Existing flood resilience assessments face a fundamental trade-off: correlational analyses of real-world data suffer from confounding bias, while simulations of hypothetical scenarios lack empirical grounding. To address this identification gap, we propose a physically-grounded causal inference framework that derives unbiased causal parameters directly from physical observation. First, we generate high-fidelity flood maps from synthetic aperture radar (SAR) imagery using a fine-tuned U-Net model adapted for dense urban environments. Second, we integrate these empirical maps into a microscopic traffic simulation model to quantify dynamic network disruptions. Third, we apply double machine learning (DML) to isolate the causal effect of flooding on transport resilience while rigorously controlling for high-dimensional urban form confounders. Applied to a flood event in a dense coastal megacity, our analysis reveals two key discoveries: (1) a nonlinear tipping point around 25% flood intensity, distinct from recent studies assuming linear degradation, beyond which system performance collapses chaotically; and (2) a ‘dual nature of vulnerability’, where low-density suburbs suffer a fragility of isolation (2.9× higher road closure rate) while dense urban cores exhibit a fragility of congestion (1.47× greater waiting time increase). Validated across 130 sensitivity tests, this framework provides a robust, data-driven blueprint for spatially targeted resilience investments, demonstrating that causal identification in disaster contexts requires physically-grounded observation, not synthetic assumptions.

The growing complexity of industrial systems demands a transition from passive monitoring to proactive decision support, a shift that hinges on advanced intelligent perception. However, most systems remain confined to brittle, rule-based logic, which operates on fixed symptom-to-action mappings and thus cannot perceive the underlying, context-dependent operational intent. This perceptual gap is particularly detrimental especially in fault diagnosis, where this inability to adapt leads to frequent misdiagnoses and costly downtime. To overcome this limitation, this paper introduces the Intent-Aware Enhancement Framework (IAEF)1, which replaces static rules by actively creating and reasoning over a dynamic causal model. This is achieved through two core method. The Information Theory-guided Causal Graph Revision (ITCGR) algorithm provides the foundation by constructing a reliable causal model, uniquely leveraging information-theoretic metrics to guide an LLM for verifiable revisions on sparse data. Building on this model, the Multi-scale Adaptive Path Reasoning (MAPR) method then infers the true operational intent, employing a novel adaptive fusion model to robustly navigate complex inference chains. Experimental validation in a real-world case demonstrates the framework’s ability to accurately diagnose fault root causes under varying conditions, a task where traditional systems fail. The proposed approach significantly outperforms baselines, providing a foundational methodology for advancing industrial intelligence.

The development of intelligent transportation systems (ITS) in urban areas currently faces a critical misalignment between technological applications and the developmental stages of cities. Most studies on ITS to date have focused on solutions tailored to developed cities, which overlook the practical needs of growing cities. The above problem reduces the applicability of advanced technologies in resource-constrained contexts. To fill the gap, our study constructs a five-tier ITS evaluation framework for cities evolving from city 1.0 to 5.0. Through the synthesis of the literature and practical case analysis, a three-view research paradigm is proposed, “issue–science–engineering” (ISE). It integrates three key elements of ITS in urban areas: the infrastructure network, the transportation network, and the management network, which identify five distinct evolutionary stages of ITS for cities. By pinpointing common critical challenges across these stages, the study distills four priority research themes of ITS for academia: data-driven collaborative optimization, system resilience under complex disruptions, human-centered equity assurance, and incremental transitions toward sustainability. Furthermore, the study establishes a matching mechanism between technological pathways and city developmental stages, which could offer actionable insights for collaboration between industry and academia. Our study provides a decision-making framework for the development of ITS in cities at different stages. We hope that the study could contribute to a more balanced global advancement in this field.

