|
Centre Name: |
Centre For Communication Systems And Networks (CCSN) |
|
Chairperson: |
Dr. Chong Poh Kit |
|
Description of Centre:
|
The Centre for Communication Systems and Networks is established to spearhead research and innovation work in broadband network technologies, wireless networking systems, communication theory and applications and Applied Electromagnetics. The objective of the centre is to become a national and regional centre of excellence for telecommunication research. Our mission is to promote and lead research and development, technology transfer and training of R&D manpower in specific areas of telecommunication technologies to enhance competitiveness of local industries in global markets. |
|
Research area:
|
1. Broadband Network Technologies and Management, 2. Wired and Wireless Internetworking Systems, 3. Communication Theory & Applications, 4. Radio Science and Technologies |
Activities in 2014
Summary of activities
|
No. |
Date |
Event |
|
1 |
3 July 2014 |
Seminar on "3D Vision Research in CUHK" by Professor Ngan King Ngi |
|
2 |
7 Nov 2014 |
Seminar on \Advanced Neural Adaptive Processing in Interferometric and Polarimetric Radar Imaging. by Professor Akira Hirose |
Seminar on Advanced Neural Adaptive Processing in Interferometric and Polarimetric Radar Imaging
Prof Akira Hirose from Tokyo University was invited by CCSN and IEEE GRSS to give a talk on his expertise on the following date/time:
Date: 7th November 2014 (Friday)
Time: 2:00PM 4:00PM
Venue: West Room, 6th Floor, Block SA, Lee Kong Chian Faculty of Engineering and Science, Universiti Tunku Abdul Rahman, Setapak, Kuala Lumpur.
Title: Advanced Neural Adaptive Processing in Interferometric and Polarimetric Radar Imaging
Prof. Hirose spoke about advanced neural networks by focusing on complex-valued neural networks (CVNNs) and their applications in the remote sensing and imaging fields. CVNNs are suitable for adaptive processing of complex-amplitude information. Since active remote sensing deals with coherent electromagnetic wave, CVNNs are expected to work more effectively than conventional neural networks or other adaptive methods in real-number space. Quaternion (or Hypercomplex-valued) neural networks are also discussed in relation to polarization information processing. The beginning half of the talk was devoted to presentation of the basic idea, overall framework, and fundamental treatment in the CVNNs. He discussed the processing dynamics of Hebbian rule, back-propagation learning, and self-organizing map in the complex domain.
The latter half highlighted the applications of CVNN processing in the geoscience and remote sensing society (GRSS) fields. Namely, distortion reduction in phase unwrapping to generate digital elevation model (DEM) from the data obtained by interferometric synthetic aperture radar (InSAR). In polarization SAR (PolSAR), the application of quaternion networks for adaptive classification was presented as an example. Another example is ground penetrating radar (GPR) to visualize underground objects to distinguish specific targets in high-clutter situation. Finally, the prospects of CVNNs in the GRSS field was discussed.
About 100 researchers and students from UTAR and around Malaysia attended this interesting talk.