Abstract To improve the performance of the image preprocessing module in consumer electronics using an active‐matrix organic light‐emitting diode display panel, the concept of judging before processing for salt‐and‐pepper denoising is originally proposed. Firstly, a dataset for salt‐and‐pepper noise image classification is constructed, and a convolutional neural network (CNN) for judging noise image (CNN‐J) is trained. Image classified as normal by CNN‐J is not processed, while the classified noisy image is denoised. In the denoising process, a marking image and a rough denoised image are generated by CNN for noise mask (CNN‐M) and CNN for denoising (CNN‐D), respectively. Subsequently, the refined denoised image is output using the proposed refining mechanism. The middle layers of CNN‐M and CNN‐D are constructed by depth‐separable CNN to reduce the network complexity. Experimental results show that the misjudging rate of CNN‐M marking is reduced by 19.94% compared with the best existing marking method. Compared with the traditional methods, the peak signal to noise ratio of the proposed method is increased by 2.95% and the information loss is reduced by 21.46%. In addition, the computational complexity is at least 11.18% lower than that of the traditional CNN. Finally, the display of salt‐and‐pepper denoised images on the flexible AMOLED is realized.

Network slicing is an essential technology in 5G and the forthcoming 6G networks. It aims to embed multiple virtual networks, i.e., network slices, on top of a shared substrate network to meet diverse service requirements. While a considerable body of existing research strives to maximize overall profits by meeting the resource demands of the network slices, optimizing their reliability is frequently overlooked. In this paper, we formalize the network slicing problem as a multi-objective optimization problem that aims to maximize total profits and reliability of network slices. To tackle this problem, we propose a new multi-objective optimization approach that improves over the state-of-the-art algorithm, which can achieve good approximate Pareto front results balancing total profits and reliability of network slices. The performance of our proposed method is evaluated on both artificial and real-world network topologies. Experimental results demonstrate the superior performance of our proposed method compared to the baseline algorithm, outperforming the latter in 92% of instances in terms of the Hypervolume (HV) metric.

The progressively dominant role of software in safety-critical systems raise concerns about the software dependability. There are limited mature practices and guides for assessing software dependability and analyzing system-level hazards triggered by software anomalies. A problem is that faults, errors, and failures that represent software anomalies, albeit with different natures, are usually used indistinctly to predict software dependability, leading to unsolid results. The lack of such consensual conceptualization also leads to poor interoperability between supporting tools, and, consequently, difficulties in anomaly management and software maintenance. Anomaly analysis and management is more tough for safety-critical software due to its higher complexity and the safety-critical nature. The complex context of safety-critical software causes difficulties in determining the evolution/propagation path of software anomalies and the impact on system safety. To capture the nature of safety-critical software and support an understanding of mechanisms of software anomalies and associated hazards, we propose three reference ontologies: Safety-critical Software Ontology, Software Fault Ontology and Software-failure-induced Hazard Ontology, which are built based on international standards, guides, and relevant conceptual models. We also discuss the relationships among them. That will facilitate a better understanding of the software anomaly mechanisms and the design of intervening/mitigation solutions. We demonstrate how these ontologies can help analyze software problems of real-world safety-critical systems.

As a powerful architecture for large-scale computation, cloud computing has revolutionized the way that computing infrastructure is abstracted and utilized. Coupled with the challenges caused by Big Data, the rocketing development of cloud computing boosts the complexity of system management and maintenance, resulting in weakened trustworthiness of cloud services. To cope with this problem, a compelling method, i.e., Support Vector Data Description (SVDD), is investigated in this paper for detecting anomalous performance metrics of cloud services. Although competent in general anomaly detection, SVDD suffers from unsatisfactory false alarm rate and computational complexity in time series anomaly detection, which considerably hinders its practical applications. Therefore, this paper proposes a relaxed form of linear programming SVDD (RLPSVDD) and presents important insights into parameter selection for practical time series anomaly detection in order to monitor the operations of cloud services. Experiments on the Iris dataset and the Yahoo benchmark datasets validate the effectiveness of our approaches. Furthermore, the comparison of RLPSVDD and the methods obtained from Twitter, Numenta, Etsy and Yahoo, shows the overall preference for RLPSVDD in time series anomaly detection.

Neural network robustness has been a hot research topic since the discovery of adversarial examples. With the increasing threats posed by adversarial examples in safety-critical AI applications, the research problem of how to boost the robustness of neural networks has drawn even more attention in recent years. In this paper, we argue that existing methods for neural network robustness optimization primarily focus on increasing the minimum adversarial perturbation of individual datum while neglecting the purpose of the target machine learning task, i.e., classification. Consequently, we propose a neural network retraining method which implicitly enhances a model's capability in maximizing the minimum distance from data instances of all classes to the decision boundary. As demonstrated by the experiments, our method succeeds in improving the robustness of pre-trained neural networks within only a few retraining epochs while imposing little negative effect on classification accuracy, thus being applicable for online optimization of neural networks.

Knowledge of node locations is essential to Wireless Sensor Networks (WSNs) in a wide range of potential applications and their function-dependent network protocols. A number of localization approaches have already been proposed to fulfill this requirement, but few of them can be applicable to mobile sensor networks, due to their low-dimensional embeddings, Euclidean distance representation limitations, frequent node mobility and additional measurement overhead in the network. In this paper, a resilient range-based d-dimensional localization (RRDL) approach is proposed for mobile WSNs to resolve the issues. RRDL distinguishes itself from previous work with three remarkable characteristics: (1) it works for mobile networks embedded in d-dimensional Non-Euclidean space; (2) it allows static ordinary nodes with pre-known locations to act as the alternative anchor nodes, thus tolerating the motion of the original anchor nodes to ensure that other ordinary nodes can obtain their locations in an efficient manner; and (3) it introduces an efficient path-learning approach, with the knowledge of the existing paths, to represent the real network distances as far as possible, thereby eliminating additional measurement overhead and tolerating node mobility in localization. With these characteristics, RRDL exploits the iterative factorization of the random distance matrix, formed by the distances to and from a set of k-hop static neighbors, to assign each current node d-dimensional Non-Euclidean coordinate in a distributed manner. Simulation results demonstrate that RRDL achieves higher localization accuracy with a moderate communication cost in mobile sensor networks.

This abstract proposes a time series anomaly detector which 1) makes no assumption about the underlying mechanism of anomaly patterns, 2) refrains from the cumbersome work of threshold setting for good anomaly detection performance under specific scenarios, and 3) keeps evolving with the growth of anomaly detection experience. Essentially, the anomaly detector is powered by the Recurrent Neural Network (RNN) and adopts the Reinforcement Learning (RL) method to achieve the self-learning process. Our initial experiments demonstrate promising results of using the detector in network time series anomaly detection problems.

Convex hull analysis is a key research tool under the broad umbrella of machine learning and finds applications in various domains. However, due to the fact that traditional convex hull analysis usually targets low-dimensional space and just roughly estimates the shape of a dataset, its capability in describing general datasets is greatly limited. In this paper, we investigate the problem of convex hull approximation in high-dimensional space and propose to approximate the convex hull through Semi-Nonnegative Matrix Factorization (Semi-NMF). The novel problem formulation enables the utilization of the kernel trick and makes convex hull analysis readily applicable to general data description tasks, such as one-class classification and clustering. The empirical experiments show that our method successfully describes the convex hull with the approximated extreme points and achieves competitive results in both one-class classification and clustering tasks.