A space-air-ground integrated network consisting of a satellite, high altitude platforms (HAPs), unmanned aerial vehicles (UAVs), and terrestrial Internet of Things (IoT) devices is constructed to collect wide-area information. The IoT devices sense the environmental information, the UAVs fly to collect data, and the HAPs deliver the computation results to the satellite. In order to improve the information freshness, the age of information (AoI) of the system is minimized by the UAV trajectory design and network configuration under the cost and practical constraints. The optimization is decomposed into two stages, which are jointly conducted by the HAPs and UAVs. In the first stage, each UAV and IoT device cluster are paired, and the UAV obtains the minimum AoI along with the optimal destined position by deep reinforcement learning (DRL). Afterwards, the HAP performs the matching between the UAVs and the IoT device clusters by the Gale-Shapley algorithm. In the second stage, the HAPs complete the configuration of the coverage area and height of the HAPs and UAVs by the soft actor-critic DRL algorithm. The extensive simulation verifies the AoI deduction of the proposed scheme and depicts the regularities of network configuration and UAV trajectory design for the minimum AoI achievement.

As one of the basic mission of computer vision, object detection is taken as the preprocessing strategy by an increasing number of algorithms. In the field of biometric information recognition, palm detection results seriously affect the accuracy of subsequent palm-print recognition. To facilitate practical application under the unconstrained condition, we propose a parallel rotated-invariant palm detection network to locate the position, size and especially the angle of in-plane of the region of interest(ROI). In order to obtain the low time complexity meanwhile maintaining the high accuracy, we choose the anchor-free algorithm CenterNet, which detects the object as a point with size, as our baseline. Otherwise, we design the specific Unit Circle Constraint(UCC) loss function to reduce the interference of boundary angle value to network training. The experimental results on the Rotated Palm Dataset demonstrate the effectiveness of our method.

Aerial access networks have been envisioned as a promising 6G solution to enhance the ground communication systems. To better utilize the spectrum and fully explore different channel characteristics, this paper constructs an integrated network comprising the high altitude platform (HAP) and unmanned air vehicles (UAVs) with the non-orthogonal multiple access (NOMA) technology. In order to improve the transmission quality of the images and videos, a power management scheme is proposed to minimize the distortion of the transmissions from the HAP and UAVs to the terminals. The power control is formulated as a non-convex problem. The variable substitution and the first-order Tailors expansion is used to transform it into a sequence of convex problems, which are subsequently solved through Lagrangian dual method. Simulation demonstrates the signal distortion improvement achieved by the proposed scheme.

Palms alignment is an important work for palmprint recognition in uncontrolled environment. Many methods have made progress to achieve alignment. But most of them ignore the palm's angles, which could not satisfy the alignment initialization when the hand has a large in-plane rotation. In this paper, we propose a palms alignment with affine transformation method based on a two-stage convolutional neural network (CNN). The basic idea is to rotate the target palm into the same angle category to avoid the following affine registration has a big matching error at the beginning. At the stage I, the given target palm is classified into two angle categories. At the stage II the upside down palm is firstly rotated 180 degrees, and then inputted into the subsequent feature extraction network, feature matching layer and regression network to achieve the affine alignment. Experimental results have proved the effectiveness of our method.

A full-duplex ultra-dense network (FDUDN) has been envisioned as a promising network paradigm for spectrum efficiency enhancement. This paper presents a novel joint spectrum and power management scheme, which maximizes the total capacity of the FDUDN, under given quality-of-service and cross-tier interference constraints. The proposed scheme is decomposed into inter-cell and intra-cell allocation. A novel approach, which performs initial capacity-maximization allocation and successive adjustment based on the constraints, is proposed for the allocation of the inter-cell subchannels. The inter-cell power control is formulated as a non-convex optimization problem, and variable substitution is used to transform it into a convex one. Furthermore, we solve this problem through a low-complexity heuristic scheme, which utilizes the water-filling theorem in inter-cell power allocation. Finally, a time-sharing relaxation method is adopted to solve the intra-cell subchannel allocation problem and reduce the computation complexity. The Computer simulation demonstrates the enhancement effect of the proposed scheme in terms of the capacity, spectrum efficiency, and power efficiency.

User-centric ultra-dense network (UUDN) has been envisioned as a promising network paradigm due to its advantages over traditional cell-centric structure. This paper introduces full duplex (FD) technology into UUDN and presents a joint scheme of user access, subchannel allocation and power control for FD UUDN. The scheme firstly maximizes the total network capacity under given rate requirements and transmit power constraints. Then if there are no feasible solutions, the system finds the minimal total power of the network to satisfy the rate requirements. The capacity maximization problem is solved by MAPEL algorithm and the power minimization problem is solved by a proposed heuristic algorithm. Simulation demonstrates the spectrum efficiency enhancement and the consumed power reduction of UUDN compared with cell-centric UDN.

Full duplex ultra-dense network (FDUDN) has been envisioned as a promising network paradigm for spectrum efficiency enhancement. This paper presents a novel power management scheme, which maximizes the total capacity of FDUDN, under given Quality-of-Service (QoS) and cross-tier interference constraints. The inter-cell power control is formulated as a non-convex optimization problem and variable substitution is used to transform it into a convex one. Furthermore, we solve this problem through a low-complexity heuristic scheme, which utilizes the water-filling theorem in inter-cell power allocation. Simulation demonstrates the enhancement effect of the proposed scheme in terms of the capacity and the power efficiency.

There are huge amount of tasks and data to be processed in cloud rendering environment.How to effectively schedule them is the key to ensure the overall performance of the cloud rendering environment.In this paper, an improved task scheduling algorithm based on genetic algorithm (PMGA) and probability model is proposed, which aims to minimize the total time and cost of task scheduling .First, the fitness function relating to the total time and task cost is improved under the consideration of the user's satisfaction to the rendering services.Then, a probability model is constructed for the scheduling algorithm, which is used to achieve the non-linear adaptive adjustment of the crossover rate function and the mutation rate function.As a result, the evolutionary ability of poor individuals in the population can be enhanced, avoiding the stagnation in the early stages.Finally, experiments are performed to demonstrate that PMGA has a better ability of optimization than that of traditional adaptive genetic algorithm (AGA).Our approach contributes to reduce the total time and the scheduling cost of the cloud rendering tasks.