Due to its unique signal propagation environment, the introduction of uncrewed aerial vehicles (UAVs) for 6G communications has brought many new challenges. These new challenges, particularly increased resource constraints and signal interference among UAVs, necessitate optimal UAV deployment through trajectory planning. Unfortunately, existing two-dimensional (2D) UAV trajectory planning techniques with pre-determined heights can hardly meet the demands of ground user equipment (UE) through opportunistic use of limited radio resources. To overcome the related issues, a new multi-UAV three-dimensional (3D) trajectory planning strategy enabled by multi-agent deep reinforcement learning (MADRL) is proposed in this work. First, the position of each UAV at every timeslot can be adaptively adjusted in 3D to boost the agility of on-demand deployment. Furthermore, more comprehensive system performance metrics, including UE coverage rate, downlink sum rate, and energy consumption, are jointly considered as the optimization objectives, formulating a multi-objective optimization problem for multi-UAV 3D trajectory planning. To support the diverse demands of UAVs autonomously, a MADRL algorithm, multi-agent proximal policy optimization (MAPPO), is further developed as the solution. Simulations have been conducted based on practical scenario settings. The results indicate that the improved MAPPO can empower the 3D movements of UAVs based on their local observations while optimizing the system performance.

This work presents an accurate and robust method for estimating normals from point clouds. In contrast to predecessor approaches that minimize the deviations between the annotated and the predicted normals directly, leading to direction inconsistency, we first propose a new metric termed Chamfer Normal Distance to address this issue. This not only mitigates the challenge but also facilitates network training and substantially enhances the network robustness against noise. Subsequently, we devise an innovative architecture that encompasses Multi-scale Local Feature Aggregation and Hierarchical Geometric Information Fusion. This design empowers the network to capture intricate geometric details more effectively and alleviate the ambiguity in scale selection. Extensive experiments demonstrate that our method achieves the state-of-the-art performance on both synthetic and real-world datasets, particularly in scenarios contaminated by noise. Our implementation is available at https://github.com/YingruiWoo/CMG-Net_Pytorch.

In this paper, we present a unmanned aerial vehicles (UAV) relay covert communication scheme assisted by an intelligent reflecting surface (IRS), which is exploited to improve channel quality between transmitter and legitimate user. Specifically, we formulate a nonconvex optimization problem to maximize average covert rate, where trajectory of the UAV, transmit beamforming (TB) at Alice, and passive beamforming (PB) of the IRS under the covert constraint are considered. To tackle the difficult problem, we divide it into trajectory optimization (TO) subproblem, TB optimization subproblem, and PB optimization subproblem and then solve them alternately via successive convex approximation algorithm and semidefinite relaxation technique respectively. Numerical results demonstrate the effectiveness of the proposed approach and provide insights on how covert rate is influenced by the trajectory, TB, and PB.

Internet of Vehicles (IoV) has enabled intelligent services for connected vehicles such as advanced driver assistance and autonomous vehicles. However, due to the multiple external communication interfaces, intelligent connected vehicles (ICVs) are vulnerable to malicious network intrusion attacks. The malicious attackers can not only remotely intrude into the in-vehicle networks (IVNs) and control the compromised vehicles, but also invade the neighboring vehicles through IoV. To protect the compromised vehicles from being manipulated, a novel federated long short-term memory (LSTM) neural network-based IVN intrusion detection method is proposed in this paper. Specifically, based on the periodicity of the ID sequence of IVN messages, an LSTM neural network model is built for the incoming message ID prediction, and an ID prediction-based network intrusion detection method is developed subsequently. Moreover, an FL framework working in client-server mode is built for secure and efficient LSTM neural network model training in IoV systems. In the framework, ICVs work as the clients for local model training, and base stations (BSs) equipped with mobile edge computing (MEC) servers are the parameter servers for global model parameter aggregation. Simulations have been conducted based on the practical dataset. The numerical results indicate that the detection accuracy of the federated-LSTM based method on spoofing, replay, drop, and DoS attacks is beyond 90%.

