Cross-modal semantic communication plays a crucial role in emergency response systems. However, there are still two major challenges in practical applications: insufficient semantic compression due to the computing constraints of the source device, and poor signal generation at the sink device caused by harsh communication environment. To this end, this work fully leverages multi-modal interactive large AI model (LAM) distillation to enhance sparse feature representation for dynamic residual compression, while utilizing LAM adversarial feature mapping to repair the feature impairment for accurate signal generation, thereby achieving low latency and high reliable communication. Specifically, we first propose a scalable cross-modal semantic communication framework, which constructs a multi-modal semantic knowledge base (MSKB) by semantic similarity to support cross-modal semantic codec. On this basis, residual-guided cross-modal semantic encoding (RCSE) is designed, which employs video-infrared bidirectional knowledge distillation to lightweight LAM for feature extraction, and initially compresses features by inter-modal correlations. Further, according to the link state, the similar features in MSKB are dynamically stripped and the residual features are compressed for low-latency transmission. Additionally, an adversarial mapping-based cross-modal semantic decoding (AMCSD) is developed, which leverages adversarial mutual information (MI) to map features in LAM to impaired features, and discriminate semantic fidelity to enhance the mapping robustness, ensuring accurate signal generation. Finally, an emergency simulation platform is constructed. Experiments demonstrate that our scheme reduces the transmission latency by 27.64% and improves the signal generation precision by 14.06%.

With the popularity of unmanned inspection and telemedicine applications, edge source devices need to transmit multimodal data such as video, text, infrared, etc. in real-time in a computing power and bandwidth-constrained environment, whereas traditional single-modal compression and steganography methods struggle to balance efficiency and security. To address the current lack of end-to-end efficient methods that jointly consider multimodal coding and steganography, this paper is the first to propose a cross-modal private and covert communication scheme with constraints of computation and bandwidth, unifying cross-modal fusion, invertible steganography, and hyperprior image compression into a single model, and introducing a multi-stage joint training strategy. First, a lightweight composition-steganography-compression pipeline is designed at the edge source device, which composes visible and infrared signals into a semantically enhanced image, generates a natural stego image through invertible steganography, and produces a compact bit-stream through deep compression, achieving a 51.5% reduction in bitrate and a 48.3% reduction in encoding latency. Second, a multi-stage decoding-cross-modal reconstruction pipeline is built at the sink device to sequentially complete bitstream decompression, inverse steganography, and cross-modal reconstruction, ultimately outputting visible images (PSNR 30.37 dB) and infrared images (PSNR 31.58 dB), with a 40.9% reduction in decoding latency. Finally, a three-stage joint training further enhances PSNR and saves an additional 6% bitrate. Experimental results validate the efficiency, security, and robustness of the proposed method in resource-constrained environments.

Multi-modal traffic is becoming dominant across vertical domains. Rather than reconstructing raw data with content-agnostic fidelity, many emerging applications are inherentlytask-orientedand exhibit exploitable inter-modal correlations. In this paper we study such scenarios within the Shannon framework, modeling them as a CEO-type multi-terminal source coding problem under logarithmic loss, where asemantic priorSis available at both the encoders and the decoder. We refer to this formulation astask-oriented distributed cross-modal source coding(TD-CMSC) to emphasize its multimodal sensing application, while the underlying mathematical problem remains a classical log-loss CEO / multi-terminal source coding model augmented with the semantic prior S. On the theoretical side, we characterize the corresponding rate–distortion region under log-loss with semantic prior S in a general multi-encoder setting, and, under a total-rate constraint, we derive the associated distortion– rate function together with an explicit single-letter expression for the optimal per-modality rate allocation at the extreme points of the region. On the technical side, leveraging these results, we design a coding system for vector Gaussian sources that combines task-oriented conditional quantization with successiveWyner–Ziv coding. Numerical experiments confirm the feasibility and rate efficiency of the proposed design.

Federated learning emerges as a key enabler toward pervasive intelligence across IoT ecosystems with provable privacy guarantees. While recent efforts on client selection have been made for optimizing its communication efficiency in iterative model aggregation over resource-constrained networks, their scalability fundamentally breaks down in dense deployments. This limitation stems from the NP-hard complexity of congestion-aware scheduling, where co-channel interference creates exponentially growing solution spaces. In this context, we present a novel client selection framework with asymptotic scalability in massive IoT, which leverages the intrinsic graph topology with insights from statistical physics. First, this work formulate a universal client selection problem, capturing both positive network externalities derived from collaborative knowledge exchange and congestion effects induced by co-channel interference. This formulation is then transformed into a node classification task via Ising spin Hamiltonian mapping, establishing an explicit connection between federated learning, statistical physics, and graph optimization. Building on this foundation, we develop a lightweight graph neural solver that adaptively selects clients via recognizing node state with iterative neighbor aggregation of learnable embeddings. Comprehensive experiments validate that our approach maintains state-of-the-art scheduling performance, while scaling to network sizes orders of magnitude beyond what conventional methods can handle.

With the rise of immersive communications, live tactile streaming has become essential for delivering active tactile feedback. However, mainstream bitrate-scalable streaming methods—designed for traditional audio/video applications—overlook the latency-sensitive nature of tactile streams, significantly degrading the user's Quality of Experience (QoE) in multi-modal scenarios. To address this challenge, we propose a novel live tactile streaming strategy that integrates both coding and transmission optimizations. For coding, we design the Dual-Scalable Tactile Coding (DSTC) framework, which provides scalable options for both latency and bitrate. For transmission, we develop the Tactile Adaptive Bitrate (TABR) framework, which dynamically selects the optimal configuration based on fluctuating network conditions and time-varying transmission demands. Technically, DSTC offers multiple latency options by configuring variable window lengths during buffering, achieved through fixed-length single-window encoding followed by multi-window temporal fusion. Inspired by the base-enhancement mechanism, DSTC quantizes residuals by adjusting quantization bit-width, providing multiple bitrate options while preserving perceptual quality. Finally, by reducing the combined selection space into two subspaces, TABR jointly optimizes latency and bitrate options to maximize QoE. Experimental results demonstrate that our strategy achieves over 94.4% compression, enables flexible scalability for both latency and bitrate, and significantly enhances QoE under dynamic network conditions.

