Machine learning algorithms for wireless sensor networks: A survey

Nowadays, many disruptive Internet-of-Things (IoT) applications emerge, such as augmented/virtual reality online games, autonomous driving, and smart everything, which are massive in number, data intensive, computation intensive, and delay sensitive. Due to the mismatch between the fifth generation (5G) and the requirements of such massive IoT-enabled applications, there is a need for technological advancements and evolutions for wireless communications and networking toward the sixth-generation (6G) networks. 6G is expected to deliver extended 5G capabilities at a very high level, such as Tbps data rate, sub-ms latency, cm-level localization, and so on, which will play a significant role in supporting massive IoT devices to operate seamlessly with highly diverse service requirements. Motivated by the aforementioned facts, in this article, we present a comprehensive survey on 6G-enabled massive IoT. First, we present the drivers and requirements by summarizing the emerging IoT-enabled applications and the corresponding requirements, along with the limitations of 5G. Second, visions of 6G are provided in terms of core technical requirements, use cases, and trends. Third, a new network architecture provided by 6G to enable massive IoT is introduced, i.e., space–air–ground–underwater/sea networks enhanced by edge computing. Fourth, some breakthrough technologies, such as machine learning and blockchain, in 6G are introduced, where the motivations, applications, and open issues of these technologies for massive IoT are summarized. Finally, a use case of fully autonomous driving is presented to show 6G supports massive IoT.

Enabling Massive IoT Toward 6G: A Comprehensive Survey

A variety of communication networks, such as industrial communication systems, have to provide strict delay guarantees to the carried flows. Fast and close to optimal quality of service (QoS) routing algorithms, e.g., delay-constrained least-cost (DCLC) routing algorithms, are required for routing flows in such networks with strict delay requirements. The emerging software-defined networking (SDN) paradigm centralizes the network control in SDN controllers that can centrally execute QoS routing algorithms. A wide range of QoS routing algorithms have been proposed in the literature and examined in individual studies. However, a comprehensive evaluation framework and quantitative comparison of QoS routing algorithms that can serve as a basis for selecting and further advancing QoS routing in SDN networks is missing in the literature. This makes it difficult to select the most appropriate QoS routing algorithm for a particular use case, e.g., for SDN controlled industrial communications. We close this gap in the literature by conducting a comprehensive up-to-date survey of centralized QoS routing algorithms. We introduce a novel four-dimensional (4D) evaluation framework for QoS routing algorithms, whereby the 4D correspond to the type of topology, two forms of scalability of a topology, and the tightness of the delay constraint. We implemented 26 selected DCLC algorithms and compared their runtime and cost inefficiency within the 4D evaluation framework. While the main conclusion of this evaluation is that the best algorithm depends on the specific sub-space of the 4D space that is targeted, we identify two algorithms, namely Lagrange relaxation-based aggregated cost (LARAC) and search space reduction delay-cost-constrained routing (SSR+DCCR), that perform very well in most of the 4D evaluation space.

https://mediatum.ub.tum.de/doc/1420144/file.pdf

Unicast QoS Routing Algorithms for SDN: A Comprehensive Survey and Performance Evaluation

The recent novel coronavirus (also known as COVID-19) has rapidly spread worldwide, causing an infectious respiratory disease that has killed hundreds of thousands and infected millions. While test kits are used for diagnosis of the disease, the process takes time and the test kits are limited in their availability. However, the COVID-19 disease is also diagnosable using radiological images taken through lung X-rays. This process is known to be both faster and more reliable as a form of identification and diagnosis. In this regard, the current study proposes an expert-designed system called COVIDetectioNet model, which utilizes features selected from combination of deep features for diagnosis of COVID-19. For this purpose, a pretrained Convolutional Neural Network (CNN)-based AlexNet architecture that employed the transfer learning approach, was used. The effective features that were selected using the Relief feature selection algorithm from all layers of the architecture were then classified using the Support Vector Machine (SVM) method. To verify the validity of the model proposed, a total of 6092 X-ray images, classified as Normal (healthy), COVID-19, and Pneumonia, were obtained from a combination of public datasets. In the experimental results, an accuracy of 99.18% was achieved using the model proposed. The results demonstrate that the proposed COVIDetectioNet model achieved a superior level of success when compared to previous studies.