Auditory brainstem response (ABR) is a weak evoked EEG signal that provides an objective measure for assessing auditory function. However, the traditional extraction method, namely, averaging is noise-sensitive and needs thousands of trials, which places high demands on the subjects and the experimental environment. Kalman weighted (KW) technique has the potential to extract ABR with high quality but relies heavily on expert experience for precise parameter tuning. In this article, an adaptive Kalman denoising technique, which can adaptively adjust the parameter, was developed. A comprehensive investigation was carried out on different noise types (pink noise/Gaussian white noise/uniform noise), proportions (20%/40%/60%/80%/100%), amplitudes (20/40/60/80μV), and integrated manners (early-noised/intermittent-noised/late-noised). Multiple metrics, such as Pearson correlation coefficient, root mean square error, latency and amplitude of characteristics wave, and the wave recognition rate were calculated for evaluation. The simulation results showed that the proposed method outperformed the averaging and KW techniques over these evaluation metrics. Also, these evaluation metrics of the proposed method were much more stable than those of averaging the KW. Finally, we verified the proposed method in the real scenario. It is believed that the proposed method opens a window for daily ABR-based auditory health condition screening, which can benefit the early detection and diagnosis of auditory diseases.

Extreme rainfall and flood events increasingly threaten urban transportation networks, yet conventional resilience evaluations fail to capture the dynamic interplay between flooding, traffic congestion, and emergency service accessibility. To address the above gap, this study provides an integrated framework for transportation resilience evaluation with the proposed spatiotemporal accessibility analysis. Our approach combines real-time traffic simulation, flood modeling, an enhanced two-step floating catchment area (E2SFCA) method with a novel congestion-sensitive impedance function, and grid-based percolation theory to quantify network fragmentation via accessibility thresholds and largest connected component (LCC) metrics. A case study in Shanghai’s Huangpu District demonstrates that peak-hour floods induce greater accessibility losses and faster network fragmentation than off-peak events. Sensitivity analysis highlights accessibility’s higher responsiveness to congestion dynamics over facility siting, highlighting the importance of adaptive traffic management in disaster planning. The workflow provides a robust tool for planners to anticipate vulnerabilities, prioritize interventions, and enhance time-critical disaster preparedness.

Path planning is an important step in ensuring the safety of unmanned surface vehicle (USV) navigation and executing missions quickly and efficiently. However, current USV path planning methods lack comprehensive consideration of electronic nautical charts and meteorological data, resulting in planned paths being unable to fully utilize marine environmental conditions, which may easily lead to collisions and long navigation times. Based on the above considerations, our study designs a USV path planning system that comprehensively considers the multimodal information from electronic nautical charts and meteorological data. The system consists of three parts: 1) the image processing module; 2) the meteorological analysis module; and 3) the path planning module. In detail, the image processing module obtains the geographical feature information from the electronic chart and constructs a static obstacle environment. The meteorological analysis module obtains the meteorological feature information from meteorological data and constructs a dynamic meteorological vector field environment. The path planning module introduces a designed double deep Q-Network (DQN) structure, a multivariate weighted Dueling network, and a priority sampling mechanism to enhance the DQN algorithm for promising performance in USV path planning. Extensive experiments illustrate the superior performance of the proposed fusion DQN algorithm. Furthermore, the feasibility of the entire path planning system is confirmed.

The demand, technologies, and market all put forward the request for platformization of the vehicle logistics industry. In China, a few logistics companies have plans but only one has initially built a platform for vehicle logistics. This platform has also attracted a considerable number of service providers to join, which has led to competition between service providers and the platform. To promote the platformization of the vehicle logistics industry and attract more customers to use platform-based services, how to leverage the incentive effect of subsidies is a topic of concern for the government. Motivated by the above, this article discusses whether the exogenous subsidies (provided to customers for platform service or providers service) can accelerate the process of the vehicle logistics industry. We explore the role of subsidies by developing a model (a hotelling line) that describes the differentiated competition between the platform and service providers. Our study found that subsidies do not always work as expected. The effectiveness of the subsidy depends on service advantages and customer preferences. Subsidies may even be counterproductive if customers prefer service providers or if platform services lack advantages. This is a reminder for both the government and industry that to accelerate the platformization of the vehicle logistics industry, it is necessary to combine reality and not blindly subsidize.

