|
|
|
题名
|
作者
|
年代
|
出处
|
被引量
|
| 1 | Motion trajectory prediction based on a CNN-LSTM sequential model显示文摘Accurate monitoring the surrounding environment is an important research direction in the field of unmanned systems such as bio-robotics,and has attracted much research attention in recent years.The trajectories of surrounding vehicles should be predicted accurately in space and time to realize active defense and running safety of an unmanned system.However,there is uncertainty and uncontrollability in the process of trajectory prediction of surrounding obstacles.In this study,we propose a trajectory prediction method based on a sequential model,that fuses two neural networks of a convolutional neural network(CNN)and a long short-term memory network(LSTM).First,a box plot is used to detect and eliminate abnormal values of vehicle trajectories,and valid trajectory data are obtained.Second,the trajectories of surrounding vehicles are predicted by merging the characteristics of CNN space expansion and LSTM time expansion;the hyper-parameters of the model are optimized according to a grid search algorithm,which satisfies the double-precision prediction requirement in space and time.Finally,data from next generation simulation(NGSIM)and Creteil roundabout in France are taken as test cases;the correctness and rationality of the method are verified by prediction error indicators.Experimental results demonstrate that the proposed CNNLSTM method is more accurate and features a shorter time cost,which meets the prediction requirements and provides an effective method for the safe operation of unmanned systems. | Guo XIE Anqi SHANGGUAN Rong FEI Wenjiang JI Weigang MA Xinhong HEI | 2020 | Science China(Information Sciences)2020，63，11： | 24 |
| 2 | Bayesian mechanism for rational secret sharing scheme显示文摘We consider the cooperation of rational parties in secret sharing. We present a new methodology for rational secret sharing both in two-party and multi-party settings based on Bayesian game. Our approach can resolve the impossible solutions to a rational secret sharing model. First, we analyze the 2-out-of-2 rational secret sharing using Bayesian game, which makes us able to consider different classes of the protocol player(for'good' and 'bad' players) and model attributes such as any other parties' preferences and beliefs that may affect the outcome of the game. Thus, the new model makes us able to reason rational secret sharing from the perspective of Bayesian rationality, a notion that may be in some scenarios more appropriate than that defined as per pure rational. According to these analyses, we propose a Bayesian rational protocol of 2-out-of-2 secret sharing. Also, our techniques can be extended to the case of t-out-of-n Bayesian rational secret sharing easily.Our protocol is adopted only by the parties in their decision-making according to beliefs and Bayes rule, without requiring simultaneous channels and can be run over asynchronous networks. | TIAN YouLiang PENG ChangGen LIN DongDai MA JianFeng JIANG Qi JI WenJiang | 2015 | Science China(Information Sciences)2015，58，5： | 9 |
| 3 | One-Time Rational Secret Sharing Scheme Based on Bayesian Game显示文摘The rational secret sharing cannot be realized in the case of being played only once,and some punishments in the one-time rational secret sharing schemes turn out to be empty threats.In this paper,after modeling 2-out-of-2 rational secret sharing based on Bayesian game and considering different classes of protocol parties,we propose a 2-out-of-2 secret sharing scheme to solve cooperative problem of a rational secret sharing scheme being played only once.Moreover,we prove that the strategy is a perfect Bayesian equilibrium,adopted only by the parties in their decision-making according to their belief system (denoted by the probability distribution) and Bayes rule,without requiring simultaneous channels. | TIAN Youliang MA Jianfeng PENG Changgen CHEN Xi JI Wenjiang | 2011 | Wuhan University Journal of Natural Sciences2011，16，5： | 8 |
