The deployment of battery charging stations (BCS) has emerged as a critical bottleneck in robotic mobile fulfillment systems (RMFS), directly governing operational continuity and system-level throughput. Optimizing BCS deployment under multi-visit charging demands remains a significant challenge, particularly in dynamic environments with fluctuating workloads and spatiotemporal constraints.We propose CLAP-IGA (Integrated Genetic Algorithm Considering Charging Logic and Allocation Path), a constraint-embedded evolutionary framework that jointly optimizes BCS layout, robot routing, and multi-visit task scheduling. CLAP-IGA incorporates a rolling-horizon replanning mechanism and embeds real-time battery state tracking, time-varying order arrival dynamics, and spatiotemporal path conflict management directly into the evolutionary process. Two deployment strategies—internal and external BCS configurations—are systematically compared to characterize their trade-offs across varying operational scales. Experiments across three operational scales demonstrate that CLAP-IGA reduces total completion time by up to 30% and improves charging station utilization by 18% relative to standard GA, greedy, and DQN baselines. The findings further reveal a counterintuitive capacity-threshold interaction: naively expanding BCS capacity can paradoxically degrade throughput, underscoring the necessity of co-designing charging policy and infrastructure rather than optimizing either in isolation.

This paper proposed an integrated waveform design and parameter optimization method to realize real-time detection and communication for inverted echo sounders (IES). The approach balances detection performance and communication quality in active sonar systems. An integrated detection– communication waveform (GIDC) is developed using the orthogonality and parameter diversity of generalized sinusoidal frequency modulation (GSFM). The waveform incorporates differential binary phase-shift keying (DBPSK) modulation and superimposed orthogonal GSFM signals, enabling simultaneous acoustic detection and data transmission. To enhance performance, parameter optimization constraints are formulated for the carrier GSFM based on quantitative ambiguity function (AF) analysis and bit error rate (BER) metrics, and are solved using an improved genetic algorithm (GA). The optimization effectively suppresses autocorrelation sidelobes, improves reverberation suppression, and ensures reliable error rate performance. The simulation results on Gaussian and vertical underwater acoustic channels confirm that the proposed waveform achieves robust joint detection and communication. Compared with conventional waveforms, the GIDC exhibits higher detection-delay accuracy and lower BER, demonstrating excellent integrated performance suitable for underwater applications.

Subsea pipelines are prone to exposure due to natural factors such as earthquakes and vortices, which necessitates regular condition monitoring. Multi-beam echo sounders (MBES) can provide high-precision seabed topographic information, while side-scan sonar (SSS) excels at capturing high-resolution seabed texture features. The integration of these two data sources can complement each other, thereby improving the detection accuracy of subsea pipelines. To achieve effective fusion, high-precision spatial registration is required. However, existing registration algorithms still face challenges such as uneven feature point distribution, dependence on prior knowledge, and unstable matching. This paper proposes a multi-source sonar image registration algorithm for subsea pipelines, named A Hierarchical Feature Structure-Driven Method for Multi-Source Sonar Image Registration of Subsea Pipelines (HFSM). First, the method designs a grid-based multi-scale corner detection (MS-CD), which effectively enhances the spatial distribution balance of feature points. Next, a multi-window geometric-texture joint feature descriptor (MW-GTD) is proposed, which combines direction-sensitive curvature and spatial shadow distribution features within different scale windows. Finally, a multi-layer coarse-to-fine guided matching strategy (ML-CFGM) is introduced to enhance the matching stability of images in feature-sparse regions and realize multi-layer feature matching. The superiority of the proposed method is validated with real-world data, providing technical support for the efficient registration of MBES and SSS images and subsea pipeline detection.

Radar-based gesture recognition and person identification offer a natural, convenient, and privacy-preserving approach to human-computer interaction. However, most existing research focuses predominantly on learning for a single task, which requires separate models for each task. This separation increases the complexity of the deployment and the computational overhead. To address these challenges, this study introduces a multi-task learning framework that simultaneously performs gesture recognition and person identification using a miniature radar sensor. By leveraging radar's capacity to capture finegrained spectral and spatial motion patterns, the framework incorporates micro-Doppler and range-Doppler processing, alongside a multi-branch architecture to enhance modality-specific feature representation. It enables unified learning of shared and task-specific features within a single network architecture. The proposed model, MTxLSTM, integrates CNN and the recent xLSTM to mitigate task interference, improve generalization, and improve gesture recognition through person-specific nuances while enhancing person identification by leveraging contextual gesture information. Experimental results reveal that MTxLSTM outperforms existing multi-task learning frameworks and stateof- the-art models, achieving 99.21% in gesture recognition and 98.59% in person identification with moderate model complexity and inference speed. This study concurrently executes gesture recognition and person identification using a miniature radar sensor, and marking the first application of xLSTM in radar sensing technology.

Radar-based human activity recognition (HAR) has emerged as a critical component in various applications, ranging from smart homes to healthcare monitoring. Radar has several advantages: a wide detection range, a certain penetration ability, non-contact and non-perception detection ability, not being affected by light, and privacy-preserving. However, achieving high accuracy with efficiency remains a significant challenge due to the complexity of radar signals and the variability in human activities. Currently, the majority of research efforts are centered on enhancing performance, often at the expense of computational efficiency. In this paper, we propose RadarAttn, a novel approach that integrates visual attention mechanisms with self-attention to enhance the performance and efficiency of HAR systems. The architecture of RadarAttn can reduce floating-point operations (FLOPs) and parameter counts while improving accuracy. Our method leverages the visual attention mechanism to focus on the most relevant regions of radar spectrograms. Simultaneously, the self-attention mechanism is used to capture long-range dependencies within the radar signal, enabling the model to learn complex patterns associated with different activities. Experimental results on benchmark radar-based HAR datasets demonstrate that RadarAttn significantly outperforms state-of-the-art methods in both accuracy and computational efficiency. Our approach offers a promising direction for developing robust and scalable radar-based HAR systems for real-world applications.

