Volumen 32 (2022): Heft 4 (December 2022)
Big Data and Artificial Intelligence for Cooperative Vehicle-Infrastructure Systems (Special section, pp. 523-599), Baozhen Yao, Shuaian (Hans) Wang and Sobhan (Sean) Asian (Eds.)

To solve the mismatch between the supply and demand of shared electric vehicles (SEVs) caused by the uneven distribution of SEVs in space and time, an SEV relocating optimization model is designed based on a reward mechanism. The aim of the model is to achieve a cost-minimized rebalancing of the SEV system. Users are guided to attend the relocating SEVs by a reward mechanism, and employees can continuously relocate multiple SEVs before returning to the supply site. The optimization problem is solved by a heuristic column generation algorithm, in which the driving routes of employees are added into a pool by column generation iteratively. In the pricing subproblem of column generation, the Shuffled Complex Evolution–University of Arizona (SCE–UA) is designed to generate a driving route. The proposed model is verified with the actual data of the Dalian city. The results show that our model can reduce the total cost of relocating and improve the service efficiency.

The aim of this paper is to develop a container ship traffic model for port simulation studies. Such a model is essential for terminal design analyses and testing the performance of optimization algorithms. This kind of studies requires accurate information about the ship stream to build test scenarios and benchmark instances. A statistical model of ship traffic is developed on the basis of container ship arrivals in eight world ports. The model provides three parameters of the arriving ships: ship size, arrival time and service time. The stream of ships is divided into classes according to vessel sizes. For each class, service time distributions and mixes of return time distributions are provided. A model of aperiodic arrivals is also proposed. Moreover, the results achieved are used to compare port specific features.

Public transportation is often disrupted by disturbances, such as the uncertain travel time caused by road congestion. Therefore, the operators need to take real-time measures to guarantee the service reliability of transit networks. In this paper, we investigate a dynamic scheduling problem in a transit network, which takes account of the impact of disturbances on bus services. The objective is to minimize the total travel time of passengers in the transit network. A two-layer control method is developed to solve the proposed problem based on a hybrid control strategy. Specifically, relying on conventional strategies (e.g., holding, stop-skipping), the hybrid control strategy makes full use of the idle standby buses at the depot. Standby buses can be dispatched to bus fleets to provide temporary or regular services. Besides, deep reinforcement learning (DRL) is adopted to solve the problem of continuous decision-making. A long short-term memory (LSTM) method is added to the DRL framework to predict the passenger demand in the future, which enables the current decision to adapt to disturbances. The numerical results indicate that the hybrid control strategy can reduce the average headway of the bus fleet and improve the reliability of bus service.

This paper considers direct mobile-to-mobile (M2M) communications with a dual antenna selection (AS) system at a destination mobile node (DMN) in interference limited, dissimilar composite fading environments. In particular, we model dissimilar interference limited signals at the inputs of the dual branch AS system as (i) the ratio of two Nakagami-m (N) random variables (RVs) at the first branch and (ii) the ratio of two Rice RVs at the second branch, in order to account for non line-of-sight (NLOS) and line-of-sight (LOS) communications, respectively. Moreover, we assume variable powers of the desired as well as interference signals at the output of the DMN in order to account for the impact of shadowing. For the proposed model, we derive probability density functions, cumulative distribution functions, outage probabilities and average level crossing rates. The derived statistical results are evaluated for all the statistical measures considered and are graphically presented in order to provide insight into the impact of composite fading severities and LOS factors for the desired signal, as well as for the interference, on the system performances.

We present a novel approach to vision-based localization of electric city buses for assisted docking to a charging station. The method assumes that the charging station is a known object, and employs a monocular camera system for positioning upon carefully selected point features detected on the charging station. While the pose is estimated using a geometric method and taking advantage of the known structure of the feature points, the detection of keypoints themselves and the initial recognition of the charging station are accomplished using neural network models. We propose two novel neural network architectures for the estimation of keypoints. Extensive experiments presented in the paper made it possible to select the MRHKN architecture as the one that outperforms state-of-the-art keypoint detectors in the task considered, and offers the best performance with respect to the estimated translation and rotation of the bus with a low-cost hardware setup and minimal passive markers on the charging station.