Task-oriented communications for multi-modal applications emerge with the intelligence-oriented evolution of Internet of Things, where massive computation offloading with heterogeneous streaming requirements greatly challenges the existing mobile networks. Compared with semantic coding which reduces intra-modality redundancy by feature extraction, cross-modal coding further exploits inter-modality association and thus acts as a promising solution. However, unresolved information-theoretic issues hinder its full promise: 1) how to characterize the achievable region of cross-modal coding for task-oriented communications, and 2) to what extent can task-oriented communications benefit from exploiting inter-modality association. Therefore, this work first establishes a cross-modal rate-distortion function for task-oriented communications, and proves the feasibility of optimizing its information-bottleneck inspired transformation for guiding the design of learnable codec. In particular, the optimal feature representation is specified by a converging iterative solver under perfect statistical knowledge. Second, we prove a new bound on compression gains of cross-modal coding in task-oriented communications, based on a sufficient condition for cross-modal representation to be effective. Furthermore, a typical learnable codec is designed, whose loss function can be theoretically interpreted by our derived results. Finally, experimental evaluations verify the positive correlation between cross-modal coding gains and inter-modality association levels.

Multi-modal visual signals are prevalent in emergency communications. To ensure high reliability of signal transmission under bandwidth constraints, it is crucial to compress redundant information both within and between modalities as much as possible, and ensure the fidelity of the reconstructed signals. Most existing studies depend exclusively on single-modal coding schemes and fail to effectively leverage the semantic correlations between modalities. In this paper, we introduce an end-to-end general cross-modal visual coding scheme, namely CMVC, which aims to jointly compress multi-modal visual signals (such as visible and infrared signals). First, we propose a cross-modal asynchronous entropy module that extracts common features using a cross-attention mechanism. Additionally, we enhance the accuracy of common features extraction by maximizing mutual information loss. This module further compresses multi-modal visual signals by compressing only the residual features between modalities. Second, we propose a cascaded enhancement module based on cross-modal Mamba that fuses complementary information to enhance the reconstruction quality of multi-modal visual signals. Finally, extensive experimental results demonstrate that our scheme significantly outperforms other advanced methods on visible-infrared datasets. Even at low bitrates, multi-modal visual signals can still achieve excellent reconstruction quality. Additionally, our scheme exhibits outstanding compression and reconstruction performance when applied to visible-depth signals, effectively demonstrating its robustness and generalizability.

With the rise of the Tactile Internet, delivering real-time and high-fidelity tactile feedback is crucial for enhancing immersion in multimedia services. However, existing tactile coding methods fail to simultaneously adapt to the diverse delay requirements of multimedia services and the time-varying network bandwidth. To address these challenges, this paper proposes a Scalable Tactile Coding (STC) method, which provides flexible coding delays and bitrates across multiple levels while ensuring human perceptual quality. Specifically, we first propose a tactile coding framework based on a non-stationary autoencoder for efficient compression, which features both delay-scalable and rate-scalable advantages. Second, by trading the balance between delay and computation, we design a sliding window approach that utilizes overlapping coding to reduce buffer delay. This approach provides multiple delay options to accommodate diverse delay requirements, thus realizing the desired delay-scalable effect. Third, inspired by the base-enhancement strategy of scalable video coding, we design a non-uniform quantization method to compress residual signals, which can be leveraged to dynamically enhance tactile signal fidelity. By adjusting the quantization bit-width, this method provides multiple levels of bitrates, thereby achieving a rate-scalable effect. Extensive experimental results demonstrate that STC achieves a bitrate reduction of over 92.3 % while maintaining satisfactory perceptual quality. Additionally, STC further supports flexible bitrate adjustment and satisfy various delay requirements.

Traditional communication faces significant challenges in multimodal scenarios, including surging network capacity demands and the neglect of semantic value. Although semantic communication achieves data compression through semantic feature extraction and refinement, existing methods have drawbacks such as inflexible compression, high computational complexity, and the separation of feature extraction and refinement from transmission scheduling, making it difficult to trade-off semantic integrity and transmission efficiency. To this end, this paper proposes a task-oriented cross-modal semantic transmission scheme, which is based on the task requirements, dynamically adjusts the feature fusion strength and utilizes semantic correlations to enhance the task-related features, and then evaluates the feature priority and selects the task-critical features for transmission, realizing the best of both worlds. Specifically, we design a task feedback-based cross-modal feature fusion method, which establishes a mapping between computing state and feature fusion level, and dynamically optimizes the fusion weight decomposed by the fusion level through task loss. On this basis, the cross-modal features are aligned and complemented using semantic correlation to refine the task-relevant features. Further, we propose a feature priority-based multi-mode semantic transmission method, which determines the feature priority by a task-response-based feature importance assessment model. Accordingly, a reinforcement learning (RL)-based dual-modal feature selection strategy is designed to select task-critical features for reliable transmission by coupling transmission performance with task requirements. Additionally, simulation results show that compared with the baseline, our method improves task accuracy by 10.6% and reduces transmission latency by 7.2% on average.

Incorporating tactile feedback into traditional audio-visual multimedia services has gradually become the killer application in the Beyond 5G era. However, current state-of-the-art tactile coding approaches struggle to achieve extreme compression, thereby significantly impacting the transmission quality of visual streams due to resource competition. To address this challenge, this paper proposes an efficient cross-modal coding method that fully leverages semantic correlations between visual and tactile modalities. Specifically, we first construct a crossmodal coding architecture based on the predictive coding, enabling flexible and scalable bitrates to meet diverse compression requirements and adapt to dynamic network conditions. By introducing explainable surface semantics (e.g., friction, texture) as intermediates, we then associate visual modality with tactile modality to extract their potential correlations from the perspectives of multiple physical properties. Finally, we design a cross-modal feature fusion module through exploiting semantic correlations to further improve reconstruction quality of tactile signals, thereby reducing the bitrates required for tactile residuals and facilitating more efficient transmission. Experimental results demonstrate that the proposed tactile coding method achieves high bitrate compression, with almost no impact on visual stream quality.

