Search

Most human synthesis schemes use high-performance servers, so the user interaction experience of mobile devices is not satisfied. Viewing human synthesis results on smartphones directly increases user interaction and enhances user experience. This paper proposes a smart frame selection network (SFSN) on mobile devices to reduce the traffic between smartphones and cloud. We leverage the attention and relationship model to focus on the relationship between a single frame and the entire video, which can better select important frames, thus reducing the traffic and computing effectively. In addition, we build a multi-task human synthesis system based on SFSN to process the generation tasks such as background changing, pose transfer and virtual try-on in a unified framework. Evaluation results indicate proposed approach reduces the number of frames to be processed by more than 42.2%. [ABSTRACT FROM AUTHOR]

In heterogeneous networks where macro cells and metro cells use the same frequency band to communicate with their respective users, the major problem limiting performance is the interference caused by macro cells to metro cells. The information theoretic result known as dirty paper coding provides a way to address this problem and significantly improve the performance of heterogeneous networks with co-channel deployment. In this paper, we show how a simple dirty paper coding scheme employing Tomlinson-Harashima pre-coding with partial interference pre-subtraction can be employed by metro cells to mitigate the interference caused by macro cells. A performance study included in this paper shows that the proposed dirty paper coding scheme can lead to significant improvement in user rate statistics. [ABSTRACT FROM AUTHOR]

Stability in queue characteristics with average power and maximized data processing is a prominent research issue in any networks. These should be ensured even in Mobile Edge Computing (MEC) models where smooth and continuous integration of innovative applications are provided with low latency and improved quality. An offloading plan is required for ensuring this with regulation of processing capacity and network operational cost in edge nodes which will improve the efficiency of the IoT with edge computing. A task-based offloading algorithm is proposed in this paper for taking smart decisions for better resource allocation and augmentation of computational capabilities to the MEC server by allowing mobile devices (MDs) for offloading their intensive computation-based tasks to proximal Multi-eNodeBs (Multi-eNBs) based on the time-varying channel desired state. A wireless MEC devices model which is being used by many users for broadcasting their task is considered. The queue stability and minimizing the consumed energy along with maximizing the reward even under the constrained deadline is maintained by our proposed novel framework, named DCARL–ARP (Deep Convolution Attention Reinforcement Learning–Adaptive Rewarding Policy) which combines the Deep Convolution and Lyapunov optimization with feature map attention mechanism. DCARL–ARP is incorporated for the proper state selection decisions at different time frame. The performance analysis and evaluation prove that the DCARL–ARP has the optimum computation rate which is appropriate for real-time implementation in varying channel conditions. The experimental evaluation shows that this mechanism can effectively reduce the average energy consumption for execution by 0.02% and the average data queue length by 50%. [ABSTRACT FROM AUTHOR]

Under the condition of high performance sports, the physical state of Wushu routine athletes is very different from that of commons, and they need the strength support of the core muscle tissue. Specifically, core strength training has an important impact on the physical stability of Wushu routine athletes, and strengthening core strength training can improve their physical quality. In core strength training, video training method can make up for the shortcomings of traditional training methods. In addition, with the rapid development of wireless network technology, video service has become the mainstream application of mobile Internet. At the same time, users' experience needs for video services under wireless networks have gradually changed, and the traditional video Quality of Experience (QoE) is difficult to fully reflect users' actual experience quality. Therefore, this paper proposes a QoE prediction model based on core strength training video information, data of quality of service, and behaviors of Wushu routine athletes. The experimental results show that the QoE prediction model of core strength training video converges rapidly in the training process, and has a good fitting effect on the training set and verification set. Furthermore, the QoE prediction model proposed in this paper can improve the accuracy of subjective QoE of Wushu routine athletes in wireless network environment. The construction of QoE prediction model is the premise of optimizing QoE. An effective QoE prediction model can reflect the real video experience of Wushu routine athletes and provide a comprehensive and accurate QoE reference for the construction of core strength training video, so as to improve the physical quality of Wushu routine athletes. [ABSTRACT FROM AUTHOR]

Device-free localization (DFL) systems have aroused extensive attention because it is more convenient than device-enabled localization systems, and fingerprint-based localization method is usually used in DFL systems. Although fine-grained information can be provided by the channel state information (CSI), but changes in the environment over time can cause the CSI become different. Therefore, the real-time CSI data can't match with the data in the fingerprint map established beforehand very well, which can lead to the inaccuracy of the positioning result. This paper presents a DFL system, which adopts transfer learning method to update the fingerprint map and employs the Light Gradient Boosting Machine (LightGBM) algorithm to train the fingerprint map. Wavelet transform is used in this paper to filter the noise in the raw CSI data and the CSI data on a portion of the fingerprint points are collected to update the established fingerprint map by joint distribution adaptation in the update stage. After classifying the CSI data of the testing point by LightGBM, the position coordinate is achieved by the confidence regression method. By using LightGBM, the proposed system can achieve the average distance error of 0.48m, outperforming the result by using eXtreme Gradient Boosting (XGBoost) and Gradient Boost Decision Tree (GBDT). According to the result of the four-week experiment, the average distance error of this system can be decreased by 21% compared with not using the calibration method. [ABSTRACT FROM AUTHOR]

With the rapid development of computer technology and network communication technology, embedded micro control system has been widely used. It is crucial in the fields of large-scale chemical equipment, mechanized production base, transportation and future robots. Combined with the current Internet of Things technology, the equipment needs to be kept on the network during operation, real-time data comparison, data feedback, data reception and other network operations to provide strong help for human society. Focusing on the network communication level, due to the improvement of hardware and software technology, the basic link work has become the foundation part of realizing network communication, and the real problem is often the information transmission. For example, for wireless channel estimation and optimization based on embedded system, it is necessary to eliminate the interference of irresistible factors as far as possible, overview the defects in algorithm level and logic analysis level since the development of network communication technology, discuss the impact of network communication module of embedded monitoring system in practical application as far as possible, and make the error infinite to zero under the premise of unchanged hardware conditions. Based on the above conditions, the lightweight channel estimation method and the optimization under the condition of sparse matrix are proposed. This paper studies the network communication of embedded devices, especially the channel link in network communication, and focuses on the channel estimation algorithm. This paper proposes the advantages of LS and MMSE algorithms. According to the experimental results, although in terms of speed indicators, it still maintains better than the traditional algorithm in terms of average throughput, transmission delay, response time, transmission rate and so on in a static environment. [ABSTRACT FROM AUTHOR]

