For speech emotion recognition (SER), emotional feature set with high dimension may produce redundant features and influence the recognition rate. To solve this problem, feature selection of speaker-independent speech...
详细信息
For speech emotion recognition (SER), emotional feature set with high dimension may produce redundant features and influence the recognition rate. To solve this problem, feature selection of speaker-independent speech based on genetic algorithm (GA) is proposed, which can obtain optimal feature subset. And a four-level emotional classification method based on support vector machine (SVM) is proposed according to the confusion degree among different emotional categories. A framework of speaker-independent SER is presented and the classification experiments based on proposed methods by using Chinese speech database from institute of automation of Chinese academy of sciences (CASIA) are performed, where the speaker-independent features selected by the proposed feature selection method and Spearman correlation analysis are used for emotion recognition, respectively. The experimental results show that the proposal achieved 77.6% recognition rate on average, which is about 1.2% higher than other recognition methods. By proposal, it would be efficient to distinguish the emotional states of different speakers from speech.
Blackbody radiation source is used as a standard device for infrared thermometer, it plays increasingly important roles in the field of calibration. Through experiment discoveries that it is a typical nonlinear system...
详细信息
Blackbody radiation source is used as a standard device for infrared thermometer, it plays increasingly important roles in the field of calibration. Through experiment discoveries that it is a typical nonlinear system and has a large transport delay when the blackbody is rise temperature or cooling in order to reach set temperature points. Based on the temperature control of blackbody is a kind of typical multi-variable, strong coupling and time-varying nonlinear controlsystem. The paper proposes applying the theory of active disturbance rejection controller (ADRC) to suppress various disturbances and improve the dynamic performance of blackbody radiation source. First of all, describing the working principle of blackbody radiation source and building its mathematical model. Secondly, introducing the control method of ADRC, which is applied to the temperature controlsystem of blackbody radiation source. Finally, through MATLAB/SIMULINK platform to simulate and compare the temperature control performances of blackbody among ADRC, PID and Smith predictor(SP) control strategies. The simulation results show that proposed ADRC algorithm improves the abilities of anti-interference of system and it is without overshoot. In addition, the results also indicated that the control method of ADRC shortens plant stable time and has a strong prospect for practical applications.
On the basis of increasing the transmission distance of the 1553B bus, in order to maintain the simplicity and stability of the bus and improve its anti-jamming ability, the 1553B signal relay circuit based on FPGA is...
On the basis of increasing the transmission distance of the 1553B bus, in order to maintain the simplicity and stability of the bus and improve its anti-jamming ability, the 1553B signal relay circuit based on FPGA is designed in this paper. The signal transmission part is consists of the software and the hardware, and the chip of ZYNQ series is used in the FPGA. Firstly, the transmitted signal oscillation is transformed into a group of positive and negative differential signals, which are realized by transformer (pmdb25). Secondly, the signal is sent to the main control chip of ZYNQ series through signal acquisition chip and level conversion chip. Finally, the data is processed by software program and forwarded to the receiver. The specific experiments have been done on the 1553B signal transmission platform, which significantly show that the proposed scheme is reasonable and reliable.
Real Time Bidding (RTB), widely publicized as one of the most promising big-data-driven business models for online computational advertising, has the potential of effectively monetizing user clicks and impressions via...
详细信息
This paper is concerned with the Tobit Kalman filtering for a class of discrete-time linear systems. A set of Bernoulli random variables is introduced to describe the randomly occurring censored measurements, which ar...
详细信息
In order to compromise the conflicts between control accuracy and system efficiency of conventional electro-hydraulic servo systems,a novel pump-valve coordinated electro-hydraulic servo system was designed and a corr...
详细信息
In order to compromise the conflicts between control accuracy and system efficiency of conventional electro-hydraulic servo systems,a novel pump-valve coordinated electro-hydraulic servo system was designed and a corresponding control strategy was *** system was constituted of a pumpcontrolled part and a valve-controlled part,the pump controlled part is used to adjust the flow rate of oil source and the valve controlled part is used to complete the position tracking control of the hydraulic *** on the system characteristics,a load flow grey prediction method was adopted in the pump controlled part to reduce the system overflow losses,and an adaptive robust control method was adopted in the valve controlled part to eliminate the effect of system nonlinearity and parametric uncertainties due to variable hydraulic parameters and system loads on the control *** experimental results validated that the adopted control strategy increased the system efficiency obviously with guaranteed high control accuracy.