Device-to-Device (D2D) content sharing supports real-time applications but still faces challenges of large data and limited resources. With the growing computing capabilities of terminal devices, semantic content sharing has emerged as a promising solution. In this paper, a cooperative transmission D2D semantic content sharing based on probabilistic graphs is investigated to enhance user quality of experience (QoE). Specifically, D2D is divided into requesters and helpers. It is noteworthy that if both matching entities have knowledge bases, smaller-sized semantic information can be obtained by further compressing the semantic data. To encourage cooperation between D2D, we design utility functions for helpers and requesters, and formulate an optimization problem to maximize system utility by optimizing compression ratio, transmit power, and D2D pairing. In order to solve this problem, we introduce a matching game framework. First, we use an Nelder-Mead (NM)-based heuristic algorithm to solve the optimization problem for the compression ratio and transmit power. Then, a distributed cooperative semantic content sharing matching algorithm is proposed to achieve one-to-one matching, ultimately resulting in a stable strategy. The simulation results validate the optimality and convergence of the proposed algorithm. Compared to classical distributed algorithms, the proposed algorithm improves QoE performance by over 4.8%.

The expansion of the Industrial Internet of Things (IIoT), driven by informatization and intelligence, has made real-time monitoring for ensuring system safety and efficient production more critical than ever. However, in extreme industrial environments, harsh communication conditions and limited computing power impede reliable data transmission and processing, thus posing significant challenges to precise and continuous monitoring for massive IIoT. To this end, this paper proposes a digital twin (DT)-enabled hierarchical monitoring scheme by fully considering communication, computing, and control (3C) collaboration. Specifically, we first propose a DT-enabled 3C collaboration architecture, which builds an accurate digital representation of physical entities, and then completes the missing state based on shared-specific features to evolve continuously across the device lifecycle. Next, we design a multi-agent reinforcement learning (MARL)-based collaborative monitoring method, which formulates the joint optimization problem of compression rate and region assignment for monitoring nodes according to 3C performance. Then, we propose a mask state-assisted MARL scheduling method to refine the mask state space, take advantage of MARL’s distributed decision-making and centralized evaluation, and ensure timely monitoring of massive IIoT. Finally, we build a mine industry simulation platform and verify the effectiveness of the proposed method. The numerical results demonstrate a marked improvement in monitoring utility over traditional methods.

Multi-modal services that integrate signals such as audio, video, and haptic are poised to dominate the 5G and beyond era. Due to the presence of inter-modal redundancy and interference, it is highly challenging to simultaneously meet the demands for real-time, reliability, and high capacity in multi-modal services. Cross-modal communication, taking full use of inter-modal correlations, has been viewed as a promising solution. This paper aims to provide theoretical support for this approach by addressing two key issues: i) the benefits of cross-modal source coding (CMSC) in eliminating inter-modal redundancy, and ii) the benefits of cross-modal channel coding (CMCC) in alleviating inter-modal interference. Specifically, we first construct a cross-modal communication system model to illustrate how inter-modal correlations can be leveraged by incorporating common semantic information in both source coding and channel coding. Next, we analyze the reduction in error probability for a target modality’s symbols at the same coding rate and coding delay, both with and without assistance from other modalities and common semantics, to quantify the benefits of CMSC. Finally, we analyze the differences in achievable channel degrees of freedom and sum capacities under the same channel conditions, both with and without the utilization of common semantics, to quantify the advantages of CMCC. In the three case studies, numerical results validate the theoretical soundness of CMSC and CMCC for binary sources over a Gaussian channel, as well as their feasibility on a practical audio, video and haptic teleoperation platform.

With the rise of the Internet of Everything, machine-type wireless video applications like intelligent surveillance are increasingly becoming mainstream network services. However, the massive transmission of video streams heavily burdens wireless networks. Existing methods typically establish a correlation between the transmitted content and the quality of experience or service, making it challenging to balance trade-offs among decision quality, bandwidth utilization, and latency requirements. To address this issue fundamentally, this paper proposes a novel perspective by designing wireless video transmission strategies from the angle of decision quality, where only the content that impacts the decision outcomes is transmitted. The highlight of this paper is designing a lightweight yet efficient binary classifier that predicts whether the current content will change decision outcomes based on content discrepancies, measured only through pixel-level differences and macroblock-level similarity. Furthermore, these discrepancies can be used to distinguish the background, thereby further saving bandwidth by reusing the background information. Additionally, a fine-tuning module is incorporated to flexibly update the classifier model, ensuring adaptability across various scenarios. Extensive results demonstrate that the proposed strategy achieves over 81% redundant bandwidth savings while maintaining decision quality and catering to strict latency requirements on computation-constrained devices.

Wireless emergency networks play a crucial role in natural disasters, enabling seamless communication between explorers (e.g., rescue robots) and remote command centers. However, unstable communication links and limited computational resources hinder explorers from directly transmitting massive real-time content for remote human observation or locally computing the latest detection results. To address this challenge, this paper introduces a cross-modal semantic communications paradigm, where our highlights are characterized by precise semantic extraction, low-complexity implementation, and progressive semantic transmission. Specifically, by simplifying the desired task from human-oriented signal recovery to the machine-oriented decision, we firstly deploy a lightweight cross-modal semantic encoder on the explorer, which precisely extracts compact semantics relevant to the decision-making based on inter-modal correlations. Then, to mitigate the impact of intermittent network connections, we develop a scalable semantic transmission strategy that encodes extracted semantics as base and enhanced semantics, progressively delivering them once the network becomes active. Numerical results indicate remarkable benefits of cross-modal semantic communications in terms of decision accuracy, model size, and transmission latency.

In the cellular Internet of Things (CIoT), it is crucial to ensure the information freshness for status update applications. Considering the centralized access methods could cause large access delay and hamper timely status updates, this paper exploits the random access method and studies decentralized status update schemes to minimize the average age of information (AoI) for CIoT. However, due to the non-cooperation among machine type communication devices (MTCDs) in random access, packet collisions are inevitable, which makes it tricky to improve the AoI performance. In this regard, we design novel age-based status update schemes to control the transmission behavior of MTCDs, where the AoI at the MTCDs and the base station (BS) is used. We first model the AoI minimization problem as a Markov decision process. Then, through variable substitution and linear programming, we get a slightly more computationally complex status update scheme, where the dual threshold structure of the scheme is proved theoretically. To facilitate system design and reduce computational complexity, we further design a low-complexity scheme, where the age thresholds at both the MTCDs and BS are optimized. Simulation results verify that the proposed schemes significantly outperform the common access scheme.

