Aiming at the problems of low data rate and limited battery power of traditional underwater wireless sensor network (UWSN) based on acoustic communication, a resource allocation strategy for magnetic induction (MI) communication-based UWSN in ocean current scenario is investigated in this paper. Specifically, multiple sensor nodes (SNs) are distributed in seawater at different depths. First, an autonomous underwater vehicle (AUV) is introduced to charge the SNs by magnetic coupling resonant wireless power transfer (MCR-WPT) technology. Then, the SNs transmit data to the AUV through MI communication. The influence of the ocean current on the SNs and AUV is analyzed. A genetic algorithm-based particle swarm optimization algorithm is used to optimize the AUV navigation trajectory. After collecting the data from the SNs, the AUV moves to the position under a surface base station and sends the collected data to the surface base station by MI communication. To minimize system energy consumption, the transmitting power of AUV and SNs are jointly optimized under the constraints of energy causality and transmitting power. The suboptimal solution to the formulated optimization problem is obtained by adopting the improved sparrow search algorithm (ISSA) combining Cauchy variation and reverse learning. Simulation results show that the ISSA has lower system energy consumption than other benchmark methods.

Sensor nodes (SNs) in underwater wireless sensor network (UWSN) may generate massive amounts of data and have computing task requirements. In this paper, mobile edge computing (MEC) is considered in UWSN. A resource allocation strategy in autonomous underwater vehicle (AUV)-aided MEC system is investigated to minimize the total system energy consumption. Specifically, the MEC servers are deployed at both AUV and buoy floating on the sea. By adopting magnetic induction (MI) communication technology, the AUV collects computing tasks from different SNs. Partial tasks are computed at the AUV, while the rest of tasks are offloaded to the buoy. The trajectory of the AUV, the transmitting power of SNs and the AUV, and the offloading ratio coefficient are jointly optimized. The suboptimal solution to the formulated optimization problem is obtained by using a social learning particle swarm optimization (SL-PSO) algorithm. Simulation results show that the proposed strategy has a faster convergence speed and better global search capability compared with other baseline schemes.

Aiming at the problem of low data rate in autonomous underwater vehicle (AUV)-based underwater acoustic communication system, a hybrid magnetic induction (MI) and reconfigurable intelligent surface (RIS)-assisted communication strategy is proposed to maximize system channel capacity. Specifically, an AUV first collects data from all the seafloor nodes by adopting the MI communication technology. Then, the AUV forwards the data to another AUV carried with a RIS by using the underwater acoustic communication method. With the help of the RIS, a strong reflective path between the first AUV and a surface base station (BS) on the sea is formed. The surface BS could receive the data at a relatively high data rate. In order to maximize the system channel capacity, the acoustic incidence angle, the distance between the first AUV and the RIS, the distance between the RIS and the surface BS, acoustic signal frequency, and transmitting power are jointly optimized. The formulated optimization problem is solved by employing a butterfly optimization algorithm (BOA) and an improved butterfly optimization algorithm (IBOA), respectively. Simulation results show that the IBOA can increase the system channel capacity more effectively than the basic BOA.

The traditional underwater wireless sensor network (UWSN) based on acoustic communication has the shortcomings of low data rate and limited battery power. In this paper, hybrid acoustic and magnetic induction (MI) communication are considered to overcome the above drawbacks. A resource allocation strategy in autonomous underwater vehicle (AUV)-assisted edge computing UWSN is investigated to minimize the total system delay. Specifically, all the sensor nodes (SNs) are divided into different clusters. The SNs within a cluster send the data to the cluster head (CH) via the acoustic communication. The CH forwards the data to the AUV by the MI communication. Then, the AUV moves to the position under a surface vehicle (SV) carried with a edge server. The AUV forwards the data to the edge server through the MI communication. The transmitting power, channel bandwidth, and computational resources are jointly optimized. The formulated non-convex optimization problem is solved by using an alternating iterative optimization algorithm. Compared with other schemes, the proposed strategy can reduce the total system delay more effectively.

