Day 2 :
Mississippi State University
Time : 09:05-09:45
Nicolas H. Younan is currently the Department Head and James Worth Bagley Chair of Electrical and Computer Engineering at Mississippi State University. He received the B.S. and M.S. degrees from Mississippi State University, in 1982 and 1984, respectively, and the Ph.D. degree from Ohio University in 1988. Dr. Younan’s research interests include signal processing and pattern recognition. He has been involved in the development of advanced signal processing and pattern recognition algorithms for data mining, data fusion, feature extraction and classification, and automatic target recognition/identification. He has published over 250 papers in refereed journals and conference proceedings, and book chapters. He served as the General Chair and Editor for the 4th IASTED International Conference on Signal and Image Processing, Co-Editor for the 3rd International Workshop on the Analysis of Multi-Temporal Remote Sensing Images, Guest Editor - Pattern Recognition Letters and JSTARS, and Co-Chair - Workshop on Pattern Recognition for Remote sensing (2008-2010)..
Satellite precipitation estimation at high spatial and temporal resolutions is beneficial for research and applications in the areas of weather, flood forecasting, hydrology, and agriculture. In this presentation, we incorporate advanced image processing and pattern recognition tools into the Precipitation Estimation from Remotely Sensed Information using Artificial Neural Networks Cloud Classification System (PERSIANN-CCS) methodology to enhance satellite precipitation and rainfall estimation. The enhanced algorithm incorporates five main steps to derive precipitation estimates: 1) segmenting the satellite infrared cloud images into patches, 2) extracting features from the segmented cloud patches, 3) feature selection or dimensionality reduction, 4) categorizing the cloud patches into separate groups, and 5) obtaining a relationship between the brightness temperature of cloud patches and the rain- rate (T-R) for every cluster. In addition to the features utilized for cloud patch classification, wavelet and lightning features are also extracted. Both feature selection and dimensionality reduction techniques are used to reduce the dimensionality as well as diminish the effects of the redundant and irrelevant features. A variety of feature selection techniques, such as Feature Similarity Selection and a Filter-Based Feature Selection using Genetic Algorithm are examined and the Entropy Index (EI) fitness function is used to evaluate the feature subsets. Furthermore, Independent Component Analysis was examined and compared to other linear and nonlinear unsupervised dimensionality reduction techniques to reduce the dimensionality and increase the estimation performance. The results show that the enhanced algorithm incorporating the above techniques improves precipitation estimation.
Technical University of Cluj-Napoca
Time : 09:45-10:25
Dorian Gorgan is Professor in Computer Science Department of the Technical University of Cluj-Napoca and PhD supervisor in Computers and Information Technology, and coordinator of the Computer Graphics and Interactive System Laboratory. His fields of interest involve parallel and distributed processing over HPC infrastructures such as Grid, Cloud, Multicore, and cluster, development of platforms and applications for spatial data processing and visualization, interdisciplinary research in the domains of Earth Sciences and Earth Observations. He has been involved as scientific coordinator and WP leader in national and international research projects such as BIGEARTH, PECSA, enviroGRIDS, IASON, SEE-GRID-SCI, GiSHEO, mEducator, iTRACE, MedioGrid, COMPLEXHPC, and KEYSTONE. He has been member of scientific and reviewing committees of many ISI journals and international conferences, and gave more than 350 papers and presentations in journals and prestigious conferences in the domains of Computer Science and Earth Observation.
Huge data are being generated by our everyday actions and the plethora of machines and sensors which surround us. This is especially true for the fields of study which regularly deal with Earth Science and Earth Observation data. The last decade has seen a dramatic increase in the data volumes available to the general public, and especially to creative people, in order to produce unexpected valuable results through flexible and adaptive approaches.
The high performance computation systems are able to satisfy the requirements for data transformation, classification, and highlighting of the significant data. Even so, the capacity of these systems for data analysis is quite limited. Nevertheless, the human brain has much more capacity for data analysis, synthesis and understanding. The human brain uses the greatest capacity of the visual channel to receive information. Therefore, combining the great computing capacity of the computer and, the visual analysis and reasoning of the human brain, could be an interesting and promising approach for data processing, mining and understanding.