To ensure the users’ immersive experience in cross-modal communication, overcoming the end-to-end (E2E) latency through prediction has attracted attention and shown its superiority. However, existing prediction schemes encounter formidable challenges in the presence of multi-modal signals, primarily to adapt and satisfy the prediction requirements of diverse multi-modal services, as well as to fully exploit and effectively utilize the correlation features of multi-modal signals for precise prediction. To this end, this work presents a flexible prediction scheme for low-latency cross-modal communication. Specifically, we first propose an adaptive prediction-aware cross-modal communication framework, which reduces the delay by predicting and transmitting the future multi-modal signals in advance, and flexibly adjusts the prediction horizon to satisfy the prediction accuracy of different multi-modal services. Next, we design an information gain-assisted graph attention (IGGA) method for cross-modal signal prediction, which leverages the graph attention block to extract the intra-modal, inter-modal spatial and temporal correlation features, and effectively optimize and utilize these features with the information gain (IG), thereby facilitating precise cross-modal signal prediction. Finally, numerical experiments conducted on a self-built dataset, a public dataset, and a multi-modal acupuncture platform demonstrate the superiority of the proposed scheme in low-latency cross-modal communication.

The multi-modal robotic teleoperation, as an important application in human-computer interaction (HCI), is playing a significant role in various domains such as industry, healthcare, and education. However, existing robotic teleoperation systems face significant challenges with multi-modal signals, primarily in designing a cross-modal communication architecture that caters to diverse modal requirements and ensuring high-quality cross-modal signal reconstruction even in poor network conditions. To this end, this work proposes a general cross-modal signal reconstruction scheme by taking full advantage of the correlation among different modality signals. Specifically, we first propose a scalable cross-modal communication architecture that meets the diverse needs of various modality signals using multi-modal encoding and multi-directional decoding, eliminating the need for a specialized feature extraction model. Next, we design a masked auto-encoder with discriminator assistance (MAE-D) cross-modal signal reconstruction method, which leverages the idea of generative confrontation by combining the codec for signal reconstruction with the discriminator responsible for assessing the authenticity of the reconstructed signal to achieve accurate and efficient cross-modal signal reconstruction. Finally, numerical experiments conducted on our self-built multi-modal dataset, a public dataset, and a teleoperation simulation platform demonstrate that the proposed scheme offers significant advantages in cross-modal signal reconstruction.

With the explosive growth of online multi-modal applications that typically include audio, video, and haptic signals, immersive experience (IE) improvement has been broadly regarded as one of the most important tasks. Compared with traditional quality of experience (QoE) improvement for online audio/video applications, it highlights two sequential technical challenges to be resolved: i) much more stringent demand of real-time improvement due to the incorporation of delay-sensitive haptic signals, and ii) high-dimensional instead of existing one-dimensional (i.e.,network-level) paradigm for better online improvement. To get over this dilemma, this work systematically addresses the following three fundamental problems: i) which factors influence IE, ii) how to online improve IE, and iii) to what extent of the corresponding IE improvement can be achieved. To this end, we first comprehensively explore and categorize the influence factors on IE from various dimensions. Then, by combing network resource scheduling with the multi-domain collaboration of user profile, device specification, and application type, an online IE improvement strategy is proposed based on the efficient linear contextual bandit with the$L_{1}$-norm estimation. Finally, we derive the theoretical bound of IE improvement, scaling at a poly-logarithmical function of data dimension. Numerical results on the practical system also demonstrate the remarkable improvement on IE.

Multi-modal applications are expected to dominate in the 5G and B5G era. However, traditional source coding methods are not efficient or reliable due to neglecting semantic redundancy and mutual influences between different modalities' sources. To address this, cross-modal source coding (CMSC) has been proposed as a promising solution. However, there are still two main challenges: determining the optimum rate of CMSC considering delay and reliability constraints, and designing a practical CMSC near the optimum rate. To tackle these challenges, this paper focuses on studying the optimum source coding rate of CMSC and its practical implementation. On the theoretical side, an$(n,\epsilon)$-achievable rate region is derived, representing the source coding rates subject to a fixed blocklength$n$and the target error probability$\epsilon$. Additionally, the optimum source coding rate can be approximated by calculating the infimum of the$(n,\epsilon)$-achievable rate region with a rate dispersion function. On the technical side, a general implementation for CMSC is proposed, which fully leveraging channel coding and artificial intelligence (AI) semantic analysis to achieve the optimum rate. Numerical results demonstrate that CMSC can obtain 50% improvement in theory and 37.5% enhancement in practice against the baseline model abstracted from traditional schemes when multi-modal sources are semantically correlated.

In fine-grained visual categorization (FGVC), most part-based frameworks do not work effectively in some extremely challenging scenarios such as partial occlusion. This limitation is due to the heavy disorder of local features extracted from such occluded targets. To address this issue, we propose a global information-assisted network (GIAN), where auxiliary global information can search the useful elements of local information and integrate with them for an efficient unified feature representation. In particular, in order to acquire the global information, we design a global attention-concentrated convolutional neural network (GAC-CNN) by extending a convolutional neural network with a nonlocal GCN module. Then, the unified feature representation is produced by two strategies. On the one hand, a global–local aggregation strategy is developed to selectively integrate global features with local features through consistency evaluation and reweighting method. On the other hand, an alternative knowledge distillation strategy is developed to help generate more powerful global and local features. Two strategies collaboratively make the unified features more robust and more discriminative than traditional part-based features. Experimental results show that the proposed GIAN can achieve accuracies of 92.8%, 93.8%, and 95.7% on CUB-200-2011, FGVC Aircraft, and Stanford Cars, respectively.

Digital twin (DT) has emerged as a key enabler for the intelligent-oriented evolution of mobile networks. With the rise of privacy concerns for enabling intelligent applications in DT-empowered mobile networks (DTMNs), federated learning has garnered wide attention due to its potential on breaking down data silos. However, the data privacy of federated learning is greatly threatened by emerging gradient leakage attacks, and the need for frequent knowledge exchange limits its training efficiency over resource-constrained DTMNs. To circumvent such dilemmas, this work first proposes a privacy-enhanced federated learning framework based on cloud-edge-client collaborations. Particularly, model splitting between clients and edge servers makes gradient leakage attacks computationally prohibitive, and cloud-side partial model aggregation provides hierarchical data utility. To improve the training efficiency of the proposed learning framework, we further establish its communication and computation cost models, and develop a DT-assisted multi-agent deep reinforcement learning-based resource scheduler for joint client association and channel assignment. Finally, as a case study of intelligent applications in DTMNs, a human-robot collaborative nursing task is designed to evaluate the practical performance of our proposed scheduler. Experimental results show its superiority in saving training costs and preserving learning accuracy.

