At present, there is an urgent need for blockchain interoperability technology to realize interconnection between various blockchains, data communication and value transfer between blockchains, so as to break the ‘ value silo’ phenomenon of each blockchain. Firstly, it lists what people understand about the concept of interoperability. Secondly, it gives the key technical issues of cross-chain, including cross-chain mechanism, interoperability, eventual consistency, and universality. Then, the implementation of each cross-chain key technology is analyzed, including Hash-locking, two-way peg, notary schemes, relay chain scheme, cross-chain protocol, and global identity system. Immediately after that, five typical cross-chain systems are introduced and comparative analysis is made. In addition, two examples of cross-chain programmability and their analysis are given. Finally, the current state of cross-chain technology is summarized from two aspects: key technology implementation and cross-chain application enforcement. The cross-chain technology as a whole has formed a centralized fixed mechanism, as well as a trend of modular design, and some of the solutions to mature applications were established in the relevant standards organizations, and the cross-chain technology architecture tends to be unified, which is expected to accelerate the evolution of the open cross-chain network that supports the real needs of the interconnection of all chains.

Human motion prediction is a critical issue in human-robot collaboration (HRC) tasks. In order to reduce thelocal error caused by the limitation of the capture range and sampling frequency of the depth sensor, a hybrid human motion prediction algorithm, optimized sliding window polynomial fitting and recursive least squares (OSWPF-RLS) was proposed. The OSWPF-RLS algorithm uses the human body joint data obtained under the HRC task as input, and uses recursive least squares (RLS) to predict the human movement trajectories within the time window. Then, the optimized sliding window polynomial fitting (OSWPF) is used to calculate the multi-step prediction value, and the increment of multi-step prediction value was appropriately constrained. Experimental results show that compared with the existing benchmark algorithms, the OSWPF-RLS algorithm improved the multi-

step prediction accuracy of human motion and enhanced the ability to respond to different human movements.  

Aiming at the shortcomings of current gesture tracking methods in accuracy and speed, based on deep learning You Only Look Once version 4 (YOLOv4) model, a new YOLOv4 model combined with Kalman filter rea-time hand tracking method was proposed. The new algorithm can address some problems existing in hand tracking technology such as detection speed, accuracy and stability. The convolutional neural network (CNN) model YOLOv4 is used to detect the target of current frame tracking and Kalman filter is applied to predict the next position and bounding box size of the target according to its current position. The detected target is tracked by comparing the estimated result with the detected target in the next frame and, finally, the real-time hand movement track is displayed. The experimental results validate the proposed algorithm with the overall success rate of 99.43%

at speed of 41.822 frame/ s, achieving superior results than other algorithms. 

Data island and information opacity are two major problems in collaborative administration. Blockchain has the potential to provide a trustable and transparent environment encouraging data sharing among administration members. However, the blockchain only stores Hash values and transactions in blocks which makes it unable to store big data and trace their changes. In this paper, a labor arbitration scheme based on blockchain was proposed to share labor arbitration data. In the system, a collaborative administration scheme that provides a big data storage model combined blockchain and interplanetary file system ( IPFS) is designed. It can store big data and share these data among different parties. Moreover, a file version control mechanism based on blockchain is designed to manage the data changes in IPFS network. It creates a tracing chain that consists of many IPFS objects to track changes of stored data. The relationship of previous and current IPFS objects recorded by blockchain can describe the changes of administration data and trace the data operations. The proposed platform is used in Rizhao City in China, and the experiment result shows collaborative administration scheme achieves traceability with high throughput and is more efficient than traditional hypertext transfer protocol ( HTTP) way to share data.

Existing algorithms of news recommendations lack in depth analysis of news texts and timeliness. To address these issues, an algorithm for news recommendations based on time factor and word embedding ( TFWE) was proposed to improve the interpretability and precision of news recommendations. First, TFWE used term frequency- inverse document frequency ( TF-IDF ) to extract news feature words and used the bidirectional encoder representations from transformers ( BERT ) pre-training model to convert the feature words into vector representations. By calculating the distance between the vectors, TFWE analyzed the semantic similarity to construct a user interest model. Second, considering the timeliness of news, a method of calculating news popularity by integrating time factors into the similarity calculation was proposed. Finally, TFWE combined the similarity of news content with the similarity of collaborative filtering ( CF) and recommended some news with higher rankings to users. In addition, results of the experiments on real dataset showed that TFWE significantly improved precision, recall, and F1 score compared to the classic hybrid recommendation algorithm.

