The kernel method is a tool that converts data to a kernel space where operation can be performed. When converted to a high-dimensional feature space by using kernel functions, the data samples are more likely to be linearly separable. Traditional machine learning methods can be extended to the kernel space, such as the radial basis function (RBF) network. As a kernel-based method, support vector machine (SVM) is one of the most popular nonparametric classification methods, and is optimal in terms of computational learning theory. Based on statistical learning theory and the maximum margin principle, SVM attempts to determine an optimal hyperplane by addressing a quadratic programming (QP) problem. Using Vapnik–Chervonenkis dimension theory, SVM maximizes generalization performance by finding the widest classification margin within the feature space. In this paper, kernel machines and SVMs are systematically introduced. We first describe how to turn classical methods into kernel machines, and then give a literature review of existing kernel machines. We then introduce the SVM model, its principles, and various SVM training methods for classification, clustering, and regression. Related topics, including optimizing model architecture, are also discussed. We conclude by outlining future directions for kernel machines and SVMs. This article functions both as a state-of-the-art survey and a tutorial.

The evolution of IoT devices has generated huge demand for wireless bandwidth in order to meet the operational needs of new generation IoT applications. This bandwidth problem is further exacerbated by another characteristics of IoT applications, i.e. IoT devices are usually deployed in massive number, thus leading to an awkward scenario that many bandwidth-hungry devices are chasing after the very limited wireless bandwidth within a small geographic area. As such, cognitive radio has received much attention of the research community as an important means for addressing the bandwidth needs of IoT applications. In this paper, we investigate the structure frameworks and potential applications of cognitive IoT. We further discuss the spectrum-based functionalities and heterogeneity for cognitive IoT. Security and privacy issues involved in cognitive IoT are also investigated. Finally, the research challenges and future direction for the cognitive-radio-based IoT networks are presented.

The universal filtered multi-carrier (UFMC) has been taken as a promising candidate for 5G waveform, where a finite impulse response (FIR) filter is employed to shape the waveform and enhance its resistance to inter-carrier interference (ICI). Previous studies have used the Dolph-Chebyshev filter due to its low side-lobe levels, but at the cost of low flexibility to filter performance control. Hence, this paper puts forward an effective scheme to design anti-interference filter for UFMC system, where the Nyquist condition (or sampling inter-symbol interference equivalently), the in-band distortion and the out-of-band emission are taken into consideration. First, this paper models the filter design as a constrained minimax optimization concerning above filter performance indexes. Then, the original nonconvex constraints on Nyquist condition are approximately transformed to a linear matrix inequation (LMI) and two linear inequations. Finally, the optimization problem is solved by the semi-definite programming (SDP). The numerical examples explicitly demonstrate the flexible performances tradeoff of the proposed method, in which the included filter performance indexes can be effectively controlled. Moreover, the bit-error-rate (BER) tests of the UFMC system confirms the effectiveness of our study, where the designed filters with smaller ISI show BER advantages over previous used filters.

Satellite communication is an important technology for the coverage of open country, and plays a vital role of link channel in remote Internet of Things (IoT). However, various kinds of IoT terminals may suffer from the limited battery capacity and computing capability. Therefore, this article proposes a new multiuser IoT system design, in which the satellite link is used to provide communication service for access points (AP), and allow terminals to download and upload data through APs. Then, the AP will exploit simultaneous wireless information and power transfer (SWIPT) and mobile edge computing (MEC) technologies to alleviate the deficiencies mentioned above. Moreover, the AP will equip with the full duplex (FD) and multi-input multi-output (MIMO) technologies to further improve the spectrum efficiency. Besides, a hybrid energy storage is assumed in the AP, i.e., the energy may come from power grid or renewable energy. Taking into account all issues above, we optimize the uplink achievable rate through jointly optimizing the CPU frequency, computation tasks, terminal transmitting power and the ratio of MEC task. In order to solve this optimization problem, we first decouple it into two sub-problems. For the first one, we can obtain the closed-form solution of CPU frequency. For the second one, we continue to decompose it into two non-convex problems, and then the iterative active-set method is used to solve these two problems. Numerical simulations demonstrate the effectiveness of the proposed design.

The problem of target localization in WSN (wireless sensor network) has received much attention in recent years. However, the performance of traditional localization algorithms will drastically degrade in the non-line of sight (NLOS) environment. Moreover, variable methods have been presented to address this issue, such as the optimization-based method and the NLOS modeling method. The former produces a higher complexity and the latter is sensitive to the propagating environment. Therefore, this paper puts forward a simple NLOS identification and localization algorithm based on the residual analysis, where at least two line-of-sight (LOS) propagating anchor nodes (AN) are required. First, all ANs are grouped into several subgroups, and each subgroup can get intermediate position estimates of target node through traditional localization algorithms. Then, the AN with an NLOS propagation, namely NLOS-AN, can be identified by the threshold based hypothesis test, where the test variable, i.e., the localization residual, is computed according to the intermediate position estimations. Finally, the position of target node can be estimated by only using ANs under line of sight (LOS) propagations. Simulation results show that the proposed algorithm can successfully identify the NLOS-AN, by which the following localization produces high accuracy so long as there are no less than two LOS-ANs.

With the increasing deployment of IoT devices and applications, a large number of devices that can sense and monitor the environment in IoT network are needed. This trend also brings great challenges, such as data explosion and energy insufficiency. This paper proposes a system that integrates mobile edge computing (MEC) technology and simultaneous wireless information and power transfer (SWIPT) technology to improve the service supply capability of WSN-assisted IoT applications. A novel optimization problem is formulated to minimize the total system energy consumption under the constraints of data transmission rate and transmitting power requirements by jointly considering power allocation, CPU frequency, offloading weight factor and energy harvest weight factor. Since the problem is non-convex, we propose a novel alternate group iteration optimization (AGIO) algorithm, which decomposes the original problem into three subproblems, and alternately optimizes each subproblem using the group interior point iterative algorithm. Numerical simulations validate that the energy consumption of our proposed design is much lower than the two benchmark algorithms. The relationship between system variables and energy consumption of the system is also discussed.