Video stitching poses a fundamental challenge: while video frames exhibit strong spatiotemporal coupling, prevailing decoupled paradigms artificially separate spatial and temporal information, leading to limited precision and severe efficiency bottlenecks. Consequently, achieving a joint spatiotemporal optimization remains a critical, unresolved objective in this field. To overcome this, we propose an unsupervised video stitching framework that fundamentally reconceptualizes the task as a joint spatiotemporal state estimation problem, driven by temporal propagation and a dynamic memory mechanism. Building upon spatiotemporally decoupled multi-view inputs, we design a Spatially-Aware Gated Recurrent Unit (SA-GRU) structure that mines intrinsic spatiotemporal feature correlations to establish cross-frame temporal propagation and spatiotemporal mapping, thereby compensating for missing temporal information and improving alignment. To overcome the perceptual constraints of sliding windows, we introduce a Temporally-Gated Recurrent Unit (T-GRU) structure integrated with a Spatiotemporal Attention Fusion (STA-Fusion) module, which adaptively integrates long-term historical context with current spatiotemporal constraints to smooth stitching trajectories and enable long-term stabilization with a minimal memory footprint. Evaluations on the Stabstitch-D dataset demonstrate that our method outperforms existing approaches in alignment and geometric fidelity, achieving a PSNR of 31.18, an SSIM of 0.907, and a distortion measure of 0.011. Compared to traditional sliding-window approaches, our framework drastically reduces the memory footprint.

Few-shot Action Recognition (FSAR) aims to recognize novel actions from only a few labeled examples, posing challenges due to limited supervision and complex temporal dynamics. Existing methods often adopt a unified motion modeling strategy for both short- and long-term dynamics, overlooking the need to adapt motion pattern extraction to the specific temporal properties inherent to different timescales. This forces models to hedge against multi-scale relevance through exhaustive searches over temporal tuples, followed by heavy spatio-temporal fusion, which substantially increases parameters and computation and ultimately limits efficiency. To this end, we propose the efficient Temporal Consistency and Variation-Guided Spatio-Temporal Aggregation Network (TCV-STA), which comprises four key components: the Temporal Consistency Module (TCM), the Temporal Variation Module (TVM), the Spatio-Temporal Aggregation attention (STA), and the Shifted Window Temporal Attention (SWTA). The TCM captures stable motion patterns to suppress short-term perturbations and enhance temporal consistency for robust motion representation, while the TVM models dynamic motion patterns to highlight long-term variations that improve inter-class discriminability and facilitate intra-class alignment. Built upon these complementary motion cues, the STA selectively aggregates spatial and temporal representations under the guidance of the learned stable and dynamic motion patterns, avoiding global dense fusion. Finally, to address the limited receptive field and discontinuous modeling caused by frame grouping in TCM and TVM, we adapt a SWTA to capture longer-range temporal dependencies and ensure smooth transitions across subaction segments for few-shot action recognition. Experiments demonstrate that TCV-STA achieves competitive accuracy across four widely-used FSAR benchmarks while reducing parameters by up to 27.9% and computational cost by 21.3%, striking a favorable balance between accuracy and efficiency for deployment in resource-constrained scenarios.

Collaborative edge computing (CEC) enables multiple edge servers (ESs) to cooperatively process computation-intensive tasks generated by resource-constrained industrial internet of things devices. A challenge arises when offloading similar tasks from devices to ESs triggers duplicate computation, resulting in severe resource waste. To address this, computation reuse has recently been proposed to reduce response delay and energy consumption by caching task results at the edge. However, existing studies either overlook the time validity of task results or ignore the result retrieval cost, resulting in decreased practicality in real-world scenarios. In this paper, we propose a computation reuse-enabled CEC framework, where reusable task results are cached in edge networks and can be accessed if they are within the validity and the similarity of task inputs exceeds the preset thresholds. To minimize the long-term system cost comprising weighted task delay and energy consumption under the resource constraints, we formulate a joint task offloading, resource allocation, result retrieval and result caching (T3R) problem. Then, we propose a diffusion model-based graph reinforcement learning (DMGRL) algorithm to fully exploit the graph structural information of the edge network and optimize T3R policy. Extensive experimental results demonstrate that compared to baseline algorithms, the DMGRL algorithm achieves 37.4% maximum cost reduction and faster convergence speed.

Most of the existing methods to evaluate the quality of panoramic content mainly focus on studying the quality evaluation of static panoramic images, rather than the more widely used dynamic panoramic videos. Also, the few panoramic video quality metrics that are available have obvious weaknesses in terms of robustness. To this end, we propose a robust quality evaluator for panoramic videos (RQE-PV). First, a viewport prediction module is proposed by developing a multi-step fixation screening mechanism to simulate the characteristics of limited visual range and excavate the process of human eye movement. Further, both the temporal and spatial features are explored and fused for quality prediction. The superior robustness of the proposed method has been demonstrated on two public panoramic video databases.

Unmanned aerial vehicle (UAV) can serve as aerial base station to quickly restore the communication coverage of the disaster area, but finite energy poses a crucial challenge to UAV emergency communications. To maximize the average energy efficiency of UAV emergency communications, we propose the energy-efficient spectrum allocation and deployment (ESAD) scheme, which covers all disaster users and guarantees the quality of service (QoS) for users by deploying multiple UAVs. Based on the QoS requirement of user and graph coloring method, we propose the interference avoidance algorithm, which avoids interference among users served by the same UAV and interference among UAVs through user spectrum resource allocation and UAV spectrum management, respectively. Then, the ESAD scheme is proposed to achieve the maximum average energy efficiency of UAV while covering all disaster users. Simulation results show that compared with traditional schemes, the proposed scheme effectively reduces the number of deployed UAVs and improves the average energy efficiency of UAV emergency communications.

