Skeleton-based action recognition has achieved remarkable performance with the development of graph convolutional networks (GCNs). Existing methods tend to capture spatial dependencies through learnable adjacency matrices, where nodes receive latent representations from neighbors at arbitrary distances within the encoded skeletal graph structure. However, they struggle to model spatial high-order structural representations, such as feature differences across distances. In addition, the temporal convolution with fixed receptive fields limits their capacity to capture long-range temporal dependencies. In this work, we propose a simple yet effective method, DeltaGC, to leverage spatial high-order modeling. Specifically, we adaptively encode the delta feature by computing the subtraction between the highorder feature and the zero-order feature with a pre-defined hopwise adjacency matrix table. This design offers more informative representations and complements existing methods. Moreover, the concept of deformable modeling is introduced and a multi-scale deformable temporal convolution module, named MS-DTC, is designed for more flexible receptive fields and stronger modeling capacity. Extensive experiments demonstrate the superiority of our approach. Both the compact version, DeltaGCN-S, and the larger variant, DeltaGCN-L, achieve competitive performance against state-of-the-art methods, with DeltaGCN-L establishing superior results on multiple benchmarks.

In multi-cell multi-user multiple-input multiple-output (MC MU-MIMO) visible light communication (VLC) systems, each user is equipped with multiple closely-placed photodiodes (PDs) with similar channel gains, leading to severe inter-cell interference and intra-cell interference. To address this problem, this paper proposes a hybrid dimming (HD) scheme with MIMO VLC transceiver design, which jointly optimizes transmit and receive antenna selection (TRAS), cell clustering and precoding (TRASP-HD) for MC MU-MIMO VLC systems. In this scheme, a sum-rate maximization problem under the dimming level and illumination uniformity is formulated and solved by being divided into two sub-problems. In particular, The first sub-problem is on TRAS and cell formation based on the criterion of sum-rate maximization under the illumination uniformity constraint. With the same goal, the second sub-problem is on optimizing the precoding matrices of each cell. Finally, these two sub-problems are iteratively solved to obtain a convergent solution. Simulation results verify that in a typical indoor scenario, the mean bandwidth efficiency of TRASP-HD scheme is 2.36 bit/s/Hz higher than the conventional MC MU-MIMO system.

Skeleton-based Human interaction action recognition is a great challenge in the field of human activity analysis. The existing graph convolutional networks (GCNs) based recognition methods ignore the spatial-temporal interactive features between two persons. Therefore, we propose Attention Inter-active Graph Convolutional Network(AIGCN) to explore hu-man interaction. First, we design an Interactive Attention En-coding GCN(IAE-GCN) module to extract interactive spatial structures, reflecting their influence on each other by regarding joint position encoding as semantic information. Second, we propose Interactive-Attention Mask TCN (IAM-TCN) that extracts temporal interactive features, representing temporal attentional excitation signal among the different joints of dif-ferent people along the time. Finally, we verify the effectiveness of our method on classic human interaction datasets SBU and interactive action sub-datasets of NTU-RGB+D and NTU-RGB+D 120, and experiment shows that our models achieve state-of-the-art performance.

Graph convolutional networks (GCNs) have proven their effectiveness and success in skeleton-based action recognition. Regular GCNs separate spatial and temporal operations. And for spatial graph convolution, the self-attention mechanism is commonly used to enable the generation of adaptive data-driven graphs, which limits the receptive field of each vertex. In order to address such a concern, we propose the graph involution network (GIN). A novel operation called graph involution is applied to offer each joint a global reception field, while also largely improving temporal-wise and channel-wise flexibility during the process of feature aggregation. We also find that predefined graphs that came from human natural skeleton structures restrict the remote information exchanges. Therefore we also propose a novel graph topology called spiral graph topology, connecting body joints spirally, which brings valuable additional information hints and improves feature aggregation efficiency. Experiments conducted on different benchmarks on two large-scale datasets show the effectiveness of our proposed network.

