时间：2019-08-12 08:00 至 2019-08-14 18:00
会议时间：2019-08-12 08:00至 2019-08-14 18:00结束
会议地点： 南京 详细地址会前通知
Dr. Mohd Afizi Mohd Shukran, Associate Professor
Faculty of Science and Defence Technolog, Department of Computer Science, Universiti Pertahanan Nasional Malaysia, Malaysia
Biography: Dr. Mohd Afizi Mohd Shukran, currently an Associate Professor in Department of Computer Science in Universiti Pertahanan Nasional Malaysia (UPNM). He has several research experiences including 60 published journals and over 40 proceedings. Also, he has several computer science professional certifications such as MCSE, MCSA and ENSA. About education backgrounds, he obtained the bachelor degree in Information System from Melbourne University, Australia. Then he got his Master of Information Technology and Doctor of Philosophy (PhD) in Sydney University, Australia.
Topic: Information Retrieval in Internet of Things (IoT)
Abstract: Information retrieval (IR) involves solving problems by analysing data already present in databases. Due to the explosive growth of both business and scientific databases, extracting efficient classification rules from such databases has become an important task. This is because IR technique is an important form of knowledge extraction and can help to make key decisions. Nevertheless, classification technique can be improved by integrating the latest technology, namely, Swarm Intelligence. This study proposes two types of IR techniques: Artificial Bee Colony, and Intelligent Dynamic Swarm, which are both based on Swarm Intelligence. This is because Swarm Intelligence has the capability to adapt well in changing environments and is immensely flexible and robust. The first swarm based classifier involves using the advantages of Artificial Bee Colony as an optimization tool to do the data classification. This proposed Artificial Bee Colony based classifier has been implemented to the Anomaly based Network Intrusion Detection System. To our knowledge, it is the first time that the Artificial Bee Colony technique has been applied to solve the network intrusion detection problem. Another swarm based IR that has been proposed in this study is a novel Intelligent Dynamic Swarm, which is based on Particle Swarm Optimization. Unlike a conventional Particle Swarm Optimization algorithm, this novel algorithm can directly cope with discrete variables. In addition, Intelligent Dynamic Swarm can successfully avoid premature convergence, which is considered a serious drawback of traditional Particle Swarm Optimization. These two proposed new swarm based data classification algorithms have been evaluated using the UCI data set, KDD-99 datasets developed by MIT Lincoln Labs, and the pre-processed image data. The experimental results showed that both the Intelligent Dynamic Swarm are robust and able to achieve high IR accuracy in a changing environment within the data instances. Therefore, proposed IR can provide a promising direction for solving complex problems that may not be solved by traditional approaches.
Dr. Yun Tian, Assistant Professor
Department of Computer Science, Eastern Washington University, USA
Biography: Dr. Yun Tian currently works for the Department of Computer Science at Eastern Washington University as an Assistant Professor. Dr. Tian’s research interests include Grid and Cloud computing, parallel computing, GPGPU computing and Big Data. He published more than ten papers in the last five years in the fields of cloud computing, parallel and distributed computing on prestigious venues, such as IEEE Big Data Congress, Journal of Parallel and Distributed Computing, Journal of Microprocessors and Microsystems and so on. Dr. Tian is a reviewer for numerous famed journals or conferences.
Topic: Interactively and Remotely Visualize Large 3-D Terrain Data Stored in the Cloud
Abstract: In this work, we design and implement a visualization system which enables scientists in an internet browser to interactively and remotely visualize 3-Dimensional terrain features at any location of interest on a multi-resolution 3-Dimensional map. The proposed system primarily consists of two components, including a client rendering engine and a group of high-performance servers that prefetch the interested tile of the 3D terrain data, decodes the data title, then forwards the data title to a requesting client. Runs on a AWS EC2 virtual machine, each high-performance server, corresponding to one of the sixteen zoom levels of the 3D terrain data, is able to accommodate hundreds of client requests in parallel. The proposed system is designed to improve the research environments and methodologies in geology and environmental sciences. For example, a geologist might explore the surrounding terrain of a hydroelectric dam when making an evacuation plan for an earthquake.