Sigeru Omatu is Professor of at the Department of Electronics, Information and Communication, Faculty of Engineering, Osaka Institute of Technology, Osaka, Japan. He received his Ph.D. in Electronic Engineering from Osaka Prefecture University and joined the faculty at University of Tokushima in 1969. He was Professor of University of Tokushima in 1988 and Professor of Osaka Prefecture University in 1995. He has been Professor of Osaka Institute of Technology since 2010.
His honors and awards include the Best Paper Awards for Optimal Sensor Location for Distributed Parameter Systems, IEE of Japan, 1991, for Intelligent Classification, JSME, 1995, for Coin and Bill Classification, SICE, Japan, 1995, IEEJ Outstanding Achievement Award, 2005 for Intelligent Systems Approach, for Intelligent Smell Classification, IARIA, 2008, for Neuro-Control, IARIA, 2009. Furthermore, he received Ichimura Distinguished Award for Intelligent Classification of Bill Money, New Technology Development Foundation, 1996, and in 2011, Commendation for Science and Technology by the Minister of Education, Culture, Sports, Science and Technology, Research Category, Study on Intelligent Recognition and Control by Neural Networks and Progress Award on Odor Sensing and Classification, IEE of Japan. He becomesSICE Fellow, IEE of Japan Fellow and IARIA Fellow.
He used to be the President of ISCIA (Institute of Systems, Control and Information Association, Japan) in 2007 and President of Electronics, Information and Systems Society, IEEJ, 2004-2006, Regional Editor of EAAI (IFAC Journal) for 1998-2001, Associate Editor of IEEE Transactions on Neural Networks for 1993-2003, and IMA Journal of Mathematical Control and Information (Oxford University Press) since 1991.
His research area covers intelligent signal processing, pattern recognition, intelligent control, and adaptive control.

Odor Sensing and Classification by Intelligent Neural Networks.

ABSTRACT- Conventional odor classification methods have been considered under steady state conditions of temperature, humidity, density, etc. In real applications, those conditions may not occur and they will be variable from time to time. Therefore, it is necessary to find some features which are independent on various environmental conditions. In this paper, using a derivative of odor density and odor sensing data in log scale, we will find a feature of the odor which is independent on the density. Using this feature, we construct an electronic nose which is independent on odor density based on a neural network. The neural network used here is a competitive neural network by the learning vector quantization (LVQ). Various odors are measured with an array of many metal oxide gas sensors. After removing noises from the odor data which are measured under the various concentrations, we take the maximum values among the time series data of odors. to reduce the effect of concentration, we use a normalization method to reduce the fluctuation of the data due to the concentration levels. Those data are used to classify the various odors of tees and coffees. The classification results show the effectiveness of the proposed method.