In vehicular cloud computing (VCC) systems, the vehicle cloud (VC) consists of computing resources for multiple vehicles to assist the remote cloud (RC) in making real-time decisions on driving vehicles, to improve road safety and driving comfort. The acquisition of additional cloud facilities to increase the capacity of VCC systems when processing intensive requests for cloud resources is costly. A recent approach uses multiple remote microclouds (RMCs) to assist RCs in processing requests because they are smaller and less costly than RCs. Therefore, this paper presents a VCC system with multiple RCs and RMCs, in which an algorithm for allocating request resources among VCs, RMCs, and RCs. Subsequently, this paper proposes an improved simulated annealing algorithm (ImSA) based on density of vehicles in a geographical area to deploy RCs and RMCs with the minimal deployment cost and response cost. For real applications, the accuracy and effectiveness of the proposed algorithm are evaluated on the basis of the real traffic data from three different areas (i.e., urban area, outskirts, and suburban area) in one week. [ABSTRACT FROM AUTHOR]

Industrial internet traffic prediction is not only an academic problem, but also a concern of industry and network performance department. Efficient prediction of industrial internet traffic is helpful for protocol design, traffic scheduling, detection of network attacks, etc. This paper proposes an industrial internet traffic prediction method based on the Echo State Network. In the first place this paper proves that the industrial internet traffic data are self-similar by means of the calculation of Hurst exponent of each traffic time series. It indicates that industrial internet traffic can be predicted utilizing nonlinear time series models. Then Echo State Network is applied for industrial internet traffic forecasting. Furthermore, to avoid the weak-conditioned problem, grid search algorithm is used to optimize the reservoir parameters and coefficients. The dataset this paper perform experiments on are large-scale industrial internet traffic data at different time scale. They come from Industrial Internet in three regions and are provided by ZTE Corporation. The result shows that our approach can predict industrial internet traffic efficiently, which is also a verification of the self-similarity analysis. [ABSTRACT FROM AUTHOR]

With the continuous development of new energy power generation and smart grid, Power Electronic Transformer (PET) has a good prospect for development because of its remarkable advantages. Based on the topology of AC/DC/AC, the modulation strategy with dual-PWM (Pulse Width Modulation) is adopted to control the operation of power electronic transformers in this paper. The PET structure consists of three units: importation portion, isolation portion and output portion. Model building and analyzing both at the input and output terminals are achieved step by step. And the simulation of the whole PET system with dual-PWM is accomplished with MATLAB/ Simulink. The simulation results show the control system stability and output voltage regulation precision are improved with feed-forward voltage decoupling vector control system. The correctness and effectiveness of the control strategy are demonstrated through the simulation. PETs play an important role in enhancing power supply reliability for Power Grid and promoting the new energy power generation development. [ABSTRACT FROM AUTHOR]

With the development of science and technology and the popularization of e-commerce, the application of wireless network technology in the business field has gradually become a hot spot of academic research, which also brings us new topics and challenges. The secure payment system based on the improved TOTP algorithm proposed in this paper involves the WAP wireless secure payment theory and the application of mobile e-commerce. This paper first studies the WAP wireless network theory of mobile payment system, and proposes the WAP algorithm flow based on identity encryption. Then, the secure wireless execution environment of the WAP encryption payment algorithm is analyzed in depth. This paper discusses the security requirements of the WAP wireless network payment system. Based on the identity encryption algorithm, several practical algorithms are proposed, and a wireless network mobile payment model combining NTRU and ECC is constructed to improve the WAP algorithm. This paper proposes a WAP wireless network security payment system based on the improved TOTP algorithm, constructs its overall structure, and designs a core algorithm with strong adaptability, including the improved TOTP algorithm and risk assessment algorithm. Finally, the performance of the WAP e-commerce secure payment system is tested and analyzed. The research found that when the 256-bit key was used to encrypt the login information, the number of tests was 23,588, the number of concurrent threads was 200, the number of requests per second was 518, the average response time was 0.219 s, the average traffic was 500 KB/s, and the error rate was 2%. It can be seen from the data that the WAP wireless secure payment system operates normally with low network delay and can respond to operation requests quickly under the condition of concurrent access by multiple users, with strong overall pressure resistance. The work of this paper has a good reference value for the construction of the WAP wireless network payment system and the design and application of mobile e-commerce, which is conducive to further research. [ABSTRACT FROM AUTHOR]

Aiming at the received signal strength index (RSSI) in wireless positioning system, an improved weighted KNN fingerprint positioning algorithm is proposed in this paper. The algorithm pre-processes fingerprint data in offline stage that including eliminating outliers and Kalman filtering first, in order to improve the accuracy of data acquisition. Secondly, the fingerprint data is partitioned by using RSSI to attenuate obstacles such as walls. Then, points with significant RSSI differences in each region are selected as regional feature points, and the distance between RSSI of test points and feature points in each region is calculated respectively to determine the region in which the test points are located. Geometric method is used to analyse and define the correlation degree, and KNN is re-weighted to achieve accurate positioning in the region. Finally, experiments were carried out in the indoor environment to complete the establishment of the fingerprint database. Compared with the existing NN, KNN and WKNN, the experimental analysis results show that the accumulated error and average error are better than the traditional algorithm with the increase of measurement points, which has reference value for the complex environment positioning technology. [ABSTRACT FROM AUTHOR]

With the rapid development of wireless communication technology, modulation signals are more and more intensive in the same frequency. Time-frequency overlapped signal over co-channel widely exists in the shortwave, ultrashort wave and satellite channels, so the research on the time-frequency overlapped signals in non-cooperation receiver is of great significance. This paper firstly studies on blind estimation of amplitude of time-frequency overlapped signals. On the basis of deep analysis of cyclic stationary characteristic in the time-frequency overlapped signals, an amplitude estimation method of time frequency overlapped signal over co-channel based on four-order cyclic cumulants is proposed. The magnitude of the signal components is estimated by using the amplitude value of four-order cyclic cumulants of overlapped signals in certain cyclic frequency. And then an initial phase estimation method based on four-order cyclic cumulants is proposed in this paper. Experiments are conducted to verify the proposed parameter estimation method of time-frequency overlapped signals in this paper. Simulation results show that the proposed blind estimation method can achieve better estimation performance in low signal-to-noise ratio (SNR) conditions. [ABSTRACT FROM AUTHOR]

In recent years, with the increasing number of terminal connections, high-density deployment scenarios have become important scenarios for future wireless networks. Ultra-high throughput (EHT) in high density deployment scenarios is the technical goal of IEEE 802.11be, the next-generation wireless local area network (WLAN) standard. However, in a high-density deployment scenario, interference suppression between BSSs is serious, which seriously affects the throughput of a WLAN. And the resources available are limited. Therefore, for the next generation WLAN standard, this paper proposes a downlink transmission scheme based on AP coordination and the orthogonal frequency division multiple access (OFDMA) protocol and the non-orthogonal multiple access (NOMA) protocol, named Co-OFDMA–NOMA scheme. The core idea is to transform the interference and suppression relationship between neighboring BSSs into the relationship of mutual coordination and assistance through the Co-OFDMA–NOMA protocol proposed in this paper. Firstly, a downlink transmission scheme named the Co-OFDMA–NOMA protocol is designed. In addition, the protocol and its framework structure have good backward compatibility. Theoretical analysis shows that the proposed Co-OFDMA–NOMA protocol has significant performance gain, and simulation results prove the effectiveness of the scheme. [ABSTRACT FROM AUTHOR]

