Brain-tuning enhances brain alignment and downstream performance by fine-tuning speech language models with neural recordings.However, previous work relies primarily on fMRI, whose temporal resolution integrates neural activity over seconds, blending distinct processing stages into a single supervision signal and precluding temporally targeted training.We introduce ECoG-tuning, which leverages electrocorticography's millisecond precision to train speech language models.We design temporally targeted windows-a speech window capturing acoustic-phonetic encoding and a language window capturing higher-order linguistic processing-grounded in neuroscientific findings about temporal encoding hierarchies.Evaluating three models on the Podcast ECoG dataset, we find that ECoG-tuning significantly improves brain alignment over pretrained and distillation baselines.Notably, full spatiotemporal dynamics yield 7-17% higher alignment than time-averaged supervision across models, and language-window tuning produces larger gains in higher-order language regions, indicating that temporal precision provides additional training value.Moreover, ECoG-tuned models consistently improve or maintain downstream performance.Overall, our work provides initial evidence that electrophysiology is a viable brain-tuning modality, demonstrating how neuroscientific insights into processing hierarchies can inform principled model training strategies.

The Internet of Vehicles (IoV) enhances road safety and supports autonomous driving through real-time communication, but current methods face key challenges: rigid resource allocation due to static architectures, communication failures in low-signal areas from infrastructure reliance, and passive defense mechanisms struggle to counter coordinated attacks, while high-latency encryption algorithms further compromise framework real-time performance. To address this, we propose a blockchain-based dynamically adaptive restructuring framework. It enables real-time IoV cluster restructuring by splitting overloaded IoVs to reduce communication overhead, or merging nearby IoVs to optimize resource utilization. In infrastructure-sparse zones, vehicles establish temporary multi-hop communication links based on relative mobility to ensure continuous connectivity. A multi-layered security mechanism integrates physical validation, event verification, and majority voting, achieving over 95% resistance to data tampering. Compared to Raft, PoS, and PBFT, our framework improves consensus speed by 27.06%–38.56%, and reduces transaction latency by 7%–35%, 15%–54%, and 27%–66%, respectively. It also maintains high robustness under dense traffic, high mobility, and weak signals, offering a proactive, adaptive security paradigm for intelligent transportation frameworks.

Transfer learning leverages existing models to help train new models, rather than training the new models from scratch. Unfortunately, realizing transfer learning in distributed cloud-edge networks faces critical challenges such as online training, uncertain network environments, time-coupled control decisions, and the balance between resource consumption and model accuracy. In this paper, targeting classification tasks, we study the settings of both homogeneous and heterogeneous transfer learning in cloud-edge networks via orchestrating model placement, data dispatching, and inference aggregation. We formulate non-linear mixed-integer programs of long-term cost optimization over consecutive time slots, and design polynomial-time online algorithms by exploiting the real-time trade-off between preserving previous control decisions and applying new control decisions. Our approaches produce new models by combining the existing pre-trained offline models and the online models that are continuously updated based on the inference results of data samples arriving in streams. We rigorously prove that our approaches only incur the number of inference mistakes no greater than a constant times that of the single best model in hindsight, and achieve constant competitive ratios for the total cost. Evaluations have confirmed the superior performance of our approaches compared to other state-of-the-art methods upon real-world data traces, under text classification transfer learning tasks.

The rising demand for blockchain interoperability is accelerating advancements in cross-chain bridge technologies, which are crucial for a seamless information transfer in multi-blockchain ecosystems. Existing blockchain bridges are typically classified into two categories: custodial and non-custodial. Custodial bridges use a trusted third party for easier and faster transactions but depend on custodian trust, while non-custodial bridges enhance transparency and control with smart contracts but increased complexity and latency. Currently, no bridge design successfully combines the benefits of both while avoiding their drawbacks. This paper presents EquiLink, a semi-custodial bridge that combines the benefits of both custodial and non-custodial methods. EquiLink employs a smart contract, known as the EquiLink Service, to initiate cross-chain transfers. It then uses the EquiLink Network, a system composed of remote-attested Trusted Execution Environments (TEEs), to verify and issue these transfers between two blockchains. Any eligible participants validated through remote attestation can join the EquiLink Network and contribute to the bridge’s functionality. Additionally, participants are regulated by an economic model, providing an extra layer of security through economic incentives. This semi-custodial bridge enhances transparency and control for users. Meanwhile, it mitigates the risks associated with centralized custody and decentralization. In the evaluation, EquiLink is resilient against both replay and physical attacks. Additionally, it operates efficiently, reducing transaction costs by 14.1% and latency by 18.9%

In the pursuit of data privacy and reduced latency, the adoption of edge intelligence has surged. Meanwhile, the enormous increase in AI has resulted in significant energy consumption. Edge intelligence plays a crucial role in Energy Demand Response (EDR). However, existing edge intelligence falls short of meeting the demands of co-locating training and inference tasks while satisfying EDR. Specifically, the intertwinement between balancing energy consumption, system delay and model accuracy, and uncertain future inputs adds to the challenge of designing an online sustainable system for co-located training and inference tasks. To address these challenges, we propose a novel two-timescale system for co-locating training and inference EDR. Our approach satisfies EDR by strategically planning training schedules on macro-timescales and migrating inference requests between heterogeneous edges on micro-timescales while minimizing long-term cost. We introduce a novel online polynomial time algorithm that first breaks down the problem into two subproblems, which are subsequently solved using an online-learning-based fractional algorithm and a randomized roun ding algorithm, respectively. Rigorous analysis demonstrates that our approach achieves both sublinear dynamic regret and sublinear dynamic fit. Extensive trace-driven evaluations validate the practical superiority of our approach over multiple existing methods, highlighting its effectiveness in real-world scenarios.

The explainability of electroencephalogram (EEG) decoding significantly contributes to brain-computer interfaces (BCI) and cognitive neuroscience. Although a few explainable artificial intelligence (XAI) methods have attempted to associate EEG features with the spatial and temporal characteristics of EEG signals, a model-agnostic explainability framework across various deep learning (DL) models is still lacking. In this work, AGAM-EEG (activation-gradient attribution map in EEG) is proposed, which offers adaptive model-agnostic explainability across DL models for EEG decoding. AGAM-EEG initially calculates the gradients of feature maps with respect to the predicted class at the target layer. Subsequently, AGAM-EEG infers the spatial-temporal relevance distribution by integrating activation responses with class-conditional gradients. The integration enables a refined propagation of discriminative cues across the spatial and temporal dimensions of the EEG signals. A novel technique based on the normalized discounted cumulative gain (NDCG) is designed to select the best XAI methods. AGAM-EEG is validated across 6 DL models on 2 public cognitive datasets. Compared with other XAI methods, AGAM-EEG achieves improvements of 4.0% and 3.8% in the spatial and temporal dimensions on NDCG, demonstrating superior explainability.

Sharding is a promising solution for improving blockchain scalability by distributing the workload across smaller groups of nodes called shards. However, it presents significant challenges, such as balancing tradeoffs between transactions per second (TPS), cross-shard transactions (CSTx), and confirmation latency in dynamic, online environments. While increasing the number of shards enhances TPS within individual shards, it also raises CSTx frequency, leading to higher failure probabilities, increased communication overhead, and prolonged confirmation times. Moreover, managing the number of shards and their configurations under one-sided feedback scenarios adds further complexity. To address these challenges, we model sharding as an online one-sided feedback optimization problem, focusing on maximizing long-term utilities. We introduce a polynomial-time online algorithm that adapts selection probabilities based on feedback information to address this NP-hard problem. Through rigorous analysis, we demonstrate that our approach achieves dynamic regret that grows sub-linearly over time. Extensive evaluations on real-world datasets confirm that our method outperforms existing baseline algorithms in terms of practical performance.

To make edge AI inference carbon-neutral, we perform a comprehensive mathematical and algorithmic study on the complex online management of AI model selection and placement with carbon allowance trading. This work is non-trivial due to the critical challenges such as the unknown stochastic distributions and arrivals of inference data, the exploration-exploitation tradeoff with model switching cost, and the uncertain, time-varying allowance prices and system environments. We first model a long-term stochastic cost optimization problem to capture these challenges. Then, we design a novel learning-centric decomposition-based online algorithmic framework which, on the one hand, samples and places the models repeatedly to minimize the expected inference loss with bounded model switches, and on the other hand, buys and sells carbon allowances cost-efficiently in real time toward carbon neutrality without relying on future allowance prices and system emissions. We further formally prove multiple performance guarantees of our algorithms in terms of sub-linear regret and fit. Finally, we conduct trace-driven evaluations to confirm the substantial advantages of our approach compared to baselines and state-of-the-arts in practice.