The presentation highlights the solutions and issues of the visual analysis on multidimensional massive data. The experiments consider the n-dimensional value space of data and techniques for interactive navigation and visualization. The user may control the visualization and navigation in order to identify and detail the critical regions, points and tendencies within the value space. The examples cover use cases in the domains of Earth Science, Earth Observations and medicine.
Chinese University of Hong Kong
Time : 10:45-11:25
Bo Huang is a Professor in the Department of Geography and Resource Management, The Chinese University of Hong Kong, where he is also the Associate Director of Institute of Space and Earth Information Science and the Director of MSc Program in GeoInformation Science. He received Changjiang Scholar Chair Professorship, the highest academic award issued to an individual in higher education by the Ministry of Education of PR China. Dr. Huang’s research interest focuses on geographical information science and he has published extensively in this field, including over 100 refereed international journal articles. He currently serves as the Asia-Pacific Editor of International Journal of Geographical Information Science (Taylor & Francis). In recent years he has been exploring along the line of unified remote sensing image fusion, convinced that this new paradigm will revolutionize the way how remote sensing data are integrated, analyzed and utilized in the future.
The recent decades have witnessed the launch of a large number of orbiting satellite sensors with different spatial, temporal, spectral, and angular (STSA) characteristics, resulting in dramatic improvements in the ability to acquire images of the Earth surface, and a boom in remote sensing (RS) applications in environmental, ecological, and disaster monitoring. However, current RS technology cannot meet the requirement of monitoring dense and dynamic urban environments with complex structures and changes that require high spatial detail, frequent coverage, fine spectral resolution, and multi-angle observation. This is largely due to the fact that there is no satellite sensor that can achieve simultaneously high STSA resolution. Unified satellite image fusion aims to circumvent this obstacle by achieving high resolution with respect to all the image properties for a virtual satellite sensor. The generated high STSA resolution imagery can greatly contribute to the exploration and improvement of existing satellite image resources for urban environmental applications by detecting more details in a more accurate manner. This presentation will introduce to you the speaker’s endeavors along this line of research, including both the methodologies and applications in environmental and land use monitoring.
Kyrgyz State Technical University
Time : 11:25-12:05
Ryspek Usubamatov has graduated as professional engineer, completed Ph.D from Bauman Moscow State Technical University and Doctor of Technical Sciences from Academy of Sciences of Kyrgyzstan. He worked as an engineer-designer of machine tools at engineering company. He is a professor of Kyrgyz State Technical University and worked at universities in Malaysia. He has published more than 300 papers in reputed journals, more than 60 patents of inventions in engineering and seven books in area of manufacturing engineering. He supervised six Ph.D and several dozens of MSc. students. His research interests in area of Gyroscope theory and Productivity theory for Industrial Engineering.
Gyroscope devices are primary units for navigation and control systems in aviation, space, ships, and other industries. The main property of the gyroscope device is maintaining the axis of a spinning rotor for which mathematical models have been formulated on the law of kinetic energy conservation and the changes in the angular momentum. However, known mathematical models for the gyroscope effects do not match actual forces and motions underway. The nature of the gyroscope properties is more complex than is represented by contemporary theories. Recent investigations have demonstrated that gyroscopes have four inertial forces interdependently and simultaneously acting on them. These forces are internal kinetic energies generated by the mass-elements and centre-mass of the spinning rotor and represented by centrifugal, Coriolis, and common inertial forces as well as changes in angular momentum. The applied torque generates internal resistance torques that based on action of centrifugal and Coriolis forces; and the precession torques generated by common inertial forces and by the change in the angular momentum. Apart these, the friction forces acting on the gyroscope supports play considerable role in decreasing the internal kinetic energy of the spinning rotor. The new mathematical models for gyroscope effects describe clearly and exactly all known and new gyroscope properties. Mathematical models for the most unsolvable motions of the gyroscope with one side support are validated by practical tests. Formulated models for motions of the gyroscope represent fundamental principles of gyroscope theory based on the actions of internal centrifugal, Coriolis and inertial forces and the change in angular momentum, and external applied and friction forces. This new theoretical approach for the gyroscope problems represents new challenge in engineering science.