of...     

Mining fuzzy association rules for classification problems

The effective development of data mining techniques for the discovery of knowledge from training samples for classification problems in industrial engineering is necessary in applications, such as group technology. This paper proposes a learning algorithm, which can be viewed as a knowledge acquisition tool, to effectively discover fuzzy association rules for classification problems. The consequence part of each rule is one class label. The proposed learning algorithm consists of two phases: one to generate large fuzzy grids from training samples by fuzzy partitioning in each attribute, and the other to generate fuzzy association rules for classification problems by large fuzzy grids. The proposed learning algorithm is implemented by scanning training samples stored in a database only once and applying a sequence of Boolean operations to generate fuzzy grids and fuzzy rules; therefore, it can be easily extended to discover other types of fuzzy association rules. The simulation results from the iris data demonstrate that the proposed learning algorithm can effectively derive fuzzy association rules for classification problems.     

Development of an agent-based system for manufacturing control and coordination with ontology and RFID technology

Integrating physical objects with the corresponding enterprise applications any time any where is the essential issue for a real-time enterprise. This study proposes a multi-agent system framework called agent-based manufacturing control and coordination (AMCC) system, a agent-based framework using ontology and RFID technology to monitor and control dynamic production flows and also to improve the traceability and visibility of mass customization manufacturing processes. The capabilities offered by multi-agent systems to respond to RFID events in real-time and a broad class of agent design and coordination issue regarding just in time (JIT) and just in sequence (JIS) manufacturing processes are also exploited in this study. To validate the proposed framework, case study of a bicycle manufacturing company is used to demonstrate how the proposed framework can benefit its JIT production. Finally, an example prototype system is implemented to demonstrate the concept of the proposed framework.     

Intelligent service-integrated platform based on the RFID technology and software agent system

The mobility of the popular goods on the shelves will have a crucial impact on the store sales. For retailers, the seasonal or news-induced demand for commodity will have the flocking effect or business opportunity lasting for some time; if the product shortage occurs, consumers will immediately turn to other stores, and the sale opportunity will be missed.Traditionally, to confirm the demand for commodity, the stores primarily employ the point-of-sale (POS) system to monitor the inventory of goods, but the turnover rate of popular goods is very demanding. The inventory information supplied by the POS system is that generated after the ledger-closing stage, and it cannot precisely match the actual quantity of goods on the shelves. Therefore, in order to prevent the monetary loss due to the information gap, we propose the “intelligent service-integrated platform”, which employs the software agent as the framework to construct the integrated information system mechanism. We also employ the radio frequency identification (RFID) technology to realize the smart shelf as the trigger point for the retrieval of commodity message. At the same time, we develop the interactive information platform to provide the consultation and promotion service of goods. The overall framework will help enhance the performance of the sales outlets and improve the customer service, while addressing the time effect issue of the popular commodity.