In this study, signal processing approaches and nonlinear identification are used to measure seismic responses of reinforced concrete (RC) structures using the shaking table test. To analyze structural nonlinearity, an equivalent linear system with time-varying model parameters, singular spectrum analysis to elucidate residual deformation, and wavelet packet transformation analysis to yield the energy distribution among components are adopted to detect the nonlinearity. Then, damage feature extraction is conducted using both the Holder exponent and the Level-1 detail of the discrete wavelet component. Finally, the modified Bouc-Wen hysteretic model and the system identification process are employed to the shaking table test data to evaluate the physical parameters, including the stiffness degradation, the strength deterioration and the pinching hysteresis. Finally, the identified stiffness and strength degradation functions from the test data of RC frames in relation to the degree of ground shaking, damage index and the identified nonlinear features are discussed. Based on the proposed method, both signal-based and modelbased identifications, the relationship between the damage occurrence and severity of structural damage can be identified. Figure 9. (a) Comparison of Inter-story drift ratio, the Holder exponent, Level-1 detail component and residuals estimated from SSA with respect to time from response data of RCF6. Correlation of singularities is identified among different analyses; (b) comparison of Inter-story drift ratio, the Holder exponent, Level-1 detail component and residuals estimated from SSA with respect to time from response data of RCF2. Correlation of singularities is identified among different analyses; and (c) comparison of the Inter-story drift ratio, the Holder exponent, Level-1 detail component and residuals estimated from SSA with respect to time from response data of RCF4. Correlation of singularities is identified among different analyses.To quantify the damage to these four RC frames, the hysteretic model parameters were evaluated from the load-displacement data of the RC frame. The original rough data were not used; rather, the SSA method was applied to filter out the high-frequency components (>20.0 Hz) of the recorded