Search

The fuzzy min-max (FMM) neural network can be regarded as a typical fuzzy hyperbox classifier that is designed in a sequential way, which leads to an input order drawback and overlap elimination limitation. In this paper, we propose a two-stage-based genetic algorithm (TGA) to construct blue a fuzzy hyperbox classifier (FHC) in a simultaneous way. The simultaneous method is realized by estimating all parameters of hyperboxes at one time rather than by separately determining the parameters of hyperboxes in a sequential way. In this paper, we propose a two-stage-based genetic algorithm to construct the fuzzy hyperbox classifier. The overall TGA consists of two stages, namely, the construction stage and optimization stage. The construction stage is aimed at designing the FHC structure, while the goal of the optimization stage is to further optimize the FHC structure. Using a two-stage genetic algorithm to directly construct a fuzzy hyperbox classifier can overcome the problem of input order and hyperbox overlap. The experimental results show that the proposed FHC yields higher classification accuracy in comparison with the stage-of-the-art FMMs reported in the literature. [ABSTRACT FROM AUTHOR]

Instance segmentation is a typical visual task that requires per-pixel mask prediction with a category label for each instance. For the decoder in instance segmentation network, parallel branches or towers are commonly adopted to deal with instance- and dense-level predictions. However, this parallelism ignores inter-branch and inner-branch relationships. Besides, how the different branches are connected is unclear, which is difficult to explore manually in practice. To address the above issues, we introduce Neural Architecture Search (NAS) to automatically search for hardware and memory-friendly feature sharing branch. Concretely, applying to instance segmentation, we design a search space considering both operations and sharing connections of parallel branches. Through a tailored reinforcement learning(RL) paradigm, we can efficiently search multiple architectures with different shared patterns and tap more feature selection possibilities. Our method is generically useful and can be transferred to analogous multi-task networks. The searched architecture shares features in the middle of the head branches and utilizes instance-level head features to generate pixel-level predictions. Extensive experiments demonstrate the effectiveness and surpass classical parallel decoder networks, exceeding BlendMask by 1.2% on bounding box mAP and 0.9% on segmentation mAP. [ABSTRACT FROM AUTHOR]

Lightness enhancement is a long-standing research topic in computer vision. Existing deep learning-based approaches usually extract features from the low-light image to model the enlightening process, which may fall short of robustness since low-light features can be unreliable in heavily dark regions. Inspired by the fact that infrared imaging is immune to illumination variation, we propose to exploit an extra infrared image to help brighten the low-light one. Specifically, we design a deep convolutional neural network to jointly extract the infrared and low-light features and produce a normal-light image under the supervision of multi-scale loss functions, including a discriminator loss that enforces the network output image to mimic a real one. Moreover, a contextual attention module is proposed to reconstruct reliable low-light features in heavily dark regions by exploring feature correlation consistency among low-light and infrared features. Extensive experiments on two composited and one real-world datasets demonstrate the superiority of the proposed approach over existing methods qualitatively and quantitatively. [ABSTRACT FROM AUTHOR]

The exponential device growth in industrial Internet of things (IIoT) has a noticeable impact on the volume of data generated. Edge-cloud computing cooperation has been introduced to the IIoT to lessen the computational load on cloud servers and shorten the processing time for data. General programmable logic controllers (PLCs), which have been playing important roles in industrial control systems, start to gain the ability to process a large amount of industrial data and share the workload of cloud servers. This transforms them into edge-PLCs. However, the continuous influx of multiple types of concurrent production data streams against the limited capacity of built-in memory in PLCs brings a huge challenge. Therefore, the ability to reasonably allocate memory resources in edge-PLCs to ensure data utilization and real-time processing has become one of the core means of improving the efficiency of industrial processes. In this paper, to tackle dynamic changes in arrival data rate over time at each edge-PLC, we propose to optimize memory allocation with Q-learning distributedly. The simulation experiments verify that the method can effectively reduce the data loss probability while improving the system performance. [ABSTRACT FROM AUTHOR]

It is demonstrated that the deployment cost profiling varies for the various AI architecture possibilities, and that this cost should be taken into account when deploying and choosing the AI/ML solution. I The article by Narengerile et al. i proposes a new beam training approach via deep reinforcement learning to take use of machine learning technologies that will be used to build sixth-generation (6G) communication networks. [Extracted from the article]

Internet of connected vehicles (IoV) are expected to enable intelligent traffic management, intelligent dynamic information services, intelligent vehicle control, etc. However, vehicles' data privacy is argued to be a major barrier toward the application and development of IoV, thus causing a wide range of attentions. Local differential privacy (LDP) is the relaxed version of the privacy standard, differential privacy, and it can protect users' data privacy against the untrusted third party in the worst adversarial setting. Therefore, LDP is potential to protect vehicles' data privacy in the practical scenario, IoV, although vehicles exhibit unique features, e.g., high mobility, short connection times, etc. To this end, in this paper, we first give an overview of the existing LDP techniques and present the thorough comparisons of these work in terms of advantages, disadvantages, and computation cost, in order to get the readers well acquainted with LDP. Thereafter, we investigate the potential applications of LDP in securing IoV in detail. Last, we direct several future research directions of LDP in IoV, to bridge the gaps between LDP researches and the privacy preservation in IoV. The originality of this survey is that it is the first work to summarize and compare the existing LDP research work and that it also does an pioneering work toward the in-depth analysis of the potential applications of LDP in privacy preservation in IoV. [ABSTRACT FROM AUTHOR]