Traditional underwater wireless communication in single medium has the limitations of low rate and high delay. In this paper, magnetic induction (MI)-based cross-medium communication is taken into account to reduce the transmission delay. Specifically, multiple autonomous underwater vehicles are used to collect data from underwater sensor nodes by MI communication. The collected data is directly transferred to a unmanned aerial vehicle above the water via ultra-low frequency MI communication. The cross-medium data collection and transmission problem is formulated an optimization problem. The objective is to minimize the total delay under the constraints of transmitting power, transmission distance, and number of turns of MI coil. A standard particle swarm optimization (SPSO) algorithm and a quantum-behaved particle swarm optimization (QPSO) algorithm are adopted to obtain the suboptimal solution, respectively. Simulation results show that the QPSO algorithm is superior to the SPSO algorithm in reducing the total delay.

Aiming at the problem of limited energy stored in unmanned aerial vehicle (UAV), a resource allocation strategy for UAV-assisted edge computing in wireless powered communication networks is investigated in this paper. By deploying a laser beam director on the ground, sufficient energy can be provided for the UAV in a short period of time. Then, multiple ground terminals obtain energy from this UAV by radio frequency energy harvesting method and offload their computational tasks to the UAV with edge server. The resource allocation problem is modeled as an optimization problem. The optimization objective is to minimize the total energy consumption of the UAV subject to the constraints of energy and data causality, computational resources, and transmitting power. The suboptimal solution is obtained by introducing an imperialist competitive algorithm. Simulation results show that the imperialist competitive algorithm consumes less energy compared with the particle swarm optimization algorithm and the equal upload time allocation method.

Spatio-temporal action detection is a fundamental task that detects persons and recognizes their actions from videos. It requires reasoning about the spatial-temporal interactions between persons and their surroundings. Recently, more modalities have been found by researchers, which puts higher demands on the reasoning capability of the method, yet a method capable of holistic reasoning is still lacking. To this end, we propose a heterogeneous graph network, which aims to reason the spatial-temporal interactions among different types of nodes (video entities) and edges (inter-entity relations). Concretely, it includes spatial and temporal graphs, which are alternately updated. The spatial graph contains nodes of person appearance, person pose, object appearance, and hand interaction, and the temporal graph has person nodes at different moments. For information aggregation, we propose a person-centric heterogeneous graph reasoning algorithm, which introduces heterogeneity into the graphs through node-type-specific projections and modulated edge-type-specific representations. We find that the introduction of heterogeneity enriches the model’s ability to understand multi-modality, which facilitates better parsing of complex semantic relations in videos and potentially leads to further mining of spatial-temporal interactions between entities in the future. Experimental results on four public datasets demonstrate the superiority of our method. Code will be available after acceptance.

Annotated electroencephalogram (EEG) data is the prerequisite for artificial intelligence-driven EEG autoanalysis. However, the scarcity of annotated data due to its high-cost and the resulted insufficient training limits the development of EEG autoanalysis. Generative self-supervised learning, represented by masked autoencoder, offers potential but struggles with non-Euclidean structures. To alleviate these challenges, this work proposes a self-supervised graph masked autoencoder for EEG representation learning, named GMAEEG. Concretely, a pretrained model is enriched with temporal and spatial representations through a masked signal reconstruction pretext task. A learnable dynamic adjacency matrix, initialized with prior knowledge, adapts to brain characteristics. Downstream tasks are achieved by finetuning pretrained parameters, with the adjacency matrix transferred based on task functional similarity. Experimental results demonstrate that with emotion recognition as the pretext task, GMAEEG reaches superior performance on various downstream tasks, including emotion, major depressive disorder, Parkinson's disease, and pain recognition. This study is the first to tailor the masked autoencoder specifically for EEG representation learning considering its non-Euclidean characteristics. Further, graph connection analysis based on GMAEEG may provide insights for future clinical studies.