The Internet of Medical Things (IoMT) has attracted the attention of many scholars because of its revolutionary impact on healthcare services. However, the sensitivity of medical data and the complexity of IoMT architectures pose critical challenges to privacy-preserving service design. This survey offers a comprehensive and novel investigation and classification of privacy and security issues in IoMT. We explore the issue from four distinct angles: privacy protection technologies, IoMT architecture, data type variations, and emerging technologies, with each section delving into more detailed analysis. Specifically, privacy protection technologies include cryptography method, Federated Learning (FL), blockchain technology and Differential Privacy (DP). We provide a more detailed classification for popular technologies such as blockchain. Regarding the IoMT architecture, we dissect the attack and defense mechanisms at the perception layer, the transmission and cloud layer, and the application layer. In terms of data types, we discuss the research on privacy protection based on the structural differences of various medical data. In the aspect of emerging technologies, we investigated the impact of four emerging technologies on privacy protection of IoMT. Our survey highlights the comprehensive and novel perspective of the characteristics of IoMT privacy protection, which will promote possible booming research in the future.

Underwater federated learning (UFL) is an emerging technology to realize distributed intelligent collaboration in the Internet of Underwater Things (IoUT), but its application faces two challenges: the limited bandwidth of underwater communication leads to low model transmission efficiency, and the data is characterized by low quality and high heterogeneity due to environmental interference. In this paper, an underwater federated learning framework with dual-path collaborative optimization is proposed to solve the above problems systematically through the joint design of knowledge distillation and data quality enhancement. Specifically, to optimize the transmission efficiency, a knowledge distillation mechanism is designed, and the complex model is compressed into a simplified model suitable for low-bandwidth transmission by using the collaborative distillation of lightweight teacher-student models. To enhance data quality, a supervised data quality enhancement (S-DQE) method is proposed. The integration of traditional methods with deep learning-based approaches optimizes feature representation through the joint application of contrastive learning and adversarial training, thereby effectively addressing the issue of low-quality underwater data. Finally, numerical results are given to compare the final scheme with the initial federated learning scheme, lightweight model scheme, and lightweight-data quality enhancement scheme, clearly demonstrating its performance gains.

In distributed learning, the End-Edge-Cloud architecture is gaining widespread adoption. However, the cross-layer data interaction in EEC systems significantly increases the risk of privacy breaches. To address this challenge, this paper proposes a novel dynamic privacy-protection framework named MetaDP-HE. The framework is designed to enhance privacy protection while maintaining model performance. It integrates meta-model guided differential privacy (MetaDP) with CKKS homomorphic encryption that supports floating-point operations. A dynamic coordination mechanism is introduced to optimize the parameter configurations between MetaDP and HE. Specifically, clients use the meta-model to predict privacy budgets based on data sensitivity and adjust the noise in differential privacy accordingly. Edge servers then dynamically adjust the encryption parameters of homomorphic encryption based on the noise level, achieving adaptive regulation of encryption strength. The combination of layered encryption and dynamic parameter optimization enables the system to ensure privacy protection and efficient operations when handling data at different levels. Experimental results show that MetaDP-HE outperforms traditional single-privacy methods in both privacy protection and model performance, validating its effectiveness and applicability in practical scenarios.

Centralized federated learning is being widely researched and applied. However, centralized federated learning is prone to problems such as single point of failure and privacy disclosure because it relies too much on the central server. Focusing on decentralized federated learning, this paper innovatively constructs a decentralized federated learning framework based on dynamic selection collaboration and topology optimization. Firstly, we propose a dynamic client selection algorithm based on node training quality. Then, a global network topology for data communication is constructed by us based on the Watts-Strogatz(WS) model. Finally, we design a temporary topology algorithm to realize synchronization and model update in training. In the process of decentralized federated learning, the global network topology based on WS model cooperates with the current network topology constructed by temporary topology algorithm. The two network topologies work together to realize a dynamic client selection algorithm based on node training quality. A large number of experiments verify that DFedMQ can accelerate the model convergence and improve the training effect under the premise of privacy protection.

Metacomputing optimizes distributed computing resources to enhance federated learning systems by enabling efficient resource allocation, improved scheduling, and greater scalability, thereby addressing challenges in large-scale and dynamic environments. This paper proposes an innovative framework integrating Directed Acyclic Graph (DAG) technology with federated learning within a metacomputing environment. The key contributions include a three-layer decentralized federated learning model integrating DAG and metacomputing to enhance resilience and scalability, two advanced tip selection models LazyEval Tip Selector and Precision Tip Selector to optimize node selection and improve data flow, and a Benchmark Improvement Protocol (BIP) for efficient node publishing and role adaptation.The BIP ensures that only high-performing models are published by comparing new models against established benchmarks, which enhances node collaboration and optimizes resource allocation. LazyEval Tip Selector minimizes redundant computations by leveraging a global cache and employing a lazy evaluation strategy, thereby improving computational efficiency. On the other hand, Precision Tip Selector uses a precise scoring mechanism to ensure accurate tip selection, thereby enhancing the robustness and reliability of the entire system. Collectively, these innovations enhance model training efficiency, support real-time updates, and improve the scalability of federated learning systems, making them well-suited for managing complex, dynamic environments.

