By Topic

Natural Computation (ICNC), 2011 Seventh International Conference on

Date 26-28 July 2011

Go

Filter Results

Displaying Results 1 - 25 of 138
  • [Front and back cover]

    Page(s): c1 - c4
    Save to Project icon | Request Permissions | PDF file iconPDF (165 KB)  
    Freely Available from IEEE
  • [Title page]

    Page(s): i
    Save to Project icon | Request Permissions | PDF file iconPDF (108 KB)  
    Freely Available from IEEE
  • [Copyright notice]

    Page(s): ii
    Save to Project icon | Request Permissions | PDF file iconPDF (90 KB)  
    Freely Available from IEEE
  • Freely Available from IEEE
  • Keynote speakers

    Page(s): iv - xii
    Save to Project icon | Request Permissions | PDF file iconPDF (216 KB)  
    Freely Available from IEEE
  • Organizing Committee

    Page(s): xiii
    Save to Project icon | Request Permissions | PDF file iconPDF (91 KB)  
    Freely Available from IEEE
  • Technical Program Committee

    Page(s): xiv - xviii
    Save to Project icon | Request Permissions | PDF file iconPDF (95 KB)  
    Freely Available from IEEE
  • Invited session organizers

    Page(s): xix
    Save to Project icon | Request Permissions | PDF file iconPDF (60 KB)  
    Freely Available from IEEE
  • Reviewers

    Page(s): xx - xxii
    Save to Project icon | Request Permissions | PDF file iconPDF (85 KB)  
    Freely Available from IEEE
  • Table of contents - Volume 4

    Page(s): xxiii - xxxiv
    Save to Project icon | Request Permissions | PDF file iconPDF (193 KB)  
    Freely Available from IEEE
  • Fast detect shadow from single outdoor image

    Page(s): 1827 - 1831
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (776 KB) |  | HTML iconHTML  

    There have been important advances in shadow detection in the images and videos recently. However, most shadow detection methods designed for the image sequences are not suitable for the single still image. The state-of-art shadow detection for still image is facing problems of not effective in general application. This paper presents a fast shadow detection method for single out-door image. The method is divided into three phase - image partition phase, partition enhance phase and shadow detection phase. By utilizing common phenomena in the shadow aspect, shadow detection in the single outdoor image becomes more simpler and more effective based on our research, and it runs at least 4-5 times faster than the instinct image based shadow detection method according to our experiments. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • FPGA implementation of a CORDIC-based radix-4 FFT processor for real-time harmonic analyzer

    Page(s): 1832 - 1835
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (428 KB) |  | HTML iconHTML  

    In this paper, the design of a CORDIC algorithm based radix-4 FFT processor is presented which is primarily intended to be used in power harmonic signal processing. The processor is implemented in a Field Programmable Gate Array (FPGA) that is characteristics of high efficiency, low cost, convenient implementation and short development cycle, and its performance is found to be satisfactory. The choice of the CORDIC algorithm for realizing the basic butterfly operation for the FFT which eliminates the need for storing twiddle factors and angles saves a lot of hardware compared to its counterparts employing other techniques. A dual-port memory structure and the corresponding addressing scheme are used to realize the in-place data access. The address generation unit required for fetching data from and writing results into the dual-port memory in proper sequence, is also incorporated within the chip which houses the controller as well. The full design is implemented using ALTERA CycloneII EP2C8Q208C8 series FPGA requiring approximately 3162 configurable logic blocks. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Hyperspectral unmixing using non-negative matrix factorization with automatically estimating regularization parameters

    Page(s): 1836 - 1840
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (261 KB) |  | HTML iconHTML  

    Hyperspectral unmixing is a process by which pixel spectra in a scene are decomposed into constituent materials and their corresponding fractions. Nonnegative matrix factorization (NMF) is a method recently developed to deal with matrix factorization. This paper proposes a hyperspectral unmixing algorithm using auto-NMF based on the L-curve theory. It is an approach to automatically estimate regularization parameters, which are manually chosen subjectively and difficultly in the traditional regularized non-negative matrix factorization (RNMF). We experiment traditional algorithms and auto-NMF on the synthetic data, better results are obtained from auto-NMF, indicating it is an effective technique for hyperspectral unmixing. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Moving object detection with cast shadow suppression

    Page(s): 1841 - 1844
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (268 KB) |  | HTML iconHTML  