| 4 | Microstructure and mechanical properties of sand-cast Mg-6Gd-3Y-0.5Zr alloy subject to thermal cycling treatment显示文摘This work was undertaken to investigate the microstructural evolution, mechanical properties and fracture behavior of sand-cast Mg-6 Gd-3 Y-0.5 Zr(GW63) alloy subject to thermal cycling treatment. In order to simulate the thermal cycling under extreme service conditions(space or moon environments), the sand-cast and T6 treated GW63 alloys were subjected to thermal cycling treatment which consists of deep cryogenic-elevated temperature cycling treatment(DCET) and deep cryogenic cycling treatment(DCT). Results indicate that there are significant gains in yield strength(YS) and ultimate tensile strength(UTS) of the sand-cast GW63 alloy after DCET, whereas the T6 state alloy undergoes a different variation in mechanical properties. However, no appreciable influence is revealed on the mechanical properties of the tested GW63 alloys after DCT. Meanwhile, the DCT and DCET have no obvious effects on the fracture morphology. The DCT enhances the precipitation kinetics via providing favorable nucleation sites for the precipitation of second phases. The elevated temperature process of DCET plays a crucial role in improving the aging-hardening responses and releasing the stress concentration brought by DCT to a great extent, leading to overcome the obstacle of essential phase transformation. The changes in mechanical properties are primarily attributed to the phase transformation of the studied alloys during DCET. | Beiping Zhou Wencai Liu Guohua Wu Liang Zhang Xiaolong Zhang Hao Ji Wenjiang Ding | 2020 | Journal of Materials Science & Technology2020，36，8： | 4 |
| 5 | Tree-Based Proactive Routing Protocol for Wireless Mesh Network显示文摘Wireless Mesh Network (WMN) is seen as an effective Internet access solution for dynamic wireless applications. For the low mobility of mesh routers in WMN, the backbone topography can be effectively maintained by proactive routing protocol. Pre-proposals like Tree Based Routing (TBR) protocol and Root Driven Routing (RDR) protocol are so centralized that they make the gateway become a bottleneck which severely restricts the network performance. We proposed an Optimized Tree-based Routing (OTR) protocol that logically separated the proactive tree into pieces. Route is partly computed by the branches instead of root. We also discussed the operation of multiple Internet gateways which is a main issue in WMN. The new proposal lightens the load in root, reduces the overhead and improves the throughput. Numerical analysis and simulation results confirm that the performance of WMN is improved and OTR is more suitable for large scale WMN. | Ji Wenjiang Ma Jianfeng Ma Zhuo Ran Youliang | 2012 | China Communications2012，9，1： | 2 |
| 6 | High-cycle fatigue behavior of Mg-8Li-3Al-2Zn-0.5Y alloy under different states显示文摘In this study,the tensile and high-cycle fatigue properties of as-cast,solid solution treated and as-extruded Mg-8Li-3Al-2Zn-0.5Y alloy are investigated.The results show that the yield strength and ultimate tensile strength of as-cast alloy is 198.1 MPa and 222.5 MPa,which are improved to 274.7 MPa and 321.7 MPa,282.4 MPa and 319.3 MPa after solid solution and extrusion treatment,respectively.The high-cycle fatigue strength(at 10^(7)cycles,R=-1)of as-cast studied alloy is 65 MPa,which is improved to 90 MPa and 105 MPa after solid solution and extrusion treatment,respectively.The improvement of fatigue property of the solid solution treated alloy is mainly due to the lattice distortion caused by solid solution hindering the crack propagation.However,the improvement of fatigue property of the as-extruded alloy is mainly due to that the refined grains,stacked dislocations and dispersed secondary particles impede the crack propagation. | Xiang Peng Xinli Liang Wencai Liu Guohua Wu Hao Ji Xin Tong Liang Zhang Wenjiang Ding | 2021 | Journal of Magnesium and Alloys2021，9，5： | 1 |
| 7 | Towards energy efficient cloud:an optimized ant colony model for virtual machine placement显示文摘A virtual machine placement optimization model based on optimized ant colony algorithm is proposed.The model is able to determine the physical machines suitable for hosting migrated virtual machines.Thus,it solves the problem of redundant power consumption resulting from idle resource waste of physical machines.First,based on the utilization parameters of the virtual machine,idle resources and energy consumption models are proposed.The models are dedicated to quantifying the features of virtual resource utilization and energy consumption of physical machines.Next,a multi-objective optimization strategy is derived for virtual machine placement in cloud environments.Finally,an optimal virtual machines placement scheme is determined based on feature metrics,multi-objective optimization,and the ant colony algorithm.Experimental results indicate that compared with the traditional genetic algorithms-based MGGA model,the convergence rate is increased by 16%,and the optimized highest average energy consumption is reduced by 18%.The model exhibits advantages in terms of algorithm efficiency and efficacy. | ZHANG Liumei WANG Yichuan ZHU Lei JI Wenjiang | 2016 | Journal of Communications and Information Networks2016，1，4： | 1 |