OBJECTIVE: Neonatal pain can have long-term adverse effects on newborns' cognitive and neurological development. Video-based Neonatal Pain Assessment (NPA) method has gained increasing attention due to its performance and practicality. However, existing methods focus on assessment under controlled environments while ignoring real-life disturbances present in uncontrolled conditions. METHODS: We propose a video-based NPA method, which is robust to four real-life disturbances and adaptively highlights keyframes. Our method involves a region-channel-attention module for extracting facial features under the disturbances of facial occlusion and pose variation; a body language analysis module robust to disturbances from body occlusion and movement interference, which utilizes skeleton sequences to represent the neonate's body; and a keyframes-aware convolution to get rid of information located at non-contributing moments. For evaluation, we built an NPA video dataset of 1091 neonates with disturbance annotations. RESULTS: The results show that our method consistently outperforms state-of-the-art methods on the full dataset and nine subsets, where it achieves an accuracy of 91.04% on the full dataset with an accuracy increment of 6.27%. Contributions: We present the problem of video-based NPA under uncontrolled conditions, propose a method robust to four disturbances, and construct a video NPA dataset, thus facilitating the practical applications of NPA.

Mobile edge computing (MEC) moves computeintensive tasks to the edge of wireless networks, which can effectively reduce service latency and improve quality of service. A resource allocation strategy for multiple unmanned aerial vehicles-supported MEC system with dense mobile users (MU) is investigated in this paper. By applying a magnetically coupled resonance wireless power transfer technology, the MU can harvest enough energy from a wireless charging station in a short time. The models of MU energy harvesting, data transmission, and task computation are analyzed. Under the constraints of energy causality, CPU computing resources, channel bandwidth, and transmitting power, the resource allocation problem for minimizing system latency is established. A quantum-behaved particle swarm optimization (QPSO) algorithm and a standard particle swarm optimization (SPSO) algorithm are used to obtain the suboptimal solution. Simulation results show that the QPSO algorithm is more effective in reducing system latency compared to the SPSO algorithm and the benchmark scheme.

Abstract Due to the limited coverage of base station (BS) and battery capacity of mobile users, the resource allocation strategy in multiple unmanned aerial vehicles (UAVs)‐assisted edge computing system with nonlinear energy harvesting is investigated in this paper. The cooperation between BS and multi‐UAV is considered, which can provide extensive coverage for users with mobility. Mobile users can simultaneously offload computation bits to the BS and the UAV, and mobile users harvest energy from BS and UAV. Meanwhile, the mobility of users is taken into account. Moreover, an echo state network (ESN)‐based prediction algorithm is utilized for predicting the future positions of mobile users. Therefore, the UAV can reach the predicted users' positions in advance to ensure the continuity of communication. The objective of the resource allocation strategy is to maximize the energy efficiency by jointly optimizing bandwidth allocation, computation resources, the trajectory of UAV, and transmitting power of mobile users. Then, the resource allocation problem is formulated as a mixed‐integer nonlinear programming problem. The quantum‐behaved particle swarm optimization (QPSO) algorithm is used to solve the problem. Simulation results demonstrate that the proposed strategy can achieve higher energy efficiency than other benchmark strategies. In addition, QPSO algorithm outperforms the standard particle swarm optimization algorithm and genetic algorithm in terms of energy efficiency.

Aiming at the the characteristic of dependency relationship existing among multiple tasks, a resource allocation strategy for multi-task mobile edge computing systems is investigated in this paper. Sequential dependency relationship among multiple tasks is taken into account. When the current task completes offloading, the next task can be offloaded without waiting for the current task to finish computing. By using a two-tier offloading strategy, when the edge server in small base station has insufficient computing capacity, the offloading task could be further divided and offloaded to the edge server in macro base station with sufficient computation resources. The resource allocation problem is formulated as an optimization problem. The objective is to minimize the total computation time of the overall system under the constraints of computing capability range of user, maximal computing resource of edge server, and maximal transmitting power of user. To solve the formulated optimization problem, a suboptimal solution is obtained by adopting a quantum-behaved particle swarm optimization (QPSO) algorithm. Simulation results show that the performance of the proposed strategy is superior to other benchmark strategies, and QPSO algorithm has less computation time compared with the standard particle swarm optimization algorithm.

