Learning of the user behavior structure based on the time granularity analysis model by Lin Guo, Xiaoying Liu

“…This method of data collection has high cost, low data coverage, and lagging survey results. The algorithm proposed in this article analyzes purchasing data from e-commerce platforms and extracts short- and long-term consumption matrices of consumers. …”
Get full text

Transmission scheduling scheme based on deep Q learning in wireless network by Jiang ZHU, Tingting WANG, Yonghui SONG, Yali LIU

“…To cope with the problem of data transmission in wireless networks,a deep Q learning based transmission scheduling scheme was proposed.The Markov decision process system model was formulated to describe the state transition of the system.The Q learning algorithm was adopted to learn and explore the system states transition information in the case of unknown system states transition probability to obtain the approximate optimal strategy of the schedule node.In addition,when the system state scale was big,the deep learning method was employed to map the relation between state and behavior to solve the problem of the large amount of computation and storage space in Q learning process.The simulation results show that the proposed scheme can approach the optimal strategy based on strategy iteration in terms of power consumption,throughput,packets loss rate.And the proposed scheme has a lower complexity,which can solve the problem of the curse of dimensionality.…”
Get full text

Energy-efficient load balancing in wireless sensor network: An application of multinomial regression analysis by Ruwaida M Zuhairy, Mohammed GH Al Zamil

“…The contribution of this research is to propose an energy-efficient load balancing strategy based on the proposed prediction model for the purpose of enhancing the lifetime of wireless infrastructure. Our proposed algorithm grows linearly in terms of time complexity. …”
Get full text

Identification of the boundary regime in the process of water-oil displacement from the reservoir by Gamzaev Khanlar

“…Based on the proposed computational algorithm, numerical experiments were carried out for the model oil reservoir.…”
Get full text

Development Path Planning of Sports and Wellness Town under the Background of Computer Virtual Reality Technology by Lichun Chen, Bingxu Lu

“…In addition, this article uses the single-network ADP algorithm to solve the event-triggered HJB equation and adopts a new weight update law. …”
Get full text

Multi-objective Optimization Design of RV Reducer Considering the Cycloid Gear Profile Modification by Wang Quan, Zeng Lilei, Qin Zhengzheng

“…In view of the fact that the influence of cycloid gear profile modification on contact force is not taken into account in the structural design of RV reducer，a multi-objective optimization design method for the structure of RV reducer considering cycloid gear profile modification is proposed.Combining the theory of tooth profile modification with the calculation of contact stress of cycloidal gear，considering the factors of volume，efficiency and contact stress，an optimization mathematical model with small volume，high efficiency and low contact stress of cycloidal gear as multi-objective function is established.The solution is carried out by using NSGA-II algorithm，and compared with single-objective optimization method.The results show that compared with the original design，the volume of RV reducer decreases by 21.24%，the efficiency increases by 2.03%，and the contact stress of cycloid wheel decreases by 20.26%.Meanwhile，the multi-objective optimization method has higher comprehensive performance than the single-objective optimization method.…”
Get full text

Planetary Gearbox Fault Diagnosis based on LMD Sample Entropy and ELM by Zhang Ning, Wei Xiuye, Xu Jinhong

“…In order to solve the difficult problem of early fault feature extraction of planetary gearbox and consider that the planetary gearbox vibration signal is coupling and nonlinear，and the signal has multiple transmission paths，a planetary gearbox fault diagnosis method based on Local Mean Decomposition（LMD） and Sample Entropy and Extreme Learning Machine（ELM） is proposed.Firstly，the vibration signal is adaptively decomposed into a plurality of PF components by LMD，and the first four PF components including the main fault information are selected in combination with the correlation coefficient and the variance contribution rate.Secondly，the Sample Entropy of the signal is calculated to form a feature vector.Finally，the feature vector is input into ELM for fault classification.Experiments are carried out on the planetary gearbox test bench，compared with the probabilistic neural network classification algorithm，and compared with the feature vector based on Singular Value Decomposition （SVD）.The results verify the effectiveness of the proposed method.…”
Get full text