Vehicular ad hoc network (VANET) is one of the challenging research areas in recent times with applications to intelligent traffic systems. In VANET, the link between vehicles going in opposite directions only lasts for a very short time when they are within range of each other, otherwise lost, hindering the complete exchange of meaningful information. Most valuable applications on VANET are related to safety-related applications that require real-time response. If the safety and the real-time requirements are not met, serious consequences may result in the form of traffic accidents or failed rescue operations. Flooding attacks on route request packet (RREQ) disrupt the communication between parties, reduce the successful packet delivery rate, and introduce excessive packet transmission delays. This type of attacks, when executed over VANET, may result in disastrous consequences for critical applications such as collision warning or autonomous vehicle assistance. Many security solutions have been proposed; however, they all have several limitations: either they fail to recognise malicious nodes when they attack with low frequency rates, or they suffer performance degradation because of the burden of add-on security measures by the solutions even when malicious nodes are not present in the environment. This paper proposes a Median Filter based flooding attacks detection algorithm (MFFDA) that enables efficient and reliable operation on VANET. The MFFDA solution is novel in three aspects: (1) it uses a route discovery frequency vector (V) to capture a node's behavioral history; (2) it uses a nonlinear mapping to transform the representational space V into a new space VMF through the use of a Median Filter; (3) it utilises a robust statistic-the median value (mv)—of the data sample V and a suitable separating hyperplane to detect malicious nodes. The paper also proposes the Flooding Attacks Prevention and Detection Routing Protocol (FAPDRP), that incorporates the proposed MFFDA for routing protection. Using NS2, the paper simulated the FAPDRP and related protocols in both attacked and normal network scenarios. The results show that the proposed solution has an accuracy over 98.5% under the minimal flooding attacks 10 pkt/s, outperforms those of previous studies. In addition, the performance of FAPDRP approaches that of the AODV in both attacked and normal network scenarios. This confirms that the proposed MFFDA satisfies the delay, efficiency, and reliability constraints for VANET environment. [ABSTRACT FROM AUTHOR]

As the processing power of mobile terminals increases, wireless network applications such as voice assistants can put more context-sensitive tasks on the mobile terminals, thus reducing the wireless network bandwidth needed and the cost of data storage in the cloud. Co-reference annotation, identifying the same semantics in context, is one of the critical techniques in these tasks. However, there are some problems with the existing co-reference annotation standards. First, the annotation is incomplete. Second, the types of annotated mentions are inconsistent. Third, there are currently no metrics for the above characteristics. Analyzing the above-mentioned issues, this paper proposes a new co-reference annotation standard. The new standard can annotate more semantics and co-reference relations and only adopts two types of mentions for annotation. Meanwhile, this paper presents a performance evaluation corpus and designs three performance metrics for evaluating the new standard according to the completeness of semantic annotation, the completeness of co-reference annotation, and the consistency of mention. The experiment shows that the new standard outperforms all the baseline methods and achieves 0.95 in the completeness of semantic annotation, 0.68 in the completeness of co-reference annotation, and 0.57 in the consistency of types of mentions. [ABSTRACT FROM AUTHOR]

A massive number of Internet-of-things (IoT) devices communicate with each other in a wireless network for applications like smart cities, smart classrooms and smart agriculture. The real-time information exchange between these massive IoT nodes require connectivity and coverage. Advanced wireless techniques, cooperation among the communicating nodes and use of relays are fast emerging. But, increasing the communication reliability without adding to the energy or hardware overhead is the main challenge for these relay enabled massive IoT networks. Use of large number of relay nodes, antennas, radio-frequency (RF) transceiver chains in the cooperative communication enabled network increases the hardware complexity of the system. This paper addresses this challenge by proposing an energy efficient resource management model. The proposed resource optimization framework enables selection of optimal relay node and optimal number of antennas at the mobile node such that the system outage performance is improved. It is analysed that the resource optimization improves the outage probability by 12% at transmit power of 10dB at source node. The impact of increasing the number of node antennas on system ergodic capacity is also highlighted. The presented analysis finds applications in 6G enabled smart cities for seamless multimedia communication. As compared to existing systems with no resource optimization, the paper claims that incorporating resource optimization also results in huge energy savings at the mobile nodes. [ABSTRACT FROM AUTHOR]

With the increasing complexity and cost of industrial control systems and the rapid development of information technology, the tolerance of industrial control equipment to performance degradation, productivity decline, and hidden safety hazards is getting lower and lower. Immediate detection of failures of industrial control equipment is of great significance for the safety of industrial control systems and reducing maintenance costs. Faced with these challenges, the traditional fault diagnosis technology based on expert knowledge has been insufficient to meet the requirements of accuracy and real-time fault diagnosis of industrial control systems due to its high cost and low efficiency. Aiming at the problem that the fault diagnosis method in the current industrial control environment is not systematic, this paper proposes a Safety Fault diagnosis system for industrial intelligent control equipment based on DevOps concept and deep CNN. Based on the in-depth analysis of the principles of CNN, this paper improves the model's robustness from the perspective of data set enhancement, fault diagnosis performance, and noise immunity analysis. Finally, it is proved through experiments that the fault diagnosis model can effectively deal with the lack of fault samples by adopting the fault data set enhancement method based on periodic overlapping sampling. Our fault diagnosis system based on DevOps and CNN proposed in this paper has high scalability and can accurately predict fault input. [ABSTRACT FROM AUTHOR]

A web search, an online video, a connected Nest device, and hundreds of cloud services all give us a response in a fraction of a second. But what really happens when we click search or send a request. The request travels over the public internet and into fiber network. Millions of requests or packets of data travel through miles of cable over land and under sea, converging at one of the many data centers that operate all over the world. Data Center (DC) is the core site of data operation, storage and forwarding, which is also an important part of cloud platform. A large number of commercial switches and servers are usually deployed at the DC. The DC is a complex set of facilities. Data center networks (DCN) is a network applied in the DC, because the traffic in DC presents the typical characteristics of centralized exchange data and increased traffic, which puts forward further requirements for the DCN. DCN connects a large-scale server cluster and is a bridge for data transmission and storage. With the expansion of DC and the increasing number of service types, communication within data centers becomes more frequent. On the other hand, traffic between data centers has also increased dramatically. Considering the multi-layered transmission mode and traffic characteristics of DCN, this paper proposes a software defined networking (SDN) -based multi-layered traffic scheduling scheme for DCN, which is mainly focused on hop count, criticality and cost. Moreover, based on SDN architecture and Deep Q-Network of Reinforcement Learning (RL), the intelligent multi-layered traffic scheduling scheme is proposed to obtain the current optimal global routing strategy according to the real-time traffic demand in the network. The simulation results show that the proposed scheme outperforms benchmarks in terms of average throughput, normalized total throughput, link bandwidth utilization, average round-trip time and network traffic bandwidth loss rate. [ABSTRACT FROM AUTHOR]

