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.
Physiological signals are often organized in the form of multiple dimensions (e.g., channel, time, task, and 3-D voxel), so it is better to preserve original organization structure when processing. Unlike vector-based methods that destroy data structure, canonical polyadic decomposition (CPD) aims to process physiological signals in the form of multiway array, which considers relationships between...
A method for electromagnetic radiation source identification is proposed. The spatial characteristic of a radiation source is taken as the unique parameter for support vector machines (SVMs) to identify. First, the location of radiation source is determined by the triangulation method, and then its spatial characteristic is collected by a band receiver array with simulation, which removes the limit...
In this paper, a novel nonlocal dictionary learning method is proposed for sparse-representation-based classification (SRC) to label high-dimensional hyperspectral imagery (HSI). In SRC, the conventional dictionary is constructed using all of the training pixels, which is inefficient due to the high-dimension low-sample-size classification problem. In this paper, we construct the dictionary by adding...
Feature selection and classification are important tasks in medical data mining. However, different misclassifications of medical cases could lead to different losses. This paper proposes a framework for medical data classification and relevant feature selection by the combination of the trace ratio criterion and a novel cost-sensitive linear discriminant analysis classifier approach. The proposed...
In this paper, based on the analysis of the principle of double cross positioning, the selected target placed on the positioning baseline's perpendicular bisector so as to cross-positioning and the positioning model under different geometric distribution conditions is established which is on the positioning baseline's perpendicular bisector, the target distance, lateral angle which are the key factors...
Fuzz used the concept of black-box testing, is critical to an auto vulnerability mining method, there is blindness in this method. This paper presents a semi-automation model of vulnerability mining based on local fuzz with data stream control and hidden debug technology, the practice shows us that this algorithm makes the fuzz much faster and correct.
Nowadays, a lot of computer-aided systems for Chinese handwriting education have been developed. Their general idea is to match the strokes of the learner's character with those of the template character, and then determine the handwriting errors according to the matching result. It is clear that the stroke matching accuracy is the key issue. Therefore, this paper presents an automatic matching algorithm,...
For estimation of single tree parameters using 1:6000 large-scale aerial photographs, tree species identification is an important starting point. This paper presents a new approach for identifying tree species, delineating individual trees and extracting single tree space coordinates in coniferous and deciduous forests of Liangshui National Nature Reserve of P. koraiensis, Northeast of China. To identify...
This paper proposes an effective method for extracting corner features on structured environment based on sensor fusion of monocular vision and laser range data during Simultaneous Localization and Mapping (SLAM). Fusing vision and laser data of the same corner feature, not only improving the accuracy of SLAM, but also obtaining more three-dimensional information, which extends a two-dimensional map...
With the significantly improved data availability in remote sensing technology, mid-resolution images have become the primary data source for crop sown area measurement in large scale. However, it is still difficult to solve the problems of spectrum heterogeneity in one field and spectra similarity between fields. This paper developed mixed field decomposition method and tested the method in an urban...
The problem about measurement of position and attitude of the existing pushing railway bridge construction engineering machinery needs to be solved. The paper designs two kinds of measurement devices adopting phototransistors array and CCD aimed at the demands of pushing railway bridge construction. Multiple serial port communication technique is used to connect devices with industrial PC. Effectiveness...
Decision tree algorithm is not only the important part of machine learning, but also the most widely used data mining tool. At present, there are many algorithms of generating decision tree, but when the database which we rely on exists noise, high quality knowledge is hard to obtain by ID3 algorithm. In this paper, we propose the data mining method based on second learning in case of ID3 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.