Search

In order to improve the accuracy and robustness of existing automated crack detection methods, a fully convolutional neural network for pixel-level detection based on densely connected and deeply supervised network is proposed. First, the densely connected layers are applied for enhancing the propagation and reuse of crack features. Then, the deeply supervised modules are designed to make network extract more significant features through multi-scale levels. Finally, the feature maps from different scales are fused to achieve complementarity at different levels. In addition, a class-balanced cross-entropy loss function is designed to balance backgrounds and cracks by increasing the weight of crack pixel loss. The proposed method is tested on three public datasets, and the experiments show that our method is superior to state-of-the-art methods in accuracy, speed and robustness.

Covariance analysis describing function technique is a conventional method to solve the performance analysis of the nonlinear missile guidance system. Aiming at the faultiness of covariance analysis describing function technique and its improved method, this paper proposes a new method to solve the mean and covariance transfer issue by using the high-degree spherical-radial cubature rule. In terms of simulation models, the nonlinear missile guidance system contains the saturation link to limit the lateral acceleration command and the initial heading error is introduced. In addition, the zero-mean target evasive maneuver with exponentially-decaying autocorrelation function is chosen as the input of the missile guidance system. Furthermore, compared with the existing methods, the proposed method has higher computational efficiency, accuracy and better applicability in high-dimensional nonlinear systems by theoretical derivation and simulation results from the mean and covariance values of relative lateral separation. Finally, the presented analysis method can be used as a general method for the design and statistical analysis of multidimensional nonlinear systems.

The integrity and accuracy of positioning are crucial factors in vehicle safety. This article proposes an enhanced real-time array calibration (ERAC) technique based on real-time array error calibration with the Beidou Navigation Satellite System (BDS). Through fixed-point positioning tests and road tests, it is found that the ERAC method is superior to the traditional methods in terms of accuracy, stability, confidence, and the time required to reconstruct reliable points. The performance of the tested receiver is better than that of a commercial receiver with standard single-point positioning (SSP) in the context of multipath interference. Furthermore, the ERAC method meets the requirements for autonomous vehicle (AV) monitoring and public safety, especially in terms of the lane-level accuracy indicator, and its integrity indicators are greater than 95% to 97%. Additionally, the ERAC method has the potential to become an alternative solution for automatic vehicle safety monitoring in certain scenarios. This technique also has the ability to meet the wide positioning requirements of various vehicles and scenarios by adjusting its technical details.

Recently, microservice has been a popular architecture to construct cloud-native systems. This novel architecture brings agility and accelerates the software development process significantly. However, it is not easy to manage and operate microservice systems due to their scale and complexity. Many approaches are proposed to automatically operate microservice systems such as anomaly detection. Nevertheless, those methods cannot be sufficiently validated and compared due to a lack of real microservice systems, which leads to the slow process of intelligent operation. These challenges inspire us to build a system named “VWR”, a framework of Virtual War Room for operating microservice applications which allows users to simulate their microservice architectures with low overhead and inject multiple types of faults into the microservice system with chaos engineering. VWR can mimic user requests and record the end-to-end tracing data (i.e., service call chains) for each request in a way consistent with OpenTracing. With easily designed tests and the produced streaming tracing data, the users can validate the performance of their intelligent operation algorithms and improve the algorithms as needed. Besides, based on the streaming tracing data generated by VWR, we introduce a novel unsupervised anomaly detection algorithm based on Matrix Sketch and set it as a default intelligent operation algorithm in VWR. This algorithm can detect anomalies by analyzing high-dimensional performance data collected from a microservice system in a streaming manner. The experimental result in VWR shows that the matrix sketch based method can precisely detect anomalies in microservice systems and outperform some widely used anomaly detection methods such as isolation forest in some scenario. We believe more approaches on the intelligent operation of microservice systems can be constructed based on VWR.

This paper proposes a state prediction adaptive sliding mode (SPASM) control method for the remotely piloted system (RPS). With consideration of the time delay caused by the large transmission delay existing in the RPS, a prediction algorithm is proposed to provide the state prediction by using the state transition matrix. To approximate the uncertain lag of the remotely piloted vehicle (RPV) control augmentation system, an adaptive law is proposed to estimate the parameter uncertainties, and the overestimating problem is resolved efficiently. Meanwhile, to deal with the unmodeled dynamics and the predicted errors, a sliding mode controller is designed to guarantee the robustness of the whole closed-loop system. The simulation results show that the SPASM controller can not only guarantee the stability of the RPS in the presence of large time delay but also has a desirable performance of tracking the pilot’s inputs while existing the unmodeled dynamics and parameter uncertainties.

Electronic health records (EHRs) replaced the old paper-based systems to make patient data more accurate, reliable, and more accessible. Yet, the EHRs system requires high transmission cost, energy, and waste of time for both doctors and patients. Furthermore, EHRs security presents a serious issue threatening the patient's privacy. Most of the third-party hosting systems have some issues related to the users' privacy and data security. Hence, it is necessary to restrict the access control policies and develop efficient mechanisms for cloud-based EHRs data. In this paper, a sensitive and energetic access control (SE-AC) mechanism is proposed for managing the cloud-hosted EHRs and providing a fine-grained access control even in critical situations. The proposed mechanism ensures the confidentiality of the patient's data, where only authorized individuals to have permission to be able to edit or review certain of the patient's data. Each EHR data is encrypted by the managing authority before submitting to the cloud storage. The requesting user can get dynamically changing permissions based on authentication and context attributes. In addition, seven major aspects have been quantified to assess the operation of any access control that could be deployed in the Internet-of-Thing (IoT). The security analysis indicates that the SE-AC mechanism is secure and will prevent any unauthorized access. The results show exceptional compatibility and performance with different setups and configuration.