@article{MAKHILLJEAS2016111414109,
    title = {Intrusion Detection System Framework Based on Machine Learning for
Cloud Computing},
    journal = {Journal of Engineering and Applied Sciences},
    volume = {11},
    number = {14},
    pages = {3279-3284},
    year = {2016},
    issn = {1816-949x},
    doi = {jeasci.2016.3279.3284},
    url = {https://makhillpublications.co/view-article.php?issn=1816-949x&doi=jeasci.2016.3279.3284},
    author = {Mohammed Hasan,Mohamad Fadli,Ngahzaifa Binti Ab. and},
    keywords = {IDS,proposed,hybrid,ELM,KDD},
    abstract = {Security is a rich research area and there are many solutions create to protect the information and
make the systems safer. Intrusion detection is one of the powerful solutions in security. Current-day network
Intrusion-Detection Systems (IDS) have several flaws such as low detection rates and high rates of false
positive alerts and the need for constant human intervention and tuning. This research focus on design
intrusion detection system based hybrid Extreme Learning Machine (ELM) and Genetic Algorithm (GA). ELM
is randomly generated the parameters because that this research proposes use GA to provide the ELM
parameters to find the best classifier that work as IDS. This model will test in Knowledge Discovery and Data
Mining Contest 1999 (KDD Cup 99) and Network Security Laboratory-Knowledge Discovery and Data Mining
(NSL-KDD) data set. Evaluate the performance of the proposed hybrid by using standard evaluate matrices.}
    }