A Multi-Robot Collaborative Exploration Method Based on Deep Reinforcement Learning and Knowledge Distillation by Rui Wang, Ming Lyu, Jie Zhang

“…To this end, we propose to view the robot team as an agent and obtain a policy network that can be centrally executed by training with an improved SAC deep reinforcement learning algorithm. In addition, we transform the obtained policy network into distributed networks that can be adapted to communication-constrained scenarios using knowledge distillation. …”
Get full text

Multi-camera video collaborative analysis method based on edge computing by Zhibo QI, Lei DU, Ru HUO, Fan YANG, Tao HUANG

“…In order to reduce the processing volume of multi-camera real-time video data in smart city scenarios, a video collaborative analysis method based on machine learning algorithms at the edge was proposed.Firstly, for the important objects detected by each camera, different key windows were designed to filter the region of interest (RoI) in the video, reduce the video data volume and extract its features.Then, based on the extracted data features, the same objects in the videos from different cameras were annotated, and a strategy for calculating the association degree value between cameras was designed for further reducing the video data volume.Finally, the GC-ReID algorithm based on graph convolutional network (GCN) and re-identification (ReID) was proposed, aiming at achieving the collaborative analysis of multi-camera videos.The experimental results show that proposed method can effectively reduce the system latency and improve the video compression rate while ensuring the high accuracy, compared with the existing video analysis methods.…”
Get full text

Cultivation of Innovative Ability of College Physical Education Students Based on the Internet of Things Multimedia Environment by Bin Cai

“…In this paper, a terminal collaborative indoor positioning algorithm based on RSSI fingerprint optimization was proposed to study the innovation ability of physical education students in colleges and universities. …”
Get full text

Low-power transmission method for uplink millimeter-wave massive MIMO-NOMA system based on GSIC by Hui WANG, Qixin TAI, Liu LIU, Hong WANG, Rongfang SONG

“…The combination of non-orthogonal multiple access (NOMA) and millimeter-wave (mmWave) massive multiple-input multiple-output (MIMO) can meet the requirements for huge throughput and massive connectivity in future wireless communication network.The total system power minimization for uplink mmWave massive MIMO-NOMA was studied, and a novel framework for a hybrid beamforming mmWave massive MIMO-NOMA uplink transmission system was proposed based on group-level successive interference cancellation (GSIC).Specifically, users were grouped according to channel gain, intergroup users being served by NOMA and intra group users being served by space division multiple access.By designing analog beamforming matrices for different groups and performing joint optimization for digital beamforming and power control, a parallel iterative algorithm was proposed to solve the optimization problem.Simulation results show that the proposed method outperforms the conventional mmWave massive MIMO-NOMA based on clustering and user-level SIC in terms of total power consumption.…”
Get full text

Using wavelet denoising and mathematical morphology in the segmentation technique applied to blood cells images by Macarena Boix, Begoña Cantó

“…Finally, theproposed algorithm made in MatLab environment is verified for a selected blood cells.…”
Get full text

Characterization and Evaluation of Rotation Accuracy of Hydrostatic Spindle under the Influence of Unbalance by Dongju Chen, You Zhao, Jingfang Liu

“…Finally, the least squares evaluation algorithm is used to evaluate the rotation error of the hydrostatic spindle, and a method for evaluating the rotation accuracy of the hydrostatic spindle with high calculation accuracy and calculation efficiency is proposed.…”
Get full text

Service clustering method based on description context feature words and improved GSDMM model by Qiang HU, Jiaji SHEN, Guanghui JING, Junwei DU

“…To address the problem that current service clustering methods usually faced low quality of service representation vectors, a service clustering method based on description context feature words and improved GSDMM model was proposed.Firstly, a feature word extraction method based on context weight was constructed.The words that fit well with the context of service description were extracted as the set of feature words for each service.Then, an improved GSDMM model with topic distribution probability correction factor was established to generate service representation vectors and achieve distribution probability correction for non-critical topic items.Finally, K-means++ algorithm was employed to cluster Web services based on these service representation vectors.Experiments were conducted on real Web services in Web site of Programmable Web.Experiment results show that the quality of service representation vectors generated by the proposed method is higher than of other topic models.Further, the performance of our clustering method is significantly better than other service clustering methods.…”
Get full text