Abstract Background RNA methylation (RM) regulates gene expression regulation, RNA stability, and protein translation. Accurate prediction of RM modification sites is essential for understanding their biological functions. However, existing wet-lab detection techniques face challenges including operational complexity and high costs. Deep learning (DL) methods have been applied to this task. However, existing methods show performance degradation with smaller training datasets. For instance, the Bidirectional Gated Recurrent Unit (BGRU) demonstrates substantial performance degradation. Contrastive Learning Network (CNN) can extract local pattern features but learns overly specific patterns with sample-limited data, resulting in poor feature generalization. Bidirectional Long Short-Term Memory (BiLSTM) excels at modeling long-range dependencies but cannot sufficiently learn gating mechanism parameters to capture effective sequence representations with limited samples. Transformer processes sequences in parallel and captures global dependencies through self-attention, but its quadratic computational complexity and large parameter count make it prone to overfitting on small datasets. Current DL methods show reduced performance when training data is limited. Results This study proposes a Multi-view Contrastive Learning with CNN-BiLSTM-Attention (MCLCBA) framework for RM modification site prediction. The multi-view approach comprises a primary view and auxiliary view, where the primary view utilizes DNA Bidirectional Encoder Representations from Transformers (DNABERT) to extract sequence contextual features, and the auxiliary view employs Chaos Game Representation (CGR) to extract structural features. Feature extraction includes four components: data augmentation, multi-view encoders, projection heads, and contrastive loss functions. By implementing dual differential data augmentation strategies and constructing multi-view network architectures for feature processing and fusion, the model learns discriminative feature representations invariant to data augmentation through maximizing positive sample similarity while minimizing negative sample similarity. This effectively addresses sample-limited feature learning scenarios. Experimental results on the sample-limited m 7 G dataset demonstrate that MCLCBA achieves AUROC and AUPRC of 85.64% and 86.94%, respectively, improving upon existing methods by 5–6% in both metrics. Conclusions Through multi-view contrastive learning, MCLCBA provides an approach for RM sites under sample-limited scenarios.

Edge video analytics enables agile responses of machine-centric applications by streaming videos from end devices to edge servers (ESs) for resource-intensive deep neural network (DNN) inference. Quality of Inference (QoI), reflected by end-to-end analytics delay and inference accuracy, is crucial for the high-quality real-time decision-making. Due to the limited ES resources and dynamic network conditions, video configuration adaptation and fine-grained resource allocation are necessary to enhance the QoI of video streams, which involves a delicate balance between delay and accuracy. In this article, we propose an edge-enabled multivideo analytics framework, in which performing DNN inference relies on heterogeneous resources, including CPU, GPU, and memory. Considering the different impacts of heterogeneous resources on QoI and double-queue backlogs, we formulate the joint video configuration adaptation, CPU-GPU resource allocation, and batch size selection (JCCGB) problem based on semi-Markov decision process to maximize the long-term average QoI. Then, Lyapunov optimization is applied to transform the original problem into one that minimizes the Lyapunov drift-plus-penalty upper bound, thereby ensuring the stability of both the transmission and computation queues. To tackle the potential multimodality of the optimal configuration adaptation and resource allocation policy, we propose the diffusion-deep-reinforcement-learning-based JCCGB (DD-JCCGB) scheme. This approach effectively enhances the policy performance and accelerates the training process. Experiments driven by real-world network traces demonstrate that the DD-JCCGB algorithm improves the long-term average QoI and outperforms baseline schemes.

Achieving high-precision interference recognition for autonomous aerial vehicle (AAV) swarm communications in complex electromagnetic environments is of great significance for developing efficient anti-interference schemes and improving the security of AAV swarm communication. Although deep learning-based interference recognition methods for AAV swarm communication can achieve good recognition performance, they usually rely on a large number of high-quality labeled samples and only consider a single representation of the interference signal as input. This leads to low accuracy and poor robustness of interference recognition in scenarios with changing electromagnetic environments or insufficient samples. To address these issues, this article proposes a data-knowledge-driven method for AAV swarm communication interference recognition. A dual-input interference recognition network (DIRNet) with a few model parameters is designed, incorporating deep features extracted based on the data-driven approach and manual features designed based on expert knowledge. Simulation experiments are conducted under sufficient-sample, cross-environment, and insufficient-sample scenarios. The results demonstrate that the proposed AAV swarm communication interference recognition method not only improves the recognition accuracy of interference signals under these conditions. Moreover, it also shows good robustness in complex dynamic environments.

The deployment of multi-stream fusion strategy on behavioral recognition from skeletal data can extract complementary features from different information streams and improve the recognition accuracy, but suffers from high model complexity and a large number of parameters. Besides, existing multi-stream methods using a fixed adjacency matrix homogenizes the model’s discrimination process across diverse actions, causing reduction of the actual lift for the multi-stream model. Finally, attention mechanisms are commonly applied to the multi-dimensional features, including spatial, temporal and channel dimensions. But their attention scores are typically fused in a concatenated manner, leading to the ignorance of the interrelation between joints in complex actions. To alleviate these issues, the Front-Rear dual Fusion Graph Convolutional Network (FRF-GCN) is proposed to provide a lightweight model based on skeletal data. Targeted adjacency matrices are also designed for different front fusion streams, allowing the model to focus on actions of varying magnitudes. Simultaneously, the mechanism of Spatial-Temporal-Channel Parallel Attention (STC-P), which processes attention in parallel and places greater emphasis on useful information, is proposed to further improve model’s performance. FRF-GCN demonstrates significant competitiveness compared to the current state-of-the-art methods on the NTU RGB+D, NTU RGB+D 120 and Kinetics-Skeleton 400 datasets. Our code is available at: https://github.com/sunbeam-kkt/FRF-GCN-master.