The deep sea has abundant resources and is regarded as the "sixth continent" that humans can use. Although research on the deep sea has made some progress, its exploration is not deep enough. The acquisition and analysis of deep-sea images can provide important technical means for deep-sea exploration and the acquisition of information. However, there is currently no complete underwater image dataset. For this reason, this paper is the first deep-sea visual dataset of the South China Sea, contains over 100 TB videos and 1 million high quality images. This paper also applies the dataset to underwater image enhancement and image superresolution, and the experiment proves the effectiveness of the dataset. [ABSTRACT FROM AUTHOR]

The work presents a novel computationally efficient transmission policy for throughput maximization over point-to-point sensor links employing harvest-use-store protocol with finite storage capacity battery. In these settings, under finite averaging duration constraint, the stochastic dynamic programming (SDP) technique provides the optimal solution for throughput maximization, but the implementation complexity for SDP is prohibitively large. Thus, there is a need to explore new solutions that can provide near-optimal throughput with lower implementation complexity. The work in this paper presents a adaptive transmission policy based on uniform thresholding that achieves a near-optimal throughput obtainable by SDP. Quantitative comparison with optimal online policies shows that the proposed policy attains performance close to SDP with lower implementation complexity. [ABSTRACT FROM AUTHOR]

In recent years, electromagnetic spectrum has become an indispensable national strategic resource in the information age and an important strategic support for the development of national informatization. With the rapid proliferation of wireless data today, the demand for electromagnetic spectrum is also growing rapidly, and spectrum resources are limited, leading to the increasingly prominent problem of spectrum scarcity. In response to the traditional spectrum prediction methods for spectrum prediction with extended time and low accuracy, this paper analyzes the spectrum correlation of different channels that are in the same service, performs the similarity measure of frequency dimension data, and proves the correlation between the spectrum; and predicts the spectrum data with different time occupancy, and conducts deep mining of the spectrum target behavior from the time–frequency dimension. The experiments mainly use sequence to sequence (Seq2Seq) based Long Short-Term Memory (LSTM) to predict the data of each occupancy degree, and compare with the traditional LSTM network, Autoregressive Integrated Moving Average model (ARIMA), etc. The prediction accuracy of the method in this paper is higher. At the same time, the abnormal spectrum is monitored using the Mahalanobis distance algorithm, the detection accuracy reaches 100%. [ABSTRACT FROM AUTHOR]

Systems which can utilize the energy efficiently have been of much interest due to its promise to mitigate the energy crises. Internet of Things (IoT), i.e. the intercommunication of machines for an effective delivery of services with minimal human intervention, can form the basis of such systems. IoT based systems are gaining popularity due to the availability of high-speed mobile networks coupled with cost effective, accessible and fast embedded hardware. In this paper we propose an IoT based smart home management system using sensors, actuators, smartphone, web services and micro-controllers. The paper offers interoperability with exceptionally reliable connections. The system architecture takes care of the scenario where the devices are turned off when they are not in use. Being an entirely open source framework, a more deterministic control of security features can be attained by the user. Unlike existing frameworks, the proposed architecture makes the IoT system completely available via internet and open source systems. Finally, the implemented prototype demonstrates a flexible platform that can be extended to cater to changing needs. [ABSTRACT FROM AUTHOR]

In this paper, we focus on the dynamic collaborative charging scheduling problem with multiple Mobile Chargers (MCs) in the Wireless Rechargeable Sensor Networks (WRSNs) with obstacles. Firstly, we use the Fresnel Diffraction Model (FDM) to describe the influences of obstacles on the charging process. Secondly, we propose a new charging group division algorithm, which can select the sets of the sensor nodes that can be charged simultaneously and determine the selection ranges of the charging spots. Thirdly, we propose a charging spots selection algorithm based on the FDM, which can not only reduce the number of sensor failures, but also guarantee the high-level charging utility. Fourthly, we propose a dynamic zonal collaborative charging scheduling scheme. It divides the charging zones to achieve balanced distribution of the charging loads. When a zone is not schedulable, our scheme will redistribute its high energy-cost charging tasks to the zone with less load for dynamic adjustment. When some charging tasks can not be adjusted, our scheme will discard the ones with less contribution, minimizing the losses of the network. Finally, we conduct a large number of simulations to verify the performances of our work. The simulation results show that our scheme has obviously better performances compared with the other arts. [ABSTRACT FROM AUTHOR]

Spectrum sensing technology can effectively improves the utilization of spectrum resources by empowering unauthorized users to access the idle spectrum opportunely. This paper proposes a new spectrum sensing algorithm to determine whether a signal exists under impulsive noise by only using the sampled data. First, this method uses the Similarity Measure of samples to construct the test statistic. Theoretical analysis shows that it can suppress the influence of impulsive noise, realize accurate signal detection and improve the reliability of the system with fewer samples. Then, the probability distribution of test statistic is investigated through statistical theory analysis, under the both case of the absence and the presence of primary user signals, respectively, and the probabilities of detection and the false alarm are derived. After that, we give the detection threshold for a given false-alarm probability. Finally, experimental simulation confirms the effectiveness of the proposed algorithm and the correctness of theoretical analysis. [ABSTRACT FROM AUTHOR]

Accurately obtaining the length, quantity and distribution of fruit branches plays an important role in orchard irrigation management, disease control and improving fruits' yield and quality. Recently, edge computing has been proposed for digital orchard management as it can increase computing power for computationally intensive applications. However, due to the diversity of fruit tree morphological structures and the complexity of the planting environment, the traditional method of obtaining fruit tree phenotypes with centralized computing on cloud servers faces many challenges in terms of efficiency and accuracy. In this paper, we propose a hierarchical growing method (HG) suitable for deployment at the edge to achieve semantic segmentation and instance segmentation of fruit tree point clouds at the organ scale. Furthermore, extract fruit trees phenotypic trait at the organ scale based on the result of point clouds segmentation. Numerous experiment show that the proposed HG method can efficiently carry on instance segmentation of branches and phenotypic trait extraction by the joint analysis and processing of point cloud data. The MAE, RMSE and IOU of the primary branches reach 0.025 m, 0.113 and 0.720, respectively. [ABSTRACT FROM AUTHOR]

As communication capabilities of mobile devices continue to advance, ensuring reliability and security has become increasingly crucial. The aerial tracking system presented in this paper provides a useful solution for tracking and tracing objects in various scenarios. To ensure reliability and security, the system incorporates appropriate mechanisms, including Lightweight Cryptography, to prioritize confidentiality and integrity. The Android component of the system has two modes of operation: Tracker Mode, running on a smartphone mounted on a drone (RPA), and Client Mode, running on mobile devices on the ground. In Client Mode, users transmit their positioning and trajectory information via Bluetooth Low Energy beacon mode, which is then relayed to the server backend via the 4G/5G network once the RPA enters an area with coverage. The system provides a reliable and secure solution for situations where tracking and tracing are essential, such as the supervision and control of public areas with capacity control or tracking and localizing people in isolated environments. [ABSTRACT FROM AUTHOR]

