Mohammadmehdi Hosseini

Dr. Mohammadmehdi Hosseini

Department of computer engineering, Islamic Azad University, Shahrood, Shāhrūd, Semnān, Iran
orcid

Research Focus & Metrics

Academic Career Length

15Years (2012-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
Verified
Journal Article
Open access
PDF file
HAHaider kasim Ali
Haider kasim Ali
Mohammadmehdi HosseiniMohammadmehdi Hosseini
Mohammadmehdi Hosseini
AYAhmad Yousofi
Ahmad Yousofi
MAMurtadha Ali Alazzawi
Murtadha Ali Alazzawi
Intrusion detection in network systems is a critical challenge due to the ever-increasing volume and complexity of cyber-attacks. Traditional methods often struggle with high-dimensional data and the need for real-time detection. This paper proposes a comprehensive intrusion detection method utilizing a novel wrapped feature selection approach combined with a long short-term memory classifier optimized with the whale optimization algorithm to address these challenges effectively. The proposed method introduces a novel feature selection technique using a multi-layer perceptron and a hybrid genetic algorithm-particle swarm optimization algorithm to select salient features from the input dataset, significantly reducing dimensionality while retaining critical information. The selected features are then used to train a long short-term memory network, optimized by the whale optimization algorithm to enhance its classification performance. The effectiveness of the proposed method is demonstrated through extensive simulations of intrusion detection tasks. The feature selection approach effectively reduced the feature set from 78 to 68 features, maintaining diversity and relevance. The proposed method achieved a remarkable accuracy of 99.62% in DDoS attack detection and 99.40% in FTP-Patator/SSH-Patator attack detection using the CICIDS-2017 dataset and an anomaly attack detection accuracy of 99.6% using the NSL-KDD dataset. These results highlight the potential of the proposed method in achieving high detection accuracy with reduced computational complexity, making it a viable solution for real-time intrusion detection.

1 August 2014 in International Journal of Applied Earth Observation and Geoinformation
Verified
Journal Article
Closed access
Bardia YousefiBardia Yousefi
Bardia Yousefi
SMSeyed Mostafa Mirhassani
Seyed Mostafa Mirhassani
AAAlireza AhmadiFard
Alireza AhmadiFard
Mohammadmehdi HosseiniMohammadmehdi Hosseini
Mohammadmehdi Hosseini

16 November 2024 in International Journal of Imaging Systems and Technology
Verified
Journal Article
Closed access
Mohammadmehdi HosseiniMohammadmehdi Hosseini
Mohammadmehdi Hosseini
ZMZahra Mosahebeh
Zahra Mosahebeh
SCSomenath Chakraborty
Somenath Chakraborty
AGAbdorreza Alavi Gharahbagh
Abdorreza Alavi Gharahbagh

19 August 2024 in Security and Privacy
Verified
Journal Article
Closed access
PDF file
RMR. Mohammadi
R. Mohammadi
Mohammadmehdi HosseiniMohammadmehdi Hosseini
Mohammadmehdi Hosseini
RBR. Bahrami
R. Bahrami

1 November 2013
Verified
Conference Paper
Closed access
BYBardia Yousefi
Bardia Yousefi
HTHua-Nong Ting
Hua-Nong Ting
SMSeyed Mostafa Mirhassani
Seyed Mostafa Mirhassani
Mohammadmehdi HosseiniMohammadmehdi Hosseini
Mohammadmehdi Hosseini
Here the problem of breast lesions detection using spatiotemporal based features is addressed. As the breast cancer is one of the most crucial reasons for death of women, earlier finding such lesions can increase the life of patients and more efficient treatment. Previously, Gabor wavelet has been introduced for spatiotemporal feature methods. In this approach, a multi-channel Gabor wavelet filter bank applied to the mammography image along with wavelet fusion made feature set. A Bayesian classifier classifies the final features into two different classes, normal and lesion class, with considering sparseness in features. Morphological operation with various structure elements of the mammography images has a crucial role in pre-processing stage of classification. The benchmark has been done utilizing 40 cases of Digital Database for Screening Mammography (DDSM) dataset. Training stage of classification performs by training map comprising 5 cases, normal and abnormal lesion cases. Proposed approach achieves accuracy of 98.75 percent which is relatively comparable with state-of-the-art methods(i.e.[10]).

11 December 2023 in Multimedia Tools and Applications
Verified
Journal Article
Closed access
PDF file
HZHamed Zargari
Hamed Zargari
Mohammadmehdi HosseiniMohammadmehdi Hosseini
Mohammadmehdi Hosseini
Abdorreza AlaviGharahbaghAbdorreza AlaviGharahbagh
Abdorreza AlaviGharahbagh