Cracks are an important indicator reflecting the safety status of infrastructures. This paper presents an automatic crack detection and classification methodology for subway tunnel safety monitoring. With the application of high-speed complementary metal-oxide-semiconductor (CMOS) industrial cameras, the tunnel surface can be captured and stored in digital images. In a next step, the local dark regions with potential crack defects are segmented from the original gray-scale images by utilizing morphological image processing techniques and thresholding operations. In the feature extraction process, we present a distance histogram based shape descriptor that effectively describes the spatial shape difference between cracks and other irrelevant objects. Along with other features, the classification results successfully remove over 90% misidentified objects. Also, compared with the original gray-scale images, over 90% of the crack length is preserved in the last output binary images. The proposed approach was tested on the safety monitoring for Beijing Subway Line 1. The experimental results revealed the rules of parameter settings and also proved that the proposed approach is effective and efficient for automatic crack detection and classification.

With the fast development of industrial IoT, a large amount of data is being generated continuously by different sources. Storing all the raw data in the IIoT devices locally is unwise considering that the end devices energy and storage space are strictly limited. Moreover, the devices are unreliable and vulnerable to many threats because the networks may be deployed in remote and unattended areas. In this paper, we design a flexible and economical framework for data processing, storage and retrieval in IIoT by integrating fog computing and cloud computing. Specifically, all the raw data are first preprocessed by the edge server and then the time-sensitive data are used and stored locally. The non-time-sensitive data are transmitted to the cloud server to support data retrieval and mining in the future. Simulation results illustrate that the proposed framework can greatly improve the efficiency and security of data storage and retrieval in IIoT.

Edge computing has emerged as a promising technique because of its advantages in providing low-latency computation offloading services for resource-limited mobile user devices and IoT applications. Computationally intensive artificial intelligence (AI) tasks are well suited to be offloaded to the Cloudlet server, but there is a lack of energy-delay optimization models specifically designed for this edge AI scenario. {\color{red}In this paper, we propose a multiple algorithm service model (MASM) that provides heterogeneous algorithms with different computation complexities and required data sizes to fulfill the same task}, and develop an optimization model that aims at reducing the energy and delay cost by optimizing the workload assignment weights (WAWs) and computing capacities of virtual machines (VMs), at the same time guaranteeing the quality of the results (QoRs). We propose a tide ebb algorithm to solve the MASM optimization model, and we prove its Parato optimality. Numerical results obtained demonstrate the effectiveness of our proposed method, and prove that the energy and delay costs can be significantly reduced by sacrificing the QoR of the offloaded AI tasks.

There is continuously increasing interest in research on multi-sensor data fusion technology. Because Dempster’s rule of combination can be problematic when dealing with conflicting data, there are numerous issues that make data fusion a challenging task, including the exponential explosion, Zadeh Paradox, and one-vote veto. These issues lead to a great difference between the fusion results and real results. This paper applies the idea of analyzing distance-based evidence conflicts, introduces the concept of vector space, and proposes a new cosine theorem-based method of identifying and expressing conflicting data. In addition, this paper proposes a new data fusion algorithm based on the degree of mutual support between beliefs, which is based on the Jousselme distance-based combination rule proposed by Deng et al. Simulation results demonstrate that the presented algorithm achieves great improvements in both the accuracy of identifying conflicting data and that of fusing conflicting data.

Short-term traffic prediction consists a crucial component in intelligent transportation systems. With the explosion of automated traffic monitoring sensors and the flourishing of deep learning techniques, a growing body of deep neural network models have been employed to tackle this problem. In particular, convolutional neural networks (CNN) and long short-term memory (LSTM) recurrent networks have demonstrated their advantages in modeling and predicting the spatiotemporal evolution of traffic flows. In this paper, we propose a novel Convolutional LSTM neural network architecture for multi-lane short-term traffic prediction. Compared to existing methods, we highlight the importance of (1) applying multiple features to characterize traffic conditions; (2) explicitly considering the routing between neighbouring lanes and downstream/upstream traffics; and (3) predicting multiple time-step traffic in a rolling-prediction manner. Experiments on 10 months 5-minute interval observations of the US I-101 Northern freeway at California Bay Area verify the proposed model. The results show that our model has considerable advantages in predicting multi-lane short-term traffic flow.

Energy efficiency is one of the most important concerns in cloud/edge computing systems. A major benefit of the Dynamic Voltage and Frequency Scaling (DVFS) technique is that a Virtual Machine (VM) can dynamically scale its computation frequency on an on-demand basis, which is helpful in reducing the energy cost of computation when dealing with stochastic workloads. In this paper, we study the joint workload allocation and computation resource configuration problem in distributed cloud/edge computing. We propose a new energy consumption model that considers the stochastic workloads for computation capacity reconfiguration-enabled VMs. We define Service Risk Probability (SRP) as the probability a VM fails to process the incoming workloads in the current time slot, and we study the energy-SRP tradeoff problem in single VM. Without specifying any distribution of the workloads, we prove that, theoretically there exists an optimal SRP that achieves minimal energy cost, and we derive the closed form of the condition to achieve this minimal energy point. We also derive the closed form for computing the optimal SRP when the workloads follow a Gaussian distribution. We then study the joint workload allocation and computation frequency configuration problem for multiple distributed VMs scenario, and we propose solutions to solve the problem for both Gaussian and unspecified distributions. Our performance evaluation results on both synthetic and real-world workload trace data demonstrate the effectiveness of the proposed model. The closeness between the simulation results and the analytical results prove that our proposed method can achieve lower energy consumption compared with fixed computation capacity configuration methods.