Multiobjective-Optimized Design of a New UWB Antenna for UWB Applications by C. Moreno de Jong van Coevorden, M. Fernández Pantoja, Salvador G. García, A. Rubio Bretones, R. Gómez-Martín, K. Palmer

“…A multiobjective genetic algorithm has been applied to design a new printed, bow-tie antenna for ultrawideband applications, that is, ground penetrating radar, short range and high data rate communications, and so forth. …”
Get full text

Towards load adaptive routing based on link critical degree for delay-sensitive traffic in IP networks by Yang YANG, Jia-hai YANG, Hui WANG, Chen-xi LI, Yu-ding WANG

“…A load adaptive routing algorithm (LARA) was presented which could avoid the link to be congested to reduce the end-to-end delay. …”
Get full text

Dynamic switching based real-time routing in low-duty-cycle wireless sensor networks by Quan CHEN, Hong GAO

“…The dynamic switching based real-time(DSRT)routing protocol was proposed to handle the arbitrary end-to-end(E2E)real-time communication in the low-duty-cycle wireless sensor networks.Firstly,the concept of available speed was designed to compensate for the big sleep latency and facilitate discovering the routes with less latency based on two-hop neighbors’ information(at lease about 20% routing path with less latency was discovered by DRST in the experiments).Moreover,it was noticed that the congestion extent in the low-duty-cycle network was determined not only by the number of packets in the network output queue,but also the destination of the packets.However,the traditional method with one-hop neighbors’ information cannot differentiate this kind of congestion.Therefore,combined with the dynamic switching mechanism,the DSRT proposed a congestion avoiding algorithm by classifying the packets in the queue.Through comprehensive experiments,the efficiency of routing discovering and congestion avoiding of the DSRT protocol is demonstrated,and the E2E delay is decreased by at least 200% when the traffic was high.…”
Get full text

DYNAMIC CHARACTERISTICS OF A COLLISION SYSTEM WITH DRY FRICTION AND NONLINEAR CONSTRAINTS (MT) by MA Shuo, ZHU XiFeng, WANG JianFeng

“…Through the fourth-order variable step Runge-Kutta numerical algorithm, the dynamics of the mechanical vibration system generated by the low-frequency excitation of the p/1 periodic motion are analyzed. …”
Get full text

Scalable Fixed Point QRD Core Using Dynamic Partial Reconfiguration by Gayathri R. Prabhu, Bibin Johnson, J. Sheeba Rani

“…The square root and inverse square root operations in the Givens rotation algorithm are handled using a modified look-up table (LUT) based Newton-Raphson method, thereby reducing the area by 71% and latency by 50% while operating at a frequency 49% higher than the existing boundary cell architectures. …”
Get full text

Geometric Information and Rational Parametrization of Nonsingular Cubic Blending Surfaces by Minghao Guo, Tieru Wu, Shugong Zhang

“…Especially for the specific forms of these surfaces, we conclude that they must be 𝐹3, 𝐹4, or 𝐹5 surfaces, and a criterion is given for deciding their surface types. Besides, using the algorithm proposed by Berry and Patterson in 2001, we obtain the uniform rational parametric representation of these specific forms. …”
Get full text

Application of BO-BiGRU based post equalizer in high-speed underwater visible light communication system by Haoyu ZHANG, Li YAO, Chaoxu CHEN, Jianyang SHI, Chao SHEN, Nan CHI

“…Signals are susceptible to nonlinear effects in the process of underwater visible light communication (UVLC) channel transmission.In order to improve the communication performance of the system, it is very important to recover the received signals.A bidirectional gated recurrent unit model based on Bayesian optimization algorithm (BO-BiGRU) was proposed as post equalizer in UVLC system, which could automatically find the optimal hyperparameters.BO-BiGRU model was applied to the 1.2 m underwater experimental platform.64 quadrature amplitude modulation (QAM)-carrierless amplitude-and-phase modulation (CAPM) was adopted, and 3.10 Gbit/s rate of data transfer was achieved under the condition that the bit error ratio (BER) of the system was less than 3.8×10^-37% forward error correction (FEC), which is 128 Mbit/s higher than the traditional post equalization method.…”
Get full text

