) (otherwise 0 The Application of the System Parameter Fusion Principle to Optimizing an Integrated System for Library Management ZHENGQIN WU 1 QIANGGUO PU 2 NIKOS MASTORAKIS 3 1 Library, 2 Computer Center, University of Science and Technology of Suzhou, Jiangsu 215011, China 3 Hellenic Naval Academy, Terma Hatzikyriakou, 18539 Piraeus, Greece Also: WSEAS, Ag.I.Theologou 17-23, 15773, Zografou, Athens, Greece Abstract: - Modern technology provides a great amount of information. But for computer monitoring systems or computer control systems, in order to have the situation in hand, we need to reduce the number of variables to one or two parameters, which express the quality and/or security of the whole system. In this paper the authors introduce the system parameter fusion principle put forward by the second author and present how to apply it to optimizing an integrated system for library management combining with the Delphi technique and AHP. Keywords: - Data fusion, Library management, Delphi technique, Analytical Hierarchy Process 1 Introduction The computer integrated system for library management (CISLM) is a complicated system which concerns the function of library management, the performance of the system hardware and software, and the investment for the system[1]. During the development of library automation, there are several schemes and targets in selecting and introducing the scheme of the library integrated system. The problem of choosing which one is decided by optimizing decisions. Since in the factors connected with the integrated system there exist many interactions and contradictions, which are only qualitative targets. This brings a lot of difficulty to the user's subjective judge and decision. We must have a systematic and practical evaluation target system, and we must have a set of scientific auxiliary decision methods. The Analytical Hierarchy Process(AHP) is a convenient way for quantitative analysis to un-quantitative matters in system engineering, it is also an effective method for people to objectively subscribe the subjective judge. In this paper the authors introduce the system parameter fusion principle put forward by the second author, and present how to apply the system parameter fusion principle to optimizing an integrated system for library management combining with the Delphi technique and AHP. 2 The System Parameter Fusion Principle Modern technology provides a great amount of information. It appears in various forms such as texts, graphics, images, and even sounds. This great amount of information in various forms will submerge useful data, which must be easy to process and present to human supervisors. In computer monitoring systems, especially real-time expert systems, we need one or two parameters to express the quality and/or security of the whole system. Let M i be the measurement value of the i th variable (i = 1,2,...,n), O i the optimum of the i th variable, H i the upper limit of the i th variable, L i the lower limit of the i th variable, W i the weight of the i th variable. W i indicates the importance of this variable in the system, The more important the variable in the system is, the greater value we ascribe to the W i . There are two synthesized parameters, G, which indicates the quality of the system, and S, which indicates the security of the system. In which, f(M i ) is the quality function, the value limits are from 0 to 1. f(M i ) can be the linear function of M i , or other quadratic function of M i . First this paper gives two simple forms: (1) f(M i ) can be the simplest linear function of M (1) . 1 W n 1 i i = ∑ = ) O M L (if L O L M i i i i i i i < < − − (4) ) H M O (if H O H M i i i i i i i < < − − (3b) ) M ( f ln W S ln , . e . i i n 1 i i ⋅ = ∑ = (2) ) f(M W G i n 1 i i ⋅ = ∑ = (3a) ) f(M S i w n 1 i i ∏ = = ) M ( f i = Proceedings of the 5th WSEAS Int. Conf. on SIMULATION, MODELING AND OPTIMIZATION, Corfu, Greece, August 17-19, 2005 (pp379-383)