Abstract The 5G and beyond (B5G) networks are expected to provide significantly increased capacity for diverse services with limited spectrum resources. However, new aspects of B5G networks particularly the ultra‐dense network deployment and the heterogeneous network structure, make spectrum resources highly distributed in three‐dimension (3D), which brings unprecedented challenges for highly efficient spectrum utilization, especially in an indoor environment. To tackle the challenges on dynamic spectrum utilization and improving the volume capacity of indoor 3D networks, a collaborated crowdsensing approach is proposed for the coordinated 3D spectrum utilization through integrating the crowdsensing, data analytics, and software defined network (SDN) techniques. The integration of sensing, learning, and intelligent control provides critical capabilities for timely observing 3D radio resources and enabling the coordinated radio resource utilization among co‐existing indoor heterogeneous networks (HetNets). Case study confirms the superiority of the proposed coordinating method on achieved volume capacity.

Data dissemination of vehicles is critical for vehicular networks because of the extensive impact of traffic information. The existing works for data dissemination in vehicular networks mainly use data scheduling algorithms to transmit data among vehicles. However, it is challenging to meet the ultrareliable and low-latency requirements of data transmission among vehicular networks due to the intrinsic movement characteristic of vehicles. To promote the data dissemination of vehicular networks, a data dissemination algorithm with trajectory privacy protection is proposed in this article, which leverages the cooperative distribution of key tasks and distance deviation. Specifically, the key tasks are disseminated to vehicles first, and the trajectory privacy protection scheme is further developed to guarantee the security of data transmission by the exploration of distance deviation and pseudonym entropy. Simulation results indicate that the proposed adaptive data dissemination algorithm is approximately 60%, 69%, and 50% better than the state-of-the-art scheduling algorithms in terms of connectivity degree, transmission delay, and average distance deviation for the vehicular network.

In this article, an adaptive tracking control approach is developed for a class of strict-feedback nonlinear systems with time-varying full state constraints. As a breakthrough in this system, the special function constraints (whose constraint boundary is relevant to both state variables and time) are considered, which are rarely studied by research work. And there is no doubt that this method increases the complexity of designing this scheme. Furthermore, the time-varying integral barrier Lyapunov functions combining with backstepping technique is introduced to break the limitation of traditional methods as well as achieve the full state constraints. Meanwhile, fuzzy logic systems are selected to approximate unknown nonlinear functions. It is verified that all closed-loop signals are bounded and all states are forced in the time-varying boundness. In addition, the proposed control strategy has a good performance. The effectiveness of the theoretical analysis results is proved via a simulation example.

The awareness of physical network topology in a large-scale Internet of Things (IoT) system is critical to enable location-based service provisioning and performance optimization. However, due to the dynamics and complexity of IoT networks, it is usually very difficult to discover and update the physical topology of the large-scale IoT systems in real-time. Considering the stringent latency requirements in IoT systems, while the initial processing time for topology discovery can be tolerated, latency due to real-time topology update constitutes an even higher level of challenge. In this paper, a novel fast hierarchical topology update scheme is proposed for the large-scale IoT systems enabled by using the edge-cloud collaborative architecture. Specifically, an event-driven neighbor update algorithm, termed as TriggerOn, is firstly developed to update the local neighbor table of the end devices when device association or disassociation occurs. Based on the updated neighbor tables, the physical topology update of the subnet is conducted at the coordinated edge device, where a hybrid multidimensional scaling (MDS) based 3D localization algorithm is developed to locate the newly associated devices. Simulation results have indicated that as compared to the benchmark methods, the neighbor discovery latency has been reduced dramatically, and the 3D localization accuracy has been improved. Furthermore, the overall latency incurred by the proposed hierarchical physical topology update scheme is significantly lower than the distributed consensus-based update scheme, especially for the large-scale IoT subnets.