With the rapid development of wireless technology and Mobile communication technology worldwide, Mobile Learning represents a new learning trend in the field of higher education, and has gradually become the development trend and research hotspot of independent learning and lifelong learning. Based on modern wireless network mobile communication terminal technology, this paper proposes a Granott model-driven mobile learning system. Firstly, the Granott model is studied and analyzed, and the ubiquitous computing with physical integration and spontaneous interoperation is used to control the Android mobile terminal, which greatly improves the interactivity of M-Learning. Then JSON is selected to optimize the data transmission format in Ajax, and j Query is used to parse JSON data. Ajax + JSON + j Query can shield the complexity of DOM parsing XML files, greatly shorten the data transmission time and improve the efficiency of Granott model. Finally, the Fast kernel density estimation (Fast KDE) algorithm is introduced to compress the data transmitted by Ajax + JSON + j Query, so as to obtain a reasonable number of training samples. Through experiments and relevant data analysis, the proposed mobile learning system based on modern wireless network mobile communication terminal technology, optimized by JSON and Fast KDE algorithm, driven by Granott model, can efficiently complete the learning task, and improve the ubiquity, interactivity, timeliness of mobile learning. [ABSTRACT FROM AUTHOR]

Edge computing provides a real-time guarantee for the industrial internet. Server deployment is the first step to building an edge computing system, and the deployment strategy has a huge impact on system delay and reliability. Industrial environments place higher demands on reliability than other common environments. However, existing research on edge server deployment assumes that the server will not fail and thus rarely considers edge server reliability while reducing delay. This paper focuses on edge server deployment approach for delay reduction and reliability enhancement in the industrial internet. Firstly, a basic edge server deployment model is established to optimize server load balancing and delay. On this basis, an edge server deployment model with enhanced reliability is established. This model improves system reliability by adding fault-tolerant servers when deploying edge servers. When some edge servers in the system fail, the fault-tolerant servers will intervene in time and start working to replace the failed edge servers. To solve the optimal deployment strategy, an Improved Grey Wolf-Genetic Algorithm-based deployment algorithm is proposed. The deployment algorithm improves the traditional genetic algorithm's performance to find the global optimal solution by improving the initialization and mutation part of the genetic algorithm. The deployment algorithm selects appropriate wireless access points (WAPs) to deploy fault-tolerant edge servers among a large number of WAPs. Simulation results show that the established fault-tolerant model can significantly improve system reliability while reducing system delay. The proposed algorithm performs better compared with existing algorithms in terms of convergence speed and finding the optimal deployment location. [ABSTRACT FROM AUTHOR]

Human exploration of the ocean has never stopped. A large number of sensors are placed in the ocean to establish ocean sensor networks to obtain more information about the marine environment, crustal dynamic changes and so on. With the development of science and technology, Autonomous Underwater Vehicles (AUV) appear and are widely used in marine sensor networks. Due to the complex and changeable ocean environment, the slow speed of traditional and the lack of reasonable path planning and other reasons, AUV waste a lot of time and energy, which cannot efficiently collect information. In this paper, the Unmanned Aerial Underwater Vehicle (UAUV) is introduced into the ocean sensor network. Establish a two-dimensional scene model, find the best water entry point for UAUV to complete the task in the shortest time and minimum power consumption by traversing the search algorithm, and compare the performance of UAUV cross domain mode and underwater mode to collect marine sensor data. Meanwhile, establishing three-dimensional ocean sensor scene model, and using DDQN algorithm to solve the path planning problem of UAUV. The results show that the cross-domain mode of UAUV in the two-dimensional scene model saves 74.7% times and 24.34% energy compared with the traditional underwater mode. In the three-dimensional scene model, the UAUV is trained to the optimal path by the DDQN algorithm, which saves 60.94% of the time and 20.26% of the energy compared to the traditional underwater mode. The results prove the feasibility, stability and efficiency of UAUV introduction into marine sensor network, the effectiveness of DDQN algorithm to solve UAUV path planning problems. [ABSTRACT FROM AUTHOR]

The application of mobile intelligent terminal in the teaching of physical education in colleges and universities opens up a new world for teachers' education and students' study. Based on modern mobile wireless network terminal technology, this paper presents a motion attitude recognition system based on quaternion algorithm. The wireless mobile system adopts HMCL electronic module, and is equipped with MEMS chip of digital communication, which greatly eliminates the accumulation error of gyroscope and improves the accuracy of azimuth data acquisition. The data of 7 triaxial ADXL345 accelerometers and triaxial L3G4200D gyroscopes were combined with Kalman filtering for data fusion. Using the updated angular velocity data and initial value, the quaternion is constantly updated to solve the joint Angle. The experiment of human body climbing stairs with load of 0 kg, 5 kg, 10 kg and 15 kg was carried out. The experimental results were compared with those captured by high-speed camera. The error of joint Angle and motion posture of the experimenter was controlled within 5%, which verified the correctness of the model. In physical education, teachers can use this terminal system to accurately grasp whether the students' movements are standard or not, so that the teaching effect can be effectively guaranteed. [ABSTRACT FROM AUTHOR]

The requests of broadband coverage area and the expected user demand is satisfied by the satellite industry by using multiple spot beams of high throughput satellites with fixed multi-beam pattern and footprint planning. The technology core of high-throughput satellite is multi-beam technology, and the means to efficiently reuse spectrum is a full-frequency reuse scheme. In order to study the channel capacity limit of multi-beam satellite systems, the Wiener-Gaussian access model of terrestrial cellular systems is analyzed in this paper. This paper analyzes the Wiener-Gaussian access model of terrestrial cellular systems, then considers the difference between the spatial characteristics and gain characteristics of the multi-beam satellite system compared with the terrestrial cellular system, and proposes a Wiener model suitable for the multi-beam satellite communication system. On this basis, the channel capacity limit of multi-beam satellites under different fading conditions is deduced when using optimal linear precoding and minimum mean square error precoding. It provides theoretical support for the in-depth study of the channel capacity mechanism and system performance of multi-beam satellites. [ABSTRACT FROM AUTHOR]