    This paper presents a moving object detection method with cast shadow suppression in the RGB color space. Firstly, the background model is constructed by the metrically trimmed mean and updated adaptively. Then, the information of brightness, texture, and chromaticity is fused to discriminate the shadow and the moving object. Our experimental results demonstrate the good performance of the proposed method. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Music retrieval method based on filter-bank feature and earth mover's distance

    Page(s): 1845 - 1849
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (290 KB) |  | HTML iconHTML  

    In this paper, we propose a novel music retrieval method using a filter bank feature and earth mover's distance (EMD). In the proposed method, we use MFCCs for acoustic features and EMD for a distance measurement. Evaluation experimental results show that the accuracy of the proposed method achieves 96.73%. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Recovering sinusoids from data using bayesian inference with RJMCMC

    Page(s): 1850 - 1854
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (296 KB) |  | HTML iconHTML  

    We consider a problem of detecting and estimating of noisy sinusoids within a Bayesian probabilistic inferential framework in which inferences about signal parameters are drawn from posterior probability density function (PDF). However, this requires evaluation of some complicated high-dimensional integrals. Therefore, an efficient computational algorithm is implemented to draw samples from the posterior PDF of parameters under various proposal distributions. This algorithm, coded in Mathematica, is used for synthetic data sets. Simulations results support its effectiveness. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Region-based semi-supervised clustering image segmentation

    Page(s): 1855 - 1858
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (541 KB) |  | HTML iconHTML  

    To make image segmentation accord with user's inclinations, semi-supervised clustering image segmentation is used. It applies manual guides and pays more attention to user's preferences. Watershed is adopted to segment image into series of small regions, which are basic units for segmentation. In the method, adjacent or nearby regions for labeled regions are assumed to belong to the same cluster. Labeled data and unlabeled data are gotten based on manual guides and assigned different weights during iterative processes. A penalty function is introduced when labeled data are incorrectly segmented. For a complex object to be segmented, its different parts are first segmented independently, and the outputs are merged finally. The experimental results show that region-based semi-supervised clustering image segmentation is fast and precise, and its classification results are more in line with user's requirements. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Spatio-temporal video object segmentation using moving detection and graph cut methods

    Page(s): 1859 - 1862
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (528 KB) |  | HTML iconHTML  

    Segmentation of video foreground objects from background has many important applications, such as human computer interaction, video compression, multimedia content editing and manipulation. From a single video sequence with a moving foreground object and stationary background, this paper propose a novel algorithm to extract video object using graph cut and moving detection methods. The key idea in our paper is to obtain the moving object region which can be set as the possibility foreground, and the other region set as background, then this prior can be used by means of graph cut, video segmentation is then transformed to static image segmentation which can be achieved by binary min-cut. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Study of flame simulation based on dynamic video texture

    Page(s): 1863 - 1866
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (267 KB) |  | HTML iconHTML  

    A method based on Video texture is introduced to solve the problem of real-time and reality of flame simulation. Video texture is a new media, which has qualities between those of a photography and a video. The key problem of video texture synthesis is how to find and display repeatable video segments. This method can enhance rendering quality significantly, and meet requirements of real-time. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Temporal-spatial change research on pure masson pine forest with decision-tree's help

    Page(s): 1867 - 1871
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (532 KB) |  | HTML iconHTML  

    Ecological deterioration caused by pure masson pine forest in red soil region in South China has severely endangered local ecosystem and sustainable development of social economy. To understand temporal-spatial distribution and succession rule of pure masson pine forest is an important basic study to control pure masson pine forest. Current research mainly relies on traditional interpretation by remote sensing image, which has lower accuracy in identification of specific tree species. This study, taking Changting County in Fujian Province as study area, in the view of soil erosion and on the base of man-land relationship, analyzes emergence driving force of pure masson pine forest from aspects of tree species, habitat condition, ecological environment and human activities; from the remote sensing images of Changting County in 1975, 1990, 1999 and 2006, it also analyzes distribution of pure masson pine forest in different periods based on relatively complete system of knowledge rules and by means of decision-tree algorithm; meanwhile, it distinguishes non-erosion area and vegetation restoration area in different periods. The result shows that since 1975 spatial succession of pure masson pine forest in Changting County has a downward tendency, which is most evident during 1975 and 1990, but slowed down after 1990.Comparison between the result of decision classification and data from monitoring actual sample shows that identification result from decision-tree is more accurate and dependable, which provides a theoretical base to control regional pure masson pine forest and soil and water loss. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The research for the correlation between ERD/ERS and CSP

