Towards the Next-Generation of Network Monitoring Systems

A special issue of Informatics (ISSN 2227-9709).

Deadline for manuscript submissions: closed (15 January 2022) | Viewed by 7877

Special Issue Editor


E-Mail Website
Guest Editor
Department of Electronic and Communications Technology, Autonomous University of Madrid, 28049 Madrid, Spain
Interests: network management and monitoring; traffic forecasting and classification; high-performance in low-cost hardware; computer networks; performance evaluation; queuing theory; cloud computing; IoT

Special Issue Information

Dear Colleagues,

Network-monitoring systems have proven to be a fundamental tool for helping network managers in their task of tracking network operation. Network-monitoring systems are useful to detect, and eventually solve, issues with slow or failing components, as they provide managers with both dashboards (with multiple time series of relevant metrics) and rich sets of measurements useful for determining the root causes of any incident. In addition, monitoring systems usually provide managers with mechanisms and algorithms to automatically identify abnormal behaviors and traffic anomalies in time series, flows or packet payloads, which trigger alarms in both active and proactive ways.

However, diverse factors are making the task of network monitoring harder than ever: the heterogeneity of the services and infrastructure of the Internet; the ever-increasing demand for both bandwidth and low latency from users; the advent of new paradigms, such as the Internet of Things, which calls for the -deployment of network probes around the world; the externalization of management tasks; and the balance between the costs and capacity of probes are some of the most significant challenges today.

This scenario opens up the opportunity for the next generation of monitoring systems that combine the most efficient capture modules, the application of both new data aggregation mechanisms and novel analysis approaches (especially those based on cutting-edge approaches such as machine learning), the exploitation of concepts such as software-defined networking and network-function virtualization, the support of cloud infrastructure to provide real monitoring as a service in public/private clouds, and the development of  detailed and useful dashboards without ignoring the costs of the probes and other hardware expenses.

To this end, this Special Issue is soliciting conceptual, theoretical, and experimental contributions to addressing a set of current challenges in the area of systems for network monitoring. The topics of interest include but are not limited to:

  • Novel visualization approaches and dashboards for networks metrics.
  • Improved capture and storage mechanisms for network measurements.
  • Techniques and algorithms for the automatic analysis of network measurements.
  • Algorithms and novel approaches to identify the root causes of network anomalies.
  • Data reduction for forensic analysis.
  • Use of software defined networking (SDN) and network function.
  • Virtualization (NFV) concepts for the development of monitoring systems.
  • The exploitation of machine learning techniques, such as neural networks, to improve monitoring systems.
  • The hardware/software optimization of monitoring systems for high-speed networks (>10 Gb/s).
  • The hardware/software optimization of monitoring systems for low-cost probes (<USD 1000).
  • Hybrid monitoring systems in public/private clouds.
  • Monitoring as a service in the cloud.
  • The monitoring of traffic at the application level, and the classification and identification of classes of traffic.
  • Experiences, deployments and testing of network-monitoring systems.
Dr. José Luis Garcia-Dorado

Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Informatics is an international peer-reviewed open access quarterly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 1800 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Published Papers (1 paper)

Order results
Result details
Select all
Export citation of selected articles as:

Research

22 pages, 3855 KiB  
Article
Windows PE Malware Detection Using Ensemble Learning
by Nureni Ayofe Azeez, Oluwanifise Ebunoluwa Odufuwa, Sanjay Misra, Jonathan Oluranti and Robertas Damaševičius
Informatics 2021, 8(1), 10; https://doi.org/10.3390/informatics8010010 - 10 Feb 2021
Cited by 60 | Viewed by 7196
Abstract
In this Internet age, there are increasingly many threats to the security and safety of users daily. One of such threats is malicious software otherwise known as malware (ransomware, Trojans, viruses, etc.). The effect of this threat can lead to loss or malicious [...] Read more.
In this Internet age, there are increasingly many threats to the security and safety of users daily. One of such threats is malicious software otherwise known as malware (ransomware, Trojans, viruses, etc.). The effect of this threat can lead to loss or malicious replacement of important information (such as bank account details, etc.). Malware creators have been able to bypass traditional methods of malware detection, which can be time-consuming and unreliable for unknown malware. This motivates the need for intelligent ways to detect malware, especially new malware which have not been evaluated or studied before. Machine learning provides an intelligent way to detect malware and comprises two stages: feature extraction and classification. This study suggests an ensemble learning-based method for malware detection. The base stage classification is done by a stacked ensemble of fully-connected and one-dimensional convolutional neural networks (CNNs), whereas the end-stage classification is done by a machine learning algorithm. For a meta-learner, we analyzed and compared 15 machine learning classifiers. For comparison, five machine learning algorithms were used: naïve Bayes, decision tree, random forest, gradient boosting, and AdaBoosting. The results of experiments made on the Windows Portable Executable (PE) malware dataset are presented. The best results were obtained by an ensemble of seven neural networks and the ExtraTrees classifier as a final-stage classifier. Full article
(This article belongs to the Special Issue Towards the Next-Generation of Network Monitoring Systems)
Show Figures

Figure 1

Back to TopTop