Transportation mode-aware trajectory recovery is the fundamental for individual oriented downstream tasks in intelligent transportation systems. Different from vehicle based trajectory recovery, it suffers from the heterogeneity and sparsity issues arising from the insufficient data labelled for distinct transportation modes (e.g., obtaining limited individual trajectories from modes like walking or cycling due to privacy concerns while obtaining rich vehicle trajectories from the mode like driving). To alleviate this, we develop a novel Cross-trAnsportation-mode Knowledge transfEr method with meta learning, coined as Cake, to first learn generalized parameters from source modes (i.e., the relatively dense modes) and then share the meta knowledge with the targets (i.e., more sparse modes), which significantly improve the recovery performance for the sparse. To achieve this, we first develop an efficient fine-GRAined Personalized trajectory rEcovery model called Grape, to incorporate the cross-granularity features with coarse-centered and fine-centered subgraph learning and learn the intrinsic characteristics of transportation modes with auto-correlation efficiently. Then we design a personalized memory to store distinct parameters for diverse interests of individual groups and read the memory for predictor’s input features according to the previous learnt features. At last, we employ the feature reuse strategy based on meta learning to iteratively make adaptions from the source to the target. Extensive experimental results on real-world dataset demonstrate that our proposed method significantly outperforms the state-of-arts for the sparse modes.

Situation awareness (SA) is a crucial factor affecting flight safety for pilots, yet few studies have focused specifically on modeling SA for pilots, resulting in limited success. In this paper, we propose a novel multimodal deep learning approach to monitor pilots’ SA. The approach combines handcrafted and deep features obtained from eye movement and flight control data collected from 27 novice pilots across different training phases using a flight simulator. Ground truth SA measurements were obtained using the Situation Awareness Global Assessment Technique (SAGAT). The handcrafted features included 13 eye movements and 22 flight control features, while deep features were extracted from time-series of gaze positions using a deep extractor based on Transformer. By fusing the handcrafted features of eye movement and flight control, along with one deep feature of eye movement, we predicted the final SA level. Through leave-one-flight-out cross-validation, our model achieved a higher accuracy of 92.04%. The results indicate that the multimodal model outperforms the unimodal models, with the eye movement modality demonstrating superiority over the flight control modality in predicting SA. This suggests our method provides an objective means of predicting pilot’s SA and offers new insights for SA assessment in aviation and other fields. Overall, our multimodal deep learning approach holds promise for enhancing pilot training and flight safety by facilitating a more comprehensive understanding of pilots’ SA during critical flight scenarios.

Chronic disease patients often require revisits for long-term care. Online medical services shift revisits to online, which can improve the access to chronic care and reduce the burden on offline medical services. However, whether Internet healthcare can truly match the medical supply and demand, one of the critical issues is the efficient advance scheduling of the integrated online and offline systems. This study investigates the advance scheduling problem for the first visit and revisit patients in chronic care. The uncertainty of revisit status (i.e., online or offline) and heterogeneity of online and offline revisits (i.e., revisit interval, continuity of care violation penalty) are considered. A stochastic mixed-integer programming model is formulated for assigning patients to a specific physician on a specific day over the course of a finite planning period. The aim is to minimize the expected sum of three cost components related to offline and online services: overtime and idle time, continuity of care violation penalty, and fixed setup. This study proposes a modified progressive hedging algorithm and applies a sequential decision-making framework to obtain rolling time advance schedules. Results of the numerical analysis demonstrate the effectiveness of our algorithm compared to both the published state-of-the-art Lagrangian decomposition embedded with surrogate subgradient method and the commercial solver Gurobi. The insight obtained from the experiments is that a capacity allocation scheme with all physicians assigned with both offline and online capacities would be a good choice for considerable cost savings.Note to Practitioners—Internet healthcare is becoming increasingly popular. Operation and management issues have arisen in the integrated online and offline appointment systems. A sequential decision-making method embedded with a stochastic programming model and a modified PHA is proposed to help decision-makers generate the first visit and revisit advance schedules for chronic care. The performance of this approach and the system is thoroughly verified. Results show that the developed decision technique can lessen the operational cost generated by scheduling and realize the goal of continuity of care. This study offers a useful tool to help with intelligent patient advance scheduling in an integrated management system of online and offline chronic care.

