Araştırma Çıktıları / Research Outputs
Permanent URI for this communityhttps://ada.atilim.edu.tr/handle/123456789/6
Browse
Browsing Araştırma Çıktıları / Research Outputs by Author "Abayomi-Alli,O."
Now showing 1 - 2 of 2
- Results Per Page
- Sort Options
Conference Object Citation Count: 3An Improved Feature Selection Method for Short Text Classification(Institute of Physics Publishing, 2019) Mısra, Sanjay; Misra,S.; Matthews,V.O.; Odusami,M.; Abayomi-Alli,A.; Ahuja,R.; Maskeliunas,R.; Computer EngineeringText has become one of the widest means of communication on mobile devices due to cheap rate and convenience for instance short text, web document, emails, instant messages. The exponential growth of text documents shared among users globally has increased the threat of misclassification associated with mobile devices such as Spam, Phishing, License to kill, Malware and privacy issues. Existing studies have shown that the major problem associated with text message classification is the poor representation of feature thus reducing accuracy and increasing f-measure rate. Thus, a modified Genetic Algorithm (GA) for improve feature selection and Artificial Immune System (AIS) algorithm was proposed for effective text classification in mobile short messages. The system will be deployed on an Android OS. © 2019 Published under licence by IOP Publishing Ltd.Conference Object Citation Count: 20An Improved Model for Alleviating Layer Seven Distributed Denial of Service Intrusion on Webserver(Institute of Physics Publishing, 2019) Mısra, Sanjay; Misra,S.; Adetiba,E.; Abayomi-Alli,O.; Damasevicius,R.; Ahuja,R.; Computer EngineeringApplication layer or Layer Seven Distributed Denial of service (L7DDoS) intrusion is one of the greatest threats that intrusion a webserver. The hackers have different motives which could be for Extortion, Exfiltration e.t.c Researchers have employed several methods to prevent L7DDoS intrusion especially using machine learning. Although Machine learning techniques has proven to be very effective with high detection accuracy, the approach still find it difficult to detect Hyper Text Transfer Protocol (HTTP) based botnet traffic on web server with high false positive rate. The adoption of deep learning based technique using Long Short Term Memory (LSTM) will alleviate this problem. © 2019 Published under licence by IOP Publishing Ltd.