Aiming at the shortcomings of current gesture tracking methods in accuracy and speed, based on deep learning You Only Look Once version 4 (YOLOv4) model, a new YOLOv4 model combined with Kalman filter rea-time hand tracking method was proposed. The new algorithm can address some problems existing in hand tracking technology such as detection speed, accuracy and stability. The convolutional neural network (CNN) model YOLOv4 is used to detect the target of current frame tracking and Kalman filter is applied to predict the next position and bounding box size of the target according to its current position. The detected target is tracked by comparing the estimated result with the detected target in the next frame and, finally, the real-time hand movement track is displayed. The experimental results validate the proposed algorithm with the overall success rate of 99.43%

at speed of 41.822 frame/ s, achieving superior results than other algorithms. 

Unmanned aerial vehicle base stations ( UAV-BSs) can provide a fast network deployment scheme for heterogeneous networks. However, unmanned aerial vehicle (UAV) has limited capability and cannot assist the base station (BS) well. The ability of a UAV to assist the BSs is limited, and the cluster deployment relies on the leading UAV. The dispersive deployment of multiple UAVs (multi-UAVs) need a macro base station (MBS) to determine their positions to prevent collisions or interference. Therefore, a distributed cooperative deployment scheme is proposed for UAVs to solve this problem. The scheme can increase the ability of UAVs to assist users and reduce the pressure on BSs to deploy UAVs. Firstly, the randomly distributed users are pre-clustered. Then the placement problem was modeled as a circle expansion problem and a pre-clustering radius expansion algorithm was proposed. Under the constraint of users-data rates, it provides services for more users. Finally, the proposed algorithm was compared with the density-aware placement algorithm. The simulation results show that the proposed algorithm can provide services for more users and improve the coverage rate of users while ensuring the data rates.

Blockchain technology is used in edge computing ( EC) systems to solve the security problems caused by single point of failure ( SPOF) due to data loss, task execution failure, or control by malicious nodes. However, the disadvantage of blockchain is high latency, which contradicts the strict latency requirements of EC services. The existing single-level sharded blockchain system ( SLSBS) cannot provide different quality of service for different tasks. To solve these problems, a multi-level sharded blockchain system ( MLSBS) based on genetic algorithm ( GA) is proposed. The shards are classified according to the delay of the service, and the parameters such as the shard size of different shards are different. Using the GA, the MLSBS obtains the optimal resource allocation strategy that achieves maximum security. Simulation results show that the proposed scheme outperforms SLSBS.

In order to meet the emerging requirements for high computational complexity, low delay and energy consumption of the 5th generation wireless systems (5G) network, ultra-dense networks (UDNs) combined with multi-access edge computing ( MEC) can further improve network capacity and computing capability. In addition, the integration of green energy can effectively reduce the on-grid energy consumption of system and realize green computation. This paper studies the joint optimization of user association (UA) and resource allocation (RA) in MEC enabled UDNs under the green energy supply pattern, users need to perceive the green energy status of base stations (BSs) and choose the one with abundant resources to associate. To minimize the computation cost for all users, the optimization problem is formulated as a mixed integer nonlinear programming (MINLP) which is NP-hard. In order to solve the problem, a deep reinforcement learning ( DRL)-based association and optimized allocation (DAOA) scheme is designed to solve it in two stages. The simulation results show that the proposed scheme has good performance in terms of  computationcost and time out ratio, as well achieve load balancing potentially.

Vehicle trajectory modeling is an important foundation for urban intelligent services. Trajectory prediction of cars is a hot topic. A model including convolutional neural network (CNN) and long short-term memory (LSTM) was proposed, which is named trajectory-CNN-LSTM (TCL). CNN can extract the spatial features of the trajectory in the input image. Besides, LSTM can extract the time-series features of the input trajectory. After that, the model uses fully connected layers to merge the two features for the final predicting. The experiments on the Porto dataset of The European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML-PKDD) show that the average prediction error of TCL is reduced by 0.15 km, 0.42 km, and 0.39 km compared to the trajectory-convolution (T-CONV), multi-layer perceptron (MLP), and recurrent neural network (RNN) model, respectively.

