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.
Datasets used in financial distress forecast are unbalanced. The traditional method gets lower predict accuracy especially in small samples of unbalanced datasets. The datasets are balanced with SMOTE method and then classified with the classical decision tree algorithm C4.5. The results show that the prediction model based on C4.5 algorithm gets the better performance.
In bioinformatics fields, Predicting protein subcellular location is an important task, because protein has to be located in its proper position in a cell to perform its biological functions. Therefore, predicting protein location is an important and challenging task in current molecular and cellular biology. In this paper, a computational method based AdaBoost.M1 algorithm and pseudo amino acids...
In this paper, a data fusion method was presented to combine multi Computational Fluid Dynamics models together in a target to constitute a scheme which could give an accurate and expeditious prediction of CFD simulation and reduce the total computational cost in a global optimization using Genetic Algorithm. Numerical models were defined as lower and higher fidelity according to the accuracy and...
The study of educational evaluation is by now mostly limited within the realm of the science of education itself, and is frequently found to depend on qualitative analysis. Nevertheless, the study of science is apt to combine several subjects and focus on the accuracy and comparability of the analysis. In this project, a quantitative study of educational evaluation is conducted in the framework of...
Policy of national student loans accelerates the reform of higher education in China and the process of market mechanism of talents training in a very great degree, and provides the important guarantee for the poor college students. However, at present, high default rate makes commercial bank which provides student loans bear the risk of bad debt, and affects the policy of national student loan to...
Mutual information is a criterion widely used in statistical language modeling word associations and feature selection. Principle component analysis (PCA) is a statistical technique for unsupervised dimension reduction. K-means clustering is commonly used data clustering for unsupervised learning tasks. In this paper, we first select features from native feature space by mutual information to reduce...
An automatic speed detection device of coal gas parsing speed based on microcontroller is designed in this paper. The STC12C5A60S2 MCU is the core of the system and the multi-scale segmentation of gas detection gas sensors system is designed in this paper to achieve the purpose of the coal gas parsing speed automatic detection. While a kind of large-capacity SD card data storage unit is designed to...
Image annotation is an indispensable step in the process of CBIR (content-based image retrieval). It comprehensively considered both features of the image visual and text messages, which can improve the accuracy of the content-based image retrieval and make image search system more accurate when getting target image. Based on the study about the mainstream technology of the current image mark methods,...
Traditional classification algorithms used in remote sensing images have many problems, such as the low operation speed, low accuracy and difficult convergence. Support Vector Machine (SVM) is a new machine learning method of statistical learning theory based on small samples of machine learning rules. This paper deals with the remote sensing image classification by the support vector machine, using...
The data mining technology is more and more widely used. How to construct a Bayesian belief network has been discussed in many different ways. As one of the classical algorithms, the branch and bound technique based on the minimum description length principle has been proposed by Joe Suzuki in 1998. But one of the most important premises of the B&B Technique is that an attributes' dependence ordering...
A stereo vision-based obstacle awareness and avoidance algorithm for indoor UAVs is described in this paper. While in most papers UAVs perceive the environment by vision-based obstacle discrimination, in our method a scene depth map is directly used, which makes our algorithm more adaptive in complex environment with numerous obstacles. For the purpose of lower time cost and less match mistakes, edge...
As one of the key technologies in Ad hoc networks, clock synchronization is the prerequisite of important network functions. Main consideration in clock synchronization are the choice of global clock and the accuracy, in which the existing clock synchronization methods still suffer lack. In this paper, the network delay is measured in networking process, and the network nodes complete synchronization...
In order to improve the initial alignment accuracy and convergence rate of the SINS system, proposed the improved UKF algorithm (AUKF) based on the Unscented Kalman Filter (UKF). Noise statistical characteristics are mostly unknown in real systems, when it was effected by the initial value errors and dynamic model errors, AUKF algorithm can real-time adjust the covariance of the state vector and observation...
In this paper a hybrid particle swarm optimization algorithm based on tendency cognition is presented. It combines tendency cognition, ensemble learning, and subpopulation strategies together. The first one increases the convergent speed and ensemble learning can achieve a more accurate result by combining particles. The last one increases the diversity. And this algorithm is compared with standard...
According to the method based on linear sinusoid tracer of adaptive theory for active power filter, there was contradiction between detecting accuracy and dynamic response. And the error in the algorithm was affected by the high order-harmonics, so this system couldn't detect harmonic current accurately. Based on the analysis above, a method based on improved sinusoid tracer of adaptive theory was...
Commodity price is always a matter related to national welfare and people's livelihood. In 2010, the country's central government put ‘Price Control’ as an important matter among national priorities and did enormous efforts for it. As a center area of Central Plain Economic Zone, He Nan Province has more reasons to keep commodity price in check. Based itself on the grey fuzzy theory the paper tries...
A method of measuring the PT secondary voltage drop based on GPS is introduced, Because it get the reference time through GPS, two instrument in different place can collect data at the same time. Take no account of harmonic and the magnetic disturbance which affect the voltage acquisition, This article analyzed the distinction error caused by ADC accuracy and the data numbers which are sampled in...
In order to eliminate the shortcomings in apple color grading, such as the slow speed, the large error, a novel fast intelligent grading method is presented, which is based on the improved particle swarm optimization (PSO) algorithm and Support Vector Machine. The main process is to acquire the colority of apple surface by the computer vision technology and extract its features which used as the samples...
A new method of indoor and outdoor seamless positioning is proposed that only using ray tracing to solve the problem of that each positioning technology can only support one specific environment and with various precision at the present time, which implement the indoor and outdoor seamless positioning quickly, reliable, accurate. The experiment shows that this method is correctness and has the advantage...
Traditional feature selection for classification can only treat with decision tables. The paper proposes a feature selection technique based on equivalent relation, which works well for both decision tables and information systems. The approach can compute the significance attribute from a database. The measure also takes into account the attribute support degree in decision tables. The experiment...
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.