Obtaining ground truth annotations for 3D pose estimation (3D HPE) typically depends on motion capture equipment (Mocap), which is not only expensive but impractical for widespread deployment. In contrast, triangulation can reconstruct 3D poses solely from multi-view 2D poses with known camera parameters, eliminating the need for Mocap. However, inherent noise in 2D pose predictions introduces uncertainties, compromising the reliability of the results. To obtain more reliable annotations with noisy input, we introduce an annotation approach for the 3D HPE task, driven by prior knowledge of the skeletal configuration. We split our approach into two steps: first a parametric model is designed to enhance confidence predictions. Then, a differentiable weighted triangulation is employed to estimate the 3D pose in world space, leveraging the predicted confidence scores as weights. The pipeline is trained using a bone length loss. Moreover, we collect a multi-view dataset for 3D HPE and annotate it using our proposed annotation tool. This dataset is characterized by more construction scenarios, including heavier occlusion cases, diverse viewing directions, and the integration of various optical sensors, setting it apart from existing datasets. Experiments on both our dataset and Human3.6M demonstrate the effectiveness of our method.

Abstract Background Epi-transcriptome regulation through post-transcriptional RNA modifications is essential for all RNA types. Precise recognition of RNA modifications is critical for understanding their functions and regulatory mechanisms. However, wet experimental methods are often costly and time-consuming, limiting their wide range of applications. Therefore, recent research has focused on developing computational methods, particularly deep learning (DL). Bidirectional long short-term memory (BiLSTM), convolutional neural network (CNN), and the transformer have demonstrated achievements in modification site prediction. However, BiLSTM cannot achieve parallel computation, leading to a long training time, CNN cannot learn the dependencies of the long distance of the sequence, and the Transformer lacks information interaction with sequences at different scales. This insight underscores the necessity for continued research and development in natural language processing (NLP) and DL to devise an enhanced prediction framework that can effectively address the challenges presented. Results This study presents a multi-scale self- and cross-attention network (MSCAN) to identify the RNA methylation site using an NLP and DL way. Experiment results on twelve RNA modification sites (m6A, m1A, m5C, m5U, m6Am, m7G, Ψ, I, Am, Cm, Gm, and Um) reveal that the area under the receiver operating characteristic of MSCAN obtains respectively 98.34%, 85.41%, 97.29%, 96.74%, 99.04%, 79.94%, 76.22%, 65.69%, 92.92%, 92.03%, 95.77%, 89.66%, which is better than the state-of-the-art prediction model. This indicates that the model has strong generalization capabilities. Furthermore, MSCAN reveals a strong association among different types of RNA modifications from an experimental perspective. A user-friendly web server for predicting twelve widely occurring human RNA modification sites (m6A, m1A, m5C, m5U, m6Am, m7G, Ψ, I, Am, Cm, Gm, and Um) is available at http://47.242.23.141/MSCAN/index.php . Conclusions A predictor framework has been developed through binary classification to predict RNA methylation sites.

The computing process of tasks in Industrial Internet of Things (IIoT) environments is becoming increasingly complex due to the development of 5G and artificial intelligence. Leading devices are increasingly relying on heterogeneous platforms that integrate different types of processing units, such as CPUs, GPUs, and other resources, to meet the requirements of delay-sensitive and computing-intensive tasks. However, compared to conventional general-proposed CPU computing, CPU–GPU heterogeneous computing typically involves three processes, i.e., task preprocessing, hybrid computing, and result aggregation. These processes are associated with particular computing resources, which increases the difficulty of task offloading and computing resource allocation under task-specific resource and delay constraints. In this article, we first propose a three-stage heterogeneous computing (TSHC) model to practically describe the computing process of parallelizable tasks. Considering the heterogeneous computing resources, device queue backlogs, and collaboration of multiple edge servers, the joint task offloading and heterogeneous resource allocation (JCOHRA) problem is formulated to minimize the long-term average delay of tasks. Then, the Lyapunov optimization method is adopted to simplify the long-term queue stability constraint to a single-slot dynamic optimization problem, which is then modeled as a Markov decision process (MDP). Owing to the tight coupling between decision variables and enormous action space, we propose the multihead proximal policy optimization (MH-PPO)-based JCOHRA algorithm, which is enabled by elaborate constraint transformation and reward function design. Simulation results demonstrate that the JCOHRA scheme achieves better performance than baseline methods in minimizing the long-term average delay of tasks.

The Internet of Medical Things (IoMT) and fog computing facilitate the shift from hospital-based medical examinations to real-time electronic healthcare. A novel transmit scheme for fog computing-enabled IoMT is proposed in this article to address real-time monitoring needs, utilizing uplink and downlink rate splitting (RS) techniques. Fog computing enables offloading partial computation tasks to the edge server while processing the remaining tasks locally to reduce computing time. Uplink and downlink RS techniques offer flexible co-channel interference management to minimize offloading and feedback durations. The primary objective is to minimize the overall time cost encompassing task offloading, data processing, and result feedback. For this purpose, decisions on task offloading, computing resource allocation, uplink beamforming, downlink beamforming, and common rate allocation are jointly designed. However, this approach leads to a nonconvex optimization problem. Several auxiliary variables are introduced to handle this, and accurate surrogates are constructed to smooth the logarithmic transmit rate. Additionally, closed-form expressions are derived for optimal computing resource allocation per user. Based on these formulations, computing resource allocation and energy consumption are transformed into a convex constraint set. Finally, an alternating optimization algorithm is developed to update auxiliary and intrinsic variables iteratively. Simulation results demonstrate the effectiveness of the proposed transmit scheme and algorithm, showing substantial improvements over several baseline methods.

