Preferred Language
Articles
/
TBesUJEBVTCNdQwC_5RQ
Comparison of ML/DL Approaches for Detecting DDoS Attacks in SDN
...Show More Authors

Software-defined networking (SDN) presents novel security and privacy risks, including distributed denial-of-service (DDoS) attacks. In response to these threats, machine learning (ML) and deep learning (DL) have emerged as effective approaches for quickly identifying and mitigating anomalies. To this end, this research employs various classification methods, including support vector machines (SVMs), K-nearest neighbors (KNNs), decision trees (DTs), multiple layer perceptron (MLP), and convolutional neural networks (CNNs), and compares their performance. CNN exhibits the highest train accuracy at 97.808%, yet the lowest prediction accuracy at 90.08%. In contrast, SVM demonstrates the highest prediction accuracy of 95.5%. As such, an SVM-based DDoS detection model shows superior performance. This comparative analysis offers a valuable insight into the development of efficient and accurate techniques for detecting DDoS attacks in SDN environments with less complexity and time.

Scopus Clarivate Crossref
View Publication
Publication Date
Thu Oct 31 2019
Journal Name
Journal Of Theoretical And Applied Information Technology
AN ENHANCED EVOLUTIONARY ALGORITHM WITH LOCAL HEURISTIC APPROACH FOR DETECTING COMMUNITY IN COMPLEX NETWORKS
...Show More Authors

Preview PDF
Scopus (5)
Scopus
Publication Date
Wed Sep 23 2020
Journal Name
Artificial Intelligence Research
Hybrid approaches to feature subset selection for data classification in high-dimensional feature space
...Show More Authors

This paper proposes two hybrid feature subset selection approaches based on the combination (union or intersection) of both supervised and unsupervised filter approaches before using a wrapper, aiming to obtain low-dimensional features with high accuracy and interpretability and low time consumption. Experiments with the proposed hybrid approaches have been conducted on seven high-dimensional feature datasets. The classifiers adopted are support vector machine (SVM), linear discriminant analysis (LDA), and K-nearest neighbour (KNN). Experimental results have demonstrated the advantages and usefulness of the proposed methods in feature subset selection in high-dimensional space in terms of the number of selected features and time spe

... Show More
View Publication
Crossref
Publication Date
Thu Dec 19 2024
Journal Name
Ieee Explorer
A Novel Flow Priority and Continuity Control Mechanism in SDN Network
...Show More Authors

In recent days, the escalating need to seamlessly transfer data traffic without discontinuities across the Internet network has exerted immense pressure on the capacity of these networks. Consequently, this surge in demand has resulted in the disruption of traffic flow continuity. Despite the emergence of intelligent networking technologies such as software-defined networking, network cloudification, and network function virtualization, they still need to improve their performance. Our proposal provides a novel solution to tackle traffic flow continuity by controlling the selected packet header bits (Differentiated Services Code Point (DSCP)) that govern the traffic flow priority. By setting the DSCP bits, we can determine the appropriate p

... Show More
View Publication
Scopus Crossref
Publication Date
Tue May 23 2023
Journal Name
Journal Of Engineering
Enhancement of the Detection of the TCP SYN Flooding (DDoS) Attack
...Show More Authors

The major of DDoS attacks use TCP protocol and the TCP SYN flooding attack is the most common one among them. The SYN Cookie mechanism is used to defend against the TCP SYN flooding attack. It is an effective defense, but it has a disadvantage of high calculations and it doesn’t differentiate spoofed packets from legitimate packets. Therefore, filtering the spoofed packet can effectively enhance the SYN Cookie activity. Hop Count Filtering (HCF) is another mechanism used at the server side to filter spoofed packets. This mechanism has a drawback of being not a perfect and final solution in defending against the TCP SYN flooding attack. An enhanced mechanism of Integrating and combining the SYN Cookie with Hop Count Filtering (HCF) mech

