Using of Two Analyzing Methods Multidimensional Scaling and Hierarchical Cluster for Pattern Recognition via Data Mining Abstract -- The present study aims at making comparison between two analyzing methods , multidimensional scaling and hierarchical clustering methods ,on the other hand, to imply data mining by using of these two analyzing methods to classify and discriminate twenty five samples of technician pieces (Prehistoric goblets) through the study of Engineering shapes and special figures for every sample separately (case by case) , which backs to the periods before B.C. and discovered in Malaysia .The results of two methods concord and resemble each other equally in their classifications of Data. A multidimensional Scaling method seems to be more precise and give more details in comparison with hierarchical cluster methods. Keywords: MDS, HCA, Pattern Recognition, Data Mining I- INTRODUCTION From the beginning and ancient centuries, human being concerned with traces and Antiques, and considered as one of the basic symbols that referred to cultures at that time and witness of its progress and development. The Engineering shapes and figures are major principles and basic symbols that discriminate and classify any technician piece (Prehistoric goblets) from another's, and also can express the Engineering shape by distances that may present these technician pieces in the best way. The primary utility of statistics is that they aid in reducing data into more manageable pieces of information from which inferences or conclusions. The present research aims to classify and discriminate many of technician pieces and Prehistoric goblets by studying the Engineering figures of every pieces separately i.e. case by case by using two methods of analyses: scaling multidimensional scaling and hierarchical clustering, of twenty five types models of different Prehistoric goblets that come back to period before B.C. which discovered in Malaysia . To achieve and perform this goal , this paper divided into three sections, The first includes giving a central pictures about theoretical frame for both methods of analyses ,Multidimensional scaling and hierarchical cluster analysis. The second section concerned of practical part and discussion the results for both methods of analyses. The final section contains the conclusions that were derived from the results of the present research. II- DATA MINING (DM) Data mining is predicted to be "one of the most revolutionary developments of the next decade," according to the online technology magazine ZDNET News. In fact, the Massachusetts Institute of Technology (MIT) Review pointed that choosing of data mining will be one of ten emerging technologies that will change the word, which is processed under Knowledge discovery field. (2) Data Mining is the analysis of (often-large) observational data sets to find unsuspected relationships and summarize the data in novel ways that are both understandable and useful to the user. (3, 4) DM is one of the important steps of KDD process.. The common algorithms in current data mining practice include the following.  Clustering: maps a data item into one of several clusters, where cluster are natural grouping of data items based on similarity matrices.  Association rules: describes association relationship among different attributes.  Summarization: provides a compact description for a subset of data.  Dependency modeling: describes significant dependencies among variables III- PATTERN RECOGNITION TECHNIQUE (5,6) Data mining is the process of identifying patterns and relationships in data that often are not obvious in large, complex data sets. As such, data mining involves pattern recognition and, by extension, pattern discovery. Pattern recognition is most often concerned with automatic classification of characters. The pattern recognition process starts with the unknown pattern, and ends with a label for the pattern. From an information-processing perspective, pattern recognition can be viewed as a data simplification process that filters extraneous data from consideration and labels the remaining data according to classification scheme. The major steps in the pattern recognition processes are:  Features Selection. Given a pattern, the first step in pattern recognition is to select a set of features or attributes from the universe available features that will be used to classify the pattern.  Measurement. The measurement phase of the pattern recognition, involves converting the original shape into a representation that can be easily manipulated programmatically, depending on the underlying technology used to perform the pattern matching operation.  Features Extraction. Features extraction involves searching for features in the data that are defines as relevant to pattern matching during feature selection. Clustering techniques, in which similar data are Ali A. Ibrahim College of Science AL-Nahrain –University Fwzi M. ALnaima College of Engineering AL-Nahrain –University Ammar D. Jasim College of Information Engineering AL-Nahrain –University Ali A. Ibrahim et al | IJCSET |January 2013 | Vol 3, Issue 1, 16-20 ISSN:2231-0711 Available online @ www.ijcset.net 16