Concrete is one of the most common materials used to construct a variety of civil infrastructures. However, since concrete is susceptible to fractures, it is essential to confirm the strength development of concrete during the curing process, in order to prevent unexpected collapse. To address this issue, this study proposes an artificial neural network (ANN)-based strength estimation technique using several kinds of strength related factors of concrete materials. In particular, the variations in mechanical properties of concrete were measured through electro-mechanical impedance (EMI) change using an embedded piezoelectric sensor. The ANN was trained to estimate the strength of concrete by using watercement ratio, curing time and temperature, maturity from internal temperature, and 1-CC of the EMI signals. The trained ANN was verified with conventional strength estimation models throughout a series of experimental studies. According to the comparison results, it is noted that the proposed technique could be very effectively applied to estimate the strength of concrete.