The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
Network node positioning technology is one of the important supporting technologies in the practical application of wireless sensor. In order to overcome the measurement error of the least squares method for wireless sensor networks (WSNs) node affect their positioning accuracy, an improved positioning algorithm least squares(LS) is proposed. In order to obtain the optimal reference node, the algorithm...
Image registration is an important technology of image processing and has a broad application. Good adaptability, computing speed and registration accuracy are the basic requirements in image registration. In recent years, the image registration algorithm based on local invariant features is becoming a hot spot of research, such as the SIFT method is one of them. But the traditional SIFT algorithm...
By combining two fast training methods, i.e., the weights-direct-determination (WDD) method and Levenberg-Marquardt method, this paper proposes a novel training algorithm called weights and structure policy (WASP) for the three-layer feedforward neuronet, in addition to the algorithm of weights and structure determination (WASD). Note that the pruning-while-growing and second-pruning techniques are...
High dimensional and unbalanced datasets are the main problems which prevent from achieving ideally churn prediction performance. Features selection is necessary to be adopted to enhance the model performance. A new predicting framework is proposed in this paper which uses complementary fusion of the multilayer features. Several subsets and new features were acquired according to feature factorization...
The classification performance of Support Vector Machine (SVM) is heavily influenced by its kernel parameter g and penalty factor c. in this paper, Cross-validation (CV) based grid-search optimization, CV-based genetic algorithm (GA) and CV-based particle swarm optimization (PSO) are respectively used for parameters optimization in SVM for fault classification of inverters in traction converter. Simulation...
Contouring control can provide precision machine tool control an effective method, and many methods have been proposed to date. Direct drive of linear motor is the inevitable demand and trends for improving CNC processing speed and precision. XY table contouring systems involve competing control objective of maximizing accuracy while minimizing traversal time. To meet high-speed, high precision and...
Chillers operation energy efficiency is the main factors affecting the efficiency of air conditioning systems. A chillers operation energy efficiency model and its method for a real chiller plant were proposed in this paper, whose parameters were optimized by GA optimization algorithm. Moreover, as R_RMSE (Relative Root Mean Square Error) was adopted as the evaluation of the prediction accuracy, the...
Infrared measuring device is a device used for infrared radiation characteristic measurement. It is widely applied to each field of the military, industrial, medical, agriculture and forestry in our production life. The calibration of infrared measuring equipment directly affects the system error and the test precision of the instrument, so establish the feasible and effective calibration method,...
Hot strip rolling flatness and gauge complex system has the features of strong coupling, uncertainty and nonlinearity. To improve the control accuracy, a strip flatness and gauge decoupling control method is put forward based on QDRNN-PID. The simulation results compared to the traditional PID control show that the decoupling control strategy has better control effect, adaptive tracking ability and...
Aiming at the randomness of intelligent vehicle data collection and the huge difference between the data collected which may easily result in information conflict, missing of effective data and large decreasing of effective data, method of distribution chart is used to eliminate negligent errors on the basis of multi-sensor data collecting and data is processed by adaptive weighted information fusion...
A tracking guidance scheme based on nonlinear model predictive control is proposed for low-thrust transfer trajectory. According to the optimal nominal transfer trajectory, the NMPC is used to design the predictive model of perturbed orbit. Performance index of receding optimization is established, which can indicate the difference between the nominal trajectory and prediction trajectory. Taking the...
In the case of PWM rectifier unsteady virtual flux amplitude caused by grid voltage instability. We can't achieve constant flux amplitude saturation limit. In order to eliminate the errors caused by direct current drift and initial value in voltage model based flux estimation of direct power control system, a new virtual flux observer based on virtual flux linkage to be perpendicular to grid voltage,...
The inconsistent diagnostic information often occurs in fault diagnosis of complex equipments. In order to improve the diagnosis precision, an integrated fault diagnosis method is proposed based on variable precision rough set (VPRS) and Naive Bayesian network classifier (NBNC). Firstly, according to the relative discernibility of the original fault diagnosis decision table, the β in VPRS is self-determined...
The method of nondestructive testing for aircraft skin composite defects using infrared thermography is very effective. But, against the problem of how to rapidly and accurately identify for the defects of specific types needs to be further study. Based on the analysis of the existed classifier for skin damages, a complex group classifier based on lie group machine learning algorithm is introduced...
A new method to achieve most luminous efficacy of LED mixing color is developed in this paper, and then algorithm simulation, samples design and validation of the results have been carried out. Compared with the traditional manual LED proportion calculation method, new LED proportion calculation method is optimized by artificial fish swarm algorithm (AFSA). As for AFSA with slow rate of convergence...
This paper proposes a robust hand posture recognition system based on RGBD images. While much research has focused on human body posture recognition, this work investigates skeleton-free hand detection, tracking and posture recognition. This work consists of two different parts. In the first part, we utilize random forest to get pixel detection of hand and mean-shift to track hand based on RGBD images...
A novel multiple autocorrelation method for single trial EEG feature extraction was proposed. The time courses of ERD/ERS during motor imagery were investigated by calculating multiple autocorrelation before power spectrum analysis. Then the averaged power spectrums on specific frequency bands were sent to a K-nearest classifier to validate the separability between different classes. Compared with...
Optical navigation technology is widely used in precision guidance for autonomous landing and obstacle avoidance. According to the requirements of the computer vision landing location system on a planetary lander, this paper mainly studies the image feature matching algorithm in the process of autonomous navigation during landing on asteroids. A matching algorithm based on local feature regions was...
Distributed energy resources and energy-storage units are parallel connected through converters in a DC bus microgrid. Current sharing is a basic requirement for microgrid and many current sharing methods are proposed. Distinct from those methods like the average current method, centralized method and master-slave method, the droop control method does not need any interconnections between the converters...
Non-negative Matrix Factorization (NMF) algorithm and its variations have been successfully applied to many fields, but how to set the characteristic dimension value and the sparse factors value to improve recognition accuracy has been puzzling the researchers. Until now, it is regretful that the rigorous algorithm doesn't appear. The purpose of this paper is not to improve existing NMF algorithm...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.