Aiming at the problem that the user devices (UDs) far from the base station (BS) suffer from the doubly near-far effect, a resource allocation strategy for unmanned aerial vehicle (UAV)-assisted non-linear energy harvesting mobile edge computing (MEC) system is investigated in this paper. By deploying a UAV, remote user devices can harvest energy from both the BS and the UAV in the non-linear energy harvesting way, but only offload computing tasks to the MEC server on the UAV to reduce the influence of the doubly near-far problem. The nearby user devices only harvest energy from the BS in the non-linear energy harvesting way and offload computing tasks to the MEC server on the BS. The resource allocation problem is modeled as a non-linear programming problem by jointly optimizing the UDs’ local computing capability, UDs’ transmitting power, and the flight trajectory of the UAV. The objective is to maximize the sum of computation bits of all UDs under the constraints of energy consumption of UDs and UAV and the speed of the UAV. The suboptimal solution is obtained by introducing the differential evolution (DE) algorithm. Simulation results show that compared with the partial optimization methods of transmitting power, local computing capability, and the flight trajectory of the UAV based on the DE algorithm, the proposed method has different degrees of increase in the sum of computation bits of all UDs.

Aiming at the problem of insufficient ground terminal (GT) energy in unmanned aerial vehicle (UAV) aided wireless powered communication networks (WPCN) using radio frequency energy harvesting, the minimum throughput maximization resource allocation strategy based on magnetic coupling resonant wireless power transfer is studied in this paper. In the original UAV-aided WPCN, a power transfer UAV equipped with magnetic coupling resonance device is introduced. At the same time, each GT installs a receiving coil. Through the magnetic coupling resonance, the power transfer UAV provides sufficient energy for the GT in turn. In order to maximize the minimum throughput of all GTs, the UAV trajectory for receiving information, GT transfer power and timeslot allocation proportion are jointly optimized. Since the optimization problem is nonconvex, the appropriate convex bound of nonconvex constraint is derived by concave-convex process, and the suboptimal solution of the original problem is obtained by iterative optimization algorithm. The simulation results show that the proposed method has a certain degree of improvement in the minimum throughput compared with the method of fixed UAV trajectory and fixed timeslot allocation ratio.

Aiming at the problem that mobile terminal (MT) harvests less energy from ambient radio frequency (RF) sources, the resource allocation strategy in mobile edge computing (MEC) system with hybrid energy harvesting is investigated in this paper. By deploying multiple magnetic induction energy quick charging stations (MI-CSs) within the coverage area of the base station, the MT can supplement extra energy at a nearby MI-CS when the energy harvested from ambient RF sources is about to be exhausted. The MT offloads computing task to edge server by leveraging MEC technology. The resource allocation problem is formulated as an optimization problem. The objective is to minimize the total energy consumption of MTs under the constraints of computing capability range of MT, maximal computing resource of edge server, computing delay of task, and battery energy of MT. The suboptimal solution is obtained by adopting the quantum-behaved particle swarm optimization (QPSO) algorithm. Simulation results show that the QPSO algorithm has less energy consumption compared with the standard particle swarm optimization algorithm and the fixed computing resource allocation method.

Aiming at the influence of user equipment (UE) mobility on computational results feedback of mobile edge computing (MEC) server, a resource allocation strategy based on virtual machine migration is proposed to maximize the system energy efficiency (EE). UEs can harvest radio frequency energy from multiple frequency bands as they move. When the UE moves over a long distance, virtual machine migration is adopted to transfer the computational tasks offloaded by the UE from the initial MEC server to the current MEC server. After the current MEC server completes the computational task, it can directly feed the computational results back to the UE, which can significantly reduce the delay. After the current MEC server completes the computational task, it will feed the computational results back to the UE. By jointly considering offloading computational task by the UE and computational results feedback of MEC server, the problem of power and subcarrier allocation is modeled as a mixed integer nonlinear programming problem. The goal is to maximize the system EE under the constraints of energy consumption, subcarrier allocation, and transmitting power. The suboptimal solution is obtained by introducing the genetic algorithm. Simulation results show that the proposed method has higher EE than partial power or subcarrier allocation methods based on the genetic algorithm.

