This study is aimed at exploring the prediction of the various hand gestures based on Force Myography (FMG) signals generated through piezoelectric sensors banded around the forearm. In the study, the muscles extension and contraction during specific movements were mapped, interpreted, and a control algorithm has been established to allow predefined grips and individual finger movements. Decision Tree Learning (DTL) and Support Vector Machine (SVM) have been used for classification and model recognition. Both of these estimated models generated an averaged accuracy of more than 80.0%, for predicting grasping, pinching, left flexion, and wrist rotation. As the classification showed a distinct feature in the signal, a real-time control system based on the threshold value has been implemented in a prosthetic hand. The hand motion has also been recorded through Virtual Motion Glove (VMD) to establish dynamic relationship between the FMG data and the different hand gestures. The classification of the hand gestures based on FMG signal will provide a useful foundation for future research in the interfacing and utilization of medical devices.