Machine Learning Techniques for Security of Internet of Things (IoT) and Fog Computing Systems

Moh, Melody; Raju, Robinson

doi:10.1109/hpcs.2018.00116

Cited by 43 publications

(34 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Once completed, (3) the results are compared between workers and the workplace to establish the appropriate design parameter, and (4) finally, when the design parameter has been selected, filters or amplifiers of variety are employed to adjust the Competences-Capacities between workers and the workplace. Each dimension that characterizes the enactive paradigm is defined by a set of variables that are identified through a questionnaire in the design phase and later in the work process through a set of sensors integrated in wearables, which are processed locally in real time (edge) to customize the environment for the worker [56,57] in the nearby environment (fog) and thus adjust to the worker the parameters of the surrogate model that allows the adaptation of the workplace to a particular worker through machine learning and other affective design algorithms [58]. Finally, data from sensors and wearables are sent to the cloud to update the surrogate model, adapting the work environment to the worker in an evolutionary way.…”

Section: Methods Techniques and Toolsmentioning

confidence: 99%

See 1 more Smart Citation

Framework for the Development of Affective and Smart Manufacturing Systems Using Sensorised Surrogate Models

Ávila-Gutiérrez

Aguayo-González

Lama-Ruiz

2021

Sensors

View full text Add to dashboard Cite

Human Factor strategy and management have been affected by the incorporation of Key Enabling Technologies (KETs) of industry 4.0, whereby operator 4.0 has been configured to address the wide variety of cooperative activities and to support skills that operate in VUCA (volatile, uncertain, complex, and ambiguous) environments under the interaction with ubiquitous interfaces on real and virtual hybrid environments of cyber-physical systems. Current human Competences-Capacities that are supported by the technological enablers could result in a radically disempowered human factor. This means that in the processes of optimization and improvement of manufacturing systems from industry 4.0 to industry 5.0, it would be necessary to establish strategies for the empowerment of the human factor, which constitute symbiotic and co-evolutionary socio-technical systems through talent, sustainability, and innovation. This paper establishes a new framework for the design and development of occupational environments 5.0 for the inclusion of singularized operators 4.0, such as individuals with special capacities and talents. A case study for workers and their inclusion in employment is proposed. This model integrates intelligent and inclusive digital solutions in the current workspaces of organizations under digital transformation.

show abstract

Section: Methods Techniques and Toolsmentioning

confidence: 99%

“…Figure 11 and Table 8 cover the various frameworks and algorithms in cloud, fog, and edge that have been collected from [56][57][58]82]. Firstly, this includes sensorization and data acquisition at the edge, followed by processing in fog, massive data ingestion, and its subsequent storage and treatment under cognitive computing.…”

Section: Case Studymentioning

confidence: 99%

Framework for the Development of Affective and Smart Manufacturing Systems Using Sensorised Surrogate Models

Ávila-Gutiérrez

Aguayo-González

Lama-Ruiz

2021

Sensors

View full text Add to dashboard Cite

show abstract

“…Among several RL techniques, Q-learning requires low computational resources for its implementation and does not require the knowledge of the model of the environment, thus being a suitable learning technique for the resource-constrained fog nodes [29]. Furthermore, Q-learning has been used extensively to address resource allocation problems [30], thus being a suitable learning technique for the problem.…”

Section: B Proposed Resource Allocation Mechanismmentioning

confidence: 99%

Reinforcement Learning-Based Resource Management Model for Fog Radio Access Network Architectures in 5G

2021

View full text Add to dashboard Cite

The need to cope with the continuously growing number of connected users and the increased demand for mobile broadband services in the Internet of Things has led to the notion of introducing the fog computing paradigm in fifth generation (5G) mobile networks in the form of fog radio access network (F-RAN). The F-RAN approach emphasises bringing the computation capability to the edge of the network so as to reduce network bottlenecks and improve latency. However, despite the potential, the management of computational resources remains a challenge in F-RAN architectures. Thus, this paper aims to overcome the shortcomings of conventional approaches to computational resource allocation in F-RANs. Reinforcement learning (RL) is presented as a method for dynamic and autonomous resource allocation, and an algorithm is proposed based on Q-learning. RL has several benefits in resource allocation problems and simulations carried out show that it outperforms reactive methods. Furthermore, the results show that the proposed algorithm improves latency and thus has the potential to have a major impact in 5G applications, particularly the Internet of Things.

show abstract

“…Lately, detection methods based on ensemble methods and deep learning approaches have emerged as prevalent detection techniques. In [8], authors provided a comprehensive study on the various machine learning techniques like Decision Tree, KNN, Random Forest, etc. and how machine learning based intrusion detection techniques at fog layer are capable of detecting abnormalities or attack.…”

Section: Introductionmentioning

confidence: 99%

Intrusion Detection Based on Autoencoder and Isolation Forest in Fog Computing

2020

View full text Add to dashboard Cite

Fog Computing has emerged as an extension to cloud computing by providing an efficient infrastructure to support IoT. Fog computing acting as a mediator provides local processing of the endusers' requests and reduced delays in communication between the end-users and the cloud via fog devices. Therefore, the authenticity of incoming network traffic on the fog devices is of immense importance. These devices are vulnerable to malicious attacks. All kinds of information, especially financial and health information travel through these devices. Attackers target these devices by sending malicious data packets. It is imperative to detect these intrusions to provide secure and reliable service to the user. So, an effective Intrusion Detection System (IDS) is essential for the secure functioning of fog without compromising efficiency. In this paper, we propose a method (Auto-IF) for intrusion detection based on deep learning approach using Autoencoder (AE) and Isolation Forest (IF) for the fog environment. This approach targets only binary classification of the incoming packets as fog devices are more concerned about differentiating attack from normal packets in real-time. We validate the proposed method on the benchmark NSL-KDD dataset. Our technique of intrusion detection achieves a high accuracy rate of 95.4% as compared to many other state-of-art intrusion detection methods.

show abstract

Machine Learning Techniques for Security of Internet of Things (IoT) and Fog Computing Systems

Cited by 43 publications

References 9 publications

Framework for the Development of Affective and Smart Manufacturing Systems Using Sensorised Surrogate Models

Framework for the Development of Affective and Smart Manufacturing Systems Using Sensorised Surrogate Models

Reinforcement Learning-Based Resource Management Model for Fog Radio Access Network Architectures in 5G

Intrusion Detection Based on Autoencoder and Isolation Forest in Fog Computing

Contact Info

Product

Resources

About