| 1. |
- Rabbani, Hami, et al.
(författare)
-
Improving the Achievable Rates of Optical Coherent Transmission with Back-Propagation
- 2018
-
Ingår i: IEEE Photonics Technology Letters. - 1041-1135 .- 1941-0174. ; 30:14, s. 1273-1276
-
Tidskriftsartikel (refereegranskat)abstract
- The power allocation in wavelength-division multi- plexed (WDM) fiber-optic links with digital back-propagation (BP) is optimized in order to improve the achievable rates (AR). The power allocation is performed using a convex optimization technique based on a modulation-format-dependent time-domain model capable of including the nonlinear Kerr effects. In a fully loaded WDM link with heterogeneous (uneven) nonlinear interference noise (NLIN) spectrum, the AR gain of nonlinear BP over linear electronic dispersion compensation is 60% larger if per-channel power optimization is allowed than if all transceivers use an equal (flat) optimized power. The heterogeneous NLIN spectrum results from performing BP on a subset of the channels. However, the gain of per-channel power optimization disappears for the homogeneous (nearly flat) NLIN spectrum. Moreover, we show that the improvement obtained by joint channel power allocation is more pronounced for links with a larger number of spans.
|
|
| 2. |
- Rabbani, Hami, et al.
(författare)
-
Quality of Transmission Aware Optical Networking Using Enhanced Gaussian Noise Model
- 2019
-
Ingår i: Journal of Lightwave Technology. - 0733-8724 .- 1558-2213. ; 37:3, s. 831-838
-
Tidskriftsartikel (refereegranskat)abstract
- We present a new joint routing, wavelength, and power allocation method for optical network planning. The introduced gradient-based convex optimization approach has a lower computational complexity, compared to common linear programming techniques, suitable for both static as well as time-critical dynamic network planning with fast convergence requirement. The proposed scheme takes physical-layer impairments into account, using the enhanced Gaussian noise nonlinear model. In contrast to methods exploiting the theoretical full link spectrum utilization assumption (fully occupied fiber-optic C-hand spectrum), we focus on maximizing the network achievable rate and minimum signal-to-noise ratio (SNR) margin of networks with partial spectrum utilization in their links, relevant to the majority of empirical metro network scenarios. According to numerical results, the network achievable rate can be improved around 17% by performing power optimization over the individual launch power of network lightpaths compared to optimizing a single flat (equal) launch power for all the lightpaths. Moreover, the minimum SNR margin of the simulated network is improved by about 23 dB. Finally, it is observed that maximizing the network minimum SNR margin needs the launch power of each lightpath to be proportional to the total nonlinear interference noise efficiency influencing the lightpath.
|
|
| 3. |
- Rabbani, Mahdi, et al.
(författare)
-
A Hybrid Machine Learning Approach for Malicious Behaviour Detection and Recognition in Cloud Computing
- 2020
-
Ingår i: Journal of Network and Computer Applications. - London : Academia Press. - 1084-8045 .- 1095-8592. ; 151
-
Tidskriftsartikel (refereegranskat)abstract
- The rapid growth of new emerging computing technologies has encouraged many organizations to outsource their data and computational requirements. Such services are expected to always provide security principles such as confidentiality, availability and integrity; therefore, a highly secure platform is one of the most important aspects of cloud-based computing environments. A considerable improvement over traditional security strategies is achieved by understanding how malware behaves over the entire behavioural space. In this paper, we propose a new approach to improve the capability of cloud service providers to model users’ behaviours. We applied a particle swarm optimization-based probabilistic neural network (PSO-PNN) for the detection and recognition process, in the first module of the recognition process, we meaningfully converted the users’ behaviours to an understandable format and then classified and recognized the malicious behaviours by using a multi-layer neural network. We took advantage of the UNSW-NB15 dataset to validate the proposed solution by characterizing different types of malicious behaviours exhibited by users. Evaluation of the experimental results shows that the proposed method is promising for use in security monitoring and recognition of malicious behaviours. © 2019 Elsevier Ltd
|
|
| 4. |
- Rabbani, Mahdi, et al.
(författare)
-
A Review on Machine Learning Approaches for Network Malicious Behavior Detection in Emerging Technologies
- 2021
-
Ingår i: Entropy. - Basel : MDPI. - 1099-4300. ; 23:5
-
Forskningsöversikt (refereegranskat)abstract
- Network anomaly detection systems (NADSs) play a significant role in every network defense system as they detect and prevent malicious activities. Therefore, this paper offers an exhaustive overview of different aspects of anomaly-based network intrusion detection systems (NIDSs). Additionally, contemporary malicious activities in network systems and the important properties of intrusion detection systems are discussed as well. The present survey explains important phases of NADSs, such as pre-processing, feature extraction and malicious behavior detection and recognition. In addition, with regard to the detection and recognition phase, recent machine learning approaches including supervised, unsupervised, new deep and ensemble learning techniques have been comprehensively discussed; moreover, some details about currently available benchmark datasets for training and evaluating machine learning techniques are provided by the researchers. In the end, potential challenges together with some future directions for machine learning-based NADSs are specified.
|
|