... Show More
View Publication Preview PDF
Crossref
Publication Date
Thu Dec 16 2021
Journal Name
Translational Vision Science & Technology
A Hybrid Deep Learning Construct for Detecting Keratoconus From Corneal Maps
...Show More Authors

View Publication
Scopus (27)
Crossref (26)
Scopus Clarivate Crossref
Publication Date
Fri Mar 01 2013
Journal Name
Journal Of Economics And Administrative Sciences
The Role of Forensic Accounting in Detecting Financial Fraud
...Show More Authors

A Forensic Accounting is represent science that deals with the application of knowledge in the areas of accounting, finance, tax and audit for the analysis, investigation, inquiry, inspection and testing issues in the civil law and criminal law in an attempt to reach the truth through which enable the Forensic Accountant to provide his Expert opinion , forensic accounting plays a major role by providing a range of important services in the field of investigation for fraud and litigation support, As one of the most important legal and accounting functions is to investigate allegations of alleged by the related parties, especially those allegations related to the existence of fraud, since the goal of judicial accountant will depend

... Show More
View Publication Preview PDF
Crossref (1)
Crossref
Publication Date
Wed Jan 10 2024
Journal Name
The American Journal Of Interdisciplinary Innovation And Research
SUBJECT: REVIEW METHODS OF DETECTING SUGAR IN A SAMPLE
...Show More Authors

Publication Date
Sun Oct 01 2023
Journal Name
Baghdad Science Journal
Detecting DNA of multispecies dinoflagellate cysts in the sediment from three estuaries of Makassar strait and fishing port using CO1 primer: Is it CO1 primer suitable for detecting DNA dinoflagellate?
...Show More Authors

Most dinoflagellate had a resting cyst in their life cycle.  This cyst was developed in unfavorable environmental condition. The conventional method for identifying dinoflagellate cyst in natural sediment requires morphological observation, isolating, germinating and cultivating the cysts.  PCR is a highly sensitive method for detecting dinoflagellate cyst in the sediment.  The aim of this study is to examine whether CO1 primer could detect DNA of multispecies dinoflagellate cysts in the sediment from our sampling sites. Dinoflagellate cyst DNA was extracted from 16 sediment samples. PCR method using COI primer was running. The sequencing of dinoflagellate cyst DNA was using BLAST. Results showed that there were two clades of dinoflag

... Show More
View Publication Preview PDF
Scopus (1)
Crossref (1)
Scopus Crossref
Publication Date
Tue Dec 11 2018
Journal Name
Iraqi National Journal Of Nursing Specialties
Episiotomy preventing approaches among midwives in Kurdistan region
...Show More Authors

Objectives: This study aimed to findout approaches which used by midwives for avoiding episiotomy and assess their knowledge regarding complications of episiotomy in three main cities of Kurdistan region. Methodology: A cross-sectional study was conducted between 1st January and 15th April 2014 in the three biggest maternity teaching hospitals. The study population included all the midwives (n=53) working in delivery rooms. Data were collected through interview with midwives. Results: The Midwives stated the followings as complications of episiotomy: tear into the rectum muscle or rectum itself (52.8%), bleedi

... Show More
View Publication Preview PDF
Publication Date
Sun Jan 01 2023
Journal Name
Journal Of Engineering
Intelligent Congestion Control of 5G Traffic in SDN using Dual-Spike Neural Network
...Show More Authors

Software Defined Networking (SDN) with centralized control provides a global view and achieves efficient network resources management. However, using centralized controllers has several limitations related to scalability and performance, especially with the exponential growth of 5G communication. This paper proposes a novel traffic scheduling algorithm to avoid congestion in the control plane. The Packet-In messages received from different 5G devices are classified into two classes: critical and non-critical 5G communication by adopting Dual-Spike Neural Networks (DSNN) classifier and implementing it on a Virtualized Network Function (VNF). Dual spikes identify each class to increase the reliability of the classification

... Show More
View Publication Preview PDF
Crossref (2)
Crossref