Concrete segments are commonly utilized as linings in shield tunnels to support the load from the surrounding ground, with their mechanical performance playing a crucial role in ensuring tunnel safety. During the construction of shield tunnels, these segments are assembled on-site, and grouting is performed concurrently to promptly fill the gap between the segment and the surrounding ground. However, inadequate grouting can lead to the formation of voids, which are hidden construction defects that compromise the mechanical stability of the tunnel segments. This study explores the impact of grouting voids on the mechanical performance of concrete segmental tunnels during construction using a 3D numerical simulation. A 3D finite-element model of a segmented shield tunnel with grouting voids was developed based on the load-structure method. The analysis focused on the effects of void characteristics, such as their angle, position, and length, on the tunnel's mechanical behavior. The results indicate that voids located at the tunnel crown reduce the vertical convergence of the tunnel cross-section, while voids at the waist exacerbate its horizontal convergence. Additionally, the presence of voids alters the bending moment distribution in the segments. Compared to the case without a void, there is a reversal of the bending moment when the void is located at the crown, and the bending moment increases from −13 kN·m to 24 kN·m, potentially causing tensile damage. Furthermore, voids also induce stress concentration within the segments, and the maximum stress concentration factor (SCF) occurs at the center of the voids as 2.44. However, when a circumferential joint intersects the void, joint opening causes stress redistribution, with the most significant stress concentration appearing at 45° on both sides of the void. These findings contribute to better damage recognition and enhance the safety assurance of concrete shield tunnels.

Data sanitization in the context of Internet of Things (IoT) privacy refers to the process of permanently and irreversibly hiding all sensitive information from vast amounts of streaming data. Taking into account the dynamic and real-time characteristics of streaming IoT data, we propose a parallel evolutionary Privacy-Preserving Data Mining (PPDM), called High-performance Evolutionary Data Sanitization for IoT (HEDS4IoT), and implement two mechanisms on a Graphics Processing Units (GPU)-aided parallelized platform to achieve real-time streaming protected data transmission. The first mechanism, the Parallel Indexing Engine (PIE), generates retrieval index lists from the dataset using GPU blocks. These lists are used in place of the dataset during the PPDM process. The second mechanism, called Parallel Fitness Function Engine (PF2E), parallelizes the index lists on the GPU threads to speed up the computation of the quality of solutions generated by the evolutionary algorithm, in which deferential evolution is adopted as the evolutionary algorithm. In addition to the ability for Big data, the HEDS4IoT can be adaptively adjusted for dynamic nature of IoT where new streaming data is considered for data sanitization. Our experimental results with extensive benchmarks show that, at the kernel level, the PIE and PF2E mechanisms are averagely 33.5x and 53.7x faster than their CPU-implemented version, respectively. At the application level, our findings demonstrate that the HEDS4IoT can perform the PPDM process 47.7x faster than some of the state-of-art methods.

A problem with machine learning (ML) techniques for detecting intrusions in the Internet of Things (IoT) is that they are ineffective in the detection of low-frequency intrusions. In addition, as ML models are trained using specific attack categories, they cannot recognize unknown attacks. This article integrates strategies of cost-sensitive learning and multitask learning into a hybrid ML model to address these two challenges. The hybrid model consists of an autoencoder for feature extraction and a support vector machine (SVM) for detecting intrusions. In the cost-sensitive learning phase for the class imbalance problem, the hinge loss layer is enhanced to make a classifier strong against low-distributed intrusions. Moreover, to detect unknown attacks, we formulate the SVM as a multitask problem. Experiments on the UNSW-NB15 and BoT-IoT datasets demonstrate the superiority of our model in terms of recall, precision, and F1-score averagely 92.2%, 96.2%, and 94.3%, respectively, over other approaches.