At present, the semantic communication system considered the case that one of the intelligent tasks needs to be completed, while a single Internet of Things (IoT) device is usually required to complete multiple different tasks in reality. Moreover, it is difficult to obtain a large number of labels for some complex tasks to achieve high precision, such as object detection. Existing methods for few-shot detection mainly focus on transfer across domains, but there is the following problem in application: the parameters of the encoder cannot be shared at transmitter among different tasks, which leads to the storage pressure of the IoT devices required to transmit semantic information for multiple different tasks. To address this problem, we propose a novel transfer learning approach, Semantic Transfer Across Tasks, in which we leverage the semantic information to guide the training process of object detection with fewer labels and share the encoder architecture between classification and detection in the semantic communication system. Inspired by Grad-CAM, we select the semantic information which is important to detection, and we propose a semantic distance to improve the performance of few-shot detection. Experimental results show that our approach improved the mean average precision of few-shot detection in the semantic communication system and reduced the storage pressure of IoT devices.

This article proposes a hybrid dimming (HD) scheme based on joint light-emitting diode (LED) selection and precoding design (TASP-HD) for multiple-user (MU) multiple-cell (MC) visible light communications (VLCs) systems. In TASP-HD, both the LED selection and the precoding of each cell can be dynamically adjusted to reduce the intra- and inter-cell interferences while satisfying illumination constraints. First, an MU-MC-VLC system model is established, and then a sum-rate maximization problem under the dimming level and illumination uniformity constraints is formulated. In this studied problem, the indices of activated LEDs and precoding matrices are optimized, which result in a complex nonconvex mixed-integer problem. To solve this problem, the original problem is separated into two subproblems. The first subproblem, which maximizes the sum rate of users via optimizing the LED selection with a given precoding matrix, is a mixed-integer problem solved by the penalty method. With the optimized LED selection matrix, the second subproblem which focuses on the maximization of the sum-rate via optimizing the precoding matrix is solved by the Lagrangian dual method. Finally, these two subproblems are iteratively solved to obtain a convergent solution. Simulation results verify that in a typical indoor scenario under a dimming level of 70%, the mean bandwidth efficiency (MBE) of TASP-HD is 4.8 bit/s/Hz and 7.13 bit/s/Hz greater than analog dimming (AD) and digital dimming (DD), respectively.

This paper proposes a hybrid dimming scheme based on joint design of transmit antenna selection and precoding (TASP-HD) for dimmable multi-cell multi-user multiple-input single-output visible light communications systems. In TASPHD, both the direct current bias and the number of activated light-emitting-diodes are dynamically adjusted to achieve efficient communications under the constraints of dimming level and illumination uniformity. With the goal of maximizing the sum-rate of users, a joint transmit antenna selection and precoding design problem is formulated. This problem is a non-convex, mixed integer problem, and thus it is non-deterministic polynomial time hard. To solve the problem, the original problem is separated into two subproblems. The first subproblem is a mixed integer problem in terms of transmit antenna selection, which is solved by the branch-and-bound algorithm. With the obtained transmit antenna selection matrix, the second subproblem in terms of the precoding matrix is solved by the Lagrangian dual method. Finally, these two subproblems are iteratively solved to obtain a convergent solution. The simulation results verify that the proposed TASP-HD can achieve 6 dB signal-to-noise ratio gains over the analog dimming scheme when the dimming level is 70% for a target bit error rate of 10-3.

In this study, the authors focus on energy efficiency (EE) optimisation via the cooperation of small cell base stations (SBSs) in dense small cell networks (DSCNs) where the control plane (C‐plane) and data plane (D‐plane) are decoupled. They propose a coalition‐based sleep mode and power allocation (CSMPA) scheme to improve the DSCN EE while guaranteeing the target rates of users and maintaining the system capacity. In the CSMPA scheme, the cooperation of SBSs is formulated as a coalitional game in partition form and a centralised heuristic coalition formation algorithm without power cost is developed to achieve the final stable coalition structure. Each SBS can serve users in the active subframes and sleep in those subframes without data transmission. Afterwards, since the interference between coalitions affects EE, a distributed price‐based power allocation algorithm is presented to optimise the transmit power of active SBSs per subframe. System‐level simulation results show that the proposed CSMPA scheme can yield less number of outage users and significant EE performance gain without jeopardising system capacity.

