Fog computing is an encouraging technology in the coming generation to pipeline the breach between cloud data centers and Internet of Things (IoT) devices. Fog computing is not a counterfeit for cloud computing but a persuasive counterpart. It also accredits by utilizing the edge of the network while still rendering the possibility to interact with the cloud. Nevertheless, the features of fog computing are encountering novel security challenges. The security of end users and/or fog nodes brings a major dilemma in the implementation of real life scenario. Although there are several works investigated in the security challenges, physical layer security (PLS) in fog computing is not investigated in the above. The distinctive and evolving IoT applications necessitate new security regulations, models, and evaluations disseminated at the network edge. Notwithstanding, the achievement of the current cryptographic solutions in the customary way, many aspects, i.e., system imperfections, hacking skills, and augmented attack, has upheld the inexorableness of the detection techniques. Hence, we investigate PLS that exploits the properties of channel between end user and fog node to detect the impersonation attack in fog computing network. Moreover, it is also challenging to achieve the accurate channel constraints between end user and fog node. Therefore, we propose Q-learning algorithm to attain the optimum value of test threshold in the impersonation attack. The performance of the propose scheme validates and guarantees to detect the impersonation attack accurately in fog computing networks.

The convolution neural network (CNN) has achieved state-of-the-art performance in many computer vision applications e.g., classification, recognition, detection, etc. However, the global optimization of CNN training is still a problem. Fast classification and training play a key role in the development of the CNN. We hypothesize that the smoother and optimized the training of a CNN goes, the more efficient the end result becomes. Therefore, in this paper, we implement a modified resilient backpropagation (MRPROP) algorithm to improve the convergence and efficiency of CNN training. Particularly, a tolerant band is introduced to avoid network overtraining, which is incorporated with the global best concept for weight updating criteria to allow the training algorithm of the CNN to optimize its weights more swiftly and precisely. For comparison, we present and analyze four different training algorithms for CNN along with MRPROP, i.e., resilient backpropagation (RPROP), Levenberg–Marquardt (LM), conjugate gradient (CG), and gradient descent with momentum (GDM). Experimental results showcase the merit of the proposed approach on a public face and skin dataset.

Quantum inspired particle swarm optimization (QPSO) stimulated by perceptions from particle swarm optimization and quantum mechanics is a stochastic optimization method. Although, it has shown good performance in finding the optimal solution to many electromagnetic problems. However, sometimes it falls to local optima when dealing with hard optimization problems. Thus, to preserve a good balance between local and global searches to avoid premature convergence in quantum particle swarm optimization, this paper proposed three enhancements to the original QPSO method, the proposed method is called modified quantum particle swarm optimization (MQPSO) algorithm. Firstly, a novel selection technique is introduced that will choose the best particle among the population within the search domain to achieve a high-performance exploration. Secondly, a new mutation method is used to preserve the easiness of available QPSOs. Also, a dynamic parameter strategy is proposed for further facilitating the algorithm and tradeoff between exploration and exploitation searches. The experimental results obtained by solving standard benchmark functions and an electromagnetic design problem which is the superconducting magnetic energy storage (SMES) system available in both three parameters and eight parameters problems are reported to showcase the usefulness of the proposed approach.

Quantum particle swarm optimization (QPSO), inspired from the basic concept of PSO algorithm and quantum theory, is a stochastic searching algorithm. However, the algorithm may encounter a premature convergence when dealing with multimodal and complex inverse problems. Thus, some improvements are introduced. More especially, one will randomly select the best particle to take part in the current search domain. Also, a mutation strategy is added to the mean best position, and an enhancement factor (EF) is incorporated to enhance the global search capability to find the global optimum solution and to avoid premature convergence. Moreover, some parameter updating strategy is proposed to tradeoff the exploration and exploitation searches. Experiments have been conducted on well-known multimodal functions and an inverse problem. The numerical results showcase the merit and efficiency of the proposed modified quantum inspired particle swarm optimizer (MQPSO).

The selection of semantic concepts for modal construction and data collection remains an open research issue. It is highly demanding to choose good multimedia concepts with small semantic gaps to facilitate the work of cross-media system developers. However, very little work has been done in this area. This paper contributes a new, real-world web image dataset for cross-media retrieval called FB5K. The proposed FB5K dataset contains the following attributes: 1) 5130 images crawled from Facebook; 2) images that are categorized according to users’ feelings; 3) images independent of text and language rather than using feelings for search. Furthermore, we propose a novel approach through the use of Optical Character Recognition (OCR) and explicit incorporation of high-level semantic information. We comprehensively compute the performance of four different subspace-learning methods and three modified versions of the Correspondence Auto Encoder (Corr-AE), alongside numerous text features and similarity measurements comparing Wikipedia, Flickr30k and FB5K. To check the characteristics of FB5K, we propose a semanticbased cross-media retrieval method. To accomplish cross-media retrieval, we introduced a new similarity measurement in the embedded space, which significantly improved system performance compared with the conventional Euclidean distance. Our experimental results demonstrated the efficiency of the proposed retrieval method on three different datasets to simplify and improve general image retrieval.