Multi-sensor array, usually referred to as Sensor/Data Fusion,is one of the ab-sorbing topics in Artificial Intelligence and Machine Learning studies. The ad-vantages of multiple-sensor data fusion in terms of cost, accuracy, and reliabil-ity will be explained in this workshop. Generally, “Data Fusion” deals with the synergistic combination of data provided by various knowledge sources or sensors to provide a clear perception of a given scene or environment. The use of sensor/data fusion concept has advantages such as “Redundancy”, “Complementary”, “Timeliness” and “Less Costly Information.” Fusion characterization addressing the application domain, fusion objective, fusion process input-output (I/O) characteristics, and sensor suite configuration will be shown. In this workshop the different models and levels of Data Fusion will be presented. Different data fusion meth-ods, including the conventional and intelligent approaches with their appli-cation in Sensor/Data Fusion, Industrial Automation, Information Technology, Bioinformatics, Transportation Systems (ITS), and Financial Engineering will be presented. Typical examples using data fusion toolboxes will be shown. The contents of this workshop are given below:Data Fusion Principles & Practice:Background (Decision Supporting Systems)Sensor/Data fusion overviewDefinition & FormulationFusion: A Fission inversion modelFusion characterization: Application domain, Fusion objective, Fusion process input/output characteristics, Sensor suite configuratio Different Level Fusion ArchitecturesDifferent Fusion Model ArchitecturesDecision Fusion in a Parallel Sensor suiteDetection (Binary) Decision AnalysisMultihypothesis Decision AnalysisComparison of Mathematical Tools in Data FusionDifferent Techniques of Sensor fusion: Conventional Approaches Knowledge-based Systems/Intelligent ApproachesConventional Approaches: OWA (Ordered Weighted Averaging Method) Kalman Filter Bayesian Method Dempster Shafer Method Knowledge-based Systems / Intelligent Approaches: Fuzzy Logic (Integral Operators) Neural Network Typical examples using available toolboxes.
Prof. of Control Systems Engineering, School of ECE, University of Tehran
Behzad received his B.Sc. degree in mechanical engineering from Iran University of Science and Technology (IUST) in 1984 and M.Sc and Ph.D. degrees in control systems engineering from the University of Manchester, Institute of Science and Technology (UMIST), U.K. in 1987 and 1991 respectively. He joined the school of electrical and computer engineering, university of Tehran in 1992 where he is currently professor of control systems engineering. He has been the member of International Society of Information Fusion (ISIF) since 2002 and senior member of IEEE since 2006. He is now serving as the chair of IEEE control system chapter in Iran section since March 2019. He is the author/co-author of more than 360+ articles including 120+ journal papers and 20+ book chapters. His fields of research include advanced industrial control, advanced instrumentation systems and applications of data/information fusion in areas such as robotics, process control, mechatronics, information technology (IT), bioinformatics, intelligent transportation systems (ITS) and financial engineering.