Machine-type communication (MTC) has been considered as one of the key enablers for intelligent Internet of Things (IoT) applications. However, existing evaluating metrics, no matter the Quality of Service (QoS) or Quality of Experience (QoE), cannot truly and accurately reflect the quality of MTC when it serves machine decision making. To address this problem, this work proposes a new performance index, Quality of Decision (QoD), to elegantly capture the essence of MTC and precisely depict the corresponding functionality. First, the physical components and logical processes that affect the quality of MTC in analytics-oriented scenarios are carefully studied. Second, through jointly considering the factors of the commonness and individuality, we propose a layered QoD framework capable of independently evaluating and monitoring the quality of data to be acquired, delivered, and processed for enabling machine decision making. Third, we design a typical QoD-driven transmission scheme for video analytics by avoiding over provisioning of sensing and communication capabilities, which shows super efficiency compared to traditional human-perception-oriented approaches. We believe that the utilization of QoD will significantly promote the application of MTC in building various intelligent IoT systems.

Medical robots with audio-video-haptic streams, as indispensable devices for remote healthcare, are playing ever-increasing roles in mitigating the spread of infectious diseases. However, existing medical robots are far from precise and efficient because of the following two technical challenges, including i) how to ensure the haptic fidelity for precise manipulation, and ii) how to alleviate the impact of haptic streams on the quality of visual navigation for efficient operation. To this end, this work explores the benefits of edge-based cross-modal communications (CMCs), which take full advantage of potential correlations among different modalities’ streams, to realize high reliability and throughput. Specifically, to compensate for the reliability loss caused by wireless transmission, a semantic-aided cross-modal reconstruction framework is firstly designed at edge nodes for high haptic fidelity. Then, a user experience-driven stream scheduling strategy is developed to enhance the visual quality by fully leveraging edge computing and network slicing. In particular, different from traditionally interrupting audio/video stream transmission to prioritize haptic streams, we jointly schedule resources to different modalities’ streams via estimating haptic arrival time. Finally, as a classical case study, we independently construct a remote throat swab sampling platform based on CMCs to evaluate practical performance, and numerical results indicate the significant improvements in terms of various metrics.

Integrated sensing, communication, and computation (ISCC) will become a key enabler for automation applications. However, since the performance region of ISCC has a higher dimension than those of traditional wireless networks, existing schedulers typically fail to simultaneously meet the heterogeneous requests in ISCC. In this work, we propose a novel wireless scheduling architecture to explore the coordination gains of sensing, communication, and computation from a perspective of joint optimization. Specifically, we first construct an implementation framework of ISCC by combining the mobile edge computing paradigm with the integrated sensing and communication technology, where the inherent tradeoff between sensing, communication, and computation performance is characterized. Next, a joint device association and subchannel assignment problem is formulated to capture the network externalities induced by resource competition among mobile devices with multi-functional requirements. Due to its intractability, we then reformulate it in the matching theoretical manner. To obtain a mutually satisfactory solution under externalities, an iterative matching algorithm is developed by introducing pairwise stability and proved to be convergent and stable. The extensive simulations elucidate the significant superiority of our proposed scheme over those externality-unaware wireless schedulers.

Since haptic communications have an extreme requirement for the latency performance, the overdue content delivery will decrease the application experience. In order to reduce the transmission delay, we try to construct a cache-enabled D2D-assisted content-sharing framework, where the neighboring helpers preset contents and adjust their transmission power to timely serve more requesters. In particular, we modify the existing definition of the “closest” friend and take the social relationship into account to measure the overall influence caused by available neighboring helpers. However, such cooperation consumes the storage space and energy of the helpers, and accordingly, we introduce blockchain technology to propose an effective incentive mechanism where the helpers act as consensus users of blockchain and obtain the reward, i.e., the allocated computing power by the base station (BS), by contributing their local resources. Guided by this, the benefit of each helper is defined as a tradeoff of the reward and overheads. Meanwhile, we formulate the multiuser content delivery problem with the goal of maximizing the global benefits as the multiuser content delivery game. Then, we prove that the proposed game is an exact potential game (EPG) with at least one pure-strategy Nash equilibrium (NE). Meanwhile, the context-aware content delivery-based concurrent better reply (CCDCBR) algorithm is proposed to achieve a desirable solution. Finally, simulation results verify the validity of the proposed game model as well as the proposed algorithm.

Win-win cooperation has been broadly treated as one of the most promising goals for device-to-device (D2D) content sharing, especially for the ultrareliable low-latency communications (URLLC) scenario. Unfortunately, the exiting solutions are built on several seemly unpractical conditions: 1) abundant prior information on network and user; 2) optimization variables limited to 1-D space; and 3) a preset order on users' decision making. In this work, we propose a win-win-driven D2D content-sharing scheme by exploring the blind matching theory. Specifically, we first derive the closed-form expressions of latency and reliability performance for D2D content-sharing scenarios. Accordingly, the URLLC-oriented joint optimization problem for provider-demander pairing and power control of potential providers is formulated as a two-sided one-to-one context-free matching game, which involves a collection of agreement functions of potential providers and demanders' aspiration levels and exploits a modified notion of pairwise stability as the solution concept. Then, we design a distributed algorithm by utilizing the market and information decentralization characteristics of the blind matching algorithm. Both theoretical analysis and numerical results validate the performance properties, including convergence, optimality, and complexity.

In this article, we investigate the performance of massive machine type communications (mMTC) in status update systems, where massive machine type communication devices (MTCDs) send status packets to the BS for system monitoring. However, massive MTCDs sending status packets to the BS will cause severe packet collisions, which will have a negative impact on status update performance. In this case, it is necessary to carry out reasonable access control and resource allocation scheme to improve the status update performance for mMTC. In this article, taking the features of mMTC into consideration, we first analyze access control, packet collisions and packet errors in mMTC respectively, and derive the closed-form expression of the average age of information for all MTCDs as the performance metric, and then propose a joint access control, frame division and subchannel allocation scheme to improve the overall status update performance. Simulation and numerical results verify the correctness of theoretical results and show that our proposed scheme can achieve almost the same performance as the exhaustive search method and outperforms benchmark schemes.

