To develop an in-process quality control system, a sensor technique and a decision-making algorithm need to be applied during machining operations. Several sensor techniques have been used in the in-process prediction of quality characteristics in machining operations. For example, an accelerometer sensor can be used to monitor the vibration of milling operations to develop an on-line surface roughness measuring technique in end milling operations. A dynamometer sensor can be used to generate cutting forces in machining; however, the effects of surface roughness caused by cutting forces have not been taken into consideration in past research. Lee and Lin (2000) indicated that cutting forces have the most significant impact on the quality of machined parts in end milling operations. Therefore, cutting force is to be included in developing cutting parameters affecting a surface roughness recognition system in end milling operations. In this research, a multiple linear regression (MLR)-based in-process surface roughness recognition (IPSRR) system using a dynamometer was applied to predict surface roughness using cutting force, spindle speed, feed rate, and depth of cut as input parameters in end milling operations. The purpose of this study was to analyze cutting forces to find out the most significant cutting force magnitude that affected surface roughness and to evaluate whether a MLR approach for surface roughness recognition could be used for prediction in the IPSRR system. Analysis and results of the system are presented. (Contains 4 figures.)