An integrated approach to the fault-tolerant control (FTC) of a quadcopter unmanned aerial vehicle (UAV) with incipient actuator faults is presented. The framework is comprised of a radial basis function neural network (RBFNN) fault detection and diagnosis (FDD) module and a reconfigurable flight controller (RFC) based on the extremum seeking control approach. The dynamics of a quadcopter subject to incipient actuator faults are estimated using a nonlinear identification method comprising a continuous forward algorithm (CFA) and a modified golden section search (GSS) one. A time-difference-of-arrival (TDOA) method and the post-fault system estimates are used within the FDD module to compute the fault location and fault magnitude. The impact of bi-directional uncertainty and FDD detection time on the overall FTC performance and system recovery is assessed by simulating a quadcopter UAV during a trajectory tracking mission and is found to be robust against incipient actuator faults during straight and level flight and tight turns.

The paper deals with the problem of health-aware fault-tolerant control of a vehicle fleet. In particular, the development process starts with providing the description of the process along with a suitable Internet-of-Things platform, which enables appropriate communication within the vehicle fleet. It also indicates the transportation tasks to the designated drivers and makes it possible to measure their realization times. The second stage pertains to the description of the analytical model of the transportation system, which is obtained with the max-plus algebra. Since the vehicle fleet is composed of heavy duty machines, it is crucial to monitor and analyze the degradation of their selected mechanical components. In particular, the components considered are ball bearings, which are employed in almost every mechanical transportation system. Thus, a fuzzy logic Takagi–Sugeno approach capable of assessing their time-to-failure is proposed. This information is utilized in the last stage, which boils down to health-aware and fault-tolerant control of the vehicle fleet. In particular, it aims at balancing the exploitation of the vehicles in such a way as to maximize they average time-to-failure. Moreover, the fault-tolerance is attained by balancing the use of particular vehicles in such a way as to minimize the effect of possible transportation delays within the system. Finally, the effectiveness of the proposed approach is validated using selected simulation scenarios involving vehicle-based transportation tasks.

The diagnosis of systems is one of the major steps in their control and its purpose is to determine the possible presence of dysfunctions, which affect the sensors and actuators associated with a system but also the internal components of the system itself. On the one hand, the diagnosis must therefore focus on the detection of a dysfunction and, on the other hand, on the physical localization of the dysfunction by specifying the component in a faulty situation, and then on its temporal localization. In this contribution, the emphasis is on the use of software redundancy applied to the detection of anomalies within the measurements collected in the system. The systems considered here are characterized by non-linear behaviours whose model is not known apriori. The proposed strategy therefore focuses on processing the data acquired on the system for which it is assumed that a healthy operating regime is known. Diagnostic procedures usually use this data corresponding to good operating regimes by comparing them with new situations that may contain faults. Our approach is fundamentally different in that the good functioning data allow us, by means of a non-linear prediction technique, to generate a lot of data that reflect all the faults under different excitation situations of the system. The database thus created characterizes the dysfunctions and then serves as a reference to be compared with real situations. This comparison, which then makes it possible to recognize the faulty situation, is based on a technique for evaluating the main angle between subspaces of system dysfunction situations. An important point of the discussion concerns the robustness and sensitivity of fault indicators. In particular, it is shown how, by non-linear combinations, it is possible to increase the size of these indicators in such a way as to facilitate the location of faults.