    Page(s): 1872 - 1876
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (487 KB) |  | HTML iconHTML  

    The event-related (de)synchronization (ERD/ERS) phenomenon is used to build motor imagery Brain Computer Interface (BCI) system. Common Spatial Pattern (CSP) algorithm is mainly applied to extract feature in mu rhythm. However there is no evidence to prove the features are directly related to ERD/ERS phenomenon. In this paper we design the experiment to analyze the relationship between the feature extracted by CSP algorithm and the ERD/ERS phenomenon. The experiment contains two methods of Band Power and CSP for the comparison. The result shows that there is low correlation between the MI system based on CSP and the ERD/ERS. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Using SPOT 5 high spatial resolution image to detect vegetation patches at Gudong oil field

    Page(s): 1877 - 1880
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (720 KB) |  | HTML iconHTML  

    Numbers and areas and locations of vegetation community patch are the important parameters for vegetation function and structure researches. In this paper, vegetation community patches are extracted using SPOT 5 high spatial resolution fusion image based on mathematical morphology. Firstly, vegetation is extracted according to the scatter plot between B3 and B2. Then vegetation community patches are detected based on the criterion of circle and ellipse object. And the centers of the patches are located. Finally, two types of the spatial structure models of vegetation communities are outlined. The experiments at Gudong oil field show that the algorithms for extracting circle and ellipse object based on mathematical morphology are simple and effective for detecting vegetation community patch. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • 7Be aerosols in the Arctic atmosphere - modelling of air mass trajectories

    Page(s): 1881 - 1884
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (553 KB) |  | HTML iconHTML  

    The activity size distributions of the natural radionuclide tracer 7Be in different inhalable fractions (<;0.39 μm, 0.391-0.69 μm, 0.69-1.3 μm, 1.3-2.1 μm, 2.1-4.2 μm, 4.2-10.2 μm and >;10.2 μm) were determined in the boreal atmosphere in the Arctic Research Centre of the Finnish Meteorological Institute (FMI) at Sodankylä, Finland (67°22' N, 26°38' E, 180m asl). The activity median aerodynamic diameter (AMAD) ranged from 0.54 μm to 1.05 μm. More than 75% of the 7Be activity was found to be associated with particles smaller than 1.3 μm. An anticorrelation was observed between the AMAD values and 7Be activities. The observed correlation between the AMAD values and RH% can be due to the intense condensation process during high RH% conditions resulting in increased particle sizes. But this associated with possibly higher scavenging rates of aerosols does not necessarily alone explain the anticorrelation between the AMAD and the 7Be activities. The air mass origin associated with synoptic scale weather phenomena may contribute to that too. To study this an analysis of air mass back-trajectories was performed. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Notice of Retraction
    A 3PL enterprise customer satisfaction evaluation method based on soft sets.

    Page(s): 1885 - 1888
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (528 KB) |  | HTML iconHTML  

    Notice of Retraction

    After careful and considered review of the content of this paper by a duly constituted expert committee, this paper has been found to be in violation of IEEE's Publication Principles.

    We hereby retract the content of this paper. Reasonable effort should be made to remove all past references to this paper.

    The presenting author of this paper has the option to appeal this decision by contacting TPII@ieee.org.

    Currently, the logistics development very fast in China, but the third party logistics enterprise service record system is not perfect to bring the evaluation of the customer satisfaction a difficulty. Therefore reasonable evaluations the third party logistics enterprise customer satisfaction and promote logistics service level are the utmost urgency. In this paper, we describe the basic theories and theorems of soft sets, make use of the not enough perfect service record data and analyze the third party logistics enterprise customer satisfaction evaluation method based on soft sets. Finally, we show that the soft sets theory is a valid method to resolve the third party logistics enterprise customer satisfaction evaluation problem through the analysis of one case. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A coal mine production scheduling optimization system and its application

    Page(s): 1889 - 1892
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (342 KB) |  | HTML iconHTML  

    To raise the utilization rate of coal and gain more profit, a production scheduling optimization system was developed with Visual Basic .NET and MATLAB. The system can not only promote coal mine production but also enable coal mine to response to market demands and customer requirements quickly. Furthermore, the coal company can adjust production plan to realize maximum profits based on the optimized schedule provide by the system. Lastly, the system was applied successfully in a surface coal mine of China. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.