| 8 | Game strategies for distributed denial of service defense in the Cloud of Things显示文摘Integration of the IoT(Internet of Things)with Cloud Computing,termed as the CoT(Cloud of Things)can help achieve the goals of the envisioned IoT and future Internet.In a typical CoT infrastructure,the data collected from wireless sensor networks and IoTs is transmitted through a SG(Smart Gateway)to the cloud.The bandwidth between an IoT access point and SG becomes a bottleneck for information transmission between the IoT and the cloud.We propose a novel game theory model to describe the CoT attacker,who expects to use minimum set and energy consumption of IoT attack devices to occupy as many bandwidth resources as possible in a given time period;and the defender,who expects to minimize false alarms.By analyzing this model,we have found that the game theory model is a non-cooperative and repeated incomplete information game,and Nash equilibrium is existent,perfected by the subgame.The best strategy for each stage of the attack is to adjust the attack link number dynamically based on the comparison results of value E and turning point E_(0)for each time period.At the same time,the defender adjusts the threshold valueβdynamically,based on the comparison results of the Load value and expected value ofαfor each time period.The simulation result shows that our strategy can significantly mitigate the harm of a distributed denial of service attack. | WANG Yichuan ZHANG Yefei HEI Xinhong JI Wenjiang MA Weigang | 2016 | Journal of Communications and Information Networks2016，1，4： | 1 |
| 9 | CL-TAP: An Efficient Certificateless Based Trusted Access Protocol for WLAN显示文摘Based on the certificateless public key cryptography and the trusted computing technologies, a certificateless based trusted access protocol for WLAN(Wireless local area networks) is proposed. Such protocol realizes the mutual authentication and unicast session key agreement between STA and AP within 3 protocol rounds. In particular, the platform authentication and integrity verification are achieved during the authentication procedure. The security properties of the new protocol are examined using the Extended Canetti-Krawczyk security model. The analytic comparisons show that the new protocol is very efficient in both computing and communications. | MA Zhuo LI Fenghua MA Jianfeng JI Wenjiang | 2014 | Chinese Journal of Electronics2014，23，1： | 1 |
| 10 | A Risk Prediction Model Based on Crash History Data for Railway Trams显示文摘Risk prediction is an important task to ensuring the driving safety of railway trams.Although data-driven intelligent methods are proved to be effective for driving risk prediction,accuracy is still a top concern for the challenges of data quality which mainly represent as the unbalanced datasets.This study focuses on applying feature extraction and data augmentation methods to achieve effective risk prediction for railway trams,and proposes an approach based on a self-adaptive K-means clustering algorithm and the least squares deep convolution generative adversarial network(LS-DCGAN).The data preprocessing methods are proposed,which include the K-means algorithm to cluster the locations of trams and the extreme gradient boosting recursive feature elimination based feature selection algorithm to retain the key features.The LS-DCGAN model is designed for sparse sample expansion,aiming to address the sample category distribution imbalance problem.The experiments implemented with the public and real datasets show that the proposed approach can reach a high accuracy of 90.69%,which can greatly enhances the tram driving safety. | JI Wenjiang YANG Jiangcheng WANG Yichuan ZHU Lei QIU Yuan HEI Xinhong | 2023 | Chinese Journal of Electronics2023，32，5： | 0 |
您所在的机构暂未开通此部分的功能，请联系管理员