Quality assessment for stitched panoramic images (SPIQA) is of great significance for the stitching algorithm optimization. By contrast, this task is much more challenging and arduous than traditional IQA task due to the high resolution of stitched panoramic images and the particularity and complexity of stitching distortions. For this task, we propose an effective method based on patch registration and bidimensional feature aggregation (PRBFA). First, inspired by the attention mechanism of the human visual system and the limited range of human vision, a soft patch segmentation and selection method is presented to determine the key patches in panoramic images to participate in the following patch matching and feature alignment stages, achieving patch registration between the panoramic image and the corresponding constituent images. Further, to fully simulate the human visual perception process from local viewport to panorama, the feature exploration is successively performed from local to global, which is also adaptive to the complexity of the distortions in stitched panoramic images. For performance testification, extensive experiments are conducted on the publicly released SPIQA database, the results of which prove the performance superiority of the PRBFA method.

Underwater magnetic induction (MI)-assisted acoustic cooperative multiple-input-multiple-output (MIMO) technology enables reliable communication with high throughput over long transmission distances. The combination of such as technology and underwater wireless sensor networks (UWSNs) is initiating a novel underwater Internet of Things (IoT paradigm): underwater MI-assisted acoustic cooperative MIMO WSNs. The MIMO UWSNs meets the requirements of reliable communication networks connecting underwater sensor nodes and remote surface base station (BS) for the next generation of smart ocean applications. The objective of the paper is to obtain the cooperative MIMO formation scheme in these networks for minimizing the nodes' energy consumption, simultaneously ensuring the connectivity of nodes and surface BS, and improving the coverage of networks. This paper proposes a scaly cooperative MIMO formation (SCMF) scheme based on the greedy algorithm to solve the constrained optimization problem, which is a two-phase method. In the first phase, the members of the cooperative MIMO are preliminarily determined while ensuring that there is only a single coverage hole in each iteration. In the second phase, a new master node (MN) is selected and the transmission power is determined to reduce energy consumption. Simulation results show that our proposed scheme not only fills the gap that the existing algorithm does not consider the network coverage, but also confirms that it can achieve significant energy saving and prolongs the network lifetime considerably.

The current learning pipelines for robotics manipulation infer movement primitives sequentially along the temporal-evolving axis, which can result in an accumulation of prediction errors and subsequently cause the visual observations to fall out of the training distribution. This paper proposes a novel hierarchical behavior cloning approach which tries to dissociate standard behaviour cloning (BC) pipeline to two stages. The intuition of this approach is to eliminate accumu-lation errors using a fixed spatial representation. At first stage, a high-level planner will be employed to translate the initial observation of the scene into task-specific spatial waypoints. Then, a low-level robotic path planner takes over the task of guiding the robot by executing a set of pre-defined elementary movements or actions known as primitives, with the goal of reaching the previously predicted waypoints. Our hierarchical keypoints-based paradigm aims to simplify existing temporal-evolving approach to a more simple way: directly spatialize the whole sequential primitives as a set of 8D waypoints only from the very first observation. Plentiful experiments demon-strate that our paradigm can achieve comparable results with Reinforcement Learning (RL) and outperforms existing offline BC approaches, with only a single-shot inference from the initial observation. Code and models are available at: https://github.com/KevinRiou22/spatial-fixing-il

Panoramic image quality assessment (PIQA) is crucial to the successful application of technologies that can provide immersive visual experience. Stitching distortions are one of the main types of distortions that result in panoramic image degradation. However, most existing PIQA methods are general-purpose ones, which ignore the special characteristics of the stitching distortions caused by imperfect stitching algorithms. This results in unsatisfactory performance. To this end, we propose an effective stitched PIQA method, which consists of an imaginary reference generation (IRG) module and a hierarchical quality prediction (HQP) module. Among them, the IRG module is proposed to mimic the capability of the human visual system in imagining the raw version in the face of a degraded image. For the IRG module learning, we construct a large-scale database. The HQP module is presented to adapt to the particularity and complexity of stitching distortions, which is achieved by the pyramid feature aggregation. Extensive experiments and comparisons have been performed on the stitched PIQA database and the experimental results demonstrate the superiority of the proposed method in evaluating the quality of stitched panoramic images.

Edge computing (EC) is a promising technology to support a variety of performance-sensitive intelligent applications, especially in the Industrial Internet of Things (IIoT). The sensing-data-driven applications whose task processing requires sensing data from various sensors are typical applications in IIoT systems. The placement of caching and computing edge service functions for such applications is vital to ensure system performance and resource utilization in EC-enabled IIoT systems. Therefore, this paper investigates the joint caching and computing edge service placement (JCCESP) for multiple sensing-data-driven IIoT applications in an EC-enabled IIoT system. The JCCESP problem is formulated as a Markov Decision Process (MDP). Then, a deep reinforcement learning (DRL)-based approach is proposed to address the challenges like limited prior knowledge and the heterogeneity of such IIoT systems. Under such an approach, the policy network of the DRL agent is constructed based on an encoder-decoder model to tackle various applications requiring different numbers of service functions. A REINFORCE-based method is further employed to train the policy network. Simulation results indicate that the performances achieved by our proposed approach can converge after training and are significantly superior to benchmarks.