Harmonic Classification with Enhancing Music Using Deep Learning Techniques by Wen Tang, Linlin Gu

“…Two aspects of harmony are considered, chord and global key, facing the issue of the extraction problem by the algorithm of machine learning. Contribution here is to recognize chords in the music by the feature extraction method (voiced models) that performd better than manually one. …”
Get full text

An Approach for Modeling, Simulation, and Optimization of Catalytic Production of Methyl Ethyl Ketone by Zahra Parhizi, Milad Nayebi, Edris Mohammadzadeh, Reza Torfi

“…Eventually, an evolutionary genetic algorithm was adopted to optimize the reactor to maximize MEK production. …”
Get full text

Network traffic classification method basing on CNN by Yong WANG, Huiyi ZHOU, Hao FENG, Miao YE, Wenlong KE

“…Since the feature selection process will directly affect the accuracy of the traffic classification based on the traditional machine learning method,a traffic classification algorithm based on convolution neural network was tailored.First,the min-max normalization method was utilized to process the traffic data and map them into gray images,which would be used as the input data of convolution neural network to realize the independent feature learning.Then,an improved structure of the classical convolution neural network was proposed,and the parameters of the feature map and the full connection layer were designed to select the optimal classification model to realize the traffic classification.The tailored method can improve the classification accuracy without the complex operation of the network traffic.A series of simulation test results with the public data sets and real data sets show that compared with the traditional classification methods,the tailored convolution neural network traffic classification method can improve the accuracy and reduce the time of classification.…”
Get full text

Channel estimation for hybrid intelligent reflecting surface structure assisted mmWave communications by Youhua FU, Dong CHEN

“…When adding intelligent reflecting surface (IRS) for assist communication in millimeter wave communication, the system becomes complicated and difficult to obtain channel state information (CSI).To solve these challenges, a hybrid intelligent reflecting surface structure was adopted, that is, the IRS was composed of a large number of passive elements and the limited radio frequency (RF) chains, where the limited RF chains were used to estimate the channel between the base station/terminal and the IRS.Based on the structure, a channel estimation scheme was proposed, which was based on the limited RF chains.First, an improved multiple signal classification algorithm was used to estimate the departure angle and arrival angle of the channel at the same time, and then a complex parallel deep neural network was proposed to estimate the path gain.Through simulation and comparison between the proposed scheme and other methods, the superiority of the proposed scheme is proved.…”
Get full text

Bayesian Non-Parametric Mixtures of GARCH(1,1) Models by John W. Lau, Ed Cripps

“…Inference is Bayesian, and a Markov chain Monte Carlo algorithm to explore the posterior distribution is described. …”
Get full text

Research on EEG signal classification of motor imagery based on AE and Transformer by Rui JIANG, Liuting SUN, Xiaoming WANG, Dapeng LI, Youyun XU

“…The motor imagery brain-computer interface has always been the focus of scholars.But traditional system cannot accurately extract significant signals and has low classification accuracy.To overcome such difficulty, a new Transformer model was proposed based on the auto-encoder (AE).The filter bank common spatial pattern (FBCSP) was used to extract the features of multiple frequency bands, and the AE was exploited to obtain the dimensionality-reduced feature matrix.Finally, it considered the influence of the global signal features by the position encoding of the Transformer model and considered the internal correlation of the feature matrix by using the multi-head self-attention mechanism.By comparison with the traditional K-nearest neighbors (KNN) system based on linear discriminant analysis (LDA), the experimental results validates that the classification effect of AE+Transformer model is better than that of LDA+KNN system.It shows that the improved algorithm is suitable for the binary classification of motor imagery.…”
Get full text

Research on the Classification of Policy Instruments Based on BERT Model by Jiani Zhao, Cheng Li

“…The research tries to apply the automatic classification algorithm based on BERT (Bidirectional Encoder Representation from Transformer) to the policy instruments to improve the efficiency and accuracy of policy instruments classification. …”
Get full text