In order to meet the application requirements of autonomous vehicles, this paper proposes a simultaneous localization and mapping (SLAM) algorithm, which uses a VoxelGrid filter to down sample the point cloud data, ...
详细信息
In order to meet the application requirements of autonomous vehicles, this paper proposes a simultaneous localization and mapping (SLAM) algorithm, which uses a VoxelGrid filter to down sample the point cloud data, with the combination of iterative closest points (ICP) algorithm and Gaussian model for particles updating, the matching between the local map and the global map to quantify particles' importance weight. The crude estimation by using ICP algorithm can find the high probability area of autonomous vehicles' poses, which would decrease particle numbers, increase algorithm speed and restrain particles' impoverishment. The calculation of particles' importance weight based on matching of attribute between grid maps is simple and practicable. Experiments carried out with the autonomous vehicle platform validate the effectiveness of our approaches.
In order to solve kinematic redundancy problems of a hydraulic quadruped walking robot,which include leg dragging,sliding,impingement against the ground,an improved gait planning algorithm for this robot is proposed i...
详细信息
In order to solve kinematic redundancy problems of a hydraulic quadruped walking robot,which include leg dragging,sliding,impingement against the ground,an improved gait planning algorithm for this robot is proposed in this ***,the foot trajectory is designated as the improved composite cycloid foot ***,the landing angle of each leg of the robot is controlled to satisfy friction cone to improve the stability performance of the *** with the controllable landing angle of quadruped robot and a geometry method,the kinematic equation is derived in this ***,agait planning method of quadruped robot is proposed,a dynamic co-simulation is done with ADAMS and MATLAB,and practical experiments are *** validity of the proposed algorithm is confirmed through the co-simulation and *** results show that the robot can avoid sliding,reduce impingement,and trot stably in trot gait.
This paper focuses on the problem of L 2 -L ∞ dynamic output feedback controller (DOFC) design for nonlinear switched systems with nonlinear perturbations in the Takagi- Sugeno fuzzy framework. First, the average dw...
详细信息
This paper focuses on the problem of L 2 -L ∞ dynamic output feedback controller (DOFC) design for nonlinear switched systems with nonlinear perturbations in the Takagi- Sugeno fuzzy framework. First, the average dwell time approach is used to stabilize a nonlinear switched system exponentially under an arbitrary switching law. Then, based on the technique of piecewise Lyapunov functions, a fuzzy-rule-dependent DOFC is designed to ensure that the overall closed-loop system is exponentially stable with a weighted L 2 -L ∞ performance level (γ, α). The solvability condition for the desired DOFC is derived using a linearization technique. It is shown that the controller parameters can be obtained as solutions to a set of strict linear matrix inequalities that are numerically solvable with available standard software. Finally, two simulation examples illustrate effectiveness of the developed technique, including cognitive-radio systems.
The effluent total phosphorus(ETP) is an important parameter to evaluate the performance of wastewater treatment process(WWTP). In this study, a novel method, using a data-derived soft-sensor method, is proposed to ob...
详细信息
The effluent total phosphorus(ETP) is an important parameter to evaluate the performance of wastewater treatment process(WWTP). In this study, a novel method, using a data-derived soft-sensor method, is proposed to obtain the reliable values of ETP online. First, a partial least square(PLS) method is introduced to select the related secondary variables of ETP based on the experimental data. Second, a radial basis function neural network(RBFNN) is developed to identify the relationship between the related secondary variables and ETP. This RBFNN easily optimizes the model parameters to improve the generalization ability of the soft-sensor. Finally, a monitoring system, based on the above PLS and RBFNN, named PLS-RBFNN-based soft-sensor system, is developed and tested in a real WWTP. Experimental results show that the proposed monitoring system can obtain the values of ETP online and own better predicting performance than some existing methods.
暂无评论