![]() |
| |||||||||||
SI AID 2024 : SPECIAL ISSUE on Adaptive Intrusion Detection System using Machine Learning in Wireless Sensor Networks | |||||||||||
Link: https://www.degruyter.com/journal/key/comp/html | |||||||||||
| |||||||||||
Call For Papers | |||||||||||
๐๐๐๐พ๐๐ผ๐ ๐๐๐๐๐ ๐ค๐ฃ ๐ผ๐๐๐ฅ๐ฉ๐๐ซ๐ ๐๐ฃ๐ฉ๐ง๐ช๐จ๐๐ค๐ฃ ๐ฟ๐๐ฉ๐๐๐ฉ๐๐ค๐ฃ ๐๐ฎ๐จ๐ฉ๐๐ข ๐ช๐จ๐๐ฃ๐ ๐๐๐๐๐๐ฃ๐ ๐๐๐๐ง๐ฃ๐๐ฃ๐ ๐๐ฃ ๐๐๐ง๐๐ก๐๐จ๐จ ๐๐๐ฃ๐จ๐ค๐ง ๐๐๐ฉ๐ฌ๐ค๐ง๐ ๐จ
This special issue in ๐ข๐ฝ๐ฒ๐ป ๐๐ผ๐บ๐ฝ๐๐๐ฒ๐ฟ ๐ฆ๐ฐ๐ถ๐ฒ๐ป๐ฐ๐ฒ (๐๐ ๐ฎ๐ฌ๐ฎ๐ฎ: ๐ญ.๐ฑ) focuses on A vast variety of detection nodes make up a Wireless Sensor Networks (WSN), which collects and sends data to a central point. However, distribution tactics, communications channels, and limited supply nodes provide a number of safety concerns for WSN. Therefore, in order to enhance the security aspects of wireless sensor networks, it is imperative to identify unauthorized access. These functions are given to the network-by-network intrusion detection systems, and they are necessary for all interactions on the network. Intrusion Detection Systems (IDS) frequently include Machine Learning (ML) approaches; yet, ML techniques' effectiveness is subpar when managing unbalanced assaults. According to their inadequate rechargeable energy supply, small bandwidth assistance, data travel over multiple hop nodes, reliance on intermediaries or other nodes, dispersed nature, and organization, WSN nodes are vulnerable to a variety of security-related attacks. The widespread use of WSN presents issues for maintaining their secrecy, credibility, and reliability. Intrusion detection serves as a strong first line of defense for the WSNs and is a crucial active defense mechanism. The disparity between dependable information distribution and restricted sensing power, as well as the dispute over the impact of detection and the scarcity of network resources, must be balanced given the special characteristics of WSN. WSN may overcome the drawbacks of conventional monitoring techniques, which considerably lower the expense of detection while also streamlining the laborious procedure. WSN assaults are visible at every model tier. Because of this, wireless sensor nodes face a variety of problems. Some are connected to technical concerns, while others arise as a result of assaults. To identify and stop threats, defensive and network monitoring systems must be built. The ability to create an affordable ML model for quick intrusion detection and prevention in border regions using WSN is made possible by the notable rise in appeal of accessible ML algorithms and the sharp rise in the utilization of artificial data. However, extra protection precautions need to be taken since WSNs differ from typical networks in terms of design and technology. To guarantee WSN security, an IDS is modelled in this work. A hybrid architecture that combines the use of