In public safety networks (PSNs), it is an important issue how reliable data transmission recovers when some base stations (BSs) are damaged by natural disasters. An unmanned aerial vehicle (UAV) is used as a temporal relay station to transmit data of ground users (GUs) to an undamaged BS. In this paper, we consider a swarm of UAVs and introduce the following three roles for its management: (1) Relay UAVs (RUs) sacrifice their coverage capabilities to preserve the network connectivity; (2) Air BS UAVs (BUs) perform a covering task; (3) Standby UAVs (SUs) remain inactive. Then, we formulate an optimal coverage problem where we assign a role to each UAV to maximize the number of GUs that can transmit their data to the undamaged BS. First, we transform the problem into an exact potential game (EPG) whose utility function is designed based on the number of GUs served by each UAV. Next, we propose a learning algorithm to obtain an optimal role assignment and utilize the Fiedler eigenvalue, which represents the algebraic connectivity of the network topology of the swarm, to update the strategy selection probabilities. Finally, by simulation, it is shown that the proposed algorithm can strike a better balance between coverage and connectivity preservation than other benchmark algorithms.

Abstract Background Recent research recommends that epi-transcriptome regulation through post-transcriptional RNA modifications is essential for all sorts of RNA. Exact identification of RNA modification is vital for understanding their purposes and regulatory mechanisms. However, traditional experimental methods of identifying RNA modification sites are relatively complicated, time-consuming, and laborious. Machine learning approaches have been applied in the procedures of RNA sequence features extraction and classification in a computational way, which may supplement experimental approaches more efficiently. Recently, convolutional neural network (CNN) and long short-term memory (LSTM) have been demonstrated achievements in modification site prediction on account of their powerful functions in representation learning. However, CNN can learn the local response from the spatial data but cannot learn sequential correlations. And LSTM is specialized for sequential modeling and can access both the contextual representation but lacks spatial data extraction compared with CNN. There is strong motivation to construct a prediction framework using natural language processing (NLP), deep learning (DL) for these reasons. Results This study presents an ensemble multiscale deep learning predictor (EMDLP) to identify RNA methylation sites in an NLP and DL way. It organically combines the dilated convolution and Bidirectional LSTM (BiLSTM), which helps to take better advantage of the local and global information for site prediction. The first step of EMDLP is to represent the RNA sequences in an NLP way. Thus, three encodings, e.g., RNA word embedding, One-hot encoding, and RGloVe, which is an improved learning method of word vector representation based on GloVe, are adopted to decipher sites from the viewpoints of the local and global information. Then, a dilated convolutional Bidirectional LSTM network (DCB) model is constructed with the dilated convolutional neural network (DCNN) followed by BiLSTM to extract potential contributing features for methylation site prediction. Finally, these three encoding methods are integrated by a soft vote to obtain better predictive performance. Experiment results on m1A and m6A reveal that the area under the receiver operating characteristic(AUROC) of EMDLP obtains respectively 95.56%, 85.24%, and outperforms the state-of-the-art models. To maximize user convenience, a user-friendly webserver for EMDLP was publicly available at http://www.labiip.net/EMDLP/index.php ( http://47.104.130.81/EMDLP/index.php ). Conclusions We developed a predictor for m1A and m6A methylation sites.

Abstract The working face is the most dangerous place of coal mines, and it is difficult (even impossible) to replenish energy by replacing batteries of sensor nodes in the working faces. This paper presents a wireless charging method for this scenario that is composed of two sub methods called mining charging and maintaining charging, respectively. Mining charging provides opportunistic charging services during the process of coal cutting through two airborne Mobile Chargers (MCs) installed on the two ends of the shearer and two portable MCs carried by shearer drivers. Maintaining charging provides opportunistic charging services for nodes in the charging radius when scraper conveyor repairmen and hydraulic support repairmen check or repair equipment, with each repairman carrying one portable MC. Simulation results show that both mining charging and maintaining charging can give energy replenishment for nodes in coal faces. When charging power of MCs is greater than or equal to 5.2 W, the first row of nodes can work sustainably. If the energy requirements of the second row of nodes are also met, the charging power of MCs cannot be less than 12 W.

Edge computing (EC) extends the ability of cloud computing to the network edge to support diverse resource-sensitive and performance-sensitive IoT applications. However, due to the limited capacity of edge servers (ESs) and the dynamic computing requirements, the system needs to dynamically update the task allocation policy according to real-time system states. Service migration is essential to ensure service continuity when implementing dynamic task allocation. Therefore, this article investigates the long-term dynamic task allocation and service migration (DTASM) problem in edge-cloud IoT systems where users’ computing requirements and mobility change over time. The DTASM problem is formulated to achieve the long-term performance of minimizing the load forwarded to the cloud while fulfilling the seamless migration constraint and the latency constraint at each time of implementing the DTASM decision. First, the DTASM problem is divided into two subproblems: 1) the user selection problem on each ES and 2) the system task allocation problem. Then, the DTASM problem is formulated as a Markov decision process (MDP) and an approach based on deep reinforcement learning (DRL) is proposed. To tackle the challenge of vast discrete action spaces for DTASM task allocation in the system with a mass of IoT users, a training architecture based on the twin-delayed deep deterministic policy gradient (DDPG) is employed. Meanwhile, each action is divided into a differentiable action for policy training and one mapped action for implementation in the IoT system. Simulation results demonstrate that the proposed DRL-based approach obtains the long-term optimal system performance compared to other benchmarks while satisfying seamless service migration.