Aiming at the difference in number of users in busy time and spare time for the femto base station (FBS), the power allocation problem of maximizing the total downlink information is investigated in this paper. By deploying a pico base station carried by unmanned aerial vehicle (PBS-UAV), it provides services for users of multiple FBSs in spare time. Both the FBS and PBS-UAV have energy harvesting function. During the busy time, the FBS and PBS-UAV simultaneously harvest energy from the macro base station, and FBSs transmit data to users. During the spare time, multiple FBSs are replaced by the PBS-UAV to communicate with users in downlink. The power allocation problem is modeled as an optimization problem. The objective is to maximize the amount of downlink information of FBSs and PBS-UAV while satisfying the constraints of FBS and PBS-UAV energy consumption and transmission power. The optimal solution is obtained by using an augmented Lagrange multiplier method. The simulation results show that compared with the equal power method and partial fixed power method with PBS-UAV, the proposed method has an increase in terms of total information to different degrees.

In this study, the problem of adaptive modulation and frame length (AMFL) is investigated in long‐term evolution for railway (LTE‐R) communication system. By considering the effect of frame length, a novel AMFL strategy based on Moore state machine (MSM) is proposed. The influence of the frame length on the goodput is discussed by theoretical analysis and simulation evaluation. According to modulation and frame length schemes (MFLSs) adopted in LTE‐R system, the finite state set of the MSM is designed. For different MFLSs, the frame error rate (FER) and signal‐to‐noise ratio (SNR) curve is obtained. By giving a target FER, the SNR thresholds corresponding to different MFLSs are achieved. From the perspectives of modulation priority and frame length priority, two different AMFL‐MSMs are designed to change MFLSs dynamically. Simulation results show that the proposed two AMFL‐MSMs have more stable goodput than the common modulation schemes and less symbol energy consumption than the high‐order modulation scheme. In addition, the AMFL‐MSM with modulation priority has better performance than the AMFL‐MSM with frame length priority in terms of goodput stability.

In this paper, the problem of adaptive modulation and frame length (AMFL) is investigated in long-term evolution for railway (LTE-R) communication system. By considering the effect of frame length, a novel AMFL strategy based on Moore state machine (MSM) is proposed. The influence of the frame length on the goodput is discussed by simulation evaluation. According to modulation and frame length schemes (MFLS) adopted in LTE-R system, the finite state set of the MSM is designed. For different MFLSs, the frame error rate (FER) and signal-to-noise ratio (SNR) curve is obtained. By giving a target FER, the SNR thresholds corresponding to different MFLSs are achieved. From the perspectives of modulation priority and frame length priority, two different AMFL-MSMs are designed to change MFLSs dynamically. Simulation results show that the proposed two AMFL-MSMs have more stable normalized goodput and less symbol energy consumption than the high-order modulation scheme. Moreover, compared with common MFLS, two AMFL-MSMs have higher average normalized goodput at different speeds.

Aiming at excessive users existing in a pico base station (PBS) of heterogeneous networks, the resource allocation problem of maximizing the total uplink throughput is investigated in this paper. By deploying a relay node with energy harvesting, some users of the PBS are transferred to the adjacent idle PBS. The resource allocation problem is formulated as an optimization problem. The objective is to maximize the total uplink throughput of users in the PBS under the constraints of the user's minimum data rate, the energy consumption, and transmission power of the relay node. The optimal solution is obtained by using the augmented Lagrange multiplier method. Simulation results show that the proposed method has higher throughput compared with the conventional method (i.e., some PBS users are transferred to the macro base station). Moreover, compared with the equal power method, the proposed method has an increase in terms of throughput to a certain degree.

Resource allocation in mobile edge computing (MEC)- based wireless networks with energy harvesting has attracted great attention. However, existing works assume that mobile devices are stationary while harvesting energy. In this paper, an uplink resource allocation strategy is developed in MEC-based heterogeneous networks. A random mobility model is designed to describe the movement of the user equipment (UE). Meanwhile, the UE can harvest energy from six frequency bands while moving along a certain path. The energy harvesting model of the UE is given by an integral expression. The objective of the resource allocation problem is to maximize the energy efficiency (EE) under the constraints of energy consumption, total data rate requirement, sub-carrier allocation, and transmission power. A quantum-behaved particle swarm optimization (QPSO) algorithm is employed to obtain a sub-optimal solution. Numerical results show that the amount of energy harvested by the UE decreases as the moving speed increases. Moreover, the QPSO algorithm has higher EE than an existing particle swarm optimization algorithm.

