多源信息融合

合集下载
  1. 1、下载文档前请自行甄别文档内容的完整性,平台不提供额外的编辑、内容补充、找答案等附加服务。
  2. 2、"仅部分预览"的文档,不可在线预览部分如存在完整性等问题,可反馈申请退款(可完整预览的文档不适用该条件!)。
  3. 3、如文档侵犯您的权益,请联系客服反馈,我们会尽快为您处理(人工客服工作时间:9:00-18:30)。

1st Int’l Conf. on Recent Advances in Information Technology | RAIT-2012 |
A Project Selection Framework of DSS by Dempster-Shafer Theory under Fuzziness
Tuli Bakshi
Jadavpur University Kolkata, India tuli.bakshi@
Subir Kumar Sanyal, Bijan Sarkar
Dept. of Production Engineering Jadavpur University, Kolkata, India sanyal_s_k@yahoo.co.in, bijon_sarkar@
A. Sinharay
Dept. of IT Future Institute of Engineering & Management, Kolkata, India arindam.sinharay@
Abstract: This paper exposits evolutionary MCDM techniques which integrates Dempster –Shafer Theory (DST) of evidence, quantificational evidence preference from different criteria based on belief function. In this paper, current researchers’ proposed method is able to preference rank a no. of alternative projects under uncertainty for project selection based on imperfect information coming out from more or less reliable and conflicting sources. Under fuzziness the integrated MCDM method uses possibility and belief function theory to take a decision based on imprecise and uncertain evaluations of quantitative and qualitative criteria. The derived ranking of alternative is based on DST related belief and plausibility measures. Keywords: Dempster-ShaferTheory (DST), uncertainty, imperfect information, belief and plausibility measures.
decisions are based on multiple criteria with variable expressed by the decision makers. Usually, the available information to evaluate those criteria remain imperfect and the sources of these information are not always reliable and may be conflicting. The problem is therefore to propose a decision support system that are capable to process both the complexity of decision problem including relative and subjective importance of the criteria, the impurity and heterogeneities of information, reliability and conflict level of information of sources. The main purpose of the present work is to analyze the decision mechanism as it is constrained by the relative importance of attribute elements and the independent valuation of these elements for existing alternatives. The mathematical tool used includes fuzzy sets [6, 7, 8, and 9] and the Dempster-Shafer theory [10]. II. UNCERTENTY AND IMPERFECTION INFORMATION & OTHER DEFINATION
I. INTRODUCTION Being a temporary attempt, a project needs to create a unique product, service or result. Temporary signifies that a particular project has a definite dead line, reaching the dead line the project objectives has been gained or it becomes clear that the project objective will not be made or the necessity of the project no longer exists. In real world, there can be multiple alternative projects. A decision maker (DM) has to choose one alternative, which must be the best option. Therefore, it is a very difficult task [1]. Selection and evaluation of a project involves decisions those are critical to profitability, growth and survival of organization in the competitive world. This type of decision involves multiple factors such as identification, considerations and analysis of viability. According to Hwang and Yoon [2] Multi-criteria decision making (MCDM) is applied to preferable decisions among available classified alternatives by multiple attributes. Therefore, MCDM is one of the most widely used decision methodology in project selection problems. The MCDM is a method that follows the analysis of several criteria, simultaneously. In this method, economic, environmental, social and technological factors are considered for the selection of the project and for making the choice sustainable [3-5]. Several frameworks have been proposed for solving MCDM problems. In reality
978-1-4577-0697-4/12/$26.00 ©2012 IEEE
Any decision is closely related to information quality. Uncertainty, often used in common language, is indeed only one of all the various types of information imperfection which are inconsistency, imprecision, incompleteness and uncertainty Probability theory is widely used to represent uncertainty but fails to handle vague, imprecise, uncertain and conflicting information. New theories have proposed to handle those different types of imperfect information. A. Fuzzy sets and possibility theories Fuzzy sets theory [11] represents vague information and relates an imprecise quantitative evaluation with a qualitative category as defined by an expert. Possibility theory [12], [13] represents both imprecision and uncertainty using possibility distribution. Instead of a single discrete evaluation, several consonant intervals with increasing confidence levels can be chosen: the wider the interval is, the more confident the expert is in his evaluation of the criterion.

相关文档
最新文档