With the increasing number of terminal devices in the sensor network and the Internet of things, non-orthogonal multiple access (NOMA) will be widely used in the future to improve spectrum resource utilization. In this paper, we considered how to control massive devices in the downlink in of scenario of space-based Internet of Things (S-IoT). In the case of multiple base stations (BSs), user fairness is a difficult problem, which usually requires a traversal algorithm to achieve the optimal solution. However, the time complexity caused by this method is the product of the complexity of user grouping and power allocation, which is unbearable. We split the problem into two sub-problems changing complexity from product form to additive form, and solve them by using low time complexity algorithms respectively. Firstly, we use a threshold-based algorithm to implement user grouping, and then use a bisection iterative algorithm for power allocation. In the simulation, we compared design with several benchmarks and results show that the minimum user rate is significantly improved and closed to optimal value by using proposed algorithm in this paper. [ABSTRACT FROM AUTHOR]

The increased use of wearables in recent years has fostered a great technological development in this area, although without the appropriate supervision usability may go first than security. In addition to this, the fact that wearables have been requiring more and more personal data from the user makes them attractive devices for an attacker. In this paper we propose a set of tests for evaluating the security and privacy of wearables and we apply them to analyse the security and privacy of a set of commercial wearables that are targeted at minors, who represent a group with especially high requirements in this regard. We define the testing scenario, expose the tools to support the research, and specify the testing process to be followed. Based on the obtained results, although the considered low-end devices are broadly speaking less secure than high-end ones, most of them present security and privacy flaws, which illustrates the necessity of regulation that ensures the fulfilment of appropriate security and privacy requirements. [ABSTRACT FROM AUTHOR]

Classification algorithm is the crucial technique for machine vision system. The Transfer Component Analysis has been introduced for workpiece classification system. The dataset with five classes of workpieces is constructed for experiments, and the data augmentation strategies have been employed to prevent class imbalance problems. The Histogram of the Oriented Gradient features are extracted over workpiece images, and they are transformed by the Transfer Component Analysis and the Principal Component Analysis separately. The Maximum Mean Discrepancy distances have been employed to measure the distribution distances between the training set and the testing set. And the results indicate that the Transfer Component Analysis has dramatically reduced the distribution differences in a dimensionality reduction subspace, better than the Principal Component Analysis. The Error Correction Output Code is combined with Support Vector Machine and K-Nearest Neighbor respectively as the classifiers. The macro-averaged F 1 measure is adopted to evaluate the classifiers performance. Experiment results show that, the Transfer Component Analysis is particularly beneficial for improving the classification performance, and the Support Vector Machine is more favorable than the K-Nearest Neighbor for workpiece classification. The method of the Transfer Component Analysis combined with the Support Vector Machine possesses the best classification performance among these methods in this paper. [ABSTRACT FROM AUTHOR]

The accuracy of ultrasonic nondestructive examination is limited by the limitation of near field diffraction. With the development of nearfield optical, angular spectrum method is introduced into the acoustic field, which provides a significant direction for the ultrasonic diffraction limit resolution detection. The main research of this paper is the transmission of near field ultrasound in thin workpiece and the law of the interaction of tiny flaws. The paper establishes the relationship between the longitudinal wave signal and the structure of the workpiece and the types of flaws. A method is found that whether there are flaws can be determined near field area by analysing the acoustic field characteristics of workpiece surface. Finally, comparing the calculation results with the finite element simulation, they verify each other, the method turns out to be correct in this paper. The model can also be used to improve the ultrasonic noise reduction algorithm and the extraction of minimal defect feature. It has a greatly practical significance. [ABSTRACT FROM AUTHOR]

Wireless communications play an important role in ensuring ease of access to shared electronic health records (EHR) across health service providers which is essential and significant for prompt patients' care, especially in cases of emergency medical conditions. With the need to support anytime, anywhere access to, potentially bandwidth hungry, medical records, electronic healthcare applications will continue to benefit from advanced wireless network technologies such as 5G and beyond. With sharing, it is crucial to provide patients with security and privacy guarantees, and allow them to certain control of access to their data. Existing solutions mostly assume that patients are available to authorize requests to access their EHR, which is impractical as the patient may be unconscious. This paper proposes a secure and privacy protecting protocol whereby the patient can pre-delegate the authorization for the access of his/her EHR. Our patient(user)-centric proposal combines Self-Sovereign Identity (SSI) concepts and model with Secure Multi-party Computation (SMPC) and Threshold Cryptography (TC) to enable secure identity and authorization verification. A block cipher encryption sharing approach is adopted for the threshold SMPC which extends the AES-GCM symmetric encryption model into a full-fledged cryptographic platform. Two mechanisms are implemented for the block cipher encryption, namely XOR and Cascade, and experiments are conducted to compare them. We conclude that the XOR mechanism can scale for larger thresholds, while Cascade performed better for a lower threshold (≤ 3). This paper also performs a threat analysis of the protocol and approach, and validates its correctness and complexity. We conclude that the approach can achieve the security and privacy protection of the patient's personal EHR, as well as the autonomy of the patient to control the authorization for the access and sharing. [ABSTRACT FROM AUTHOR]

In cognitive radio network (CRN), effective spectrum management provides better quality of service. The spectrum is limited but the significance of the spectrum is increasing at each network generation. Due to the ineffective spectrum allocation policies, several researches have indicated that a vast segment of the licensed radio is not viably used. A CRN is an intelligent spectrum utilization innovation that provides better spectrum interface. Spectrum sensing detects unused spectrum in the manner that protects interferences to the authorized users. In principle, the secondary user (SU) receives the primary user (PU) signal and reports it to the fusion center for decision or spectrum allocation. The SU cooperates in the detection of the presence or absence of the PU. This type of spectrum sensing is called cooperative spectrum sensing. However, the significance of this type of spectrum sensing is blurred by the security problems. Malicious users can deliberately report misleading information regarding the presence of the PU. Hence, in this paper, a support vector machine learning algorithm is proposed to statistically learn the behavior of the malicious users and it classifies the legitimate SU and malicious users. A particle swarm optimization algorithm is also integrated to learn the smallest possible distinguishable malicious users' energy report deviation from the legitimate SUs. The probability of detection and energy of detection have been applied to evaluate the contribution of the proposed method. Finally, the simulation results have confirmed that better spectrum management can be derived from the proposed statistical approach. [ABSTRACT FROM AUTHOR]

The future communication network will be composed of ground-based, sea based, air-based and space-based networks to build a distributed air, space and sea integrated global intelligent network across regions, airspace and sea areas. High altitude platform stations (HAPS) communication system combines the advantages of satellite and land communication systems, and effectively avoids their disadvantages. Artificial intelligence technology enables the wireless communication network, establishes the mathematical model of the wireless network according to the historical situation of the wireless network then trains the mathematical model and continuously optimizes the model, so as to obtain the optimal model, and then adjusts the model parameters according to the changes of the network in practice. The multi antenna system is mounted on the high-altitude platform stations to form multi beam to provide services for users. The beams between different the users will interfere with each other, which will affect the beam performance of high-altitude platform stations. This paper introduces an anti-interference algorithm based on particle swarm optimization. First we construct the anti-interference mathematical model of multi antennas system of high-altitude platform station. Then we train this model through particle swarm optimization algorithm. Finally, the performance of the algorithm is verified by simulation. [ABSTRACT FROM AUTHOR]