Cross-modal applications that elaborately integrate audio, video, and haptic streams will become the mainstream of the eHealth systems. However, existing stream schedulers usually fail to simultaneously meet the cross-modal transmission requests in terms of low latency, high reliability, high throughput, and low complexity. To circumvent this dilemma, this article proposes a general cross-modal stream scheduling scheme by fully taking advantage of the characteristics of different modal streams and their underlying temporal, spatial, and semantic relevance. Specifically, we first propose a hierarchical stream category framework, in which the transmission priority of the modal stream instead of the data flow can be flexibly settled. Next, we design a series of modal-aware stream scheduling schemes by jointly making use of the network slice and mobile edge computing to achieve the tradeoff among the various metrics. Importantly, the transmission strategy can be adjusted adaptively to realize the optimal resource allocation. Subsequently, we analyze the relationship among the user experience, multi-modal impact, and stream scheduling through investigating the interacted impacts among the different modal streams, then develop a user experience based scheduling switch strategy to improve the application generality and reduce the performance fluctuation. Numerical objective and subjective results demonstrate the efficiency of the proposed cross-modal scheduling scheme.

Cross-modal communication is playing an increasingly important role in improving receivers' immersive experience. The main challenge lies in ensuring the heterogeneous requirements of the cross-modal stream. Especially, the discontinuity of the received haptic signals caused by the delay should be eliminated. Unfortunately, existing schemes study the cross-modal stream separately, which leads to that the haptic signal is distorted, or the audio-visual quality is reduced. To solve this problem fundamentally, we propose a joint transmission framework combining prediction and device-to-device (D2D) communication by taking advantage of the correlation of the haptic signals and the proximity feature of the receivers. Specifically, on the theoretical end, to completely eliminate the discontinuity, we propose a prediction mechanism by predicting and sending the future signals in advance. To compensate for the reliability loss brought by prediction, D2D links are efficiently established on the receivers' side. On the technical end, we first design a minimum resource (e.g., power) consumption search algorithm based on the binary search to obtain the optimal prediction horizon. Moreover, we develop a simple but efficient transmission mode selection algorithm based on the Hungarian algorithm. Experimental results demonstrate the advantages of our proposed scheme in saving the power consumption.

In order to make device-to-device (D2D) content sharing give full play to its advantage of improving local area services, one of the important issues is to decide the channels that D2D pairs occupy. Most existing works study this issue in static environment, and ignore the guidance for D2D pairs to select the channel adaptively. In this paper, we investigate this issue in dynamic environment where D2D pairs’ activeness and wireless channel are dynamic. Specifically, we propose a pricing-based approach to guide D2D pairs to select different channels according to the spectrum resource states adaptively. Then, we formulate the pricing-based channel selection problem as an expected global price-to-performance ratio minimum problem. In order to solve it in a tractable manner, we make an approximately equivalent transformation to it. After that, we model the transformed problem as a stochastic game and prove it to be an exact potential game, which has at least one pure strategy Nash Equilibrium (NE) point. In order to reach the pure strategy NE points in dynamic environment, we design a channel selection learning algorithm based on stochastic learning automata, which only requires little information exchange. Simulation results show that our proposed algorithm outperforms other benchmark algorithms.

Content recommendation based on device-to-device (D2D) multicast communications is expected to become a promising approach to improve local area services. Importantly, two main challenges should be considered: i) user clustering-in order to be tailored to recommend contents, the members in the same cluster should have great similarity in multiple characteristics, and ii) link allocation-we should use as little resource consumption and information exchange as possible while keeping the recommendation accuracy. In this paper, we firstly quantify the degree of the similarity between two target users with regard to multiple characteristics. Guided by such similarity, we define a clustering validity index in terms of between-within proportion (BWP) to characterize the clustering performance. Then, the issue of user clustering is modeled as a sum BWP maximum problem, and a user clustering algorithm based on modified K-means algorithm is designed to solve it in a fast-operating and low-complexity way. After user clustering, we model the issue of link allocation as a weighted aggregate interference minimization problem, and then transform it to an exact potential game. As such, a link allocation algorithm based on stochastic learning algorithm is proposed which helps to obtain the result of this game in a distributed way without complete information. Also, we analyze its convergence and optimality performance. Simulation results demonstrate the effectiveness of our proposed algorithms.

More and more network media users concern about their privacy issues since they know that their network behaviors are being observed, and thus the observable users' data are not reliable and sufficient in this case. How to evaluate the true quality of experience (QoE) of the privacy-aware users has become a significant technical challenge because of the most majority of existing data-driven QoE evaluation schemes based on the premise of the true and adequate users' observations. To get over this dilemma, this paper proposes a systematic and robust QoE evaluation scheme with unreliable and insufficient observation data. Specifically, we first translate the subjective privacy-aware QoE evaluation problem into an objective rational user analysis procedure. Then, a semantics-based similarity measurement for multidimensional correlation analysis is constructed to classify the observable data. Subsequently, the highlight of this paper lies in proposing a class-level joint user classification and data cleaning strategy by frequently updating the training processes. Through elaborately designing an iterative framework, it can effectively resolve the data sparsity and inconsistency problems due to the user privacy-aware preferences. Importantly, we also introduce an efficient QoE model construction method for online implementation, and numerical results validate its efficiency for different kinds of privacy-aware users.

Device-to-device (D2D) multicast communications have become a promising technology to satisfy the increasing demands for popular content sharing among users. However, most of the existing works mainly focus on the benefits resulting from constituting the clusters, while ignoring the ever-present costs. Facing the coexistence of the benefits and costs, the two issues should be tackled, i.e., i) how to motivate the users to form clusters, and ii) how to achieve a balance between them. In our work, a social-monetary-aware incentive model based on the social ties and the content fee is proposed to motivate both the cluster head (CH) and content requesters (CRs) to form clusters. Then, we formulate the cluster formation problem as an incentive-based coalition formation game with nontransferable utility, where the utility takes into account the benefits in terms of the content fee and the costs in terms of the transmission delay. An incentive-based cluster formation algorithm based on the merge-and-split rules and the Pareto order is proposed. Its performance, e.g., the convergence, the stability, is discussed, and is also evaluated by extensive simulations based on the comparisons with other algorithm.