As an emerging topic in industrial digital transformation, digital business development in the context of platformization has received widespread attention. A large number of industrial companies have established new platform-based systems for digital business development by integrating their original information systems. The unified platform development mode promotes the integration of previously decentralized knowledge. However, the massive expansion of the knowledge system under platformization causes it to be no easier for developers to master or understand the core knowledge (context, concepts, and elements) of the business to be developed. According to the above dilemmas we have observed in the industry, in this article, a domain knowledge network modeling method for the knowledge system under platformization and a GP-based rule generation method for recognizing core business knowledge in the domain knowledge network are proposed for the first time. Our experiment and practical case study verify that our method can recognize a set of core business knowledge from a large knowledge network efficiently, which could help developers understand the business to be developed with a lower cognitive load. We hope the idea of platform-based business development and core business knowledge recognition can provide a reference for those companies that need efficient digital business development.

Optical character recognition (OCR) technology is promoting the process of automation in daily information recording and inspection of industrial meters. However, bad installation scenes and long-time running cause industrial meters to age to varying degrees, which increases the difficulty of OCR. Besides, in practice, operators typically use handheld cameras to extract tag information from industrial meters. During the shooting process, extreme lighting, free shooting angles, and shooting distance also cause many difficulties for OCR. Considering such difficulties, an end-to-end recognition architecture is developed to obtain a better OCR performance. The proposed architecture can quickly extract structured information from normal or skewed text images. A novel yolov5_adaloss with a specific penalty factor is designed to alleviate the influence of illumination, installation scene, age, skew, and distance on the classification accuracy of Tags. For images with large skew angles, a mathematical method is proposed to calculate the text inclination angle for better OCR performance. The contribution of this work is twofold. First, the architecture proposed is lightweight, which only needs a low computing cost and a short inference time. Second, as a practical application-oriented architecture, this work does not require much training, labeling, and fine-tuning, which is easy to generalize to other structured text recognition tasks. Experiments show that the method proposed in this article can achieve excellent performance in meter tag recognition tasks on actual industrial images of meters.

Electroencephalogram (EEG) has been widely utilized in emotion recognition due to its high temporal resolution and reliability. However, the individual differences and non-stationary characteristics of EEG, along with the complexity and variability of emotions, pose challenges in generalizing emotion recognition models across subjects. In this paper, an end-to-end framework is proposed to improve the performance of cross-subject emotion recognition. A novel evolutionary programming (EP)-based optimization strategy with neural network (NN) as the base classifier termed NN ensemble with EP (EPNNE) is designed for cross-subject emotion recognition. The effectiveness of the proposed method is evaluated on the publicly available DEAP, FACED, SEED, and SEED-IV datasets. Numerical results demonstrate that the proposed method is superior to state-of-the-art cross-subject emotion recognition methods. The proposed end-to-end framework for cross-subject emotion recognition aids biomedical researchers in effectively assessing individual emotional states, thereby enabling efficient treatment and interventions.

Multiple-view stereo has potential applications in robotic operations and autonomous driving (unstructured environment construction, visual servo). With assisted depth information, inertial navigation systems can achieve precise navigation. It is, especially suitable for GPS failures in complex environments. Accurate depth estimation is a challenge in low-textured or occluded regions. To alleviate the inference of incorrect depth, a multi-stage pixel-visibility learning-based stereo network is presented in this paper. Its improvements are as follows: 1) a new content-adaptive cost volume aggregation mechanism based on neighboring pixel-wise visibility is designed to effectively produce more accurate and smoother depth map predictions in the object boundary. 2) global convolution block and boundary refinement block are developed to regularize its cost volume, they can learn the inherent constraints of feature matching correspondence and effectively mitigate the depth estimation uncertainty in low-textured regions. 3) a new loss function is designed to measure the uncertainty of predicted probability distribution and enhance the reliability of depth map inference. Experimental results on the indoor DTU datasets and the outdoor Tanks & Temples datasets indicate that our method can achieve superior performance and has a powerful generalization ability, which is comparable to state-of-the-art works. Note to Practitioners—Multiple-view stereo (MVS) can estimate dense 3D representations of scenes, which is widely used in autonomous driving, robotic navigation, virtual reality (VR), and augmented reality (AR). Aiming at the problem of incorrect depth inference in low-textured or occluded regions, this work proposes a novel multi-stage depth prediction method based on neighboring pixel-wise visibility. Our method cannot only achieve accurate depth estimation for robot perception but also make no concession to real-time performance. It is clear that the proposed method has good potential in 3D reconstruction, robotic navigation, and VR/AR fields to provide accurate depth estimation in real-time with limited memory consumption.