By placing edge service functions in proximity to IoT facilities, edge computing can satisfy various IoT applications’ resource and latency requirements. Sensing-data-driven IoT applications are prevalent in IoT systems, and their task processing relies on sensing data from sensors. Therefore, to ensure the Quality of Service (QoS) of such applications in an edge-enabled IoT system, dedicated caching functions (CFs) are required to cache necessary sensing data. This article considers an edge-enabled IoT system and investigates the joint caching and computing service placement (JCCSP) problem for sensing-data-driven IoT applications. Then, deep reinforcement learning (DRL) is exploited to address the problem since it can adapt to a heterogeneous system with limited prior knowledge. In the proposed DRL-based approaches, a policy network based on the encoder–decoder model is constructed to address the issue of varying sizes of JCCSP states and actions caused by different numbers of CFs related to applications. Then, an on-policy REINFORCE-based method is adopted to train the policy network. After that an off-policy training method based on the twin-delayed (TD) deep deterministic policy gradient (DDPG) is proposed to enhance the training efficiency and experience utilization. In the proposed DDPG-based method, a weight-averaged twin-$Q$-delayed (WATQD) algorithm is introduced to reduce the bias of$Q$-value estimation. Simulation results show that our proposed DRL-based JCCSP approaches can achieve converged performance that is significantly superior to benchmarks. Moreover, compared with the original TD method, the proposed WATQD method can significantly improve the training stability.

Omnidirectional image (OI) quality assessment is crucial to facilitate the development of virtual reality (VR) related technology. In this work, a distortion discrimination assisted multi-stream network is proposed for OI quality assessment. The multi-stream architecture is constructed by generating the viewport images received by the retina at one point to simulate the characteristics of humans perceiving VR contents. Additionally, the strategy of generating several viewport image sets from one OI is proposed for data augmentation. Furthermore, the facts that the human brain has the ability for both quality assessment and distortion type distinguishment, and the process of human brain handling two tasks exists information interaction inspire us to employ an auxiliary distortion discrimination task to facilitate the quality assessment task learning. Extensive experiments conducted on two public OI databases demonstrate the superiority of the proposed method to both traditional 2D quality metrics and existing metrics specific for OIs. Moreover, utilizing the assistant task is proven to be more effective than the single task learning for OI quality evaluation. Better generalization performance is also verified to be another valuable trait of the proposed method.

Artificial intelligence technology can be used to solve some problems that are difficult to be solved by traditional wireless communication. OFDM system has been widely used at present, but the resource consumption of pilot module is very high. Therefore, this paper reviews the OFDM communication system from the point of view of signal processing. At the receiving end of OFDM system, the deep learning method is adopted to jointly optimize each communication module of the receiving end. A intelligent receiver of OFDM communication system based on the Densenet neural network structure is designed and by optimizing the structure of Densenet neural network, the intelligent receiver is realized. This method can recover information at the receiving end and avoid complex pilot operation and signal error accumulation. The simulation results show that the intelligent receiver improves the receiver performance of OFDM communication system.

This paper proposes an unmanned aerial vehicle (UAV)-aided full-duplex non-orthogonal multiple access (FD-NOMA) method to improve spectrum efficiency. Here, UAV is utilized to partially relay uplink data and achieve channel differentiation. Successive interference cancellation algorithm is used to eliminate the interference from different directions in FD-NOMA systems. Firstly, a joint optimization problem is formulated for the uplink and downlink resource allocation of transceivers and UAV relay. The receiver determination is performed using an access-priority method. Based on the results of the receiver determination, the initial power of ground users (GUs), UAV, and base station is calculated. According to the minimum sum of the uplink transmission power, the Hungarian algorithm is utilized to pair the users. Secondly, the subchannels are assigned to the paired GUs and the UAV by a message-passing algorithm. Finally, the transmission power of the GUs and the UAV is jointly fine-tuned using the proposed access control methods. Simulation results confirm that the proposed method achieves higher performance than state-of-the-art orthogonal frequency division multiple-access method in terms of spectrum efficiency, energy efficiency, and access ratio of the ground users.

In this article, we address the social-awareness property and unmanned-aerial-vehicle (UAV)-assisted information diffusion in emergency scenarios, where UAVs can disseminate alert messages to a set of terrestrial users within their coverage, and then these users can continuously disseminate the received data packets to their socially connected users in a device-to-device (D2D) multicast manner. In this regard, we have to solve both the dynamic cluster formation and spectrum sharing problems in stochastic environments, since both UAVs and terrestrial users may arrive or depart suddenly. For the cluster formation problem, considering that the data rate of a multicast cluster is determined by the member with the worst link condition, we formulate it as a many-to-one matching game and adopt the rotation-swap algorithm to maximize the expected number of users receiving the alerting messages in each time slot. For the dynamic spectrum sharing problem, aiming at eliminating the interference while minimizing the channel switching cost, we propose a dynamic hypergraph coloring approach to model the cumulative interference and maintain the mutual interference at a low level by exploring a small number of vertices, when the graph is dynamically updated, i.e., the insertion/deletion of vertex/edge. Moreover, we prove some crucial properties, including global stability, convergence, and complexity. Finally, simulation results show that our proposed approach can achieve a better tradeoff among the information diffusion speed, channel switch cost, and complexity.