The deep learning-based (DL-based) Channel State Information (CSI) feedback faces significant challenges in openworld wireless communication systems, where CSI data is characterized by multi-scenario diversity and high dynamics. These properties introduce distribution bias and distribution shift issues: the former leads to overfitting during model training, while the latter causes model degradation during deployment and catastrophic forgetting during updates. To address these challenges across the artificial intelligence (AI) lifecycle, this work proposes a unified scenarios-aware CSI feedback framework that operates throughout the training, monitoring, and updating phases. It includes: bias-resilient model training, which introduces CSI scenario awareness to enhance CSI reconstruction while mitigating overfitting; learnable-free outof-distribution (OOD) detection for model monitoring, which identifies distribution shifts and enables efficient updates via in-distribution (ID) samples filtering; and forgetting-resistant model updating via a hybrid domain adaptation (HDA) strategy, which retains knowledge of known scenarios while improving CSI reconstruction in unseen scenarios. Extensive experiments demonstrate the superiority of the scenario-aware CSI feedback framework: it achieves up to 4.65 dB normalized mean squared error (NMSE) improvement over its prototype in random bias setups dataset, enables responsive OOD detection using both Softmax and energy-based confidence functions with an average gain of 1 dB after updates on filtering ID samples, and facilitate adaptation to unseen scenarios (up to 0.30 similarity improvement) while preserving known knowledge (above 97.6% scenario-aware accuracy) even under significant scenario shifts. Codes are available on GitHub1.

The rapid evolution of AI has driven advancements across numerous sectors. In the domain of government affairs, large language models (LLMs) hold significant potential for applications such as policy analysis, data processing, and decision support. However, their adoption in government settings faces considerable challenges, including data accessibility issues, the absence of standardized evaluation criteria, and concerns regarding model accuracy, reliability, and security. To address these challenges, we propose a comprehensive evaluation framework specifically designed for LLMs in government affairs. Built on modular principles, this framework ensures adaptability across various industries. Additionally, we introduce the Multi-Scenario Government Affairs Benchmark (MSGABench 1 ) dataset, a Chinese-language dataset specifically crafted to meet the practical needs of government professionals. Employing the proposed framework and the MSGA dataset, we conducted an empirical evaluation of 15 prominent LLMs, revealing critical insights: (1) Performance: Many models demonstrated low accuracy and reliability, particularly under minor input variations, with some dropping below 35% accuracy, whereas GPT-4 achieved above 95% reliability; (2) Security and Compliance: Significant concerns were identified, including privacy vulnerabilities, legal compliance risks, and persistent biases, which may hinder secure deployments in government contexts; (3) Task Avoidance: Certain models exhibited excessive caution, often avoiding responses to basic tasks like document classification and government-related inquiries, which restricts their usability. These findings highlight essential limitations and opportunities for improvement, contributing to the safe and effective application of LLMs in the government sector.

While ensemble methods can tackle concept drifts, obtaining pretrained models and conducting ensemble learning upon streamed data impose fundamental challenges, including the dynamic balance between system overhead and inference accuracy in uncertain system environments, and the interlacement between desired economic properties and long-term participation. In this paper, we propose the joint optimization which enables service providers to obtain models via repetitive auctions from the model providers and conduct ensemble methods online in a cost-efficient manner. We design polynomial-time online algorithms to solve the underlying non-linear mixed-integer social cost minimization problem, involving bid selection, payment allocation, model hosting, and ensemble model-weight adaption. We further rigorously prove the performance guarantees with our approach, such as the sub-linear dynamic regret for the bidding cost, the sub-linear dynamic fit for the long-term participation constraint, the truthfulness and the individual rationality for the auctions, the upper bound for ensemble inference loss, and the parameterized-constant competitive ratio for the long-term social cost. Through extensive trace-driven evaluations under real-world settings, we have validated the significant advantages of our approach over multiple baselines and state-of-the-art algorithms.

Multi-vehicle pursuit (MVP) such as autonomous police vehicles pursuing suspects is important but very challenging due to its mission and safety-critical nature. While multi-agent reinforcement learning (MARL) algorithms have been proposed for MVP in structured grid-pattern roads, the existing algorithms use random training samples in centralized learning, which leads to homogeneous agents showing low collaboration performance. For the more challenging problem of pursuing multiple evaders, these algorithms typically select a fixed target evader for pursuers without considering dynamic traffic situation, which significantly reduces pursuing success rate. To address the above problems, this paper proposes a Progression Cognition Reinforcement Learning with Prioritized Experience for MVP (PEPCRL-MVP) in urban multi-intersection dynamic traffic scenes. PEPCRL-MVP uses a prioritization network to assess the transitions in the global experience replay buffer according to each MARL agent’s parameters. With the personalized and prioritized experience set selected via the prioritization network, diversity is introduced to the MARL learning process, which can improve collaboration and task-related performance. Furthermore, PEPCRL-MVP employs an attention module to extract critical features from dynamic urban traffic environments. These features are used to develop a progression cognition method to adaptively group pursuing vehicles. Each group efficiently targets one evading vehicle. Extensive experiments conducted with a simulator over unstructured roads of an urban area show that PEPCRL-MVP is superior to other state-of-the-art methods. Specifically, PEPCRL-MVP improves pursuing efficiency by 3.95$\%$over Twin Delayed Deep Deterministic policy gradient-Decentralized Multi-Agent Pursuit and its success rate is 34.78$\%$higher than that of Multi-Agent Deep Deterministic Policy Gradient. Codes are open-sourced.

Deep learning (DL)-based channel state information (CSI) feedback provides satisfactory reconstruction accuracy of downlink CSI for the base station in massive multiple-input multiple-output (MIMO) systems. Although the introduction of codeword quantization improves the efficiency and feasibility of DL-based CSI feedback networks, the gradient problem caused by quantizers in the training stage compromises the performance of neural networks. In this paper, by considering the test channel as an equivalent of ideal rate-distortion quantization in a mutual information sense, we propose a test channel-based quantization module (TCQM) for DL-based CSI feedback networks which mitigates the gradient problem in the end-to-end training of CSI feedback networks. Moreover, the training of the CSI feedback network with TCQM is not dependent on the design of practical quantizer in the inference stage, which reduces the complexity of the training and design constraints of the CSI feedback system. Finally, for the setting of fixed feedback overhead, based on the idea of TCQM, we propose an adaptive training strategy for CSI feedback networks to evaluate the proper combination of codeword length and quantization rate of codeword elements to achieve the optimal reconstruction accuracy. Experiment results show that the proposed schemes outperform existing codeword quantization schemes in the literature.

In medical situations, head-mounted displays have gained significant attention for providing physicians with immediate access to patient information. Traditional vital signs monitoring needs physical contact to patient and separates display to physicians. However, it is difficult to integrate the advanced computer-human interaction with contactless vital signs monitoring device. This paper discusses the design and implementation of HoloCV, a scalable mixed reality-based system that supports contactless vital signs monitoring and presents real-time pre-diagnostic results of patient to the visual field of physicians. HoloCV is supported by a distributed architecture divided into three interrelated applications responsible for advanced computer-human interaction, radar and thermal infrared device integration, computation and communication infrastructure, respectively. To monitor vital signs contactlessly and continuously, the HoloCV utilizes Impulse-Radio Ultra-WideBand(IR-UWB) radar and thermal infrared camera to achieve monitoring respiration rate, heart rate, blood pressure, and temperature. By running the YOLOv7-Tiny model directly on Microsoft Hololens2 head-mounted displays, HoloCV can achieve real-time object detection and present real-time visualizations of vital signs data on the detected targets. The overall weight of the system is less than or equal to 5 kilograms. It has a detection range of 0.5m to 3m, and can continuously operate for more than 1 hour with a standby time of 5 hours. The working environment temperature ranges from 0°C to 46°C. The heart rate measurement range is from 50 to 150 BPM, the respiratory rate measurement range is from 10 to 50 BPM. The temperature measurement range is from 32 degrees Celsius to 42 degrees Celsius, and the blood pressure measurement range is from 50 to 180 mmHg. With its capability for real-time and non-contact monitoring of vital signs, this HoloCV system differentiates itself from traditional contact-based devices, providing physicians with a convenient means to assess patients' conditions and administer necessary treatments without physical contact. The codes of the proposed HoloCV are made publicly available.

