Adaptive threshold techniques for cognitive radio‐based low power wide area network

Spectrum sensing is an efficient technology for addressing the shortage of spectrum resources. Widely used methods usually employ model-based features as the test statistics, such as energies and eigenvalues, ignoring the temporal correlation aspect. Deep learning based methods have the potential to focus on various aspects, including temporal correlation. However, the existing ones are not good at capturing the temporal correlation features from spectrum data as traditional convolutional neural network (CNN) and long short-term memory network (LSTM) are used for feature extraction. Traditional CNNs were not designed to capture the global temporal correlations from time series data. Standard LSTM captures the temporal correlations based on the data collected from previous time slots only and cannot emphasize some important parts of a time series. This article proposes a data-driven deep learning based model to classify the received raw signals automatically, where the received signal data is considered time-series data. The proposed deep neural network (DNN) model is mainly featured with 1-dimensional convolutional neural network (1D CNN), bidirectional long short-term memory network (BiLSTM), and self-attention (SA). The 1D CNN and BiLSTM are responsible for extracting the local features and global correlations from the time series data, and BiLSTM could extract sufficient features in opposite directions. The SA layer enables the classifier network to emphasize those important features obtained by BiLSTM. The sim-ulation results demonstrate that our model performs better than a number of existing DNN models in terms of the probabilities of missed detection and false alarm, especially when the signal to noise ratio is low. Moreover, the impacts of the modulation scheme and sample length on the detection performance are studied.

Section: Offline Trainingmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Spectrum sensing in cognitive radio: A deep learning based model

Xing

Qin

Luo

et al. 2021

“…However, the CR technology can solve the challenges of resource limitation for IoT applications by providing access to more bandwidth, for example, through enhanced spectrum sensing techniques. [133][134][135]…”

Section: Cognitive-iotsmentioning

confidence: 99%

A review of industrial wireless communications, challenges, and solutions: A cognitive radio approach

Oyewobi

Djouani

Kurien

2020

Integral and crucial to performance of wireless sensor networks (WSNs), and specifically industrial wireless sensor network (IWSN) is stable, robust, reliable, and ubiquitous communications system. Though, wired communications system is suitable for industrial communications and is resilient to shadowing and multipath fading effects of industrial‐WSN environments, yet its wireless counterpart is a much preferred industrial communications technology due to reduced cost and high flexibility which it offers in comparison to wired communications. However, overcrowding of the industrial, scientific, and medical band, where IWSN is deployed together with other heterogeneous technologies, as well as resultant scarcity of usable frequency spectrum has restrained exclusive application of wireless technology for industrial communications. Nonetheless, cognitive radio (CR) has ability to increase spectrum utilization efficiency and channel capacity for industrial wireless communications (IWC) through opportunistic/dynamic spectrum access (DSA) technique. In this review article, we examine how DSA can benefit IWC through exploitation of new perspectives of white space definitions in the licensed bands as well as unlicensed bands. While discussing the potential of DSA for IWC, we have considered the unique characteristics of IWC as well as technical challenges and issues imposed by industrial‐WSN. Accordingly, we have suggested and proffered appropriate CR‐based solutions in mitigating some of the challenges where necessary.

“…It has explored various LPWAN technologies based on the network layer to allow the user to use artificial intelligence efficiently and comfortably. Onumanyi et al 17 used adaptive threshold techniques to analyze the compatibility of CRN‐LPWAN systems. To achieve this, they proposed an appropriate network architecture and physical layer model for optimal integration of the CRN into the LPWAN.…”

Section: Introductionmentioning

confidence: 99%

An improved genetic algorithm approach to spectrum sensing for long range based cognitive radio networks

Yalçın

2022

By designing cognitive radio networks (CRNs) for low power wide area networks (LPWANs), adaptive spectrum sensing plays an important role in using frequency bands effectively. With spectrum sensing, existing spectrum holes are filled by enabling secondary users to use the licensed band that primary users do not use. Many researchers have proposed various optimization or artificial intelligence techniques in CRNs for spectrum sensing. However, there is hardly any adaptive spectrum sensing method integrated into the LoRa communication standard, which is a very popular LPWAN technology. For this purpose, an adaptive optimization based spectrum sensing methodology with an improved genetic algorithm is proposed in this study. Depending on this methodology, two fitness functions adapted to the LoRa-based network are defined. Thanks to these functions, the movement of individuals in the network population is provided. In parallel, received signal strength values of optimum LoRa nodes were determined by genetic coding, and bands to be used by SUs instead of PUs were discovered considering minimum bit errors. To verify the success of the proposed method, various simulation experiments were carried out. The performance results strikingly show that the proposed method is quite successful for LoRa-CRNs. For example, the proposed method significantly improved the bit error rate performance, and reduced the number of faulty transmissions caused by packet collisions. It also reduced the packet error rate by more than 8% per minute in a 200-node network.