0 (1).jpg

Dr. Yuanzhu Chen

Professor, Department of Computer Science, Memorial University of Newfoundland, Canada

Speech Title: Interconnectedness -- from classic theory of graphs to emerging science of networks

Speech Abstract: 

What are the commonalities between transfer of data packets on the Internet, ordering web pages by a search engine, formation of communities and opinions in a social network, spread of diseases, chemical reactions of molecules in a cell, flow of cash in a financial market, and collaboration among movie actors? If modeled with networks, what are the physical laws governing the structures and evolution of these networks of varying natures? This talk provides a narrative of the emergence of the science of networks, and how such a transition from reductionism to holism of scientific research through interconnectedness affects everyone of us.


A. Prof Guoqin Kang

College of Information and Communication, National University of Defense Technology, China

Speech Title:  Analysis on the New Progress of Spectrum Planning of IMT-2020(5G)

Speech Abstract:  

In order to allocate reasonable spectrum resources above 6 GHz for 5th-Generation (5G) in China, this paper analyzes the new progress of upcoming World Radio Conference-2019 (WRC-19) agenda 1.13, the 3rd Generation Partnership Project (3GPP) 5G New Radio (NR), and Chinese 5G spectrum planning. It analyses the possibility of Chinese spectrum planning in several candidate frequency bands with Monte-Carlo simulation, including 24.75-27.5 GHz, 31.8-33.4 GHz, 37-43.5 GHz, 64-71 GHz, 71-76 GHz and 81-86 GHz. The compatibility is viable between mobile service (MS) and earth exploration satellite service (EESS), radio astronomy service (RAS), inter-satellite service (ISS) in 24.75-27.5 GHz. It’s likely to allocate 24.75-27.5 GHz to 5G in China. There is coexisting difficulty and adverse propagation condition in 31.8-33.4 GHz. It is almost impossible to allocate 31.8-33.4 GHz to 5G in China. It is compatible between MS and fixed-satellite service (FSS), EESS (passive) with additional isolation and out-of- band emission limitation in 37-43.5 GHz. It is possible to allocate 37-43.5 GHz to 5G in China.


Dr. Alex Noel Joseph Raj 

Shantou University, China 

Speech Title: An Hybrid UNet Model for Medical Image Segmentation



Introduction about Computer Vision


   Types of Segmentation – Semantic Segmentation and Instance Segmentation


CNN based Segmentation

   Convolution, Pooling Operation

   Problems with CNN and the Need for Up sampling

UNET Architecture

   Segmentation Examples with Ultrasound Images

Hybrid Model – RDA-UNET Model

   What’s new?


Segmentation results with RDA-UNET Model


Dr. Ala Alarood

Assistant Professor, University of Jeddah, Kingdom of Saudi Arabia

Speech Title: Improved Steganalysis Technique using Artificial Neural Network for MP3 Files

Speech Abstract:  

MP3 files are one of the most widely used digital audio formats that provide a high compression ratio with reliable quality. Their widespread use has resulted in MP3 audio files becoming excellent covers to carry hidden information in audio steganography on the Internet. Emerging interest in uncovering such hidden information has opened up a field of research called steganalysis that looked at the detection of hidden messages in a specific media.  Unfortunately, the detection accuracy in steganalysis is affected by bit rates, sampling rate of the data type, compression rates, file track size and standard, as well as benchmark dataset of the MP3 files. This research thus proposed an effective technique to steganalysis of MP3 audio files by deriving a combination of features from MP3 file properties. Several trials were run in selecting relevant features of MP3 files like the total harmony distortion, power spectrum density, and peak signal-to-noise ratio (PSNR) for investigating the correlation between different channels of MP3 signals. The least significant bit (LSB) technique was used in the detection of embedded secret files in stego-objects. This involved reading the stego-objects for statistical evaluation for possible points of secret messages and classifying these points into either high or low tendencies for containing secret messages. Feed Forward Neural Network with 3 layers and traingdx function with an activation function for each layer were also used. The network vector contains information about all features, and is used to create a network for the given learning process. Finally, an evaluation process involving the ANN test that compared the results with previous techniques, was performed. A 97.92% accuracy rate was recorded when detecting MP3 files under 96 kbps compression. These experimental results showed that the proposed approach was effective in detecting embedded information in MP3 files. It demonstrated significant improvement in detection accuracy at low embedding rates compared with previous work.