Along with the exponential growth of mobile data traffic over the past few years, dense small cell networks are considered an attractive solution to cope with the mobile traffic demand. However, users of small cells in dense environment are exposed to serious co-tier interference problem and users at the edge of small cells have worse performance especially. In order to improve the performance of redefined edge users and maintain the throughput of the network, we propose a clustering-based co-tier interference coordination (CCIC) scheme on the downlink (DL) side to mitigate co-tier interference to edge users. Firstly, small cells are clustered based on the graph coloring algorithm (GCA). Secondly, we schedule frequency resources into two bands as well as group users into two categories. Different kinds of bands are assigned to corresponding users. Accordingly we reduce power on a band defined as center band to mitigate interference to edge users. Then a utility function is proposed to find the optimal transmission power of each small cell base station (SBS) on center band. Finally, differential evolution (DE) algorithm is applied to obtain the optimal transmission power. System level simulation results show that our proposed scheme can greatly improve the edge user throughput with slightly sacrificing the overall throughput. Meanwhile, it can improve the network energy efficiency (EE) dramatically.

Dense small cell networks (SCNs) has emerged as a cost-effective way of supporting a rapid growth of traffic demand. However, a large number of small cell base stations (SBSs) will consume a lot of energy, which is not conductive to improve the SCNs energy efficiency (EE). In this study, a novel small cell grouping based power control scheme is proposed to save energy as well as to maintain the network throughput for dense SCNs. Specifically, small cells are divided into different groups according to both the load and the inter-cell interference levels between the dense small cells, and accordingly the transmission power of the SBSs is reduced based on the proposed utility function. The existence of the optimal solutions to the problem is discussed, then the differential evolution (DE) is applied to obtain the optimal transmission power. System level simulation results demonstrate that the proposed scheme can significantly improve the SCNs EE without sacrifice of the network throughput.

Nowadays the rapid growth of user data rate requirement prompts dense deployment of small cell. However, the dense deployment strategy will bring in new interference problem due to the short distance between cells. Coordinated Multiple Point (CoMP) transmission is considered to be an effective way to mitigate Inter-Cell Interference (ICI). In this paper, we propose a novel CoMP transmission algorithm for dense deployment of small cell, which takes advantage of both Joint Transmission (JT) and Dynamic Point Blanking (DPB) CoMP technologies. Considering the capacity of backhaul link and the characteristics of these two categories of cooperation, JT scheme is used between macro base stations (which are relatively fewer than small cells) and small cells, and DPB technology is used among small cells. Simulation results shows our algorithm achieves better Energy Efficiency (EE) and edge user Spectrum Efficiency (SE) than JT transmission at the cost of little decrease in average SE per sector if proper parameter is set. The gain ratio obtained in dense small cell deployment is more obvious than in sparse deployment.

Cell coverage and network capacity are two major challenges for the evolving 4G cellular wireless communication networks. Hierarchical layering of cells with macro base stations coexisting with low-power base stations in a service area has been investigated as a promising technique for enhancing the coverage extension and reducing the transmit power consumption, which has emerged as a candidate for green communications. However, the cell splitting gain can only be achieved when both inter-layer and co-tier interference are properly handled. In this paper, a basic co-channel heterogeneous network (HetNet) deployment scenario with two cell layers is considered. The scheduler groups all the user equipments (UEs) into three sets according to the signal to interference plus noise ratio (SINR) and the factor RI. Furthermore, the total spectrum band is divided into three parts based on the size of user sets and the two layers both reduce the transmission power in some specific bands, so that contributes to interference mitigation and throughput enhancement. Simulation results show that the proposed method can not only promote the energy efficiency (EE) but also enhance system performance in terms of both cell edge users' SINR and system capacity.

As traditional wireless cellular networks are facing a rapid growth of traffic demand, future networks may consist of a large number of small cells which are densely deployed. However, networks in dense environment is exposed to strong inter-cell interference problem which is critical to networks capacity. To solve the problem, we use the Graph Coloring Algorithm (GCA) to divide the small cells into different clusters to mitigate the serious inter-cell interference between the dense small cells, and accordingly reducing the transmission power of small cell BSs in some subframes based on the proposed utility function. The existence of the optimal solutions to the problem is discussed, then the Differential Evolution (DE) is applied to search the optimal transmission power which maximizes the proposed utility function. Intensive simulations show that the proposed scheme can significantly mitigate the co-tier interference and maximize networks capacity.