A Self-Adaptive and Link-Aware Beaconless Forwarding Protocol for VANETs by Changle Li, Yun Chen, Xiaolei Han, Lina Zhu

“…Furthermore, it proposes a comprehensive algorithm to calculate the waiting time by taking the greedy strategy, link quality, and the traffic load into account. …”
Get full text

Design and Application of Electromechanical Control System Based on Computer Fault Tolerance Technology by Rui Wei

“…In order to improve the stability and control effect of the electromechanical control system, this paper designs the electromechanical control system combined with the computer fault-tolerant technology and proposes an electromechanical control signal processing algorithm. In order to improve the accuracy of the path loss calculation, according to Fresnel’s law, this paper deduces the expression of the reflection coefficient of electromechanical control signal with the distance between the transmitting antenna and the receiving antenna as the main variable and then compares the path loss with the ground and the ceiling as the reflecting surface. …”
Get full text

A load balanced and energy efficient underwater clustering protocol for UWSN by Xinbin LI, Mengling GAO, Lei YAN

“…Focused on the low energy efficiency and short lifetime of underwater wireless sensor network（UWSN）,a load balanced and energy efficient underwater clustering（LBEEUC）protocol for UWSN was proposed.For cluster head settings,due to the consideration of load balanced,the proportion of cluster heads based on experience-load was set.The area with high experience-load could obtain more cluster heads than other areas to process data forwarding.And then,for intra-cluster communication,some relay nodes were set to save energy of long range data transmission between cluster head and nodes.Relay nodes also could be used to eliminate redundant information by advance data fusion.Finally,for inter-cluster routing,Q-learning algorithm was used to implement optimal path planning based on the criterion of least energy consuming.The simulation results demonstrate that the LBEEUC protocol can efficiently improve the energy utilization,prolong the network lifetime and balance the energy consumption of the network.…”
Get full text

Noise robust chi-square generative adversarial network by Hongjun LI, Chaobo LI, Shibing ZHANG

“…Aiming at the obvious difference of image quality generated by generative adversarial network under different noises,a chi-square generative adversarial network (CSGAN) was proposed.Combing the advantages of quantification sensitivity and sparse invariance,the chi-square divergence was introduced to calculate the distance between the generated samples and the original samples,which could reduce the influence of different noises on the generated samples and the quality requirement of original samples.Meanwhile,the network architecture was built and the global optimization objective function was constructed to enhance the adversarial performance.Experimental results show that the quality of the images generated by the proposed algorithm has little difference,and the network is more robust to different noises than the state-of-the-art networks.The application of chi-square divergence not only improves the quality of generated images,but also increases the robustness of the network under different noises.…”
Get full text

ID-based ring signature on prime order group from asymmetric pairing by Hongxia HOU, Mingrui ZHANG, Yanqi ZHAO, Xiaoli DONG

“…For the problem that the security proof was difficult to be realized under the standard model in the existing ID-based ring signature schemes, an ID-based ring signature scheme proven secure in the standard model was proposed.Firstly, the formal definitions of security model and adversary model of ID-based ring signature were given.Then, a specific ID-based ring signature scheme was constructed on the prime order groups from asymmetric pairings.Finally, the security analysis and performance analysis were given.The results of security analysis show that the proven security of the proposed scheme is achieved under the standard model by using the dual system encryption technique.The results of performance analysis show that the operation efficiency of each algorithm in the proposed scheme is improved effectively, compared with existing ID-based ring signature schemes from dual system, it is shorter to take the time in generating and verifying signature.…”
Get full text

A Fixed-Time Hierarchical Formation Control Strategy for Multiquadrotors by Miaojie Huang, Qiang Lu

“…This paper deals with the problem of multiquadrotor collaborative control by developing and analyzing a new type of fixed-time formation control algorithm. The control strategy proposes a hierarchical control framework, which consists of two layers: a coordinating control layer and a tracking control layer. …”
Get full text