Device-to-Device (D2D) multicast communication is becoming a promising technology to improve local area service. In this paper, we present a distributed social-aware clustering method to group the content requesters (CRs) into clusters. Specifically, a cluster head (CH) selection algorithm based on social maximum weight (SMW) is firstly proposed to select the CHs from the original CRs. After that, we propose a cluster formation optimization framework via a non-transferable utility coalition formation game (CFG), and a distributed coalition formation algorithm for clustering is proposed based on preference relationship and switch operations. Moreover, the final coalition structure is proved to be Nash-stable. Numerical results are presented to verify the effectiveness of our proposed schemes.

Joint link and power allocation for device‐to‐device (D2D) communication underlaying cellular networks are necessary to coordinate the mutual interference. Most of the works consider the sum interference from D2D pairs. However, mobile devices are carried by human beings who are connected with social ties. For one cellular user, the strengths of the social ties with D2D pairs are different. Thus, his interference tolerance temperatures (ITTs) are various. In this study, we distinguish D2D pairs through the social ties, and propose a social aware pricing‐based joint link and power allocation scheme. Specifically, the base station (BS) prices the interference on every link and updates the prices according to the ITTs of cellular users. Subsequently, with the prices, the competition of D2D pairs for the links is modelled as a non‐cooperative game. The authors prove the existence and the uniqueness of the Nash equilibrium (NE), and demonstrate that the NE is Pareto optimal. Moreover, an iterative decentralised algorithm is designed to solve the game. Especially, if the number of the price on one link for one D2D pair being updated is up to an upper bound, the power is forced to be 0. Numerical simulations verify the effectiveness of the authors' proposed scheme.

Data service has been considered as one the most prominent characteristics for Industrial Internet of Things (IIoT). This paper studies how to design an optimal computing manner for a general IIoT system. On the theory end, we analyze the relationship between the data processing and the energy consumption through investigating the content correlation of the captured data. Importantly, we derive an exact expression for the performance of IIoT by combining computation with intelligence. On the application end, we design an efficient way to obtain a threshold by approximating the performances of different computing manners, and show how to apply it to practical IIoT applications. We believe that the proposed computation rules hold great significance for the IIoT designer, that is, it is better to use distributed computing manner when the content correlation is high, otherwise, centralized computing manner is better.

Massive multimedia services have been considered as one the most prominent characteristics for smart cities. In this paper, we propose an energy-efficient content delivery system via the device-to-device communications, which realizes the large-scale content delivery among mobile devices with constrained energy, unpredictable demand, limited storage, random mobility, and opportunistic transmission. The highlights of this paper lie in two parts. On the theoretical end, through exploring the relationship among the coding, storage, and transmission, a systematic energy-saving content delivery fashion is investigated. On the technical end, a totally distributed content delivery system is designed in a simple and efficient manner, in which each device only utilizes local information to make decisions and implements its own scheme individually. Importantly, the proposed scheme is realized in a practical smart city system, and numerical results demonstrate that it is flexible to various users' needs and communication environments.

The cache‐enabled device‐to‐device (D2D) communication is a burgeoning technique to offload cellular traffic. In this study, the authors conducted the joint cache policy and transmit power to maximise the content‐related energy efficiency (CREE) for the cache‐enabled D2D network. Specifically, the authors model the random distribution of mobile users by the Poisson point process and derive the closed‐form CREE via considering the D2D establishment threshold and signal‐to‐interference ratio threshold at the same time. Then the authors aim to determine the optimal cache policy and transmit power for maximising the CREE in two practical cases, respectively. Since the optimisation problem in both cases are non‐linear non‐convex problems and share the same mathematical form, the authors focus on the first case and propose a two‐step iterative algorithm to find a stationary solution due to its intractability. This iterative algorithm builds on two subproblems which are proved to have optimal solutions. Numerical simulations show that the joint optimisation can obtain more than two times the CREE compared with either of the single optimisation for cache policy or transmit power.

Device-to-device (D2D) content sharing has become a promising solution to support the growing popularity of multimedia contents for local services. Considering the randomness of content location, the limited storage and transmission capability of devices, and the coexistence of altruistic and selfish user behaviors, how to optimally match the demanders to the providers of contents and how to stimulate an efficient cooperation are of importance for achieving the full benefits of D2D content sharing. Especially when the base-station-to-device (B2D), D2D, and novel multi-D2D sharing modes coexist, the issue of content sharing mode selection plays the predominant role in such matching. In this paper, we introduce a notion of social-aware rate, which combines the social selfishness from the social knowledge with the link rate to ensure the physical link quality and the effective cooperation together. Then, the social-aware rate-based content sharing mode selection problem is modeled as a maximum weighted mixed matching problem, which can be computationally reduced to a submodular welfare problem subject to a matroid constraint. Subsequently, we develop a best-effort distributed algorithm framework, which displays alternatives of various computation complexities and approximation ratios to satisfy the diverse practical needs.

With the emerging demands for local area services of popular content downloading, D2D communication is recognized as a promising technical support for cellular networks. In this work, we propose a social-aware content downloading mode selection scheme, which involves a novel mode, named MD2D, by collaborating multiple available D2D links. In particular, we construct a social-aware evaluation framework, which understands the interplay between physical transmission property and social networking characteristics for defining the performance metric with respect to the downloading mode selection. Accordingly, we formulate the social-aware content downloading mode selection problem based on the combinatorial auctions. By exploring the submodular approximation of this problem, we design a social-aware mode selection algorithm. We demonstrate that the solution achieves incentives for content contribution and resistance to misbehaving potential content providers, and also derive a theoretic upper bound of the corresponding performance loss.

In this work, we propose a dynamic distributed resource sharing scheme which jointly considers mode selection, resource allocation, and power control in a unified framework for general D2D communications. First, we model the joint issue of mode selection and resource allocation as a hedonic coalition formation game, while accounting for the tradeoff between the benefits in terms of available rate and the costs in terms of the mutual interference. Moreover, we develop a coalition formation process based on the switch rule, through which each cellular user makes an individual and distributed decision to form a Nash-stable partition. Second, we view the members of each coalition as a whole, and formulate a power control problem to share the aim of maximizing the sum-rate of cellular links in this coalition. To solve this NP-hard problem with online operation, we present a power control process, which employs the local piecewise-linear approach to take a locally and separately approximate optimal outcome. Finally, we present a dynamic resource sharing algorithm, which iteratively operates the coalition formation and power control processes.