The traditional routing method makes use of limited information on the network links to make routing decisions, which makes it difficult to adapt to the dynamic and complex network and adjust the router's forward strategy. To address these issues, this paper proposes an intelligent routing method based on the Software Defined Network (SDN), Dueling DQN (a Deep Reinforcement Learning algorithm) and network traffic state prediction. First, the global network awareness information is obtained with the SDN network measurement mechanism, which is converted into a traffic matrix consisting of multiple network link status information such as bandwidth and delay, etc. Then, the optimal forwarding route under the current network state is generated by predicting the network traffic matrix and the Dueling DQN. The experimental results show that: (1) compared with the traditional Dijkstra and OSPF routing methods, the proposed method significantly improves the network throughput and effectively reduces the network delay and packet loss rate; (2) comparing with the reinforcement learning algorithms DDPG and PPO, the proposed approach achieves a faster convergence state, which improves the efficiency of network routing. [ABSTRACT FROM AUTHOR]

Unmanned Aerial Vehicle (UAV) Internet of things have been widely used in military and civilian fields such as rescue, disaster relief, urban planning. Positioning service is the core technology for UAVs to perform various tasks. However, the UAV may be attacked by external conditions, resulting in its inability to obtain self-location information during mission. For the positioning problem of UAV signal interference, this paper proposes a cooperative positioning of UAV based on optimization algorithm. In order to solve the difficulty of UAV positioning, we propose the following solutions. Firstly, we construct different numbers of beacon nodes by using the flight information of UAVs in different cycles. Secondly, the unknown number of the positioning to be solved of the UAV is reduced to improve the accuracy and speed of the subsequent optimization algorithm. Thirdly, A multi-objective optimization model is established of the UAV motion parameters under inequality constraints. And we utilize a penalty function to convert the optimization model into a minimal value solution problem under no constraints. Finally, the positioning results of each UAV are obtained by the optimization algorithm. [ABSTRACT FROM AUTHOR]

The development of various communication technologies has made it possible to connect any intelligent device with each other and to the Internet. However, with the proliferation of such devices, the need for dynamic networks that require less efforts in managing and optimizing end users experience is mounting at a fast pace. Wireless Mesh Networks (WMNs) are a good choice not only to meeting users demands but also to reducing maintenance and upfront costs. Nevertheless, deploying a reliable highly connected WMN at low cost requires the utilization of the least possible mesh routers, yet fully interconnected and able to cover all mesh clients. To cope with these challenges, we have previously implemented a hybrid intelligent system, called WMN-PSODGA, which combines two intelligent algorithms: Particle Swarm Optimization and Distributed Genetic Algorithm. In this paper, we consider Boulevard and Stadium distributions of mesh clients and evaluate the performance of the WMN for different router replacement methods. By comparing the simulation results for each distribution and router replacement method, we conclude that the best scenario in terms of client coverage, router connectivity and load balancing is Stadium distribution with Rational Decrement of Vmax Method as a router replacement method. [ABSTRACT FROM AUTHOR]

The construction of smart city has become the frontier trend of city development. Smart education shows the inner beauty of smart city, and smart education is the connotation extension of educational informatization. At present, smart education has become an important symbol of education modernization worldwide, which is an important way to improve the quality and efficiency of education, cultivate innovative talents, and is the inevitable choice to realize the leap-forward development of education. Furthermore, preschool education is a critical period for the rapid development of children's nervous system. Education in this period plays a decisive role in children's development and is also a necessary condition for their development of intelligence and potential. However, traditional teaching cannot guarantee the fun of children's teaching activities. According to the characteristics of multi-sensory, immersive, and interactive virtual reality (VR) technology, VR is introduced into the live demonstration application of preschool education. Since VR video contains information in all directions of a scene, its data volume is much larger than that of traditional video, and different panoramic video projection layout schemes have a great impact on the quality of video. To solve this problem, a continuous layout method based on octahedral projection is proposed, which eliminates the internal discontinuous edges and has good boundary continuity. Experimental results show that the layout method proposed in this paper has good performance in both video quality and computing cost, which provides power for VR technology in the live demonstration of preschool education, and increases the immersion and comfort of children when watching VR videos. [ABSTRACT FROM AUTHOR]

The consequences of sustainable and greener mobility have been demonstrated previous year by the pandemic situation. One significant benefit was to reduce the level of noise, dust and air pollution from the traffic in many European countries due to reduced mobility most of the population. Positive phenomena was also recorded in the Slovak Republic. Today's urban mobility offers new, more sustainable ways of transport for residents, especially app-based and shared-ride services, which have become increasingly widespread and very popular. Undoubtedly offer a level of convenience unseen before in the urban mobility systems throughout the world. Although new forms of transport are developed in most Slovak cities, their operation is not very rational and therefore individual car transport still dominates at the expense of sustainable ways of transport. In our paper, we analyze the traffic situation in the city of Nitra, as the large number of trips in the course of the peak-hours often results in severe traffic congestion. Multimodality is one of the solutions to improve the current traffic situation, as it allows urban residents to choose from a range of alternative travel options. The main aim of this paper is to determinate the possibilities of multimodal urban mobility in the city of Nitra in addition to analyze how the potential change in the variability of choice of means of transport affects the urban mobility behaviour. In order to meet stated objectives, a marketing research was conducted. The research findings point to the fact that the current urban infrastructure and overall possibilities are limited, the consequence of which is that travel behaviour of citizens does not demonstrate the features of sustainable urban mobility. Our results point to major differences in attitudes of Nitra´s residents from different urban and sub-urban areas. [ABSTRACT FROM AUTHOR]

Industrial Internet of Things (IIoT) has been envisioned as a killer application of 5G and beyond. However, due to the shortness of computation ablility and batery capacity, it is challenging for IIoT devices to process latency-sensitive and resource-sensitive tasks. Moblie Edge Computing (MEC), as a promising paradigm for handling tasks with high quality of service (QoS) requirement and for energy-constrained IIoT devices, allows IIoT devices to offload their tasks to MEC servers, which can significantly reduce the task process delay and energy consumptions. However, the deployment of the MEC servers rely heavily on communication infrastructure, which greatly reduce the flexibility. Toward this end, in this paper, we consider multiple Unmanned Aerial Vehicles (UAV) eqqipped with transceivers as aerial MEC servers to provide IIoT devices computation offloading opportunities due to their high controbility. IIoT devices can choose to offload the tasks to UAVs through air-ground links, or to offload the tasks to the remote cloud center through ground cellular network, or to process the tasks locally. We formulate the multi-UAV-Enabled computation offloading problem as a mixed integer non-linear programming (MINLP) problem and prove its NP-hardness. To obtain the energy-efficient and low complexity solution, we propose an intelligent computation offloading algorithm called multi-agent deep Q-learning with stochastic prioritized replay (MDSPR). Numerical results show that the proposed MDSPR converges fast and outperforms the benchmark algorithms, including random method, deep Q-learning method and double deep Q-learning method in terms of energy efficiency and task successful rate. [ABSTRACT FROM AUTHOR]