Radar sensing is gaining increasing attention due to its unique advantages, including being device-free, privacy-preserving, and capable of penetrating obstacles. It has been extensively studied in various applications such as human activity recognition, vital sign monitoring, and person identification. However, most existing research focuses on a single specific application, and there remains a lack of studies or datasets dedicated to multi-task radar sensing. In this paper, we collected a dataset for two sensing tasks, including gesture recognition and person identification, via a miniature mm-wave radar. The raw radar signals were processed using micro-Doppler and range-Doppler techniques to extract spectral and spatial representations. We propose an improved multi-task radar sensing framework (MT-DualFormer) that incorporates attention-based cross-task feature distillation and contrastive learning to maximize task performance. MT-DualFormer consists of dual branches with CNN and Transformer modules, capturing both spatial and temporal dependencies in radar data. Attention-based cross-task feature distillation enables knowledge transfer between gesture recognition and person identification tasks. Meanwhile, contrastive learning ensures embedding space separability, facilitating robust task-specific classification. In the evaluation, MT-DualFormer achieves accuracy rates of 98.87% for gesture recognition and 97.96% for person identification, surpassing five representative multi-task approaches and ten state-of-the-art models. This study underscores the importance of leveraging task correlations to enhance the performance of radar-based sensing systems.

With the continuous development of 6G technology and the Internet of Things, small terminal devices are gradually joining deep model training through wireless networks, leading to the evolution of federated learning. In comparison to traditional centralized learning, federated learning not only leverages the computational power of individual terminals but also ensures the security of terminal data. However, the increasing number of devices poses new requirements on resource utilization in federated learning at scale. In this paper, we aim to address these challenges by proposing an energy-efficient and adaptive resource allocation strategy for wireless heterogeneous layered federated learning model (HLFLM). Specifically, we deploy both macro base stations and multiple micro base stations to construct a HLFLM, and perform resource allocation for subcarriers and power optimization. This approach focuses on optimizing energy consumption in federated learning networks while enhancing scalability and real-time performance of wireless communication. Experimental results demonstrate the effectiveness of the proposed method in medium-sized scenarios.

In the context of rising demands for marine resource exploitation and scientific research, collaborative trajectory planning for multiple Autonomous Underwater Vehicles (AUVs) in complex underwater environments—marked by obstacles, ocean currents, and low visibility—remains a critical challenge. Although the Gray Wolf Optimization (GWO) algorithm has advanced multi-objective trajectory planning, it faces issues such as poor high-dimensional space adaptability, susceptibility to local optima, and insufficient constraint handling. To address these, this article proposes a multi-AUV trajectory planning algorithm (EA-GWO) based on evolutionary learning to improve GWO. The method optimizes multi-AUV trajectory planning by leveraging hierarchical population hunting behavior, integrating position update equations to prioritize population bootstrapping, and balancing exploration and exploitation via fitness-based population distribution. Experimental validation across general, ocean current, and threat environments compares EA-GWO with the traditional GWO and multiple population GWO (MP-GWO). For sailing time: in the general environment, EA-GWO reduces total time by 90.6% compared to GWO and 90.6% compared to MP-GWO; in the ocean current environment, it cuts time by 0.9% versus GWO and 2.4% versus MP-GWO; in the threat environment, it cuts time by 13.6% versus GWO and 14.9% versus MP-GWO. For sailing distance: in the general environment, EA-GWO shortens total distance by 9.8% compared to GWO and 3.4% compared to MP-GWO; in the ocean current environment, it reduces distance by 2.3% versus GWO and 4.9% versus MP-GWO; in the threat environment, it shortens distance by 5.5% versus GWO and 1.0% versus MP-GWO. In terms of convergence performance reflected by the fitness curve: across the three environments, EA-GWO demonstrates faster convergence speed. These results highlight that EA-GWO outperforms the other two algorithms in sailing time, distance, and convergence efficiency, verifying its effectiveness in real-time dynamic coordination and constraint handling for multi-AUV missions.

Current research in human activity recognition primarily emphasizes enhancing accuracy, with limited exploration into computational efficiency and hardware compatibility. Recently, Mamba has sparked substantial interest within the realm of deep learning. Mamba is a hardware-aware algorithm enabling very efficient training and inference. Researchers are applying Mamba to various tasks, demonstrating significant promise in both language and vision tasks. It is worthwhile to investigate the use of Mamba for efficient human activity recognition. In this paper, we proposed a hybrid neural network that integrates CNN and visual Mamba, called ActivityMamba. The SE-Mamba block in ActivityMamba utilizes both CNN’s local and Mamba’s global context modeling while keeping computation and memory efficiency. We evaluated the ActivityMamba on five public benchmark datasets collected by using three different sensing techniques. ActivityMamba achieved higher performance than vision transformers, vision Mamba, and CNNs with fewer FLOPs and parameters. It sets a new SOTA on all five datasets, which are 91.78% OA and 89.13% F1 on the USC-HAD dataset, 99.19% OA and 98.64% F1 on the UT-HAR dataset, 99.82% OA and F1 on the DIAT dataset, 98.59% OA and 98.65% F1 on the UCI-HAR dataset, and 95.41% OA and 93.14% F1 on the UniMib dataset. Our work is the first to investigate the CNN-Mamba hybrid network for efficient human activity recognition.

Captured retinal images vary greatly in quality. Low-quality images increase the risk of misdiagnosis. This motivates to design effective retinal image quality assessment (RIQA) methods. Current deep learning-based methods usually classify the image into three levels of "Good", "Usable", and "Reject", while ignoring the quantitative feedback for more detailed quality scores. This study proposes a unified RIQA framework, named QAC-Net, that can evaluate the quality of retinal images in both qualitative and quantitative manners. To improve the prediction accuracy, QAC-Net focuses on extracting discriminative features by using two strategies. On the one hand, it adopts a pyramid network structure that simultaneously inputs the scaled images to learn quality-aware features at different scales and purify the feature representation through a consistency loss. On the other hand, to improve feature representation, it utilizes a quality-aware contrastive (QAC) loss that considers quality relationships between different images. The QAC losses for qualitative and quantitative evaluation tasks have different forms in view of the task differences. Considering the shortage of datasets for the quantitative evaluation task, we construct a dataset with 2,300 authentically distorted retinal images, each of which is annotated with a numerical quality score through subjective experiments. Experimental results on public and our constructed datasets show that our QAC-Net is competent for the RIQA tasks with considerable performance.