This research is focused on decision-making problems with redundant and incomplete information under a fuzzy environment. Firstly, we present the definition of incomplete fuzzy soft sets and analyze their data structures. Based on that, binary relationships between each pair of objects and the “restricted/relaxed AND” operations in the incomplete fuzzy soft set are discussed. After that, the definition of incomplete fuzzy soft decision systems is proposed. To reduce the inconsistency caused by the redundant information in decision making, the significance of the attribute subset, the reduct attribute set, the optimal reduct attribute set and the core attribute in incomplete fuzzy soft decision systems is also discussed. These definitions can be applied in an incomplete fuzzy soft set directly, so there is no need to convert incomplete data into complete one in the process of reduction. Then a new decision-making algorithm based on the above definitions can be developed, which can deal with redundant information and incomplete information simultaneously, and is independent of some unreliable assumptions about the data generating mechanism to forecast the incomplete information. Lastly, the algorithm is applied in the problem of regional food safety evaluation in Chongqing, China, and the corresponding comparison analysis demonstrates the effectiveness of the proposed method.

In some applications, there are signals with a piecewise structure to be recovered. In this paper, we propose a piecewise sparse approximation model and a piecewise proximal gradient method (JPGA) which aim to approximate piecewise signals. We also make an analysis of the JPGA based on differential equations, which provides another perspective on the convergence rate of the JPGA. In addition, we show that the problem of sparse representation of the fitting surface to the given scattered data can be considered as a piecewise sparse approximation. Numerical experimental results show that the JPGA can not only effectively fit the surface, but also protect the piecewise sparsity of the representation coefficient.

Segmentation of the border of the human pigmented lesions has a direct impact on the diagnosis of malignant melanoma. In this work, we examine performance of (i) morphological segmentation of a pigmented lesion by region growing with the adaptive threshold and density-based DBSCAN clustering algorithm, and (ii) morphological segmentation of the pigmented lesion border by region growing of the lesion and the background skin. Research tasks (i) and (ii) are evaluated by a human expert and tested on two data sets, A and B, of different origins, resolution, and image quality. The preprocessing step consists of removing the black frame around the lesion and reducing noise and artifacts. The halo is removed by cutting out the dark circular region and filling it with an average skin color. Noise is reduced by a family of Gaussian filters 3×3−7×7 to improve the contrast and smooth out possible distortions. Some other filters are also tested. Artifacts like dark thick hair or ruler/ink markers are removed from the images by using the DullRazor closing images for all RGB colors for a hair brightness threshold below a value of 25 or, alternatively, by the BTH transform. For the segmentation, JFIF luminance representation is used. In the analysis (i), out of each dermoscopy image, a lesion segmentation mask is produced. For the region growing we get a sensitivity of 0.92/0.85, a precision of 0.98/0.91, and a border error of 0.08/0.15 for data sets A/B, respectively. For the density-based DBSCAN algorithm, we get a sensitivity of 0.91/0.89, a precision of 0.95/0.93, and a border error of 0.09/0.12 for data sets A/B, respectively. In the analysis (ii), out of each dermoscopy image, a series of lesion, background, and border segmentation images are derived. We get a sensitivity of about 0.89, a specificity of 0.94 and an accuracy of 0.91 for data set A, and a sensitivity of about 0.85, specificity of 0.91 and an accuracy of 0.89 for data set B. Our analyses show that the improved methods of region growing and density-based clustering performed after proper preprocessing may be good tools for the computer-aided melanoma diagnosis.

Borrowing from well known fault tolerant approaches based on redundancy to mask the effect of faults, redundancy-based intrusion tolerance schemes are proposed in this paper, where redundancy of ICT components is exploited as a first defense line against a subset of compromised components within the redundant set, due to cyberattacks. Features to enhance defense and tolerance capabilities are first discussed, covering diversity-based redundancy, confusion techniques, protection mechanisms, locality policies and rejuvenation phases. Then, a set of intrusion tolerance variations of classical fault tolerant schemes (including N Version Programming and Recovery Block, as well as a few hybrid approaches) is proposed, by enriching each original scheme with one or more of the previously introduced defense mechanisms. As a practical support to the system designer in making an appropriate choice among the available solutions, for each developed scheme a schematic summary is provided, in terms of resources and defense facilities needed to tolerate f value failures and k omission failures, as well as observations regarding time requirements. To provide an example of more detailed analysis, useful to set up an appropriate intrusion tolerance configuration, a trade-off study between cost and additional redundancy employed for confusion purposes is also carried out.