System identification(SI) techniques using dynamic responses and behaviors of structural systems become an outstanding issue of researchers. However the conventional SI techniques are identified to be non-practical to the complex and tall buildings, due to limitation of the availability of an accurate data that is magnitude or location of external loads. Thus a technique to estimate structural properties of building without input measurement data and using limited response is essential in structural health monitoring. In this study, the improved least square method for damage detection is proposed and verified by shaking table tests on three-story plane frame steel structures. In results damage detection was performed in each member level.