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.
This study proposed a new method of urban impervious surface extraction from very high resolution (VHR) imagery, by combining spatial and spectral unmixing and decision tree classification. Endmember classes were first defined, where two shadow endmembers were used. Spatial homogeneity and spectral purity were fused to extract endmembers, i.e., spatial and spectral endmember. A modified multiple endmember...
Big date technology plays an important role in intelligent safety supervision. Based on overall framework of safety supervision big date platform, this issue demonstrates the process from the source to the end-user and the safety supervision big data application architecture. The data integration, analysis, processing and display technologies were analyzed to meet the requirements of intelligent safety...
The analysis of students' behavior can provide an effective reference for campus construction, as well as the cultivation and management of students' life. In this work, based on the information collected from the digital campus card, we study the correlation between book borrowing behavior and academic achievements, as well as the consuming capability distribution and campus movement trajectory from...
The performances of light-weight and the anti-damage are a pair of conflicting optimization goals. Basing on the damage data of explosion simulation, it studies multi-objective optimization of cantilever box girder about lightweight and anti-damage. Firstly, the method of PCA is introduced to mine the damage data of simulation experiments. Secondly -- the regression function about the damage of cantilever...
In this paper, a method of Attribute Reduction Based on Discernibility Matrix and a proximal support vector machine (psvm) is integrated and used to implement a classification of digitized mammograms. The Attribute Reduction Algorithm is used to reduce useless and interfering attributes of medical images, and the proximal support vector machine that runs faster, and is easy to implement, is used to...
Digital steganography is a kind of data security technique. In this paper, a new information hiding scheme was proposed. In this scheme, we embed secret message into still digital images based on (7,4) Hamming Code and Wet Paper Codes. It embeds seven secret bits into a pixel-group of seven cover pixels at a time at first, if that is unsuccessful, it embeds the first three secret bits into that pixel-group...
In order to study the damage on weapon equipment by explosive shock wave, simulation experiments were carried out to research explosive impact damage on stiffened cantilever box girder. Data mining method of PCA was introduced to process the damage data in simulation experiments. Basing on simulation and data mining, it discussed multi-objective optimization of stiffened cantilever box girder about...
In order to improve searching results of Web pages and enhancing Web crawling operation, the Web page clustering based on searching keywords is proposed in this paper, which firstly employed matching degree between Web pages and searching keywords to decide the sequence of showing pages of searching results. Then clustering algorithm was chosen to group pages of searching results according to matching...
In order to research the damage on weapon equipment by explosive shock wave, simulation experiments were carried out to study explosive impact damage on stiffened cantilever box girder. By using principal component analysis (PCA), it presented a data mining method on equipment structure damage. The precision analysis and regression analysis show that the damage data mining method based on PCA was...
Continuous blood pressure (BP) measurement based on pulse wave velocity (PWV) requires acquiring two pulse waves from different locations of human body. Choosing suitable and effective pulse transducers is critical for measuring PWV accurately and stably. In this paper, ultrasonic transducer, strain transducer, bio-electric resistance transducer and infrared light transducer are chosen as the objects...
In order to support the DW appliances' function comprehensively and efficiently, we propose a general common information platform system (CIPS) framework, which can integrate the data from the complex, multiple dimension and heterogeneous sources. Utilizing the hierarchical tree theory, a general formal definition and knowledge description method is developed to define and descript the complex and...
In order to research the damage on weapon equipment by explosive shock wave, simulation experiments were carried out to study explosive impact damage on cantilever box girder. By using principal component analysis (PCA), it presented a data mining method on cantilever box girder damage. It showed that: the calculating result by using this method was agreeable with the result by using traditional method...
This paper divides the complex sample data into three types: complete sample data, incomplete sample data and mixed sample data. After a lot of practice, this paper puts forward the general data mining model system based on the complex sample data and explains the meanings of the three models. Then it takes the data mining model of complete sample data for example to introduce the model's application...
In this paper, an intelligent system based on the DSP processor TMS320F2812 is presented to detect the faults of armatures of printed circuit motors. The system samples the output waveforms of the target circuit in high-speed. By using the fast Fourier transform (FFT) and frequency spectrum analysis, the system estimates automatically whether a short circuit or a break exists in the circuits of armatures.
The tactile assessments on a set of men's suitings were conducted by an expert panel according to the standardized techniques and processes. Based on the obtained sensory data, a hybrid model integrating the use of fuzzy set theory and genetic algorithms was then developed to study the fuzzy relations between various sensory components and the total fabric hand. In this method, fuzzy comprehensive...
Modular product evaluation is one of key technologies in modular design. Three kinds of evaluation methods, which based on three modular design styles, were proposed in this paper. These methods integrated customer satisfaction index (CSI), product customization index (PCI) or modularity degree index (MDI). Then several modularization customized products can be evaluated. Some customer satisfaction...
In this paper, a new evolutionary method named genetic relation algorithm (GRA) has been proposed and applied to the portfolio selection problem. The number of brands in the stock market is generally very large, therefore, techniques for selecting the effective portfolio are likely to be of interest in the financial field. In order to pick up a fixed number of the most efficient portfolio, the proposed...
These models are designed to enable personalized recommendation to handle the semantic phenomenon. Based on ontology, the method of document feature extraction and user interest model were improved. Two personalized recommendation models were proposed for different scenes. Taking the Web pages about vehicle for example, results show that the model can do personalized recommendation effectively, and...
Present, there is more research on supervised clustering ensemble algorithm, but the research on unsupervised clustering ensemble is studied less. In order to partition data points under fully unsupervised conditions, the hierarchical clustering ensemble algorithm based on association rules (HCEAR) is proposed in this paper. The optimal number of clusters is determined by average degree of clustering...
The achievable transmission rate of the multicast services is in general limited by the worst case mobile users within the multicast service sectors. Yet, unlike relay-assisted unicast service, there is a unique challenge in applying relay to multicast service. To be more specific, the multicast service shall be able to provide a uniform treatment for the mobile users within and without the relay...
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.