Semi-supervised learning has attracted wide attention from many researchers since its ability to utilize a few data with labels and relatively more data without labels to learn information. Some existing semi-supervised methods for medical image segmentation enforce the regularization of training by implicitly perturbing data or networks to perform the consistency. Most consistency regularization methods focus on data level or network structure level, and rarely of them focus on the task level. It may not directly lead to an improvement in task accuracy. To overcome the problem, this work proposes a semi-supervised dual-task consistent joint learning framework with task-level regularization for 3D medical image segmentation. Two branches are utilized to simultaneously predict the segmented and signed distance maps, and they can learn useful information from each other by constructing a consistency loss function between the two tasks. The segmentation branch learns rich information from both labeled and unlabeled data to strengthen the constraints on the geometric structure of the target. Experimental results on two benchmark datasets show that the proposed method can achieve better performance compared with other state-of-the-art works. It illustrates our method improves segmentation performance by utilizing unlabeled data and consistent regularization.

The application of automation technology and artificial intelligence technology has promoted the improvement of the business capabilities of enterprises in industrial scenarios. Compared with the improvement or innovation of the business process, in recent years, part of academic research and practical applications has also shifted their attention from a single point of business intelligence perspective to a comprehensive intelligent upgrade of the industrial system. To the best of our knowledge, however, there is little research on the concept and model of the industrial intelligent system (IIS). To make up for the lack, this article presents the concept and reference model of IIS by analyzing the intelligentization requirement of the industrial systems. Different from academic research on general intelligent system capabilities, the reference model given emphasizes factors that need to be considered when implementing IIS in the industry. By analyzing the reference model, knowledge as the core driving force of IIS is recognized. Then, the four main forms of knowledge in IIS, as well as the role and key technologies of knowledge in different stages of IIS, are discussed in detail. In addition, several important potential applications of IIS are pointed out in this article.

Recognition of amount in figures in the financial multi-bill scenes is crucial for the automatic banking business. However, the diversity of banking business and the limitation of customer data privacy determine that it is difficult to collect a large number of sample datasets. Aiming at the problem of insufficient training data in multi-bill scenes and the low accuracy of the detection model, this article proposes a new generative adversarial network (GAN) to generate new samples and to expand the bill dataset, which is then adopted to train a framework for recognition of the bill amount. In the proposed WGAN-SA, a residual block is adopted as the basic structure of the generator and the discriminator, and the self-attention mechanism is also utilized to improve the generation performance. In addition, Wasserstein distance is utilized to measure the distance between real and synthetic samples. Experimental results on the benchmark dataset and comparisons with state-of-the-art works show that our proposed WGAN-SA can effectively improve the few-sample learning performance. Besides, experiments on the bill dataset verify that our method can solve the problem of model collapse and has the ability to generate images of the amount in figures with better fidelity and variety, which is also helpful to achieve better bill amount recognition performance compared with other latest works.

