More recently, smart agriculture has received widespread attention, which is a deep combination of modern agriculture and the Internet of Things (IoT) technology. To achieve the aim of scientific cultivation and precise control, the agricultural environments are monitored in real time by using various types of sensors. As a result, smart agricultural IoT generated a large amount of multidimensional time series data. However, due to the limitation of applied scenarios, smart agricultural IoT often suffers from data loss and misrepresentation. Moreover, some intelligent decision-makings for agricultural management also require the detailed analysis of data. To address the above problems, this article proposes a new anomaly detection model based on generative adversarial networks (GAN), which can process the multidimensional time series data generated by smart agricultural IoT. GAN is a deep learning model to learn the distribution patterns of normal data and capture the temporal dependence of time series and the potential correlations between features through learning. For the problem of generator inversion, an encoder–decoder structure incorporating the attention mechanism is designed to improve the performance of the model in learning normal data. In addition, we also present a new reconstruction error calculation method that measures the error in terms of both point-wise difference and curve similarity to improve the detection effect. Finally, based on three smart agriculture-related datasets, experimental results show that our proposed model can accurately achieve anomaly detection. The experimental precision, recall, and F1 score exceeded the counterpart models by reaching 0.9351, 0.9625, and 0.9482, respectively.

With the development of 5G technology, Mobile Edge Computing (MEC) has become a promising technology that is widely used in the Industrial Internet of Things (IIoT) and other fields. However, the increase in terminal devices and massive data growth has brought new challenges to MEC systems. How to meet the latency requirements of mobile devices while reducing system costs as much as possible is an urgent problem to be solved. To address this problem, we construct a smart factory model and formulate a mixed-integer nonlinear programming problem with the goal of minimizing the weighted sum of task delay and energy consumption. Considering that this problem is non-deterministic polynomial hard (NP-hard), we choose the Deep Q-network (DQN) approach to solve the objective function. In order to avoid the inaccurate Q-value estimation problem of the Double DQN algorithm and the overestimation problem of the Dueling DQN algorithm, we combine them to propose a Double-Dueling DQN (D3QN) algorithm. The simulation results show that the D3QN algorithm significantly outperforms the DQN, the Double DQN, and the Dueling DQN algorithm in reducing the total system cost.

Recently, a Fisher–Snedecor F composite fading model has gained great attention due to its mathematical tractability and modeling accuracy. However, its bivariate statistical characteristics have not been considered yet in the previous technical literature. In this paper, we present a bivariate Fisher–Snedecor F distribution with identical shaping parameters and study its applications in the wireless communication systems. We first derive novel theoretical formulations of the statistical characteristics for the bivariate Fisher–Snedecor F distribution model, which include the joint probability density function (PDF), the joint cumulative distribution function (CDF), the joint moment generating function (MGF) and the joint moments. Then, capitalizing on the above statistical expressions, some exact and asymptotic expressions of performance criteria, such as the outage probability, the average bit/symbol error probability (ABEP/ASEP), and the average channel capacity, for dual-branch selection combing and maximal ratio combing diversity systems are derived, respectively. Especially, the exact expressions of the ABEP/ASEP for several classical modulation schemes are obtained in terms of the multivariate Fox’s H-function by applying the Mellin-Barnes type contour integral. Furthermore, we investigate the second-order statistics of a sampled Fisher-Snedecor F composited fading envelope by utilizing the joint CDF, and obtain the mathematical expressions of the level crossing rate (LCR) and the average fade duration (AFD). Finally, we employ numerical and simulation results to demonstrate the validity of the theoretical analysis under various correlated fading and shadowing scenarios.

Nowadays, smart Internet of Things (IoT) technology as a new paradigm has been widely used in different fields of our lives. Massive amounts of high-dimensional time-series data are generated by sensors in the smart IoT, where data anomalies may often occur. Detecting anomalies in sensor data is crucial to ensure IoT systems’ stability, security, and reliability. However, the traditional anomaly detection methods often entail transmitting the data to the cloud or a centralized server for processing, which can result in increased latency, making it unsuitable for real-time application scenarios. Conversely, deploying anomaly detection directly on edge devices improves detection speed and efficiency. To this end, this paper proposes a lightweight time-series anomaly detection model combining Attention Anomaly Detection Generative Adversarial Networks (att-ADGANs) and Knowledge Distillation (KD). In the initial phase, we train a GAN network with encoder and decoder architectures to capture normal data distribution features. Subsequently, the GAN network is compressed and distilled into a lightweight model using KD. Furthermore, we present a Series-Knowledge Distillation GAN (S-KDGAN) framework that leverages progressive distillation to enhance distillation efficiency and minimize performance degradation. Experimental results show that the S-KDGAN compresses the computation at ratios of 2.37:1, 48.85:1, and 15.93:1 on the SWMRU, KDDCUP99, and HomeC datasets, and performance degradation rates of only 1.38%, 2.27%, and 1.61%. After comparing with other models, the effectiveness and superiority of the S-KDGAN distillation framework are proved.

In some emerging wireless applications, such as wearable communication and low-power sensor network applications, wireless devices or nodes not only require simple physical implementation approaches but also require certain reliable receiver techniques to overcome the effects of multipath or shadowed fading. Switched diversity combining (SDC) systems could be a simple and promising solution to the above requirements. Recently, a Fisher–Snedecor $\mathcal{F}$ composited fading model has gained much interest because of its modeling accuracy and calculation tractability. However, the performance of SDC systems over $\mathcal{F}$ fading channels has not yet been analyzed in the open literature. To this end, this paper presents a systematic analysis of SDC systems over $\mathcal{F}$ fading channels, including dual-branch switch-and-stay combining (SSC), multibranch switch-and examine combining (SEC), and SEC with post-examining selection (SECps) systems. We first investigate the statistical characteristics of univariate and bivariate $\mathcal{F}$ distributions. Then, these statistical expressions are introduced into the above SDC systems and the statistical metrics of the output signal-to-noise ratio (SNR) for these systems are deduced in different $\mathcal{F}$ fading scenarios. Thirdly, certain exact and novel expressions of performance criteria, such as the outage probability, the average bit error probability and average symbol error probability, as well as the average channel capacity for SSC, SEC, and SECps are derived. To find the optimum performance, optimal analysis is performed for the independent and identically distributed cases. Finally, numerical evaluation and simulations are carried out to demonstrate the validity of the theoretical analysis under various $\mathcal{F}$ fading scenarios. According to the obtained results, the multipath fading parameter has more influence on the performance of SDC systems than the shadowing parameter, the correlation coefficient, or the average SNR. Importantly, the SDC systems can provide switched diversity gains only when the switching threshold is not too large or too small compared to the average SNR.