/pdf/covidetectionet-covid-19-diagnosis-system-based-on-x-ray-1d7vfbbmqb.pdf

COVIDetectioNet: COVID-19 diagnosis system based on X-ray images using features selected from pre-learned deep features ensemble

Sensor technologies empower Industry 4.0 by enabling integration of in-field and real-time raw data into digital twins. However, sensors might be unreliable due to inherent issues and/or environmental conditions. This article aims at detecting anomalies in measurements from sensors, identifying the faulty ones and accommodating them with appropriate estimated data, thus paving the way to reliable digital twins. More specifically, we propose a general machine-learning-based architecture for sensor validation built upon a series of neural-network estimators and a classifier. Estimators correspond to virtual sensors of all unreliable sensors (to reconstruct normal behaviour and replace the isolated faulty sensor within the system), whereas the classifier is used for detection and isolation tasks. A comprehensive statistical analysis on three different real-world data-sets is conducted and the performance of the proposed architecture validated under hard and soft synthetically-generated faults.

Sensor-Fault Detection, Isolation and Accommodation for Digital Twins via Modular Data-Driven Architecture

Wireless sensor networks (WSNs) are prone to many failures such as hardware failures, software failures, and communication failures. The fault detection in WSNs is a challenging problem due to sensor resources limitation and the variety of deployment field. Furthermore, the detection has to be precise to avoid negative alerts, and rapid to limit loss. The use of machine learning seems to be one of the most convenient solutions for detecting failure in WSNs. In this paper, support vector machines (SVMs) classification method is used for this purpose. Based on statistical learning theory, SVM is used in our context to define a decision function. As a light process in term of required resources, this decision function can be easily executed at cluster heads to detect anomalous sensor. The effectiveness of SVM for fault detection in WSNs is shown through an experimental study, comparing it to latest for the same application.

Fault Detection in Wireless Sensor Networks Through SVM Classifier

Vehicular ad hoc networks are a special type of MANET providing vehicle to vehicle and vehicle to roadside wireless communications. Vehicular ad-hoc network (VANET) have been designed in order to assist drivers on the road with a variety of applications especially in preventing danger and saving lives. For such ends, broadcasting is a suitable scheme to convey emergency messages dissemination to the entire network. Broadcasting in VANETs is a challenging task due to the specific VANET features such as nodes mobility and frequent topology changes. VANET applications, especially those related with human life saving, are delay sensitive and have specific requirements in terms of performances and QoS. A QoS aware broadcasting scheme relies on different factors and has to deal with hard constraints. In this paper, we introduce a survey of broadcasting in vehicular networks and discussion of different performance and QoS related to broadcasting issues. Furthermore, a comparative study of QoS aware broadcasting protocols classifying them according to different taxonomies is elaborated. This survey specifies QoS requirements and performance metrics of VANET services. Furthermore, this survey focuses on QoS aware broadcasting as a challenging problem regrading VANET characteristics.

A survey and comparative study of QoS aware broadcasting techniques in VANET

Homomorphic encryption systems statement: Trends and challenges

Due to the number of constraints and the dynamic nature of vehicular ad hoc networks (VANET), effective information exchange always remains a difficult task. Management of various load control parameters between the different nodes of the urban VANET (UVANET) network makes the optimization is difficult. In this work, we use a multi-objective problem that takes the parameters of our algorithm based on the Graph Classification Method with Attribute Vectors (GCMAV) as input. This algorithm aims to provide an improved class lifetime, an improved information delivery rate, a reduced inter-class overload, and an optimization of a global criterion. A scalable algorithm is used to optimize the parameters of the GCMAV. Then, to address the performance and security challenges in the UVANET environment, we introduce an Efficient Key Management Scheme (KMSUNET) based on symmetric and asymmetric encryption. Our KMSUNET diagram takes into account the position of the vehicle nodes, the speed, the direction, the number of neighboring vehicle nodes, and the reputation of each node. The simulations were carried out using the NetSim simulator and Multi-Objective Evolutionary Algorithms (MOEA) framework to optimize parameters. Experiments were carried out with realistic maps of Open Street Maps and its results were compared with other algorithms. The survey suggests that the proposed methodology works well concerning the average lifetime of the inter-classes and the information's delivery rate.

Bechir Alaya

Papers

Fault Detection in Wireless Sensor Networks Through SVM Classifier

A survey and comparative study of QoS aware broadcasting techniques in VANET

Homomorphic encryption systems statement: Trends and challenges

Clustering method and symmetric/asymmetric cryptography scheme adapted to securing urban VANET networks

SAMNET: Self-adaptative multi-kernel clustering algorithm for urban VANETs