In this work, we study the problem of green uplink resource sharing over mobile device-to-device (D2D) communications underlaying cellular network. We first construct a analysis model of energy efficiency, which takes into account different sharing modes, as well as QoS requirement and spectrum utilization of each user. Then, we formulate the sharing problem as a non-transferable coalition formation game, with the characteristic function which accounts for the gains in terms of energy efficiency and the costs in terms of mutual interference. Then, the resulting coalition structure shows the energy-efficient sharing strategy on the joint mode selection, uplink link reusing allocation, and power management. Moreover, we develop a distributed coalition formation algorithm based on the merge-and-split rule and the Pare to order. The distributed solution is characterized through stability notions and is adapted to user mobility. Simulation results are provided to demonstrate the effectiveness of our proposed game model and algorithm.

It is well known that a cooperative communication technique can offer significant energy saving improvements. In particular, the efficient relay resource allocation makes energy saving practically appealing. In this work, we propose an auction-based relay power allocation scheme over multi-user relay networks from the energy-efficient perspective. In particular, during the relay resource allocation operation, three major design goals are considered: 1) efficient utilization of relay resources, in terms of Pareto optimal relay power allocation; 2) insurance of competitive fairness among competing users; and 3) guarantee of distributed implementation with relaxation of restrictions on complete private knowledge and accurate assessments of convergence. Specifically, we take full advantage of the auction mechanism, i.e., competitive fairness with the incomplete private information of other nodes, to model the interaction among the users as a multi-winner auction based on the optimal bidding decision. By treating the proposed auction mechanism as a non-cooperative game, we obtain the unique and Pareto optimal Nash equilibrium (NE), which yields the optimal bidding decision and allocation of the relay power. Moreover, we design a distributed algorithm based on best-response functions to reach the NE allocation. In particular, the convergence and the convergent rate of the algorithm are analyzed quantitatively to clarify the application scenarios.

In this work, with respect to the uncertainty about the individual information, we investigate the relay power allocation problem from the energy-efficient, Pareto optimal, and competitive fairness perspective. At first, we design an easy-implementation energy efficiency metric, which aims at striking a balance between the QoS provisioning and the energy consumption. Then, an auction mechanism is proposed for relay power allocation. By transferring the auction mechanism into a game, we prove the existence, uniqueness, and Pareto optimality of the Nash equilibrium (NE) for our auction game, and show that the allocation strategies from the NE can achieve the energy efficiency in terms of the proposed metric. Next, we develop a distributed relay power allocation algorithm based on our best-response functions to reach the Pareto optimal NE. Importantly, we not only certify the convergence of the proposed algorithm, but also provide quantitative analysis on it. Extensive simulations results are conducted to confirm the validity of the analytical results.

In this work, we propose a correlated equilibrium (CE)-based energy-efficient resource allocation scheme for uplink OFDMA systems. At first, we construct an energy-efficient resource allocation game, where each subcarrier is viewed as a player to choose the most satisfying user, and the objective is to balance the tradeoff between the total energy efficiency and the fairness. Since the CE can achieve better performance by helping the non-cooperative players coordinate their strategies, we employ the CE to analyze the proposed game. Next, we derive the condition under which the CE is Pareto optimal and employ linear programming duality to show its closed-form expressions. Furthermore, we present a linear programming method and a distributed algorithm based on the regret matching procedure to implement the CE, respectively. Simulation results demonstrate that our scheme is able to achieve good convergence, Pareto optimality, and fairness.

Owing to the evolution of green communications, energy efficiency is treated as an important performance metric of a uplink orthogonal frequency division multiple access (OFDMA) system. In this study, the authors propose an energy-efficient resource allocation scheme by using the correlated equilibrium (CE). At first, the authors construct an energy-efficient resource allocation game, where each subcarrier is viewed as a player to choose the most satisfying user, and the objective is to balance the tradeoff between the total energy efficiency and the fairness. Since the CE can achieve better performance by helping the non-cooperative players coordinate their strategies, the authors employ the CE to analyse the proposed game. Next, the authors derive the condition under which the CE is Pareto optimal and employ linear programming duality to show its closed-form expressions. Furthermore, the authors present a linear programming method and a distributed algorithm based on the regret matching procedure to implement the CE, respectively, which can help us determine the desired resource allocation. Simulation results demonstrate that our scheme is able to achieve good convergence, Pareto optimality and fairness.

In this work, we study the problem of how to strike a balance between the QoS provisioning and the energy efficiency when a cooperative communication scheme is applied to a clustered wireless sensor network. Specifically, we first characterize the tradeoff by a multi-variable optimization problem, with the goal of balancing the outage performance and the network lifetime. Then, we horizontally decompose the problem into the concatenation of two subproblems: i) the long-haul transmit power per sensor node, and ii) the set of assisting cluster nodes. For the former one, an optimal long-haul transmit power solution is proposed based on the Lambert W function. The latter one is modeled as a coalition formation game, where the characteristic function is designed based on the combination of the former subproblem's results. Furthermore, an optimal algorithm is proposed by using a dynamic coalition formation process based on the best-reply process with trial opportunity. Extensive simulation results are presented to demonstrate the effectiveness of our proposed scheme.

In this paper, we focus on the problem of how to strike a balance between the QoS provisioning and the energy consumption when a cooperative communication scheme is applied in a clustered wireless sensor network. We characterize this tradeoff by a multi-variable optimization problem, with the goals of jointly maximizing the outage performance and the network lifetime. Then, we horizontally decompose the problem into the concatenation of two subproblems: (i) the long-haul transmit power per sensor node, and (ii) the set of assisting cluster nodes (CNs). For the former one, the optimal long-haul transmit power solution is presented based on the Lambert W function, only with the knowledge of statistic channel state information. Moreover, a dynamic coalition formation game theoretical framework is modeled to solve the latter one. A corresponding algorithm is proposed by using a dynamic coalition formation process based on the best-reply process with trial opportunity. Through this algorithm, a stable coalition structure with a core allocation can be obtained, which can show the optimal set of assisting CNs. Extensive simulation results are provided to demonstrate the effectiveness of our proposed scheme.