Tool wear is well known to affect tool life, surface quality and production time. Because of this an online tool wear measurement and prediction systems has been developed, using a low-cost sensor. This study proposed the alternatif for cutting force measurement using strain gauge. A two-channel strain gauge is mounted at the tool holder to measure the deflection in both tangential direction and feed direction. New statistical analysis is used to identify and characterize the changes in signals from the sensors. A database for prediction tool wear is build from experimental data when cutting hardened carbon steel S45C using cutting tool insert NC30P grade. A user-friendly graphical user interface (GUI) has been developed for online prediction purposes. Results show that online prediction tool wear is quite satisfactory with RMSE between 0.0135 and 0.0273, and MAPE between 0.0745 and 0.1226. This is an efficient and low-cost method which can be used in the real machining industry to predict the level of wear in the cutting tool.