It is widely agreed that reference-based super-resolution (RefSR) achieves superior results by referring to similar high quality images, compared to single image super-resolution (SISR). Intuitively, the more references, the better performance. However, previous RefSR methods have all focused on single-reference image training, while multiple reference images are often available in testing or practical applications. The root cause of such training-testing mismatch is the absence of publicly available multi-reference SR training datasets, which greatly hinders research efforts on multi-reference super-resolution. To this end, we construct a large-scale, multi-reference super-resolution dataset, named LMR. It contains 112, 142 groups of 300×300 training images, which is 10× of the existing largest RefSR dataset. The image size is also some times larger. More importantly, each group is equipped with 5 reference images with different similarity levels. Furthermore, we propose a new baseline method for multi-reference super-resolution: MRefSR, including a Multi-Reference Attention Module (MAM) for feature fusion of an arbitrary number of reference images, and a Spatial Aware Filtering Module (SAFM) for the fused feature selection. The proposed MRefSR achieves significant improvements over state-of-the-art approaches on both quantitative and qualitative evaluations. Our code and data are available at: https://github.com/wdmwhh/MRefSR.

With the rich 4D visual information of light rays, light field (LF) applications contribute to the development of immersive multimedia and virtual reality, where LF depth estimation is the critical problem. However, existing light field depth estimation algorithms deliver weak performance in edge and textureless regions. In this paper, we propose the feature-extraction and attention mechanism-based network (FEAMNet), which can effectively handle edges and textureless regions in depth maps. The FEAMNet contains a dilated-convolution and average-pooling (DCAP) feature extraction module with a large receptive field to acquire multi-scale features. And the channel attention-based disparity regression (CADR) module is introduced to measure the importance weights of different feature channels for high accuracy. The experimental results show that the FEAMNet outperforms state-of-the-art algorithms, such as OACC and DistgDisp. The implementation of our FEAMNet with the mentioned dataset is open sourced at https://github.com/lymwxq/FEAMNet.

Distributed edge computing systems that participate in Emergency Demand Response (EDR) programs can adjust workload across heterogenous edges to reduce total energy consumption. Unfortunately, this approach may not always reduce sufficient energy as required by EDR. In this paper, we propose to leverage Electrical Vehicles (EVs) and Vehicle-to-Grid (V2G) techniques to provide energy to the edge system, and design an auction mechanism to incentivize EVs to discharge energy for the edges. Yet, we face critical challenges, such as the uncertainty of EV bid arrivals, the restriction of discharging deadlines, and the desire to achieve required economic efficiency. To overcome such challenges, we design a novel online approach,$E^{3}$DR, of multiple algorithms that decompose our original NP-hard social cost minimization problem into two subproblems, solve the first subproblem via reformulation, the primal-dual optimization theory, and a careful payment design, and solve the second subproblem via standard solvers. We have rigorously proved that our approach finishes in polynomial time, achieves truthfulness and individual rationality economically, and leads to a parameterized competitive ratio for the long-term social cost. Through extensive evaluations using real-world data traces, we have validated the superior practical performance of our approach compared to existing algorithms.

In recent years, Light Field (LF) video has grabbed much attention as an emerging form of immersive media. LF collects, through a lens matrix, light information emanating in every direction, and obtains rich information about the scene, providing users with an immersive 6 Degrees of Freedom (DoF) experience. The visual content between different viewpoints is highly homogenized, suggesting the possibility of good compression and encoding. However, most fixed-structure LF coding schemes are difficult to adapt to the real-time requirements of different LF applications and best-effort network conditions causing packet loss. In this paper, we propose a dynamic adaptive LF video transmission scheme that can achieve high compression and yet provide near-distortion-free LF video when the network condition is stable. Additionally, for unstable network conditions a description scheduling algorithm is proposed, which can decode the LF video with the highest possible quality even if partial data cannot be received completely and/or timely. We achieve this by designing a Multiple Description Coding (MDC) based solution to transport the LF video compressed by a Graph Neural Network (GNN) model. Experimental results show that the scheduling algorithm can improve the quality of the decoding results by 3% to 15%. Compared with other similar schemes, our system greatly improves the reliability of the video streaming system against packet loss/error and supports heterogeneous receivers.

Owing to increasing connected medical devices and rapid development of deep learning technologies, the Internet of Medical Things (IoMT) has attracted great attention for healthcare monitoring with intelligent sensors. Radar serves as a non-contact healthcare device, continuously measuring human’s vital signs and behavior to provide daily and comprehensive long-term record on health status. However, radar sensor data collected from various users and families usually involve sensitive personal information, while traditional deep learning technologies using IoMT radar data may present high privacy leakage risks. This paper proposes FedRadar, a novel federated multi-task transfer learning framework for radar-based heartbeat rate and activity monitoring in IoMT to solve these challenges. It deals with the decentralized structure, training personalized multi-task models collaboratively, combining the shared relevance knowledge of human’s physiological information while keeping personal radar data locally for privacy protection. First, the multi-task neural network is built on the spatial-temporal radar data to capture the potential relationship and shared representations between human’s vital sign and activity. Furthermore, the federated learning with knowledge transfer scheme is designed to achieve personalized local models by transferring coarse relevant features and keeping fine-grained individual information. Extensive experiments demonstrate the effectiveness and robustness of FedRadar with 2.8% and 2.5% superior than local training model respectively on the accuracy of heartbeat rate estimation and activity classification in realistic constructed radar datasets. In addition, FedRadar is extensible and suitable to continuously monitor multiple health indicators with privacy protection in IoMT. The FedRadar codes and constructed radar datasets are available onhttps://github.com/bupt-uwb/FedRadar.

Transfer learning does not train from scratch but leverages existing models to help train the new model of better accuracy. Unfortunately, realizing transfer learning in distributed cloud-edge networks faces critical challenges such as online training, uncertain network environments, time-coupled control decisions, and the balance between resource consumption and model accuracy. We formulate distributed transfer learning as a non-linear mixed-integer program of long-term cost optimization. We design polynomial-time online algorithms by exploiting the real-time trade-off between preserving previous decisions and applying new decisions, based on primal-dual one-shot solutions for each single time slot. While orchestrating model placement, data dispatching, and inference aggregation, our approach produces new models via combining the existing offline models and the online models being trained using weights adaptively updated based on inference upon data samples that dynamically arrive. Our approach provably incurs the number of inference mistakes no greater than a constant times that of the single best model in hindsight, and achieves a constant competitive ratio for the total cost. Evaluations have confirmed the superior performance of our approach compared to alternatives on real-world traces.

The pursuit-evasion game in Smart City brings a profound impact on the Multi-vehicle Pursuit (MVP) problem, when police cars cooperatively pursue suspected vehicles. Existing studies on the MVP problems tend to set evading vehicles to move randomly or in a fixed prescribed route. The opponent modeling method has proven considerable promise in tackling the non-stationary caused by the adversary agent. However, most of them focus on two-player competitive games and easy scenarios without the interference of environments. This paper considers a Team-to-Team Multi-vehicle Pursuit (T2TMVP) problem in the complicated urban traffic scene where the evading vehicles adopt the pre-trained dynamic strategies to execute decisions intelligently. To solve this problem, we propose an opponent-aware reinforcement learning via maximizing mutual information indicator (OARLM2I2) method to improve pursuit efficiency in the complicated environment. First, a sequential encoding-based opponents joint strategy modeling (SEOJSM) mechanism is proposed to generate evading vehicles' joint strategy model, which assists the multi-agent decision-making process based on deep Q-network (DQN). Then, we design a mutual information-united loss, simultaneously considering the reward fed back from the environment and the effectiveness of opponents' joint strategy model, to update pursuing vehicles' decision-making process. Extensive experiments based on SUMO demonstrate our method outperforms other baselines by 21.48% on average in reducing pursuit time. The code is available at https://github.com/ANT-ITS/OARLM2I2.

The multi-vehicle pursuit (MVP), as a problem abstracted from various real-world scenarios, is becoming a hot research topic in the Intelligent Transportation System (ITS). The combination of Artificial Intelligence (AI) and connected vehicles has greatly promoted the research development of MVP. However, existing works on MVP pay little attention to the importance of information exchange and cooperation among pursuing vehicles under the complex urban traffic environment. This paper proposed a graded-Q reinforcement learning with information-enhanced state encoder (GQRL-IESE) framework to address this hierarchical collaborative multi-vehicle pursuit (HCMVP) problem. In the GQRL-IESE, a cooperative graded Q scheme is proposed to facilitate the decision-making of pursuing vehicles to improve pursuing efficiency. Each pursuing vehicle further uses a deep Q network (DQN) to make decisions based on its encoded state. A coordinated Q optimizing network adjusts the individual decisions based on the current environment traffic information to obtain the global optimal action set. In addition, an information-enhanced state encoder is designed to extract critical information from multiple perspectives and uses the attention mechanism to assist each pursuing vehicle in effectively determining the target. Extensive experimental results based on SUMO indicate that the total timestep of the proposed GQRL-IESE is less than other methods on average by 47.64%, which demonstrates the excellent pursuing efficiency of the GQRL-IESE. Codes are outsourced in https://github.com/ANT-ITS/GQRL-IESE.