In the context of Industry 4.0, the medical industry is horizontally integrating the medical resources of the entire industry through the Internet of Things (IoT) and digital interconnection technologies. Speeding up the establishment of the public retrieval database of diagnosis-related historical data is a common call for the entire industry. Among them, the Magnetic Resonance Imaging (MRI) retrieval system, which is one of the key tools for secure and private the Internet of Medical Things (IoMT), is significant for patients to check their conditions and doctors to make clinical diagnoses securely and privately. Hence, this paper proposes a framework named MRCG that integrates Convolutional Neural Network (CNN) and Graph Neural Network (GNN) by incorporating the relationship between multiple gallery images in the graph structure. First, we adopt a Vgg16-based triplet network jointly trained for similarity learning and classification task. Next, a graph is constructed from the extracted features of triplet CNN where each node feature encodes a query-gallery image pair. The edge weight between nodes represents the similarity between two gallery images. Finally, a GNN with skip connections is adopted to learn on the constructed graph and predict the similarity score of each query-gallery image pair. Besides, Focal loss is also adopted while training GNN to tackle the class imbalance of the nodes. Experimental results on some benchmark datasets, including the CE-MRI dataset and a public MRI dataset from the Kaggle platform, show that the proposed MRCG can achieve 88.64% mAP and 86.59% mAP, respectively. Compared with some other state-of-the-art models, the MRCG can also outperform all the baseline models.

As an emerging delivery pattern, long-distance non-standardized delivery (LND) is receiving the attention of large logistics companies. Despite the growing demand and customer market for LND, so far there is no mature logistics platform for LND. For logistics companies planning to carry out LND services, there is currently no feasible and effective operations methodology. This paper summarizes the characteristics of LND from the perspective of operations and preliminarily explores the operations methodology of LND. Specifically, the two issues, driver assignment and order settlement for LND, are discussed in detail. To the best of our knowledge, our paper is the first one to study the complete operations methodology for LND. Our proposed methodology could help these large logistics companies that have already launched long-distance standardized delivery services expand the scope of their service. Experimental results demonstrate the feasibility and effectiveness of the proposed driver assignment and order settlement methods. Finally, the paper discusses the impact of drivers’ human factors on LND operations and concludes with several interesting findings. These findings can help the future exploration of how to design a more efficient and beneficial logistics platform for LND.

To respond to the rapid growth of shipping container throughput, terminals urgently need to improve the efficiency of thier operations and reduce operational costs through automation and intellectualization upgrades, thereby improving service levels and enhancing market competitiveness. Due to the advantages of reliable transportation, efficient operation, and environmental friendliness, AGV-based automated container terminal (ACT) has become the development trend of container terminals. To help ACT improve its operational management capabilities, plenty of scholars have explored the transportation system of ACT. Through the analysis of operational management issues, the paper defines the four main research topics in vehicle transportation of the ACT including equipment scheduling, path planning, exception handling, and vehicle management. Then, in each topic, the works in the recent 25 years are summarized and several research opportunities for possible follow-up research directions in different fields are proposed. We expect our survey could not only provide references for more scholars on the research of operation and management of terminals, but also provide guidance for system evaluation and improvement for terminal system engineers and operation managers.

Driver identification has been popular in the field of driving behavior analysis, which has a broad range of applications in anti-thief, driving style recognition, insurance strategy, and fleet management. However, most studies to date have only researched driver identification without a robust verification stage. This paper addresses driver identification and verification through a deep learning (DL) approach using psychological behavioral data, i.e., vehicle control operation data and eye movement data collected from a driving simulator and an eye tracker, respectively. We design an architecture that analyzes the segmentation windows of three-second data to capture unique driving characteristics and then differentiate drivers on that basis. The proposed model includes a fully convolutional network (FCN) and a squeeze-and-excitation (SE) block. Experimental results were obtained from 24 human participants driving in 12 different scenarios. The proposed driver identification system achieves an accuracy of 99.60% out of 15 drivers. To tackle driver verification, we combine the proposed architecture and a Siamese neural network, and then map all behavioral data into two embedding layers for similarity computation. The identification system achieves significant performance with average precision of 96.91%, recall of 95.80%, F1 score of 96.29%, and accuracy of 96.39%, respectively. Importantly, we scale out the verification system to imposter detection and achieve an average verification accuracy of 90.91%. These results imply the invariable characteristics from human factors rather than other traditional resources, which provides a superior solution for driving behavior authentication systems.

