With the emergence of large datasets in real-time applications as network intrusion detection, systems classification have gained more attention due to the importance of these applications and the increasing generation of these network traffic information. The proliferation of Internet and networking applications, coupled with the widespread availability of system hacks and viruses have increased the need for network security. However, the huge network traffic data slow down the entire intrusion detection process and may lead to unsatisfactory classification accuracy due to the computational difficulties in handling such data. Classifying a huge amount of data usually lead to higher computational complexity. We propose sequential classifiers based on data selection process for intrusion detection. The performance of the proposed approach is evaluated using a intrusion detection dataset, KDD Cup'99 dataset, which is a typical example of large-scale datasets. The evaluation results show that our approach achieves better precision and lower computational cost compared with the state-of-the-art mechanisms.