Abstract As a new VR multimedia format, Light Field (LF) has received more and more attention. LF can support users to move freely within a certain range during the experience. However, the limitation of LF acquisition technology has become the main obstacle to its large‐scale application. Since the current hardware technology cannot produce a lens small enough to meet the needs of LF capture, the intensity of the collected LF image is usually insufficient. Although there are many software LF reconstruction algorithms have been proposed to make captured result denser, they all face the problem of poor generalization in the application process. In this work, it is attempted to locate the factors that affect the performance of LF reconstruction from both the angular and spatial domains. The analysis results show that it is affected not only by the edge and texture of the LF content in the spatial domain, but also by the adjacent disparity and the reflection characteristics in the angular domain. An indicator to quantify the impact of these factors on reconstruction performance is also proposed, which will be helpful to design a new generalized adaptive LF reconstruction algorithm in the future.

Due to the enormous energy consumption and the wide geographic distribution, Electrical Vehicle (EV) charging stations are believed to have great potential in Emergency Demand Response (EDR) participation. However, EDR limits the electricity drawn from the power grid by the charging station, and can pose threats to satisfying EVs’ charging demand. In this paper, in order to complement the charging station’s energy supply to meet the dynamic EV charging demand, we formulate an online EV charging scheduling problem under EDR as a non-linear mixed-integer program, and propose a novel polynomial-time online algorithm and auction mechanism to jointly incentivize EVs with energy to sell their energy and utilize the charging station’s local generator to produce energy. Our approach conducts an auction in each single round based on a primal-dual method and ties these auctions over time to optimize the system’s long-term social cost, while accommodating the local generator’ on/off-state control, each EV bidder’s cumulative energy budget constraint, and the power grid’s EDR energy cap. Our approach achieves the economic properties of truthfulness, individual rationality, and computational efficiency simultaneously for each auction, and a parameterized-constant competitive ratio for the long-term social cost. By rigorous theoretical analysis and trace-driven experimental studies, the results exhibit that our approach outperforms multiple alternative algorithms regarding the social cost, attains the economic properties, and also executes efficiently in practice.

Deep learning (DL)-based channel state information (CSI) feedback improves the capacity and energy efficiency of massive multiple-input multiple-output (MIMO) systems in frequency division duplexing mode. However, multiple neural networks with different lengths of feedback overhead are required by time-varying bandwidth resources. The storage space required at the user equipment (UE) and the base station (BS) for these models increases linearly with the number of models. In this paper, we propose a DL-based changeable-rate framework with novel quantization scheme to improve the efficiency and feasibility of CSI feedback systems. This framework can reutilize all the network layers to achieve overhead-changeable CSI feedback to optimize the storage efficiency at the UE and the BS sides. Designed quantizer in this framework can avoid the normalization and gradient problems faced by traditional quantization schemes. Specifically, we propose two DL-based changeable-rate CSI feedback networks CH- CsiNetPro and CH- DualNetSph by introducing a feedback overhead control unit. Then, a pluggable quantization block (PQB) is developed to further improve the encoding efficiency of CSI feedback in an end-to-end way. Compared with existing CSI feedback methods, the proposed framework saves the storage space by about 50% with changeable-rate scheme and improves the encoding efficiency with the quantization module.

Mobile users are often reluctant to participate in federated learning to train models, due to the excessive consumption of the limited resources such as the mobile devices’ energy. We propose an auction-based online incentive mechanism, FLORA, which allows users to submit bids dynamically and repetitively and compensates such bids subject to each user’s long-term battery capacity. We formulate a nonlinear mixed-integer program to capture the social cost minimization in the federated learning system. Then we design multiple polynomial-time online algorithms, including a fractional online algorithm and a randomized rounding algorithm to select winning bids and control training accuracy, as well as a payment allocation algorithm to calculate the remuneration based on the bid-winning probabilities. Maintaining the satisfiable quality of the global model that is trained, our approach works on the fly without relying on the unknown future inputs, and achieves provably a sublinear regret and a sublinear fit over time while attaining the economic properties of truthfulness and individual rationality in expectation. Extensive trace-driven evaluations have confirmed the practical superiority of FLORA over existing alternatives.

We present a 4D Light Field (LF) video dataset, collected by a custom-made camera matrix, to be used for designing and testing algorithms and systems for LF video coding, processing, and streaming. Compared to existing LF datasets, ours provides LF videos, as opposed to only images, and at higher frame resolution, higher number of viewpoints, and/or higher framerate, offering the best visual quality LF video dataset. To achieve this, we built a 10 x 10 LF capture matrix composed of 100 cameras, each with a 1920 x 1056 resolution. We used this matrix to record videos in real and varying illumination and scene dynamics conditions. The dataset contains a total of nine groups of LF videos: eight groups collected with a fixed camera matrix position and orientation recording indoor potted plants, furniture, etc., and the last group collected by rotating around an outdoor environment with roadside vehicles, pedestrians, etc. Each group of LF videos consists of 100 video streams encoded with H.265/HEVC. Scene changes vary from static to slightly dynamic to highly dynamic, providing a good level of diversity. As an example, we present the results of a depth estimation method and show that our dataset can be used for applications such as objection detection, 3D modeling, and others.

Massive multiple-input multiple-output (MIMO) wireless communication technology with the characteristics of hyperconnectivity is an ideal channel to connect the industrial Internet of Things (IIoT) and the cyber-physical system. It provides stable and reliable connectivity from the data center to distributed user terminals and the IIoT. However, traditional massive MIMO suffers from high power consumption and fabrication cost. The design of energy-efficient massive MIMO technology is essential for larger scale industrial deployments. In this article, we design three types of nonlinear RF chain structures, which not only reduce the power consumption of massive MIMO systems but also save fabrication costs. Information theoretic analysis demonstrates the power efficiency performance of our nonlinear system design. Our nonlinear MIMO system designs can increase the power efficiency by up to 2.3 times compared with the traditional MIMO system. We have demonstrated that our systems can achieve the same uplink rate as traditional MIMO by increasing the number of receiving antennas but with less overall power consumption. We also proposed an algorithm to overcome the problem of low computational efficiency due to high-dimensional integration when calculating the uplink achievable rate of nonlinear MIMO. Moreover, we reveal that when the skew-normal distribution is used as signaling, the nonlinear MIMO systems can achieve better performance than the Gaussian distribution.

The rise of Artificial Intelligence of Things (AIoT) makes everything connected smartly, which can enrich industrial productivity. With the help of learning-based wireless communications, terminals in AIoT can communicate with each other and collaborate intelligently. However, one of the critical issues faced in AIoT deployment is the lack of available large datasets for the training of artificial intelligence algorithms in the industrial environment. In this paper, we propose a channel data augmentation algorithm for the dataset limitation cases in intelligent industrial wireless communication systems using generative adversarial networks (GAN). Specifically, we first show the performance of deep learning-based channel state information (CSI) feedback algorithm trained with different size of datasets. Then we develop a GAN for the channel data augmentation to enhance the performance of CSI feedback algorithm. Finally, we apply the enhanced approach to an insufficient dataset for the performance evaluation. Experimental results show that our method can achieve at most 3dB performance improvement than other traditional data augmentation approaches in increasing the accuracy of CSI feedback algorithm when the size of dataset is limited to 10000.

Channel state information (CSI) reporting is important for multiple-input multiple-output (MIMO) wireless transceivers to achieve high capacity and energy efficiency in frequency division duplex (FDD) mode. CSI reporting for massive MIMO systems could consume large bandwidth and degrade spectrum efficiency. Deep learning (DL)-based CSI reporting integrated with channel characteristics has demonstrated success in improving CSI compression and recovery. To further improve the encoding efficiency of CSI feedback, we develop an efficient DL-based compression framework CQNet to jointly tackle CSI compression, codeword quantization, and recovery under the bandwidth constraint. CQNet is directly compatible with other DL-based CSI feedback works for further enhancement. We propose a more efficient quantization scheme in the radial coordinate by introducing a novel magnitude-adaptive phase quantization framework. Compared with traditional CSI reporting, CQNet demonstrates superior CSI feedback efficiency and better CSI reconstruction accuracy.