Envelope tracking (ET) is a significant technique to improve the efficiency of power amplifier (PA) in the power back-off region, especially in modern mobile communication system with a high peak-to-average power ratio (PAPR). Different ET implementation solutions, especially the way of choosing shaping table, have a great impact on the performance of ET system. In this paper, a transistor-level PA and a behavior-level supply modulator are introduced to analyze the performance of ET PA system. The power-added efficiency (PAE), AM-to-AM distortion, AM-to-PM distortion and Adjacent Channel Leakage Ratio (ACLR) are investigated to explain the impacts of different commonly-used shaping methods. Simulation results indicate that adopting ET technology increases the efficiency of RF PA largely, and the shaping methods applied in supply modulation will affect a lot in efficiency and linearity. Consequently, a new dualmode ET shaping method is proposed in this paper to guarantee high efficiency as far as possible without introducing too much distortions. Besides, it also improves the linearity where the PAE is at a lower level.

Dense deployment of small cell in heterogeneous networks (HetNet) is considered as a promising way to cope with the exponential growth in mobile traffic demand. In such scenario, coverage optimization is a challenge due to the unplanned deployment and plug-and-play feature of small cell. In this paper, the coverage performance of the network is analyzed under different deployment density of small cells. Then the coverage problem is modeled as a cost function which includes the inappropriate coverage ratio of the network. After that, the ant colony algorithm (ACA) is applied to find the optimal pilot Tx power of each small cell through the minimization of the cost function. Finally, compared to the fixed coverage scheme, the proposed algorithm can not only reduce the ratio of coverage hole but also the proportion of coverage overlap as well.

Improving network Energy Efficiency (EE) in wireless communications has attracted increasing attention recently. The purpose of our research is to optimize the network power consumption and preserve the throughput of macrocells User Equipments (UEs) at the same time. We solve the problem by controlling the transmission power of macro base stations (BSs) in some subframes based on the proposed utility function, and accordingly scheduling picocells Cell Range Expansion (CRE) UEs in these subframes. The existence of the optimal solutions to the problem is discussed, then the Differential Evolution (DE) is applied to search the optimal transmission power which maximizes the proposed utility function. System level simulation results show that the proposed algorithm can not only optimize the network power consumption but also improve the throughput of the network, which will lead to the network EE improvement.

Deployment of small cells within macrocell layout is a promising approach to meet the rapid growth of traffic demand. Cell range expansion (CRE) has been introduced into LTE-Advanced to balance cell load. Small cell CRE users may suffer severe downlink (DL) co-tier and cross-tier interference introduced by dense deployment of small cells. In this paper, we propose a joint coloring-based resource allocation and power reduction scheme to mitigate interference to CRE users while maintaining the network throughput. In order to mitigate the co-tier interference, we firstly group CRE users based on interference graph by coloring and allocate orthogonal resources to different groups. Then, small base stations (SBSs) reduce power on resources occupied by CRE users in other SBSs. In order to alleviate the cross-tier interference, macro base stations (MBSs) power reduction is provided based on a utility function. We apply particle swarm optimization (PSO) strategy to obtain the optimal power. System level simulation results show that our proposed algorithm can greatly improve the CRE user throughput with slightly sacrificing the macrocell throughput. Meanwhile, it can improve the network energy efficiency (EE).

In Heterogeneous Network (HetNet), reasonable resource allocation has attracted extensive attention. To allocate the resource more effectively, we propose a novel algorithm from the perspective of both time domain and power domain. On the one hand, we propose an adaptive Almost Blank Subframe (ABS) configuration scheme to dynamically match the network resources with the real-time load. On the other hand, we propose a utility function of macrocells' power control and a corresponding scheduling scheme to make a tradeoff between the two-tier macro-pico networks and protect the victim users as well. The existence of the optimal solution to the problem is proved, and Differential Evolution (DE) is applied to find the optimal solution. System level simulation results show that the proposed algorithm can not only enhance the load balance between macrocell and picocell, but also provide a great improvement on the performance of edge users with little overall throughput cost.

In this paper, we investigate how picocells overlaid in macrocells expand their coverage areas under different Cell Range Expansion (CRE) strategies in a macro-pico heterogeneous network. Through system level simulations, the relationships among the presented CRE strategies are specified from both qualitative and quantitative perspective, in which network topologies using different CRE strategies are displayed, and load balancing performance is compared in terms of CRE user ratio. Relatively good CRE strategies are derived from statistics. Furthermore, as CRE will largely decrease network throughput due to unexpected interference on the downlink path from Macrocell Base Stations (MBSs) to CRE users, we then apply Coordinated Multi-Point (CoMP) transmission in heterogeneous deployment to deal with the inter-cell interference. Intensive simulations show that CoMP could significantly improve both cell average Spectrum Efficiency (SE) and 5% cell edge SE, and a recommended value of CoMP bias which decides CoMP user ratio is given at last.

