Change point detection (CPD) is a valuable technique in time series (TS) analysis, which allows for the automatic detection of abrupt variations within the TS. It is often useful in applications such as fault, anomaly, and intrusion detection systems. However, the inherent unpredictability and fluctuations in many real-time data sources pose a challenge for existing contemporary CPD techniques, leading to inconsistent performance across diverse real-time TS with varying characteristics. To address this challenge, we have developed a novel and robust online CPD algorithm constructed from the principle of discriminant analysis and based upon a newly proposed between-class average and variance evaluation approach, termed B-CAVE. Our B-CAVE algorithm features a unique change point measure, which has only one tunable parameter (i.e. the window size) in its computational process. We have also proposed a new evaluation metric that integrates time delay and the false alarm error towards effectively comparing the performance of different CPD methods in the literature. To validate the effectiveness of our method, we conducted experiments using both synthetic and real datasets, demonstrating the superior performance of the B-CAVE algorithm over other prominent existing techniques.

Some recent survey statistics suggest that low power wide area networks (LPWANs) are fast becoming the most prevalent communication platform used in many applications of the Internet of Things (IoT). However, because most LPWANs are generally deployed in the presently congested industrial, scientific, and medical bands, they are invariably plagued by problems associated with spectral congestion, such as increased interference, reduced data rates, and spectra inefficiency. These problems are solvable by integrating cognitive radio (CR) technologies in LPWAN (termed CR-LPWAN), for which some pioneering solutions now exist in the literature. Consequently, this article takes an early look at some of these pioneering efforts pertaining to the development of CR-LPWAN systems. We discuss a general network architecture and a physical layer front-end model suitable for CR-LPWAN systems. Then, some notable state-of-the-art approaches for CR-LPWAN systems are discussed. Potential advantages of CR-LPWAN systems for IoT-based applications are also presented, and this article closes with a few research challenges and future research directions in this regard. This article aims to serve as a starting point for most budding researchers who may be interested in the development of effective and efficient CR-LPWAN systems for the enhancement of different IoT-based applications.

In this paper, we have discussed the integration of Cognitive Radio (CR) in Low Power Wide Area Network (LPWAN) based on a generic network architecture and a PHY layer front-end model. Essentially, since most existing LPWAN technologies are proprietary in nature, it is necessary to present insights that may spur newer developments to enhance many Internet of Things (IoT)-based applications, including Industrial IoT (IIoT) applications such as smart factories, smart metering, and smart city architectures. Generally, this paper will benefit researchers who may be seeking to develop CR-LPWAN systems towards enhancing IoT-based applications.

This paper introduces a novel application of an enhanced Wavelet-based Scale Space Filtering (WSSF) algorithm called Adaptive WSSF (AWSSF). The AWSSF concept was conceived to improve Spectrum Sensing (SS) in Cognitive Radio (CR). The algorithm is based on a novel adaptation of the WSSF and Otsu's algorithm (from Image Processing). The AWSSF decomposes the estimated signals into different scale levels by using Wavelet Transformation (WT) theory. Thereafter, it directly multiplies samples from adjacent scales towards reducing the noise samples, while simultaneously increasing the true Licensed User (LU) signals. Furthermore, we adapted Otsu's multi-threshold algorithm for use in the AWSSF to compute the optimum threshold value for the different decomposition levels towards filtering the wavelet coefficients. During evaluation in the low Signal to Noise Ratio (SNR) region, the AWSSF algorithm was compared to the traditional ED, and shown to perform better. We also compared with other WT based approaches at SNR =-10dB, and the AWSSF achieved better results. The AWSSF met the performance requirement of the IEEE 802.22 standard as compared to other approaches, and thus considered viable for application in CR.

In this paper, a newly proposed Real Valued Neural Network (RVNN) based Energy Detector (ED) is presented for Cognitive Radio (CR) application. With little available on the performance of EDs in varying spectrum occupancy conditions, we provide a study to understand how occupancy variation affects the performance of a newly proposed RVNN based ED and other ED schemes. Other factors such as varying Signal to Noise Ratio (SNR) and model order values were also examined in this study and result analysis conducted using the Precision-detection statistics. Implication of results obtained indicate that the RVNN based ED would perform optimum in high occupancy and SNR conditions for a model order choice of P = 20. We also observed that the RVNN based ED would provide better precision performance characteristics over the Periodogram, Welch and Multitaper based ED schemes compared herein. Hence, the RVNN based ED suffices as a favourable choice for CR application even under varying occupancy conditions.