Accepted Papers

  • Task scheduling Algorithm Based on Resources Pre-Sorting in Cloud Computing
    Ge Junwei, Zhang Yanchun and Fang Yiqiu, Chongqing University of Posts and Telecommunications, China.
    The method according to the task preferences to classify the resource, so that different tasks can be complete in different resource preferences pooling. It has narrowed the scope of resource selection. Simulation results show that the algorithm compared with other algorithms have improved in the task completion time and resource utilization aspects. With the development of cloud computing, resources in cloud system become more and more. In order to find the appropriate resources better and faster to complete the task as soon as possible, we present a method of pre-sorting to classify resources.
  • Human Gait Analysis and Recognition Using Support Vector Machines
    Deepjoy Das and Sarat Saharia, Tezpur university India
    Human gait reveals feelings, intentions and identity which is perceived by most human beings. To understand this perceptual ability, Swedish psychologist Gunnar Johansson (1973), devised a technique known as PL (Point Light) animation of biological motion. In his work, the activity of a human is portrayed by the relative motions of a small number of markers positioned on the head and the joints of the body. This paper explores the basic concept of PL animation along with machine vision and machine learning techniques to analyze and classify gait patterns. Basically, frames of each video are background subtracted, the silhouette noise found were salt noise and noise connected in large blobs which are detected and removed based on morphological operations and area of connected components respectively. Image is then segmented and body points such as hand ,knee, foot, neck, head, waist along with the speed, height ,width ,area of person are determined by an algorithm. We then fit sticks connecting pairs of points. The magnitude and direction of these stick along with other features forming a 24-dimensional feature vector for each frame of a video are classified using SVM Modelling using LIBSVM Toolkit. The maximum recognition accuracy found during testing by cross validation with parameters of LIBSVM was 93.5%.
  • A Simple Noninvasive Approach for Fetal Electrocardiogram Extraction Based on Wavelet Transform
    Abed Al Raoof K. Bsoul, Yarmouk University, Jordan.
    To assess the health of a fetus during pregnancy, the fetal electrocardiogram signal is monitored. The signal is obtained by indirect or direct methods. Although direct method is more accurate, the former is medically accepted because it has no impact on the fetus and the mother. However, the quality of the obtained signal is very low; hence determination of the fetal heartbeats' is hard and needs an expert. In this research, the maternal electrocardiogram signal as obtained non-invasive from the abdomen is used to extract the fetal heart signal using wavelet transform. The implementation of the method is simple and the results show that it is promising.
  • Image Adaptive Thresholding for Multiphase Wavy Flow
    Mustafa Al-Naser, Moustafa Elshafei and Abdelsalam Al-Sarkhi, King Fahd University of Petroleum and Minerals, Saudi Arabia.
    Multiphase flow measurement is a very challenging issue in process industry. One of the promising approaches for multiphase flow analysis is image processing. Image segmentation is very important step in multiphase flow analysis. Determination of appropriate threshold value is very critical step for correct identification of the liquid and gas phases. There are two main thresholding techniques: Global and Adaptive. Adaptive thresholding is more suitable for multiphase flow case due to itís adaptability to image conditions such non-uniform illumination and noise. In this work, six adaptive thresholding techniques are examined for the case of wavy flow regime. These algorithms are used to estimate the wave shape and mix region between liquid and gas. In general, the adaptive algorithms are able to compensate for non-uniform illumination and they are able to estimate wave shape and mix region correctly. The execution time for the adaptive techniques is higher than global thresholding technique, but with the availability of new powerful PCs, it will become a minor issue.
  • Fall Event Analysis by Discrete Cosine Transform on Smart Phone
    Yung-Gi Wu and Sheng-Lun Tsai, Chang Jung Christian University, Taiwan
    Fall detection is one of the major issues in health care filed. Falls can cause serious injury both in physiology and psychology, especially to the old people. A reliable fall detector can provide rapid emergency medical care for the fallen down people. Thus, a reliable and effectively fall detection system is necessary. Smart phone becomes one of the necessities in daily life. People use the smart phone to communicate and enjoy the entertainment. Most of the smart phones are equipped with G-sensor to detect the gravity in tri-axis. In this paper, we analyze the signal from the G-sensor of tri-axial accelerometer by Discrete Cosine Transform (DCT) to detect the occurrence of fall from the activities of daily living (ADL). ADL consist of walking, standing and sitting. Experimental results show that the result of analysis can help to detect the falls effectively.
  • Classification of Convective and Stratiform Cells in Meteorological Radar Images Using Svm Based on A Textural Analysis
    Abdenasser Djafri and Boualem Haddad, University of Science and Technology Houari Boumediene, Algeria
    This contribution deals with the discrimination between stratiform and convective cells in meteorological radar images. This study is based on a textural analysis of the latter and their classification using a Support Vector Machine (SVM). First, we applied different textural parameters such as energy, entropy, inertia and local homogeneity. Through this experience, we identified the different textural features of both the stratiform and convective cells. Then, we used an SVM to find the best discriminating parameter between the two types of clouds. The main goal of this work is to better apply the Palmer and Marshall Z-R relations specific to each type of precipitation.