Mobile crowdsensing is a new paradigm for intelligent mobile devices to collect and share various types of sensing data in the urban environment. The recent rapid development of unmanned aerial vehicle (UAV) technology facilitates the realization of crowdsensing because UAVs have high-efficiency mobility in the urban environment and have been used in various areas of aerial photography, agriculture, plant protection, express transportation, disaster relief, and so on. However, for UAVs, one of the key issues for the archival of efficient crowdsensing is task allocation, which must balance the task quality and cost. This paper first proposes a mathematical model for task allocation for UAVs in crowdsensing. Then, for the effectiveness of data sensing, three algorithms are proposed to allocate tasks for the purpose of minimizing the incentive cost while ensuring the quality of sensing data. The proposed algorithms include the minimum cost first (MCF) algorithm, which assigns a high priority to UAVs with the lowest cost, the maximum ratio first (MRF) algorithm, which assigns a high priority to UAVs with a high ratio of sensing quality and sensing cost, and a genetic algorithm-based one (GA-TA), which comprehensively considers the factors such as UAV sensing quality, sensing cost, and execution ability. Experimental results show that, compared with MCF and MRF, GA-TA achieves the lowest total sensing cost, average task cost, and total moving distance of UAVs, and the highest average contribution of UAVs. Considering all factors, GA-TA is the best task allocation algorithm for UAVs in crowdsensing on average. [ABSTRACT FROM AUTHOR]

To reconstruct the high resolution image makes sense from single image with low resolution. Most conventional methods assume that the blur kernel is known, however the blur kernel within single blurring image is always unknown, then it is necessary to generate the kernel dynamically during deblurring. The paper proposes single image high-fidelity blind deblurring method based on GAN. The degradation of super resolution networks is first used to synthesize high resolution images. A blur kernel discriminator is then trained to analyze the generated high-resolution images and errors that occur when the prediction generator provides incorrect blur kernel. Thus, the blur kernel provided by the generator is closer to the actual image. Finally, through the redefinition and optimization of loss function, the perception loss is replaced by the per-pixel loss to obtain better visual effects. Experiments show that the proposed method can achieve high fidelity deblurring results 1.2% higher than those of traditional methods. [ABSTRACT FROM AUTHOR]

In recent years, mobile edge computing (MEC), as a powerful computing paradigm, provides sufficient computing resources for Internet of Things (IoT). Generally, the deployment of MEC servers closer to mobile users has effectively reduced access delays and the cost of using cloud services. However, the multi-objective resource allocation for IoT applications to meet service requirements (i.e., the shortest completion time of IoT applications, the load balance and lower energy consumption of MEC servers, etc.) still faces severe challenges. To address this challenge, a multi-objective resource allocation method, named MRAM, is proposed in this paper for IoT. Technically, the pareto archived evolution strategy is leveraged to optimize the time cost of IoT applications, load balance and energy consumption of MEC servers. Furthermore, the multiple criteria decision making and the technique for order preference by similarity to ideal solution are utilized to obtain the optimal multi-objective resource allocation strategy. Ultimately, the comprehensive analysis of MRAM is introduced in detail. [ABSTRACT FROM AUTHOR]

Since business processes are important assets of enterprises, thousands of business processes are modeled. After modeling business process models, a problem arises here is how to improve the efficiency of these models? In this paper, we propose a novel approach to refactor business process models with process fragments substitution for efficiency improvement. First, we propose a process model smell for identifying inefficient process fragments in business process models based on a sequence relation matrix and a data dependency matrix. Second, we propose a refactoring technique to replace inefficient process fragments in business process models with efficient process fragments. After refactoring, concurrent execution of business tasks in efficient process fragments can be maximized, so the efficiency of business process models can be improved. Experiments show our approach can improve efficiency of business process models effectively. [ABSTRACT FROM AUTHOR]

With the rapid development of artificial intelligence, hand gesture detection has gradually become a research hotspot in human–computer interaction. However, the traditional hand gesture detection has low robustness and detection accuracy, and brings the problem of privacy protection. Therefore, this paper proposes a Faster Region-based Convolutional Neural Network (F-RCNN) hand gesture detection method based on Frequency Modulated Continuous Wave (FMCW) radar with 3-Dimensions deep convolutional Generative Adversarial Networks (3-DCGAN). In particular, the range Doppler and angle of the hand gestures are calculated by FMCW radar. Then, the semantic label maps of the Range-Time-Map, Doppler-Time-Map and Angle-Time-Map images are respectively sent to the 3-DCGAN to expand the datasets. After that, the original and the 3-DCGAN generated images are sent to F-RCNN for jointly training. The classifier function is designed, and a learning ranking based assessment called Rank based Quality Score (RQS) is applied to improve the detection performance. The experimental results show that the mean average precision reaches to 80.8%. Moreover, the RQS for hand gesture detection is as high as 96.3%, which is increased by 5.8% compared to the traditional F-RCNN. [ABSTRACT FROM AUTHOR]

The spatial network has numerous nodes and complex links, which makes it more suitable for the Multipath Transmission Control Protocol (MPTCP). As an extension of the traditional TCP protocol, this protocol can aggregate the bandwidth of multiple paths to improve transmission performance. However, the traditional network architecture has limited support for MPTCP, making it impossible to select a good transmission path for the subflow according to the current global network status, so it is easy to cause subflow collision. By separating the control plane and data plane, the Software Defined Network (SDN) architecture can obtain the global network status and better manage the network. The introduction of SDN can solve the problem that traditional networks cannot optimize subflow transmission based on the global network status. However, the existing SDN-based solutions mainly optimize the terrestrial network and take the available bandwidth of the network as the key reference factor, which is not suitable for the network environment with a large scale of time and space such as the spatial network. Besides, due to the high-speed movement of satellite nodes, frequent link switching will cause the selected path to fail and affect the subflow transmission on the path. For this reason, a dynamic subflow allocation strategy for multi-path transmission in SDN-based spatial networks is proposed in this paper, which uses the SDN controller to monitor and analyze the network status, and selects multiple optimal and disjoint transmission paths for the subflow based on the delay and bandwidth of the path to improve the link utilization and load balancing. Then, the strategy uses the predictable characteristics of the spatial network topology to predict the link to be disconnected, reselects the optimal path for the subflow, and solves the problem that the subflow cannot be continuously transmitted due to link switching. The experimental results show that the strategy in this paper is more suitable for the spatial network, because the selected path has lower delay and higher bandwidth. It solves the collision problem of subflows, and makes the subflow transmission have better stability in the highly dynamic spatial network. [ABSTRACT FROM AUTHOR]