The use of high-quality 360° panoramic video is booming in the video industry. However, existing schemes for smartphones suffer from significant bandwidth consumption as they transmit the entire panoramic views in very high resolutions. This demand for bandwidth becomes even more problematic when multiple adjacent smartphones compete to access the same content, which further challenges a wireless network's capacity, and when the available bandwidth fluctuates much more than wired networks. In this paper, we propose a cooperative streaming scheme for tile-based 360° video using scalable video coding (SVC) to maximize a group of users' quality of experience. We formulate an optimization problem to choose optimal downloading and sharing subsets from a set of all requested SVC layers of tiles to maximize the effective quality of the users' viewport while meeting the feasibility of the bandwidth of heterogeneous networks. We then show that the problem is NP-hard and compose a heuristic approach. In the approach, we rank the SVC layers based on the aggregated group-level preference to guide the devices' downloading and sharing activities. A prototype on the Android platform is developed to test the approach's performance, and the real-world results show that our proposed scheme outperforms baseline alternatives.

Modern vehicles are equipped with wireless communication technologies, allowing them to communicate with each other and forming large self-organized ad hoc networks (or vehicular ad hoc networks (VANETs)). VANETs, while promising new approaches for improving road safety, require privacy of vehicles (or drivers) to be protected from a variety of threats. Although pseudonym schemes have provided a promising solution at the upper layers, privacy attacks could still be carried out from medium access control (MAC) layer. In this paper, we first introduce a new MAC layer context linking attack, which could link the old and new pseudonyms of a vehicle by analyzing its transmission characteristics. To deal with the attack, we propose a time division multiple access based MAC-layer-Attack-Resistant Pseudonym (MARP) scheme. Unlike traditional approaches that design the MAC protocols and pseudonym schemes separately, MARP allows vehicles to change their transmission slots and pseudonyms collaboratively. Thus, the unlinkability is guaranteed. Taking the pseudonym age, anonymity set size and time-to-confusion as the location privacy metrics, we derive an analytical model to quantify location privacy achieved in MARP. The analytical model is general to be applied for other pseudonym schemes. Extensive simulation results have validated the analytical model, showed that MARP can resist the MAC context linking attack and guarantee location privacy and efficient transmission for vehicles in VANETs.

Pseudonyms have been adopted to preserve identity privacy of nodes in distributed networks. Frequent and unlinkable changes of pseudonyms need to be enabled by having at least k nodes change together to confuse potential eavesdroppers. Existing approaches either depend on the coordination from central controllers, or involve interactive signaling between the nodes. This can potentially compromise privacy. This paper proposes a fully uncoordinated approach to change pseudonyms in distributed networks, where each node uses a pseudonym until its expiration and then changes after a random delay. We develop a new model to analyse the time-varying population of changing pseudonyms. Critical conditions are analytically established, under which individual nodes can independently change their pseudonyms while their identity privacy is preserved. The conditions are validated by illustrative examples. Corroborated by simulations, the accuracy of the analytical model improves, as the number of nodes increases. The analysis confirms that, the k-anonymity can be achieved at a negligible throughput loss in the case of large networks.

Proactive content caching at the network-edge is envisioned as a key technique to reduce backhaul congestion and latency in popular content delivery. Data storage units, however, require additional energy, which offers a challenge to researchers who intend to reduce energy consumption up to 90% in next generation networks. The concept of powering data storage units by renewable energy aligns with this energy reduction target. In this article, we introduce a proactive caching strategy, which caches content in helper nodes in a cooperative manner considering intermittent renewable energy and variable content load for various hours of the day. The hypothesis is that the amount of renewable energy available to various helper nodes varies depending on the node location and time of the day. The content load across helper nodes also varies with time. As such, if helper nodes work cooperatively by considering the available renewable energy and content load at each helper node, the aggregate non-renewable energy consumption for content caching can be further reduced. We model the research challenge as an optimization problem. Furthermore, we also present a heuristic solution. Our proposed scheme achieves a significant reduction in non-renewable energy consumption by 23% over the existing green solution.

As a new form of volumetric media, Light Field (LF) can provide users with a true six degrees of freedom immersive experience because LF captures the scene with photo-realism, including aperture-limited changes in viewpoint. But uncompressed LF data is too large for network transmission, which is the reason why LF compression has become an important research topic. One of the more recent approaches for LF compression is to reduce the angular resolution of the input LF during compression and to use LF reconstruction to recover the discarded viewpoints during decompression. Following this approach, we propose a new LF reconstruction algorithm based on Graph Neural Networks; we show that it can achieve higher compression and better quality compared to existing reconstruction methods, although suffering from the same problem as those methods—the inability to deal effectively with high-frequency image components. To solve this problem, we propose an adaptive two-layer compression architecture that separates high-frequency and low-frequency components and compresses each with a different strategy so that the performance can become robust and controllable. Experiments with multiple datasets 1 show that our proposed scheme is capable of providing a decompression quality of above 40 dB, and can significantly improve compression efficiency compared with similar LF reconstruction schemes.

Streaming services have become increasingly popular in recent years, causing an upsurge in video traffic. The continuing upsurge will put enormous stress on existing network infrastructures. This has motivated researchers to find innovative solutions to address this challenge. Proactive content caching at the network edge is considered one such innovative solution, which can reduce backhaul congestion during evening peak hours. Consequently, researchers have introduced numerous approaches to cache content at the network edge. While the focus so far is on reducing the congestion, security issues in relation to content breach at caching nodes have not been adequately addressed so far. Content storage units at the network edge are more vulnerable to malicious attacks, and the loss incurred in this process can be significant. In this paper, we introduce a security aware caching technique to reduce the amount of potential loss caused by security attacks. We investigate the trade-off between the savings achieved from the implementation of proactive caching at caching nodes and the probable loss caused by security attacks. We model the research question as an optimization problem, and provide an optimal solution, which selects the suitable content to be cached at the most suitable nodes so that the loss caused by content breach becomes marginal. Simulation results show that our proposed technique significantly minimizes the loss caused by security attacks.

As a new form of volumetric media, the technology of light field and its compression has gradually become the research hotspots in academia. The scheme of compressing using the sparsity of the light field is a very promising idea, which has the characteristics of high compression rate and is not affected by the occlusion of scene objects. However, the instability of the reconstruction algorithm's performance on different datasets limits the further application of this solution. Since the quality of the decompression outputs will be limited below the reconstruction result, the poor performance of the reconstruction algorithm on some light field images will result in a very low PSNR upper limit for the compression scheme. This paper finds that the main reason for this performance problem is the poor ability of the algorithm to process the high-frequency components of the light field. And in order to solve it, an adaptive two-layer light field compression scheme is presented. The proposed scheme separates the high-frequency components and the low-frequency components of the light field so that they can be independently compressed. Through the adaptive adjustment, the data of different frequency component can adopt different compression strategies, so that the performance of the proposed scheme can be optimal. Experiments with multiple datasets1 show that the proposed scheme can break the upper limit of PSNR caused by sparse reconstruction and is capable to provide decompression results above 40 dB. It also achieves significant improvement in compression efficiency under diverse requirements.

The Internet of Things (IoT) is visioned to connect everything in the world by a common networking technique. In spite that Internet protocol is the most prevailing networking solution, it is difficult to adapt to IoT which is born with scalability, heterogeneity, and dynamics. Thanks to the content-centric communication paradigm, it exerts data-naming strategy to incorporate the heterogeneity and dynamics so as to apply for IoT, composing Named Data Networking (NDN) of Things. However, the paradigm also introduces new types of security attacks. In this paper, the NDN of Things architecture will be illustrated and the security analysis is conducted. Furthermore, the potential security attacks of NDN of Things are categorized and the performance impact caused by security attacks is evaluated. Finally, the solutions for NDN of Things security attacks are discussed and a blockchain solution is illustrated.