As the Internet of Things (IoT) is maturing and acquires its social flavor, the Social IoT enables smart devices to build inter-thing social networks without human intervention. As a new form of smart devices, unmanned aerial vehicles (UAVs) are finding their way into IoT applications. The integrated Social Internet of Flying Things (SIoFT) can provide the social-aware UAV-assisted services. However, the broadcast nature of air-to-ground (A2G) channels makes them vulnerable to being eavesdropped by terrestrial malicious users due to their strong line-of-sight (LoS) links. In this paper, we investigate to ensure the security of A2G communications when the location information of multiple potential eavesdroppers cannot be perfectly estimated. Following the “no pain no gain” principle, the terrestrial users who reuse the UAV cellular spectrum will act as friendly jammers to realize “win-win” situation. Hence, joint trajectory design, power control, and channel allocation optimization problem is formulated to maximize the average secrecy rate of UAVs in worst case. In the first stage, we utilize the block coordinate descent method and successive convex optimization method to solve the trajectory design and power control problems in an iterative manner. In the second stage, we convert the user pairing problem into a popular matching problem with externalities. Two distributed algorithms are proposed to maintain the popular matching under dynamics. Moreover, we conduct detailed analysis of the popularity, convergence, and computational complexity. Simulation results demonstrate the superiority of our proposed method in terms of different performance metrics.

As a new Internet of Things (IoT) paradigm where smart devices work socially by exploiting social ties with adjacent devices, the Social IoT can effectively meet the real-time data sharing demands in Industrial IoT scenario, with the inter-device social relations being incentives. Besides, precaching on device level can potentially combat the backhaul capacity bottlenecks. Considering the limited cache memory, we may not use the whole capacity for caching, but leave a fraction for buffering data packets. In this article, we investigate how to maximize the quality of experience while minimizing the energy consumption. First, we design a proactive cache placement scheme for cost minimization. Next, we conceive the content sharing procedure with the framework of tripartite graph and propose a ternary stable matching algorithm to let devices self-organize the content sharing. Finally, we prove that inconspicuous manipulation with domino effect can further improve the system performance.

For the impact of the bitrate change of video streaming services according to the available bandwidth on user satisfaction, in this paper, we propose a spatial and temporal feature-based reduced reference (RR) quality assessment for rate-varying videos in wireless networks called STRQAW. First, simulating the orientation selectivity mechanism of the human visual system (HVS), the histogram of the orientation selectivity-based visual pattern in each frame is extracted as the spatial feature. The histogram similarity between the rate-varying video and the original video is computed as the spatial metric. Second, we extract the temporal variation of the DCT coefficients of the consecutive frame differences as the temporal feature. The temporal variation similarity between the rate-varying video and the original video is calculated as the temporal metric. Finally, we take into account the recency effect and assess the overall quality by combining the temporal and spatial metric. The experimental results using the Laboratory for Image and Video Engineering (LIVE) mobile video quality assessment (VQA) database show that STRQAW is consistent with the subjective assessment results, which means it reflects human subjective feelings well and it provides an evaluation for adjusting compression-coding rates in real time. STRQAW can be used to guide video application providers and network operators working towards satisfying end-user experiences.

The Internet of Things (IoT) is expected to bring great benefits to users, operators, and manufactures in different application scenarios. Given that smart objects which can exploit their own social networks and share contents via device-to-device (D2D) communications, the combined social IoT promises to collect information as well as to provide services more efficiently. This application scenario requires lower latency and higher reliability, and then we adopt D2D-based caching to reduce the downloading latency while guaranteeing the reliable delivery. To achieve this joint optimization objective, we conceive the interdependence with the framework of hierarchical bipartite graph. In this way, this combinatorial problem can be decoupled into a content sharing problem and a resource allocation problem. To solve the first one, we propose a content sharing-oriented matching algorithm with projecting social characters onto physical links. To solve the second one, we formulate this resource allocation problem as equivalent to a many-to-one matching game with peer effect. We then design a novel distributed algorithm with rotation-swap, which can converge to a stable state with limited number of iterations. Formulating the convergence procedure as another NP-hard problem, we further design a coloring-based heuristic algorithm to find a near-optimal solution. We conduct extensive simulations to demonstrate that our proposed schemes can achieve a better tradeoff between performance and complexity than other benchmarks.

Device-to-device (D2D) communications allow direct transmissions between two adjacent user devices, which can improve system performance in cellular networks. Considering full-duplex (FD) relaying outperforms half-duplex (HD) relaying in spectrum and energy efficiency, we apply the FD relaying-based D2D communication scheme in heterogeneous cellular network, which allows D2D links to underlay cellular downlink by assigning D2D transmitters as FD relays to assist cellular downlink transmissions. Although the scheme can improve the utilization of spectrum resource dramatically, the unreasonable resource sharing of D2D users will increase the inter-user interference. Therefore, in this paper, we try to optimize the throughput of D2D users on the premise of ensuring the quality of service (QoS) of cellular users. To this end, we first propose a D2D transmit power-allocation scheme and use Gale-Sharpley (GS) algorithm in matching theory to solve the resource allocation problem. Next, a Cheating algorithm based on cooperative game theory is proposed to further improve the throughput of D2D users. More importantly, due to the NP-hardness of finding the optimal solution of Cheating algorithm, we propose a heuristic algorithm based on depth first search (DFS) which using different colors to represent the different statements of D2D users to find a near-optimal solution. The simulation results show that the proposed algorithm compared with GS algorithm can significantly improve the total throughput of D2D users, and it also has lower complexity and better throughput performance against existing Cheating algorithm.