Deep reinforcement learning models have achieved promising results in the path planning problem for uncrewed aerial vehicles (UAVs). However, their update mechanisms can lead to overestimation and poor stability. This study addresses these issues by using a more realistic reward function, assigning priorities to experiences in the experience replay pool, and employing double decoupling of state and action values in Q-networks. We train the improved Deep Q-Network (DQN) algorithm for three-dimensional environment simulation experiments in a simulated environment. The 3D simulation experiments compare the algorithm with the A-star and unimproved DQN algorithms. The experimental results show that the algorithm has been improved, demonstrating its enhanced performance in the final path planning results. Moreover, the final testing results reveal that the UAV can safely reach the target point from the starting point.

Drone participation in truck delivery is a potential booster for the last-mile logistics system, which has been an emerging hot research field. Among that, how to arrange a fleet of drones from the truck and optimize the vehicle routing problem with drones (VRPDs) is a key issue. However, most existing studies fail to derive the feasible solutions due to unordered customer distributions and multivariant drone feature constraints. In this article, we propose a novel self-driven reinforcement learning structure, named constraint-based hybrid pointer network (CH-Ptr-Net) model, which is a hybrid pointer network approach composed of graph neural network (GNN) embedding and attention decoder. We go into developing the simpler embedding version for multiple drones-assisted truck delivery. The CH-Ptr-Net model tends to generate a set of optimal delivery sequence, after constructing the mixed-integer linear program (MILP) formulation. Extensive numerical testing indicates that the proposed method performs better than recent exact and heuristic approaches for collaborative delivery routing optimization with the truck carrying multiple drones.

With the development of Internet of Medical Things(IOMT), a lot of medical data are stored and released for both scientific research and practical applications. Accurate medical data is very valuable, but it also brings a huge risk of privacy leakage. Moreover, improving the privacy of data often leads to the reduction of data validity. Privacy and effectiveness are in conflict, and their balance is a typical multi-objective optimization problem (MOP). In this paper, we try to use differential privacy to disturb medical data to protect personal privacy. We propose the Environment Switching Algorithm (ESA) based on evolutionary learning to solve this MOP. ESA has excellent performance, which can ensure convergence speed and optimization performance at the same time. The result of optimization is a pareto front (PF) of huge scale, which includes solutions with different characteristics. We put forward a method of double clustering to select the appropriate solution from PF. Based on the above, we conclude the whole method as Flexible Differential Privacy Algorithm based on Evolutionary Learning (FDPEL). FDPEL can realize flexible differential privacy for medical data, while ensuring data privacy and data validity. FDPEL is suitable for privacy protection of medical data of different scales, which makes it have a practical applications value.

Automatic modulation recognition (AMR) of underwater acoustic (UWA) signals is incredibly challenging due to the complexity of UWA channels and the severity of ocean noise. In the presence of noise interference, single-modal features fail to fully represent the characteristics of different modulated signals. While the in-phase/quadrature (I/Q) and time-frequency maps can adequately represent the signal features in the time, frequency, and time-frequency domains, the direct integration of the two modalities is ineffective because of the variations in shape, information granularity, and noise manifestation. To address the low recognition rate caused by the above issues, we propose a two-stream transformer (TSTR) based network for AMR of UWA signals. First, the input pre-processing layer obtains the I/Q and time-frequency features from the received signals. Then, the feature capture layer extracts high-dimensional signal features in the time, frequency, and time-frequency domains. Finally, the classification layer estimates the modulation of the signals. A multi-head self-attention module with adaptive soft thresholding is used in the feature capture layer to provide noise reduction and redundant feature rejection while retaining context information. Moreover, multi-scale ghost convolution is employed to address the inability of the transformer to efficiently extract spatial characteristics from the signals. Results are presented using real UWA channels from the Watermark dataset for two different seas which show that the TSTR improves recognition by 1.2% and 5.9% over the best existing model. Further, it has better generalization capabilities and the model has a small number of parameters so the time complexity is low.

Wireless sensing and communication evolved separately in the past. However, Integrated Sensing and Communication (ISAC) unlocks a new era of mobile network capabilities, with WiFi emerging as a prime candidate. By leveraging existing WiFi infrastructure and frequencies, ISAC enables powerful services like accurate localization and human activity recognition (HAR). WiFi-based HAR is a prime example powered by the magic of ISAC. WiFi Channel State Information (CSI) is susceptible to human movement disturbances; the alterations in CSI mirror the dynamic attributes of human activities. Given the intricate relationship between human activities and CSI, numerous deep learning models have been introduced to enhance HAR accuracy. Recently, transformer-based models have achieved excellent performance in various tasks, including speech recognition, natural language processing, and image classification. This has spurred research into incorporating transformer-based models into WiFi sensing applications. However, their application in WiFi-based HAR remains nascent. Vision transformer is well-suited for analyzing WiFi CSI signals in the form of spectra, such as the Doppler frequency spectrum frequently utilized in related studies, owing to its data structure mimicking that of images. In this study, we explored five widely used Vision Transformer architectures (vanilla ViT, SimpleViT, DeepViT, SwinTransformer, and CaiT) for WiFi CSI-based HAR using two publicly available datasets, UT-HAR and NTU-Fi HAR. Our work aims to assess and compare the performance of diverse ViT architectures for WiFi CSI-based HAR and provide guidelines for WiFi-based HAR modeling and ViT selection, considering accuracy, model size, and computational efficiency.