In traditional cellular networks, User Equipments (UEs) always connect to the strongest Base Station (BS), which offers either the maximum Signal to Interference Plus Noise Ratio (SINR) or the best Reference Signal Received Power (RSRP). However, in heterogeneous networks, due to a large difference of transmit power between macrocells and low power nodes, the user association methods mentioned above may lead to unbalance of user distribution between the two kinds of BSs. The goal of our research is to balance the user association between macrocells and picocells while maintain the network performance. We solve the user association problem by introducing the topological potential between UEs and BSs, from which both the channel condition and the number of severing UEs in each cell are considered. Since maximizing the topological potential in network-wide is NP-hard, a heuristic method is proposed to reach a suboptimal. Finally, the tradeoff between association fairness and network throughput is discussed via system level simulation, and a better fairness user association is given compared to the range expansion method in the same condition of network throughput.

Heterogeneous Network (HetNet) in 3GPP is a promising way to increase network coverage and capacity compared to macro cellular-only network. In order to further increase network capacity and balance cell load, Cell Range Expansion (CRE) and time-domain Inter-Cell Interference Coordination (ICIC) have been introduced into LTE-Advanced. The goal of our research is to mitigate the interference towards the User Equipments (UEs) served by the picocells and maintain the throughput of macrocells at the same time. We solve the problem by reducing the transmission power of macro Base Stations (BSs) in some subframes based on the proposed utility function, and accordingly scheduling picocell CRE UEs in these subframes. The existence of optimal solutions to the problem is discussed, and the Differential Evolution (DE) is applied to find the optimal transmission power which maximizes the utility function. System level simulation results show that the proposed algorithm can not only increase the total network's capacity but also improve the load balance between macrocell and picocell.

This paper addresses how to improve the energy efficiency of OFDMA femtocell networks with sleep mode. Firstly, the energy consumption of the sleep mode is analyzed. Considering the requirements of improving the energy efficiency and ensuring the QoS of users, we extend the definition of effective capacity to formulate the tradeoff relationship between the energy efficiency and the waiting delay of users. Then two optimization schemes of sleep mode parameter are proposed: (1) Maximize the energy efficiency with effective capacity constraint; and (2) Maximize the effective capacity with energy efficiency constraint. And the performances are analyzed, including average energy consumption, energy efficiency, effective capacity and waiting time. Simulation results show that the effective capacity-based parameter optimization of sleep mode can achieve a good tradeoff between energy efficiency and QoS of users in OFDMA femtocell networks.

This paper addresses the cross-tier interference issue in two-tier OFDMA femtocell networks using hybrid spectrum allocation. Firstly, we propose a classification method for users. The macro users are classified into several categories based on their geographic location, and femto users are classified according to the categories of macro users. Then, based on such user classifications, a hybrid spectrum allocation (HSA) scheme is proposed. HSA employs a dynamic orthogonal spectrum allocation for macro user categories according to the number of MUEs in two-tier networks, and fractional spectrum reuse for femto user categories based on their different communication environments. Simulation results show that the proposed scheme can improve outage and throughput performance of macro users with less impact on femto users.

This paper addresses the cross-tier interference mitigation problem in two-tier OFDMA femtocell networks using power control. We model the objective of power control with utility functions for macrocell and femtocell, respectively. And we discuss the existence of optimal solutions to power control problems. Then a power control algorithm with Differential Evolution (DE) is developed to find the optimal power settings which maximize the utility function. Through numerical calculation, we study how to properly set the parameters of DE for our proposed utility functions. Furthermore, the performance of power control algorithm with different tunable coefficients of utility function is also analyzed by system level simulation. Simulation results show that our proposed algorithm can improve the outage and throughput performance of macro users with minor impact on femtocell users. Meanwhile, our proposed algorithm is easy to implement in distributed manner.

This paper addresses the power control problem in two-tier OFDMA femtocell networks to alleviate the cross-tier interference. We model the objective of power control with utility function, and proof the proposed utility function is strictly concave with respect to transmission power. Then a power control algorithm with Particle Swarm Optimization is developed to find the optimal power settings to maximize the utility function. Simulation results show that our proposed algorithm can improve the outage and throughput performance of macro users with less impact on femtocell users. Meanwhile, our proposed algorithm is easy to implement in distributed manner and efficient in computation.