Chromosome enumeration is an essential but tedious procedure in karyotyping analysis. To automate the enumeration process, we develop a chromosome enumeration framework, DeepACEv2, based on the region based object detection scheme. The framework is developed following three steps. Firstly, we take the classical ResNet-101 as the backbone and attach the Feature Pyramid Network (FPN) to the backbone. The FPN takes full advantage of the multiple level features, and we only output the level of feature map that most of the chromosomes are assigned to. Secondly, we enhance the region proposal network's ability by adding a newly proposed Hard Negative Anchors Sampling to extract unapparent but essential information about highly confusing partial chromosomes. Next, to alleviate serious occlusion problems, besides the traditional detection branch, we novelly introduce an isolated Template Module branch to extract unique embeddings of each proposal by utilizing the chromosome's geometric information. The embeddings are further incorporated into the No Maximum Suppression (NMS) procedure to improve the detection of overlapping chromosomes. Finally, we design a Truncated Normalized Repulsion Loss and add it to the loss function to avoid inaccurate localization caused by occlusion. In the newly collected 1375 metaphase images that came from a clinical laboratory, a series of ablation studies validate the effectiveness of each proposed module. Combining them, the proposed DeepACEv2 outperforms all the previous methods, yielding the Whole Correct Ratio(WCR)(%) with respect to images as 71.39, and the Average Error Ratio(AER)(%) with respect to chromosomes as about 1.17.

Internet of Things (IoT) technology has been pervasively applied to environmental monitoring, due to the advantages of low cost and flexible deployment of IoT enabled systems. In many large-scale IoT systems, accurate and efficient data sampling and reconstruction is among the most critical requirements, since this can relieve the data rate of trunk link for data uploading while ensure data accuracy. To address the related challenges, we have proposed an unmanned aerial vehicle (UAV) enabled spatial data sampling scheme in this paper using denoising autoencoder (DAE) neural network. More specifically, a UAV-enabled edge-cloud collaborative IoT system architecture is first developed for data processing in large-scale IoT monitoring systems, where UAV is utilized as mobile edge computing device. Based on this system architecture, the UAV-enabled spatial data sampling scheme is further proposed, where the wireless sensor nodes of large-scale IoT systems are clustered by a newly developed bounded-size K-means clustering algorithm. A neural network model, i.e., DAE, is applied to each cluster for data sampling and reconstruction, by exploitation of both linear and nonlinear spatial correlation among data samples. Simulations have been conducted and the results indicate that the proposed scheme has improved data reconstruction accuracy under the sampling ratio without introducing extra complexity, as compared to the compressive sensing-based method.

Wireless sensor networks (WSNs) have been rapidly integrated into Internet of Things (IoT) systems, empowering rich and diverse applications such as large-scale environment monitoring. However, due to the random deployment of sensor nodes (SNs), physical topology of the WSNs cannot be controlled and typically remains unknown to the IoT cloud server. Therefore, in order to derive the physical topology at the cloud for effective real-time event detection, a cloud-orchestrated physical topology discovery scheme for large-scale IoT systems using unmanned aerial vehicles (UAVs) is proposed in this paper. More specifically, the large-scale monitoring area is first split into a number of subregions for UAV-enabled data collection. Within the subregions, parallel Metropolis-Hastings random walk (MHRW) is developed to gather the information of WSN nodes, including their IDs and neighbor tables. The collected information is then forwarded to the cloud through UAVs for the initial generation of logical topology. Thereafter, a network-wide 3-D localization algorithm is further developed based on the discovered logical topology and multidimensional scaling method (Topo-MDS), where the UAVs equipped with global positioning system are served as mobile anchors to locate the SNs. Simulation results indicate that the parallel MHRW improves both the efficiency and accuracy of logical topology discovery. In addition, the Topo-MDS algorithm dramatically improves the 3-D location accuracy, as compared to the existing algorithms in the literature.

The recent advancement of Internet of Things (IoT) technologies has enabled many emerging applications, including smart building and connected vehicles. These advanced applications generate massive amount of data at the edge of IoT networks, which usually need to be relayed to a remote data center for further real-time processing. However, uploading all these IoT data to the cloud platform imposes a heavy burden on the underlying network. The unavoidable long delay from data exchange and processing significantly reduces the time-responsiveness of real-time IoT applications. Recently, fog computing has been introduced to IoT applications as an intermediate between end devices and cloud for primary IoT data processing. In this paper, a temporal IoT data reduction scheme through fog computing is proposed to reduce the total amount of IoT data uploaded to the cloud. More specifically, IoT data are first modeled as multivariate normal distribution by the cloud. Dual Kalman filters (KF) with identical parameters are then deployed at both the cloud and fog platforms. The same predictions are simultaneously triggered by the dual KFs at both platforms. Only the measured IoT data out of predicted range are further uploaded from fog to cloud. Otherwise, predicted values at both platforms are used instead of measurements. A simple prototype IoT system is developed for performance evaluation. Experimental results indicate that the proposed scheme significantly reduces the number of packets uploaded to the cloud platform with high data accuracy.