With the continuous improvement of hardware computing power, edge computing of industrial data has been gradually applied. In the past decade, the promotion of edge computing has also greatly improved the efficiency of industrial production. Compared with the conventional cloud computing, it not only saves the bandwidth consumption of data transmission, but also ensures the terminal data security to a certain extent. However, the continuous update of attack types also put forward new requirements for the privacy protection of industrial edge computing. So it should fundamentally solve the risk of industrial data leakage in the process of deep model training in edge terminal. In this article, we propose a new federated edge learning framework based on hybrid differential privacy and adaptive compression for industrial data processing. Specifically, it first completes the adaptive gradient compression preparation, then constructs the industrial federated learning model, and finally makes use of adaptive differential privacy model to optimize, so as to complete the privacy protection towards the transmission of gradient parameters in industrial environment. By optimizing the hybrid differential privacy and adaptive compression, we can better prevent the terminal data privacy against inference attacks. The experimental results show that this method is very effective in the industrial edge computing situation, and it also opens up a new direction for the effect of differential privacy in federated learning.

For emerging industrial Internet of Things (IIoT), intelligent anomaly detection is a key step to build smart industry. Especially, explosive time-series data pose enormous challenges to the information mining and processing for modern industry. How to identify and detect the multidimensional industrial time-series anomaly is an important issue. However, most of the existing studies fail to handle with large amounts of unlabeled data, thus generating the undesirable results. In this article, we propose a novel integrated deep generative model, which is built by generative adversarial networks based on bidirectional long short-term memory and attention mechanism (AMBi-GAN). The structure for the generator and the discriminator is the bidirectional long short-term memory with attention mechanism, which can capture time-series dependence. Reconstruction loss and generation loss test the input of sample training space and random latent space. Experimental results show that the detection performance of our proposed AMBi-GAN has the potential to improve the detection accuracy of industrial multidimensional time-series anomaly toward IIoT in the era of artificial intelligence.

Drone logistics delivery is a potential booster to redefine the logistics system efficiency, which has been a new special hot research field. Among that, how to optimize drone trajectory data and find optimal delivery path is a crucial problem. However, most existing studies fail to derive the feasible trajectory data due to underestimating drone energy consumption and delivery multi-variant constraints for air transportation. In this paper, we propose a novel self-driven learning procedure, named attention-based pointer network (A-Ptr-Net) model, which can solve drone delivery trajectory optimization problem. The generated A-Ptr-Net model coupled with attention mechanism is effective on adapting to the new drone trajectory data automatically, regardless of explicit distance matrix. We go into developing the convex function constraints related to drone nonlinear energy consumption, customer demand and service time windows, which is applied on A-Ptr-Net model for optimizing the drone logistics delivery. Numerical experiments indicate that the proposed method performs significantly better than classical heuristics for drone trajectory analysis and optimization.

Recently, the visual quality evaluation of screen content images (SCIs) has become an important and timely emerging research theme. This article presents an effective and novel blind quality evaluation metric for SCIs by using stacked autoencoders (SAE) based on pictorial and textual regions. Since the SCI consists of not only the pictorial area but also the textual area, the human visual system (HVS) is not equally sensitive to their different distortion types. First, the textual and pictorial regions can be obtained by dividing an input SCI via an SCI segmentation metric. Next, we extract quality-aware features from the textual region and pictorial region, respectively. Then, two different SAEs are trained via an unsupervised approach for quality-aware features that are extracted from these two regions. After the training procedure of the SAEs, the quality-aware features can evolve into more discriminative and meaningful features. Subsequently, the evolved features and their corresponding subjective scores are input into two regressors for training. Each regressor can obtain one output predictive score. Finally, the final perceptual quality score of a test SCI is computed by these two predicted scores via a weighted model. Experimental results on two public SCI-oriented databases have revealed that the proposed scheme can compare favorably with the existing blind image quality assessment metrics.

Clinically, proper polyp localization in endoscopy images plays a vital role in the follow-up treatment (e.g., surgical planning). Deep convolutional neural networks (CNNs) provide a favoured prospect for automatic polyp segmentation and evade the limitations of visual inspection, e.g., subjectivity and overwork. However, most existing CNNs-based methods often provide unsatisfactory segmentation performance. In this paper, we propose a novel boundary constraint network, namely BCNet, for accurate polyp segmentation. The success of BCNet benefits from integrating cross-level context information and leveraging edge information. Specifically, to avoid the drawbacks caused by simple feature addition or concentration, BCNet applies a cross-layer feature integration strategy (CFIS) in fusing the features of the top-three highest layers, yielding a better performance. CFIS consists of three attention-driven cross-layer feature interaction modules (ACFIMs) and two global feature integration modules (GFIMs). ACFIM adaptively fuses the context information of the top-three highest layers via the self-attention mechanism instead of direct addition or concentration. GFIM integrates the fused information across layers with the guidance from global attention. To obtain accurate boundaries, BCNet introduces a bilateral boundary extraction module that explores the polyp and non-polyp information of the shallow layer collaboratively based on the high-level location information and boundary supervision. Through joint supervision of the polyp area and boundary, BCNet is able to get more accurate polyp masks. Experimental results on three public datasets show that the proposed BCNet outperforms seven state-of-the-art competing methods in terms of both effectiveness and generalization.

