In this paper, we investigate intelligent handoff decisions in femtocell networks, with the goal of achieving a seamless femtocell-to-femtocell handoff procedure that minimizes unnecessary handoffs and provides a good quality of connection to mobile users. To this aim, we propose a promising handoff scheme called Optimized Handoff based on Mobility Prediction and Call Admission Control (OHMP-CAC). Our proposal is based on a next cell prediction module using an efficient Hidden Markov Model (HMM) predictor on one hand, and a Call Admission Control (CAC) algorithm with service differentiation for applications with and without QoS constraints, on the other hand. To gauge the effectiveness of our proposal, we conducted extensive simulations based on real human mobility traces. Results show that OHMP-CAC outperforms existing approaches in terms of the number of handoffs, the dwell time, and the handoff decision time, while providing a connection with excellent quality of signal to femtocell user equipments (UE).