People counting is one of the hottest issues in sensing applications. Impulse radio ultrawideband radar has been extensively adopted to count people because it provides a device-free solution without illumination and privacy concerns. However, current solutions have limited performances in congested environments due to signal superpositions and obstructions. In this letter, a hybrid feature extraction method based on the curvelet transform and the distance bin is proposed. First, 2-D radar matrix features are extracted at multiple scales and multiple angles by applying the curvelet transform. Then, the distance bin concept is introduced by dividing each row of the matrix into several bins along the propagating distance to select features. A radar signal data set is constructed for three density scenarios, including people randomly walking in a constrained area at densities of three and four persons per square meter and people in a queue with an average between-person distance of 10 cm. The number of people in the data set scenarios varies from 0 to 20. Four classifiers-a decision tree, an AdaBoost classifier, a random forest, and a neural network-are compared to validate the hybrid features. The random forest achieves the highest accuracy of above 97% in the three density scenarios. To further investigate the reliability of the hybrid features, they are compared with three other features: cluster features, activity features, and features extracted by a convolutional neural network. The comparison results reveal that the proposed hybrid features are stable, and their performance is substantially more effective than that of the others.

In vehicular ad hoc networks (VANETs), safety messages must be protected for location privacy. Pseudonym schemes have provided a promising solution. However, attacks could still be carried out from the medium access control (MAC) layer. In this paper, we present a new MAC semantic linking attack that links the new and old pseudonyms by analyzing the vehicles' transmission patterns in the MAC layer, even if they change pseudonyms simultaneously. To deal with the attack, a MAC layer aware pseudonym (MAP) scheme is proposed. The MAP scheme is compatible with the standard and coordinates each vehicle to access the wireless medium in a time- slotted manner. In MAP scheme, vehicles change pseudonyms and slot utilization pattern consistently. The interactive influence between the pseudonym changing and safety message transmission is evaluated. Taking the pseudonym age, anonymity set size, time-toconfusion and packet delivery ratio as the performance metrics, extensive simulation results have verified that the MAP scheme can improve the location privacy and enhance transmission efficiency in VANETs.

With the rapid development of mobile communication, data traffic is exploding, which leads to a more dense and irregular deployment of the small cells. Large-scale and dense deployment of small cells will bring about huge energy consumption and strong interference. Meanwhile the evolution trend of future mobile network is extending to three dimensional (3D) space. So the analysis of Energy Efficiency (EE) for future 3D ultra dense mobile network is of great concern. In this paper, we optimize the Base Station (BS) density for enhancing EE by the combine of sleeping strategy and coordinate multi-point transmission under 3D dense urban scenarios using the tool of 3D stochastic geometry. Firstly, we derive the coverage probability and energy efficiency expressions. Then based on monotonicity analysis, the optimal BS density that satisfies coverage probability constraint is calculated. And the numerical results show both the coverage probability and energy efficiency have a significant improvement compared with deploying BS sleeping strategy only.

The performance of a vehicular ad hoc network (VANET) largely depends on the underlying medium access control (MAC), as it determines the schedule utility of physical resources. However, in existing time-division multiple access (TDMA)-based MAC protocols, a node usually acquires slots based on what each node senses, which is typically the coupling of the control and data plane. This coupling makes the TDMA protocols unable to rapidly and agilely deal with the challenges in VANETs, such as high mobility and dynamic network densities. Inspired by the software-defined network (SDN), we propose a novel SDN-based MAC protocol, named sdnMAC, to handle these challenges. A novel roadside openflow switch (ROFS) is designed as the roadside unit, controlled by the openflow controller. The sdnMAC can be divided into two tiers, the management of ROFSes (MA-ROFS) by the controller and the management of vehicles (MA-VEH) by ROFSes. In MA-ROFS, the controller schedules the cooperative sharing of time slot information among ROFSes. In MA-VEH, each ROFS allocates slots based on this shared information, thus decoupling of the control and data plane. This decoupling provides great rapidness and agility to sdnMAC, thus handling the rapid mobility and varying vehicle densities. Extensive simulations using network simulator NS3 and traffic simulator SUMO are performed. It is shown that the sdnMAC protocol can better meet the requirements of cooperative safety in VANETs.

To meet the booming demand for higher data rates, Small Base Stations (SBSs) are deployed densely and irregularly, leading to the rapid increases in energy consumption. Meanwhile, the evolution trend of future mobile network is extending to three dimensional (3D) space. Therefore, the energy efficiency for future 3D ultra dense mobile networks is of high significance. In this paper, we focus on analyzing the energy efficiency with sleeping strategy of 3D dense mobile network. Firstly, we derive the expressions of the coverage probability and energy efficiency by using the tool of 3D stochastic geometry, where the locations of SBSs and users are modeled as two independent 3D spatial Poisson Point Processes. In addition, the expression of energy efficiency for BS activation probability is derived to observe explicitly the impact of sleep mode on the energy efficiency. Finally, simulation results confirm the accuracy of our analysis.

Communication security is one of the most significant issues to draw people's attention in vehicular ad-hoc networks (VANETs). To prevent from malicious nodes and ensure the confidence and integrity of the messages, vehicles have to authenticate each other and support message signature and encryption. As the most prospective approaches, though the generally accepted wireless access for vehicular environment (WAVE) specifications have standardized the security algorithms to exchange the confidential data between vehicles, few of systems consider two technical aspects of signature and encryption together and implement on the real on-board unit (OBU). In this paper, a WAVE based secured vehicular communication system has been developed and WAVE security algorithms ECDSA and ECIES have been implemented to enhance communication security. The certificate authority (CA) has been introduced to the algorithms for authentication and preventing from the malicious nodes. The alternative security levels have been designed according to the different types of messages. Considering the execution time and communication cost of the constituent steps, real-world test has been conducted in our proposed application scenarios to manifest how security procedures affect the communication performance. The results have attested that the system in different security levels can achieve a secure data transmission with no effect on communication.

Many broadcast protocols have been proposed in Vehicular ad-hoc Network (VANET) for safety applications and traffic efficiency. GeoBroadcast, which the sender sends information to the geographical area, has been standardized by the ETSI Technical Committee ITS. The routing protocol is a key technology satisfying communication requests of high reliability, low delay and universality for GeoBroadcast. However, there are few implementation and field test of routing protocol. This paper proposes a Received Signal Strength Indicator (RSSI) based Omni-Directional Routing (ROR) Algorithm. This protocol based on the combination of two protocols: the Greedy Forwarding (GF) that is a sender-based protocol, and the Contention-Based Forwarding (CBF) that is a receiver-based protocol. Furthermore, ROR takes RSSI, driving direction and dynamic scene into account. Meanwhile we conduct extensive field tests with more than twenty vehicles to evaluate the performance of vehicle communication in terms of Packet Loss Rate (PLR), Node Coverage Ratio (NCR) and Average End-to-End Delay (E2ED). By comparing the performance of CBF and Advanced Forwarding protocol with the ROR, ROR in real vehicle's environment has higher NCR and lower E2ED, in particular when the topology of the vehicles changes frequently in the target area.

With the rapid development of streaming media, communications between Device-to-Device is becoming a magnetic solution to improve the performance of cellular network.Although numerous papers have been published in the past, most of them just focus on novel description but ignore the classical theory to be innovated. In this paper, inspired by BitTorrent protocol, we propose a dynamic d2d system for video sharing using cellular interface and WiFi Direct technology. In our scenario, we consider a cluster of users within proximity of each other viewing the same video, and traffic of cellular will be offloaded onto WiFi Direct. In this paper, we implement a BitTorrent similar system on mobile devices to share video named MTV, which constructs a D2D network and converts the transmission between users from previous cellular interface to wifi interface. Benefiting from video sharing and properties of BitTorrent, our system will not only bring improvements on downloading rate and reduction on traffic consumption, but also support dynamic joining and leaving which were rarely mentioned in previous work. And we provide several experimental scenes to demonstrate the advantages of our proposed system on aspect of speed, traffic and dynamic adaption.

Nowadays social networking services (SNS) have become an important part of our daily-life. Thanks to the rapid development of mobile computing technologies, more and more people start to use mobile devices, e.g., smartphones and tablets, to access the SNS. Different from the traditional way, i.e., using the desktop PCs to access the web interface of the SNS, using mobile devices will introduce more flexibility. However, there is a lack of a comprehensive study to evaluate the effects of using mobile devices to access SNS. In this paper, we study the Twitter social network by comparing between the emerging mobile users and traditional web users. We have three major findings. First, by examining the tweet posting behavior, we find that mobile users are more active for posting shorter tweets, while less active for retweeting. Second, by referring to the social structure, we can see that the social network composed by mobile users are less clustered, while the radius and diameters of mobile social graph are shorter. Finally, we introduce one classic simulation scenarios, which is information diffusion in SNS. The simulation results indicate that the mobile effects actually decrease the scope of information diffusion as they are less active for message forwarding.