The development of Internet of Things (IoT) brings new changes to various fields. Particularly, industrial IoT (IIoT) is promoting a new round of industrial revolution. With more applications of IIoT, privacy protection issues are emerging. Especially, some common algorithms in IIoT technology, such as deep models, strongly rely on data collection, which leads to the risk of privacy disclosure. Recently, differential privacy has been used to protect user-terminal privacy in IIoT, so it is necessary to make in-depth research on this topic. In this article, we conduct a comprehensive survey on the opportunities, applications, and challenges of differential privacy in IIoT. We first review related papers on IIoT and privacy protection, respectively. Then, we focus on the metrics of industrial data privacy, and analyze the contradiction between data utilization for deep models and individual privacy protection. Several valuable problems are summarized and new research ideas are put forward. In conclusion, this survey is dedicated to complete comprehensive summary and lay foundation for the follow-up research on industrial differential privacy.

The continuous development of industry big data technology requires better computing methods to discover the data value. Information forecast, as an important part of data mining technology, has achieved excellent applications in some industries. However, the existing deviation and redundancy in the data collected by the sensors make it difficult for some methods to accurately predict future information. This article proposes a semisupervised prediction model, which exploits the improved unsupervised clustering algorithm to establish the fuzzy partition function, and then utilize the neural network model to build the information prediction function. The main purpose of this article is to effectively solve the time analysis of massive industry data. In the experimental part, we built a data platform on Spark, and used some marine environmental factor datasets and UCI public datasets as analysis objects. Meanwhile, we analyzed the results of the proposed method compared with other traditional methods, and the running performance on the Spark platform. The results show that the proposed method achieved satisfactory prediction effect.

Visual perception refers to the process of organizing, identifying, and interpreting visual information in environmental awareness and understanding. With the rapid progress of multimedia acquisition technology, research on visual perception has been a hot topic in the academical field and industrial applications. Especially after the introduction of artificial intelligence theory, intelligent visual perception has been widely used to promote the development of industrial production towards intelligence. In this article, we review the previous research and application of visual perception in different industrial fields such as product surface defect detection, intelligent agricultural production, intelligent driving, image synthesis, and event reconstruction. The applications basically cover most of the intelligent visual perception processing technologies. Through this survey, it will provide a comprehensive reference for research on this direction. Finally, this article also summarizes the current challenges of visual perception and predicts its future development trends.

In 3-D attitude angle estimation, monocular vision-based methods are often utilized for the advantages of short-time and high efficiency. However, the limitations of these methods lie in the complexity of the algorithm and the specificity of the scene, which needs to match the characteristics of the cooperation object and the scene. In this article, we propose a fully connected attitude detection network (FADN), which combines neural network and traditional algorithms for 3-D attitude angle estimation. FADN provides a whole process from the input of a single frame image in the industrial video stream to the output of the corresponding 3-D attitude angle estimation. Benefiting from the end-to-end estimation framework, FADN avoids tedious matching algorithms and thus has certain portability. A series of comparative experiments based on the rendering software 3-D Studio Max (3d Max) have been carried out to evaluate the performance of FADN. The experimental results show that FADN has high estimation accuracy and fast running speed. At the same time, the simulation results reliably prove the feasibility of FADN, and also promote the research in real scenarios.

In diverse applications of the industrial Internet of Things (IIoT), the six degrees of freedom (6-DoF) information is essential, which determines the attitude and position of a 3-D object. Nevertheless, due to the complexity and variability of the scenarios, higher requirements are imposed on the 6-DoF estimation. Among them, occlusion is one of the knottiest problems, which causes significant performance degradation and needs to be solved urgently. Therefore, in this article, we propose a completely new and universal multibranch network (MBN) for industrial applications. Our method is based on monocular vision system and convolutional neural network (CNN) framework. First and foremost, it reduces occlusion interference by focusing on the physical area characteristics of the image. Compared with the traditional CNN-based method, it owns higher accuracy and lower estimation error under occlusion. Second, we propose five algorithms to process the predictions of the independent branches, further effectively improving performance. Third, we optimize the marker to solve the inequality problem in attitude angle estimation. Furthermore, we design and conduct a series of experiments, and the experimental results sufficiently prove the superiority of MBN.

In this paper, a competitive no-reference metric is proposed to assess the perceptive quality of screen content images (SCIs), which uses the human visual edge model and AdaBoosting neural network. Inspired by the existing theory that the edge information which reflects the visual quality of SCI is effectively captured by the human visual difference of the Gaussian (DOG) model, we compute two types of multi-scale edge maps via the DOG operator firstly. Specifically, two types of edge maps contain contour and edge information respectively. Then after locally normalizing edge maps, L -moments distribution estimation is utilized to fit their DOG coefficients, and the fitted L -moments parameters can be regarded as edge features. Finally, to obtain the final perceptive quality score, we use an AdaBoosting back-propagation neural network (ABPNN) to map the quality-aware features to the perceptual quality score of SCIs. The reason why the ABPNN is regarded as the appropriate approach for the visual quality assessment of SCIs is that we abandon the regression network with a shallow structure, try a regression network with a deep architecture, and achieve a good generalization ability. The proposed method delivers highly competitive performance and shows high consistency with the human visual system (HVS) on the public SCI-oriented databases.

Panoramic video and stereoscopic panoramic video are essential carriers of virtual reality content, so it is very crucial to establish their quality assessment models for the standardization of virtual reality industry. However, it is very challenging to evaluate the quality of the panoramic video at present. One reason is that the spatial information of the panoramic video is warped due to the projection process, and the conventional video quality assessment (VQA) method is difficult to deal with this problem. Another reason is that the traditional VQA method is problematic to capture the complex global time information in the panoramic video. In response to the above questions, this paper presents an end-to-end neural network model to evaluate the quality of panoramic video and stereoscopic panoramic video. Compared to other panoramic video quality assessment methods, our proposed method combines spherical convolutional neural networks (CNN) and non-local neural networks, which can effectively extract complex spatiotemporal information of the panoramic video. We evaluate the method in two databases, VRQ-TJU and VR-VQA48. Experiments show the effectiveness of different modules in our method, and our method outperforms state-of-the-art other related methods.