Internet of Things (IoT) is emerging as the underlying technology of our connected society, which enables many advanced applications. In IoT-enabled applications, information of application surroundings is gathered by networked sensors, especially wireless sensors due to their advantage of infrastructure-free deployment. However, the pervasive deployment of wireless sensor nodes generate massive amount of sensor data, and data outliers are frequently incurred due to the dynamic nature of wireless channels. As operation of IoT systems relies on sensor data, data redundancy and data outliers could significantly reduce the effectiveness of IoT applications or even mislead systems into unsafe conditions. In this paper, a cluster-based data analysis framework is proposed using recursive principal component analysis (R-PCA), which can aggregate the redundant data and detect the outliers in the meantime. More specifically, at a cluster head, spatially correlated sensor data collected from cluster members are aggregated by extracting the principal components (PCs), and potential data outliers are determined by the abnormal squared prediction error score, which is defined as the square of residual value after extraction of PCs. With R-PCA, the parameters of PCA model can be recursively updated to adapt to the changes in IoT systems. Cluster-based data analysis framework also releases the computational and processing burdens on sensor nodes. Practical databases-based simulations have confirmed that the proposed framework efficiently aggregates the correlated sensor data with high recovery accuracy. The data outlier detection accuracy is also improved by the proposed method compared to other existing algorithms.

Wireless sensor networks (WSNs) are widely considered as the most important information gathering platform in enabling Internet of Things (IoT). In order to evolve the traditional WSNs for low-power and low-loss IoT applications, time slotted channel hopping (TSCH) MAC protocol has been proposed to tackle the single channel and inefficient medium access drawbacks through improved network topology awareness. However, the problem of maintaining the physical topology of a WSN at the server end remains unresolved. In this paper, we propose a novel physical topology discovery scheme for WSNs by exploitation of random walk process and iterative multilateration localization algorithm. Explicitly, information specific to the sensor nodes, including IDs and neighbor tables, are collected in the random walk process. The physical topology is then reconstructed at the server end based on the collected information and the iterative multilateration localization algorithm. Simulation results indicate that the average location offset between the established topology and the ground- truth topology can be as low as 1.26m.

Wireless sensor networks have already been pervasively utilized due to the rapid deployment of information and communication technology (ICT) in many industrial applications, which generate massive amount of sensor data. This development has brought several technical challenges in sensor data processing, e.g., data fault and data redundancy. Principal component analysis (PCA) has been used recently to process the massive but correlated sensor data. However, the conventional PCA method is difficult to be adapted in following the dynamic conditions of wireless sensor networks. In this paper, recursive principal component analysis (R-PCA) method is exploited to progressively update the transformation basis for extracting principal components. Furthermore, a novel R-PCA based algorithm is proposed to address data fault and data redundancy problems. Different from conventional PCA-based algorithms, the proposed algorithm is cluster-based so that the network efficiency can be further improved. Simulations based on a practical dataset have been conducted to evaluate the performance of algorithms. Simulation results show that the proposed algorithm improves the fault detection accuracy by about 20% and reduces the data restoration error by about 28%.

Energy efficiency is one of the most critical issues in wireless sensor networks, since the sensor nodes are usually battery powered. These energy-constrained sensor nodes are usually densely distributed in indoor environments, which leads to spatially correlated sensor data and low network efficiency. Thus, one way to improve energy efficiency is to reduce the redundancy caused by the correlated data. In this paper, a new sensor scheduling algorithm, based on data correlation, is proposed. The sensor nodes are clustered into groups by a new adaptive dual-metric K-means (DK-means) algorithm. Within each group, the sensor nodes take turns to work as a group representative and transmit data to the sink. Thus, the energy consumed by the redundant transmissions of the correlated sensor data is saved. Performance evaluation of the proposed mechanism is conducted through OPNET simulations. The simulation results show that the adaptive DK-means algorithm significantly improves data reliability, as compared to the adaptive K-means algorithm. Furthermore, this improvement in reliability is achieved with minimal cost in terms of complexity. Finally, it is shown that the proposed sensor scheduling algorithm achieves energy savings of up to 58%, as compared to the baseline ZigBee protocol.