The data caching in Device-to-Device (D2D) networks enables the quick data access in mobile networks. The D2D channels allows content sharing when two devices are in close proximity which can help improve resource utilization and network capacity. Due to the selfish nature of users, they wish to get as much replication as possible in the opportunistic connections, seeking to maximize their own profit. However, caching resources for other nodes may lead cost to the node who serves as cache. It lacks incentives for mobile nodes to cache for other peers in D2D network. In this paper, we use an incentive method to make mobile nodes cache for others and aim to minimize the total cost of getting object data in the network. The total cost is occurred by the cache placement of cache nodes and accessing cost of the other nodes. We consider the social ties and physical distance as the factors for the cost. We model the data cache problem as a socially-aware payment game, and we introduce a hierarchical caching scheme to incentive nodes to cache, which use the user relationship to construct the cost function. In order to model user relationship, we divide the network into three categories in perspective a node: self, friends and strangers. We obtain the Nash equilibrium of the game and propose a heuristic algorithm to solve the cache placement problem. The extensive simulation results show that our algorithm gain significant cache benefit.

In this paper, we propose a hierarchical architecture based on software defined networking (SDN) to manage the physical resources in vehicular ad-hoc networks (VANETs), namely sdnMAC. First of all, a novel roadside unit (denoted by ROFS) is designed, which is an OpenFlow switch equipped with a wireless interface. Then, a hierarchical architecture is proposed for sdnMAC, consisting of two tiers, one is the management of the ROFSs by the Controller, the other is management of vehicles by ROFSs. Due to the cooperative share of slots information, sdnMAC can provide pre-warning of collisions and agility to topology change and varying densities of vehicles.

In this paper, reinforcement learning (RL) based power control algorithm in underlay D2D communication is studied. The approach we use regards D2D communication as a multi-agents system, and power control is achieved by maximizing system capacity while maintaining the requirement of quality of service(QoS) from cellular users. We propose two RL based power control methods for D2D users, i.e., team-Q learning and distributed-Q learning. The former is a centralized method in which only one Q-value table needs to be maintained, while the latter enables D2D users to learn independently and reduces the complexity of Q-value table. Simulation results show the difference of the two Q-learning algorithm in terms of convergence and reward function. In addition, it is shown that through our distributed-Q learning, D2D users not only are able to learn their power in a self-organized way, but also achieve better system performance than that using traditional method in LTE(Long Term Evolution).

In this paper, a scenario was considered that cellular user equipments (UEs) and device to device (D2D) communication pairs exist in a full duplex cell. Limited frequency resources are shared by a large number of UEs, and complex interference is introduced due to resource sharing between uplink, downlink UEs and D2D links. To manage the resource and achieve the maximum total system capacity, a non-deterministic polynomial (NP) hard optimization problem is formulated. To efficiently solve the problem, a Graph based Two-step Resource Allocation (GTRA) algorithm is proposed. In the first step, a full duplex base station (BS) allocates resources to half duplex uplink and downlink UEs by a graph coloring based algorithm. The second step is a bipartite graph based Multi-Stage Matching (MSM) algorithm to allocate resources to D2D pairs. The GTRA algorithm can effectively allocate the spectrum resources with low complexity while guaranteeing the Quality of Service (QoS) of cellular UEs as well. Simulation results show that our proposed algorithm performs better than the reference algorithms.

Advertising among vehicles has become popular with the proliferation of vehicular ad-hoc networks (VANETs). Since the price of the advertisements broadcast in such networks decay over time, distributing advertisements with a high price value to more private vehicles can generate more revenues to the sellers. In this paper, we consider a bus-based priced advertising scenario in a VANET, in which the buses act as the sources of advertisements and broadcast advertisements to private vehicles running within their communication range. Meanwhile, in the area where no bus exists, private vehicles share their advertising segments. The manner in which the buses and the private vehicles distribute and share advertisements in the network so as to draw the largest benefit is addressed in our formulated problem. To solve this problem, a bus-based priced advertisement dissemination scheme dubbed Bus-Ads is proposed by using coalition formation game. First, a bus-broadcast method is presented to enable each bus to distribute the priced advertising segments with the largest potential benefit to surrounding private vehicles. Second, we apply coalition formation game to guide private vehicles to construct broadcast coalitions for efficient advertisement sharing. Simulation results demonstrate that our proposed Bus-Ads method can achieve about twice the total benefits compared with that of the non-coalition-based approach.

Opportunistic Mobile Social Networks (MSNs) as a kind of social network in which nodes are opportunistically connected. Many data routing strategies have been proposed for opportunistic MSNs. Most of them apply a utility for relay selection that a node with a higher utility value is selected as relay. However, such utility-based routing strategies run into dead end problem in which the data is stuck into a node with local maximal utility value. In this paper, we propose a virtual routing method named VIRO, which exerts conformal mapping to convert the local topology of dead end into a virtual geometric map to guarantee data dissemination to the next relay. We first convert the utility into geometric planner, and then conduct the discrete Ricci Flow bypass the gap between the dead end and next relay. Extensive experiment results suggest VIRO can reduce the ratio of dead end effectively so that the data delivery ratio is enhanced up to 42% by increasing only a slight amount of delay and cost.

Nowadays, Voice of LTE (VoLTE) is used to support voice communications in LTE network. As one of the key techniques for VoLTE, semi-persistent scheduling (SPS) is important to improve the capacity of VoLTE users. However with SPS, the resource and modulation and coding scheme (MCS) are usually decided by the initial scheduling and keep unchanged during the active state. Considering the continuously changing channel, it is hard to ensure the performance of the voice packet. In order to solve this problem, a resource allocation algorithm is proposed based on the prediction of channel quality change. Furthermore, the data rate of Adaptive multi Rate(AMR) codec is adaptively adjusted in the resource allocation algorithm to reduce VoLTE's impact on other data services. Simulation results prove that the proposed algorithm can reduce the retransmission of VoLTE users and improve the throughput performance of other traffic businesses.

With the widespread popularity of mobile terminals, wireless video has become an indispensable part of daily life. The conventional wireless video transmission scheme which consists of separate digital source coding and digital channel coding is now unable to meet the broadcast and mobile scenarios owing to the dramatic changes in its channel conditions. However, a newly uncoded transmission scheme called SoftCast was presented to provide graceful quality transition. SoftCast performs power allocation over chunks to decrease the amount of Meta data. But the magnitudes vary dramatically in some chunks and SoftCast expends very large power to transmit some coefficients with large value. This paper introduces a scalable video SoftCast using Magnitude Shift to constraint the value of DCT coefficients. It only costs little power and bandwidth to transmit the overhead generated by Magnitude Shift. The experimental results show that the proposed scheme can improve the performance of the original SoftCast using 3D-DCT transform by 2-5dB.

Heterogeneous networks (HetNets) have been considered as a promising technique for improving spectral efficiency, but the energy efficiency influenced by the fluctuation of user numbers should not be neglected to achieve green communications. We introduce the energy-efficient switch-off mode algorithm for pico cells to reduce power consumption in the self-organizing network (SON). Once the switch-off mode is initiated in some picked pico cells, the users connecting to these cells would face the problem of redistribution. In this paper, we introduce the energy saving (ES) strategy based on the prediction of load capability to select pico cells to enter switchoff mode. Furthermore, network flow based load balancing (LB) is proposed to provide solution of uneven load status caused by ES. System level simulations are conducted to exhibit the performance enhancement that the proposed algorithm can reduce energy consumption as well as improve the balanced degree of resource allocation significantly.

The performance of the mobile video broadcast is weakened when applying the traditional broadcast scheme which is forced to pick a single bit rate supported by the worst receiver. It leads to the drawback that receivers with better channels cannot obtain better video qualities. This paper proposed distributed Realcast, an analog video delivery scheme based on real value transmission, to provide differentiated video service. It utilizes a series of linear operations to encode video without digital processing so that the channel noise is proportional to the distortion in video pixels and achieve channel adaptive transmission. Meanwhile, a distributed video coding scheme combining the frame difference method and the coset coding is proposed to realize the efficient video compression and prevent error propagation. In addition, distributed Realcast performs the motion compensated extrapolation method at both the encoder and decoder to avoid the transmission of motion vectors and release the stress of limited bandwidth. Simulation results indicate that distributed realcast outperforms Softcast, a representative analog video broadcast scheme, by nearly 3db.