The deepening of ocean measurement work requires higher transmission bandwidth and information calculation efficiency, which provides an opportunity for fog computing. Compared with cloud computing, fog computing shows distribution because it concentrates data processing and application on devices at the edge of the network. In this article, the Ocean of Things (OoT) framework is designed for marine environment monitoring based on the Internet of Things technology. The OoT is divided into three layers: 1) data acquisition layer; 2) fog layer; and 3) cloud layer. In the fog layer, in order to complete the quality control of the sensor measurement data, we use the numerical gradient-based method to process the original acquisition data. An improved D-S algorithm is designed for multisensor information fusion, reducing the data capacity and improving data quality. In the cloud layer, we build ocean information change models based on the fog layer data to predict the dynamic ocean environment. The designed fog layer is evaluated based on marine multisensor information. The results have shown that fog-based multisensor data processing shows low time consumption and high reliability. Moreover, this article uses real temperature data sets to evaluate the prediction accuracy of the cloud model. Finally, we tested the performance of the designed OoT framework with multiple data sets. The simulation results show that the framework can improve the efficiency of data utilization at sea and improve the efficiency of information utilization.

In the era of industrial 4.0, industrial Internet of Things (IIoT) has brought essential changes to human society. For IIoT, communication in network can be defined as the basic condition for further development and integrated information exchange. In this way, cached-enabled heterogeneous industrial network is necessary to be optimized. In this paper, we consider the optimal geographical placement of contents in cache-enabled heterogeneous networks to minimize the total missing probability. And the probability represents that typical user cannot find requested file in the nearby base stations (BSs). In contract to existing works which only concern content placement, we jointly optimize content placement at BSs and activation densities of BSs of different tiers subject to the cache size limits and the constraint on the BSs energy consumption cost. In addition, the user distribution in this work is modeled by a homogeneous Poisson Point Process. We prove that the original optimization problem can be transformed to a convex problem. The convexity of the optimization problem allows us to apply the KKT conditions to derive useful analytical results of the optimal solution. Based on this, we propose a low-complexity near-optimal algorithm to find the approximated content placement probabilities. We further extend the optimization to heterogeneous networks with the user distribution modeled by the modified Cluster Process. Extensive simulation results show the superior performance of joint optimization of content placement and BSs activation densities compared to only optimizing content placement.

With the wide application of stereoscopic video technology, the quality of stereoscopic video has attracted people's attention. Objective stereoscopic video quality assessment (SVQA) is highly challenging, but essential, particularly the no-reference (NR) SVQA method, where reference information is not needed and a large number of samples are required for training and testing sets. However, as far as we know, there are only a few samples in the established stereo video database, which is unsuitable for NR quality assessment and seriously hampers the development of NR-SVQA method. For these difficulties that we encountered, we carry out a comprehensive subjective evaluation of stereoscopic video quality in our newly established TJU-SVQA databases that contain various contents, mixed resolution coding and symmetrically/asymmetrically distorted stereoscopic videos. Furthermore, we propose a new inter-frame cross map to predict the objective quality scores. We compare and analyze the performance of several state-of-the-art 2D and 3D quality evaluation methods on our new databases. The experimental results on our established databases and a public database demonstrate that the proposed method can robustly predict the quality of stereoscopic videos.

An image is compressed or stretched during the multidevice displaying, which will have a very big impact on perception quality. In order to solve this problem, a variety of image retargeting methods have been proposed for the retargeting process. However, how to evaluate the results of different image retargeting is a very critical issue. In various application systems, the subjective evaluation method cannot be applied on a large scale. So we put this problem in the accurate objective-quality evaluation. Currently, most of the image retargeting quality assessment algorithms use simple regression methods as the last step to obtain the evaluation result, which are not corresponding with the perception simulation in the human vision system (HVS). In this paper, a deep quality evaluator for image retargeting based on the segmented stacked AutoEnCoder (SAE) is proposed. Through the help of regularization, the designed deep learning framework can solve the overfitting problem. The main contributions in this framework are to simulate the perception of retargeted images in HVS. Especially, it trains two separated SAE models based on geometrical shape and content matching. Then, the weighting schemes can be used to combine the obtained scores from two models. Experimental results in three well-known databases show that our method can achieve better performance than traditional methods in evaluating different image retargeting results.

Due to the wide application of stereoscopic display technology, stereoscopic video quality assessment (SVQA) is facing great challenges, but worthwhile. Stereoscopic videos contain a great deal of information, which involves not only the spatial domain but also the spatio-temporal domain. Motion in stereoscopic video plays a critical role in quality perception, while the existing SVQA methods rarely refer to motion factors, and the performance of these methods is restrained. In this article, a novel SVQA based on motion perception is introduced and its performance is superior to that of existing excellent methods. Particularly, to appropriately reduce the amount of data processing, we extract the key-frame sequences according to the influence of movement intensity on binocular visual quality perception. The binocular summation and difference operations are implemented on extracted sequences, and then spatial texture and spatio-temporal texture statistic measurement are extracted simultaneously with local binary patterns from three orthogonal planes (LBP-TOP). Experiments are implemented on two publicly available databases and the results demonstrate the effectiveness and robustness of our algorithm for various categories of distortion stereoscopic video pairs.

Aircraft tracking is a significant technology for military reconnaissance, but there is no efficient algorithm to solve this particular problem. Recently, research based on deep learning for object tracking has developed rapidly, and the performance is greatly improved compared to the traditional methods, so the authors refer to relevant work and make an improvement on the previous research to improve the performance on aircraft tracking. They first learn the idea from region‐based fully convolutional networks to perform detection on each frame of video. To avoid the target drift due to the failure of object detection on a certain frame, then they employ Kalman filter (KF) and extended KF together to predict the moving trajectory of the target. Beyond that, this method can confine the valid range based on the size of a target object, which increases the speed of detection. This approach can also correct the bounding box on adjacent frames. The steps are not complicated but have an excellent performance. Through the experiment, it is clear that the proposed method is reasonable and more precise.