A Comparative Study on TIBA Imputation Methods in FCMdd-Based Linear Clustering with Relational Data by Takeshi Yamamoto, Katsuhiro Honda, Akira Notsu, Hidetomo Ichihashi

“…Relational fuzzy clustering has been developed for extracting intrinsic cluster structures of relational data and was extended to a linear fuzzy clustering model based on Fuzzy c-Medoids (FCMdd) concept, in which Fuzzy c-Means-(FCM-) like iterative algorithm was performed by defining linear cluster prototypes using two representative medoids for each line prototype. …”
Get full text

Caching strategy based on transmission delay for D2D cooperative edge caching system by Yan CAI, Fan WU, Hongbo ZHU

“…To meet the requirements of 5G system with low delay and high reliability, for a single-caching D2D cooperative edge caching system, an optimization of the caching strategy based on transmission delay was proposed.The dynamic distributions of requesting users and idle users were modeled as the independent homogeneous poisson point process (HPPP) utilizing the stochastic geometry theory.Comprehensively considering the content popularity, user location information, device transmission power and interference, the relationship between the average transmission delay of user and the cache probability distribution was derived.Taking the average transmission delay as the objective function, the optimization problem was established, and a low complexity iterative algorithm was proposed to obtain the cache strategy with sub-optimal average transmission delay.Simulation results demonstrate that the proposed optimization cache strategy is superior to several common cache strategies in terms of transmission delay.…”
Get full text

Human Body Model for Channel Characterization Based on Ray-Tracing by Lei Xiong, Haiyang Miao, Zhiyi Yao

“…In this paper, a realistic human body is modeled with the idea of greedy algorithm. Based on the RT simulation and measurement results of path loss (PL), we derive the approximate shapes of the torso, head, arms, and legs, and propose a reference human body model whose credibility and accuracy have been verified at 2.4 GHz and 60 GHz. …”
Get full text

Classification and Visual Design Analysis of Network Expression Based on Big Data Multimodal Intelligence Technology by Zou Ping, Yueyan Liu

“…Finally, it studied the fusion algorithm between multimodal data and visual design, as well as the classification of network expression and the application result analysis of visual design in big data multimodal intelligence technology.…”
Get full text

Detection and Analysis of Tooth Profile Deviation of Cycloidal Gear based on Projection Method by Mo Jingyu, Luo Shanming, Mao Lingxia, Fan Jianming

“…Based on the optical image measurement system and the Sobel edge detection algorithm,the complete tooth profile image and the actual tooth profile edge point coordinate of the cycloid gear are obtained. …”
Get full text

Game-theoretical analysis of mobile contributors in mobile crowd sourcing network with word of mouth mode by Feng ZENG, Runhua WANG, Jia PENG, Zhigang CHEN

“…The crowdsourcer who calls for sensing service can recruit enough mobile contributors quickly with the word of mouth mode,improving the quality of sensing tasks.The behavior of mobile contributors in mobile crowdsourcing with the WoM was investigated.It was supposed that each mobile contributor was rational,seeking for the highest utility.The behavior of mobile contributors with a two-level Stackelberg game was formulated.In the first-level game,a mobile contributor who directly worked for the crowdsourcer acted as the leader,while contributors invited by first-level contributors were followers called the second-level contributors.In the second-level game,the second-level contributors were the leaders and contributors invited by them were followers.The Nash equilibrium for each Stackelberg game was proved was existed and unique,and designed an algorithm to reach the equilibrium.Backward induction approach to compute the best response of each game was adopted,and the simulation results show the correctness of theoretical analysis for the interaction among contributors in crowdsoucing with WoM.…”
Get full text