Simultaneous wireless information and power transfer is an innovative way to provide electrical energy for user equipments. However, most previous works mainly focus on energy harvesting over a relatively narrow frequency range. Due to small energy harvested by the users, the practical applications are usually limited to low power devices. In this paper, an energy-efficient uplink resource allocation problem is investigated in a cellular network with ambient radio frequency (RF) energy harvesting. In order to obtain sufficient energy, a broadband rectenna is adopted to harvest ambient RF energy over six frequency bands at the same time. From the viewpoint of service arrival in the ambient transmitter, a new energy arrival model is presented. The problem of sub-carrier and power allocation is formulated as a mixed-integer nonlinear programming problem. The objective is to maximize the energy efficiency while satisfying the energy causality and the total data rate requirement. In order to reduce the computational complexity, a suboptimal solution is derived by employing a quantum-behaved particle swarm optimization (QPSO) algorithm. Simulation results show that the QPSO method has higher energy efficiency than a conventional particle swarm optimization approach.

Resource allocation problem in high-speed railway wireless communication networks is one of the key issues to improve the efficiency of resource utilization. However, traditional resource allocation methods cannot be directly applied to this special communication system. In this paper, we propose a resource allocation approach for high-speed railway downlink orthogonal frequency-division multiplexing (OFDM) system with multiple-input multiple-output (MIMO) antennas. Sub-carriers, antennas, time slots, and power are jointly considered, which is formulated as a mixed-integer nonlinear programming problem. The effect of the moving speed on Doppler shift is analyzed to calculate the inter-carrier interference power. The objective is to maximize the throughput under the constraint of total transmission power. In order to reduce computational complexity, suboptimal solution to the optimization problem is obtained by quantum-behaved particle swarm optimization. Simulation results show that the proposed resource allocation strategy has a better performance compared with an existing one.

With the wide deployment of high-speed railway at more than 300 kilometers per hour, providing various services effectively for users in the train becomes both practical demand and interesting challenge for wireless communication. Resource allocation problem in high-speed railway communication system is one of the key issues to improve the efficiency of resource utilization. In this paper, we propose a multidimensional resource allocation strategy for high-speed railway downlink orthogonal frequency-division multiplexing (OFDM) system with multiple-input multiple-output (MIMO) antennas. Sub-carrier, antenna, time slot, and power are considered jointly, which is modeled as a nonlinear integer programming problem. The effect of the moving speed on inter-carrier interference is analyzed to calculate the transmitted power. The objective is to minimize the total transmitted power while satisfying quality of service requirement of each user. Moreover, optimal and approximate solutions are obtained by linearization and quadratic fitting, respectively. Simulation results have proved that approximate solution has lower total transmitted power than optimal solution while the computation complexity is higher.

Along with the wide deployment of high-speed railway at more than 300 km/h, providing various services effectively for users in the train becomes both practical demand and interesting challenge for wireless communication. Due to the specific environment for high-speed railway, existing radio admission control (RAC) algorithms could not suit the requirements such as frequent handover, quick decision-making duration and fast-changing physical transmission condition. The investigation on novel and proper RAC is of great importance. In this paper, we propose an effective radio admission control scheme based on Rician shading model for high-speed railway communication with MIMO antennas. Layered networks access architecture is designed in which Rician channel is used to analyze physical transmission condition. The effect of bit error rate on data rate at high moving speeds is taken into account for the RAC decision-making to get better quality of service (QoS). Moreover, different priorities for different services are considered to resolve simultaneous multiple users' access requests. Simulation results have proved that the proposed scheme may improve QoS obviously compared to the scheme that does not consider bit error rate and service priority.

This poster introduces SLAW, a Scalable Locality-aware Adaptive Work-stealing scheduler. The SLAW features an adaptive task scheduling algorithm combined with a locality-aware scheduling framework.