With the deployment of the fourth generation communication networks, mobile video broadcast services are becoming one of the essential parts of users' daily lives. As an efficient way for mobile video transmission, digital broadcast scheme is faced with the challenge of cliff effect. A novel real-value scheme called SoftCast can eliminate the cliff effect, but not efficient in removing inter- frame correlation. The proposed scheme is similar to SoftCast, and to fully exploit the inter-frame redundancy, motion alignment is involved in the temporal wavelet transform. Then the dense constellation mapping of 64K quadrature amplitude modulation is utilized to maintain the real-value property for wireless transmission. Moreover, metadata is extracted from the previous processes and transmitted in the conventional mechanism to facilitate decoding. Simulation results verify the scalability and robustness of the proposed scheme in the mobile video broadcast applications.

Compared with the CSMA based MAC protocols, the slotted reservation solutions could be more adaptable for VANETs. However, the high mobility and mobile hidden terminal (MHT) issues in vehicular environments cause a challenge of efficient and scalable slotted scheduling for TDMA MAC protocols. This paper proposes a novel near collision free reservation (CFR) MAC which is based on a recent VeMAC protocol to provide near collision free scheduling and address the mobile hidden terminal issue in VANETs. In former distributed TDMA MAC proposals like VeMAC, on the control channel of DSRC communication system, each vehicle randomly reserves dedicated time slots. However, the slot reservation of CFR MAC is more structural, based on the driving status and traffic flow of each vehicle. The performance of CFR MAC is verified via simulations and comparisons with IEEE 802.11p and VeMAC to demonstrate that superiority of CFR MAC.

To meet the requirement of very-high-rate-data transmission over wide bandwidths, carrier aggregation (CA) has been regarded as an important technology for Long Term Evolution-Advanced (LTE-A). It considers both primary component carrier (PCell) and secondary component carrier (SCell) and many operations are based on the PCell. In this paper, the load balancing performance of dynamic SCell measurement period relaxing in the LTE-A system with CA has been discussed. Furthermore, it gives the result of SCell measurement period relaxing window under different user equipment speed which is both energy-saving and harmless to the system performance.

To meet the requirement of very-high-rate-data transmission over wide bandwidths, carrier aggregation (CA) has been regarded as an important technology for Long Term Evolution-Advanced (LTE-A). It considers both primary component carrier (PCell) and secondary component carrier (SCell) and many operations are based on the PCell. In this paper, the load balancing performance of dynamic SCell measurement period relaxing in the LTE-A system with CA has been discussed. Furthermore, it gives the result of SCell measurement period relaxing window under different user equipment speed.

Scalable video coding technologies provide adaptive video applications in heterogeneous and polytropical conditions. However, the highly hierarchical feature makes the loss or unsuccessful recovery of the base-layer to be catastrophic. In this paper, a distributed scalable video coding scheme using the new advances of compressed sensing is proposed to solve this problem at the energy-constrained encoder. The wavelet coefficients of the video frames have inherent fidelity scalability which is utilized in our scheme. Furthermore, the democracy of measurements reduces the risk of base-layer loss over the packet loss channel. Experimental results show that our scheme outperforms the existing scalable compressed sensing scheme by about 2dB.

Handover Parameter Optimization (HPO) and Load Balancing (LB) are two Self-Organization network (SON) aspects which aim at improving LTE system handover performance and user's satisfaction respectively. However, there is often counteraction between LB and HPO, because LB would increase the frequency of inter-cell handover and correspondingly increase the possibility of handover problems. Furthermore, most of the LB and HPO jointly optimization methods don't consider the network allowed maximum radio link failure (RLF) ratio, which would increase the possibility of call dropping although the cell loading is balanced. In this paper we introduce the network allowed maximum RLF ratio as a key indicator and a dynamic hysteresis-adjusting (DHA) method to harmonize the two aspects. Furthermore, we take the realistic network situations into account to obtain a more reliable result. The proposed method is evaluated by a series of system-level simulation which witnesses an improvement in handover performance and number of satisfied users in LTE networks.

High Speed Railway(HSR) scenario was currently agreed as the main scenario in the 3GPP Rel.11 study item, Mobile Relay for E-UTRA. Usually, communications of high-speed railway systems suffer from problems such as Doppler spread, radio condition abrupt change and handover failure. Mobile relay is a promising scheme to solve these problems, but the quantitative performance improvement to HSR has not been fully evaluated and analyzed. In this paper, a high speed scenario with mobile relay integrated is presented to analyze these issues for LTE Advanced system. The proposed mobile relay solution with group mobility is evaluated by a series of system simulation which witnesses an improvement in train user throughput as well as system throughput, and higher handover success ratio with a decrease in radio link failure ratio.

The max C/I, Round Robin (RR) and Proportion Fair (PF) are three primary scheduling schemes adopted by LTE system to allocate shared resources among users in the time-frequency domain. However, most of the scheduling methods are static and ignore the relation between user dispersion degree of the sector and maximum PRB number (MaxPRB) allocated to one user. In this paper, we propose an improved dynamic MaxPRB-adjusting scheduling scheme (DDS) based on user SINR dispersion degree, which can win better tradeoff between throughput and user fairness in LTE downlink. Simulation results show that the proposed scheme will adjust the MaxPRB according to user SINR dispersion degree of the sector to obtain a good balance between sector throughput and user fairness.

Distributed compressive video sensing (DCVS), aiming at capturing and compressing video data simultaneously, is an emerging field which exploits both intra- and inter-frame correlation. In this paper, we present a new algorithm based on smoothed ℓ0norm (SL0) which tries to directly minimize the ℓ0norm to decode a Wyner-Ziv frame when parts of its correlated key frame's support is known as side information (SI) in a typical DCVS scenario. With the assistance of the modified initialization, our proposed algorithm can reconstruct the Wyner-Ziv frame of the same accuracy with much lower measurement rate compared to the case when the partially known support is not used as SI. It is experimentally shown that our proposed scheme outperforms GPSR at the expense of a tolerable decoding complexity. When compared with modified-cs, a large saving in decoding CPU time is achieved in sacrifice of some PSNR performance.

Adaptive modulation selection plays an important role in wireless communication and wireless sensor network since the wireless channel condition is time-varying due to some factors e.g. path-loss and multipath propagation. Therefore, using one modulation type cannot fulfill all the channel conditions and receivers. Conventional adaptive modulation selection schemes are based on packet loss statistics or SNR measurement. However, all of these methods are indirect approaches because they utilize the packet loss rate or SNR information to estimate the BER approximately and the modulation selection that based on these approximate results is not exactly. Therefore, in this paper, we propose to utilize the error estimating code (EEC) which directly represents the BER information to realize a new adaptive modulation selection scheme. Compared to traditional adaptive modulation type selection schemes, our scheme needs only a small amount of overhead and very little computational cost for the same performance.

Distributed Compressed Video Sensing (DCVS) has developed as one of the efficient solutions that guarantee low complexity video compression. In this paper, a novel DCVS algorithm with unequal protection of the video signal's elements is proposed. The new algorithm utilizes not only the sparsity and probability distribution of the video signal but also its particular unequal significance feature. Based on this feature, we design the structured irregular low-density sensing matrix to sample the signal. From the analysis and simulation results, it is confirmed that our method has higher recovery quality than the conventional Bayesian Compressed Sensing (CS) using Belief Propagation (BP). Moreover, the excellent noise-resilience of BP is preserved in our algorithm comparing to the DCVS schemes using optimization recovery.

Safety applications exploiting Vehicle-to-Vehicle (V2V) and Vehicle-to-Infrastructure (V2I) based on Vehicular Ad hoc Networks (VANETs) have made great impact on research and development in ITS. The successful delivery of the periodical safety-related beacons is the key to security of the vehicular group. To better achieve this goal, the MAC protocol has to be highly reliable and has to assure certain fairness among vehicles. In this paper, an overload tolerant TDMA (OLT-TDMA) mechanism is proposed to ensure the fairness of channel access as well as a good Quality of Service (QoS). The simulation results show that the OLT-TDMA scheme outperforms the traditional IEEE 802.11p protocol, especially in very dense traffic scenario.

In this paper, a local SNR aided sensor selecting (LSAS) algorithm is proposed to meet the energy efficiency requirement of wireless sensor networks (WSNs). In the conventional cluster routing protocols, during each round, all the subordinate sensors need to send their sensed information to their cluster heads, which is energy consuming. Realizing that it is not necessary to involve all the sensors due to the redundancy characteristic of the information on them, we propose that only those sensors with higher local SNR are selected to transmit their sensed data. Experimental results demonstrate that it is sufficient to only use the information on nodes with higher local SNR for target state estimation. The simulations also suggest that the proposed method consumes about 30%-50% less energy than the conventional method.