Cyber-physical Internet of things system (CPIoTS), as an evolution of Internet of things (IoT), plays a significant role in industrial area to support the interoperability and interaction of various machines (e.g., sensors, actuators, and controllers) by providing seamless connectivity with low bandwidth requirement. The fifth generation (5G) is a key enabling technology to revolutionize the future of industrial CPIoTS. In this paper, a communication framework based on 5G is presented to support the deployment of CPIoTS with a central controller. Based on this framework, multiple sensors and actuators can establish communication links with the central controller in full-duplex mode. To accommodate the signal data in the available channel band, the resource allocation problem is formulated as a mixed integer nonconvex programming problem, aiming to maximize the sum energy efficiency of CPIoTS. By introducing the transformation, we decompose the resource allocation problem into power allocation and channel allocation. Moreover, we consider an energy-efficient power allocation algorithm based on game theory and Dinkelbach's algorithm. Finally, to reduce the computational complexity, the channel allocation is modeled as a three-dimensional matching problem, and solved by iterative Hungarian method with virtual devices (IHM-VD). A comparison is performed with well-known existing algorithms to demonstrate the performance of the proposed one. The simulation results validate the efficiency of our proposed model, which significantly outperforms other benchmark algorithms in terms of meeting the energy efficiency and the QoS requirements.

Software defined networking (SDN) is becoming increasingly prevalent for its programmability that enables centralized network configuration and management. With the growth of SDNs, a cluster of controllers cooperatively manages more and more switches/flows in a network to avoid the single-controller congestion/failure and improve the control-plane robustness. Under the architecture with multiple controllers, it is expected to minimize the maximum response time on these controllers to provide better QoS for users. To achieve this target, two previous methods are mainly used, the static scheme and the dynamic scheme. However, these methods may lead to an increase of the control-plane communication overhead/delay. In this paper, we propose to minimize the maximum response time on controllers through flow redirecting, which is implemented by installing wildcard rules on switches. We formulate the minimum controller response time problem, which takes the flow-table size and link capacity constraints into account, as an integer linear program, and prove its NP-Hardness. Two algorithms with bounded approximation factors are designed to solve this problem. We implement the proposed methods on our SDN testbed. The testing results and extensive simulation results show that our proposed algorithm can reduce the maximum controller response time by about 50%-80% compared with the static/dynamic methods under the same controller cost, or reduce the number of controllers by 30% compared with the dynamic method while preserving almost the same controller response time.

This paper focuses on the cheating algorithm for device‐to‐device (D2D) pairs that reuse the uplink channels of cellular users. We are concerned about the way how D2D pairs are matched with cellular users (CUs) to maximize their sum rate. In contrast with Munkres’ algorithm which gives the optimal matching in terms of the maximum throughput, Gale‐Shapley algorithm ensures the stability of the system on the same time and achieves a men‐optimal stable matching. In our system, D2D pairs play the role of “men,” so that each D2D pair could be matched to the CU that ranks as high as possible in the D2D pair’s preference list. It is found by previous studies that, by unilaterally falsifying preference lists in a particular way, some men can get better partners, while no men get worse off. We utilize this theory to exploit the best cheating strategy for D2D pairs. We find out that to acquire such a cheating strategy, we need to seek as many and as large cabals as possible. To this end, we develop a cabal finding algorithm named RHSTLC, and also we prove that it reaches the Pareto optimality. In comparison with other algorithms proposed by related works, the results show that our algorithm can considerably improve the sum rate of D2D pairs.

In In-band Full-duplex (IBFD) wireless networks, the RTS/CTS mechanism is unable to establish an asymmetric dual link and to recognize the transmission mode of communication nodes to capture more opportunities of IBFD transmission, which limits total network throughput. In this paper, we propose a novel distributed IBFD MAC mechanism to establish symmetric/asymmetric dual link in wireless networks. Here we fully consider the two modes of asymmetric dual transmission. By medium access, the neighbors of communication nodes can clearly know network transmission status, which will provide extra opportunities of asymmetric IBFD dual communication. Finally, we develop a Markov model to characterize the non-saturation throughput of our proposed mechanism in IBFD wireless networks. The numerical results show that the throughput of IBFD network with our scheme nearly doubles that of HD network with RTS/CTS. Moreover, the non-saturation degree of the network has little influence on the throughput of our mechanism.

By current medium access control mechanisms designed for Half-duplex (HD), a node in distributed In-band Full-duplex (IBFD) wireless networks cannot identify the HD or IBFD transmission modes of the other nodes. This will decrease IBFD transmission opportunities by preventing simultaneous transmission in asymmetric dual link. In this paper, we propose a novel in-band Full-duplex Distributed Medium Access (FD-DMA) mechanism for wireless networks. Using this mechanism, both symmetric dual link and asymmetric dual link can be established by only one channel access. Moreover, all the neighbor nodes of primary transmitter and primary receiver can know exactly the IBFD transmission modes, which will increase the opportunity of IBFD communication and solve hidden nodes problem. The performance analysis and simulations show that the throughput of IBFD networks with FD-DMA mechanism nearly doubles that of the HD networks with RTS/CTS mechanism, and is much higher than that of IBFD networks with RTS/CTS mechanism.

The novel coal-gas dangerous-level prediction model established has advantages of the EA and BP neural nets, and overcomes the shortcomings of misreport and missing-report of others. This approach can accurately capture the complicated relationships among feature values of coal-gas outbursts and dangerous circumstances. We considered the characteristic of coal-gas outburst carefully, combining with the raw data of coal-gas monitor system in the Daping colliery and the 10thcolliery of Pingdingshan Company as well as real-time samples of accidents, and selected pattern sets to train the proposed model and generate the corresponding rules for prediction. Results show that the ENN has better performance than the ANN or the traditional method used individually, and enhances the practical techniques for prediction of coal and gas in coal mine to guarantee safety.