The Internet of Vehicles (IoV) is employed to gather real-time traffic information for drivers, and base stations in 5G systems are used to assist in traffic data transmission. For rapid implementation, the applications in vehicles are available to be offloaded to edge nodes (ENs) which are enhanced from micro base stations. Despite the benefits of IoV and ENs, the explosive growth of offloaded vehicle applications exceeds the capacity of ENs, causing the overload of fractional ENs. Therefore, it is necessary to offload the computing applications in overloaded ENs to other idle ENs, while it is a challenge to select appropriate offloading destination ENs. In this paper, we first consider edge computing framework for computation offloading in IoV under the architecture of 5G networks. We then formulate a multi-objective optimization problem to select suitable destination ENs, which aims to minimize the vehicle application offloading delay and offloading cost as well as realizing the load balance of ENs. Moreover, a computation offloading method for IoV, named COV, is designed to solve the multi-objective optimization problem. Finally, various simulation analyses demonstrate the effectiveness and efficiency of COV. [ABSTRACT FROM AUTHOR]

Considering the different weights of various heterogeneity node importance in power grid and communication network and the possibility of the power grid island as well as the independent operation of the local area network, a more accurate method is proposed to evaluate the fragility of a cyber-physical system. According to the quo of grid construction and the background of cyber-physical fusion, the hierarchical system and distributed system model are established, respectively. Simulation results of conducting random attack and deliberate attack on two systems indicate that the proposed method is correct and better than others and it can identify the balance of the network structure. The distributed system is more robust than the hierarchical system under different weighting factors, while the robustness of the hierarchical system is more sensitive to the weighting factor. [ABSTRACT FROM AUTHOR]

Steganography is a technique that transmits secret data or message in an appropriate multimedia carrier, e.g., image, audio, and video files. It comes under the assumption that if the feature is visible, the point of attack is evident. However, such technology is always used by criminals who do not want to be easily discovered to hide harmful information in various media, especially in images. Massive spreading of those harmful information will increase the difficulty of social security management. In this case, excellent image steganalysis should be developed and applied. Specially, real-time image steganalysis is necessary when information timelines need to be protected. If detection scene has large amounts of users, deep learning can be applied to improve performance of image steganalysis benefiting from its powerful processing capability. Using deep learning, real-time image steganalysis system gets higher accuracy and efficiency. In this paper, we give an account of preliminary knowledge first. A brief overview of the deep neural networks (DNN) is also presented. The combination of DNN and real-time image steganalysis is introduced. Then, we import the concept of CNN in DNN, and expound theory as well as advantages of combining CNN and image steganalysis. For multi-user scenarios, we analyze a practical real-time image steganalysis application based on outlier detection methods. At last, we prospect the future issues of real-time image steganalysis. [ABSTRACT FROM AUTHOR]

The single-phase grounding fault of power systems is influenced by a variety of factors, resulting from the developing sizes and increasing complexity of power systems. In order to take advantage of big data in power systems, we propose a revised method with the use of synchronized phasor measurement. The data-driven method is designed to detect and localize the single-phase grounding fault, which reveals the correlation between eigenvalues and status of power systems. First, it calculates the contribution of the fault to each node; it then combines with a split window to monitor power systems in real time and to detect fault more efficiently. Based on the correlation between the elements of the matrix, it is robust against bad data and highly sensitive to weak signals. In general, the proposed method is applicable to various faults and well-functioning with real-time analysis. We test the proposed method with case studies from a distribution network with 80 nodes. [ABSTRACT FROM AUTHOR]

Cyber-physical systems (CPSs) are characterized by integrating computation, communication, and physical system. In typical CPS application scenarios, vehicle-to-vehicle (V2V) and Industry Internet of Things (IIoT), due to doubly selective fading and non-stationary channel characteristics, the robust and reliable end-to-end communication is extremely important. Channel estimation is a major signal processing technology to ensure robust and reliable communication. However, the existing channel estimation methods for V2V and IIoT cannot effectively reduce intercarrier interference (ICI) and lower the computation complexity, thus leading to poor robustness. Aiming at this challenge, according to the channel characteristics of V2V and IIoT, we design two channel estimation methods based on the Bayesian filter to promote the robustness and reliability of end-to-end communication. For the channels with doubly selective fading and non-stationary characteristics of V2V and IIoT scenarios, in the one hand, basis extended model (BEM) is used to further reduce the complexity of the channel estimation algorithm under the premise that ICI can be eliminated in the channel estimation. On the other hand, aiming at the non-stationary channel, a channel estimation and interpolation method based on extended Kalman filter (EKF) and unscented Kalman filter (UKF) Bayesian filters to jointly estimate the channel impulse response (CIR) and time-varying time domain autocorrelation coefficient is adopted. Through the MATLAB simulation, the robustness and reliability of end-to-end communication for V2V and IIoT are promoted by the proposed algorithms. [ABSTRACT FROM AUTHOR]