In the context of establishing emission control areas (ECAs) in many ports to meet the challenges posed by air pollution, the use of drone-carrying sniffers to perform emission monitoring missions has become a new monitoring mode for ECAs. The operational management problem of drones in ECAs, namely, drone scheduling problem (DSP), is eliciting the attention of researchers. To consider the influence of vessel traffic on the demand for drones, this study proposes a rental-based drone operation model. In the model, the number of drones used depends on the load of monitoring missions. Maximizing the cumulative monitoring reward and minimizing the use number of drones within the minimum monitoring rate constraint are used as optimization objectives to maximize the cost return of the rental-based operation model. The rental-based drone operation model is modeled as a multi-objective DSP (MDSP). Furthermore, we horizontally compare the characteristics of MDSP with those of many classical models in the field of operations research. Afterward, we reveal the similarities and differences between MDSP and previous models. We find that MDSP has the non-first-in-first-out property, whereas most of the advanced models have the first-in-first-out property, which leads to the failure of the developed efficient algorithms in solving MDSP. Therefore, this study innovatively designs four feasible multi-objective optimization methods for MDSP. Numerical experiments are conducted to evaluate the performance of the four methods in solving MDSP with different scales. In terms of theoretical implications, experimental results prove that the proposed methods for solving MDSP are feasible and effective. In terms of practical implications, the proposed rental-based vessel monitoring operation model shows great potential for practical engineering.

The integration of the industrial Internet of Things (IoT) and blockchain technology is changing the business and management model of the supply chain. Much work is focused on how to promote the application of blockchain-based industrial IoT in the supply chain from both academic research and industrial practice. However, due to the different industrial requirements in industrial scenes, the gap between technology researches and industrial applications is still large. Therefore, the article adopts the mixed method of enterprise survey and literature review to identify the actual industrial requirements in different supply chain scenes. Also, the characteristics and applicable scenarios of industrial IoT and blockchain have been analyzed. Then, the potential application opportunities of blockchain-based industrial IoT in nine scenes are discussed in detail. This study reveals the technical challenges and practical challenges of these applications, which potentially guides research on applying industrial IoT and blockchain technology in the supply chain.

The drone has become a promising tool to improve the efficiency of vessel emission monitoring in emission control areas of the part due to its high mobility. However, how to optimize the flight path of drones to improve the weighted sum of monitored vessels, i.e., drone scheduling problem (DSP), is a not yet fully researched problem. In this paper, different from the classic optimization solution method used by the literature, an efficient ant colony-based algorithm is developed to solve DSP. Given the characteristics of DSP, a hierarchical-based pheromone update strategy and partition-based pheromone management mechanism are proposed to optimize the typical ant colony algorithm. Numerical experiments not only illustrate the feasibility of using the ant colony algorithm to solve DSP, but also show that the algorithm we proposed outperforms other compared methods in terms of the solution quality and the solving speed under different problem scales.

How to effectively organize drones to monitor pollutants from vessels is an important operational problem in port management. It is defined as the drone scheduling problem (DSP). The effectiveness of precise algorithms and heuristic algorithms in solving DSP has been reported in previous studies. In previous studies, the speed of the vessel was assumed to be constant. However, since the influence of sea waves and vessel power, such an assumption is difficult to satisfy in actual scenarios. The actual position of the vessel may deviate from the position information obtained through prior calculations. As the cumulative position deviation increases, it is possible to make the original feasible monitoring scheme infeasible. It is necessary to consider the emission monitoring dispatching of drones under vessel speed fluctuation in actual monitoring activities of the vessel. To deal with the problem, a dynamic dispatching strategy based on reinforcement learning (RL) is proposed. Considering the vessel speed fluctuation, the monitoring window is divided into multiple sub-time windows. The route information of the vessel in each sub-time window is updated according to the vessel speed fluctuations to reduce the accumulation of deviations between the prior position and the actual position. Then, a lightweight RL strategy is adopted to quickly (re)organize the monitoring scheme in each sub-time window. Numerical experiments illustrate the above division-conquer approach could effectively reduce the possibility of drone monitoring failure caused by vessel speed fluctuations. Also, the superiority of the RL-based dispatching strategy is illustrated by comparing it with multiple dispatching schemes.