authorization, overuse, and anomaly-based detection techniques with intrusion detection systems is suggested because these techniques alone are unable to offer reliability. A compact intelligent intrusion detection model for WSN is proposed in this special issue. With the use of anomalous network data, our model can detect attack behaviors in WSNs with speed and accuracy. Therefore, the supervised neural network satisfies the criterion of convenient data analysis in contrast with different machine learning methods Potential topics include, but are not limited to: โข Machine learning approaches for Intrusion detection in wireless sensor networks. โข A hierarchical neural network-based intrusion detection solution for wireless sensor networks. โข A cooperative intrusion detection technology optimized for wireless sensor networks. โข An extensively artificial network-based self-adaptive technique for wireless intrusion detection. โข A thin-layer proactive intrusion detection structure for wireless sensor networks. โข Regarding the viability of machine learning for intrusion detection in sensor networks. โข Efficient supporting vector machine-based intrusion detection method for wireless sensor networks. โข Machine learning-based intrusion detection system with optimization support in wireless sensor networks. โข Designing Intrusion Detection Systems in Wireless Sensor Networks via Machine Learning Technologies. โข A wireless Internet of things intrusion detection solution powered by machine learning. โข Developing autonomous machine learning network intrusion detection solutions for abuse. Authors are requested to submit their full revised papers complying with the general scope of the journal. The submitted papers will undergo the standard peer-review process before they can be accepted. Notification of acceptance will be communicated as we progress with the review process. === ๐ฎ๐ผ๐ฌ๐บ๐ป ๐ฌ๐ซ๐ฐ๐ป๐ถ๐น๐บ Tarek Moulahi, Qassim University, Saudi Arabia. Rateb Jabbar, Qatar University, Qatar. Musab Al-Ghadi, La Rochelle University, France. ๐ผ๐ฟ๐๐๐๐๐๐ ๐๐ฟ๐๐๐๐ Christos Anagnostopoulos, University of Glasgow, United Kingdom === ๐ซ๐ฌ๐จ๐ซ๐ณ๐ฐ๐ต๐ฌ The deadline for submissions is ๐๐จ๐ก๐ ๐ญ๐ฑ, ๐ฎ๐ฌ๐ฎ๐ฐ, but individual papers will be reviewed and published online on an ongoing basis. === ๐ฏ๐ถ๐พ ๐ป๐ถ ๐บ๐ผ๐ฉ๐ด๐ฐ๐ป All submissions to the Special Issue must be made electronically via the online submission system Editorial Manager: ๐ต๐๐๐ฝ๐://๐๐๐.๐ฒ๐ฑ๐ถ๐๐ผ๐ฟ๐ถ๐ฎ๐น๐บ๐ฎ๐ป๐ฎ๐ด๐ฒ๐ฟ.๐ฐ๐ผ๐บ/๐ผ๐ฝ๐ฒ๐ป๐ฐ๐/๐ฑ๐ฒ๐ณ๐ฎ๐๐น๐๐ฎ.๐ฎ๐๐ฝ๐ Please choose the article type โ๐๐: ๐ผ๐๐๐ฅ๐ฉ๐๐ซ๐ ๐๐ฃ๐ฉ๐ง๐ช๐จ๐๐ค๐ฃ ๐ฟ๐๐ฉ๐๐๐ฉ๐๐ค๐ฃ ๐๐ฎ๐จ๐ฉ๐๐ข ๐ช๐จ๐๐ฃ๐ ๐๐ ๐๐ฃ ๐๐๐โ. === ๐ช๐ถ๐ต๐ป๐จ๐ช๐ป ๐ผ๐ฝ๐ฒ๐ป๐ฐ๐ผ๐บ๐ฝ๐๐๐ฒ๐ฟ๐๐ฐ๐ถ๐ฒ๐ป๐ฐ๐ฒ@๐ฑ๐ฒ๐ด๐ฟ๐๐๐๐ฒ๐ฟ.๐ฐ๐ผ๐บ === ๐๐ผ๐ฟ ๐บ๐ผ๐ฟ๐ฒ ๐ถ๐ป๐ณ๐ผ๐ฟ๐บ๐ฎ๐๐ถ๐ผ๐ป, ๐ฝ๐น๐ฒ๐ฎ๐๐ฒ ๐๐ถ๐๐ถ๐ ๐ผ๐๐ฟ ๐๐ฒ๐ฏ๐๐ถ๐๐ฒ. https://www.degruyter.com/journal/key/comp/html#overview |
|