Blind or visually impaired people face special difficulties in daily life. With the advances in vision sensors and computer vision, the design of wearable vision assistance system is promising. In order to improve the life quality of the visually impaired group, a wearable system is proposed in this paper. Typically the performance of visual sensors is affected by a variety of complex factors in practice, resulting in a large number of noise and distortion. In this paper, we will creatively leverage image quality evaluation to select the captured images through vision sensors, which can ensure the input quality of scenes for the final identification system. First, we use binocular vision sensors to capture images in a fixed frequency and choose the informative ones based on stereo image quality assessment. Then the captured images will be sent to cloud for further computing. Specially, the detection and automatic result will be done for all the received images. Convolutional neural network based on big data will be used in this step. According to image analysis, the cloud computing can return the requested information for users, which can help them make a more reasonable decision in further action. Simulations and experiments show that the proposed method can solve the problem effectively. In addition, statistical results also demonstrate that wearable vision system can make visually impaired group more satisfied in visual needed situations.

With the development of the Internet-of-Things (IoT) industry, more and more fields are involved such as multimedia data. Currently, users rely on videos and images with high data volume, so it has brought more challenges for wireless communication and transmission. For multimedia data, it is obviously different from traditional communication data. So new method is required to solve the problem of high data volume in communication. The proactive content caching and the unmanned aerial vehicle (UAV) relaying techniques are deployed over IoT network, enabling the maximum throughput for the served IoT devices. Even though these two existing technologies are important to solve the problem of throughput, there are still other challenges for efficiently improving the system throughput. We mainly study the cache-enabled UAV to maximize throughput among IoT devices in the IoT with the placement of content caching and UAV location. Especially, we divide the joint optimization problem into two parts. First, the UAV deployment problem is decomposed into vertical and horizontal dimensions to ensure the optimal deployment height and 2-D position. The enumeration search method is employed to obtain the 2-D position. Then, we also formulate a concave problem for probabilistic caching placement. Experimental results have indicated that the cache-enabled UAV scheme can obtain a better throughput, which can bring new approach for multimedia data throughput maximization in IoT system.

For cyber-physical industrial networks, more and more multimedia data is faced in high-speed information transmission. The explosive data brings more challenges to the architecture of modern industrial networks. In this way, cache resource allocation technology is necessary for practical applications. In order to design reasonable caching framework, how to predict the multimedia data request is an important issue. In order to keep efficient and reliable data transmission in wireless industrial networks, security design is also critical for existing cache resource allocation. Based on previous works, some promising technologies have been applied, such as heterogeneous ultradense networks, wireless edge caching, and web content popularity prediction. In this paper, we summarize these promising technologies and provide a useful guidance for security design in cyber-physical cache resource allocation system. Specially, we can divide the proposed method into three main steps. First of all, a spatio-temporal multimedia content prediction based on long short-term memory is proposed for accurate prediction on multimedia data request. After that, we make use of Zipf fitting for caching model. At last, the caching optimization considering security is put forward in this paper. Experimental results show the satisfied performance of our proposed algorithm and it has obvious potential application value in cyber-physical industrial networks with cache resource allocation technology.

Most previous 2-D and 3-D image quality evaluators were based on shallow architectures. Their shallow architectures cannot model phenomenon occurring in human visual systems sufficiently. Disparities between left and right views have been importantly used for 3-D image quality assessment (IQA), but single disparity, depth, or cyclopean maps made from the disparities cannot thoroughly reflect the depth sense. In this paper, we propose a blind stereoscopic image quality evaluator using stacked auto-encoders (SAE). The proposed method is based on two theories on initial stages of stereopsis. One is cyclopean channel theory and the other is binocular summation/difference channels theory. Especially, a cyclopean image that models the former theory is computed to consider binocular suppression, whereas summation and difference images that model the latter one are utilized to treat the depth sense. We train three SAEs for quality-aware features from the three images in an unsupervised manner. Through the SAEs, the features are transformed into more meaningful features, and they are used to train two regressors. The regressors are used to obtain a final predicted score. Experimental results conducted on popular 3-D IQA databases prove that the proposed algorithm outperforms state-of-the-art 3-D IQA methods.

With the rapid development of Internet of Things and data interactive processing technologies, the application of Internet of Things in marine field is emerging. In the face of big oceanic data from various sensors, a model of multi-sensor interaction and data processing is proposed in this paper. On the basis of this model, an oceanic data processing algorithm based on back propagation neural network data fitting is proposed, which can be used for various types of oceanic data. In order to make the data more intuitive and improve the efficiency of data processing, we design a basic model of oceanic data visualization concluding the graphical display and processing. In this model, the standard file will be generated finally through the effective data processing. Through the comparison and analysis of experimental results, it's shown that the algorithm achieves better optimization. And the model of data interaction and visualization are suitable and reasonable in practical application.

In the field of big data applications, image information is widely used. The value density of information utilization in big data is very low, and how to extract useful information quickly is very important. So we should transform the unstructured image data source into a form that can be analyzed. In this paper, we proposed a fast image retrieval method which designed for big data. First of all, the feature extraction method is necessary and the feature vectors can be obtained for every image. Then, it is the most important step for us to encode the image feature vectors and make them into database, which can optimize the feature structure. Finally, the corresponding similarity matching is used to determined the retrieval results. There are three main contributions for image retrieval in this paper. New feature extraction method, reasonable elements ranking, and appropriate distance metric can improve the algorithm performance. Experiments show that our method has a great improvement in the effective performance of feature extraction and can also get better search matching results.