Multiple-View Stereo (MVS) aims to reconstruct the dense 3D representations of scenes. MVS has potential applications in the fields of autonomous driving (unstructured environment construction) and robotic navigation (visual-inertial navigation). To mitigate the error of depth estimation in low-textured or occluded regions, this work proposes a two-stage multi-view stereo network for fast and accurate depth estimation. The improvements of this work over the state of the art are as follows: 1) Sparse costs are constructed to jointly predict the initial depth map and surface normal by cost regularization, which proves that the surface normals can be estimated in this way with low memory consumption. 2) A new edge refinement block is developed to refine the coarse surface normal to obtain a fine-grained surface normal map. 3) Instead of using the general variance-based metric to equally aggregate cost, a new content-adaptive cost aggregation mechanism based on the similarity of the neighboring surface normal is designed for reliable cost aggregation. To the best of our knowledge, the proposed work is the first trainable network that leverages surface normal as guidance to capture neighboring pixel-visibility, which is an effective supplement to existing depth/normal estimation frameworks. Experimental results indicate that our method can not only achieve accurate depth estimation for scene perception but also make no concession to the real-time performance and limited memory bottleblock. Multiple-view stereo (MVS) aims to reconstruct the dense 3D representations of scenes. It is widely used in the fields of industrial measurement, autonomous driving, and robotic navigation. To mitigate the error of depth estimation in challenging scenarios, this work proposes a two-stage multi-view stereo network for fast and accurate depth estimation. Our method is the first trainable network that leverages surface normal as pixel-visibility guidance to aggregate reliable cost, which could achieve accurate depth estimation and provide the perception ability for the robot. The proposed method has great potential in the fields of 3D reconstruction, industrial measurement, and robotic navigation to estimate real-time and accurate depth with limited memory consumption.

This work designs an adversarial Bayesian deep network to solve the cognitive detection of pilot fatigue. Batch normalization and data enhancement are adopted in the posterior inference of the proposed model parameters to effectively improve the generalization of neural networks. The generator is used to enhance the brain power map generated from three cognitive indicators and improve the accuracy of fatigue state recognition. This work also adds adversarial noise in the vicinity of each brain electrode to form an adversarial image, which further reveals the correlation between the cognitive state of brain and the location of brain regions. Compared with other deep models and parameter optimization methods, our model achieves better detection accuracy.

Emission control area has been set up in many countries to reduce the environmental impact of vessels' emissions. However, the regulations for controlling emissions are frequently violated due to the cost of high-quality fuel. Drones currently have become an accurate and efficient way to monitor the vessels' emissions, which should be properly scheduled to cover more and higher risk of violations when facing a large number of vessels. In this paper, a scheduling model is proposed to simulate the drone scheduling monitoring problem. Due to the movement of vessels over time, the complexity of the model is too large to be solved by classical optimization methods such as CPLEX. An ant colony system algorithm is proposed to solve the scheduling problem of drones. Our method is proved to be more effective and efficient when facing a large number of vessels and drone stations in numerical experiments.

The traditional fault diagnosis methods for rolling bearing usually require the test data and training data to follow the same distribution, which cannot be always meet in real-world scenarios, since the working condition of rolling bearing is often variable. Hence, to overcome the low performance of fault diagnosis traditional methods for different data distributions, a fault diagnosis approach based on transfer learning is proposed in this paper. And the main idea of our approach is to combine joint distribution adaptation and support vector machine to diagnose bearing faults under variable working conditions. In this research, kernel-JDA is used to reduce the difference between distributions of datasets taking both the marginal and conditional distributions into consideration, while the parameters of kernel-JDA are optimized to improve the performance. Besides, multi-features including time domain features and the relative wavelet packet energy are constructed at first to prepare for fault diagnosis. After mapping the multi-features through kernel-JDA, SVM is utilized to diagnose faults of rolling bearing under different working conditions. In addition, comparison experiments on vibration signal datasets of rolling bearings are carried out to verify the effectiveness and applicability of this approach for both the normal and small sizes of the sample sets.