2019-10-22 | Professor Hamido FUJITA:On New directions in Machine Representation Learning for Biometrical Analytics



Discovering patterns from big data attracts a lot of attention due to its importance in discovering accurate patterns and features that are used in predictions for accurate biomedical information for better security.


Biometrics provides a suitable robust authenticated identification based on feature extraction for verifiable data.  Physiological Analytics are either morphological or biological. Finger prints, hand or face shapes, facial analysis, vein pattern, iris and retinal feature in the eyes, walking steps patterns, are all different pattern morphological biometrics for authentication purposes used in pattern recognition, Behavioral analytics is also another type of biometrics based authentication, like voice recognition, signature dynamics, keystrokes, gait, sound of steps and gestures, etc., and all these are used to measure individual behaviors and rhythm, for example stress or other type of behavior related to aggressive act in bank or in crowd. All these different types of biometrics have different reliability for variety of purpose. This talk provides new direction on the state of art on Physiological Analytics (PA) due to its stability in providing better authentication, not affected by stress like in the behavioral ones.


PA provides techniques to extract patterns (features) from face- based data; or fingerprint data based analytics to extract features related to features in the face or palm veins or geometry in the hands, or iris recognition, and retina.  In this talk I will focus on face recognition and fingerprints analytics, and its current state of art. The challenges in big data analytics for facial analytics and fingerprints-based data are of high dimensionality and complexity in data representation for feature extraction. Also it has class imbalance in multiclass classification problem. Conventional approaches in machine learning are not providing accurate authentication process in robust feature extraction for object like beard or hear color change.


In this talk I will present the current state of art and focus it on face recognition main problems in deep learning and multiclass classification in feature selection.



14:00-15:00,22 October, 2019 (Tuesday)



Professor Hamido FUJITA, a professor at Iwate Prefectural University (IPU), Iwate, Japan, as a director of Intelligent Software Systems. He is the Editor-in-Chief of Knowledge-Based Systems, Elsevier of impact factor (5.101) for 2018.  He received Doctor Honoris Causa from O’buda University in 2013 and also from Timisoara Technical University, (Romania) in 2018, and a title of Honorary Professor from O’buda University, Budapest, Hungary in 2011. He received honorary scholar award from University of Technology Sydney, Australia on 2012. He is Adjunct professor to Stockholm University, Sweden, University of Technology Sydney, National Taiwan Ocean University and others. He has supervised PhD students jointly with University of Laval, Quebec, Canada; University of Technology, Sydney, Australia; Oregon State University (Corvallis), University of Paris 1 Pantheon-Sorbonne, France and University of Genoa, Italy. He has four international Patents in Software System and Several research projects with Japanese industry and partners. He is vice president of International Society of Applied Intelligence, and Co-Editor in Chief of Applied Intelligence Journal, (Springer).  He has given many keynotes in many prestigious international conferences on intelligent system and subjective intelligence.  He headed a number of projects including Intelligent HCI, a project related to Mental Cloning as an intelligent user interface between human user and computers and SCOPE project on Virtual Doctor Systems for medical applications.