With the rapid development of the internet, applications of recommendation systems for online shops and entertainment platforms become more and more popular. In order to improve the effectiveness of recommendation, ex...
详细信息
With the rapid development of the internet, applications of recommendation systems for online shops and entertainment platforms become more and more popular. In order to improve the effectiveness of recommendation, external information has been incorporated into various algorithms, such as location and social relationship. However, most algorithms only focus on the introduction of external information without depth analysis of the intrinsic mechanism in the external information. This paper proposed a transfer model of social trusted relationship, and optimized the reliability of the transfer model using pruning algorithm based on original trust recommendation. A credible social relationship macro-transfer model based on iterations of new credible relationships is defined by the similarity of social relationships. With a certain interest topic as a source of information, a micro-transfer model achieves the theme of interest and credibility of the expansion using social information dissemination algorithm. To demonstrate the effectiveness of the macro and micro credible transfer models, we used the Mantra search tree pruning algorithm and the optimization algorithm of similar category replacing similar products. The experimental results show that the proposed method based on the macroscopic and microscopic transfer models of the trusted relationship enhances the success rate and stability of the recommended system.
According to the problem that the selection of traditional PID control parameters is too complicated in evaporator of Organic Rankine Cycle system(ORC),an evaporator PID controller based on BP neural netw ork optimiza...
详细信息
According to the problem that the selection of traditional PID control parameters is too complicated in evaporator of Organic Rankine Cycle system(ORC),an evaporator PID controller based on BP neural netw ork optimization is designed. Based on the control theory,the model of ORC evaporator is set up. The BP algorithm is used to control the Kp,Kiand Kdparameters of the evaporator PID controller,so that the evaporator temperature can reach the optimal state quickly and steadily. The M ATLAB softw are is used to simulate the traditional PID controller and the BP neural netw ork PID controller. The experimental results show that the Kp,Kiand Kdparameters of the BP neural netw ork PID controller are 0. 5677,0. 2970,and 0. 1353,***,the evaporator PID controller based on BP neural netw ork optimization not only satisfies the requirements of the system performance,but also has better control parameters than the traditional PID controller.
In this study, the problems of precise linearization and optimal control for the cell three-compartment transition model are investigated. According to the differential geometry theory of nonlinear system, three-compa...
详细信息
In this study, the problems of precise linearization and optimal control for the cell three-compartment transition model are investigated. According to the differential geometry theory of nonlinear system, three-compartment nonlinear affine model of intracellular and extracellular distribution of 1, 6-diphenyl-1, 3, 5-hexatriene (DPH) is established. A nonlinear state feedback expression is deduced by means of state feedback precise linearization method to realize the linearization of the nonlinear system. Furthermore, the state feedback coefficient is optimized by solving Riccati's equation. The obtained control law is simple and easy to implement. The numerical simulation results show that the feedback system constructed by the nonlinear control strategies has good stability characteristics, and the dynamic response characteristic is improved obviously.
A new honeycomb battery package structure is designed and optimized in this study. It's a honeycomb structure which uses grid to reinforce the strength. To obtain the highly accurate finite element (FE) model, the...
详细信息
The parallel manipulator has some advantages of high accuracy,high speed and high stiffness *** makes up for the shortcomings of serial *** the parallel mechanism becomes a potential motion platform with high speed an...
详细信息
ISBN:
(纸本)9781509001668
The parallel manipulator has some advantages of high accuracy,high speed and high stiffness *** makes up for the shortcomings of serial *** the parallel mechanism becomes a potential motion platform with high speed and high *** poles parallel robot improves these defects of more singularity,poor load capacity and low stiffness which exist in workspace of the classic plane five poles parallel *** and forward kinematic models are established based on the structure of the *** influence of foundation beds' location error,driving angle error and rod processing error on control accuracy is systematically *** theoretical foundation has been provided for realizing the optimal design of the robot and control in high accuracy.
By the experiment modal research for unit structure, the natural frequency and mass of US by means of experimental modal analysis is explored. Experimental modal analysis on US was applied to achieve optimal US simult...
详细信息
By the experiment modal research for unit structure, the natural frequency and mass of US by means of experimental modal analysis is explored. Experimental modal analysis on US was applied to achieve optimal US simultaneously to satisfy multiple conflicting performance requirements of mass and natural frequency of US. Then the structural parameters of US were optimized to increase natural frequencies and reduce mass. Experimental modal analysis is an efficient technique to accurately identify the dynamic behavior of a structure and provides modal parameters, such as natural frequencies and mode shapes.
With the development of information technology, the application of big data in financial aspects becomes more and more deepening. However, in the aspect of bank loans, the accuracy of traditional user loan risk predic...
详细信息
With the development of information technology, the application of big data in financial aspects becomes more and more deepening. However, in the aspect of bank loans, the accuracy of traditional user loan risk prediction models, such as KNN, Bayesian, are not benefit from the data *** paper proposes to use DNN algorithm to forecast the risk of user loan based on the difficulties of current overdue prediction and the excellent learning ability of DNN. This article uses user basic information, bank records, user browsing behavior, credit card billing records, and loan time information to evaluate whether users are delinquent. Firstly, this paper record bank records according to the transaction type, respectively, to generate income and spending data. Secondly, to sum the user browsing behavior also, and to record the average of credit card bill. In addition, in order to reduce the effect of eigenvalue size on the result, all characteristics are standardized. Finally, users who lack user information are discarded and the above fields are spliced. The spliced fields are the basic input for DNN. From the experimental results, DNN algorithm inc rease over 6% prediction than kNN, Bayes algorithm.
The purpose of this study was to investigate the features of muscle fatigue extracted from surface electromyography (sEMG) signals of lower limbs, and then to present an evaluation method of lower-limb rehabilitation ...
详细信息
The purpose of this study was to investigate the features of muscle fatigue extracted from surface electromyography (sEMG) signals of lower limbs, and then to present an evaluation method of lower-limb rehabilitation to provide physical basis for the training effect of rehabilitation. Four healthy young university students were invited to perform a pedaling exercise for 40 days. The sEMG signals of four lower-limb muscles are recorded and processed using a Butterworth filter and a Daubechies 10 wavelet. Then, the change of the ratios of the spectrums of Types I and II muscle fibers to the total number of the spectrum along the exercise are examined. The time of the first intersection of the ratios for Types I and II for each muscle is used as a performance index. The increase in the time at the beginning and the end of the training period indicates the improvement of motor function, and thus it verifies the effectiveness of the rehabilitation.
This article discuss a repetitive acceptance sampling plan based on exponentially weighted moving average (EWMA) statistic using a regression estimator under the assumption that quality parameters follow normal distri...
详细信息
暂无评论