A downlink covert communication model that consists of a base station and two legitimate users was considered. In addition to the general signals shared by the two users, the base station will send the covert signals only to one user in a certain time without wanting the other to detect this covert communication behavior. In order to achieve covert communication, two information transmission schemes are designed based on transmission antenna selection (TAS) with the help of artificial noise (AN) transmitted by the user receiving the covert signals, denoted as TAS-Ι and TAS-Πrespectively. Considering the best detection performance of the user only receiving the general signals, under the two schemes, the detection error probabilities and their average values, the connection probabilities, the system covert throughputs are separately calculated. In addition, on the premise of meeting the system’s covert conditions, an optimization scheme is proposed to maximize the covert system throughput. Finally, the simulation

results show that the proposed system can realize covert communication successfully, and the system covert performance under TAS-Ι is better than that under TAS-Π.

In order to predict traffic flow more accurately and improve network performance, based on the multifractal wavelet theory, a new traffic prediction model named exo-LSTM is proposed. Exo represents exogenous sequence used to provide a detailed sequence for the model, LSTM represents long short-term memory used to predict unstable traffic flow. Applying multifractal traffic flow to the exo-LSTM model and other existing models, the experiment result proves that exo-LSTM prediction model achieves better prediction accuracy.

The color, shape, and other appearance characteristics of the flame emitted by different flame engines are different. In order to make a preliminary judgment on the category of the device to which it belongs through studying exterior characteristics of the flame, this paper uses the flame of matches, lighters, and candles to simulate different types of flames. It is hoped that the flames can be located and classified by detecting the characteristics of flames using the object detection algorithm. First, different types of fire are collected for the dataset of experiments. The mmDetection toolbox is then used to build several different object detection frameworks, in which the dataset can be trained and tested. The object detection model suitable for this kind of problem is obtained through the evaluation index analysis. The model is ResNet50-based faster-region-convolutional neural network ( Faster R- CNN), whose mean average-precision ( mAP) is 93.6% . Besides, after clipping the detected flames through object detection, a similarity fusion algorithm is used to aggregate and classify the three types of flames. Finally, the color components are analyzed to obtain the red, green, blue ( RGB) color histograms of the three flames.

Threshold proxy re-encryption( PRE) authorizes the data access right of data subject to multiple proxies, who authorize the right again to delegatee to accomplish the end-to-end data encryption process from storage to authorization. Based on threshold PRE algorithm, in order to build a complete trusted data storage and authorization system, the four protocols, which are data access protocol, authorization proxy protocol, authorization proxy cancellation protocol and data reading authorization protocol, are defined completely. On that basis, an efficient data searching method is constructed by specifying the data delegatee. At last, to ensure the right to know of data, the audit log is processed with trusted data right confirmation based on distributed ledger technology. Meanwhile, a parallel data right confirmation processing method is defined based on hierarchical derivation algorithm of public and private key. In the end, the performance evaluation analysis of the protocol are given. Trusted data access and authorization protocol is convenient to build a complete data processing system on the premise of protecting data privacy based on public cloud storage system or distributed storage system.

In distributed systems, it is important to adjust load distribution dynamically based on server performance and load information. Meanwhile, gray release and rapid expansion are the basic requirements to ensure reliability and stability for systems with short version iteration cycles. The traditional Hash algorithm performs poorly in gray release, rapid expansion, and load distribution. To solve these problems, a novel Hash-based dynamic mapping (HDM) load balancing algorithm was proposed. On the one hand, this algorithm can adjust the load distribution dynamically based on server performance and load information. On the other hand, it implements gray release by controlling the ratio of requests assigned to the changed nodes. Additionally, HDM has a higher expansion efficiency. Experiments show that the HDM distributes the load more reasonably, provides a more stable gray release ratio, and has a higher expansion efficiency.